[sword-svn] r428 - in trunk: . clucene clucene/src clucene/src/CLucene clucene/src/CLucene/analysis clucene/src/CLucene/analysis/standard clucene/src/CLucene/config clucene/src/CLucene/debug clucene/src/CLucene/document clucene/src/CLucene/index clucene/src/CLucene/queryParser clucene/src/CLucene/search clucene/src/CLucene/store clucene/src/CLucene/util stage
scribe at crosswire.org
scribe at crosswire.org
Sun Jun 25 17:40:05 MST 2006
Author: scribe
Date: 2006-06-25 17:39:24 -0700 (Sun, 25 Jun 2006)
New Revision: 428
Modified:
trunk/clucene/clucene.bpr
trunk/clucene/src/CLucene.h
trunk/clucene/src/CLucene/CLBackwards.h
trunk/clucene/src/CLucene/CLConfig.h
trunk/clucene/src/CLucene/CLMonolithic.cpp
trunk/clucene/src/CLucene/LuceneThreads.h
trunk/clucene/src/CLucene/StdHeader.cpp
trunk/clucene/src/CLucene/StdHeader.h
trunk/clucene/src/CLucene/analysis/AnalysisHeader.cpp
trunk/clucene/src/CLucene/analysis/AnalysisHeader.h
trunk/clucene/src/CLucene/analysis/Analyzers.cpp
trunk/clucene/src/CLucene/analysis/Analyzers.h
trunk/clucene/src/CLucene/analysis/standard/StandardAnalyzer.cpp
trunk/clucene/src/CLucene/analysis/standard/StandardAnalyzer.h
trunk/clucene/src/CLucene/analysis/standard/StandardFilter.cpp
trunk/clucene/src/CLucene/analysis/standard/StandardFilter.h
trunk/clucene/src/CLucene/analysis/standard/StandardTokenizer.cpp
trunk/clucene/src/CLucene/analysis/standard/StandardTokenizer.h
trunk/clucene/src/CLucene/analysis/standard/StandardTokenizerConstants.h
trunk/clucene/src/CLucene/config/CompilerBcb.h
trunk/clucene/src/CLucene/config/CompilerGcc.h
trunk/clucene/src/CLucene/config/CompilerMsvc.h
trunk/clucene/src/CLucene/config/PlatformMac.h
trunk/clucene/src/CLucene/config/PlatformUnix.h
trunk/clucene/src/CLucene/config/PlatformWin32.h
trunk/clucene/src/CLucene/config/compiler.h
trunk/clucene/src/CLucene/config/define_std.h
trunk/clucene/src/CLucene/config/gunichartables.cpp
trunk/clucene/src/CLucene/config/repl_lltot.cpp
trunk/clucene/src/CLucene/config/repl_tchar.h
trunk/clucene/src/CLucene/config/repl_tcscasecmp.cpp
trunk/clucene/src/CLucene/config/repl_tcslwr.cpp
trunk/clucene/src/CLucene/config/repl_tcstod.cpp
trunk/clucene/src/CLucene/config/repl_tcstoll.cpp
trunk/clucene/src/CLucene/config/repl_tprintf.cpp
trunk/clucene/src/CLucene/config/repl_wchar.h
trunk/clucene/src/CLucene/config/utf8.cpp
trunk/clucene/src/CLucene/debug/condition.cpp
trunk/clucene/src/CLucene/debug/condition.h
trunk/clucene/src/CLucene/debug/error.cpp
trunk/clucene/src/CLucene/debug/error.h
trunk/clucene/src/CLucene/debug/lucenebase.h
trunk/clucene/src/CLucene/debug/mem.h
trunk/clucene/src/CLucene/debug/mempool.cpp
trunk/clucene/src/CLucene/debug/memtracking.cpp
trunk/clucene/src/CLucene/debug/pool.h
trunk/clucene/src/CLucene/document/DateField.cpp
trunk/clucene/src/CLucene/document/DateField.h
trunk/clucene/src/CLucene/document/Document.cpp
trunk/clucene/src/CLucene/document/Document.h
trunk/clucene/src/CLucene/document/Field.cpp
trunk/clucene/src/CLucene/document/Field.h
trunk/clucene/src/CLucene/index/CompoundFile.cpp
trunk/clucene/src/CLucene/index/CompoundFile.h
trunk/clucene/src/CLucene/index/DocumentWriter.cpp
trunk/clucene/src/CLucene/index/DocumentWriter.h
trunk/clucene/src/CLucene/index/FieldInfo.h
trunk/clucene/src/CLucene/index/FieldInfos.cpp
trunk/clucene/src/CLucene/index/FieldInfos.h
trunk/clucene/src/CLucene/index/FieldsReader.cpp
trunk/clucene/src/CLucene/index/FieldsReader.h
trunk/clucene/src/CLucene/index/FieldsWriter.cpp
trunk/clucene/src/CLucene/index/FieldsWriter.h
trunk/clucene/src/CLucene/index/IndexModifier.cpp
trunk/clucene/src/CLucene/index/IndexModifier.h
trunk/clucene/src/CLucene/index/IndexReader.cpp
trunk/clucene/src/CLucene/index/IndexReader.h
trunk/clucene/src/CLucene/index/IndexWriter.cpp
trunk/clucene/src/CLucene/index/IndexWriter.h
trunk/clucene/src/CLucene/index/MultiReader.cpp
trunk/clucene/src/CLucene/index/MultiReader.h
trunk/clucene/src/CLucene/index/SegmentHeader.h
trunk/clucene/src/CLucene/index/SegmentInfos.cpp
trunk/clucene/src/CLucene/index/SegmentInfos.h
trunk/clucene/src/CLucene/index/SegmentMergeInfo.cpp
trunk/clucene/src/CLucene/index/SegmentMergeInfo.h
trunk/clucene/src/CLucene/index/SegmentMergeQueue.cpp
trunk/clucene/src/CLucene/index/SegmentMergeQueue.h
trunk/clucene/src/CLucene/index/SegmentMerger.cpp
trunk/clucene/src/CLucene/index/SegmentMerger.h
trunk/clucene/src/CLucene/index/SegmentReader.cpp
trunk/clucene/src/CLucene/index/SegmentTermDocs.cpp
trunk/clucene/src/CLucene/index/SegmentTermEnum.cpp
trunk/clucene/src/CLucene/index/SegmentTermEnum.h
trunk/clucene/src/CLucene/index/SegmentTermPositions.cpp
trunk/clucene/src/CLucene/index/SegmentTermVector.cpp
trunk/clucene/src/CLucene/index/Term.cpp
trunk/clucene/src/CLucene/index/Term.h
trunk/clucene/src/CLucene/index/TermInfo.cpp
trunk/clucene/src/CLucene/index/TermInfo.h
trunk/clucene/src/CLucene/index/TermInfosReader.cpp
trunk/clucene/src/CLucene/index/TermInfosReader.h
trunk/clucene/src/CLucene/index/TermInfosWriter.cpp
trunk/clucene/src/CLucene/index/TermInfosWriter.h
trunk/clucene/src/CLucene/index/TermVector.h
trunk/clucene/src/CLucene/index/TermVectorReader.cpp
trunk/clucene/src/CLucene/index/TermVectorWriter.cpp
trunk/clucene/src/CLucene/index/Terms.h
trunk/clucene/src/CLucene/queryParser/Lexer.cpp
trunk/clucene/src/CLucene/queryParser/Lexer.h
trunk/clucene/src/CLucene/queryParser/MultiFieldQueryParser.cpp
trunk/clucene/src/CLucene/queryParser/MultiFieldQueryParser.h
trunk/clucene/src/CLucene/queryParser/QueryParser.cpp
trunk/clucene/src/CLucene/queryParser/QueryParser.h
trunk/clucene/src/CLucene/queryParser/QueryParserBase.cpp
trunk/clucene/src/CLucene/queryParser/QueryParserBase.h
trunk/clucene/src/CLucene/queryParser/QueryParserConstants.h
trunk/clucene/src/CLucene/queryParser/QueryToken.cpp
trunk/clucene/src/CLucene/queryParser/QueryToken.h
trunk/clucene/src/CLucene/queryParser/TokenList.cpp
trunk/clucene/src/CLucene/queryParser/TokenList.h
trunk/clucene/src/CLucene/search/BooleanClause.h
trunk/clucene/src/CLucene/search/BooleanQuery.cpp
trunk/clucene/src/CLucene/search/BooleanQuery.h
trunk/clucene/src/CLucene/search/BooleanScorer.cpp
trunk/clucene/src/CLucene/search/BooleanScorer.h
trunk/clucene/src/CLucene/search/CachingWrapperFilter.cpp
trunk/clucene/src/CLucene/search/CachingWrapperFilter.h
trunk/clucene/src/CLucene/search/ChainedFilter.cpp
trunk/clucene/src/CLucene/search/ChainedFilter.h
trunk/clucene/src/CLucene/search/Compare.h
trunk/clucene/src/CLucene/search/ConjunctionScorer.cpp
trunk/clucene/src/CLucene/search/ConjunctionScorer.h
trunk/clucene/src/CLucene/search/DateFilter.cpp
trunk/clucene/src/CLucene/search/DateFilter.h
trunk/clucene/src/CLucene/search/ExactPhraseScorer.cpp
trunk/clucene/src/CLucene/search/ExactPhraseScorer.h
trunk/clucene/src/CLucene/search/Explanation.cpp
trunk/clucene/src/CLucene/search/Explanation.h
trunk/clucene/src/CLucene/search/FieldCache.cpp
trunk/clucene/src/CLucene/search/FieldCache.h
trunk/clucene/src/CLucene/search/FieldCacheImpl.cpp
trunk/clucene/src/CLucene/search/FieldCacheImpl.h
trunk/clucene/src/CLucene/search/FieldDoc.h
trunk/clucene/src/CLucene/search/FieldDocSortedHitQueue.cpp
trunk/clucene/src/CLucene/search/FieldDocSortedHitQueue.h
trunk/clucene/src/CLucene/search/FieldSortedHitQueue.cpp
trunk/clucene/src/CLucene/search/FieldSortedHitQueue.h
trunk/clucene/src/CLucene/search/Filter.h
trunk/clucene/src/CLucene/search/FilteredTermEnum.cpp
trunk/clucene/src/CLucene/search/FilteredTermEnum.h
trunk/clucene/src/CLucene/search/FuzzyQuery.cpp
trunk/clucene/src/CLucene/search/FuzzyQuery.h
trunk/clucene/src/CLucene/search/HitQueue.cpp
trunk/clucene/src/CLucene/search/HitQueue.h
trunk/clucene/src/CLucene/search/Hits.cpp
trunk/clucene/src/CLucene/search/IndexSearcher.cpp
trunk/clucene/src/CLucene/search/IndexSearcher.h
trunk/clucene/src/CLucene/search/MultiSearcher.cpp
trunk/clucene/src/CLucene/search/MultiSearcher.h
trunk/clucene/src/CLucene/search/MultiTermQuery.cpp
trunk/clucene/src/CLucene/search/MultiTermQuery.h
trunk/clucene/src/CLucene/search/PhrasePositions.cpp
trunk/clucene/src/CLucene/search/PhrasePositions.h
trunk/clucene/src/CLucene/search/PhraseQuery.cpp
trunk/clucene/src/CLucene/search/PhraseQuery.h
trunk/clucene/src/CLucene/search/PhraseQueue.h
trunk/clucene/src/CLucene/search/PhraseScorer.cpp
trunk/clucene/src/CLucene/search/PhraseScorer.h
trunk/clucene/src/CLucene/search/PrefixQuery.cpp
trunk/clucene/src/CLucene/search/PrefixQuery.h
trunk/clucene/src/CLucene/search/QueryFilter.cpp
trunk/clucene/src/CLucene/search/QueryFilter.h
trunk/clucene/src/CLucene/search/RangeFilter.cpp
trunk/clucene/src/CLucene/search/RangeFilter.h
trunk/clucene/src/CLucene/search/RangeQuery.cpp
trunk/clucene/src/CLucene/search/RangeQuery.h
trunk/clucene/src/CLucene/search/ScoreDoc.h
trunk/clucene/src/CLucene/search/Scorer.h
trunk/clucene/src/CLucene/search/SearchHeader.cpp
trunk/clucene/src/CLucene/search/SearchHeader.h
trunk/clucene/src/CLucene/search/Similarity.cpp
trunk/clucene/src/CLucene/search/Similarity.h
trunk/clucene/src/CLucene/search/SloppyPhraseScorer.cpp
trunk/clucene/src/CLucene/search/SloppyPhraseScorer.h
trunk/clucene/src/CLucene/search/Sort.cpp
trunk/clucene/src/CLucene/search/Sort.h
trunk/clucene/src/CLucene/search/TermQuery.cpp
trunk/clucene/src/CLucene/search/TermQuery.h
trunk/clucene/src/CLucene/search/TermScorer.cpp
trunk/clucene/src/CLucene/search/TermScorer.h
trunk/clucene/src/CLucene/search/WildcardQuery.cpp
trunk/clucene/src/CLucene/search/WildcardQuery.h
trunk/clucene/src/CLucene/search/WildcardTermEnum.cpp
trunk/clucene/src/CLucene/search/WildcardTermEnum.h
trunk/clucene/src/CLucene/store/Directory.h
trunk/clucene/src/CLucene/store/FSDirectory.cpp
trunk/clucene/src/CLucene/store/FSDirectory.h
trunk/clucene/src/CLucene/store/IndexInput.cpp
trunk/clucene/src/CLucene/store/IndexInput.h
trunk/clucene/src/CLucene/store/IndexOutput.cpp
trunk/clucene/src/CLucene/store/IndexOutput.h
trunk/clucene/src/CLucene/store/InputStream.h
trunk/clucene/src/CLucene/store/Lock.cpp
trunk/clucene/src/CLucene/store/Lock.h
trunk/clucene/src/CLucene/store/MMapInput.cpp
trunk/clucene/src/CLucene/store/OutputStream.h
trunk/clucene/src/CLucene/store/RAMDirectory.cpp
trunk/clucene/src/CLucene/store/RAMDirectory.h
trunk/clucene/src/CLucene/store/TransactionalRAMDirectory.cpp
trunk/clucene/src/CLucene/store/TransactionalRAMDirectory.h
trunk/clucene/src/CLucene/util/Arrays.h
trunk/clucene/src/CLucene/util/BitSet.h
trunk/clucene/src/CLucene/util/Equators.cpp
trunk/clucene/src/CLucene/util/Equators.h
trunk/clucene/src/CLucene/util/FastCharStream.cpp
trunk/clucene/src/CLucene/util/FastCharStream.h
trunk/clucene/src/CLucene/util/MD5Digester.cpp
trunk/clucene/src/CLucene/util/MD5Digester.h
trunk/clucene/src/CLucene/util/Misc.cpp
trunk/clucene/src/CLucene/util/Misc.h
trunk/clucene/src/CLucene/util/PriorityQueue.h
trunk/clucene/src/CLucene/util/Reader.cpp
trunk/clucene/src/CLucene/util/Reader.h
trunk/clucene/src/CLucene/util/StringBuffer.cpp
trunk/clucene/src/CLucene/util/StringBuffer.h
trunk/clucene/src/CLucene/util/StringIntern.cpp
trunk/clucene/src/CLucene/util/StringIntern.h
trunk/clucene/src/CLucene/util/VoidList.h
trunk/clucene/src/CLucene/util/VoidMap.h
trunk/clucene/src/CLucene/util/dirent.cpp
trunk/clucene/src/CLucene/util/dirent.h
trunk/clucene/src/CLucene/util/jstreamsconfig.h
trunk/clucene/src/CLucene/util/streambase.h
trunk/clucene/src/CLucene/util/stringreader.h
trunk/stage/layout.conf
trunk/sword.bpr
trunk/sword.res
Log:
updated to current svn of clucene, as of this log date
Modified: trunk/clucene/clucene.bpr
===================================================================
--- trunk/clucene/clucene.bpr 2006-06-11 07:16:00 UTC (rev 427)
+++ trunk/clucene/clucene.bpr 2006-06-26 00:39:24 UTC (rev 428)
@@ -18,7 +18,7 @@
<PATHRC value=".;"/>
<PATHASM value=".;"/>
<LINKER value="TLib"/>
- <USERDEFINES value="UNICODE;_WIN32;_CL_DISABLE_MULTITHREADING"/>
+ <USERDEFINES value="MAX_PATH=256;UNICODE;_WIN32;_CL_DISABLE_MULTITHREADING;_DEBUG"/>
<SYSDEFINES value="_RTLDLL;NO_STRICT"/>
<MAINSOURCE value="clucene.bpf"/>
<INCLUDEPATH value="src\CLucene;src;$(BCB)\include;$(BCB)\include\vcl"/>
@@ -29,9 +29,9 @@
<OPTIONS>
<IDLCFLAGS value="-Isrc\CLucene -Isrc -I$(BCB)\include -I$(BCB)\include\vcl -src_suffix cpp
-DUNICODE -D_WIN32 -D_CL_DISABLE_MULTITHREADING -boa"/>
- <CFLAG1 value="-O2 -Q -w- -Vx -VF -X- -a8 -b- -k- -vi -c -tW -tWM"/>
- <PFLAGS value="-$Y- -$L- -$D- -v -JPHNE -M"/>
- <AFLAGS value="/mx /w2 /zn"/>
+ <CFLAG1 value="-vGc -vGt -vGd -Od -Q -w- -Vx -VF -X- -r- -a8 -b- -k -y -v -vi- -c -tW -tWM"/>
+ <PFLAGS value="-$Y+ -$W -$O- -v -JPHNE -M"/>
+ <AFLAGS value="/mx /w2 /zi"/>
<LFLAGS value="/P256"/>
</OPTIONS>
<LINKER>
@@ -94,20 +94,22 @@
Item0=$(BCB)\source\vcl
[HistoryLists\hlConditionals]
-Count=13
-Item0=UNICODE;_WIN32;_CL_DISABLE_MULTITHREADING
-Item1=_WIN32;_CL_DISABLE_MULTITHREADING
-Item2=_WIN32;HAVE_DIRENT;_CL_DISABLE_MULTITHREADING
-Item3=LUCENE_DISABLE_MULTITHREADING;_WIN32;HAVE_DIRENT
-Item4=LUCENE_DISABLE_MULTITHREADING;_WIN32;HAVE_DIRENT;_DEBUG
-Item5=_DEBUG;LUCENE_DISABLE_MULTITHREADING;_WIN32;HAVE_DIRENT
-Item6=_DEBUG;LUCENE_DISABLE_MULTITHREADING;_WIN32
-Item7=_DEBUG;LUCENE_DISABLE_MULTITHREADING;HAVE_DIRENT;_WIN32
-Item8=_DEBUG;LUCENE_DISABLE_MULTITHREADING;HAVE_DIRENT_H;_WIN32
-Item9=_DEBUG;LUCENE_DISABLE_MULTITHREADING;HAVE_DIRENT_H;_WIN32;UTF8
-Item10=_DEBUG;LUCENE_DISABLE_MULTITHREADING;HAVE_DIRENT_H
-Item11=_DEBUG;LUCENE_DISABLE_MULTITHREADING
-Item12=_DEBUG
+Count=15
+Item0=MAX_PATH=256;UNICODE;_WIN32;_CL_DISABLE_MULTITHREADING;_DEBUG
+Item1=MAX_PATH=256;UNICODE;_WIN32;_CL_DISABLE_MULTITHREADING
+Item2=UNICODE;_WIN32;_CL_DISABLE_MULTITHREADING
+Item3=_WIN32;_CL_DISABLE_MULTITHREADING
+Item4=_WIN32;HAVE_DIRENT;_CL_DISABLE_MULTITHREADING
+Item5=LUCENE_DISABLE_MULTITHREADING;_WIN32;HAVE_DIRENT
+Item6=LUCENE_DISABLE_MULTITHREADING;_WIN32;HAVE_DIRENT;_DEBUG
+Item7=_DEBUG;LUCENE_DISABLE_MULTITHREADING;_WIN32;HAVE_DIRENT
+Item8=_DEBUG;LUCENE_DISABLE_MULTITHREADING;_WIN32
+Item9=_DEBUG;LUCENE_DISABLE_MULTITHREADING;HAVE_DIRENT;_WIN32
+Item10=_DEBUG;LUCENE_DISABLE_MULTITHREADING;HAVE_DIRENT_H;_WIN32
+Item11=_DEBUG;LUCENE_DISABLE_MULTITHREADING;HAVE_DIRENT_H;_WIN32;UTF8
+Item12=_DEBUG;LUCENE_DISABLE_MULTITHREADING;HAVE_DIRENT_H
+Item13=_DEBUG;LUCENE_DISABLE_MULTITHREADING
+Item14=_DEBUG
[HistoryLists\hlTlibPageSize]
Count=8
@@ -133,13 +135,8 @@
[Compiler]
ShowInfoMsgs=1
LinkDebugVcl=0
-LinkCGLIB=0
+LinkCGLIB=1
-[CORBA]
-AddServerUnit=1
-AddClientUnit=1
-PrecompiledHeaders=1
-
[Language]
ActiveLang=
ProjectLang=
Modified: trunk/clucene/src/CLucene/CLBackwards.h
===================================================================
--- trunk/clucene/src/CLucene/CLBackwards.h 2006-06-11 07:16:00 UTC (rev 427)
+++ trunk/clucene/src/CLucene/CLBackwards.h 2006-06-26 00:39:24 UTC (rev 428)
@@ -1,18 +1,9 @@
-/**
- * Copyright 2003-2006 The Apache Software Foundation
- *
- * Licensed under the Apache License, Version 2.0 (the "License");
- * you may not use this file except in compliance with the License.
- * You may obtain a copy of the License at
- *
- * http://www.apache.org/licenses/LICENSE-2.0
- *
- * Unless required by applicable law or agreed to in writing, software
- * distributed under the License is distributed on an "AS IS" BASIS,
- * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
- * See the License for the specific language governing permissions and
- * limitations under the License.
- */
+/*------------------------------------------------------------------------------
+* Copyright (C) 2003-2006 Ben van Klinken and the CLucene Team
+*
+* Distributable under the terms of either the Apache License (Version 2.0) or
+* the GNU Lesser General Public License, as specified in the COPYING file.
+------------------------------------------------------------------------------*/
#ifndef _clucene_backwards_h
#define _clucene_backwards_h
@@ -73,7 +64,7 @@
//file naming stuff - remember we have changed all names to file naming lower case
#define fileRename _rename
-#define fileFullName _fullpath
+#define fileFullName(abs,rel) _realpath(rel,abs)
#define makeDirectory _tmkdir
#define unlinkFile _unlink
Modified: trunk/clucene/src/CLucene/CLConfig.h
===================================================================
--- trunk/clucene/src/CLucene/CLConfig.h 2006-06-11 07:16:00 UTC (rev 427)
+++ trunk/clucene/src/CLucene/CLConfig.h 2006-06-26 00:39:24 UTC (rev 428)
@@ -1,19 +1,9 @@
-/**
- * Copyright 2003-2006 The Apache Software Foundation
- *
- * Licensed under the Apache License, Version 2.0 (the "License");
- * you may not use this file except in compliance with the License.
- * You may obtain a copy of the License at
- *
- * http://www.apache.org/licenses/LICENSE-2.0
- *
- * Unless required by applicable law or agreed to in writing, software
- * distributed under the License is distributed on an "AS IS" BASIS,
- * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
- * See the License for the specific language governing permissions and
- * limitations under the License.
- */
-
+/*------------------------------------------------------------------------------
+* Copyright (C) 2003-2006 Ben van Klinken and the CLucene Team
+*
+* Distributable under the terms of either the Apache License (Version 2.0) or
+* the GNU Lesser General Public License, as specified in the COPYING file.
+------------------------------------------------------------------------------*/
#ifndef _lucene_Config_
#define _lucene_Config_
@@ -53,26 +43,26 @@
//
//if a wide character is being converted to a ascii character and it
//cannot fit, this character is used instead. Required.
-#define LUCENE_OOR_CHAR '?'
+#define LUCENE_OOR_CHAR(c) ((char)(((unsigned short)c)&0xFF))
//
//define if you would like to force clucene to use the internal
//character functions.
//Tests may display unpredictable behaviour if this is not defined.
#define LUCENE_USE_INTERNAL_CHAR_FUNCTIONS
//
-//thread locking implementation: define to use the timer based mutex hack...
-//this is NOT threadsafe, it is just a hack to help solve threading problems
-//and for temporary use by compilers which don't have windows or pthread libraries
-//#define LUCENE_THREAD_HACK
-//
//define this to enable mmap support in the fsdirectory IndexInput
//todo: only available for windows so far...need to add MMapInput.cpp to project
//EXPERIMENTAL
//#define LUCENE_FS_MMAP
//
//LOCK_DIR implementation:
-//define this to set an exact directory for the lock dir (not recommended)
+//define this to set an exact directory for the lock dir
//all other methods of getting the temporary directory will be ignored
+//you could use this to define the lock to a safe directory like /var/lock/clucene.
+//note that all lucene libraries need to use the same directory otherwise you
+//will most likely corrupt your index.
+//If your index is on a network drive, then you will need to set the lock
+//dir to the same directory on each system that access the index.
//#define LUCENE_LOCK_DIR "/tmp"
//
//define this to try and load the lock dir from this specified environment variable
@@ -154,7 +144,7 @@
//todo: currently cant be used with mempool...
#if defined(_DEBUG) && !defined(LUCENE_ENABLE_MEMORY_POOL)
#if !defined(LUCENE_DISABLE_MEMTRACKING) && !defined(LUCENE_ENABLE_MEMLEAKTRACKING)
- //#define LUCENE_ENABLE_MEMLEAKTRACKING
+ #define LUCENE_ENABLE_MEMLEAKTRACKING
#endif
#endif
//
@@ -242,6 +232,7 @@
//
//some defaults, wouldn't usually need to be changed
//Buffer size for input/output streams. Required.
+//todo: change this to BufferedIndexOutput::BUFFER_SIZE
#define LUCENE_STREAM_BUFFER_SIZE 1024
//
// DSR:2004.08.19:
Modified: trunk/clucene/src/CLucene/CLMonolithic.cpp
===================================================================
--- trunk/clucene/src/CLucene/CLMonolithic.cpp 2006-06-11 07:16:00 UTC (rev 427)
+++ trunk/clucene/src/CLucene/CLMonolithic.cpp 2006-06-26 00:39:24 UTC (rev 428)
@@ -1,18 +1,9 @@
-/**
- * Copyright 2003-2006 The Apache Software Foundation
- *
- * Licensed under the Apache License, Version 2.0 (the "License");
- * you may not use this file except in compliance with the License.
- * You may obtain a copy of the License at
- *
- * http://www.apache.org/licenses/LICENSE-2.0
- *
- * Unless required by applicable law or agreed to in writing, software
- * distributed under the License is distributed on an "AS IS" BASIS,
- * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
- * See the License for the specific language governing permissions and
- * limitations under the License.
- */
+/*------------------------------------------------------------------------------
+* Copyright (C) 2003-2006 Ben van Klinken and the CLucene Team
+*
+* Distributable under the terms of either the Apache License (Version 2.0) or
+* the GNU Lesser General Public License, as specified in the COPYING file.
+------------------------------------------------------------------------------*/
/*
* this is a monolithic file that can be used to compile clucene using one source file.
* it simplifies some build processes by avoiding static & dynamic compalation pitfalls.
@@ -32,6 +23,7 @@
#include "CLucene/config/repl_lltot.cpp"
#include "CLucene/config/repl_tcstoll.cpp"
#include "CLucene/config/repl_tprintf.cpp"
+#include "CLucene/config/threads.cpp"
#include "CLucene/config/utf8.cpp"
#include "CLucene/debug/condition.cpp"
#include "CLucene/debug/error.cpp"
@@ -110,9 +102,10 @@
#include "CLucene/store/IndexOutput.cpp"
#include "CLucene/store/RAMDirectory.cpp"
#include "CLucene/store/TransactionalRAMDirectory.cpp"
-#include "CLucene/util/BitVector.cpp"
+#include "CLucene/util/BitSet.cpp"
#include "CLucene/util/Equators.cpp"
#include "CLucene/util/FastCharStream.cpp"
+#include "CLucene/util/fileinputstream.cpp"
#include "CLucene/util/MD5Digester.cpp"
#include "CLucene/util/Misc.cpp"
#include "CLucene/util/Reader.cpp"
Modified: trunk/clucene/src/CLucene/LuceneThreads.h
===================================================================
--- trunk/clucene/src/CLucene/LuceneThreads.h 2006-06-11 07:16:00 UTC (rev 427)
+++ trunk/clucene/src/CLucene/LuceneThreads.h 2006-06-26 00:39:24 UTC (rev 428)
@@ -1,242 +1,50 @@
-/**
- * Copyright 2003-2006 The Apache Software Foundation
- *
- * Licensed under the Apache License, Version 2.0 (the "License");
- * you may not use this file except in compliance with the License.
- * You may obtain a copy of the License at
- *
- * http://www.apache.org/licenses/LICENSE-2.0
- *
- * Unless required by applicable law or agreed to in writing, software
- * distributed under the License is distributed on an "AS IS" BASIS,
- * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
- * See the License for the specific language governing permissions and
- * limitations under the License.
- */
+/*------------------------------------------------------------------------------
+* Copyright (C) 2003-2006 Ben van Klinken and the CLucene Team
+*
+* Distributable under the terms of either the Apache License (Version 2.0) or
+* the GNU Lesser General Public License, as specified in the COPYING file.
+------------------------------------------------------------------------------*/
#ifndef _LuceneThreads_h
#define _LuceneThreads_h
#if defined(_LUCENE_PRAGMA_ONCE)
# pragma once
#endif
-CL_NS_DEF(util)
#if defined(_CL_DISABLE_MULTITHREADING)
- #define SCOPED_LOCK_MUTEX(theMutex)
- #define SCOPED_LOCK_MUTEX_EX(theMutex,mutexname,dummy)
+ #define SCOPED_LOCK_MUTEX(theMutex)
+ #define SCOPED_LOCK_MUTEX_EX(theMutex,mutexname,dummy)
+ #define DEFINE_MUTEX(x)
+ #define STATIC_DEFINE_MUTEX(x)
+#else
- #define DEFINE_MUTEX(x)
- #define STATIC_DEFINE_MUTEX(x)
-#else //_CL_DISABLE_MULTITHREADING
-
-#if defined(_LUCENE_THREADMUTEX)
- //do nothing
-
-#elif defined(LUCENE_THREAD_HACK) //LUCENE_THREAD_HACK
- ///a lock mutex hack
- class mutex_default{
+ #if defined(_LUCENE_DONTIMPLEMENT_THREADMUTEX)
+ //do nothing
+ #elif defined(_CL_HAVE_PTHREAD)
+ #include "CLucene/config/threadPthread.h"
+ #elif defined(_CLCOMPILER_MSVC) || defined(__MINGW32__) //note that mingw32 could have pthreads, so put this after.
+ #include "CLucene/config/threadCSection.h"
+ #else
+ #error A valid thread library was not found
+ #endif //mutex types
+
+ CL_NS_DEF(util)
+ class mutexGuard
+ {
private:
- int locked;
- _LUCENE_THREADID_TYPE threadId;
+ _LUCENE_THREADMUTEX* mrMutex;
+ mutexGuard(const mutexGuard& clone);
public:
- mutex_default(const mutex_default& clone){
- locked=0;
- threadId=0;
- }
- mutex_default(){
- locked=0;
- threadId=0;
- }
- ~mutex_default(){
- }
- void lock(){
- _LUCENE_THREADID_TYPE id = _LUCENE_CURRTHREADID;
- if ( this->threadId == id ){
- locked++;
- }else{
- while ( locked>0 )
- _sleep(1);
- this->threadId = id;
- locked=1; //wait till unlocked, then lock
- }
- }
- void unlock(){
-#if defined(_DEBUG)
- if ( locked > 0 ){
- if ( locked == 1 )
- this->threadId = 0;
- locked--;
- } else
- _CLTHROWA(CL_ERR_Runtime, "Mutex wasn't locked");
-# else
- if ( locked == 1 )
- this->threadId = 0;
- locked--;
-# endif // _DEBUG
- }
- };
- #define _LUCENE_THREADMUTEX CL_NS(util)::mutex_default
- #define _LUCENE_THREADMUTEX_USINGDEFAULT
-
-#elif defined(_CLCOMPILER_MSVC) || defined(__MINGW32__)
- #if !defined(LUCENE_USE_WINDOWS_H) && !defined(_WINDOWS_)
- //we have not explicity included windows.h and windows.h has
- //not been included (check _WINDOWS_), then we must define
- //our own definitions to the thread locking functions:
- struct CRITICAL_SECTION
- {
- struct critical_section_debug * DebugInfo;
- long LockCount;
- long RecursionCount;
- void * OwningThread;
- void * LockSemaphore;
- #if defined(_WIN64)
- unsigned __int64 SpinCount;
- #else
- unsigned long SpinCount;
- #endif
- };
+ mutexGuard( _LUCENE_THREADMUTEX& rMutex );
+ ~mutexGuard();
+ };
+ CL_NS_END
+
+ #define SCOPED_LOCK_MUTEX(theMutex) CL_NS(util)::mutexGuard theMutexGuard(theMutex);
+ #define DEFINE_MUTEX(theMutex) _LUCENE_THREADMUTEX theMutex;
+ #define STATIC_DEFINE_MUTEX(theMutex) static _LUCENE_THREADMUTEX theMutex;
- extern "C" __declspec(dllimport) void __stdcall InitializeCriticalSection(CRITICAL_SECTION *);
- extern "C" __declspec(dllimport) void __stdcall EnterCriticalSection(CRITICAL_SECTION *);
- extern "C" __declspec(dllimport) void __stdcall LeaveCriticalSection(CRITICAL_SECTION *);
- extern "C" __declspec(dllimport) void __stdcall DeleteCriticalSection(CRITICAL_SECTION *);
- extern "C" __declspec(dllimport) unsigned long __stdcall GetCurrentThreadId();
- #endif
-
- ///a windows implementation of the lock mutex
- ///todo: boost has a InterlockedExchange way of locking too. More backwards compatible/faster???
- class mutex_win32
- {
- private:
- CRITICAL_SECTION mtx;
- public:
- mutex_win32(const mutex_win32& clone){
- InitializeCriticalSection(&mtx);
- }
- mutex_win32()
- { InitializeCriticalSection(&mtx); }
-
- ~mutex_win32()
- { DeleteCriticalSection(&mtx); }
-
- void lock()
- { EnterCriticalSection(&mtx); }
-
- void unlock()
- { LeaveCriticalSection(&mtx); }
- };
- #define _LUCENE_THREADMUTEX CL_NS(util)::mutex_win32
-
-#elif defined(_CL_HAVE_PTHREAD) && defined(_POSIX_THREADS)
- #include <pthread.h>
- ///a posix implementation of the lock mutex
- ///todo: we need a spinlock implemenation for usage in reference counting
- class mutex_pthread
- {
- private:
- pthread_mutex_t mtx;
-
-#ifndef _CL_HAVE_PTHREAD_MUTEX_RECURSIVE
- pthread_t lockOwner;
- unsigned int lockCount;
-#endif
- public:
- #ifdef _CL__CND_DEBUG
- #define PTHREAD_CHECK(c,m) CND_PRECONDITION(c==0,m)
- #else
- #define PTHREAD_CHECK(c,m) c;
- #endif
- mutex_pthread(const mutex_pthread& clone){
- #if defined(__hpux) && defined(_DECTHREADS_)
- PTHREAD_CHECK(pthread_mutex_init(&mtx, pthread_mutexattr_default), "mutex_pthread(clone) constructor failed")
- #else
- PTHREAD_CHECK(pthread_mutex_init(&mtx, 0), "mutex_pthread(clone) constructor failed")
- #endif
-
-#ifndef _CL_HAVE_PTHREAD_MUTEX_RECURSIVE
- lockCount=0;
- lockOwner=0;
-#endif
- }
- mutex_pthread()
- {
- #if defined(__hpux) && defined(_DECTHREADS_)
- PTHREAD_CHECK(pthread_mutex_init(&mtx, pthread_mutexattr_default), "mutex_pthread() constructor failed")
- #else
- PTHREAD_CHECK(pthread_mutex_init(&mtx, 0), "mutex_pthread() constructor failed")
- #endif
-
-#ifndef _CL_HAVE_PTHREAD_MUTEX_RECURSIVE
- lockCount=0;
- lockOwner=0;
-#endif
- }
-
- ~mutex_pthread()
- { PTHREAD_CHECK(pthread_mutex_destroy(&mtx), "~mutex_pthread destructor failed") }
-
- void lock()
- {
-#ifndef _CL_HAVE_PTHREAD_MUTEX_RECURSIVE
- pthread_t currentThread = pthread_self();
- if( pthread_equal( lockOwner, currentThread ) ) {
- ++lockCount;
- } else {
- PTHREAD_CHECK(pthread_mutex_lock(&mtx), "mutex_pthread::lock")
- lockOwner = currentThread;
- lockCount = 1;
- }
-#else
- PTHREAD_CHECK(pthread_mutex_lock(&mtx), "mutex_pthread::lock")
-#endif
- }
-
- void unlock()
- {
-#ifndef _CL_HAVE_PTHREAD_MUTEX_RECURSIVE
- --lockCount;
- if( lockCount == 0 )
- {
- lockOwner = 0;
- PTHREAD_CHECK(pthread_mutex_unlock(&mtx), "mutex_pthread::unlock") }
- }
-#else
- PTHREAD_CHECK(pthread_mutex_unlock(&mtx), "mutex_pthread::unlock") }
-#endif
- };
- #define _LUCENE_THREADMUTEX CL_NS(util)::mutex_pthread
-
-#else
- #error Cannot implements threads... cannot continue
-#endif //mutex types
-
-class mutexGuard
-{
-private:
- _LUCENE_THREADMUTEX* mrMutex;
- mutexGuard(const mutexGuard& clone){
- //no autoclone
- mrMutex = NULL;
- }
-public:
- mutexGuard( _LUCENE_THREADMUTEX& rMutex ) :
- mrMutex(&rMutex)
- {
- mrMutex->lock();
- }
- ~mutexGuard()
- {
- mrMutex->unlock();
- }
-};
-
-# define SCOPED_LOCK_MUTEX(theMutex) CL_NS(util)::mutexGuard theMutexGuard(theMutex);
-# define DEFINE_MUTEX(theMutex) _LUCENE_THREADMUTEX theMutex;
-# define STATIC_DEFINE_MUTEX(theMutex) static _LUCENE_THREADMUTEX theMutex;
-
#endif //_CL_DISABLE_MULTITHREADING
-CL_NS_END
#endif
Modified: trunk/clucene/src/CLucene/StdHeader.cpp
===================================================================
--- trunk/clucene/src/CLucene/StdHeader.cpp 2006-06-11 07:16:00 UTC (rev 427)
+++ trunk/clucene/src/CLucene/StdHeader.cpp 2006-06-26 00:39:24 UTC (rev 428)
@@ -1,18 +1,9 @@
-/**
- * Copyright 2003-2006 The Apache Software Foundation
- *
- * Licensed under the Apache License, Version 2.0 (the "License");
- * you may not use this file except in compliance with the License.
- * You may obtain a copy of the License at
- *
- * http://www.apache.org/licenses/LICENSE-2.0
- *
- * Unless required by applicable law or agreed to in writing, software
- * distributed under the License is distributed on an "AS IS" BASIS,
- * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
- * See the License for the specific language governing permissions and
- * limitations under the License.
- */
+/*------------------------------------------------------------------------------
+* Copyright (C) 2003-2006 Ben van Klinken and the CLucene Team
+*
+* Distributable under the terms of either the Apache License (Version 2.0) or
+* the GNU Lesser General Public License, as specified in the COPYING file.
+------------------------------------------------------------------------------*/
#include "CLucene/StdHeader.h"
#include "CLucene/util/Misc.h"
@@ -115,9 +106,6 @@
#endif //ucs2
-
-
-
//ok, these are the exceptions, but these never
//exist on non-msvc platform, so lets put it here
#ifndef _CL_HAVE_FILELENGTH
@@ -125,7 +113,7 @@
{
struct fileStat info;
if (fileHandleStat(filehandle, &info) == -1)
- _CLTHROWA( CL_ERR_IO,"fileStat error in StdHeader/fileSize" );
+ _CLTHROWA( CL_ERR_IO,"fileStat error" );
return info.st_size;
}
#endif
Modified: trunk/clucene/src/CLucene/StdHeader.h
===================================================================
--- trunk/clucene/src/CLucene/StdHeader.h 2006-06-11 07:16:00 UTC (rev 427)
+++ trunk/clucene/src/CLucene/StdHeader.h 2006-06-26 00:39:24 UTC (rev 428)
@@ -1,18 +1,9 @@
-/**
- * Copyright 2003-2006 The Apache Software Foundation
- *
- * Licensed under the Apache License, Version 2.0 (the "License");
- * you may not use this file except in compliance with the License.
- * You may obtain a copy of the License at
- *
- * http://www.apache.org/licenses/LICENSE-2.0
- *
- * Unless required by applicable law or agreed to in writing, software
- * distributed under the License is distributed on an "AS IS" BASIS,
- * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
- * See the License for the specific language governing permissions and
- * limitations under the License.
- */
+/*------------------------------------------------------------------------------
+* Copyright (C) 2003-2006 Ben van Klinken and the CLucene Team
+*
+* Distributable under the terms of either the Apache License (Version 2.0) or
+* the GNU Lesser General Public License, as specified in the COPYING file.
+------------------------------------------------------------------------------*/
#ifndef lucene_stdheader_h
#define lucene_stdheader_h
@@ -168,6 +159,7 @@
#include <wctype.h>
#elif defined(_ASCII) && defined(_CL_HAVE_CTYPE_H)
#include <ctype.h>
+ #undef LUCENE_USE_INTERNAL_CHAR_FUNCTIONS
#elif defined(_UCS2)
//must be in _UCS2 to use internal char functions
#undef LUCENE_USE_INTERNAL_CHAR_FUNCTIONS
@@ -212,6 +204,7 @@
////////////////////////////////////////////////////////
#if defined(LUCENE_USE_INTERNAL_CHAR_FUNCTIONS)
#define stringCaseFold cl_tcscasefold
+ #define stringCaseFoldCmp cl_tcscasefoldcmp
#undef _istspace
#undef _istdigit
@@ -225,20 +218,7 @@
#define _istdigit cl_isdigit
#define _totlower cl_tolower
#define _totupper cl_toupper
-
- //the methods contained in rep_wctype.h
- bool cl_isletter(TCHAR c);
- bool cl_isalnum(TCHAR c);
- bool cl_isdigit(TCHAR c);
- bool cl_isspace (TCHAR c);
- TCHAR cl_tolower (TCHAR c);
- TCHAR cl_toupper (TCHAR c);
- #define stringCaseFold cl_tcscasefold
- #define stringCaseFoldCmp cl_tcscasefoldcmp
- int cl_tcscasefoldcmp(const TCHAR * dst, const TCHAR * src);
- TCHAR* cl_tcscasefold( TCHAR * str, int len=-1 );
-
//here are some functions to help deal with utf8/ucs2 conversions
//lets let the user decide what mb functions to use... we provide pure utf8 ones no matter what.
/*#undef _mbtowc
@@ -258,34 +238,40 @@
#define _wcstombs wcstombs*/
//we are using native character functions
- //if we are using ascii, native functions (msvc mainly)
- //can crash if passed an out of range character.
- //here we fix that...
#if defined(_ASCII)
- //fix functions that deal with characters, because
- //mostly if they recieve an out of range character they will cause a segfault
- #undef _istspace
- #undef _istdigit
- #undef _istalnum
- #undef _istalpha
- #undef _totlower
- #undef _totupper
- #define _istspace(x) (((unsigned)x) < 0x100?isspace(x):0)
- #define _istdigit(x) (((unsigned)x) < 0x100?isdigit(x):0)
- #define _istalnum(x) (((unsigned)x) < 0x100?isalnum(x):0)
- #define _istalpha(x) (((unsigned)x) < 0x100?isalpha(x):0)
- //if the character being passed is out of ascii range, we
- //use the LUCENE_OOR_CHAR character as a return
- #define _totlower(x) (((unsigned)x) < 0x80?tolower(x):LUCENE_OOR_CHAR)
- #define _totupper(x) (((unsigned)x) < 0x80?toupper(x):LUCENE_OOR_CHAR)
+ #undef _istspace
+ #undef _istdigit
+ #undef _istalnum
+ #undef _istalpha
+ #undef _totlower
+ #undef _totupper
+ #define _istspace(x) isspace((unsigned char)x)
+ #define _istdigit(x) isdigit((unsigned char)x)
+ #define _istalnum(x) isalnum((unsigned char)x)
+ #define _istalpha(x) isalpha((unsigned char)x)
+ #define _totlower(x) tolower((unsigned char)x)
+ #define _totupper(x) toupper((unsigned char)x)
#endif
#endif
+//the methods contained in gunichartables.h
+typedef unsigned long clunichar;
+bool cl_isletter(clunichar c);
+bool cl_isalnum(clunichar c);
+bool cl_isdigit(clunichar c);
+bool cl_isspace (clunichar c);
+TCHAR cl_tolower (TCHAR c);
+TCHAR cl_toupper (TCHAR c);
+
+int cl_tcscasefoldcmp(const TCHAR * dst, const TCHAR * src);
+TCHAR* cl_tcscasefold( TCHAR * str, int len=-1 );
+
//we provide utf8 conversion functions
size_t lucene_utf8towc (wchar_t *ret, const char *s, size_t n);
size_t lucene_utf8towcs(wchar_t *, const char *, size_t maxslen);
size_t lucene_wctoutf8 (char * ret, const wchar_t str);
size_t lucene_wcstoutf8 (char *, const wchar_t *, size_t maxslen);
+size_t lucene_utf8charlen(const char *p);
///a blank string...
extern TCHAR* _LUCENE_BLANK_STRING;
@@ -428,13 +414,6 @@
#define _T(x) x
#endif
-//#if 0 //todo: figure out which compilers cant assign static constants
-// #define LUCENE_STATIC_CONSTANT(type, assignment) enum { assignment }
-//#else
-#ifndef LUCENE_STATIC_CONSTANT
- #define LUCENE_STATIC_CONSTANT(type, assignment) static const type assignment
-#endif
-
//third inclusion of compiler.h
//this gives CompilerXXX.h a chance to fix any of the
//default settings
Modified: trunk/clucene/src/CLucene/analysis/AnalysisHeader.cpp
===================================================================
--- trunk/clucene/src/CLucene/analysis/AnalysisHeader.cpp 2006-06-11 07:16:00 UTC (rev 427)
+++ trunk/clucene/src/CLucene/analysis/AnalysisHeader.cpp 2006-06-26 00:39:24 UTC (rev 428)
@@ -1,18 +1,9 @@
-/**
- * Copyright 2003-2006 The Apache Software Foundation
- *
- * Licensed under the Apache License, Version 2.0 (the "License");
- * you may not use this file except in compliance with the License.
- * You may obtain a copy of the License at
- *
- * http://www.apache.org/licenses/LICENSE-2.0
- *
- * Unless required by applicable law or agreed to in writing, software
- * distributed under the License is distributed on an "AS IS" BASIS,
- * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
- * See the License for the specific language governing permissions and
- * limitations under the License.
- */
+/*------------------------------------------------------------------------------
+* Copyright (C) 2003-2006 Ben van Klinken and the CLucene Team
+*
+* Distributable under the terms of either the Apache License (Version 2.0) or
+* the GNU Lesser General Public License, as specified in the COPYING file.
+------------------------------------------------------------------------------*/
#include "CLucene/StdHeader.h"
#include "AnalysisHeader.h"
@@ -49,21 +40,15 @@
_type ( typ ),
positionIncrement (1)
{
- termTextLen = _tcslen(text);
+ termTextLen = 0;
#ifndef LUCENE_TOKEN_WORD_LENGTH
- _termText = _CL_NEWARRAY(TCHAR,termTextLen+1);
- _tcsncpy(_termText,text,termTextLen+1);
- bufferTextLen = termTextLen+1;
+ _termText = NULL;
+ bufferTextLen = 0;
#else
- if ( termTextLen > LUCENE_TOKEN_WORD_LENGTH ){
- //in the case where this occurs, we will leave the endOffset as it is
- //since the actual word still occupies that space.
- termTextLen=LUCENE_TOKEN_WORD_LENGTH;
- }
- _tcsncpy(_termText,text,termTextLen+1);
- _termText[termTextLen] = 0; //make sure null terminated
+ _termText[0] = 0; //make sure null terminated
bufferTextLen = LUCENE_TOKEN_WORD_LENGTH+1;
#endif
+ setText(text);
}
void Token::set(const TCHAR* text, const int32_t start, const int32_t end, const TCHAR* typ){
@@ -71,7 +56,11 @@
_endOffset = end;
_type = typ;
positionIncrement = 1;
+ setText(text);
+}
+
+void Token::setText(const TCHAR* text){
int32_t oldlen = termTextLen;
termTextLen = _tcslen(text);
@@ -113,10 +102,10 @@
positionIncrement = posIncr;
}
-int32_t Token::getPositionIncrement() { return positionIncrement; }
+int32_t Token::getPositionIncrement() const { return positionIncrement; }
// Returns the Token's term text.
-const TCHAR* Token::termText() {
+const TCHAR* Token::termText() const{
return (const TCHAR*) _termText;
}
size_t Token::termTextLength() {
@@ -127,8 +116,21 @@
void Token::resetTermTextLen(){
termTextLen=-1;
}
+bool Token::OrderCompare::operator()( Token* t1, Token* t2 ) const{
+ if(t1->startOffset()>t2->startOffset())
+ return false;
+ if(t1->startOffset()<t2->startOffset())
+ return true;
+ return true;
+}
+Token* TokenStream::next(){
+ Token* t = _CLNEW Token;
+ if ( !next(t) )
+ _CLDELETE(t);
+ return t;
+}
TokenFilter::TokenFilter(TokenStream* in, bool deleteTS):
Modified: trunk/clucene/src/CLucene/analysis/AnalysisHeader.h
===================================================================
--- trunk/clucene/src/CLucene/analysis/AnalysisHeader.h 2006-06-11 07:16:00 UTC (rev 427)
+++ trunk/clucene/src/CLucene/analysis/AnalysisHeader.h 2006-06-26 00:39:24 UTC (rev 428)
@@ -1,18 +1,9 @@
-/**
- * Copyright 2003-2006 The Apache Software Foundation
- *
- * Licensed under the Apache License, Version 2.0 (the "License");
- * you may not use this file except in compliance with the License.
- * You may obtain a copy of the License at
- *
- * http://www.apache.org/licenses/LICENSE-2.0
- *
- * Unless required by applicable law or agreed to in writing, software
- * distributed under the License is distributed on an "AS IS" BASIS,
- * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
- * See the License for the specific language governing permissions and
- * limitations under the License.
- */
+/*------------------------------------------------------------------------------
+* Copyright (C) 2003-2006 Ben van Klinken and the CLucene Team
+*
+* Distributable under the terms of either the Apache License (Version 2.0) or
+* the GNU Lesser General Public License, as specified in the COPYING file.
+------------------------------------------------------------------------------*/
#ifndef _lucene_analysis_AnalysisHeader_
#define _lucene_analysis_AnalysisHeader_
@@ -49,8 +40,8 @@
int32_t termTextLen;
size_t bufferTextLen;
- static const TCHAR* defaultType;
public:
+ static const TCHAR* defaultType;
#ifndef LUCENE_HIDE_INTERNAL
#ifndef LUCENE_TOKEN_WORD_LENGTH
TCHAR* _termText; // the text of the term
@@ -59,7 +50,6 @@
#endif
#endif
-
Token();
~Token();
// Constructs a Token with the given text, start and end offsets, & type.
@@ -92,10 +82,11 @@
* occur with no intervening stop words.
*/
void setPositionIncrement(int32_t posIncr);
- int32_t getPositionIncrement();
- const TCHAR* termText();
+ int32_t getPositionIncrement() const;
+ const TCHAR* termText() const;
size_t termTextLength();
void resetTermTextLen();
+ void setText(const TCHAR* txt);
// Returns this Token's starting offset, the position of the first character
// corresponding to this token in the source text.
@@ -120,13 +111,7 @@
class OrderCompare:LUCENE_BASE, public CL_NS(util)::Compare::_base //<Token*>
{
public:
- bool operator()( Token* t1, Token* t2 ) const{
- if(t1->startOffset()>t2->startOffset())
- return false;
- if(t1->startOffset()<t2->startOffset())
- return true;
- return true;
- }
+ bool operator()( Token* t1, Token* t2 ) const;
};
};
@@ -147,12 +132,7 @@
* to next(), this will save a lot of object construction and destructions.
* @deprecated Kept only to avoid breaking existing code.
*/
- Token* next(){
- Token* t = _CLNEW Token;
- if ( !next(t) )
- _CLDELETE(t);
- return t;
- }
+ Token* next();
};
Modified: trunk/clucene/src/CLucene/analysis/Analyzers.cpp
===================================================================
--- trunk/clucene/src/CLucene/analysis/Analyzers.cpp 2006-06-11 07:16:00 UTC (rev 427)
+++ trunk/clucene/src/CLucene/analysis/Analyzers.cpp 2006-06-26 00:39:24 UTC (rev 428)
@@ -1,32 +1,24 @@
-/**
- * Copyright 2003-2006 The Apache Software Foundation
- *
- * Licensed under the Apache License, Version 2.0 (the "License");
- * you may not use this file except in compliance with the License.
- * You may obtain a copy of the License at
- *
- * http://www.apache.org/licenses/LICENSE-2.0
- *
- * Unless required by applicable law or agreed to in writing, software
- * distributed under the License is distributed on an "AS IS" BASIS,
- * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
- * See the License for the specific language governing permissions and
- * limitations under the License.
- */
+/*------------------------------------------------------------------------------
+* Copyright (C) 2003-2006 Ben van Klinken and the CLucene Team
+*
+* Distributable under the terms of either the Apache License (Version 2.0) or
+* the GNU Lesser General Public License, as specified in the COPYING file.
+------------------------------------------------------------------------------*/
#include "CLucene/StdHeader.h"
#include "Analyzers.h"
+#include "CLucene/util/StringBuffer.h"
CL_NS_USE(util)
CL_NS_DEF(analysis)
CharTokenizer::CharTokenizer(Reader* in) :
- //input(in), ; input is in tokenizer base class (bug fix thanks to Andy Osipienko)
- offset(0),
- bufferIndex(0),
- dataLen(0)
-
+ Tokenizer(in),
+ offset(0),
+ bufferIndex(0),
+ dataLen(0),
+ ioBuffer(NULL)
{
- input = in;
+ buffer[0]=0;
}
TCHAR CharTokenizer::normalize(const TCHAR c) const
@@ -99,15 +91,15 @@
return true;
}
-StopFilter::StopFilter(TokenStream* in, bool deleteTokenStream, TCHAR** stopWords):
+StopFilter::StopFilter(TokenStream* in, bool deleteTokenStream, const TCHAR** stopWords):
TokenFilter(in, deleteTokenStream),
- table(_CLNEW CLSetList<TCHAR*>(false))
+ table(_CLNEW CLSetList<const TCHAR*>(false))
{
fillStopTable( table,stopWords );
}
-void StopFilter::fillStopTable(CLSetList<TCHAR*>* stopTable,
- TCHAR** stopWords) {
+void StopFilter::fillStopTable(CLSetList<const TCHAR*>* stopTable,
+ const TCHAR** stopWords) {
for (int32_t i = 0; stopWords[i]!=NULL; i++)
stopTable->insert(stopWords[i]);
}
@@ -131,14 +123,14 @@
StopAnalyzer::~StopAnalyzer()
{
}
-StopAnalyzer::StopAnalyzer( TCHAR** stopWords) {
+StopAnalyzer::StopAnalyzer( const TCHAR** stopWords) {
StopFilter::fillStopTable(&stopTable,stopWords);
}
TokenStream* StopAnalyzer::tokenStream(const TCHAR* fieldName, Reader* reader) {
return _CLNEW StopFilter(_CLNEW LowerCaseTokenizer(reader),true, &stopTable);
}
-TCHAR* StopAnalyzer::ENGLISH_STOP_WORDS[] =
+const TCHAR* StopAnalyzer::ENGLISH_STOP_WORDS[] =
{
_T("a"), _T("an"), _T("and"), _T("are"), _T("as"), _T("at"), _T("be"), _T("but"), _T("by"),
_T("for"), _T("if"), _T("in"), _T("into"), _T("is"), _T("it"),
@@ -170,4 +162,149 @@
return analyzer->tokenStream(fieldName, reader);
}
+
+
+bool ISOLatin1AccentFilter::next(Token* token){
+ if ( input->next(token) ){
+ StringBuffer output;
+ int32_t l = token->termTextLength();
+ const TCHAR* chars = token->termText();
+ for (int32_t i = 0; i < l; i++) {
+ #ifdef _UCS2
+ TCHAR c = chars[i];
+ #else
+ unsigned char c = chars[i];
+ #endif
+ switch (c) {
+ case 0xC0 : // À
+ case 0xC1 : // Á
+ case 0xC2 : // Â
+ case 0xC3 : // Ã
+ case 0xC4 : // Ä
+ case 0xC5 : // Å
+ output.appendChar('A');
+ break;
+ case 0xC6 : // Æ
+ output.append(_T("AE"));
+ break;
+ case 0xC7 : // Ç
+ output.appendChar('C');
+ break;
+ case 0xC8 : // È
+ case 0xC9 : // É
+ case 0xCA : // Ê
+ case 0xCB : // Ë
+ output.appendChar('E');
+ break;
+ case 0xCC : // Ì
+ case 0xCD : // Í
+ case 0xCE : // Î
+ case 0xCF : // Ï
+ output.appendChar('I');
+ break;
+ case 0xD0 : // Ð
+ output.appendChar('D');
+ break;
+ case 0xD1 : // Ñ
+ output.appendChar('N');
+ break;
+ case 0xD2 : // Ò
+ case 0xD3 : // Ó
+ case 0xD4 : // Ô
+ case 0xD5 : // Õ
+ case 0xD6 : // Ö
+ case 0xD8 : // Ø
+ output.appendChar('O');
+ break;
+ case 0xDE : // Þ
+ output.append(_T("TH"));
+ break;
+ case 0xD9 : // Ù
+ case 0xDA : // Ú
+ case 0xDB : // Û
+ case 0xDC : // Ü
+ output.appendChar('U');
+ break;
+ case 0xDD : // Ý
+ output.appendChar('Y');
+ break;
+ case 0xE0 : // à
+ case 0xE1 : // á
+ case 0xE2 : // â
+ case 0xE3 : // ã
+ case 0xE4 : // ä
+ case 0xE5 : // å
+ output.appendChar('a');
+ break;
+ case 0xE6 : // æ
+ output.append(_T("ae"));
+ break;
+ case 0xE7 : // ç
+ output.appendChar('c');
+ break;
+ case 0xE8 : // è
+ case 0xE9 : // é
+ case 0xEA : // ê
+ case 0xEB : // ë
+ output.appendChar('e');
+ break;
+ case 0xEC : // ì
+ case 0xED : // í
+ case 0xEE : // î
+ case 0xEF : // ï
+ output.appendChar('i');
+ break;
+ case 0xF0 : // ð
+ output.appendChar('d');
+ break;
+ case 0xF1 : // ñ
+ output.appendChar('n');
+ break;
+ case 0xF2 : // ò
+ case 0xF3 : // ó
+ case 0xF4 : // ô
+ case 0xF5 : // õ
+ case 0xF6 : // ö
+ case 0xF8 : // ø
+ output.appendChar('o');
+ break;
+ case 0xDF : // ß
+ output.append(_T("ss"));
+ break;
+ case 0xFE : // þ
+ output.append(_T("th"));
+ break;
+ case 0xF9 : // ù
+ case 0xFA : // ú
+ case 0xFB : // û
+ case 0xFC : // ü
+ output.appendChar('u');
+ break;
+ case 0xFD : // ý
+ case 0xFF : // ÿ
+ output.appendChar('y');
+ break;
+
+ #ifdef _UCS2
+ case 0x152 : // Œ
+ output.append(_T("OE"));
+ break;
+ case 0x153 : // œ
+ output.append(_T("oe"));
+ break;
+ case 0x178 : // Ÿ
+ output.appendChar('Y');
+ break;
+ #endif
+ default :
+ output.appendChar(chars[i]);
+ break;
+ }
+ }
+ token->setText(output.getBuffer());
+ return true;
+ }
+ return false;
+}
+
CL_NS_END
Modified: trunk/clucene/src/CLucene/analysis/Analyzers.h
===================================================================
--- trunk/clucene/src/CLucene/analysis/Analyzers.h 2006-06-11 07:16:00 UTC (rev 427)
+++ trunk/clucene/src/CLucene/analysis/Analyzers.h 2006-06-26 00:39:24 UTC (rev 428)
@@ -1,18 +1,9 @@
-/**
- * Copyright 2003-2006 The Apache Software Foundation
- *
- * Licensed under the Apache License, Version 2.0 (the "License");
- * you may not use this file except in compliance with the License.
- * You may obtain a copy of the License at
- *
- * http://www.apache.org/licenses/LICENSE-2.0
- *
- * Unless required by applicable law or agreed to in writing, software
- * distributed under the License is distributed on an "AS IS" BASIS,
- * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
- * See the License for the specific language governing permissions and
- * limitations under the License.
- */
+/*------------------------------------------------------------------------------
+* Copyright (C) 2003-2006 Ben van Klinken and the CLucene Team
+*
+* Distributable under the terms of either the Apache License (Version 2.0) or
+* the GNU Lesser General Public License, as specified in the COPYING file.
+------------------------------------------------------------------------------*/
#ifndef _lucene_analysis_Analyzers_
#define _lucene_analysis_Analyzers_
@@ -44,10 +35,10 @@
public:
CharTokenizer(CL_NS(util)::Reader* in);
-
- virtual ~CharTokenizer(){
- }
-
+
+ virtual ~CharTokenizer(){
+ }
+
// Returns the next token in the stream, or null at EOS.
// *** This is not a pointer. Use of it must deleted.
bool next(Token* token);
@@ -124,7 +115,7 @@
/**
* Normalizes token text to lower case.
*
- * @version $Id: Analyzers.h 2014 2006-04-27 08:17:24Z ustramooner $
+ * @version $Id: Analyzers.h 2209 2006-06-15 14:12:41Z ustramooner $
*/
class LowerCaseFilter: public TokenFilter {
public:
@@ -140,17 +131,17 @@
private:
//bvk: i found this to work faster with a non-hash table. the number of items
//in the stop table is not like to make it worth having hashing.
- CL_NS(util)::CLSetList<TCHAR*>* table;
+ CL_NS(util)::CLSetList<const TCHAR*>* table;
public:
// Constructs a filter which removes words from the input
// TokenStream that are named in the array of words.
- StopFilter(TokenStream* in, bool deleteTokenStream, TCHAR* stopWords[]);
+ StopFilter(TokenStream* in, bool deleteTokenStream, const TCHAR** stopWords);
~StopFilter(){}
// Constructs a filter which removes words from the input
// TokenStream that are named in the Hashtable.
- StopFilter(TokenStream* in, bool deleteTokenStream, CL_NS(util)::CLSetList<TCHAR*>* stopTable):
+ StopFilter(TokenStream* in, bool deleteTokenStream, CL_NS(util)::CLSetList<const TCHAR*>* stopTable):
TokenFilter(in, deleteTokenStream),
table(stopTable)
{}
@@ -164,8 +155,8 @@
*
* @swig stopWords
*/
- static void fillStopTable(CL_NS(util)::CLSetList<TCHAR*>* stopTable,
- TCHAR** stopWords);
+ static void fillStopTable(CL_NS(util)::CLSetList<const TCHAR*>* stopTable,
+ const TCHAR** stopWords);
/**
* Returns the next input Token whose termText() is not a stop word.
@@ -183,7 +174,7 @@
// Filters LetterTokenizer with LowerCaseFilter and StopFilter.
class StopAnalyzer: public Analyzer {
- CL_NS(util)::CLSetList<TCHAR*> stopTable;
+ CL_NS(util)::CLSetList<const TCHAR*> stopTable;
public:
// Builds an analyzer which removes words in ENGLISH_STOP_WORDS.
@@ -191,11 +182,11 @@
~StopAnalyzer();
// Builds an analyzer which removes words in the provided array.
- StopAnalyzer( TCHAR** stopWords );
+ StopAnalyzer( const TCHAR** stopWords );
// Filters LowerCaseTokenizer with StopFilter.
TokenStream* tokenStream(const TCHAR* fieldName, CL_NS(util)::Reader* reader);
- static TCHAR* ENGLISH_STOP_WORDS[];
+ static const TCHAR* ENGLISH_STOP_WORDS[];
};
@@ -245,5 +236,26 @@
TokenStream* tokenStream(const TCHAR* fieldName, CL_NS(util)::Reader* reader);
};
+
+/**
+ * A filter that replaces accented characters in the ISO Latin 1 character set
+ * (ISO-8859-1) by their unaccented equivalent. The case will not be altered.
+ * <p>
+ * For instance, 'à' will be replaced by 'a'.
+ * <p>
+ */
+class ISOLatin1AccentFilter: public TokenFilter {
+public:
+ ISOLatin1AccentFilter(TokenStream* input, bool deleteTs):
+ TokenFilter(input,deleteTs)
+ {
+ }
+
+ /**
+ * To replace accented characters in a String by unaccented equivalents.
+ */
+ bool next(Token* token);
+};
+
CL_NS_END
#endif
Modified: trunk/clucene/src/CLucene/analysis/standard/StandardAnalyzer.cpp
===================================================================
--- trunk/clucene/src/CLucene/analysis/standard/StandardAnalyzer.cpp 2006-06-11 07:16:00 UTC (rev 427)
+++ trunk/clucene/src/CLucene/analysis/standard/StandardAnalyzer.cpp 2006-06-26 00:39:24 UTC (rev 428)
@@ -1,18 +1,9 @@
-/**
- * Copyright 2003-2006 The Apache Software Foundation
- *
- * Licensed under the Apache License, Version 2.0 (the "License");
- * you may not use this file except in compliance with the License.
- * You may obtain a copy of the License at
- *
- * http://www.apache.org/licenses/LICENSE-2.0
- *
- * Unless required by applicable law or agreed to in writing, software
- * distributed under the License is distributed on an "AS IS" BASIS,
- * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
- * See the License for the specific language governing permissions and
- * limitations under the License.
- */
+/*------------------------------------------------------------------------------
+* Copyright (C) 2003-2006 Ben van Klinken and the CLucene Team
+*
+* Distributable under the terms of either the Apache License (Version 2.0) or
+* the GNU Lesser General Public License, as specified in the COPYING file.
+------------------------------------------------------------------------------*/
#include "CLucene/StdHeader.h"
#include "StandardAnalyzer.h"
@@ -34,7 +25,7 @@
StopFilter::fillStopTable( &stopSet,CL_NS(analysis)::StopAnalyzer::ENGLISH_STOP_WORDS);
}
- StandardAnalyzer::StandardAnalyzer( TCHAR** stopWords):
+ StandardAnalyzer::StandardAnalyzer( const TCHAR** stopWords):
stopSet(false)
{
StopFilter::fillStopTable( &stopSet,stopWords );
Modified: trunk/clucene/src/CLucene/analysis/standard/StandardAnalyzer.h
===================================================================
--- trunk/clucene/src/CLucene/analysis/standard/StandardAnalyzer.h 2006-06-11 07:16:00 UTC (rev 427)
+++ trunk/clucene/src/CLucene/analysis/standard/StandardAnalyzer.h 2006-06-26 00:39:24 UTC (rev 428)
@@ -1,18 +1,9 @@
-/**
- * Copyright 2003-2006 The Apache Software Foundation
- *
- * Licensed under the Apache License, Version 2.0 (the "License");
- * you may not use this file except in compliance with the License.
- * You may obtain a copy of the License at
- *
- * http://www.apache.org/licenses/LICENSE-2.0
- *
- * Unless required by applicable law or agreed to in writing, software
- * distributed under the License is distributed on an "AS IS" BASIS,
- * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
- * See the License for the specific language governing permissions and
- * limitations under the License.
- */
+/*------------------------------------------------------------------------------
+* Copyright (C) 2003-2006 Ben van Klinken and the CLucene Team
+*
+* Distributable under the terms of either the Apache License (Version 2.0) or
+* the GNU Lesser General Public License, as specified in the COPYING file.
+------------------------------------------------------------------------------*/
#ifndef _lucene_analysis_standard_StandardAnalyzer
#define _lucene_analysis_standard_StandardAnalyzer
@@ -22,8 +13,8 @@
#include "CLucene/util/VoidMap.h"
#include "CLucene/util/Reader.h"
-#include "../AnalysisHeader.h"
-#include "../Analyzers.h"
+#include "CLucene/analysis/AnalysisHeader.h"
+#include "CLucene/analysis/Analyzers.h"
#include "StandardFilter.h"
#include "StandardTokenizer.h"
@@ -34,13 +25,13 @@
class StandardAnalyzer : public Analyzer
{
private:
- CL_NS(util)::CLSetList<TCHAR*> stopSet;
+ CL_NS(util)::CLSetList<const TCHAR*> stopSet;
public:
// <summary> Builds an analyzer. </summary>
StandardAnalyzer();
//<summary> Builds an analyzer with the given stop words. </summary>
- StandardAnalyzer( TCHAR** stopWords);
+ StandardAnalyzer( const TCHAR** stopWords);
~StandardAnalyzer();
Modified: trunk/clucene/src/CLucene/analysis/standard/StandardFilter.cpp
===================================================================
--- trunk/clucene/src/CLucene/analysis/standard/StandardFilter.cpp 2006-06-11 07:16:00 UTC (rev 427)
+++ trunk/clucene/src/CLucene/analysis/standard/StandardFilter.cpp 2006-06-26 00:39:24 UTC (rev 428)
@@ -1,18 +1,9 @@
-/**
- * Copyright 2003-2006 The Apache Software Foundation
- *
- * Licensed under the Apache License, Version 2.0 (the "License");
- * you may not use this file except in compliance with the License.
- * You may obtain a copy of the License at
- *
- * http://www.apache.org/licenses/LICENSE-2.0
- *
- * Unless required by applicable law or agreed to in writing, software
- * distributed under the License is distributed on an "AS IS" BASIS,
- * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
- * See the License for the specific language governing permissions and
- * limitations under the License.
- */
+/*------------------------------------------------------------------------------
+* Copyright (C) 2003-2006 Ben van Klinken and the CLucene Team
+*
+* Distributable under the terms of either the Apache License (Version 2.0) or
+* the GNU Lesser General Public License, as specified in the COPYING file.
+------------------------------------------------------------------------------*/
#include "CLucene/StdHeader.h"
#include "StandardFilter.h"
Modified: trunk/clucene/src/CLucene/analysis/standard/StandardFilter.h
===================================================================
--- trunk/clucene/src/CLucene/analysis/standard/StandardFilter.h 2006-06-11 07:16:00 UTC (rev 427)
+++ trunk/clucene/src/CLucene/analysis/standard/StandardFilter.h 2006-06-26 00:39:24 UTC (rev 428)
@@ -1,18 +1,9 @@
-/**
- * Copyright 2003-2006 The Apache Software Foundation
- *
- * Licensed under the Apache License, Version 2.0 (the "License");
- * you may not use this file except in compliance with the License.
- * You may obtain a copy of the License at
- *
- * http://www.apache.org/licenses/LICENSE-2.0
- *
- * Unless required by applicable law or agreed to in writing, software
- * distributed under the License is distributed on an "AS IS" BASIS,
- * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
- * See the License for the specific language governing permissions and
- * limitations under the License.
- */
+/*------------------------------------------------------------------------------
+* Copyright (C) 2003-2006 Ben van Klinken and the CLucene Team
+*
+* Distributable under the terms of either the Apache License (Version 2.0) or
+* the GNU Lesser General Public License, as specified in the COPYING file.
+------------------------------------------------------------------------------*/
#ifndef _lucene_analysis_standard_StandardFilter
#define _lucene_analysis_standard_StandardFilter
Modified: trunk/clucene/src/CLucene/analysis/standard/StandardTokenizer.cpp
===================================================================
--- trunk/clucene/src/CLucene/analysis/standard/StandardTokenizer.cpp 2006-06-11 07:16:00 UTC (rev 427)
+++ trunk/clucene/src/CLucene/analysis/standard/StandardTokenizer.cpp 2006-06-26 00:39:24 UTC (rev 428)
@@ -1,18 +1,9 @@
-/**
- * Copyright 2003-2006 The Apache Software Foundation
- *
- * Licensed under the Apache License, Version 2.0 (the "License");
- * you may not use this file except in compliance with the License.
- * You may obtain a copy of the License at
- *
- * http://www.apache.org/licenses/LICENSE-2.0
- *
- * Unless required by applicable law or agreed to in writing, software
- * distributed under the License is distributed on an "AS IS" BASIS,
- * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
- * See the License for the specific language governing permissions and
- * limitations under the License.
- */
+/*------------------------------------------------------------------------------
+* Copyright (C) 2003-2006 Ben van Klinken and the CLucene Team
+*
+* Distributable under the terms of either the Apache License (Version 2.0) or
+* the GNU Lesser General Public License, as specified in the COPYING file.
+------------------------------------------------------------------------------*/
#include "CLucene/StdHeader.h"
#include "StandardTokenizer.h"
@@ -31,8 +22,8 @@
#define DASH (ch == '-')
#define NEGATIVE_SIGN_ DASH
- #define POSITIVE_SIGN_ (ch == '+')
- #define SIGN (NEGATIVE_SIGN_ || POSITIVE_SIGN_)
+ //#define POSITIVE_SIGN_ (ch == '+')
+ //#define SIGN (NEGATIVE_SIGN_ || POSITIVE_SIGN_)
#define DOT (ch == '.')
#define DECIMAL DOT
@@ -49,7 +40,7 @@
** that's not an ALNUM or UNDERSCORE can be considered not to break the
** span. Callers should pass false if only ALNUM/UNDERSCORE are acceptable. */
#define CONSUME_WORD _CONSUME_AS_LONG_AS(ALNUM || UNDERSCORE)
- #define CONSUME_WORD_OR(otherMatches) _CONSUME_AS_LONG_AS(ALNUM || UNDERSCORE || (otherMatches))
+ //#define CONSUME_WORD_OR(otherMatches) _CONSUME_AS_LONG_AS(ALNUM || UNDERSCORE || (otherMatches))
/* It is considered that "nothing of value" has been read if:
@@ -66,7 +57,7 @@
** length indicator and move the terminator back by one character. */
#define SHAVE_RIGHTMOST(sb) (sb.getBuffer()[--sb.len] = '\0')
- #define REMOVE_TRAILING_CHARS(sb, charMatchesCondition) { TCHAR* sbBuf = sb.getBuffer(); for (int32_t i = sb.len-1; i >= 0; i--) { TCHAR c = sbBuf[i]; if (charMatchesCondition) { sbBuf[--sb.len] = '\0'; } else {break;}}}
+ //#define REMOVE_TRAILING_CHARS(sb, charMatchesCondition) { TCHAR* sbBuf = sb.getBuffer(); for (int32_t i = sb.len-1; i >= 0; i--) { TCHAR c = sbBuf[i]; if (charMatchesCondition) { sbBuf[--sb.len] = '\0'; } else {break;}}}
/* Does StringBuffer sb contain any of the characters in string ofThese? */
#define CONTAINS_ANY(sb, ofThese) (_tcscspn(sb.getBuffer(), _T(ofThese)) != static_cast<size_t>(sb.len))
Modified: trunk/clucene/src/CLucene/analysis/standard/StandardTokenizer.h
===================================================================
--- trunk/clucene/src/CLucene/analysis/standard/StandardTokenizer.h 2006-06-11 07:16:00 UTC (rev 427)
+++ trunk/clucene/src/CLucene/analysis/standard/StandardTokenizer.h 2006-06-26 00:39:24 UTC (rev 428)
@@ -1,18 +1,9 @@
-/**
- * Copyright 2003-2006 The Apache Software Foundation
- *
- * Licensed under the Apache License, Version 2.0 (the "License");
- * you may not use this file except in compliance with the License.
- * You may obtain a copy of the License at
- *
- * http://www.apache.org/licenses/LICENSE-2.0
- *
- * Unless required by applicable law or agreed to in writing, software
- * distributed under the License is distributed on an "AS IS" BASIS,
- * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
- * See the License for the specific language governing permissions and
- * limitations under the License.
- */
+/*------------------------------------------------------------------------------
+* Copyright (C) 2003-2006 Ben van Klinken and the CLucene Team
+*
+* Distributable under the terms of either the Apache License (Version 2.0) or
+* the GNU Lesser General Public License, as specified in the COPYING file.
+------------------------------------------------------------------------------*/
#ifndef _lucene_analysis_standard_StandardTokenizer
#define _lucene_analysis_standard_StandardTokenizer
Modified: trunk/clucene/src/CLucene/analysis/standard/StandardTokenizerConstants.h
===================================================================
--- trunk/clucene/src/CLucene/analysis/standard/StandardTokenizerConstants.h 2006-06-11 07:16:00 UTC (rev 427)
+++ trunk/clucene/src/CLucene/analysis/standard/StandardTokenizerConstants.h 2006-06-26 00:39:24 UTC (rev 428)
@@ -1,18 +1,9 @@
-/**
- * Copyright 2003-2006 The Apache Software Foundation
- *
- * Licensed under the Apache License, Version 2.0 (the "License");
- * you may not use this file except in compliance with the License.
- * You may obtain a copy of the License at
- *
- * http://www.apache.org/licenses/LICENSE-2.0
- *
- * Unless required by applicable law or agreed to in writing, software
- * distributed under the License is distributed on an "AS IS" BASIS,
- * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
- * See the License for the specific language governing permissions and
- * limitations under the License.
- */
+/*------------------------------------------------------------------------------
+* Copyright (C) 2003-2006 Ben van Klinken and the CLucene Team
+*
+* Distributable under the terms of either the Apache License (Version 2.0) or
+* the GNU Lesser General Public License, as specified in the COPYING file.
+------------------------------------------------------------------------------*/
#ifndef _lucene_analysis_standard_StandardTokenizerConstants
#define _lucene_analysis_standard_StandardTokenizerConstants
Modified: trunk/clucene/src/CLucene/config/CompilerBcb.h
===================================================================
--- trunk/clucene/src/CLucene/config/CompilerBcb.h 2006-06-11 07:16:00 UTC (rev 427)
+++ trunk/clucene/src/CLucene/config/CompilerBcb.h 2006-06-26 00:39:24 UTC (rev 428)
@@ -1,18 +1,9 @@
-/**
- * Copyright 2003-2006 The Apache Software Foundation
- *
- * Licensed under the Apache License, Version 2.0 (the "License");
- * you may not use this file except in compliance with the License.
- * You may obtain a copy of the License at
- *
- * http://www.apache.org/licenses/LICENSE-2.0
- *
- * Unless required by applicable law or agreed to in writing, software
- * distributed under the License is distributed on an "AS IS" BASIS,
- * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
- * See the License for the specific language governing permissions and
- * limitations under the License.
- */
+/*------------------------------------------------------------------------------
+* Copyright (C) 2003-2006 Ben van Klinken and the CLucene Team
+*
+* Distributable under the terms of either the Apache License (Version 2.0) or
+* the GNU Lesser General Public License, as specified in the COPYING file.
+------------------------------------------------------------------------------*/
#if !defined(_lucene_COMPILER_BCB)
#define _lucene_COMPILER_BCB
@@ -22,11 +13,6 @@
#undef _CL_HAVE_STRTOLL
#undef _CL_HAVE_WCSTOLL
-#ifndef _CL_HAVE_TCHAR_H
-#define _CL_HAVE_TCHAR_H 1
-#endif
-
-#define _BASE_THROW_TYPE CL_NS_STD(runtime_error)
#define _LUCENE_PRAGMA_ONCE
#define _LUCENE_PRAGMA_WARNINGS //tell lucene to display warnings using pragmas instead of #warning
#define LUCENE_DISABLE_HASHING
@@ -76,6 +62,8 @@
#define _ftime ::ftime
#define _rename rename
+ #define _realpath(rel,abs) _fullpath(abs,rel,CL_MAX_PATH)
+
#elif !defined(_lucene_COMPILER_BCB3)
#define _lucene_COMPILER_BCB3
//third inclusion
Modified: trunk/clucene/src/CLucene/config/CompilerGcc.h
===================================================================
--- trunk/clucene/src/CLucene/config/CompilerGcc.h 2006-06-11 07:16:00 UTC (rev 427)
+++ trunk/clucene/src/CLucene/config/CompilerGcc.h 2006-06-26 00:39:24 UTC (rev 428)
@@ -1,18 +1,9 @@
-/**
- * Copyright 2003-2006 The Apache Software Foundation
- *
- * Licensed under the Apache License, Version 2.0 (the "License");
- * you may not use this file except in compliance with the License.
- * You may obtain a copy of the License at
- *
- * http://www.apache.org/licenses/LICENSE-2.0
- *
- * Unless required by applicable law or agreed to in writing, software
- * distributed under the License is distributed on an "AS IS" BASIS,
- * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
- * See the License for the specific language governing permissions and
- * limitations under the License.
- */
+/*------------------------------------------------------------------------------
+* Copyright (C) 2003-2006 Ben van Klinken and the CLucene Team
+*
+* Distributable under the terms of either the Apache License (Version 2.0) or
+* the GNU Lesser General Public License, as specified in the COPYING file.
+------------------------------------------------------------------------------*/
#if !defined(_lucene_COMPILER_GCC)
#define _lucene_COMPILER_GCC
@@ -21,34 +12,6 @@
#include "CLucene/clucene-config.h" //make clucene-config.h file
#endif
-//re-define some of the _CL prefixes...
-#if defined(_CL__ASCII) && !defined(_ASCII)
- #define _ASCII _CL__ASCII
-#endif
-#if defined(_CL__UCS2) && !defined(_UCS2)
- #define _UCS2 _CL__UCS2
-#endif
-#if defined(_CL__DEBUG) && !defined(_DEBUG)
- #define _DEBUG _CL__DEBUG
-#endif
-#if defined(_CL__FILE_OFFSET_BITS) && !defined(_FILE_OFFSET_BITS)
- #define _FILE_OFFSET_BITS _CL__FILE_OFFSET_BITS
-#endif
-#if defined(_CL__LARGE_FILES) && !defined(_LARGE_FILES)
- #define _LARGE_FILES _CL__LARGE_FILES
-#endif
-#if defined(__cl_uint32_t) && !defined(uint32_t)
- #define uint32_t __cl_uint32_t
-#endif
-#if defined(__cl_uint64_t) && !defined(uint64_t)
- #define uint64_t __cl_uint64_t
-#endif
-#if defined(__cl_uint8_t) && !defined(uint8_t)
- #define uint8_t __cl_uint8_t
-#endif
-//end redefine defaults
-
-
#if defined(_ASCII)
#undef _UCS2
#elif defined(_UCS2)
@@ -57,30 +20,27 @@
#define CL_CHARSET_GUESS
#endif
+//dont allow FS_MMAP if mmap is not available
#if defined(LUCENE_FS_MMAP) && !defined(_CL_HAVE_MMAP)
- #undef LUCENE_FS_MMAP
+ #error "LUCENE_FS_MMAP is defined and MMap doesn't appear to be available"
#endif
#ifdef _CL_HAVE_NO_FUNCTION_TRY_BLOCKS
#undef _LUCENE_DISABLE_EXCEPTIONS
#define _LUCENE_DISABLE_EXCEPTIONS
- #error this is bad if you made it here... your compiler seems not to have try/catch blocks.
- #error maybe you could implement an alternative solution for us? :)
-#else
- #define _BASE_THROW_TYPE CL_NS_STD(runtime_error)
+ #error "this is bad if you made it here... your compiler seems not to have try/catch blocks."
+ #error "maybe you could implement an alternative solution for us? :)"
#endif
#ifndef _CL_HAVE_NAMESPACES
#define DISABLE_NAMESPACE
#endif
-#define _LUCENE_CURRTHREADID pthread_self()
-#define _LUCENE_THREADID_TYPE pthread_t
-
#define CL_NS_HASHING(func) __gnu_cxx::func //todo: is this best way?
#define LUCENE_DISABLE_HASHING
+//define the file functions
#define fileSeek lseek
#define fileSize _filelength
#define fileStat stat
@@ -93,13 +53,23 @@
#define fileTell(fhandle) fileSeek(fhandle, 0, SEEK_CUR)
#endif
+//this is needed early on so that CL_MAX_PATH can be correctly determined
+//in the StdHeader.h. This was earlier causing problems with macosx.
+//:: crash was due to realpath() that expects an output arguments that
+//has at least the size of PATH_MAX (even if the result has a lower size)
+#include <limits.h>
+
#ifndef _CL_HAVE_WCHAR_T
typedef unsigned short wchar_t;
#endif
-#ifdef __CYGWIN__
+#if defined(__CYGWIN__)
//cygwin seems to incorrectly define that it has wprintf???
#undef _CL_HAVE_WPRINTF
+#elif defined(__MINGW32__)
+ #ifndef _CL_HAVE_WINDOWS_H
+ #define _CL_HAVE_WINDOWS_H
+ #endif
#endif
@@ -110,13 +80,42 @@
//second inclusion
//types
- #if defined(_CL_HAVE_INTTYPES_H)
- #include <inttypes.h>
- #endif
#if defined(_CL_HAVE_SYS_TYPES_H)
#include <sys/types.h>
#endif
- #include <limits.h>
+ #if defined(_CL_HAVE_INTTYPES_H)
+ #include <inttypes.h>
+ #elif defined(_CL_HAVE_STDINT_H)
+ #include <stdint.h>
+ #else
+ #if _CL_SIZEOF_UNSIGNED_LONG_LONG==8
+ typedef unsigned long long uint64_t;
+ typedef long long int64_t;
+ #elif _CL_SIZEOF_UNSIGNED_LONG==8
+ typedef unsigned long uint64_t;
+ typedef long int64_t;
+ #else
+ #error I do not know what to use for a uint64_t.
+ #endif
+
+ /* Give us an unsigned 32-bit data type. */
+ #if _CL_SIZEOF_UNSIGNED_LONG==4
+ typedef unsigned long uint32_t;
+ typedef long int32_t;
+ #elif _CL_SIZEOF_UNSIGNED_INT==4
+ typedef unsigned int uint32_t;
+ typedef int int32_t;
+ #else
+ #error I do not know what to use for a uint32_t.
+ #endif
+
+ /* An unsigned 8-bit data type */
+ #if _CL_SIZEOF_UNSIGNED_CHAR==1
+ typedef unsigned char uint8_t;
+ #else
+ #error I do not know what to use for a uint8_t.
+ #endif
+ #endif
//second chance to fix default settings
//this must be defined later, otherwise it messes up
@@ -126,18 +125,17 @@
#define _read ::read
#endif
-
- //now that int64_t is defined, we can define this...
+ //now that int64_t is defined, we can define this...
#ifndef _CL_HAVE_FILELENGTH
#undef fileSize
#define fileSize lucene_filelength
int64_t lucene_filelength(int handle);
#endif
-
+
#elif !defined(_lucene_COMPILER_GCC3)
#define _lucene_COMPILER_GCC3
//third inclusion
-
+
#if !defined(__MINGW32__)
//define replacements
#define O_RANDOM 0
@@ -145,36 +143,20 @@
#define O_BINARY 0
#define _S_IREAD 0444
#define _S_IWRITE 0333 // write and execute permissions
-
+
//some functions that are needed - not charset dependent and not tchar type functions
#define _open open
#define _sleep(x) usleep(x*1000) //_sleep should be in millis, usleep is in micros
#define _write write
#define _snprintf snprintf
-
+
//clucene uses ascii for filename interactions
- #define _fullpath(abs,rel,len) realpath(rel,abs)
+ #define _realpath(rel,abs) realpath(rel,abs)
#define _mkdir(x) mkdir(x,0777)
#define _unlink unlink
+ #else
+ #define _realpath(rel,abs) _fullpath(abs,rel,CL_MAX_PATH)
#endif
//also required by mingw
#define _rename rename
-
-
- #if !defined(_CL_DISABLE_MULTITHREADING) && defined(_CL_HAVE_PTHREAD) && defined(_POSIX_THREADS)
- class CLuceneThreadIdCompare
- {
- public:
- enum
- { // parameters for hash table
- bucket_size = 4, // 0 < bucket_size
- min_buckets = 8
- }; // min_buckets = 2 ^^ N, 0 < N
-
- bool operator()( pthread_t t1, pthread_t t2 ) const{
- return t1 < t2;
- }
- };
- #endif
-
#endif
Modified: trunk/clucene/src/CLucene/config/CompilerMsvc.h
===================================================================
--- trunk/clucene/src/CLucene/config/CompilerMsvc.h 2006-06-11 07:16:00 UTC (rev 427)
+++ trunk/clucene/src/CLucene/config/CompilerMsvc.h 2006-06-26 00:39:24 UTC (rev 428)
@@ -1,18 +1,9 @@
-/**
- * Copyright 2003-2006 The Apache Software Foundation
- *
- * Licensed under the Apache License, Version 2.0 (the "License");
- * you may not use this file except in compliance with the License.
- * You may obtain a copy of the License at
- *
- * http://www.apache.org/licenses/LICENSE-2.0
- *
- * Unless required by applicable law or agreed to in writing, software
- * distributed under the License is distributed on an "AS IS" BASIS,
- * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
- * See the License for the specific language governing permissions and
- * limitations under the License.
- */
+/*------------------------------------------------------------------------------
+* Copyright (C) 2003-2006 Ben van Klinken and the CLucene Team
+*
+* Distributable under the terms of either the Apache License (Version 2.0) or
+* the GNU Lesser General Public License, as specified in the COPYING file.
+------------------------------------------------------------------------------*/
#if !defined(_lucene_COMPILER_MSVC)
#define _lucene_COMPILER_MSVC
@@ -23,7 +14,9 @@
#if (_MSC_VER >= 1300)
//>= 7.0
# pragma warning(disable: 4512) // This would be very annoying
+ # pragma warning(disable: 4290) // Ignore exception specification warning
#define CL_NS_HASHING(func) stdext::func
+ #define LUCENE_STATIC_CONSTANT_SYNTAX 1
#elif (_MSC_VER >= 1200)
//6.0
@@ -39,7 +32,7 @@
#define _CLDELETE_LCaARRAY(x) if (x!=NULL){delete[] __CONST_CAST(char*,x);}
#endif
- #define LUCENE_STATIC_CONSTANT(type, assignment) enum { assignment }
+ #define LUCENE_STATIC_CONSTANT_SYNTAX 2
# pragma warning(disable: 4786) // This would be very annoying
namespace std{
@@ -64,7 +57,6 @@
#endif
-#define _BASE_THROW_TYPE exception
#if _MSC_VER >= 1020
#define _LUCENE_PRAGMA_ONCE
#endif
@@ -73,9 +65,6 @@
//if we are compiling using single-threaded libraries, we can disable multi-threading stuff
#if !defined(_MT) && !defined(_CL_DISABLE_MULTITHREADING)
#define _CL_DISABLE_MULTITHREADING
-#else
- #define _LUCENE_CURRTHREADID GetCurrentThreadId()
- #define _LUCENE_THREADID_TYPE DWORD
#endif
//msvc supports large files
@@ -96,6 +85,9 @@
//_rename is not defined???
#define _rename rename
+#define CL_MAX_PATH 260 //give the windef.h value for this...
+#define _realpath(rel,abs) _fullpath(abs,rel,CL_MAX_PATH)
+
//java long type
typedef __int64 int64_t;
typedef unsigned __int64 uint64_t;
@@ -125,21 +117,4 @@
#elif !defined(_lucene_COMPILER_MSVC3)
#define _lucene_COMPILER_MSVC3
//third inclusion
-
- #ifndef _CL_DISABLE_MULTITHREADING
- class CLuceneThreadIdCompare
- {
- public:
-
- enum
- { // parameters for hash table
- bucket_size = 4, // 0 < bucket_size
- min_buckets = 8
- }; // min_buckets = 2 ^^ N, 0 < N
-
- bool operator()( DWORD t1, DWORD t2 ) const{
- return t1 < t2;
- }
- };
- #endif
#endif
Modified: trunk/clucene/src/CLucene/config/PlatformMac.h
===================================================================
--- trunk/clucene/src/CLucene/config/PlatformMac.h 2006-06-11 07:16:00 UTC (rev 427)
+++ trunk/clucene/src/CLucene/config/PlatformMac.h 2006-06-26 00:39:24 UTC (rev 428)
@@ -1,18 +1,9 @@
-/**
- * Copyright 2003-2006 The Apache Software Foundation
- *
- * Licensed under the Apache License, Version 2.0 (the "License");
- * you may not use this file except in compliance with the License.
- * You may obtain a copy of the License at
- *
- * http://www.apache.org/licenses/LICENSE-2.0
- *
- * Unless required by applicable law or agreed to in writing, software
- * distributed under the License is distributed on an "AS IS" BASIS,
- * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
- * See the License for the specific language governing permissions and
- * limitations under the License.
- */
+/*------------------------------------------------------------------------------
+* Copyright (C) 2003-2006 Ben van Klinken and the CLucene Team
+*
+* Distributable under the terms of either the Apache License (Version 2.0) or
+* the GNU Lesser General Public License, as specified in the COPYING file.
+------------------------------------------------------------------------------*/
// It is internal CLucene header - DO NOT include it directly
# define PATH_DELIMITER _T("/")
Modified: trunk/clucene/src/CLucene/config/PlatformUnix.h
===================================================================
--- trunk/clucene/src/CLucene/config/PlatformUnix.h 2006-06-11 07:16:00 UTC (rev 427)
+++ trunk/clucene/src/CLucene/config/PlatformUnix.h 2006-06-26 00:39:24 UTC (rev 428)
@@ -1,18 +1,9 @@
-/**
- * Copyright 2003-2006 The Apache Software Foundation
- *
- * Licensed under the Apache License, Version 2.0 (the "License");
- * you may not use this file except in compliance with the License.
- * You may obtain a copy of the License at
- *
- * http://www.apache.org/licenses/LICENSE-2.0
- *
- * Unless required by applicable law or agreed to in writing, software
- * distributed under the License is distributed on an "AS IS" BASIS,
- * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
- * See the License for the specific language governing permissions and
- * limitations under the License.
- */
+/*------------------------------------------------------------------------------
+* Copyright (C) 2003-2006 Ben van Klinken and the CLucene Team
+*
+* Distributable under the terms of either the Apache License (Version 2.0) or
+* the GNU Lesser General Public License, as specified in the COPYING file.
+------------------------------------------------------------------------------*/
// It is internal CLucene header - DO NOT include it directly
# define PATH_DELIMITER _T("/")
Modified: trunk/clucene/src/CLucene/config/PlatformWin32.h
===================================================================
--- trunk/clucene/src/CLucene/config/PlatformWin32.h 2006-06-11 07:16:00 UTC (rev 427)
+++ trunk/clucene/src/CLucene/config/PlatformWin32.h 2006-06-26 00:39:24 UTC (rev 428)
@@ -1,18 +1,9 @@
-/**
- * Copyright 2003-2006 The Apache Software Foundation
- *
- * Licensed under the Apache License, Version 2.0 (the "License");
- * you may not use this file except in compliance with the License.
- * You may obtain a copy of the License at
- *
- * http://www.apache.org/licenses/LICENSE-2.0
- *
- * Unless required by applicable law or agreed to in writing, software
- * distributed under the License is distributed on an "AS IS" BASIS,
- * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
- * See the License for the specific language governing permissions and
- * limitations under the License.
- */
+/*------------------------------------------------------------------------------
+* Copyright (C) 2003-2006 Ben van Klinken and the CLucene Team
+*
+* Distributable under the terms of either the Apache License (Version 2.0) or
+* the GNU Lesser General Public License, as specified in the COPYING file.
+------------------------------------------------------------------------------*/
// It is internal CLucene header - DO NOT include it directly
# define PATH_DELIMITER _T("\\")
Modified: trunk/clucene/src/CLucene/config/compiler.h
===================================================================
--- trunk/clucene/src/CLucene/config/compiler.h 2006-06-11 07:16:00 UTC (rev 427)
+++ trunk/clucene/src/CLucene/config/compiler.h 2006-06-26 00:39:24 UTC (rev 428)
@@ -1,18 +1,9 @@
-/**
- * Copyright 2003-2006 The Apache Software Foundation
- *
- * Licensed under the Apache License, Version 2.0 (the "License");
- * you may not use this file except in compliance with the License.
- * You may obtain a copy of the License at
- *
- * http://www.apache.org/licenses/LICENSE-2.0
- *
- * Unless required by applicable law or agreed to in writing, software
- * distributed under the License is distributed on an "AS IS" BASIS,
- * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
- * See the License for the specific language governing permissions and
- * limitations under the License.
- */
+/*------------------------------------------------------------------------------
+* Copyright (C) 2003-2006 Ben van Klinken and the CLucene Team
+*
+* Distributable under the terms of either the Apache License (Version 2.0) or
+* the GNU Lesser General Public License, as specified in the COPYING file.
+------------------------------------------------------------------------------*/
#if !defined(lucene_compiler_h)
#define lucene_compiler_h
@@ -45,7 +36,7 @@
#define _CLCOMPILER_MSVC _MSC_VER
#endif
-#ifdef __GNUC__
+#if defined(__GNUC__) || defined(__SUNPRO_CC) || defined(__xlC__)
#include "CLucene/config/CompilerGcc.h"
#elif defined(_CLCOMPILER_MSVC)
@@ -111,15 +102,6 @@
#undef _ASCII
#endif
-
-#ifdef IS_BIG_ENDIAN
- #ifdef _LUCENE_PRAGMA_WARNINGS
- #pragma message ("Big endian build hasn't been tested yet. Please send in your success/failure to the project.")
- #else
- #warning "Big endian build hasn't been tested yet. Please send in your success/failure to the project."
- #endif
-#endif
-
#ifndef _LUCENE_NO_NEW_STYLE_CASTS
#define __CONST_CAST(typ,var) const_cast<typ>(var)
#define __REINTERPRET_CAST(typ,var) reinterpret_cast<typ>(var)
@@ -145,41 +127,53 @@
#define LUCENE_INT32_MAX_SHOULDBE 0x7FFFFFFFL
#define LUCENE_UINT8_MAX_SHOULDBE 0xff
-#ifdef PATH_MAX
+//maximum path length. only used for buffers that use fullpath.
+//anything else should use a dynamic length.
+#if defined(CL_MAX_PATH)
+//do nothing...
+#elif defined(PATH_MAX)
#define CL_MAX_PATH PATH_MAX
#elif defined(MAX_PATH)
#define CL_MAX_PATH MAX_PATH
#elif defined(_MAX_PATH)
#define CL_MAX_PATH _MAX_PATH
#else
- #define CL_MAX_PATH 256 /* Should be safe for any weird systems that do not define it */
+ #error "CL_MAX_PATH could not be determined"
#endif
-#ifndef MAX_DIR
- #ifdef DIR_MAX
- #define MAX_DIR DIR_MAX
- #elif defined(_MAX_DIR)
- #define MAX_DIR _MAX_DIR
- #else
- #define MAX_DIR 32 /* Should be safe for any weird systems that do not define it */
- #endif
-#endif // MAX_DIR
+//this is the max filename... for now its just the same,
+//but this could change, so we use a different name
+#define CL_MAX_NAME CL_MAX_PATH
+//todo: this is a temporary fix for a potential buffer overflow...
+//should never use this
+#define CL_MAX_DIR CL_MAX_PATH*32
-#define CL_MAX_DIR MAX_DIR*CL_MAX_PATH //32 directories * 256 bytes...
-
#ifdef _LARGE_FILES
#define LUCENE_MAX_FILELENGTH LUCENE_INT64_MAX_SHOULDBE
#else
#define LUCENE_MAX_FILELENGTH LUCENE_INT32_MAX_SHOULDBE
#endif
+//use the LUCENE_STATIC_CONSTANT_SYNTAX to determine LUCENE_STATIC_CONSTANT
+#ifndef LUCENE_STATIC_CONSTANT
+ //autoconf is not properly detecting the correct method for this, and since there's no real big
+ //harm in always using an enum, we'll probably just make this the default.
+ /*#if LUCENE_STATIC_CONSTANT_SYNTAX == 1
+ #define LUCENE_STATIC_CONSTANT(type, assignment) static const type assignment
+ #elif LUCENE_STATIC_CONSTANT_SYNTAX == 2*/
+ #define LUCENE_STATIC_CONSTANT(type, assignment) enum { assignment }
+ /*#else
+ #error "LUCENE_STATIC_CONSTANT not defined, and/or LUCENE_STATIC_CONSTANT_SYNTAX is not defined to a valid value"
+ #endif*/
+#endif
+
//end of lucene_compiler_h
#elif !defined(lucene_compiler_h2)
#define lucene_compiler_h2
//here we include the compiler header again, this gives the header a
//second chance at including stuff, after the main inclusions are complete
- #if defined (__GNUC__)
+ #if defined (__GNUC__) || defined(__SUNPRO_CC) || defined(__xlC__)
#include "CLucene/config/CompilerGcc.h"
#elif defined(_CLCOMPILER_MSVC)
@@ -226,7 +220,7 @@
//here we include the compiler header again, this gives the header a
//third chance at including stuff, after the main inclusions are complete
- #if defined (__GNUC__ )
+ #if defined (__GNUC__ ) || defined(__SUNPRO_CC) || defined(__xlC__)
#include "CLucene/config/CompilerGcc.h"
#elif defined(_CLCOMPILER_MSVC)
Modified: trunk/clucene/src/CLucene/config/define_std.h
===================================================================
--- trunk/clucene/src/CLucene/config/define_std.h 2006-06-11 07:16:00 UTC (rev 427)
+++ trunk/clucene/src/CLucene/config/define_std.h 2006-06-26 00:39:24 UTC (rev 428)
@@ -1,18 +1,9 @@
-/**
- * Copyright 2003-2006 The Apache Software Foundation
- *
- * Licensed under the Apache License, Version 2.0 (the "License");
- * you may not use this file except in compliance with the License.
- * You may obtain a copy of the License at
- *
- * http://www.apache.org/licenses/LICENSE-2.0
- *
- * Unless required by applicable law or agreed to in writing, software
- * distributed under the License is distributed on an "AS IS" BASIS,
- * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
- * See the License for the specific language governing permissions and
- * limitations under the License.
- */
+/*------------------------------------------------------------------------------
+* Copyright (C) 2003-2006 Ben van Klinken and the CLucene Team
+*
+* Distributable under the terms of either the Apache License (Version 2.0) or
+* the GNU Lesser General Public License, as specified in the COPYING file.
+------------------------------------------------------------------------------*/
#ifndef lucene_define_std
#define lucene_define_std
//define a standard list of defines.
Modified: trunk/clucene/src/CLucene/config/gunichartables.cpp
===================================================================
--- trunk/clucene/src/CLucene/config/gunichartables.cpp 2006-06-11 07:16:00 UTC (rev 427)
+++ trunk/clucene/src/CLucene/config/gunichartables.cpp 2006-06-26 00:39:24 UTC (rev 428)
@@ -132,10 +132,9 @@
#warning "===== Using internal character function ====="
#endif
-bool cl_isletter(TCHAR ch)
+bool cl_isletter(gunichar c)
{
- gunichar c=ch;
- int t = TYPE ((gunichar)c);
+ int t = TYPE (c);
switch(t)
{
case G_UNICODE_LOWERCASE_LETTER: return true;
@@ -147,9 +146,8 @@
}
}
-bool cl_isalnum(TCHAR ch)
+bool cl_isalnum(gunichar c)
{
- gunichar c=ch;
int t = TYPE (c);
switch(t)
{
@@ -165,10 +163,9 @@
}
}
-bool cl_isdigit(TCHAR ch)
+bool cl_isdigit(gunichar c)
{
- gunichar c=ch;
- int t = TYPE ((gunichar)c);
+ int t = TYPE (c);
switch(t)
{
case G_UNICODE_DECIMAL_NUMBER: return true;
@@ -192,9 +189,8 @@
*
* Return value: %TRUE if @c is a punctuation character
**/
-bool cl_isspace (TCHAR ch)
+bool cl_isspace (gunichar c)
{
- gunichar c=ch;
switch (c)
{
/* special-case these since Unicode thinks they are not spaces */
@@ -239,12 +235,9 @@
wchar_t ret=0;
lucene_utf8towc(&ret,p,6);
#ifdef _UCS2
- return ret;
+ return ret;
#else
- if ( ret > 0x80 )
- return LUCENE_OOR_CHAR;
- else
- return (char)ret;
+ return LUCENE_OOR_CHAR(ret);
#endif
//return cl_utf8_get_char (p, &len);
}else
@@ -286,10 +279,7 @@
#ifdef _UCS2
return ret;
#else
- if ( ret > 0x80 )
- return LUCENE_OOR_CHAR;
- else
- return (char)ret;
+ return LUCENE_OOR_CHAR(ret);
#endif
//return lucene_utf8towc (p);
}
@@ -345,12 +335,9 @@
lucene_utf8towc(&ret,casefold_table[half].data,6);
#ifdef _UCS2
- return ret;
+ return ret;
#else
- if ( ret > 0x80 )
- return LUCENE_OOR_CHAR;
- else
- return (char)ret;
+ LUCENE_OOR_CHAR(ret)
#endif
}else if (half == start){
break;
Modified: trunk/clucene/src/CLucene/config/repl_lltot.cpp
===================================================================
--- trunk/clucene/src/CLucene/config/repl_lltot.cpp 2006-06-11 07:16:00 UTC (rev 427)
+++ trunk/clucene/src/CLucene/config/repl_lltot.cpp 2006-06-26 00:39:24 UTC (rev 428)
@@ -1,18 +1,9 @@
-/**
- * Copyright 2003-2006 The Apache Software Foundation
- *
- * Licensed under the Apache License, Version 2.0 (the "License");
- * you may not use this file except in compliance with the License.
- * You may obtain a copy of the License at
- *
- * http://www.apache.org/licenses/LICENSE-2.0
- *
- * Unless required by applicable law or agreed to in writing, software
- * distributed under the License is distributed on an "AS IS" BASIS,
- * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
- * See the License for the specific language governing permissions and
- * limitations under the License.
- */
+/*------------------------------------------------------------------------------
+* Copyright (C) 2003-2006 Ben van Klinken and the CLucene Team
+*
+* Distributable under the terms of either the Apache License (Version 2.0) or
+* the GNU Lesser General Public License, as specified in the COPYING file.
+------------------------------------------------------------------------------*/
#include "CLucene/StdHeader.h"
TCHAR* lucene_i64tot(
Modified: trunk/clucene/src/CLucene/config/repl_tchar.h
===================================================================
--- trunk/clucene/src/CLucene/config/repl_tchar.h 2006-06-11 07:16:00 UTC (rev 427)
+++ trunk/clucene/src/CLucene/config/repl_tchar.h 2006-06-26 00:39:24 UTC (rev 428)
@@ -1,18 +1,9 @@
-/**
- * Copyright 2003-2006 The Apache Software Foundation
- *
- * Licensed under the Apache License, Version 2.0 (the "License");
- * you may not use this file except in compliance with the License.
- * You may obtain a copy of the License at
- *
- * http://www.apache.org/licenses/LICENSE-2.0
- *
- * Unless required by applicable law or agreed to in writing, software
- * distributed under the License is distributed on an "AS IS" BASIS,
- * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
- * See the License for the specific language governing permissions and
- * limitations under the License.
- */
+/*------------------------------------------------------------------------------
+* Copyright (C) 2003-2006 Ben van Klinken and the CLucene Team
+*
+* Distributable under the terms of either the Apache License (Version 2.0) or
+* the GNU Lesser General Public License, as specified in the COPYING file.
+------------------------------------------------------------------------------*/
#ifndef _CL_HAVE_TCHAR_H
#if defined(_UCS2)
#define TCHAR wchar_t
Modified: trunk/clucene/src/CLucene/config/repl_tcscasecmp.cpp
===================================================================
--- trunk/clucene/src/CLucene/config/repl_tcscasecmp.cpp 2006-06-11 07:16:00 UTC (rev 427)
+++ trunk/clucene/src/CLucene/config/repl_tcscasecmp.cpp 2006-06-26 00:39:24 UTC (rev 428)
@@ -1,18 +1,9 @@
-/**
- * Copyright 2003-2006 The Apache Software Foundation
- *
- * Licensed under the Apache License, Version 2.0 (the "License");
- * you may not use this file except in compliance with the License.
- * You may obtain a copy of the License at
- *
- * http://www.apache.org/licenses/LICENSE-2.0
- *
- * Unless required by applicable law or agreed to in writing, software
- * distributed under the License is distributed on an "AS IS" BASIS,
- * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
- * See the License for the specific language governing permissions and
- * limitations under the License.
- */
+/*------------------------------------------------------------------------------
+* Copyright (C) 2003-2006 Ben van Klinken and the CLucene Team
+*
+* Distributable under the terms of either the Apache License (Version 2.0) or
+* the GNU Lesser General Public License, as specified in the COPYING file.
+------------------------------------------------------------------------------*/
#include "CLucene/StdHeader.h"
Modified: trunk/clucene/src/CLucene/config/repl_tcslwr.cpp
===================================================================
--- trunk/clucene/src/CLucene/config/repl_tcslwr.cpp 2006-06-11 07:16:00 UTC (rev 427)
+++ trunk/clucene/src/CLucene/config/repl_tcslwr.cpp 2006-06-26 00:39:24 UTC (rev 428)
@@ -1,18 +1,9 @@
-/**
- * Copyright 2003-2006 The Apache Software Foundation
- *
- * Licensed under the Apache License, Version 2.0 (the "License");
- * you may not use this file except in compliance with the License.
- * You may obtain a copy of the License at
- *
- * http://www.apache.org/licenses/LICENSE-2.0
- *
- * Unless required by applicable law or agreed to in writing, software
- * distributed under the License is distributed on an "AS IS" BASIS,
- * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
- * See the License for the specific language governing permissions and
- * limitations under the License.
- */
+/*------------------------------------------------------------------------------
+* Copyright (C) 2003-2006 Ben van Klinken and the CLucene Team
+*
+* Distributable under the terms of either the Apache License (Version 2.0) or
+* the GNU Lesser General Public License, as specified in the COPYING file.
+------------------------------------------------------------------------------*/
#include "CLucene/StdHeader.h"
Modified: trunk/clucene/src/CLucene/config/repl_tcstod.cpp
===================================================================
--- trunk/clucene/src/CLucene/config/repl_tcstod.cpp 2006-06-11 07:16:00 UTC (rev 427)
+++ trunk/clucene/src/CLucene/config/repl_tcstod.cpp 2006-06-26 00:39:24 UTC (rev 428)
@@ -1,18 +1,9 @@
-/**
- * Copyright 2003-2006 The Apache Software Foundation
- *
- * Licensed under the Apache License, Version 2.0 (the "License");
- * you may not use this file except in compliance with the License.
- * You may obtain a copy of the License at
- *
- * http://www.apache.org/licenses/LICENSE-2.0
- *
- * Unless required by applicable law or agreed to in writing, software
- * distributed under the License is distributed on an "AS IS" BASIS,
- * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
- * See the License for the specific language governing permissions and
- * limitations under the License.
- */
+/*------------------------------------------------------------------------------
+* Copyright (C) 2003-2006 Ben van Klinken and the CLucene Team
+*
+* Distributable under the terms of either the Apache License (Version 2.0) or
+* the GNU Lesser General Public License, as specified in the COPYING file.
+------------------------------------------------------------------------------*/
#include "CLucene/StdHeader.h"
Modified: trunk/clucene/src/CLucene/config/repl_tcstoll.cpp
===================================================================
--- trunk/clucene/src/CLucene/config/repl_tcstoll.cpp 2006-06-11 07:16:00 UTC (rev 427)
+++ trunk/clucene/src/CLucene/config/repl_tcstoll.cpp 2006-06-26 00:39:24 UTC (rev 428)
@@ -1,18 +1,9 @@
-/**
- * Copyright 2003-2006 The Apache Software Foundation
- *
- * Licensed under the Apache License, Version 2.0 (the "License");
- * you may not use this file except in compliance with the License.
- * You may obtain a copy of the License at
- *
- * http://www.apache.org/licenses/LICENSE-2.0
- *
- * Unless required by applicable law or agreed to in writing, software
- * distributed under the License is distributed on an "AS IS" BASIS,
- * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
- * See the License for the specific language governing permissions and
- * limitations under the License.
- */
+/*------------------------------------------------------------------------------
+* Copyright (C) 2003-2006 Ben van Klinken and the CLucene Team
+*
+* Distributable under the terms of either the Apache License (Version 2.0) or
+* the GNU Lesser General Public License, as specified in the COPYING file.
+------------------------------------------------------------------------------*/
#include "CLucene/StdHeader.h"
Modified: trunk/clucene/src/CLucene/config/repl_tprintf.cpp
===================================================================
--- trunk/clucene/src/CLucene/config/repl_tprintf.cpp 2006-06-11 07:16:00 UTC (rev 427)
+++ trunk/clucene/src/CLucene/config/repl_tprintf.cpp 2006-06-26 00:39:24 UTC (rev 428)
@@ -1,24 +1,15 @@
-/**
- * Copyright 2003-2006 The Apache Software Foundation
- *
- * Licensed under the Apache License, Version 2.0 (the "License");
- * you may not use this file except in compliance with the License.
- * You may obtain a copy of the License at
- *
- * http://www.apache.org/licenses/LICENSE-2.0
- *
- * Unless required by applicable law or agreed to in writing, software
- * distributed under the License is distributed on an "AS IS" BASIS,
- * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
- * See the License for the specific language governing permissions and
- * limitations under the License.
- */
+/*------------------------------------------------------------------------------
+* Copyright (C) 2003-2006 Ben van Klinken and the CLucene Team
+*
+* Distributable under the terms of either the Apache License (Version 2.0) or
+* the GNU Lesser General Public License, as specified in the COPYING file.
+------------------------------------------------------------------------------*/
#include "CLucene/StdHeader.h"
#include "CLucene/util/StringBuffer.h"
#ifdef __CL_INCLUDE_TPRINTF
-CL_NS_USE(util);
+CL_NS_USE(util)
//print a variable argument to a stream
//currently special number formatting is not supported. it is very minimalistic
Modified: trunk/clucene/src/CLucene/config/repl_wchar.h
===================================================================
--- trunk/clucene/src/CLucene/config/repl_wchar.h 2006-06-11 07:16:00 UTC (rev 427)
+++ trunk/clucene/src/CLucene/config/repl_wchar.h 2006-06-26 00:39:24 UTC (rev 428)
@@ -1,21 +1,14 @@
-/**
- * Copyright 2003-2006 The Apache Software Foundation
- *
- * Licensed under the Apache License, Version 2.0 (the "License");
- * you may not use this file except in compliance with the License.
- * You may obtain a copy of the License at
- *
- * http://www.apache.org/licenses/LICENSE-2.0
- *
- * Unless required by applicable law or agreed to in writing, software
- * distributed under the License is distributed on an "AS IS" BASIS,
- * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
- * See the License for the specific language governing permissions and
- * limitations under the License.
- */
+/*------------------------------------------------------------------------------
+* Copyright (C) 2003-2006 Ben van Klinken and the CLucene Team
+*
+* Distributable under the terms of either the Apache License (Version 2.0) or
+* the GNU Lesser General Public License, as specified in the COPYING file.
+------------------------------------------------------------------------------*/
#ifndef _lucene_repl_wchar_h
#define _lucene_repl_wchar_h
+#ifdef _UCS2
+
#ifndef _CL_HAVE_WCSCPY
//copy a string to another string
#error wcscpy is not defined, and a licensed replacement has not been written yet
@@ -62,6 +55,8 @@
#error wcscspn is not defined, and a licensed replacement has not been written yet
#endif
+#endif //_UCS2
+
//string function replacements
#if defined(LUCENE_USE_INTERNAL_CHAR_FUNCTIONS) || (defined(_UCS2) && !defined(_CL_HAVE_WCSCASECMP)) || (defined(_ASCII) && !defined(_CL_HAVE_STRCASECMP))
int lucene_tcscasecmp(const TCHAR *, const TCHAR *);
Modified: trunk/clucene/src/CLucene/config/utf8.cpp
===================================================================
--- trunk/clucene/src/CLucene/config/utf8.cpp 2006-06-11 07:16:00 UTC (rev 427)
+++ trunk/clucene/src/CLucene/config/utf8.cpp 2006-06-26 00:39:24 UTC (rev 428)
@@ -78,12 +78,12 @@
else \
Len = -1;
-#define UTF8_LENGTH(Char) \
+/*#define UTF8_LENGTH(Char) \
((Char) < 0x80 ? 1 : \
((Char) < 0x800 ? 2 : \
((Char) < 0x10000 ? 3 : \
((Char) < 0x200000 ? 4 : \
- ((Char) < 0x4000000 ? 5 : 6)))))
+ ((Char) < 0x4000000 ? 5 : 6)))))*/
#define UTF8_GET(Result, Chars, Count, Mask, Len) \
Modified: trunk/clucene/src/CLucene/debug/condition.cpp
===================================================================
--- trunk/clucene/src/CLucene/debug/condition.cpp 2006-06-11 07:16:00 UTC (rev 427)
+++ trunk/clucene/src/CLucene/debug/condition.cpp 2006-06-26 00:39:24 UTC (rev 428)
@@ -1,18 +1,9 @@
-/**
- * Copyright 2003-2006 The Apache Software Foundation
- *
- * Licensed under the Apache License, Version 2.0 (the "License");
- * you may not use this file except in compliance with the License.
- * You may obtain a copy of the License at
- *
- * http://www.apache.org/licenses/LICENSE-2.0
- *
- * Unless required by applicable law or agreed to in writing, software
- * distributed under the License is distributed on an "AS IS" BASIS,
- * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
- * See the License for the specific language governing permissions and
- * limitations under the License.
- */
+/*------------------------------------------------------------------------------
+* Copyright (C) 2003-2006 Ben van Klinken and the CLucene Team
+*
+* Distributable under the terms of either the Apache License (Version 2.0) or
+* the GNU Lesser General Public License, as specified in the COPYING file.
+------------------------------------------------------------------------------*/
#include "CLucene/StdHeader.h"
#include "condition.h"
#include "CLucene/util/Misc.h"
Modified: trunk/clucene/src/CLucene/debug/condition.h
===================================================================
--- trunk/clucene/src/CLucene/debug/condition.h 2006-06-11 07:16:00 UTC (rev 427)
+++ trunk/clucene/src/CLucene/debug/condition.h 2006-06-26 00:39:24 UTC (rev 428)
@@ -1,18 +1,9 @@
-/**
- * Copyright 2003-2006 The Apache Software Foundation
- *
- * Licensed under the Apache License, Version 2.0 (the "License");
- * you may not use this file except in compliance with the License.
- * You may obtain a copy of the License at
- *
- * http://www.apache.org/licenses/LICENSE-2.0
- *
- * Unless required by applicable law or agreed to in writing, software
- * distributed under the License is distributed on an "AS IS" BASIS,
- * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
- * See the License for the specific language governing permissions and
- * limitations under the License.
- */
+/*------------------------------------------------------------------------------
+* Copyright (C) 2003-2006 Ben van Klinken and the CLucene Team
+*
+* Distributable under the terms of either the Apache License (Version 2.0) or
+* the GNU Lesser General Public License, as specified in the COPYING file.
+------------------------------------------------------------------------------*/
#ifndef __CONDITION_H
#define __CONDITION_H
Modified: trunk/clucene/src/CLucene/debug/error.cpp
===================================================================
--- trunk/clucene/src/CLucene/debug/error.cpp 2006-06-11 07:16:00 UTC (rev 427)
+++ trunk/clucene/src/CLucene/debug/error.cpp 2006-06-26 00:39:24 UTC (rev 428)
@@ -1,20 +1,10 @@
-/**
- * Copyright 2003-2006 The Apache Software Foundation
- *
- * Licensed under the Apache License, Version 2.0 (the "License");
- * you may not use this file except in compliance with the License.
- * You may obtain a copy of the License at
- *
- * http://www.apache.org/licenses/LICENSE-2.0
- *
- * Unless required by applicable law or agreed to in writing, software
- * distributed under the License is distributed on an "AS IS" BASIS,
- * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
- * See the License for the specific language governing permissions and
- * limitations under the License.
- */
+/*------------------------------------------------------------------------------
+* Copyright (C) 2003-2006 Ben van Klinken and the CLucene Team
+*
+* Distributable under the terms of either the Apache License (Version 2.0) or
+* the GNU Lesser General Public License, as specified in the COPYING file.
+------------------------------------------------------------------------------*/
#include "CLucene/StdHeader.h"
-#include "CLucene/index/Term.h"
CL_NS_USE(util)
@@ -72,8 +62,9 @@
#ifndef _ASCII
CLuceneError::CLuceneError(int num, const TCHAR* str, bool ownstr)
{
- _twhat=STRDUP_TtoT(str);
+ error_number = 0;
_awhat=NULL;
+ _twhat=STRDUP_TtoT(str);
if ( ownstr )
_CLDELETE_CARRAY(str);
}
Modified: trunk/clucene/src/CLucene/debug/error.h
===================================================================
--- trunk/clucene/src/CLucene/debug/error.h 2006-06-11 07:16:00 UTC (rev 427)
+++ trunk/clucene/src/CLucene/debug/error.h 2006-06-26 00:39:24 UTC (rev 428)
@@ -1,18 +1,9 @@
-/**
- * Copyright 2003-2006 The Apache Software Foundation
- *
- * Licensed under the Apache License, Version 2.0 (the "License");
- * you may not use this file except in compliance with the License.
- * You may obtain a copy of the License at
- *
- * http://www.apache.org/licenses/LICENSE-2.0
- *
- * Unless required by applicable law or agreed to in writing, software
- * distributed under the License is distributed on an "AS IS" BASIS,
- * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
- * See the License for the specific language governing permissions and
- * limitations under the License.
- */
+/*------------------------------------------------------------------------------
+* Copyright (C) 2003-2006 Ben van Klinken and the CLucene Team
+*
+* Distributable under the terms of either the Apache License (Version 2.0) or
+* the GNU Lesser General Public License, as specified in the COPYING file.
+------------------------------------------------------------------------------*/
#ifndef _lucene_debug_error_
#define _lucene_debug_error_
Modified: trunk/clucene/src/CLucene/debug/lucenebase.h
===================================================================
--- trunk/clucene/src/CLucene/debug/lucenebase.h 2006-06-11 07:16:00 UTC (rev 427)
+++ trunk/clucene/src/CLucene/debug/lucenebase.h 2006-06-26 00:39:24 UTC (rev 428)
@@ -1,18 +1,9 @@
-/**
- * Copyright 2003-2006 The Apache Software Foundation
- *
- * Licensed under the Apache License, Version 2.0 (the "License");
- * you may not use this file except in compliance with the License.
- * You may obtain a copy of the License at
- *
- * http://www.apache.org/licenses/LICENSE-2.0
- *
- * Unless required by applicable law or agreed to in writing, software
- * distributed under the License is distributed on an "AS IS" BASIS,
- * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
- * See the License for the specific language governing permissions and
- * limitations under the License.
- */
+/*------------------------------------------------------------------------------
+* Copyright (C) 2003-2006 Ben van Klinken and the CLucene Team
+*
+* Distributable under the terms of either the Apache License (Version 2.0) or
+* the GNU Lesser General Public License, as specified in the COPYING file.
+------------------------------------------------------------------------------*/
#ifndef _lucene_debug_lucenebase_
#define _lucene_debug_lucenebase_
@@ -22,51 +13,63 @@
CL_NS_DEF(debug)
+//Lucenebase is the superclass of all clucene objects. It provides
+//memory debugging tracking and/or reference counting
class LuceneBase{
public:
-#ifdef LUCENE_ENABLE_LUCENEBASE
- static void* operator new (size_t size, char const * file, int_t line);
+#ifdef LUCENE_ENABLE_MEMLEAKTRACKING
static void* operator new (size_t size);
- static void operator delete (void *p, char const * file, int_t line);
static void operator delete (void *p);
- static int_t __cl_GetUnclosedObjectsCount(); ///< gets the number of unclosed objects
- static const char* __cl_GetUnclosedObject(int_t item); ///< get the name of the nth unclosed object
- static TCHAR* __cl_GetUnclosedObjects(); ///< get a string with the names of the unclosed objects
+ int32_t __cl_initnum; ///< The order that the object was created at. This is then used to do a lookup in the objects list
+
+ static void* operator new (size_t size, char const * file, int32_t line);
+ static void operator delete (void *p, char const * file, int32_t line);
+
+ static void* __cl_voidpadd(void* data, const char* file, int line, size_t size); ///<add arbitary data to the lucenbase_list and returns the same data
+ static void __cl_voidpremove(const void* data, const char* file, int line);///<remove arbitary data to the lucenbase_list
+ static void __cl_unregister(const void* obj); ///<un register object from the mem leak and ref count system
+
+ static int32_t __cl_GetUnclosedObjectsCount(); ///< gets the number of unclosed objects
+ static const char* __cl_GetUnclosedObject(int32_t item); ///< get the name of the nth unclosed object
+ static char* __cl_GetUnclosedObjects(); ///< get a string with the names of the unclosed objects
static void __cl_PrintUnclosedObjects(); ///< print unclosed objects to the stdout
- static void __cl_ClearMemory(); ///< delete memory in refcounted list
+
+ ///This will clear memory relating to refcounting
+ ///other tools can be used to more accurately identify
+ ///memory leaks. This should only be called just
+ ///before closing, and after retrieving the
+ ///unclosed object list
+ static void __cl_ClearMemory();
- int_t __cl_initnum; ///< The order that the object was created at.
-#else
- static void* operator new (size_t size);
- static void operator delete (void *p);
-#endif //LUCENE_ENABLE_LUCENEBASE
-#ifdef LUCENE_ENABLE_REFCOUNT
+#endif //LUCENE_ENABLE_MEMLEAKTRACKING
+
int __cl_refcount;
LuceneBase(){
- __cl_refcount=0;
+ __cl_refcount=1;
}
- int __cl_getref(){
+ inline int __cl_getref(){
return __cl_refcount;
}
- void __cl_addref(){
+ inline int __cl_addref(){
__cl_refcount++;
+ return __cl_refcount;
}
- int __cl_decref(){
- return --__cl_refcount;
+ inline int __cl_decref(){
+ __cl_refcount--;
+ return __cl_refcount;
}
-#endif //LUCENE_ENABLE_REFCOUNT
+ virtual ~LuceneBase(){};
};
-#ifdef LUCENE_ENABLE_REFCOUNT
- //we use this in the _CLDELETE macro
-#ifdef _DEBUG
- bool lucene_refCount_CanDelete(const LuceneBase* d, const char* file, const int_t line);
- bool lucene_refCount_CanDelete(const void* d, const char* file, const int_t line);
-#else
- bool lucene_refCount_CanDelete(const void* d);
- bool lucene_refCount_CanDelete(const LuceneBase* d);
-#endif
-#endif
+class LuceneVoidBase{
+ public:
+ #ifdef _DEBUG
+ //a compile time check to make sure that _CLDELETE and _CLDECDELETE is being
+ //used correctly.
+ int dummy__see_mem_h_for_details;
+ #endif
+ virtual ~LuceneVoidBase(){};
+};
CL_NS_END
#endif //_lucene_debug_lucenebase_
Modified: trunk/clucene/src/CLucene/debug/mem.h
===================================================================
--- trunk/clucene/src/CLucene/debug/mem.h 2006-06-11 07:16:00 UTC (rev 427)
+++ trunk/clucene/src/CLucene/debug/mem.h 2006-06-26 00:39:24 UTC (rev 428)
@@ -1,25 +1,17 @@
-/**
- * Copyright 2003-2006 The Apache Software Foundation
- *
- * Licensed under the Apache License, Version 2.0 (the "License");
- * you may not use this file except in compliance with the License.
- * You may obtain a copy of the License at
- *
- * http://www.apache.org/licenses/LICENSE-2.0
- *
- * Unless required by applicable law or agreed to in writing, software
- * distributed under the License is distributed on an "AS IS" BASIS,
- * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
- * See the License for the specific language governing permissions and
- * limitations under the License.
- */
-#ifndef _lucene_debug_lucenebase_
-#define _lucene_debug_lucenebase_
+/*------------------------------------------------------------------------------
+* Copyright (C) 2003-2006 Ben van Klinken and the CLucene Team
+*
+* Distributable under the terms of either the Apache License (Version 2.0) or
+* the GNU Lesser General Public License, as specified in the COPYING file.
+------------------------------------------------------------------------------*/
+#ifndef _lucene_debug_mem_h
+#define _lucene_debug_mem_h
#if defined(_LUCENE_PRAGMA_ONCE)
# pragma once
#endif
+#include "lucenebase.h"
//some memory pool definitions
#ifdef LUCENE_ENABLE_MEMORY_POOL
@@ -104,65 +96,4 @@
//into a LuceneBase*.
#define _CLVDELETE(x) if(x!=NULL){delete x; x=NULL;}
-
-CL_NS_DEF(debug)
-class LuceneVoidBase{
- public:
- #ifdef _DEBUG
- //a compile time check to make sure that _CLDELETE and _CLDECDELETE is being
- //used correctly.
- int dummy__see_mem_h_for_details;
- #endif
- virtual ~LuceneVoidBase(){};
-};
-
-//Lucenebase is the superclass of all clucene objects. It provides
-//memory debugging tracking and/or reference counting
-class LuceneBase{
-public:
-#ifdef LUCENE_ENABLE_MEMLEAKTRACKING
- static void* operator new (size_t size);
- static void operator delete (void *p);
- int32_t __cl_initnum; ///< The order that the object was created at. This is then used to do a lookup in the objects list
-
- static void* operator new (size_t size, char const * file, int32_t line);
- static void operator delete (void *p, char const * file, int32_t line);
-
- static void* __cl_voidpadd(void* data, const char* file, int line, size_t size); ///<add arbitary data to the lucenbase_list and returns the same data
- static void __cl_voidpremove(const void* data, const char* file, int line);///<remove arbitary data to the lucenbase_list
- static void __cl_unregister(const void* obj); ///<un register object from the mem leak and ref count system
-
- static int32_t __cl_GetUnclosedObjectsCount(); ///< gets the number of unclosed objects
- static const char* __cl_GetUnclosedObject(int32_t item); ///< get the name of the nth unclosed object
- static TCHAR* __cl_GetUnclosedObjects(); ///< get a string with the names of the unclosed objects
- static void __cl_PrintUnclosedObjects(); ///< print unclosed objects to the stdout
-
- ///This will clear memory relating to refcounting
- ///other tools can be used to more accurately identify
- ///memory leaks. This should only be called just
- ///before closing, and after retrieving the
- ///unclosed object list
- static void __cl_ClearMemory();
-
-#endif //LUCENE_ENABLE_MEMLEAKTRACKING
-
- int __cl_refcount;
- LuceneBase(){
- __cl_refcount=1;
- }
- inline int __cl_getref(){
- return __cl_refcount;
- }
- inline int __cl_addref(){
- __cl_refcount++;
- return __cl_refcount;
- }
- inline int __cl_decref(){
- __cl_refcount--;
- return __cl_refcount;
- }
- virtual ~LuceneBase(){};
-};
-
-CL_NS_END
#endif //_lucene_debug_lucenebase_
Modified: trunk/clucene/src/CLucene/debug/mempool.cpp
===================================================================
--- trunk/clucene/src/CLucene/debug/mempool.cpp 2006-06-11 07:16:00 UTC (rev 427)
+++ trunk/clucene/src/CLucene/debug/mempool.cpp 2006-06-26 00:39:24 UTC (rev 428)
@@ -1,18 +1,9 @@
-/**
- * Copyright 2003-2006 The Apache Software Foundation
- *
- * Licensed under the Apache License, Version 2.0 (the "License");
- * you may not use this file except in compliance with the License.
- * You may obtain a copy of the License at
- *
- * http://www.apache.org/licenses/LICENSE-2.0
- *
- * Unless required by applicable law or agreed to in writing, software
- * distributed under the License is distributed on an "AS IS" BASIS,
- * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
- * See the License for the specific language governing permissions and
- * limitations under the License.
- */
+/*------------------------------------------------------------------------------
+* Copyright (C) 2003-2006 Ben van Klinken and the CLucene Team
+*
+* Distributable under the terms of either the Apache License (Version 2.0) or
+* the GNU Lesser General Public License, as specified in the COPYING file.
+------------------------------------------------------------------------------*/
#include "CLucene/StdHeader.h"
#ifdef LUCENE_ENABLE_MEMORY_POOL
Modified: trunk/clucene/src/CLucene/debug/memtracking.cpp
===================================================================
--- trunk/clucene/src/CLucene/debug/memtracking.cpp 2006-06-11 07:16:00 UTC (rev 427)
+++ trunk/clucene/src/CLucene/debug/memtracking.cpp 2006-06-26 00:39:24 UTC (rev 428)
@@ -1,25 +1,14 @@
-/**
- * Copyright 2003-2006 The Apache Software Foundation
- *
- * Licensed under the Apache License, Version 2.0 (the "License");
- * you may not use this file except in compliance with the License.
- * You may obtain a copy of the License at
- *
- * http://www.apache.org/licenses/LICENSE-2.0
- *
- * Unless required by applicable law or agreed to in writing, software
- * distributed under the License is distributed on an "AS IS" BASIS,
- * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
- * See the License for the specific language governing permissions and
- * limitations under the License.
- */
+/*------------------------------------------------------------------------------
+* Copyright (C) 2003-2006 Ben van Klinken and the CLucene Team
+*
+* Distributable under the terms of either the Apache License (Version 2.0) or
+* the GNU Lesser General Public License, as specified in the COPYING file.
+------------------------------------------------------------------------------*/
#include "CLucene/StdHeader.h"
-
-#include "CLucene/util/StringBuffer.h"
#include "CLucene/util/Misc.h"
-bool _lucene_disable_debuglogging = true; //if LUCENE_ENABLE_CONSTRUCTOR_LOG is on, dont do log if this is true
-bool _lucene_run_objectcheck = false; //run a memory check before deleting objects
+static bool _lucene_disable_debuglogging = true; //if LUCENE_ENABLE_CONSTRUCTOR_LOG is on, dont do log if this is true
+static bool _lucene_run_objectcheck = false; //run a memory check before deleting objects
int _lucene_counter_break = -1; //to break at this item, change this
//and put break points at points below
@@ -252,52 +241,48 @@
////////////////////////////////////////////////////////////
//static
void __internalcl_PrintUnclosedObject(bool isObject, string& sb,_pointers* bp,_file* bf, bool print){
- sb.append(_T(" ") );
-
+ TCHAR ttmp[100];
+ char atmp[100];
+
+ sb.append(" ");
{
- char tmp[100];
- itoa(bp->initnumber,tmp,10);
- sb.append(tmp);
+ _i64tot(bp->initnumber,ttmp,10);
+ STRCPY_TtoA(atmp,ttmp,100);
+ sb.append(atmp);
}
if ( isObject ){
- sb.append(_T("(obj). "));
+ sb.append("(obj). ");
}else{
- sb.append(_T(". "));
+ sb.append(". ");
}
-
- TCHAR tmp[CL_MAX_DIR];
- /*if ( lb->__cl_initfile < 0 || lb->__cl_initfile >= LuceneBase_Files.size() )
- _tcscpy(tmp,_T("unknown (filename lost), use number to identify object instead"));
- else
- STRCPY_AtoT(tmp,LuceneBase_Files.at(lb->__cl_initfile),CL_MAX_DIR);*/
- STRCPY_AtoT(tmp,bf->value,CL_MAX_DIR);
- sb.append(tmp);
-
- sb.append(_T(", line ") );
+ sb.append(bf->value);
+ sb.append(", line ");
{
- char tmp[100];
- itoa(bp->initline,tmp,10);
- sb.append(tmp);
+ _i64tot(bp->initline,ttmp,10);
+ STRCPY_TtoA(atmp,ttmp,100);
+ sb.append(atmp);
}
- sb.append(_T("\n"));
+ sb.append("\n");
if ( print && sb.length() > 0 ){
- _tprintf(sb.c_str());
- sb.clear();
+ printf("%s\n", sb.c_str());
+ sb = "";
}
}
-TCHAR* __internalcl_GetUnclosedObjects(bool print){
+char* __internalcl_GetUnclosedObjects(bool print){
+ TCHAR ttmp[100];
+ char atmp[100];
SCOPED_LOCK_MUTEX(memleak_lock)
string sb;
bool unknowns = false;
if ( LuceneBase_Pointers.size() > 0 ){
{
- char tmp[100];
- itoa((int32_t)LuceneBase_Pointers.size(),tmp,10);
- sb.append(tmp);
+ _i64tot(LuceneBase_Pointers.size(),ttmp,10);
+ STRCPY_TtoA(atmp,ttmp,100);
+ sb.append(atmp);
}
- sb.append(_T(" clucene objects are still open\n"));
+ sb.append(" clucene objects are still open\n");
defPointer::iterator itr = LuceneBase_Pointers.begin();
while ( itr != LuceneBase_Pointers.end() ){
@@ -308,7 +293,7 @@
unknowns = true;
__internalcl_PrintUnclosedObject(true, sb,bp,bf,print);
- itr++;
+ ++itr;
}
defVoid::iterator itr2 = LuceneBase_Voids.begin();
@@ -325,20 +310,20 @@
}
if ( unknowns == true ){
- sb.append(_T("*** Some memory was not created with _CLNEW and was not tracked... ***\n") );
- sb.append(_T("*** Use _CLNEW instead of new when creating CLucene objects ***\n") );
- sb.append(_T("*** Memory may also have not been freed in the current context ***\n") );
+ sb.append("*** Some memory was not created with _CLNEW and was not tracked... ***\n");
+ sb.append("*** Use _CLNEW instead of new when creating CLucene objects ***\n");
+ sb.append("*** Memory may also have not been freed in the current context ***\n");
}
if ( print ){
if ( sb.length() > 0 ){
- _tprintf(sb.c_str());
- sb.clear();
+ printf("%s\n", sb.c_str());
+ sb = "";
}
return NULL;
}else{
if ( sb.length() > 0 )
- return stringDuplicate(sb.c_str());
+ return STRDUP_AtoA(sb.c_str());
else
return NULL;
}
@@ -356,7 +341,7 @@
LuceneBase_Pointers.clear();
LuceneBase_Voids.clear();
}
-TCHAR* LuceneBase::__cl_GetUnclosedObjects(){
+char* LuceneBase::__cl_GetUnclosedObjects(){
return __internalcl_GetUnclosedObjects(false);
}
//static
@@ -370,7 +355,7 @@
defPointer::iterator itr=LuceneBase_Pointers.begin();
int32_t i=0;
for ( ;itr!=LuceneBase_Pointers.end() && i<item ;itr++ ){
- i++;
+ ++i;
}
if ( itr != LuceneBase_Pointers.end() )
return itr->second->file->value;
Modified: trunk/clucene/src/CLucene/debug/pool.h
===================================================================
--- trunk/clucene/src/CLucene/debug/pool.h 2006-06-11 07:16:00 UTC (rev 427)
+++ trunk/clucene/src/CLucene/debug/pool.h 2006-06-26 00:39:24 UTC (rev 428)
@@ -1,18 +1,9 @@
-/**
- * Copyright 2003-2006 The Apache Software Foundation
- *
- * Licensed under the Apache License, Version 2.0 (the "License");
- * you may not use this file except in compliance with the License.
- * You may obtain a copy of the License at
- *
- * http://www.apache.org/licenses/LICENSE-2.0
- *
- * Unless required by applicable law or agreed to in writing, software
- * distributed under the License is distributed on an "AS IS" BASIS,
- * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
- * See the License for the specific language governing permissions and
- * limitations under the License.
- */
+/*------------------------------------------------------------------------------
+* Copyright (C) 2003-2006 Ben van Klinken and the CLucene Team
+*
+* Distributable under the terms of either the Apache License (Version 2.0) or
+* the GNU Lesser General Public License, as specified in the COPYING file.
+------------------------------------------------------------------------------*/
#ifndef _lucene_debug_pool_
#define _lucene_debug_pool_
//this code is based on the boost memory pool library
Modified: trunk/clucene/src/CLucene/document/DateField.cpp
===================================================================
--- trunk/clucene/src/CLucene/document/DateField.cpp 2006-06-11 07:16:00 UTC (rev 427)
+++ trunk/clucene/src/CLucene/document/DateField.cpp 2006-06-26 00:39:24 UTC (rev 428)
@@ -1,18 +1,9 @@
-/**
- * Copyright 2003-2006 The Apache Software Foundation
- *
- * Licensed under the Apache License, Version 2.0 (the "License");
- * you may not use this file except in compliance with the License.
- * You may obtain a copy of the License at
- *
- * http://www.apache.org/licenses/LICENSE-2.0
- *
- * Unless required by applicable law or agreed to in writing, software
- * distributed under the License is distributed on an "AS IS" BASIS,
- * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
- * See the License for the specific language governing permissions and
- * limitations under the License.
- */
+/*------------------------------------------------------------------------------
+* Copyright (C) 2003-2006 Ben van Klinken and the CLucene Team
+*
+* Distributable under the terms of either the Apache License (Version 2.0) or
+* the GNU Lesser General Public License, as specified in the COPYING file.
+------------------------------------------------------------------------------*/
#include "CLucene/StdHeader.h"
#include "DateField.h"
@@ -20,48 +11,46 @@
CL_NS_USE(util)
CL_NS_DEF(document)
- DateField::~DateField(){
- }
+DateField::~DateField(){
+}
- TCHAR* DateField::timeToString(const int64_t time) {
- if (time < 0)
- _CLTHROWA (CL_ERR_IllegalArgument,"time too early");
- /* DSR:2004.10.28: */
- /* Check for too-late time here rather than after the _i64tot call
- ** so as to avoid buffer overflow potential. */
- if (time > DATEFIELD_DATE_MAX)
- _CLTHROWA (CL_ERR_IllegalArgument, "time too late (past DATEFIELD_DATE_MAX");
+TCHAR* DateField::timeToString(const int64_t time) {
+ if (time < 0)
+ _CLTHROWA (CL_ERR_IllegalArgument,"time too early"); //todo: make richer error
+ if (time > DATEFIELD_DATE_MAX)
+ _CLTHROWA (CL_ERR_IllegalArgument, "time too late (past DATEFIELD_DATE_MAX"); //todo: make richer error
+
TCHAR* buf = _CL_NEWARRAY(TCHAR,DATEFIELD_DATE_LEN + 1);
- _i64tot(time, buf, 36);
- int32_t bufLen = _tcslen(buf);
-
- CND_PRECONDITION (bufLen <= DATEFIELD_DATE_LEN, "timeToString length is greater than 9");
-
- /* Supply leading zeroes if necessary. */
- if (bufLen < DATEFIELD_DATE_LEN) {
- const int32_t nMissingZeroes = DATEFIELD_DATE_LEN - bufLen;
- /* Move buffer contents forward to make room for leading zeroes. */
- for (int32_t i = DATEFIELD_DATE_LEN - 1; i >= nMissingZeroes; i--)
- buf[i] = buf[i - nMissingZeroes];
-
+ _i64tot(time, buf, 36);
+ int32_t bufLen = _tcslen(buf);
+
+ CND_PRECONDITION (bufLen <= DATEFIELD_DATE_LEN, "timeToString length is greater than 9");
+
+ /* Supply leading zeroes if necessary. */
+ if (bufLen < DATEFIELD_DATE_LEN) {
+ const int32_t nMissingZeroes = DATEFIELD_DATE_LEN - bufLen;
+ /* Move buffer contents forward to make room for leading zeroes. */
+ for (int32_t i = DATEFIELD_DATE_LEN - 1; i >= nMissingZeroes; i--)
+ buf[i] = buf[i - nMissingZeroes];
+
{// MSVC6 scoping fix
/* Insert leading zeroes. */
- for (int32_t i = 0; i < nMissingZeroes; i++)
- buf[i] = '0';
+ for (int32_t i = 0; i < nMissingZeroes; i++)
+ buf[i] = '0';
}
+
+ buf[DATEFIELD_DATE_LEN] = 0;
+ }
+
+ CND_PRECONDITION (_tcslen(buf) == DATEFIELD_DATE_LEN, "timeToString return is not equal to 9");
+
+ return buf;
+}
- buf[DATEFIELD_DATE_LEN] = 0;
- }
+int64_t DateField::stringToTime(const TCHAR* time) {
+ TCHAR* end;
+ return _tcstoi64(time, &end, 36);
+}
- CND_PRECONDITION (_tcslen(buf) == DATEFIELD_DATE_LEN, "timeToString return is not equal to 9");
-
- return buf;
- }
-
- int64_t DateField::stringToTime(const TCHAR* time) {
- TCHAR* end;
- return _tcstoi64(time, &end, 36);
- }
-
CL_NS_END
Modified: trunk/clucene/src/CLucene/document/DateField.h
===================================================================
--- trunk/clucene/src/CLucene/document/DateField.h 2006-06-11 07:16:00 UTC (rev 427)
+++ trunk/clucene/src/CLucene/document/DateField.h 2006-06-26 00:39:24 UTC (rev 428)
@@ -1,18 +1,9 @@
-/**
- * Copyright 2003-2006 The Apache Software Foundation
- *
- * Licensed under the Apache License, Version 2.0 (the "License");
- * you may not use this file except in compliance with the License.
- * You may obtain a copy of the License at
- *
- * http://www.apache.org/licenses/LICENSE-2.0
- *
- * Unless required by applicable law or agreed to in writing, software
- * distributed under the License is distributed on an "AS IS" BASIS,
- * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
- * See the License for the specific language governing permissions and
- * limitations under the License.
- */
+/*------------------------------------------------------------------------------
+* Copyright (C) 2003-2006 Ben van Klinken and the CLucene Team
+*
+* Distributable under the terms of either the Apache License (Version 2.0) or
+* the GNU Lesser General Public License, as specified in the COPYING file.
+------------------------------------------------------------------------------*/
#ifndef _lucene_document_DateField_
#define _lucene_document_DateField_
@@ -28,41 +19,40 @@
#define DATEFIELD_DATE_LEN 9 ////Long.toString(DATEFIELD_DATE_MAX, Character.MAX_RADIX).length()
- /**
- * Provides support for converting dates to strings and vice-versa.
- * The strings are structured so that lexicographic sorting orders by date,
- * which makes them suitable for use as field values and search terms.
- *
- * <P>
- * Note that you do not have to use this class, you can just save your
- * dates as strings if lexicographic sorting orders them by date. This is
- * the case for example for dates like <code>yyyy-mm-dd hh:mm:ss</code>
- * (of course you can leave out the delimiter characters to save some space).
- * The advantage with using such a format is that you can easily save dates
- * with the required granularity, e.g. leaving out seconds. This saves memory
- * when searching with a RangeQuery or PrefixQuery, as Lucene
- * expands these queries to a BooleanQuery with potentially very many terms.
- *
- * <P>
- * Note: dates before 1970 cannot be used, and therefore cannot be
- * indexed when using this class.
- */
- class DateField :LUCENE_BASE {
- private:
- static void initDS();
- public:
- ~DateField();
-
- /**
- * Converts a millisecond time to a string suitable for indexing.
- * @throws RuntimeException if the time specified in the
- * method argument is negative, that is, before 1970
- */
- static TCHAR* timeToString(const int64_t time);
-
- /** Converts a string-encoded date into a millisecond time. */
- static int64_t stringToTime(const TCHAR* s);
-
- };
+/**
+* Provides support for converting dates to strings and vice-versa.
+* The strings are structured so that lexicographic sorting orders by date,
+* which makes them suitable for use as field values and search terms.
+*
+* <P>Note that this class saves dates with millisecond granularity,
+* which is bad for {@link RangeQuery} and {@link PrefixQuery}, as those
+* queries are expanded to a BooleanQuery with a potentially large number
+* of terms when searching. Thus you might want to use
+* {@link DateTools} instead.
+*
+* <P>
+* Note: dates before 1970 cannot be used, and therefore cannot be
+* indexed when using this class. See {@link DateTools} for an
+* alternative without such a limitation.
+*
+* @deprecated If you build a new index, use {@link DateTools} instead. This class is included for use with existing
+* indices and will be removed in a future release.
+*/
+class DateField :LUCENE_BASE {
+private:
+ static void initDS();
+public:
+ ~DateField();
+
+ /**
+ * Converts a millisecond time to a string suitable for indexing.
+ * @throws RuntimeException if the time specified in the
+ * method argument is negative, that is, before 1970
+ */
+ static TCHAR* timeToString(const int64_t time);
+
+ /** Converts a string-encoded date into a millisecond time. */
+ static int64_t stringToTime(const TCHAR* s);
+};
CL_NS_END
#endif
Modified: trunk/clucene/src/CLucene/document/Document.cpp
===================================================================
--- trunk/clucene/src/CLucene/document/Document.cpp 2006-06-11 07:16:00 UTC (rev 427)
+++ trunk/clucene/src/CLucene/document/Document.cpp 2006-06-26 00:39:24 UTC (rev 428)
@@ -1,18 +1,9 @@
-/**
- * Copyright 2003-2006 The Apache Software Foundation
- *
- * Licensed under the Apache License, Version 2.0 (the "License");
- * you may not use this file except in compliance with the License.
- * You may obtain a copy of the License at
- *
- * http://www.apache.org/licenses/LICENSE-2.0
- *
- * Unless required by applicable law or agreed to in writing, software
- * distributed under the License is distributed on an "AS IS" BASIS,
- * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
- * See the License for the specific language governing permissions and
- * limitations under the License.
- */
+/*------------------------------------------------------------------------------
+* Copyright (C) 2003-2006 Ben van Klinken and the CLucene Team
+*
+* Distributable under the terms of either the Apache License (Version 2.0) or
+* the GNU Lesser General Public License, as specified in the COPYING file.
+------------------------------------------------------------------------------*/
#include "CLucene/StdHeader.h"
#include "Document.h"
#include "Field.h"
@@ -130,13 +121,12 @@
const TCHAR* Document::get(const TCHAR* field) const {
CND_PRECONDITION(field != NULL, "field is NULL");
-
Field *f = getField(field);
if (f!=NULL)
- return f->stringValue();
+ return f->stringValue(); //this returns null it is a binary(reader)
else
return NULL;
- } ///<returns reference
+ }
DocumentFieldEnumeration* Document::fields() const {
return _CLNEW DocumentFieldEnumeration(fieldList);
@@ -210,8 +200,9 @@
DocumentFieldEnumeration* it = fields();
int32_t count = 0;
while ( it->hasMoreElements() ){
+ Field* f = it->nextElement();
//cannot use interning here, because name is probably not interned
- if ( _tcscmp(it->nextElement()->name(),name) == 0 )
+ if ( _tcscmp(f->name(),name) == 0 && f->stringValue() != NULL )
count++;
}
_CLDELETE(it);
@@ -225,7 +216,7 @@
int32_t i=0;
while ( it->hasMoreElements() ){
Field* fld=it->nextElement();
- if ( _tcscmp(fld->name(),name)== 0 ){
+ if ( _tcscmp(fld->name(),name)== 0 && fld->stringValue() != NULL ){
ret[i] = stringDuplicate(fld->stringValue());
i++;
}
Modified: trunk/clucene/src/CLucene/document/Document.h
===================================================================
--- trunk/clucene/src/CLucene/document/Document.h 2006-06-11 07:16:00 UTC (rev 427)
+++ trunk/clucene/src/CLucene/document/Document.h 2006-06-26 00:39:24 UTC (rev 428)
@@ -1,18 +1,9 @@
-/**
- * Copyright 2003-2006 The Apache Software Foundation
- *
- * Licensed under the Apache License, Version 2.0 (the "License");
- * you may not use this file except in compliance with the License.
- * You may obtain a copy of the License at
- *
- * http://www.apache.org/licenses/LICENSE-2.0
- *
- * Unless required by applicable law or agreed to in writing, software
- * distributed under the License is distributed on an "AS IS" BASIS,
- * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
- * See the License for the specific language governing permissions and
- * limitations under the License.
- */
+/*------------------------------------------------------------------------------
+* Copyright (C) 2003-2006 Ben van Klinken and the CLucene Team
+*
+* Distributable under the terms of either the Apache License (Version 2.0) or
+* the GNU Lesser General Public License, as specified in the COPYING file.
+------------------------------------------------------------------------------*/
#ifndef _lucene_document_Document_
#define _lucene_document_Document_
@@ -26,135 +17,136 @@
///to using a java List... do we want to do this too?
CL_NS_DEF(document)
- ///\exclude Internal field enumeration
- class DocumentFieldList :LUCENE_BASE{
- public:
- DocumentFieldList(Field* f, DocumentFieldList* n);
- ~DocumentFieldList();
- Field* field;
- DocumentFieldList* next;
- };
+///\exclude Internal field enumeration
+class DocumentFieldList :LUCENE_BASE{
+public:
+ DocumentFieldList(Field* f, DocumentFieldList* n);
+ ~DocumentFieldList();
+ Field* field;
+ DocumentFieldList* next;
+};
- class DocumentFieldEnumeration :LUCENE_BASE{
- private:
- const DocumentFieldList* fields;
- public:
- DocumentFieldEnumeration(const DocumentFieldList* fl);
- ~DocumentFieldEnumeration();
- bool hasMoreElements() const;
- Field* nextElement();
- };
+class DocumentFieldEnumeration :LUCENE_BASE{
+private:
+ const DocumentFieldList* fields;
+public:
+ DocumentFieldEnumeration(const DocumentFieldList* fl);
+ ~DocumentFieldEnumeration();
+ bool hasMoreElements() const;
+ Field* nextElement();
+};
- /** Documents are the unit of indexing and search.
- *
- * A Document is a set of fields. Each field has a name and a textual value.
- * A field may be {@link Field#isStored() stored} with the document, in which
- * case it is returned with search hits on the document. Thus each document
- * should typically contain one or more stored fields which uniquely identify
- * it.
- *
- * <p>Note that fields which are <i>not</i> {@link Field#isStored() stored} are
- * <i>not</i> available in documents retrieved from the index, e.g. with {@link
- * Hits#doc(int32_t)}, {@link Searcher#doc(int32_t)} or {@link
- * IndexReader#document(int32_t)}.
- */
- class Document:LUCENE_BASE {
- private:
- DocumentFieldList* fieldList;
- float_t boost;
- public:
- Document();
- ~Document();
+/** Documents are the unit of indexing and search.
+*
+* A Document is a set of fields. Each field has a name and a textual value.
+* A field may be {@link Field#isStored() stored} with the document, in which
+* case it is returned with search hits on the document. Thus each document
+* should typically contain one or more stored fields which uniquely identify
+* it.
+*
+* <p>Note that fields which are <i>not</i> {@link Field#isStored() stored} are
+* <i>not</i> available in documents retrieved from the index, e.g. with {@link
+* Hits#doc(int32_t)}, {@link Searcher#doc(int32_t)} or {@link
+* IndexReader#document(int32_t)}.
+*/
+class Document:LUCENE_BASE {
+private:
+ DocumentFieldList* fieldList;
+ float_t boost;
+public:
+ Document();
+ ~Document();
+
+ /**
+ * <p>Adds a field to a document. Several fields may be added with
+ * the same name. In this case, if the fields are indexed, their text is
+ * treated as though appended for the purposes of search.</p>
+ * <p> Note that add like the removeField(s) methods only makes sense
+ * prior to adding a document to an index. These methods cannot
+ * be used to change the content of an existing index! In order to achieve this,
+ * a document has to be deleted from an index and a new changed version of that
+ * document has to be added.</p>
+ *
+ */
+ void add(Field& field);
+ /** Returns a field with the given name if any exist in this document, or
+ * null. If multiple fields exists with this name, this method returns the
+ * first value added.
+ * Note: name is case sensitive
+ */
+ Field* getField(const TCHAR* name) const;
+
+ /** Returns the string value of the field with the given name if any exist in
+ * this document, or null. If multiple fields exist with this name, this
+ * method returns the first value added. If only binary fields with this name
+ * exist, returns null.
+ */
+ const TCHAR* get(const TCHAR* field) const;
+
+ /** Returns an Enumeration of all the fields in a document. */
+ DocumentFieldEnumeration* fields() const;
+ /** Prints the fields of a document for human consumption. */
+ TCHAR* toString() const;
+
+ /** Sets a boost factor for hits on any field of this document. This value
+ * will be multiplied into the score of all hits on this document.
+ *
+ * <p>Values are multiplied into the value of {@link Field#getBoost()} of
+ * each field in this document. Thus, this method in effect sets a default
+ * boost for the fields of this document.
+ *
+ * @see Field#setBoost(float_t)
+ */
+ void setBoost(float_t boost);
+
+ /** Returns the boost factor for hits on any field of this document.
+ *
+ * <p>The default value is 1.0.
+ *
+ * <p>Note: This value is not stored directly with the document in the index.
+ * Documents returned from {@link IndexReader#document(int32_t)} and
+ * {@link Hits#doc(int32_t)} may thus not have the same value present as when
+ * this document was indexed.
+ *
+ * @see #setBoost(float_t)
+ */
+ float_t getBoost() const;
+
+ /**
+ * <p>Removes field with the specified name from the document.
+ * If multiple fields exist with this name, this method removes the first field that has been added.
+ * If there is no field with the specified name, the document remains unchanged.</p>
+ * <p> Note that the removeField(s) methods like the add method only make sense
+ * prior to adding a document to an index. These methods cannot
+ * be used to change the content of an existing index! In order to achieve this,
+ * a document has to be deleted from an index and a new changed version of that
+ * document has to be added.</p>
+ * Note: name is case sensitive
+ */
+ void removeField(const TCHAR* name);
+
+ /**
+ * <p>Removes all fields with the given name from the document.
+ * If there is no field with the specified name, the document remains unchanged.</p>
+ * <p> Note that the removeField(s) methods like the add method only make sense
+ * prior to adding a document to an index. These methods cannot
+ * be used to change the content of an existing index! In order to achieve this,
+ * a document has to be deleted from an index and a new changed version of that
+ * document has to be added.</p>
+ * Note: name is case sensitive
+ */
+ void removeFields(const TCHAR* name);
- /**
- * <p>Adds a field to a document. Several fields may be added with
- * the same name. In this case, if the fields are indexed, their text is
- * treated as though appended for the purposes of search.</p>
- * <p> Note that add like the removeField(s) methods only makes sense
- * prior to adding a document to an index. These methods cannot
- * be used to change the content of an existing index! In order to achieve this,
- * a document has to be deleted from an index and a new changed version of that
- * document has to be added.</p>
- *
- */
- void add(Field& field);
- /** Returns a field with the given name if any exist in this document, or
- * null. If multiple fields exists with this name, this method returns the
- * first value added.
- * Note: name is case sensitive
- */
- Field* getField(const TCHAR* name) const;
-
- /** Returns the string value of the field with the given name if any exist in
- * this document, or null. If multiple fields exist with this name, this
- * method returns the first value added.
- * Note: name is case sensitive
- */
- const TCHAR* get(const TCHAR* field) const;
- /// Returns an Enumeration of all the fields in a document.
- DocumentFieldEnumeration* fields() const;
- /** Prints the fields of a document for human consumption. */
- TCHAR* toString() const;
+ /**
+ * Returns an array of values of the field specified as the method parameter.
+ * This method can return <code>null</code>.
+ * Note: name is case sensitive
+ *
+ * @param name the name of the field
+ * @return a <code>String[]</code> of field values
+ */
+ TCHAR** getValues(const TCHAR* name);
+};
- /** Sets a boost factor for hits on any field of this document. This value
- * will be multiplied into the score of all hits on this document.
- *
- * <p>Values are multiplied into the value of {@link Field#getBoost()} of
- * each field in this document. Thus, this method in effect sets a default
- * boost for the fields of this document.
- *
- * @see Field#setBoost(float_t)
- */
- void setBoost(float_t boost);
-
- /** Returns the boost factor for hits on any field of this document.
- *
- * <p>The default value is 1.0.
- *
- * <p>Note: This value is not stored directly with the document in the index.
- * Documents returned from {@link IndexReader#document(int32_t)} and
- * {@link Hits#doc(int32_t)} may thus not have the same value present as when
- * this document was indexed.
- *
- * @see #setBoost(float_t)
- */
- float_t getBoost() const;
-
-
- /**
- * <p>Removes field with the specified name from the document.
- * If multiple fields exist with this name, this method removes the first field that has been added.
- * If there is no field with the specified name, the document remains unchanged.</p>
- * <p> Note that the removeField(s) methods like the add method only make sense
- * prior to adding a document to an index. These methods cannot
- * be used to change the content of an existing index! In order to achieve this,
- * a document has to be deleted from an index and a new changed version of that
- * document has to be added.</p>
- * Note: name is case sensitive
- */
- void removeField(const TCHAR* name);
-
- /**
- * <p>Removes all fields with the given name from the document.
- * If there is no field with the specified name, the document remains unchanged.</p>
- * <p> Note that the removeField(s) methods like the add method only make sense
- * prior to adding a document to an index. These methods cannot
- * be used to change the content of an existing index! In order to achieve this,
- * a document has to be deleted from an index and a new changed version of that
- * document has to be added.</p>
- * Note: name is case sensitive
- */
- void removeFields(const TCHAR* name);
-
- /**
- * Returns an array of values of the field specified as the method parameter.
- * This method can return <code>null</code>.
- * Note: name is case sensitive
- *
- * @param name the name of the field
- * @return a <code>String[]</code> of field values
- */
- TCHAR** getValues(const TCHAR* name);
- };
CL_NS_END
#endif
Modified: trunk/clucene/src/CLucene/document/Field.cpp
===================================================================
--- trunk/clucene/src/CLucene/document/Field.cpp 2006-06-11 07:16:00 UTC (rev 427)
+++ trunk/clucene/src/CLucene/document/Field.cpp 2006-06-26 00:39:24 UTC (rev 428)
@@ -1,18 +1,9 @@
-/**
- * Copyright 2003-2006 The Apache Software Foundation
- *
- * Licensed under the Apache License, Version 2.0 (the "License");
- * you may not use this file except in compliance with the License.
- * You may obtain a copy of the License at
- *
- * http://www.apache.org/licenses/LICENSE-2.0
- *
- * Unless required by applicable law or agreed to in writing, software
- * distributed under the License is distributed on an "AS IS" BASIS,
- * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
- * See the License for the specific language governing permissions and
- * limitations under the License.
- */
+/*------------------------------------------------------------------------------
+* Copyright (C) 2003-2006 Ben van Klinken and the CLucene Team
+*
+* Distributable under the terms of either the Apache License (Version 2.0) or
+* the GNU Lesser General Public License, as specified in the COPYING file.
+------------------------------------------------------------------------------*/
#include "CLucene/StdHeader.h"
#include "CLucene/util/Reader.h"
#include "Field.h"
Modified: trunk/clucene/src/CLucene/document/Field.h
===================================================================
--- trunk/clucene/src/CLucene/document/Field.h 2006-06-11 07:16:00 UTC (rev 427)
+++ trunk/clucene/src/CLucene/document/Field.h 2006-06-26 00:39:24 UTC (rev 428)
@@ -1,18 +1,9 @@
-/**
- * Copyright 2003-2006 The Apache Software Foundation
- *
- * Licensed under the Apache License, Version 2.0 (the "License");
- * you may not use this file except in compliance with the License.
- * You may obtain a copy of the License at
- *
- * http://www.apache.org/licenses/LICENSE-2.0
- *
- * Unless required by applicable law or agreed to in writing, software
- * distributed under the License is distributed on an "AS IS" BASIS,
- * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
- * See the License for the specific language governing permissions and
- * limitations under the License.
- */
+/*------------------------------------------------------------------------------
+* Copyright (C) 2003-2006 Ben van Klinken and the CLucene Team
+*
+* Distributable under the terms of either the Apache License (Version 2.0) or
+* the GNU Lesser General Public License, as specified in the COPYING file.
+------------------------------------------------------------------------------*/
#ifndef _lucene_document_Field_
#define _lucene_document_Field_
Modified: trunk/clucene/src/CLucene/index/CompoundFile.cpp
===================================================================
--- trunk/clucene/src/CLucene/index/CompoundFile.cpp 2006-06-11 07:16:00 UTC (rev 427)
+++ trunk/clucene/src/CLucene/index/CompoundFile.cpp 2006-06-26 00:39:24 UTC (rev 428)
@@ -1,18 +1,9 @@
-/**
- * Copyright 2003-2006 The Apache Software Foundation
- *
- * Licensed under the Apache License, Version 2.0 (the "License");
- * you may not use this file except in compliance with the License.
- * You may obtain a copy of the License at
- *
- * http://www.apache.org/licenses/LICENSE-2.0
- *
- * Unless required by applicable law or agreed to in writing, software
- * distributed under the License is distributed on an "AS IS" BASIS,
- * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
- * See the License for the specific language governing permissions and
- * limitations under the License.
- */
+/*------------------------------------------------------------------------------
+* Copyright (C) 2003-2006 Ben van Klinken and the CLucene Team
+*
+* Distributable under the terms of either the Apache License (Version 2.0) or
+* the GNU Lesser General Public License, as specified in the COPYING file.
+------------------------------------------------------------------------------*/
#include "CLucene/StdHeader.h"
#include "CompoundFile.h"
#include "CLucene/util/Misc.h"
@@ -61,7 +52,7 @@
bool success = false;
try {
- stream = dir->openFile(name);
+ stream = dir->openInput(name);
// read the directory and init files
int32_t count = stream->readVInt();
@@ -125,7 +116,7 @@
}
}
-IndexInput* CompoundFileReader::openFile(const char* id){
+IndexInput* CompoundFileReader::openInput(const char* id){
SCOPED_LOCK_MUTEX(THIS_LOCK)
if (stream == NULL)
@@ -166,7 +157,7 @@
directory->touchFile(fileName);
}
-void CompoundFileReader::deleteFile(const char* name, const bool throwError){
+bool CompoundFileReader::deleteFile(const char* name){
_CLTHROWA(CL_ERR_UnsupportedOperation,"UnsupportedOperationException");
}
@@ -184,7 +175,7 @@
}
return e->length;
}
-IndexOutput* CompoundFileReader::createFile(const char* name){
+IndexOutput* CompoundFileReader::createOutput(const char* name){
_CLTHROWA(CL_ERR_UnsupportedOperation,"UnsupportedOperationException");
}
LuceneLock* CompoundFileReader::makeLock(const char* name){
@@ -255,7 +246,7 @@
// open the compound stream
IndexOutput* os = NULL;
try {
- os = directory->createFile(fileName);
+ os = directory->createOutput(fileName);
// Write the number of entries
os->writeVInt(entries.size());
@@ -307,7 +298,7 @@
try {
int64_t startPtr = os->getFilePointer();
- is = directory->openFile(source->file);
+ is = directory->openInput(source->file);
int64_t length = is->length();
int64_t remainder = length;
int32_t chunk = bufferLength;
Modified: trunk/clucene/src/CLucene/index/CompoundFile.h
===================================================================
--- trunk/clucene/src/CLucene/index/CompoundFile.h 2006-06-11 07:16:00 UTC (rev 427)
+++ trunk/clucene/src/CLucene/index/CompoundFile.h 2006-06-26 00:39:24 UTC (rev 428)
@@ -1,18 +1,9 @@
-/**
- * Copyright 2003-2006 The Apache Software Foundation
- *
- * Licensed under the Apache License, Version 2.0 (the "License");
- * you may not use this file except in compliance with the License.
- * You may obtain a copy of the License at
- *
- * http://www.apache.org/licenses/LICENSE-2.0
- *
- * Unless required by applicable law or agreed to in writing, software
- * distributed under the License is distributed on an "AS IS" BASIS,
- * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
- * See the License for the specific language governing permissions and
- * limitations under the License.
- */
+/*------------------------------------------------------------------------------
+* Copyright (C) 2003-2006 Ben van Klinken and the CLucene Team
+*
+* Distributable under the terms of either the Apache License (Version 2.0) or
+* the GNU Lesser General Public License, as specified in the COPYING file.
+------------------------------------------------------------------------------*/
#ifndef _lucene_index_compoundfile_h
#define _lucene_index_compoundfile_h
@@ -38,7 +29,7 @@
*
*/
class CompoundFileReader: public CL_NS(store)::Directory {
-
+private:
/** Implementation of an IndexInput that reads from a portion of the
* compound file. The visibility is left as "package" *only* because
* this helps with testing since JUnit test cases in a different class
@@ -85,7 +76,6 @@
}
};
-private:
// Base info
CL_NS(store)::Directory* directory;
char fileName[CL_MAX_PATH];
@@ -104,7 +94,7 @@
char* getName();
void close();
- CL_NS(store)::IndexInput* openFile(const char* id);
+ CL_NS(store)::IndexInput* openInput(const char* id);
/** Returns an array of strings, one for each file in the directory-> */
char** list() const;
@@ -115,7 +105,7 @@
/** Set the modified time of an existing file to now. */
void touchFile(const char* name);
/** Removes an existing file in the directory-> */
- void deleteFile(const char* name, const bool throwError = true);
+ bool deleteFile(const char* name);
/** Renames an existing file in the directory->
If a file already exists with the new name, then it is replaced.
This replacement should be atomic. */
@@ -124,7 +114,7 @@
int64_t fileLength(const char* name) const;
/** Creates a new, empty file in the directory with the given name.
Returns a stream writing this file. */
- CL_NS(store)::IndexOutput* createFile(const char* name);
+ CL_NS(store)::IndexOutput* createOutput(const char* name);
/** Construct a {@link Lock}.
* @param name the name of the lock file
*/
@@ -177,7 +167,6 @@
};
-private:
CL_NS(store)::Directory* directory;
char fileName[CL_MAX_PATH];
CL_NS(util)::CLHashMap<char*, void*,
Modified: trunk/clucene/src/CLucene/index/DocumentWriter.cpp
===================================================================
--- trunk/clucene/src/CLucene/index/DocumentWriter.cpp 2006-06-11 07:16:00 UTC (rev 427)
+++ trunk/clucene/src/CLucene/index/DocumentWriter.cpp 2006-06-26 00:39:24 UTC (rev 428)
@@ -1,18 +1,9 @@
-/**
- * Copyright 2003-2006 The Apache Software Foundation
- *
- * Licensed under the Apache License, Version 2.0 (the "License");
- * you may not use this file except in compliance with the License.
- * You may obtain a copy of the License at
- *
- * http://www.apache.org/licenses/LICENSE-2.0
- *
- * Unless required by applicable law or agreed to in writing, software
- * distributed under the License is distributed on an "AS IS" BASIS,
- * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
- * See the License for the specific language governing permissions and
- * limitations under the License.
- */
+/*------------------------------------------------------------------------------
+* Copyright (C) 2003-2006 Ben van Klinken and the CLucene Team
+*
+* Distributable under the terms of either the Apache License (Version 2.0) or
+* the GNU Lesser General Public License, as specified in the COPYING file.
+------------------------------------------------------------------------------*/
#include "CLucene/StdHeader.h"
#include "DocumentWriter.h"
@@ -36,7 +27,7 @@
CL_NS_DEF(index)
/*Posting*/
- int32_t Posting::getPositionsLength(){
+ int32_t Posting::getPositionsLength() const{
return positionsLength;
}
@@ -72,7 +63,7 @@
similarity(sim),
fieldPositions(NULL),
fieldBoosts(NULL),
- termBuffer(_CLNEW Term( LUCENE_BLANK_STRING, LUCENE_BLANK_STRING ,false)){
+ termBuffer(_CLNEW Term( LUCENE_BLANK_STRING, LUCENE_BLANK_STRING )){
//Pre - d contains a valid reference to a Directory
// d contains a valid reference to a Analyzer
// mfl > 0 and contains the maximum field length
@@ -104,7 +95,7 @@
_CLDELETE(itr->second);
_CLLDECDELETE(itr->first);
- itr++;
+ ++itr;
}
postingTable.clear();
}
@@ -189,7 +180,7 @@
}
- void DocumentWriter::invertDocument(Document* doc) {
+ void DocumentWriter::invertDocument(const Document* doc) {
DocumentFieldEnumeration* fields = doc->fields();
try {
while (fields->hasMoreElements()) {
@@ -303,7 +294,7 @@
const TCHAR* text,
const int32_t position) {
- termBuffer->set(field,text, true );
+ termBuffer->set(field,text);
Posting* ti = postingTable.get(termBuffer);
if (ti != NULL) { // word seen before
@@ -380,8 +371,8 @@
quickSort(postings, left + 1, hi);
}
- #define __DOCLOSE(obj) if(obj!=NULL){ try{ obj->close(); _CLDELETE(obj);} catch(CLuceneError &e){ierr=e.number();err=e.what();} catch(...){err="Unknown error while closing posting tables";} }
- void DocumentWriter::writePostings(Posting** postings, const int32_t postingsLength, const char* segment){
+ void DocumentWriter::writePostings(Posting** postings, const int32_t postingsLength, const char* segment){
+ #define __DOCLOSE(obj) if(obj!=NULL){ try{ obj->close(); _CLDELETE(obj);} catch(CLuceneError &e){ierr=e.number();err=e.what();} catch(...){err="Unknown error while closing posting tables";} }
IndexOutput* freq = NULL;
IndexOutput* prox = NULL;
TermInfosWriter* tis = NULL;
@@ -389,11 +380,11 @@
try {
//open files for inverse index storage
const char* buf = Misc::segmentname( segment, ".frq");
- freq = directory->createFile( buf );
+ freq = directory->createOutput( buf );
_CLDELETE_CaARRAY( buf );
buf = Misc::segmentname( segment, ".prx");
- prox = directory->createFile( buf );
+ prox = directory->createOutput( buf );
_CLDELETE_CaARRAY( buf );
tis = _CLNEW TermInfosWriter(directory, segment, fieldInfos);
@@ -448,8 +439,8 @@
termVectorWriter->closeDocument();
_CLDELETE(ti);
}_CLFINALLY (
- char* err=NULL;
- int32_t ierr=0;
+ const char* err=NULL;
+ int32_t ierr=0;
// make an effort to close all streams we can but remember and re-throw
// the first exception encountered in this process
@@ -462,7 +453,7 @@
);
}
- void DocumentWriter::writeNorms(Document* doc, const char* segment) {
+ void DocumentWriter::writeNorms(const Document* doc, const char* segment) {
char fn[CL_MAX_PATH];
for(int32_t n = 0; n < fieldInfos->size(); n++){
FieldInfo* fi = fieldInfos->fieldInfo(n);
@@ -470,7 +461,7 @@
float_t norm = fieldBoosts[n] * similarity->lengthNorm(fi->name, fieldLengths[n]);
_snprintf(fn,CL_MAX_PATH,"%s.f%d",segment,n);
- IndexOutput* norms = directory->createFile(fn);
+ IndexOutput* norms = directory->createOutput(fn);
try {
norms->writeByte(CL_NS(search)::Similarity::encodeNorm(norm));
}_CLFINALLY (
Modified: trunk/clucene/src/CLucene/index/DocumentWriter.h
===================================================================
--- trunk/clucene/src/CLucene/index/DocumentWriter.h 2006-06-11 07:16:00 UTC (rev 427)
+++ trunk/clucene/src/CLucene/index/DocumentWriter.h 2006-06-26 00:39:24 UTC (rev 428)
@@ -1,18 +1,9 @@
-/**
- * Copyright 2003-2006 The Apache Software Foundation
- *
- * Licensed under the Apache License, Version 2.0 (the "License");
- * you may not use this file except in compliance with the License.
- * You may obtain a copy of the License at
- *
- * http://www.apache.org/licenses/LICENSE-2.0
- *
- * Unless required by applicable law or agreed to in writing, software
- * distributed under the License is distributed on an "AS IS" BASIS,
- * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
- * See the License for the specific language governing permissions and
- * limitations under the License.
- */
+/*------------------------------------------------------------------------------
+* Copyright (C) 2003-2006 Ben van Klinken and the CLucene Team
+*
+* Distributable under the terms of either the Apache License (Version 2.0) or
+* the GNU Lesser General Public License, as specified in the COPYING file.
+------------------------------------------------------------------------------*/
#ifndef _lucene_index_DocumentWriter_
#define _lucene_index_DocumentWriter_
@@ -40,7 +31,7 @@
Term* term; // the Term
int32_t freq; // its frequency in doc
- int32_t getPositionsLength();
+ int32_t getPositionsLength() const;
Posting(Term* t, const int32_t position);
~Posting();
};
@@ -51,10 +42,10 @@
CL_NS(analysis)::Analyzer* analyzer;
CL_NS(store)::Directory* directory;
FieldInfos* fieldInfos; //array
- int32_t* fieldPositions; //array
- float_t* fieldBoosts; //array
+ int32_t* fieldPositions; //array
+ float_t* fieldBoosts; //array
const int32_t maxFieldLength;
- CL_NS(search)::Similarity* similarity;
+ CL_NS(search)::Similarity* similarity;
// Keys are Terms, values are Postings.
// Used to buffer a document before it is written to the index.
@@ -79,7 +70,7 @@
private:
// Tokenizes the fields of a document into Postings.
- void invertDocument(CL_NS(document)::Document* doc);
+ void invertDocument(const CL_NS(document)::Document* doc);
void addPosition(const TCHAR* field, const TCHAR* text, const int32_t position);
@@ -89,7 +80,7 @@
void writePostings(Posting** postings, const int32_t postingsLength, const char* segment);
- void writeNorms(CL_NS(document)::Document* doc, const char* segment);
+ void writeNorms(const CL_NS(document)::Document* doc, const char* segment);
void clearPostingTable();
};
Modified: trunk/clucene/src/CLucene/index/FieldInfo.h
===================================================================
--- trunk/clucene/src/CLucene/index/FieldInfo.h 2006-06-11 07:16:00 UTC (rev 427)
+++ trunk/clucene/src/CLucene/index/FieldInfo.h 2006-06-26 00:39:24 UTC (rev 428)
@@ -1,18 +1,9 @@
-/**
- * Copyright 2003-2006 The Apache Software Foundation
- *
- * Licensed under the Apache License, Version 2.0 (the "License");
- * you may not use this file except in compliance with the License.
- * You may obtain a copy of the License at
- *
- * http://www.apache.org/licenses/LICENSE-2.0
- *
- * Unless required by applicable law or agreed to in writing, software
- * distributed under the License is distributed on an "AS IS" BASIS,
- * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
- * See the License for the specific language governing permissions and
- * limitations under the License.
- */
+/*------------------------------------------------------------------------------
+* Copyright (C) 2003-2006 Ben van Klinken and the CLucene Team
+*
+* Distributable under the terms of either the Apache License (Version 2.0) or
+* the GNU Lesser General Public License, as specified in the COPYING file.
+------------------------------------------------------------------------------*/
#ifndef _lucene_index_FieldInfo_
#define _lucene_index_FieldInfo_
@@ -42,8 +33,8 @@
FieldInfo(const TCHAR* na, const bool tk, const int32_t nu, const bool stv):
name(CL_NS(util)::CLStringIntern::intern(na CL_FILELINE)),
isIndexed(tk),
- number(nu),
- storeTermVector(stv){
+ storeTermVector(stv),
+ number(nu){
//Func - Constructor
// Initialises FieldInfo.
// na holds the name of the field
Modified: trunk/clucene/src/CLucene/index/FieldInfos.cpp
===================================================================
--- trunk/clucene/src/CLucene/index/FieldInfos.cpp 2006-06-11 07:16:00 UTC (rev 427)
+++ trunk/clucene/src/CLucene/index/FieldInfos.cpp 2006-06-26 00:39:24 UTC (rev 428)
@@ -1,18 +1,9 @@
-/**
- * Copyright 2003-2006 The Apache Software Foundation
- *
- * Licensed under the Apache License, Version 2.0 (the "License");
- * you may not use this file except in compliance with the License.
- * You may obtain a copy of the License at
- *
- * http://www.apache.org/licenses/LICENSE-2.0
- *
- * Unless required by applicable law or agreed to in writing, software
- * distributed under the License is distributed on an "AS IS" BASIS,
- * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
- * See the License for the specific language governing permissions and
- * limitations under the License.
- */
+/*------------------------------------------------------------------------------
+* Copyright (C) 2003-2006 Ben van Klinken and the CLucene Team
+*
+* Distributable under the terms of either the Apache License (Version 2.0) or
+* the GNU Lesser General Public License, as specified in the COPYING file.
+------------------------------------------------------------------------------*/
#include "CLucene/StdHeader.h"
#include "FieldInfos.h"
@@ -39,7 +30,7 @@
FieldInfos::FieldInfos(Directory* d, const char* name):
byName(false,false),byNumber(true)
{
- IndexInput* input = d->openFile(name);
+ IndexInput* input = d->openInput(name);
try {
read(input);
} _CLFINALLY (
@@ -48,7 +39,7 @@
);
}
- void FieldInfos::add(Document* doc) {
+ void FieldInfos::add(const Document* doc) {
DocumentFieldEnumeration* fields = doc->fields();
while (fields->hasMoreElements()) {
Field* field = fields->nextElement();
@@ -109,8 +100,8 @@
return byNumber.size();
}
- void FieldInfos::write(Directory* d, const char* name) {
- IndexOutput* output = d->createFile(name);
+ void FieldInfos::write(Directory* d, const char* name) const{
+ IndexOutput* output = d->createOutput(name);
try {
write(output);
} _CLFINALLY (
@@ -119,7 +110,7 @@
);
}
- void FieldInfos::write(IndexOutput* output) {
+ void FieldInfos::write(IndexOutput* output) const{
output->writeVInt(size());
for (int32_t i = 0; i < size(); i++) {
FieldInfo* fi = fieldInfo(i);
@@ -132,7 +123,7 @@
}
}
- void FieldInfos::read(store::IndexInput* input) {
+ void FieldInfos::read(IndexInput* input) {
int32_t size = input->readVInt();
TCHAR name[LUCENE_MAX_FIELD_LEN+1]; //todo: we make this very big, so that a jlucene field bigger than LUCENE_MAX_FIELD_LEN won't corrupt the buffer
for (int32_t i = 0; i < size; i++){
Modified: trunk/clucene/src/CLucene/index/FieldInfos.h
===================================================================
--- trunk/clucene/src/CLucene/index/FieldInfos.h 2006-06-11 07:16:00 UTC (rev 427)
+++ trunk/clucene/src/CLucene/index/FieldInfos.h 2006-06-26 00:39:24 UTC (rev 428)
@@ -1,18 +1,9 @@
-/**
- * Copyright 2003-2006 The Apache Software Foundation
- *
- * Licensed under the Apache License, Version 2.0 (the "License");
- * you may not use this file except in compliance with the License.
- * You may obtain a copy of the License at
- *
- * http://www.apache.org/licenses/LICENSE-2.0
- *
- * Unless required by applicable law or agreed to in writing, software
- * distributed under the License is distributed on an "AS IS" BASIS,
- * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
- * See the License for the specific language governing permissions and
- * limitations under the License.
- */
+/*------------------------------------------------------------------------------
+* Copyright (C) 2003-2006 Ben van Klinken and the CLucene Team
+*
+* Distributable under the terms of either the Apache License (Version 2.0) or
+* the GNU Lesser General Public License, as specified in the COPYING file.
+------------------------------------------------------------------------------*/
#ifndef _lucene_index_FieldInfos_
#define _lucene_index_FieldInfos_
@@ -73,7 +64,7 @@
bool hasVectors() const;
// Adds field info for a Document.
- void add(CL_NS(document)::Document* doc);
+ void add(const CL_NS(document)::Document* doc);
// Merges in information from another FieldInfos.
void add(FieldInfos* other);
@@ -99,8 +90,8 @@
*/
void add(const TCHAR** names, const bool isIndexed, const bool storeTermVector=false);
- void write(CL_NS(store)::Directory* d, const char* name);
- void write(CL_NS(store)::IndexOutput* output);
+ void write(CL_NS(store)::Directory* d, const char* name) const;
+ void write(CL_NS(store)::IndexOutput* output) const;
private:
void read(CL_NS(store)::IndexInput* input);
Modified: trunk/clucene/src/CLucene/index/FieldsReader.cpp
===================================================================
--- trunk/clucene/src/CLucene/index/FieldsReader.cpp 2006-06-11 07:16:00 UTC (rev 427)
+++ trunk/clucene/src/CLucene/index/FieldsReader.cpp 2006-06-26 00:39:24 UTC (rev 428)
@@ -1,18 +1,9 @@
-/**
- * Copyright 2003-2006 The Apache Software Foundation
- *
- * Licensed under the Apache License, Version 2.0 (the "License");
- * you may not use this file except in compliance with the License.
- * You may obtain a copy of the License at
- *
- * http://www.apache.org/licenses/LICENSE-2.0
- *
- * Unless required by applicable law or agreed to in writing, software
- * distributed under the License is distributed on an "AS IS" BASIS,
- * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
- * See the License for the specific language governing permissions and
- * limitations under the License.
- */
+/*------------------------------------------------------------------------------
+* Copyright (C) 2003-2006 Ben van Klinken and the CLucene Team
+*
+* Distributable under the terms of either the Apache License (Version 2.0) or
+* the GNU Lesser General Public License, as specified in the COPYING file.
+------------------------------------------------------------------------------*/
#include "CLucene/StdHeader.h"
#include "FieldsReader.h"
@@ -40,11 +31,11 @@
CND_PRECONDITION(segment != NULL, "segment != NULL");
const char* buf = Misc::segmentname(segment,".fdt");
- fieldsStream = d->openFile( buf );
+ fieldsStream = d->openInput( buf );
_CLDELETE_CaARRAY( buf );
buf = Misc::segmentname(segment,".fdx");
- indexStream = d->openFile( buf );
+ indexStream = d->openInput( buf );
_CLDELETE_CaARRAY( buf );
_size = (int32_t)indexStream->length()/8;
@@ -73,7 +64,7 @@
_CLDELETE(indexStream);
}
- int32_t FieldsReader::size() {
+ int32_t FieldsReader::size() const{
return _size;
}
Modified: trunk/clucene/src/CLucene/index/FieldsReader.h
===================================================================
--- trunk/clucene/src/CLucene/index/FieldsReader.h 2006-06-11 07:16:00 UTC (rev 427)
+++ trunk/clucene/src/CLucene/index/FieldsReader.h 2006-06-26 00:39:24 UTC (rev 428)
@@ -1,18 +1,9 @@
-/**
- * Copyright 2003-2006 The Apache Software Foundation
- *
- * Licensed under the Apache License, Version 2.0 (the "License");
- * you may not use this file except in compliance with the License.
- * You may obtain a copy of the License at
- *
- * http://www.apache.org/licenses/LICENSE-2.0
- *
- * Unless required by applicable law or agreed to in writing, software
- * distributed under the License is distributed on an "AS IS" BASIS,
- * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
- * See the License for the specific language governing permissions and
- * limitations under the License.
- */
+/*------------------------------------------------------------------------------
+* Copyright (C) 2003-2006 Ben van Klinken and the CLucene Team
+*
+* Distributable under the terms of either the Apache License (Version 2.0) or
+* the GNU Lesser General Public License, as specified in the COPYING file.
+------------------------------------------------------------------------------*/
#ifndef _lucene_index_FieldsReader_
#define _lucene_index_FieldsReader_
@@ -45,7 +36,7 @@
void close();
- int32_t size();
+ int32_t size() const;
CL_NS(document)::Document* doc(int32_t n);
};
Modified: trunk/clucene/src/CLucene/index/FieldsWriter.cpp
===================================================================
--- trunk/clucene/src/CLucene/index/FieldsWriter.cpp 2006-06-11 07:16:00 UTC (rev 427)
+++ trunk/clucene/src/CLucene/index/FieldsWriter.cpp 2006-06-26 00:39:24 UTC (rev 428)
@@ -1,18 +1,9 @@
-/**
- * Copyright 2003-2006 The Apache Software Foundation
- *
- * Licensed under the Apache License, Version 2.0 (the "License");
- * you may not use this file except in compliance with the License.
- * You may obtain a copy of the License at
- *
- * http://www.apache.org/licenses/LICENSE-2.0
- *
- * Unless required by applicable law or agreed to in writing, software
- * distributed under the License is distributed on an "AS IS" BASIS,
- * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
- * See the License for the specific language governing permissions and
- * limitations under the License.
- */
+/*------------------------------------------------------------------------------
+* Copyright (C) 2003-2006 Ben van Klinken and the CLucene Team
+*
+* Distributable under the terms of either the Apache License (Version 2.0) or
+* the GNU Lesser General Public License, as specified in the COPYING file.
+------------------------------------------------------------------------------*/
#include "CLucene/StdHeader.h"
#include "FieldsWriter.h"
@@ -41,11 +32,11 @@
CND_PRECONDITION(segment != NULL,"segment is NULL");
const char* buf = Misc::segmentname(segment,".fdt");
- fieldsStream = d->createFile ( buf );
+ fieldsStream = d->createOutput ( buf );
_CLDELETE_CaARRAY( buf );
buf = Misc::segmentname(segment,".fdx");
- indexStream = d->createFile( buf );
+ indexStream = d->createOutput( buf );
_CLDELETE_CaARRAY( buf );
CND_CONDITION(indexStream != NULL,"indexStream is NULL");
Modified: trunk/clucene/src/CLucene/index/FieldsWriter.h
===================================================================
--- trunk/clucene/src/CLucene/index/FieldsWriter.h 2006-06-11 07:16:00 UTC (rev 427)
+++ trunk/clucene/src/CLucene/index/FieldsWriter.h 2006-06-26 00:39:24 UTC (rev 428)
@@ -1,18 +1,9 @@
-/**
- * Copyright 2003-2006 The Apache Software Foundation
- *
- * Licensed under the Apache License, Version 2.0 (the "License");
- * you may not use this file except in compliance with the License.
- * You may obtain a copy of the License at
- *
- * http://www.apache.org/licenses/LICENSE-2.0
- *
- * Unless required by applicable law or agreed to in writing, software
- * distributed under the License is distributed on an "AS IS" BASIS,
- * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
- * See the License for the specific language governing permissions and
- * limitations under the License.
- */
+/*------------------------------------------------------------------------------
+* Copyright (C) 2003-2006 Ben van Klinken and the CLucene Team
+*
+* Distributable under the terms of either the Apache License (Version 2.0) or
+* the GNU Lesser General Public License, as specified in the COPYING file.
+------------------------------------------------------------------------------*/
#ifndef _lucene_index_FieldsWriter_
#define _lucene_index_FieldsWriter_
Modified: trunk/clucene/src/CLucene/index/IndexModifier.cpp
===================================================================
--- trunk/clucene/src/CLucene/index/IndexModifier.cpp 2006-06-11 07:16:00 UTC (rev 427)
+++ trunk/clucene/src/CLucene/index/IndexModifier.cpp 2006-06-26 00:39:24 UTC (rev 428)
@@ -1,18 +1,9 @@
-/**
- * Copyright 2003-2006 The Apache Software Foundation
- *
- * Licensed under the Apache License, Version 2.0 (the "License");
- * you may not use this file except in compliance with the License.
- * You may obtain a copy of the License at
- *
- * http://www.apache.org/licenses/LICENSE-2.0
- *
- * Unless required by applicable law or agreed to in writing, software
- * distributed under the License is distributed on an "AS IS" BASIS,
- * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
- * See the License for the specific language governing permissions and
- * limitations under the License.
- */
+/*------------------------------------------------------------------------------
+* Copyright (C) 2003-2006 Ben van Klinken and the CLucene Team
+*
+* Distributable under the terms of either the Apache License (Version 2.0) or
+* the GNU Lesser General Public License, as specified in the COPYING file.
+------------------------------------------------------------------------------*/
#include "CLucene/StdHeader.h"
#include "IndexModifier.h"
@@ -51,7 +42,7 @@
close();
}
-void IndexModifier::assureOpen() {
+void IndexModifier::assureOpen() const{
if (!open) {
_CLTHROWA(CL_ERR_IllegalState,"Index is closed");
}
@@ -218,7 +209,7 @@
open = false;
}
-const TCHAR* IndexModifier::toString() {
+const TCHAR* IndexModifier::toString() const{
TCHAR* dir = directory->toString();
TCHAR* ret = _CL_NEWARRAY(TCHAR,_tcslen(dir)+7); //strlen("Index@")
_tcscpy(ret,_T("Index@"));
Modified: trunk/clucene/src/CLucene/index/IndexModifier.h
===================================================================
--- trunk/clucene/src/CLucene/index/IndexModifier.h 2006-06-11 07:16:00 UTC (rev 427)
+++ trunk/clucene/src/CLucene/index/IndexModifier.h 2006-06-26 00:39:24 UTC (rev 428)
@@ -1,18 +1,9 @@
-/**
- * Copyright 2003-2006 The Apache Software Foundation
- *
- * Licensed under the Apache License, Version 2.0 (the "License");
- * you may not use this file except in compliance with the License.
- * You may obtain a copy of the License at
- *
- * http://www.apache.org/licenses/LICENSE-2.0
- *
- * Unless required by applicable law or agreed to in writing, software
- * distributed under the License is distributed on an "AS IS" BASIS,
- * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
- * See the License for the specific language governing permissions and
- * limitations under the License.
- */
+/*------------------------------------------------------------------------------
+* Copyright (C) 2003-2006 Ben van Klinken and the CLucene Team
+*
+* Distributable under the terms of either the Apache License (Version 2.0) or
+* the GNU Lesser General Public License, as specified in the COPYING file.
+------------------------------------------------------------------------------*/
#ifndef _lucene_index_IndexModifier_
#define _lucene_index_IndexModifier_
@@ -128,7 +119,7 @@
* Throw an IllegalStateException if the index is closed.
* @throws IllegalStateException
*/
- void assureOpen();
+ void assureOpen() const;
/**
* Close the IndexReader and open an IndexWriter.
@@ -143,8 +134,6 @@
void createIndexReader();
public:
- DEFINE_MUTEX(THIS_LOCK);
-
/**
* Make sure all changes are written to disk.
* @throws IOException
@@ -293,7 +282,7 @@
*/
void close();
- const TCHAR* toString();
+ const TCHAR* toString() const;
/**
Modified: trunk/clucene/src/CLucene/index/IndexReader.cpp
===================================================================
--- trunk/clucene/src/CLucene/index/IndexReader.cpp 2006-06-11 07:16:00 UTC (rev 427)
+++ trunk/clucene/src/CLucene/index/IndexReader.cpp 2006-06-26 00:39:24 UTC (rev 428)
@@ -1,18 +1,9 @@
-/**
- * Copyright 2003-2006 The Apache Software Foundation
- *
- * Licensed under the Apache License, Version 2.0 (the "License");
- * you may not use this file except in compliance with the License.
- * You may obtain a copy of the License at
- *
- * http://www.apache.org/licenses/LICENSE-2.0
- *
- * Unless required by applicable law or agreed to in writing, software
- * distributed under the License is distributed on an "AS IS" BASIS,
- * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
- * See the License for the specific language governing permissions and
- * limitations under the License.
- */
+/*------------------------------------------------------------------------------
+* Copyright (C) 2003-2006 Ben van Klinken and the CLucene Team
+*
+* Distributable under the terms of either the Apache License (Version 2.0) or
+* the GNU Lesser General Public License, as specified in the COPYING file.
+------------------------------------------------------------------------------*/
#include "CLucene/StdHeader.h"
#include "IndexReader.h"
@@ -219,7 +210,7 @@
CND_PRECONDITION(directory != NULL, "directory is NULL");
//Create a buffer of length CL_MAXDIR
- char f[CL_MAX_DIR];
+ char f[CL_MAX_PATH+10]; //add 10 in case that directory is already 260 long
//Copy the directory string to the buffer
strcpy(f,directory);
//Cat the name of the segments to buffer
@@ -470,7 +461,7 @@
CND_PRECONDITION(directory != NULL, "directory is NULL");
//Create a buffer of length CL_MAXDIR
- char f[CL_MAX_DIR];
+ char f[CL_MAX_PATH+12]; //add 12 in case that directory is already 260 long
//Copy the directory string to the buffer
strcpy(f,directory);
//Cat the name of the write.lock file to buffer
Modified: trunk/clucene/src/CLucene/index/IndexReader.h
===================================================================
--- trunk/clucene/src/CLucene/index/IndexReader.h 2006-06-11 07:16:00 UTC (rev 427)
+++ trunk/clucene/src/CLucene/index/IndexReader.h 2006-06-26 00:39:24 UTC (rev 428)
@@ -1,18 +1,9 @@
-/**
- * Copyright 2003-2006 The Apache Software Foundation
- *
- * Licensed under the Apache License, Version 2.0 (the "License");
- * you may not use this file except in compliance with the License.
- * You may obtain a copy of the License at
- *
- * http://www.apache.org/licenses/LICENSE-2.0
- *
- * Unless required by applicable law or agreed to in writing, software
- * distributed under the License is distributed on an "AS IS" BASIS,
- * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
- * See the License for the specific language governing permissions and
- * limitations under the License.
- */
+/*------------------------------------------------------------------------------
+* Copyright (C) 2003-2006 Ben van Klinken and the CLucene Team
+*
+* Distributable under the terms of either the Apache License (Version 2.0) or
+* the GNU Lesser General Public License, as specified in the COPYING file.
+------------------------------------------------------------------------------*/
#ifndef _lucene_index_IndexReader_
#define _lucene_index_IndexReader_
Modified: trunk/clucene/src/CLucene/index/IndexWriter.cpp
===================================================================
--- trunk/clucene/src/CLucene/index/IndexWriter.cpp 2006-06-11 07:16:00 UTC (rev 427)
+++ trunk/clucene/src/CLucene/index/IndexWriter.cpp 2006-06-26 00:39:24 UTC (rev 428)
@@ -1,25 +1,15 @@
-/**
- * Copyright 2003-2006 The Apache Software Foundation
- *
- * Licensed under the Apache License, Version 2.0 (the "License");
- * you may not use this file except in compliance with the License.
- * You may obtain a copy of the License at
- *
- * http://www.apache.org/licenses/LICENSE-2.0
- *
- * Unless required by applicable law or agreed to in writing, software
- * distributed under the License is distributed on an "AS IS" BASIS,
- * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
- * See the License for the specific language governing permissions and
- * limitations under the License.
- */
+/*------------------------------------------------------------------------------
+* Copyright (C) 2003-2006 Ben van Klinken and the CLucene Team
+*
+* Distributable under the terms of either the Apache License (Version 2.0) or
+* the GNU Lesser General Public License, as specified in the COPYING file.
+------------------------------------------------------------------------------*/
#include "CLucene/StdHeader.h"
#include "IndexWriter.h"
#include "CLucene/document/Document.h"
#include "CLucene/store/Directory.h"
#include "CLucene/store/Lock.h"
-#include "CLucene/store/TransactionalRAMDirectory.h"
#include "CLucene/util/VoidList.h"
#include "DocumentWriter.h"
#include "SegmentInfos.h"
@@ -277,16 +267,16 @@
SegmentInfo* si = _CLNEW SegmentInfo(segmentName, 1, ramDirectory);
CND_CONDITION(si != NULL, "Si is NULL");
- {
- SCOPED_LOCK_MUTEX(THIS_LOCK)
+ {
+ SCOPED_LOCK_MUTEX(THIS_LOCK)
- //Add the info object for this particular segment to the list
- // of all segmentInfos->
- segmentInfos->add(si);
-
- //Check to see if the segments must be merged
- maybeMergeSegments();
- }
+ //Add the info object for this particular segment to the list
+ // of all segmentInfos->
+ segmentInfos->add(si);
+
+ //Check to see if the segments must be merged
+ maybeMergeSegments();
+ }
} _CLFINALLY(
_CLDELETE_CaARRAY(segmentName);
);
@@ -465,7 +455,7 @@
if (!directory->fileExists("deletable"))
return result;
- lucene::store::IndexInput* input = directory->openFile("deletable");
+ IndexInput* input = directory->openInput("deletable");
try {
TCHAR tname[CL_MAX_PATH];
for (int32_t i = input->readInt(); i > 0; i--){ // read file names
@@ -482,7 +472,7 @@
}
void IndexWriter::writeDeleteableFiles(AStringArrayConstWithDeletor* files) {
- IndexOutput* output = directory->createFile("deleteable.new");
+ IndexOutput* output = directory->createOutput("deleteable.new");
try {
output->writeInt(files->size());
TCHAR tfile[CL_MAX_PATH]; //temporary space for tchar file name
@@ -502,7 +492,7 @@
AStringArrayConstWithDeletor::const_iterator itr = files->begin();
while ( itr != files->end() ){
directory->deleteFile( *itr );
- itr++;
+ ++itr;
}
}
@@ -524,7 +514,7 @@
deletable->push_back(STRDUP_AtoA(file)); // add to deletable
}
}
- itr++;
+ ++itr;
}
}
Modified: trunk/clucene/src/CLucene/index/IndexWriter.h
===================================================================
--- trunk/clucene/src/CLucene/index/IndexWriter.h 2006-06-11 07:16:00 UTC (rev 427)
+++ trunk/clucene/src/CLucene/index/IndexWriter.h 2006-06-26 00:39:24 UTC (rev 428)
@@ -1,18 +1,9 @@
-/**
- * Copyright 2003-2006 The Apache Software Foundation
- *
- * Licensed under the Apache License, Version 2.0 (the "License");
- * you may not use this file except in compliance with the License.
- * You may obtain a copy of the License at
- *
- * http://www.apache.org/licenses/LICENSE-2.0
- *
- * Unless required by applicable law or agreed to in writing, software
- * distributed under the License is distributed on an "AS IS" BASIS,
- * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
- * See the License for the specific language governing permissions and
- * limitations under the License.
- */
+/*------------------------------------------------------------------------------
+* Copyright (C) 2003-2006 Ben van Klinken and the CLucene Team
+*
+* Distributable under the terms of either the Apache License (Version 2.0) or
+* the GNU Lesser General Public License, as specified in the COPYING file.
+------------------------------------------------------------------------------*/
#ifndef _lucene_index_IndexWriter_
#define _lucene_index_IndexWriter_
@@ -100,7 +91,7 @@
// explicitly set a truncation policy by adjusting maxFieldLength.
LUCENE_STATIC_CONSTANT(int32_t, DEFAULT_MAX_FIELD_LENGTH = 10000);
LUCENE_STATIC_CONSTANT(int32_t, FIELD_TRUNC_POLICY__WARN = -1);
- int32_t getMaxFieldLength(){ return maxFieldLength; }
+ int32_t getMaxFieldLength() const{ return maxFieldLength; }
void setMaxFieldLength(int32_t val){ maxFieldLength = val; }
// Determines how often segment indices are merged by addDocument(). With
@@ -112,7 +103,7 @@
// interactively maintained.
//
// <p>This must never be less than 2. The default value is 10.
- int32_t getMergeFactor(){ return mergeFactor; }
+ int32_t getMergeFactor() const{ return mergeFactor; }
void setMergeFactor(int32_t val){ mergeFactor = val; }
/** Determines the minimal number of documents required before the buffered
@@ -122,7 +113,7 @@
* the number of files open in a FSDirectory.
*
* <p> The default value is 10.*/
- int32_t getMinMergeDocs(){ return minMergeDocs; }
+ int32_t getMinMergeDocs() const{ return minMergeDocs; }
void setMinMergeDocs(int32_t val){ minMergeDocs = val; }
@@ -132,7 +123,7 @@
// Larger values are best for batched indexing and speedier searches.
//
// <p>The default value is {@link Integer#MAX_VALUE}.
- int32_t getMaxMergeDocs(){ return maxMergeDocs; }
+ int32_t getMaxMergeDocs() const{ return maxMergeDocs; }
void setMaxMergeDocs(int32_t val){ maxMergeDocs = val; }
/**
Modified: trunk/clucene/src/CLucene/index/MultiReader.cpp
===================================================================
--- trunk/clucene/src/CLucene/index/MultiReader.cpp 2006-06-11 07:16:00 UTC (rev 427)
+++ trunk/clucene/src/CLucene/index/MultiReader.cpp 2006-06-26 00:39:24 UTC (rev 428)
@@ -1,18 +1,9 @@
-/**
- * Copyright 2003-2006 The Apache Software Foundation
- *
- * Licensed under the Apache License, Version 2.0 (the "License");
- * you may not use this file except in compliance with the License.
- * You may obtain a copy of the License at
- *
- * http://www.apache.org/licenses/LICENSE-2.0
- *
- * Unless required by applicable law or agreed to in writing, software
- * distributed under the License is distributed on an "AS IS" BASIS,
- * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
- * See the License for the specific language governing permissions and
- * limitations under the License.
- */
+/*------------------------------------------------------------------------------
+* Copyright (C) 2003-2006 Ben van Klinken and the CLucene Team
+*
+* Distributable under the terms of either the Apache License (Version 2.0) or
+* the GNU Lesser General Public License, as specified in the COPYING file.
+------------------------------------------------------------------------------*/
#include "CLucene/StdHeader.h"
#include "MultiReader.h"
@@ -393,7 +384,7 @@
}
void MultiTermDocs::seek(TermEnum* termEnum){
- seek(termEnum->term());
+ seek(termEnum->term(false));
}
void MultiTermDocs::seek( Term* tterm) {
@@ -403,23 +394,23 @@
CND_PRECONDITION(tterm != NULL, "tterm is NULL");
- //Assigning tterm is done as below for a reason
- //The construction ensures that if seek is called from within
- //MultiTermDocs with as argument this->term (seek(this->term)) that the assignment
- //will succeed and all referencecounters represent the correct situation
+ //Assigning tterm is done as below for a reason
+ //The construction ensures that if seek is called from within
+ //MultiTermDocs with as argument this->term (seek(this->term)) that the assignment
+ //will succeed and all referencecounters represent the correct situation
+
+ //Get a pointer from tterm and increase its reference counter
+ Term *TempTerm = _CL_POINTER(tterm);
+
+ //Finialize term to ensure we decrease the reference counter of the instance which term points to
+ _CLDECDELETE(term);
- //Get a pointer from tterm and increase its reference counter
- Term *TempTerm = _CL_POINTER(tterm);
-
- //Finialize term to ensure we decrease the reference counter of the instance which term points to
- _CLDECDELETE(term);
-
- //Assign TempTerm to term
- term = TempTerm;
-
- base = 0;
- pointer = 0;
- current = NULL;
+ //Assign TempTerm to term
+ term = TempTerm;
+
+ base = 0;
+ pointer = 0;
+ current = NULL;
}
bool MultiTermDocs::next() {
@@ -642,7 +633,7 @@
}
- Term* MultiTermEnum::term(const bool pointer) {
+ Term* MultiTermEnum::term() {
//Func - Returns the current term of the set of enumerations
//Pre - pointer is true or false and indicates if the reference counter
// of term must be increased or not
@@ -650,10 +641,13 @@
//Post - pointer = true -> term has been returned with an increased reference counter
// pointer = false -> term has been returned
- if (pointer && _term!=NULL)
- return _CL_POINTER(_term);
+ return _CL_POINTER(_term);
+ }
+ Term* MultiTermEnum::term(bool pointer) {
+ if ( pointer )
+ return _CL_POINTER(_term);
else
- return _term;
+ return _term;
}
int32_t MultiTermEnum::docFreq() const {
Modified: trunk/clucene/src/CLucene/index/MultiReader.h
===================================================================
--- trunk/clucene/src/CLucene/index/MultiReader.h 2006-06-11 07:16:00 UTC (rev 427)
+++ trunk/clucene/src/CLucene/index/MultiReader.h 2006-06-26 00:39:24 UTC (rev 428)
@@ -1,18 +1,9 @@
-/**
- * Copyright 2003-2006 The Apache Software Foundation
- *
- * Licensed under the Apache License, Version 2.0 (the "License");
- * you may not use this file except in compliance with the License.
- * You may obtain a copy of the License at
- *
- * http://www.apache.org/licenses/LICENSE-2.0
- *
- * Unless required by applicable law or agreed to in writing, software
- * distributed under the License is distributed on an "AS IS" BASIS,
- * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
- * See the License for the specific language governing permissions and
- * limitations under the License.
- */
+/*------------------------------------------------------------------------------
+* Copyright (C) 2003-2006 Ben van Klinken and the CLucene Team
+*
+* Distributable under the terms of either the Apache License (Version 2.0) or
+* the GNU Lesser General Public License, as specified in the COPYING file.
+------------------------------------------------------------------------------*/
#ifndef _lucene_index_MultiReader
#define _lucene_index_MultiReader
@@ -30,7 +21,7 @@
/** An IndexReader which reads multiple indexes, appending their content.
*
- * @version $Id: MultiReader.h 2006 2006-04-27 07:12:38Z ustramooner $
+ * @version $Id: MultiReader.h 2209 2006-06-15 14:12:41Z ustramooner $
*/
class MultiTermDocs:public virtual TermDocs {
private:
@@ -94,8 +85,9 @@
//Move the current term to the next in the set of enumerations
bool next();
- //Returns the current term of the set of enumerations
- Term* term(const bool pointer = true);
+ //Returns a pointer to the current term of the set of enumerations
+ Term* term();
+ Term* term(bool pointer);
//Returns the document frequency of the current term in the set
int32_t docFreq() const;
Modified: trunk/clucene/src/CLucene/index/SegmentHeader.h
===================================================================
--- trunk/clucene/src/CLucene/index/SegmentHeader.h 2006-06-11 07:16:00 UTC (rev 427)
+++ trunk/clucene/src/CLucene/index/SegmentHeader.h 2006-06-26 00:39:24 UTC (rev 428)
@@ -1,18 +1,9 @@
-/**
- * Copyright 2003-2006 The Apache Software Foundation
- *
- * Licensed under the Apache License, Version 2.0 (the "License");
- * you may not use this file except in compliance with the License.
- * You may obtain a copy of the License at
- *
- * http://www.apache.org/licenses/LICENSE-2.0
- *
- * Unless required by applicable law or agreed to in writing, software
- * distributed under the License is distributed on an "AS IS" BASIS,
- * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
- * See the License for the specific language governing permissions and
- * limitations under the License.
- */
+/*------------------------------------------------------------------------------
+* Copyright (C) 2003-2006 Ben van Klinken and the CLucene Team
+*
+* Distributable under the terms of either the Apache License (Version 2.0) or
+* the GNU Lesser General Public License, as specified in the COPYING file.
+------------------------------------------------------------------------------*/
#ifndef _lucene_index_SegmentHeader_
#define _lucene_index_SegmentHeader_
@@ -21,7 +12,7 @@
#endif
#include "SegmentInfos.h"
-#include "CLucene/util/BitVector.h"
+#include "CLucene/util/BitSet.h"
#include "CLucene/util/VoidMap.h"
#include "Term.h"
#include "FieldInfos.h"
@@ -44,7 +35,7 @@
int32_t _doc;
- CL_NS(util)::BitVector* deletedDocs;
+ CL_NS(util)::BitSet* deletedDocs;
CL_NS(store)::IndexInput* freqStream;
int32_t skipInterval;
int32_t numSkips;
@@ -62,7 +53,7 @@
#endif
///\param Parent must be a segment reader
- SegmentTermDocs( SegmentReader* Parent);
+ SegmentTermDocs( const SegmentReader* parent);
virtual ~SegmentTermDocs();
virtual void seek(TermEnum* termEnum);
@@ -99,7 +90,7 @@
public:
///\param Parent must be a segment reader
- SegmentTermPositions(SegmentReader* Parent);
+ SegmentTermPositions(const SegmentReader* parent);
~SegmentTermPositions();
@@ -151,7 +142,6 @@
void reWrite();
};
- private:
//Holds the name of the segment that is being read
const char* segment;
@@ -181,8 +171,8 @@
void doSetNorm(int32_t doc, const TCHAR* field, uint8_t value);
public:
#ifndef LUCENE_HIDE_INTERNAL
- ///For Internal Use. a bitVector that manages which documents have been deleted
- CL_NS(util)::BitVector* deletedDocs;
+ ///For Internal Use. a BitSet that manages which documents have been deleted
+ CL_NS(util)::BitSet* deletedDocs;
///For Internal Use. an IndexInput to the frequency file
CL_NS(store)::IndexInput* freqStream;
///For Internal Use. For reading the fieldInfos file
Modified: trunk/clucene/src/CLucene/index/SegmentInfos.cpp
===================================================================
--- trunk/clucene/src/CLucene/index/SegmentInfos.cpp 2006-06-11 07:16:00 UTC (rev 427)
+++ trunk/clucene/src/CLucene/index/SegmentInfos.cpp 2006-06-26 00:39:24 UTC (rev 428)
@@ -1,18 +1,9 @@
-/**
- * Copyright 2003-2006 The Apache Software Foundation
- *
- * Licensed under the Apache License, Version 2.0 (the "License");
- * you may not use this file except in compliance with the License.
- * You may obtain a copy of the License at
- *
- * http://www.apache.org/licenses/LICENSE-2.0
- *
- * Unless required by applicable law or agreed to in writing, software
- * distributed under the License is distributed on an "AS IS" BASIS,
- * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
- * See the License for the specific language governing permissions and
- * limitations under the License.
- */
+/*------------------------------------------------------------------------------
+* Copyright (C) 2003-2006 Ben van Klinken and the CLucene Team
+*
+* Distributable under the terms of either the Apache License (Version 2.0) or
+* the GNU Lesser General Public License, as specified in the COPYING file.
+------------------------------------------------------------------------------*/
#include "CLucene/StdHeader.h"
#include "SegmentInfos.h"
@@ -33,8 +24,9 @@
// Dir holds the Directory where the segment resides
//Post - The instance has been created. name contains the duplicated string Name.
// docCount = DocCount and dir references Dir
- STRCPY_AtoA(name,Name,CL_MAX_DIR);
- }
+ STRCPY_AtoA(name,Name,CL_MAX_NAME);
+ }
+
SegmentInfo::~SegmentInfo(){
}
@@ -49,7 +41,7 @@
//initialize counter to 0
counter = 0;
- version = 0;
+ version = Misc::currentTimeMillis();
}
SegmentInfos::~SegmentInfos(){
@@ -89,7 +81,7 @@
void SegmentInfos::add(SegmentInfo* info){
infos.push_back(info);
}
- int32_t SegmentInfos::size(){
+ int32_t SegmentInfos::size() const{
return infos.size();
}
@@ -100,7 +92,7 @@
// a SegmentsInfo intance has been created and stored.
//Open an IndexInput to the segments file
- IndexInput* input = directory->openFile("segments");
+ IndexInput* input = directory->openInput("segments");
//Check if input is valid
if (input){
try {
@@ -143,7 +135,7 @@
if(format >= 0){ // in old format the version number may be at the end of the file
if (input->getFilePointer() >= input->length())
- version = 0; // old file format without version number
+ version = Misc::currentTimeMillis(); // old file format without version number
else
version = input->readLong(); // read version
}
@@ -161,7 +153,7 @@
//Post - The new segment has been written to disk
//Open an IndexOutput to the segments file
- IndexOutput* output = directory->createFile("segments.new");
+ IndexOutput* output = directory->createOutput("segments.new");
//Check if output is valid
if (output){
try {
@@ -205,7 +197,7 @@
int64_t SegmentInfos::readCurrentVersion(Directory* directory){
- IndexInput* input = directory->openFile("segments");
+ IndexInput* input = directory->openInput("segments");
int32_t format = 0;
int64_t version = 0;
try {
Modified: trunk/clucene/src/CLucene/index/SegmentInfos.h
===================================================================
--- trunk/clucene/src/CLucene/index/SegmentInfos.h 2006-06-11 07:16:00 UTC (rev 427)
+++ trunk/clucene/src/CLucene/index/SegmentInfos.h 2006-06-26 00:39:24 UTC (rev 428)
@@ -1,18 +1,9 @@
-/**
- * Copyright 2003-2006 The Apache Software Foundation
- *
- * Licensed under the Apache License, Version 2.0 (the "License");
- * you may not use this file except in compliance with the License.
- * You may obtain a copy of the License at
- *
- * http://www.apache.org/licenses/LICENSE-2.0
- *
- * Unless required by applicable law or agreed to in writing, software
- * distributed under the License is distributed on an "AS IS" BASIS,
- * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
- * See the License for the specific language governing permissions and
- * limitations under the License.
- */
+/*------------------------------------------------------------------------------
+* Copyright (C) 2003-2006 Ben van Klinken and the CLucene Team
+*
+* Distributable under the terms of either the Apache License (Version 2.0) or
+* the GNU Lesser General Public License, as specified in the COPYING file.
+------------------------------------------------------------------------------*/
#ifndef _lucene_index_SegmentInfos_
#define _lucene_index_SegmentInfos_
@@ -33,8 +24,8 @@
///Gets the Directory where the segment resides
CL_NS(store)::Directory* getDir() const{ return dir; }
- //Unique name in directory dir
- char name[CL_MAX_DIR];
+ //Unique name in directory dir
+ char name[CL_MAX_NAME];
//Number of docs in the segment
const int32_t docCount;
@@ -75,12 +66,17 @@
//
//Format and Version have not been implemented yet
class SegmentInfos: LUCENE_BASE {
- /** The file format version, a negative number. */
- /* Works since counter, the old 1st entry, is always >= 0 */
- LUCENE_STATIC_CONSTANT(int32_t,FORMAT=-1);
+ /** The file format version, a negative number. */
+ /* Works since counter, the old 1st entry, is always >= 0 */
+ LUCENE_STATIC_CONSTANT(int32_t,FORMAT=-1);
- int64_t version; //counts how often the index has been changed by adding or deleting docs
- segmentInfosType infos;
+ /**
+ * counts how often the index has been changed by adding or deleting docs.
+ * starting with the current time in milliseconds forces to create unique version numbers.
+ */
+ int64_t version;
+
+ segmentInfosType infos;
public:
SegmentInfos(bool deleteMembers=true);
~SegmentInfos();
@@ -88,25 +84,25 @@
#ifndef LUCENE_HIDE_INTERNAL
int32_t counter; // used to name new segments
#endif
+
+ //delete and clears objects 'from' from to 'to'
+ void clearto(size_t to);
+
+ //count of segment infos
+ int32_t size() const;
+ //add a segment info
+ void add(SegmentInfo* info);
+ //Returns a reference to the i-th SegmentInfo in the list.
+ SegmentInfo* info(int32_t i);
+
+ /**
+ * version number when this SegmentInfos was generated.
+ */
+ int64_t getVersion() { return version; }
+
+ static int64_t readCurrentVersion(CL_NS(store)::Directory* directory);
- //delete and clears objects 'from' from to 'to'
- void clearto(size_t to);
-
- //count of segment infos
- int32_t size();
- //add a segment info
- void add(SegmentInfo* info);
- //Returns a reference to the i-th SegmentInfo in the list.
- SegmentInfo* info(int32_t i);
- /**
- * version number when this SegmentInfos was generated.
- */
- int64_t getVersion() { return version; }
-
- static int64_t readCurrentVersion(CL_NS(store)::Directory* directory);
-
-
//Reads segments file that resides in directory
void read(CL_NS(store)::Directory* directory);
Modified: trunk/clucene/src/CLucene/index/SegmentMergeInfo.cpp
===================================================================
--- trunk/clucene/src/CLucene/index/SegmentMergeInfo.cpp 2006-06-11 07:16:00 UTC (rev 427)
+++ trunk/clucene/src/CLucene/index/SegmentMergeInfo.cpp 2006-06-26 00:39:24 UTC (rev 428)
@@ -1,22 +1,12 @@
-/**
- * Copyright 2003-2006 The Apache Software Foundation
- *
- * Licensed under the Apache License, Version 2.0 (the "License");
- * you may not use this file except in compliance with the License.
- * You may obtain a copy of the License at
- *
- * http://www.apache.org/licenses/LICENSE-2.0
- *
- * Unless required by applicable law or agreed to in writing, software
- * distributed under the License is distributed on an "AS IS" BASIS,
- * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
- * See the License for the specific language governing permissions and
- * limitations under the License.
- */
+/*------------------------------------------------------------------------------
+* Copyright (C) 2003-2006 Ben van Klinken and the CLucene Team
+*
+* Distributable under the terms of either the Apache License (Version 2.0) or
+* the GNU Lesser General Public License, as specified in the COPYING file.
+------------------------------------------------------------------------------*/
#include "CLucene/StdHeader.h"
#include "SegmentMergeInfo.h"
-#include "CLucene/util/BitVector.h"
#include "SegmentTermEnum.h"
#include "SegmentHeader.h"
Modified: trunk/clucene/src/CLucene/index/SegmentMergeInfo.h
===================================================================
--- trunk/clucene/src/CLucene/index/SegmentMergeInfo.h 2006-06-11 07:16:00 UTC (rev 427)
+++ trunk/clucene/src/CLucene/index/SegmentMergeInfo.h 2006-06-26 00:39:24 UTC (rev 428)
@@ -1,18 +1,9 @@
-/**
- * Copyright 2003-2006 The Apache Software Foundation
- *
- * Licensed under the Apache License, Version 2.0 (the "License");
- * you may not use this file except in compliance with the License.
- * You may obtain a copy of the License at
- *
- * http://www.apache.org/licenses/LICENSE-2.0
- *
- * Unless required by applicable law or agreed to in writing, software
- * distributed under the License is distributed on an "AS IS" BASIS,
- * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
- * See the License for the specific language governing permissions and
- * limitations under the License.
- */
+/*------------------------------------------------------------------------------
+* Copyright (C) 2003-2006 Ben van Klinken and the CLucene Team
+*
+* Distributable under the terms of either the Apache License (Version 2.0) or
+* the GNU Lesser General Public License, as specified in the COPYING file.
+------------------------------------------------------------------------------*/
#ifndef _lucene_index_SegmentMergeInfo_
#define _lucene_index_SegmentMergeInfo_
@@ -20,7 +11,6 @@
# pragma once
#endif
-#include "CLucene/util/BitVector.h"
#include "SegmentTermEnum.h"
#include "SegmentHeader.h"
Modified: trunk/clucene/src/CLucene/index/SegmentMergeQueue.cpp
===================================================================
--- trunk/clucene/src/CLucene/index/SegmentMergeQueue.cpp 2006-06-11 07:16:00 UTC (rev 427)
+++ trunk/clucene/src/CLucene/index/SegmentMergeQueue.cpp 2006-06-26 00:39:24 UTC (rev 428)
@@ -1,18 +1,9 @@
-/**
- * Copyright 2003-2006 The Apache Software Foundation
- *
- * Licensed under the Apache License, Version 2.0 (the "License");
- * you may not use this file except in compliance with the License.
- * You may obtain a copy of the License at
- *
- * http://www.apache.org/licenses/LICENSE-2.0
- *
- * Unless required by applicable law or agreed to in writing, software
- * distributed under the License is distributed on an "AS IS" BASIS,
- * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
- * See the License for the specific language governing permissions and
- * limitations under the License.
- */
+/*------------------------------------------------------------------------------
+* Copyright (C) 2003-2006 Ben van Klinken and the CLucene Team
+*
+* Distributable under the terms of either the Apache License (Version 2.0) or
+* the GNU Lesser General Public License, as specified in the COPYING file.
+------------------------------------------------------------------------------*/
#include "CLucene/StdHeader.h"
#include "SegmentMergeQueue.h"
Modified: trunk/clucene/src/CLucene/index/SegmentMergeQueue.h
===================================================================
--- trunk/clucene/src/CLucene/index/SegmentMergeQueue.h 2006-06-11 07:16:00 UTC (rev 427)
+++ trunk/clucene/src/CLucene/index/SegmentMergeQueue.h 2006-06-26 00:39:24 UTC (rev 428)
@@ -1,18 +1,9 @@
-/**
- * Copyright 2003-2006 The Apache Software Foundation
- *
- * Licensed under the Apache License, Version 2.0 (the "License");
- * you may not use this file except in compliance with the License.
- * You may obtain a copy of the License at
- *
- * http://www.apache.org/licenses/LICENSE-2.0
- *
- * Unless required by applicable law or agreed to in writing, software
- * distributed under the License is distributed on an "AS IS" BASIS,
- * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
- * See the License for the specific language governing permissions and
- * limitations under the License.
- */
+/*------------------------------------------------------------------------------
+* Copyright (C) 2003-2006 Ben van Klinken and the CLucene Team
+*
+* Distributable under the terms of either the Apache License (Version 2.0) or
+* the GNU Lesser General Public License, as specified in the COPYING file.
+------------------------------------------------------------------------------*/
#ifndef _lucene_index_SegmentMergeQueue_
#define _lucene_index_SegmentMergeQueue_
Modified: trunk/clucene/src/CLucene/index/SegmentMerger.cpp
===================================================================
--- trunk/clucene/src/CLucene/index/SegmentMerger.cpp 2006-06-11 07:16:00 UTC (rev 427)
+++ trunk/clucene/src/CLucene/index/SegmentMerger.cpp 2006-06-26 00:39:24 UTC (rev 428)
@@ -1,18 +1,9 @@
-/**
- * Copyright 2003-2006 The Apache Software Foundation
- *
- * Licensed under the Apache License, Version 2.0 (the "License");
- * you may not use this file except in compliance with the License.
- * You may obtain a copy of the License at
- *
- * http://www.apache.org/licenses/LICENSE-2.0
- *
- * Unless required by applicable law or agreed to in writing, software
- * distributed under the License is distributed on an "AS IS" BASIS,
- * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
- * See the License for the specific language governing permissions and
- * limitations under the License.
- */
+/*------------------------------------------------------------------------------
+* Copyright (C) 2003-2006 Ben van Klinken and the CLucene Team
+*
+* Distributable under the terms of either the Apache License (Version 2.0) or
+* the GNU Lesser General Public License, as specified in the COPYING file.
+------------------------------------------------------------------------------*/
#include "CLucene/StdHeader.h"
#include "SegmentMerger.h"
@@ -22,10 +13,10 @@
CL_NS_DEF(index)
// File extensions of old-style index files
- char* COMPOUND_EXTENSIONS="fnm\0" "frq\0" "prx\0" "fdx\0" "fdt\0" "tii\0" "tis\0";
+ const char* COMPOUND_EXTENSIONS="fnm\0" "frq\0" "prx\0" "fdx\0" "fdt\0" "tii\0" "tis\0";
int COMPOUND_EXTENSIONS_LENGTH=7;
- char* VECTOR_EXTENSIONS="tvx\0" "tvd\0" "tvf\0";
+ const char* VECTOR_EXTENSIONS="tvx\0" "tvd\0" "tvf\0";
int VECTOR_EXTENSIONS_LENGTH=3;
SegmentMerger::SegmentMerger(Directory* dir, const char* name, const bool compoundFile): directory(dir){
@@ -347,14 +338,14 @@
//create a filename for the new Frequency File for segment
const char* buf = Misc::segmentname(segment,".frq");
//Open an IndexOutput to the new Frequency File
- freqOutput = directory->createFile( buf );
+ freqOutput = directory->createOutput( buf );
//Destroy the buffer of the filename
_CLDELETE_CaARRAY(buf);
//create a filename for the new Prox File for segment
buf = Misc::segmentname(segment,".prx");
//Open an IndexOutput to the new Prox File
- proxOutput = directory->createFile( buf );
+ proxOutput = directory->createOutput( buf );
//delete buffer
_CLDELETE_CaARRAY( buf );
@@ -660,7 +651,7 @@
//Create an new filename for the norm file
const char* buf = Misc::segmentname(segment,".f", i);
//Instantiate an IndexOutput to that norm file
- output = directory->createFile( buf );
+ output = directory->createOutput( buf );
//Condition check to see if output points to a valid instance
CND_CONDITION(output != NULL, "No Outputstream retrieved");
Modified: trunk/clucene/src/CLucene/index/SegmentMerger.h
===================================================================
--- trunk/clucene/src/CLucene/index/SegmentMerger.h 2006-06-11 07:16:00 UTC (rev 427)
+++ trunk/clucene/src/CLucene/index/SegmentMerger.h 2006-06-26 00:39:24 UTC (rev 428)
@@ -1,18 +1,9 @@
-/**
- * Copyright 2003-2006 The Apache Software Foundation
- *
- * Licensed under the Apache License, Version 2.0 (the "License");
- * you may not use this file except in compliance with the License.
- * You may obtain a copy of the License at
- *
- * http://www.apache.org/licenses/LICENSE-2.0
- *
- * Unless required by applicable law or agreed to in writing, software
- * distributed under the License is distributed on an "AS IS" BASIS,
- * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
- * See the License for the specific language governing permissions and
- * limitations under the License.
- */
+/*------------------------------------------------------------------------------
+* Copyright (C) 2003-2006 Ben van Klinken and the CLucene Team
+*
+* Distributable under the terms of either the Apache License (Version 2.0) or
+* the GNU Lesser General Public License, as specified in the COPYING file.
+------------------------------------------------------------------------------*/
#ifndef _lucene_index_SegmentMerger_
#define _lucene_index_SegmentMerger_
Modified: trunk/clucene/src/CLucene/index/SegmentReader.cpp
===================================================================
--- trunk/clucene/src/CLucene/index/SegmentReader.cpp 2006-06-11 07:16:00 UTC (rev 427)
+++ trunk/clucene/src/CLucene/index/SegmentReader.cpp 2006-06-26 00:39:24 UTC (rev 428)
@@ -1,18 +1,9 @@
-/**
- * Copyright 2003-2006 The Apache Software Foundation
- *
- * Licensed under the Apache License, Version 2.0 (the "License");
- * you may not use this file except in compliance with the License.
- * You may obtain a copy of the License at
- *
- * http://www.apache.org/licenses/LICENSE-2.0
- *
- * Unless required by applicable law or agreed to in writing, software
- * distributed under the License is distributed on an "AS IS" BASIS,
- * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
- * See the License for the specific language governing permissions and
- * limitations under the License.
- */
+/*------------------------------------------------------------------------------
+* Copyright (C) 2003-2006 Ben van Klinken and the CLucene Team
+*
+* Distributable under the terms of either the Apache License (Version 2.0) or
+* the GNU Lesser General Public License, as specified in the COPYING file.
+------------------------------------------------------------------------------*/
#include "CLucene/StdHeader.h"
#include "SegmentHeader.h"
@@ -20,7 +11,6 @@
#include "FieldsReader.h"
#include "IndexReader.h"
#include "TermInfosReader.h"
-#include "CLucene/util/BitVector.h"
#include "Terms.h"
CL_NS_USE(util)
@@ -28,7 +18,7 @@
CL_NS_USE(document)
CL_NS_DEF(index)
- SegmentReader::Norm::Norm(lucene::store::IndexInput* instrm, int32_t n, SegmentReader* r, const char* seg):
+ SegmentReader::Norm::Norm(IndexInput* instrm, int32_t n, SegmentReader* r, const char* seg):
in(instrm), number(n), reader(r), segment(seg){
//Func - Constructor
//Pre - instrm is a valid reference to an IndexInput
@@ -59,7 +49,7 @@
sprintf(buf,"%s.tmp",segment);
// NOTE: norms are re-written in regular directory, not cfs
- IndexOutput* out = reader->getDirectory()->createFile(buf);
+ IndexOutput* out = reader->getDirectory()->createOutput(buf);
try {
out->writeBytes(bytes, reader->maxDoc());
}_CLFINALLY( out->close(); _CLDELETE(out) );
@@ -133,7 +123,7 @@
freqStream = fsdir->openMMapFile( buf );
}else
#endif
- freqStream = cfsDir->openFile( buf );
+ freqStream = cfsDir->openInput( buf );
//Condition check to see if freqStream points to a valid instance and was able to open the
//frequency file
@@ -143,7 +133,7 @@
SegmentName(buf, CL_MAX_PATH,".prx");
//Open an IndexInput proxStream to the prox file
- proxStream = cfsDir->openFile( buf );
+ proxStream = cfsDir->openInput( buf );
//Condition check to see if proxStream points to a valid instance and was able to open the
//prox file
@@ -167,7 +157,7 @@
//Create a deletion file with suffix .del
SegmentName(buf, CL_MAX_PATH,".del");
//Instantiate a BitVector that manages which documents have been deleted
- deletedDocs = _CLNEW BitVector(getDirectory(), buf );
+ deletedDocs = _CLNEW BitSet(getDirectory(), buf );
}
//Open the norm file. There's a norm file for each indexed field with a byte for each document.
@@ -221,7 +211,7 @@
if (norm->dirty) {
norm->reWrite();
}
- itr++;
+ ++itr;
}
}
deletedDocsDirty = false;
@@ -329,7 +319,7 @@
//Check if deletedDocs exists
if (deletedDocs == NULL){
- deletedDocs = _CLNEW BitVector(maxDoc());
+ deletedDocs = _CLNEW BitSet(maxDoc());
//Condition check to see if deletedDocs points to a valid instance
CND_CONDITION(deletedDocs != NULL,"No memory could be allocated for deletedDocs");
@@ -461,7 +451,7 @@
//Pre - true
//Post - An unpositioned TermDocs enumerator has been returned
- return _CLNEW SegmentTermDocs((SegmentReader*)this);
+ return _CLNEW SegmentTermDocs(this);
}
TermPositions* SegmentReader::termPositions() const {
@@ -469,7 +459,7 @@
//Pre - true
//Post - An unpositioned TermPositions enumerator has been returned
- return _CLNEW SegmentTermPositions((SegmentReader*)this);
+ return _CLNEW SegmentTermPositions(this);
}
int32_t SegmentReader::docFreq(const Term* t) const {
@@ -548,7 +538,7 @@
return;
}
- lucene::store::IndexInput* _normStream = norm->in->clone();
+ IndexInput* _normStream = norm->in->clone();
CND_PRECONDITION(_normStream != NULL, "normStream==NULL")
// read from disk
@@ -668,7 +658,7 @@
if ( !d->fileExists(fileName) )
d = cfsDir;
- _norms.put(fi->name, _CLNEW Norm( d->openFile( fileName ),fi->number, this, segment ));
+ _norms.put(fi->name, _CLNEW Norm( d->openInput( fileName ),fi->number, this, segment ));
}
}
}
@@ -689,7 +679,7 @@
_CLDELETE(n);
//Move the interator to the next norm in the norms collection.
//Note ++ is an overloaded operator
- itr++;
+ ++itr;
}
_norms.clear(); //bvk: they're deleted, so clear them so that they are not re-used
}
@@ -737,7 +727,7 @@
ret[j]=STRDUP_TtoT(t);
j++;
- itr++;
+ ++itr;
}
ret[fieldSet.size()]=NULL;
return ret;
@@ -768,7 +758,7 @@
ret[j]=STRDUP_TtoT(t);
j++;
- itr++;
+ ++itr;
}
ret[fieldSet.size()]=NULL;
return ret;
Modified: trunk/clucene/src/CLucene/index/SegmentTermDocs.cpp
===================================================================
--- trunk/clucene/src/CLucene/index/SegmentTermDocs.cpp 2006-06-11 07:16:00 UTC (rev 427)
+++ trunk/clucene/src/CLucene/index/SegmentTermDocs.cpp 2006-06-26 00:39:24 UTC (rev 428)
@@ -1,35 +1,25 @@
-/**
- * Copyright 2003-2006 The Apache Software Foundation
- *
- * Licensed under the Apache License, Version 2.0 (the "License");
- * you may not use this file except in compliance with the License.
- * You may obtain a copy of the License at
- *
- * http://www.apache.org/licenses/LICENSE-2.0
- *
- * Unless required by applicable law or agreed to in writing, software
- * distributed under the License is distributed on an "AS IS" BASIS,
- * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
- * See the License for the specific language governing permissions and
- * limitations under the License.
- */
+/*------------------------------------------------------------------------------
+* Copyright (C) 2003-2006 Ben van Klinken and the CLucene Team
+*
+* Distributable under the terms of either the Apache License (Version 2.0) or
+* the GNU Lesser General Public License, as specified in the COPYING file.
+------------------------------------------------------------------------------*/
#include "CLucene/StdHeader.h"
#include "SegmentHeader.h"
-#include "CLucene/util/BitVector.h"
#include "CLucene/store/IndexInput.h"
#include "Term.h"
CL_NS_DEF(index)
- SegmentTermDocs::SegmentTermDocs(SegmentReader* Parent){
+ SegmentTermDocs::SegmentTermDocs(const SegmentReader* _parent){
//Func - Constructor
//Pre - Paren != NULL
//Post - The instance has been created
- CND_PRECONDITION(Parent != NULL,"Parent is NULL");
+ CND_PRECONDITION(_parent != NULL,"Parent is NULL");
- parent = Parent;
+ parent = _parent;
deletedDocs = parent->deletedDocs;
_doc = 0;
Modified: trunk/clucene/src/CLucene/index/SegmentTermEnum.cpp
===================================================================
--- trunk/clucene/src/CLucene/index/SegmentTermEnum.cpp 2006-06-11 07:16:00 UTC (rev 427)
+++ trunk/clucene/src/CLucene/index/SegmentTermEnum.cpp 2006-06-26 00:39:24 UTC (rev 428)
@@ -1,18 +1,9 @@
-/**
- * Copyright 2003-2006 The Apache Software Foundation
- *
- * Licensed under the Apache License, Version 2.0 (the "License");
- * you may not use this file except in compliance with the License.
- * You may obtain a copy of the License at
- *
- * http://www.apache.org/licenses/LICENSE-2.0
- *
- * Unless required by applicable law or agreed to in writing, software
- * distributed under the License is distributed on an "AS IS" BASIS,
- * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
- * See the License for the specific language governing permissions and
- * limitations under the License.
- */
+/*------------------------------------------------------------------------------
+* Copyright (C) 2003-2006 Ben van Klinken and the CLucene Team
+*
+* Distributable under the terms of either the Apache License (Version 2.0) or
+* the GNU Lesser General Public License, as specified in the COPYING file.
+------------------------------------------------------------------------------*/
#include "CLucene/StdHeader.h"
#include "SegmentTermEnum.h"
@@ -25,7 +16,7 @@
CL_NS_USE(store)
CL_NS_DEF(index)
- SegmentTermEnum::SegmentTermEnum(store::IndexInput* i, FieldInfos* fis, const bool isi):
+ SegmentTermEnum::SegmentTermEnum(IndexInput* i, FieldInfos* fis, const bool isi):
fieldInfos(fis){
//Func - Constructor
//Pre - i holds a reference to an instance of IndexInput
@@ -35,7 +26,7 @@
input = i;
position = -1;
//Instantiate a Term with empty field, empty text and which is interned (see term.h what interned means)
- _term = _CLNEW Term( LUCENE_BLANK_STRING,LUCENE_BLANK_STRING ,false);
+ _term = _CLNEW Term( LUCENE_BLANK_STRING,LUCENE_BLANK_STRING );
isIndex = isi;
termInfo = _CLNEW TermInfo();
indexPointer = 0;
@@ -203,7 +194,7 @@
return true;
}
- Term* SegmentTermEnum::term(const bool pointer) {
+ Term* SegmentTermEnum::term() {
//Func - Returns the current term.
//Pre - pointer is true or false and indicates if the reference counter
// of term must be increased or not
@@ -211,7 +202,10 @@
//Post - pointer = true -> term has been returned with an increased reference counter
// pointer = false -> term has been returned
- if ( pointer && _term!=NULL )
+ return _CL_POINTER(_term);
+ }
+ Term* SegmentTermEnum::term(bool pointer) {
+ if ( pointer )
return _CL_POINTER(_term);
else
return _term;
Modified: trunk/clucene/src/CLucene/index/SegmentTermEnum.h
===================================================================
--- trunk/clucene/src/CLucene/index/SegmentTermEnum.h 2006-06-11 07:16:00 UTC (rev 427)
+++ trunk/clucene/src/CLucene/index/SegmentTermEnum.h 2006-06-26 00:39:24 UTC (rev 428)
@@ -1,18 +1,9 @@
-/**
- * Copyright 2003-2006 The Apache Software Foundation
- *
- * Licensed under the Apache License, Version 2.0 (the "License");
- * you may not use this file except in compliance with the License.
- * You may obtain a copy of the License at
- *
- * http://www.apache.org/licenses/LICENSE-2.0
- *
- * Unless required by applicable law or agreed to in writing, software
- * distributed under the License is distributed on an "AS IS" BASIS,
- * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
- * See the License for the specific language governing permissions and
- * limitations under the License.
- */
+/*------------------------------------------------------------------------------
+* Copyright (C) 2003-2006 Ben van Klinken and the CLucene Team
+*
+* Distributable under the terms of either the Apache License (Version 2.0) or
+* the GNU Lesser General Public License, as specified in the COPYING file.
+------------------------------------------------------------------------------*/
#ifndef _lucene_index_SegmentTermEnum_
#define _lucene_index_SegmentTermEnum_
@@ -70,8 +61,10 @@
//Moves the current of the set to the next in the set
bool next();
+ //Returns a pointer to the current term.
+ Term* term();
//Returns the current term.
- Term* term(const bool pointer = true);
+ Term* term(bool pointer);
//Scan for Term term without allocating new Terms
void scanTo(const Term *term);
Modified: trunk/clucene/src/CLucene/index/SegmentTermPositions.cpp
===================================================================
--- trunk/clucene/src/CLucene/index/SegmentTermPositions.cpp 2006-06-11 07:16:00 UTC (rev 427)
+++ trunk/clucene/src/CLucene/index/SegmentTermPositions.cpp 2006-06-26 00:39:24 UTC (rev 428)
@@ -1,18 +1,9 @@
-/**
- * Copyright 2003-2006 The Apache Software Foundation
- *
- * Licensed under the Apache License, Version 2.0 (the "License");
- * you may not use this file except in compliance with the License.
- * You may obtain a copy of the License at
- *
- * http://www.apache.org/licenses/LICENSE-2.0
- *
- * Unless required by applicable law or agreed to in writing, software
- * distributed under the License is distributed on an "AS IS" BASIS,
- * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
- * See the License for the specific language governing permissions and
- * limitations under the License.
- */
+/*------------------------------------------------------------------------------
+* Copyright (C) 2003-2006 Ben van Klinken and the CLucene Team
+*
+* Distributable under the terms of either the Apache License (Version 2.0) or
+* the GNU Lesser General Public License, as specified in the COPYING file.
+------------------------------------------------------------------------------*/
#include "CLucene/StdHeader.h"
#include "SegmentHeader.h"
@@ -21,15 +12,15 @@
CL_NS_USE(util)
CL_NS_DEF(index)
- SegmentTermPositions::SegmentTermPositions(SegmentReader* Parent):
- SegmentTermDocs(Parent){
+ SegmentTermPositions::SegmentTermPositions(const SegmentReader* _parent):
+ SegmentTermDocs(_parent){
//Func - Constructor
//Pre - Parent != NULL
//Post - The instance has been created
- CND_PRECONDITION(Parent != NULL, "Parent is NULL");
+ CND_PRECONDITION(_parent != NULL, "Parent is NULL");
- proxStream = ((SegmentReader*)parent)->proxStream->clone();
+ proxStream = _parent->proxStream->clone();
CND_CONDITION(proxStream != NULL,"proxStream is NULL");
Modified: trunk/clucene/src/CLucene/index/SegmentTermVector.cpp
===================================================================
--- trunk/clucene/src/CLucene/index/SegmentTermVector.cpp 2006-06-11 07:16:00 UTC (rev 427)
+++ trunk/clucene/src/CLucene/index/SegmentTermVector.cpp 2006-06-26 00:39:24 UTC (rev 428)
@@ -1,18 +1,9 @@
-/**
- * Copyright 2003-2006 The Apache Software Foundation
- *
- * Licensed under the Apache License, Version 2.0 (the "License");
- * you may not use this file except in compliance with the License.
- * You may obtain a copy of the License at
- *
- * http://www.apache.org/licenses/LICENSE-2.0
- *
- * Unless required by applicable law or agreed to in writing, software
- * distributed under the License is distributed on an "AS IS" BASIS,
- * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
- * See the License for the specific language governing permissions and
- * limitations under the License.
- */
+/*------------------------------------------------------------------------------
+* Copyright (C) 2003-2006 Ben van Klinken and the CLucene Team
+*
+* Distributable under the terms of either the Apache License (Version 2.0) or
+* the GNU Lesser General Public License, as specified in the COPYING file.
+------------------------------------------------------------------------------*/
#include "CLucene/StdHeader.h"
#include "TermVector.h"
#include "CLucene/util/StringBuffer.h"
@@ -38,7 +29,7 @@
return field;
}
- TCHAR* SegmentTermVector::toString() {
+ TCHAR* SegmentTermVector::toString() const{
StringBuffer sb;
sb.appendChar('{');
sb.append(field);
@@ -61,11 +52,11 @@
if ( terms == NULL )
return 0;
- if ( termsLen == -1 ){
- termsLen=0;
- while ( terms[termsLen] != 0 )
- termsLen++;
- }
+ if ( termsLen == -1 ){
+ termsLen=0;
+ while ( terms[termsLen] != 0 )
+ termsLen++;
+ }
return termsLen;
}
Modified: trunk/clucene/src/CLucene/index/Term.cpp
===================================================================
--- trunk/clucene/src/CLucene/index/Term.cpp 2006-06-11 07:16:00 UTC (rev 427)
+++ trunk/clucene/src/CLucene/index/Term.cpp 2006-06-26 00:39:24 UTC (rev 428)
@@ -1,247 +1,237 @@
-/**
- * Copyright 2003-2006 The Apache Software Foundation
- *
- * Licensed under the Apache License, Version 2.0 (the "License");
- * you may not use this file except in compliance with the License.
- * You may obtain a copy of the License at
- *
- * http://www.apache.org/licenses/LICENSE-2.0
- *
- * Unless required by applicable law or agreed to in writing, software
- * distributed under the License is distributed on an "AS IS" BASIS,
- * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
- * See the License for the specific language governing permissions and
- * limitations under the License.
- */
+/*------------------------------------------------------------------------------
+* Copyright (C) 2003-2006 Ben van Klinken and the CLucene Team
+*
+* Distributable under the terms of either the Apache License (Version 2.0) or
+* the GNU Lesser General Public License, as specified in the COPYING file.
+------------------------------------------------------------------------------*/
#include "CLucene/StdHeader.h"
#include "Term.h"
#include "CLucene/util/StringIntern.h"
CL_NS_USE(util)
CL_NS_DEF(index)
-
- Term::Term(){
- //Intern fld and assign it to field
- _field = LUCENE_BLANK_STRING;
- internF = false;
- cachedHashCode = 0;
- textLen = 0;
+Term::Term(){
+ //Intern fld and assign it to field
+ _field = LUCENE_BLANK_STRING;
+ internF = false;
+ cachedHashCode = 0;
+ textLen = 0;
- //Duplicate txt and assign it to text
-#ifdef LUCENE_TERM_TEXT_LENGTH
- _text[0]=0;
-#else
+ //Duplicate txt and assign it to text
+ #ifdef LUCENE_TERM_TEXT_LENGTH
+ _text[0]=0;
+ #else
_text = LUCENE_BLANK_STRING;
- dupT = false;
-#endif
- }
+ textLenBuf = 0;
+ #endif
+ textLen = 0;
+}
- Term::Term(const TCHAR* fld, const TCHAR* txt,const bool internField){
- //Func - Constructor.
- // Constructs a Term with the given field and text. Field and text are not copied
- // Field and text are deleted in destructor only if intern is false.
- //Pre - fld != NULL and contains the name of the field
- // txt != NULL and contains the value of the field
- // internF is true or false and indicates if term Field is interned or not
- // internT is true or false and indicates if term Text is interned or not
- // canDelete defaults to true but can be false and indicates to the IGarbageCollector that the Term can be deleted when finalized
- //Post - An instance of Term has been created.Field and txt have not been copied but assigned
+Term::Term(const TCHAR* fld, const TCHAR* txt,const bool internField){
+//Func - Constructor.
+// Constructs a Term with the given field and text. Field and text are not copied
+// Field and text are deleted in destructor only if intern is false.
+//Pre - fld != NULL and contains the name of the field
+// txt != NULL and contains the value of the field
+// internF is true or false and indicates if term Field is interned or not
+// internT is true or false and indicates if term Text is interned or not
+// canDelete defaults to true but can be false and indicates to the IGarbageCollector that the Term can be deleted when finalized
+//Post - An instance of Term has been created.Field and txt have not been copied but assigned
+
+ _field = LUCENE_BLANK_STRING;
+ internF = false;
+ textLen = 0;
+ #ifdef LUCENE_TERM_TEXT_LENGTH
+ _text[0]=0;
+ #else
+ _text = LUCENE_BLANK_STRING;
+ textLenBuf = 0;
+ #endif
- CND_PRECONDITION(fld != NULL, "fld contains NULL");
- CND_PRECONDITION(txt != NULL, "txt contains NULL");
+ set(fld,txt,internField);
+}
- //todo: this needs to be re-thought. i suggest allowing construction
- //using an iterator containing the field field which can then
- //be directly manipulated.
- //if ( internField )
- _field = CLStringIntern::intern(fld CL_FILELINE);
- //else
- // _field = fld;
- internF = internField;
- cachedHashCode = 0;
+Term::Term(const TCHAR* fld, const TCHAR* txt){
+ _field = LUCENE_BLANK_STRING;
+ internF = false;
+ textLen = 0;
+ #ifdef LUCENE_TERM_TEXT_LENGTH
+ _text[0]=0;
+ #else
+ _text = LUCENE_BLANK_STRING;
+ textLenBuf = 0;
+ #endif
- textLen = _tcslen(txt);
-
- //duplicate text if necessary
-#ifdef LUCENE_TERM_TEXT_LENGTH
- if ( textLen > LUCENE_TERM_TEXT_LENGTH )
- textLen = LUCENE_TERM_TEXT_LENGTH;
- _tcsncpy(_text,txt,textLen+1);
- _text[textLen]=0;
-#else
- dupT = true;
- //if ( duplicateText ){
- if ( txt[0]==0 ){
- _text = LUCENE_BLANK_STRING;
- dupT = false;
- }else
- _text = stringDuplicate(txt);
- /*}else
- _text = txt;*/
- textLenBuf = textLen;
-#endif
+ set(fld,txt);
+}
- //this->_canDelete = canDelete;
- }
-
- Term::~Term(){
- //Func - Destructor.
- //Pre - true
- //Post - The instance has been destroyed. field and text have been deleted if pre(intrn) is false
+Term::~Term(){
+//Func - Destructor.
+//Pre - true
+//Post - The instance has been destroyed. field and text have been deleted if pre(intrn) is false
- //Unintern field
- //if ( internF )
- CLStringIntern::unintern(_field);
- _field = NULL;
+ //Unintern field
+ //if ( internF )
+ CLStringIntern::unintern(_field);
+ _field = NULL;
#ifndef LUCENE_TERM_TEXT_LENGTH
- //Deletetext if it is the owner
- if ( dupT && _text)
- _CLDELETE_CARRAY( _text );
+ //Deletetext if it is the owner
+ if ( _text != LUCENE_BLANK_STRING)
+ _CLDELETE_CARRAY( _text );
#endif
- }
+}
- const TCHAR* Term::field() const {
- //Func - Returns the field of this term, an interned string. The field indicates
- // the part of a document which this term came from.
- //Pre - true
- //Post - field has been returned
+const TCHAR* Term::field() const {
+//Func - Returns the field of this term, an interned string. The field indicates
+// the part of a document which this term came from.
+//Pre - true
+//Post - field has been returned
- return _field;
- }
+ return _field;
+}
- const TCHAR* Term::text() const {
- //Func - Returns the text of this term. In the case of words, this is simply the
- // text of the word. In the case of dates and other types, this is an
- // encoding of the object as a string.
- //Pre - true
- //Post - text has been returned
+const TCHAR* Term::text() const {
+//Func - Returns the text of this term. In the case of words, this is simply the
+// text of the word. In the case of dates and other types, this is an
+// encoding of the object as a string.
+//Pre - true
+//Post - text has been returned
- return _text;
- }
+ return _text;
+}
- void Term::set(const TCHAR* fld, const TCHAR* txt,const bool internField){
- //Func - Resets the field and text of a Term.
- //Pre - fld != NULL and contains the name of the field
- // txt != NULL and contains the value of the field
- // internF is true or false
- // internT is true or false
- //Post - field and text of Term have been reset
- CND_PRECONDITION(fld != NULL, "fld contains NULL");
- CND_PRECONDITION(txt != NULL, "txt contains NULL");
+void Term::set(Term* term, const TCHAR* txt){
+ set(term->field(),txt,false);
+}
- //save field for unintern later
- const TCHAR* oldField = _field;
- bool oldInternF = internF;
- cachedHashCode = 0;
+void Term::set(const TCHAR* fld, const TCHAR* txt,const bool internField){
+//Func - Resets the field and text of a Term.
+//Pre - fld != NULL and contains the name of the field
+// txt != NULL and contains the value of the field
+// internF is true or false
+// internT is true or false
+//Post - field and text of Term have been reset
- textLen = _tcslen(txt);
+ CND_PRECONDITION(fld != NULL, "fld contains NULL");
+ CND_PRECONDITION(txt != NULL, "txt contains NULL");
- //Delete text if it is the owner
+ //save field for unintern later
+ const TCHAR* oldField = _field;
+ bool oldInternF = internF;
+ cachedHashCode = 0;
+
+ textLen = _tcslen(txt);
+
+ //Delete text if it is the owner
#ifdef LUCENE_TERM_TEXT_LENGTH
- if ( textLen > LUCENE_TERM_TEXT_LENGTH )
- textLen = LUCENE_TERM_TEXT_LENGTH;
- _tcsncpy(_text,txt,textLen+1);
- _text[textLen]=0;
+ if ( textLen > LUCENE_TERM_TEXT_LENGTH )
+ textLen = LUCENE_TERM_TEXT_LENGTH;
+ _tcsncpy(_text,txt,textLen+1);
+ _text[textLen]=0;
#else
- //assign new text
- bool olddupT = dupT;
- dupT = true;
+ //assign new text
+ //bool olddupT = dupT;
+ //dupT = true;
- //if ( duplicateText ){
- //if the term text buffer is bigger than what we have
- if ( !olddupT && _text ){
- _text = NULL;
- textLenBuf = 0;
- }else if ( _text && textLen > textLenBuf){
- _CLDELETE_ARRAY( _text );
- textLenBuf = 0;
- }
+ //if the term text buffer is bigger than what we have
+ /*if ( !olddupT && _text ){
+ _text = NULL;
+ textLenBuf = 0;
+ }else */
+ if ( _text && textLen > textLenBuf){
+ if ( _text != LUCENE_BLANK_STRING ){
+ _CLDELETE_ARRAY( _text );
+ }else
+ _text = NULL;
+ textLenBuf = 0;
+ }
- if ( _text==NULL ){
- if ( txt[0] == 0 ){
- //if the string is blank and we aren't re-using the buffer...
- _text = LUCENE_BLANK_STRING;
- dupT = false;
- }else{
- //duplicate the text
- _text = stringDuplicate(txt);
- textLenBuf = textLen;
- }
- }else{
- //re-use the buffer
- _tcscpy(_text,txt);
- }
+ if ( _text==LUCENE_BLANK_STRING )
+ _text = LUCENE_BLANK_STRING;
+ else if ( _text==NULL ){
+ if ( txt[0] == 0 ){
+ //if the string is blank and we aren't re-using the buffer...
+ _text = LUCENE_BLANK_STRING;
+ //dupT = false;
+ }else{
+ //duplicate the text
+ _text = stringDuplicate(txt);
+ textLenBuf = textLen;
+ }
+ }else{
+ //re-use the buffer
+ _tcscpy(_text,txt);
+ }
#endif
- //Set Term Field
- //if ( internField )
- _field = CLStringIntern::intern(fld CL_FILELINE);
- //else
- // _field = fld;
- internF = internField;
+ //Set Term Field
+ if ( internField )
+ _field = CLStringIntern::intern(fld CL_FILELINE);
+ else
+ _field = CLStringIntern::intern(fld CL_FILELINE); //todo: our interning is not optimised yet...
+ internF = internField;
- //unintern old field after interning new one,
- //if ( oldInternF )
- CLStringIntern::unintern(oldField);
- }
+ //unintern old field after interning new one,
+ //if ( oldInternF )
+ CLStringIntern::unintern(oldField);
+}
- /** Compares two terms, returning true iff they have the same
- field and text. */
- bool Term::equals(const Term* other) const{
- if ( cachedHashCode != 0 && other->cachedHashCode != 0 &&
- other->cachedHashCode != cachedHashCode )
- return false;
+/** Compares two terms, returning true iff they have the same
+ field and text. */
+bool Term::equals(const Term* other) const{
+ if ( cachedHashCode != 0 && other->cachedHashCode != 0 &&
+ other->cachedHashCode != cachedHashCode )
+ return false;
- if ( _field==other->_field ){
- //this can be quicker than using compareTo, because checks
- //field length first
- if ( textLen == other->textLen ){
-
- return (_tcscmp(_text,other->_text)==0);
- }else
- return false;
- }else
- return false;
- }
+ if ( _field==other->_field ){
+ //this can be quicker than using compareTo, because checks
+ //field length first
+ if ( textLen == other->textLen ){
+ return (_tcscmp(_text,other->_text)==0);
+ }else
+ return false;
+ }else
+ return false;
+}
- size_t Term::hashCode(){
- if ( cachedHashCode != 0 )
- return cachedHashCode;
-
- cachedHashCode = Misc::thashCode(_field) + Misc::thashCode(_text,textLen);
+size_t Term::hashCode(){
+ if ( cachedHashCode != 0 )
return cachedHashCode;
- }
+ cachedHashCode = Misc::thashCode(_field) + Misc::thashCode(_text,textLen);
+ return cachedHashCode;
+}
- int32_t Term::compareTo(const Term* other) const {
- //Func - Compares two terms, to see if this term belongs before,is equal to or after
- // after the argument term.
- //Pre - other is a reference to another term
- //Post - A negative integer is returned if this term belongs before the argument,
- // zero is returned if this term is equal to the argument, and a positive integer
- // if this term belongs after the argument.
- //Check ret to see if text needs to be compared
- if ( _field == other->_field ){ // fields are interned
- //Compare text with text of other and return the result
- return _tcscmp(_text,other->_text);
- }else
- return _tcscmp(_field,other->_field);
- }
+int32_t Term::compareTo(const Term* other) const {
+//Func - Compares two terms, to see if this term belongs before,is equal to or after
+// after the argument term.
+//Pre - other is a reference to another term
+//Post - A negative integer is returned if this term belongs before the argument,
+// zero is returned if this term is equal to the argument, and a positive integer
+// if this term belongs after the argument.
- TCHAR* Term::toString() const{
- //Func - Forms the contents of Field and term in some kind of tuple notation
- // <field:text>
- //Pre - true
- //Post - a string formatted as <field:text> is returned if pre(field) is NULL and
- // text is NULL the returned string will be formatted as <:>
+ //Check ret to see if text needs to be compared
+ if ( _field == other->_field ){ // fields are interned
+ //Compare text with text of other and return the result
+ return _tcscmp(_text,other->_text);
+ }else
+ return _tcscmp(_field,other->_field);
+}
- return CL_NS(util)::Misc::join( _field, _T(":"), _text);
- }
+TCHAR* Term::toString() const{
+//Func - Forms the contents of Field and term in some kind of tuple notation
+// <field:text>
+//Pre - true
+//Post - a string formatted as <field:text> is returned if pre(field) is NULL and
+// text is NULL the returned string will be formatted as <:>
+ return CL_NS(util)::Misc::join( _field, _T(":"), _text);
+}
+
CL_NS_END
Modified: trunk/clucene/src/CLucene/index/Term.h
===================================================================
--- trunk/clucene/src/CLucene/index/Term.h 2006-06-11 07:16:00 UTC (rev 427)
+++ trunk/clucene/src/CLucene/index/Term.h 2006-06-26 00:39:24 UTC (rev 428)
@@ -1,18 +1,9 @@
-/**
- * Copyright 2003-2006 The Apache Software Foundation
- *
- * Licensed under the Apache License, Version 2.0 (the "License");
- * you may not use this file except in compliance with the License.
- * You may obtain a copy of the License at
- *
- * http://www.apache.org/licenses/LICENSE-2.0
- *
- * Unless required by applicable law or agreed to in writing, software
- * distributed under the License is distributed on an "AS IS" BASIS,
- * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
- * See the License for the specific language governing permissions and
- * limitations under the License.
- */
+/*------------------------------------------------------------------------------
+* Copyright (C) 2003-2006 Ben van Klinken and the CLucene Team
+*
+* Distributable under the terms of either the Apache License (Version 2.0) or
+* the GNU Lesser General Public License, as specified in the COPYING file.
+------------------------------------------------------------------------------*/
#ifndef _lucene_index_Term_
#define _lucene_index_Term_
@@ -56,11 +47,16 @@
#else
TCHAR* _text;
size_t textLenBuf; //a cache of text len, this allows for a preliminary comparison of text lengths
- bool dupT; //Indicates if Term Text is duplicated (and therefore must be deleted).
+ //bool dupT; //Indicates if Term Text is duplicated (and therefore must be deleted).
#endif
size_t textLen; //a cache of text len, this allows for a preliminary comparison of text lengths
bool internF; //Indicates if Term Field is interned(and therefore must be uninternd).
+
public:
+
+ //todo: these need to be private, but a few other things need to be changed first...
+ Term(const TCHAR* fld, const TCHAR* txt, bool internField);
+ void set(const TCHAR* fld, const TCHAR* txt, const bool internField);
///Constructs a blank term
Term();
@@ -69,7 +65,7 @@
* Constructor. Constructs a Term with the given field and text. Field and text are not copied
* Field and text are deleted in destructor only if intern is false.
*/
- Term(const TCHAR* fld, const TCHAR* txt, const bool internField=true); //todo:, const bool duplicateText
+ Term(const TCHAR* fld, const TCHAR* txt);
///Destructor.
~Term();
@@ -84,10 +80,22 @@
const TCHAR* text() const; ///<returns reference
///Resets the field and text of a Term.
- void set(const TCHAR* fld, const TCHAR* txt, const bool internField=true); //todo:, const bool duplicateText=true
+ inline void set(const TCHAR* fld, const TCHAR* txt){
+ set(fld,txt,true);
+ }
+
+ /**
+ * Optimized set of Term by reusing same field as this Term
+ * - avoids field.intern() overhead
+ * @param text The text of the new term (field is implicitly same as this Term instance)
+ */
+ void set(Term* term, const TCHAR* txt);
- ///Compares two terms, to see if this term belongs before,is equal to or after
- ///after the argument term.
+ /** Compares two terms, returning a negative integer if this
+ term belongs before the argument, zero if this term is equal to the
+ argument, and a positive integer if this term belongs after the argument.
+
+ The ordering of terms is first by field, then by text.*/
int32_t compareTo(const Term* other) const;
bool equals(const Term* other) const;
Modified: trunk/clucene/src/CLucene/index/TermInfo.cpp
===================================================================
--- trunk/clucene/src/CLucene/index/TermInfo.cpp 2006-06-11 07:16:00 UTC (rev 427)
+++ trunk/clucene/src/CLucene/index/TermInfo.cpp 2006-06-26 00:39:24 UTC (rev 428)
@@ -1,108 +1,98 @@
-/**
- * Copyright 2003-2006 The Apache Software Foundation
- *
- * Licensed under the Apache License, Version 2.0 (the "License");
- * you may not use this file except in compliance with the License.
- * You may obtain a copy of the License at
- *
- * http://www.apache.org/licenses/LICENSE-2.0
- *
- * Unless required by applicable law or agreed to in writing, software
- * distributed under the License is distributed on an "AS IS" BASIS,
- * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
- * See the License for the specific language governing permissions and
- * limitations under the License.
- */
+/*------------------------------------------------------------------------------
+* Copyright (C) 2003-2006 Ben van Klinken and the CLucene Team
+*
+* Distributable under the terms of either the Apache License (Version 2.0) or
+* the GNU Lesser General Public License, as specified in the COPYING file.
+------------------------------------------------------------------------------*/
#include "CLucene/StdHeader.h"
#include "TermInfo.h"
CL_NS_DEF(index)
- TermInfo::TermInfo(){
- //Func - Constructor
- //Pre - true
- //Post - Instance has been created
-
- docFreq = 0;
- freqPointer = 0;
- proxPointer = 0;
- skipOffset = 0;
- }
+TermInfo::TermInfo(){
+//Func - Constructor
+//Pre - true
+//Post - Instance has been created
+
+ docFreq = 0;
+ freqPointer = 0;
+ proxPointer = 0;
+ skipOffset = 0;
+}
- TermInfo::~TermInfo(){
- //Func - Destructor.
- //Pre - true
- //Post - Instance has been destroyed
- }
+TermInfo::~TermInfo(){
+//Func - Destructor.
+//Pre - true
+//Post - Instance has been destroyed
+}
- TermInfo::TermInfo(const int32_t df, const int64_t fp, const int64_t pp){
- //Func - Constructor.
- //Pre - df >= 0, fp >= 0 pp >= 0
- //Post - An instance has been created with FreqPointer = fp, proxPointer=pp and docFreq= df
+TermInfo::TermInfo(const int32_t df, const int64_t fp, const int64_t pp){
+//Func - Constructor.
+//Pre - df >= 0, fp >= 0 pp >= 0
+//Post - An instance has been created with FreqPointer = fp, proxPointer=pp and docFreq= df
- CND_PRECONDITION(df >= 0, "df contains negative number");
- CND_PRECONDITION(fp >= 0, "fp contains negative number");
- CND_PRECONDITION(pp >= 0, "pp contains negative number");
+ CND_PRECONDITION(df >= 0, "df contains negative number");
+ CND_PRECONDITION(fp >= 0, "fp contains negative number");
+ CND_PRECONDITION(pp >= 0, "pp contains negative number");
- freqPointer = fp;
- proxPointer = pp;
- docFreq = df;
- skipOffset = 0;
- }
+ freqPointer = fp;
+ proxPointer = pp;
+ docFreq = df;
+ skipOffset = 0;
+}
- TermInfo::TermInfo(const TermInfo* ti) {
- //Func - Constructor.
- // Initialises this instance by copying the values of another TermInfo ti
- //Pre - ti is a reference to another TermInfo
- // ti->docFreq >= 0
- // ti->freqPointer >= 0
- // ti->proxPointer >= 0
- //Post - Values of ti have been copied to the values of this Instance.
+TermInfo::TermInfo(const TermInfo* ti) {
+//Func - Constructor.
+// Initialises this instance by copying the values of another TermInfo ti
+//Pre - ti is a reference to another TermInfo
+// ti->docFreq >= 0
+// ti->freqPointer >= 0
+// ti->proxPointer >= 0
+//Post - Values of ti have been copied to the values of this Instance.
- CND_PRECONDITION(ti->docFreq >= 0, "ti->docFreq contains negative number");
- CND_PRECONDITION(ti->freqPointer >= 0, "ti->freqPointer contains negative number");
- CND_PRECONDITION(ti->proxPointer >= 0, "ti->proxPointer contains negative number");
+ CND_PRECONDITION(ti->docFreq >= 0, "ti->docFreq contains negative number");
+ CND_PRECONDITION(ti->freqPointer >= 0, "ti->freqPointer contains negative number");
+ CND_PRECONDITION(ti->proxPointer >= 0, "ti->proxPointer contains negative number");
- docFreq = ti->docFreq;
- freqPointer = ti->freqPointer;
- proxPointer = ti->proxPointer;
- skipOffset = ti->skipOffset;
- }
+ docFreq = ti->docFreq;
+ freqPointer = ti->freqPointer;
+ proxPointer = ti->proxPointer;
+ skipOffset = ti->skipOffset;
+}
- void TermInfo::set(const int32_t df, const int64_t fp, const int64_t pp, const int32_t so) {
- //Func - Sets a new document frequency, a new freqPointer and a new proxPointer
- //Pre - df >= 0, fp >= 0 pp >= 0
- //Post - The new document frequency, a new freqPointer and a new proxPointer
- // have been set
+void TermInfo::set(const int32_t df, const int64_t fp, const int64_t pp, const int32_t so) {
+//Func - Sets a new document frequency, a new freqPointer and a new proxPointer
+//Pre - df >= 0, fp >= 0 pp >= 0
+//Post - The new document frequency, a new freqPointer and a new proxPointer
+// have been set
- CND_PRECONDITION(df >= 0, "df contains negative number");
- CND_PRECONDITION(fp >= 0, "fp contains negative number");
- CND_PRECONDITION(pp >= 0, "pp contains negative number");
+ CND_PRECONDITION(df >= 0, "df contains negative number");
+ CND_PRECONDITION(fp >= 0, "fp contains negative number");
+ CND_PRECONDITION(pp >= 0, "pp contains negative number");
- docFreq = df;
- freqPointer = fp;
- proxPointer = pp;
- skipOffset = so;
- }
+ docFreq = df;
+ freqPointer = fp;
+ proxPointer = pp;
+ skipOffset = so;
+}
- void TermInfo::set(const TermInfo* ti) {
- //Func - Sets a new document frequency, a new freqPointer and a new proxPointer
- // by copying these values from another instance of TermInfo
- //Pre - ti is a reference to another TermInfo
- // ti->docFreq >= 0
- // ti->freqPointer >= 0
- // ti->proxPointer >= 0
- //Post - Values of ti have been copied to the values of this Instance.
+void TermInfo::set(const TermInfo* ti) {
+//Func - Sets a new document frequency, a new freqPointer and a new proxPointer
+// by copying these values from another instance of TermInfo
+//Pre - ti is a reference to another TermInfo
+// ti->docFreq >= 0
+// ti->freqPointer >= 0
+// ti->proxPointer >= 0
+//Post - Values of ti have been copied to the values of this Instance.
- CND_PRECONDITION(ti->docFreq >= 0, "ti->docFreq contains negative number");
- CND_PRECONDITION(ti->freqPointer >= 0, "ti->freqPointer contains negative number");
- CND_PRECONDITION(ti->proxPointer >= 0, "ti->proxPointer contains negative number");
+ CND_PRECONDITION(ti->docFreq >= 0, "ti->docFreq contains negative number");
+ CND_PRECONDITION(ti->freqPointer >= 0, "ti->freqPointer contains negative number");
+ CND_PRECONDITION(ti->proxPointer >= 0, "ti->proxPointer contains negative number");
- docFreq = ti->docFreq;
- freqPointer = ti->freqPointer;
- proxPointer = ti->proxPointer;
- skipOffset = ti->skipOffset;
- }
+ docFreq = ti->docFreq;
+ freqPointer = ti->freqPointer;
+ proxPointer = ti->proxPointer;
+ skipOffset = ti->skipOffset;
+}
CL_NS_END
-
Modified: trunk/clucene/src/CLucene/index/TermInfo.h
===================================================================
--- trunk/clucene/src/CLucene/index/TermInfo.h 2006-06-11 07:16:00 UTC (rev 427)
+++ trunk/clucene/src/CLucene/index/TermInfo.h 2006-06-26 00:39:24 UTC (rev 428)
@@ -1,18 +1,9 @@
-/**
- * Copyright 2003-2006 The Apache Software Foundation
- *
- * Licensed under the Apache License, Version 2.0 (the "License");
- * you may not use this file except in compliance with the License.
- * You may obtain a copy of the License at
- *
- * http://www.apache.org/licenses/LICENSE-2.0
- *
- * Unless required by applicable law or agreed to in writing, software
- * distributed under the License is distributed on an "AS IS" BASIS,
- * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
- * See the License for the specific language governing permissions and
- * limitations under the License.
- */
+/*------------------------------------------------------------------------------
+* Copyright (C) 2003-2006 Ben van Klinken and the CLucene Team
+*
+* Distributable under the terms of either the Apache License (Version 2.0) or
+* the GNU Lesser General Public License, as specified in the COPYING file.
+------------------------------------------------------------------------------*/
#ifndef _lucene_index_TermInfo
#define _lucene_index_TermInfo
@@ -24,44 +15,44 @@
CL_NS_DEF(index)
- LUCENE_MP_DEFINE(TermInfo)
- // A TermInfo is the record of information stored for a term.
- class TermInfo: LUCENE_POOLEDBASE(TermInfo){
- public:
- // The number of documents which contain the term.
- int32_t docFreq;
+LUCENE_MP_DEFINE(TermInfo)
+// A TermInfo is the record of information stored for a term.
+class TermInfo: LUCENE_POOLEDBASE(TermInfo){
+public:
+ // The number of documents which contain the term.
+ int32_t docFreq;
- //A pointer into the TermFreqs file (.frq)
- //The .frq file contains the lists of documents which contain each term,
- //along with the frequency of the term in that document.
- int64_t freqPointer;
+ //A pointer into the TermFreqs file (.frq)
+ //The .frq file contains the lists of documents which contain each term,
+ //along with the frequency of the term in that document.
+ int64_t freqPointer;
- //A pointer into the TermPosition file (.prx).
- //The .prx file contains the lists of positions that each term
- //occurs at within documents.
- int64_t proxPointer;
+ //A pointer into the TermPosition file (.prx).
+ //The .prx file contains the lists of positions that each term
+ //occurs at within documents.
+ int64_t proxPointer;
- int32_t skipOffset;
+ int32_t skipOffset;
- //Constructor
- TermInfo();
+ //Constructor
+ TermInfo();
- //Constructor
- TermInfo(const int32_t df, const int64_t fp, const int64_t pp);
+ //Constructor
+ TermInfo(const int32_t df, const int64_t fp, const int64_t pp);
- //Constructor
- //Initialises this instance by copying the values of another TermInfo ti
- TermInfo(const TermInfo* ti);
+ //Constructor
+ //Initialises this instance by copying the values of another TermInfo ti
+ TermInfo(const TermInfo* ti);
- //Destructor
- ~TermInfo();
+ //Destructor
+ ~TermInfo();
- //Sets a new document frequency, a new freqPointer and a new proxPointer
- void set(const int32_t docFreq, const int64_t freqPointer, const int64_t proxPointer, int32_t skipOffset);
+ //Sets a new document frequency, a new freqPointer and a new proxPointer
+ void set(const int32_t docFreq, const int64_t freqPointer, const int64_t proxPointer, int32_t skipOffset);
- //Sets a new document frequency, a new freqPointer and a new proxPointer
- //by copying these values from another instance of TermInfo
- void set(const TermInfo* ti);
- };
+ //Sets a new document frequency, a new freqPointer and a new proxPointer
+ //by copying these values from another instance of TermInfo
+ void set(const TermInfo* ti);
+};
CL_NS_END
#endif
Modified: trunk/clucene/src/CLucene/index/TermInfosReader.cpp
===================================================================
--- trunk/clucene/src/CLucene/index/TermInfosReader.cpp 2006-06-11 07:16:00 UTC (rev 427)
+++ trunk/clucene/src/CLucene/index/TermInfosReader.cpp 2006-06-26 00:39:24 UTC (rev 428)
@@ -1,18 +1,9 @@
-/**
- * Copyright 2003-2006 The Apache Software Foundation
- *
- * Licensed under the Apache License, Version 2.0 (the "License");
- * you may not use this file except in compliance with the License.
- * You may obtain a copy of the License at
- *
- * http://www.apache.org/licenses/LICENSE-2.0
- *
- * Unless required by applicable law or agreed to in writing, software
- * distributed under the License is distributed on an "AS IS" BASIS,
- * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
- * See the License for the specific language governing permissions and
- * limitations under the License.
- */
+/*------------------------------------------------------------------------------
+* Copyright (C) 2003-2006 Ben van Klinken and the CLucene Team
+*
+* Distributable under the terms of either the Apache License (Version 2.0) or
+* the GNU Lesser General Public License, as specified in the COPYING file.
+------------------------------------------------------------------------------*/
#include "CLucene/StdHeader.h"
#include "TermInfosReader.h"
@@ -59,8 +50,8 @@
char* tiiFile = Misc::segmentname(segment,".tii");
//Create an SegmentTermEnum for storing all the terms read of the segment
- origEnum = _CLNEW SegmentTermEnum( directory->openFile( tisFile ), fieldInfos, false);
- indexEnum = _CLNEW SegmentTermEnum( directory->openFile( tiiFile ), fieldInfos, true);
+ origEnum = _CLNEW SegmentTermEnum( directory->openInput( tisFile ), fieldInfos, false);
+ indexEnum = _CLNEW SegmentTermEnum( directory->openInput( tiiFile ), fieldInfos, true);
//Check if enumerator points to a valid instance
CND_CONDITION(origEnum != NULL, "No memory could be allocated for orig enumerator");
@@ -110,7 +101,6 @@
_CLDELETE_ARRAY(indexInfos);
}
-
#ifdef _CL_DISABLE_MULTITHREADING
_CLDELETE(stEnumerator);
#endif
@@ -123,7 +113,7 @@
//Get a pointer to IndexInput used by the enumeration but
//instantiated in the constructor by directory.open( tisFile )
- lucene::store::IndexInput *is = origEnum->input;
+ IndexInput *is = origEnum->input;
//Delete the enumuration enumerator
_CLDELETE(origEnum);
@@ -137,7 +127,7 @@
//Get a pointer to IndexInput used by the enumeration but
//instantiated in the constructor by directory.open( tiiFile )
- lucene::store::IndexInput *is = indexEnum->input;
+ IndexInput *is = indexEnum->input;
//Delete the enumuration enumerator
_CLDELETE(indexEnum);
@@ -147,7 +137,7 @@
}
}
- int64_t TermInfosReader::size() {
+ int64_t TermInfosReader::size() const{
//Func - Return the size of the enumeration of TermInfos
//Pre - true
//Post - size has been returened
@@ -194,6 +184,7 @@
stEnumerator = terms();
return stEnumerator;
#else
+ SCOPED_LOCK_MUTEX(enumerators_LOCK)
SegmentTermEnum* termEnum = enumerators.get(_LUCENE_CURRTHREADID);
if (termEnum == NULL){
termEnum = terms();
@@ -201,7 +192,7 @@
}
return termEnum;
#endif
- }
+ }
TermInfo* TermInfosReader::get(const Term* term){
//Func - Returns a TermInfo for a term
@@ -337,7 +328,7 @@
//Iterate through the terms of indexEnum
for (int32_t i = 0; indexEnum->next(); i++){
- indexTerms[i].set(indexEnum->term(false)->field(),indexEnum->term(false)->text(),false);
+ indexTerms[i].set(indexEnum->term(false),indexEnum->term(false)->text());
indexEnum->getTermInfo(&indexInfos[i]);
indexPointers[i] = indexEnum->indexPointer;
}
Modified: trunk/clucene/src/CLucene/index/TermInfosReader.h
===================================================================
--- trunk/clucene/src/CLucene/index/TermInfosReader.h 2006-06-11 07:16:00 UTC (rev 427)
+++ trunk/clucene/src/CLucene/index/TermInfosReader.h 2006-06-26 00:39:24 UTC (rev 428)
@@ -1,18 +1,9 @@
-/**
- * Copyright 2003-2006 The Apache Software Foundation
- *
- * Licensed under the Apache License, Version 2.0 (the "License");
- * you may not use this file except in compliance with the License.
- * You may obtain a copy of the License at
- *
- * http://www.apache.org/licenses/LICENSE-2.0
- *
- * Unless required by applicable law or agreed to in writing, software
- * distributed under the License is distributed on an "AS IS" BASIS,
- * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
- * See the License for the specific language governing permissions and
- * limitations under the License.
- */
+/*------------------------------------------------------------------------------
+* Copyright (C) 2003-2006 Ben van Klinken and the CLucene Team
+*
+* Distributable under the terms of either the Apache License (Version 2.0) or
+* the GNU Lesser General Public License, as specified in the COPYING file.
+------------------------------------------------------------------------------*/
#ifndef _lucene_index_TermInfosReader_
#define _lucene_index_TermInfosReader_
@@ -44,8 +35,9 @@
SegmentTermEnum* stEnumerator;
#else
CL_NS(util)::CLSet<_LUCENE_THREADID_TYPE, SegmentTermEnum*,
- CLuceneThreadIdCompare,
+ CL_NS(util)::CLuceneThreadIdCompare,
CL_NS(util)::Deletor::ConstNullVal<_LUCENE_THREADID_TYPE>, CL_NS(util)::Deletor::Object<SegmentTermEnum> > enumerators;
+ DEFINE_MUTEX(enumerators_LOCK)
#endif
SegmentTermEnum* getEnum();
SegmentTermEnum* origEnum;
@@ -68,7 +60,7 @@
void close();
//Return the size of the enumeration of TermInfos
- int64_t size();
+ int64_t size() const;
int32_t getSkipInterval() { return origEnum->skipInterval; }
Modified: trunk/clucene/src/CLucene/index/TermInfosWriter.cpp
===================================================================
--- trunk/clucene/src/CLucene/index/TermInfosWriter.cpp 2006-06-11 07:16:00 UTC (rev 427)
+++ trunk/clucene/src/CLucene/index/TermInfosWriter.cpp 2006-06-26 00:39:24 UTC (rev 428)
@@ -1,18 +1,9 @@
-/**
- * Copyright 2003-2006 The Apache Software Foundation
- *
- * Licensed under the Apache License, Version 2.0 (the "License");
- * you may not use this file except in compliance with the License.
- * You may obtain a copy of the License at
- *
- * http://www.apache.org/licenses/LICENSE-2.0
- *
- * Unless required by applicable law or agreed to in writing, software
- * distributed under the License is distributed on an "AS IS" BASIS,
- * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
- * See the License for the specific language governing permissions and
- * limitations under the License.
- */
+/*------------------------------------------------------------------------------
+* Copyright (C) 2003-2006 Ben van Klinken and the CLucene Team
+*
+* Distributable under the terms of either the Apache License (Version 2.0) or
+* the GNU Lesser General Public License, as specified in the COPYING file.
+------------------------------------------------------------------------------*/
#include "CLucene/StdHeader.h"
#include "TermInfosWriter.h"
@@ -80,7 +71,7 @@
skipInterval = LUCENE_DEFAULT_TERMDOCS_SKIP_INTERVAL;
const char* buf = Misc::segmentname(segment, (isIndex ? ".tii" : ".tis"));
- output = directory->createFile( buf );
+ output = directory->createOutput( buf );
_CLDELETE_CaARRAY(buf);
output->writeInt(FORMAT); // write format
@@ -172,7 +163,7 @@
output->writeVInt(fieldnum); // write field num
if ( lastTerm->__cl_refcount == 1 ){
- lastTerm->set(term->field(),term->text(),false);
+ lastTerm->set(term,term->text());
}else{
_CLDECDELETE(lastTerm);
lastTerm = _CL_POINTER(term);
Modified: trunk/clucene/src/CLucene/index/TermInfosWriter.h
===================================================================
--- trunk/clucene/src/CLucene/index/TermInfosWriter.h 2006-06-11 07:16:00 UTC (rev 427)
+++ trunk/clucene/src/CLucene/index/TermInfosWriter.h 2006-06-26 00:39:24 UTC (rev 428)
@@ -1,18 +1,9 @@
-/**
- * Copyright 2003-2006 The Apache Software Foundation
- *
- * Licensed under the Apache License, Version 2.0 (the "License");
- * you may not use this file except in compliance with the License.
- * You may obtain a copy of the License at
- *
- * http://www.apache.org/licenses/LICENSE-2.0
- *
- * Unless required by applicable law or agreed to in writing, software
- * distributed under the License is distributed on an "AS IS" BASIS,
- * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
- * See the License for the specific language governing permissions and
- * limitations under the License.
- */
+/*------------------------------------------------------------------------------
+* Copyright (C) 2003-2006 Ben van Klinken and the CLucene Team
+*
+* Distributable under the terms of either the Apache License (Version 2.0) or
+* the GNU Lesser General Public License, as specified in the COPYING file.
+------------------------------------------------------------------------------*/
#ifndef _lucene_index_TermInfosWriter_
#define _lucene_index_TermInfosWriter_
Modified: trunk/clucene/src/CLucene/index/TermVector.h
===================================================================
--- trunk/clucene/src/CLucene/index/TermVector.h 2006-06-11 07:16:00 UTC (rev 427)
+++ trunk/clucene/src/CLucene/index/TermVector.h 2006-06-26 00:39:24 UTC (rev 428)
@@ -1,18 +1,9 @@
-/**
- * Copyright 2003-2006 The Apache Software Foundation
- *
- * Licensed under the Apache License, Version 2.0 (the "License");
- * you may not use this file except in compliance with the License.
- * You may obtain a copy of the License at
- *
- * http://www.apache.org/licenses/LICENSE-2.0
- *
- * Unless required by applicable law or agreed to in writing, software
- * distributed under the License is distributed on an "AS IS" BASIS,
- * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
- * See the License for the specific language governing permissions and
- * limitations under the License.
- */
+/*------------------------------------------------------------------------------
+* Copyright (C) 2003-2006 Ben van Klinken and the CLucene Team
+*
+* Distributable under the terms of either the Apache License (Version 2.0) or
+* the GNU Lesser General Public License, as specified in the COPYING file.
+------------------------------------------------------------------------------*/
#ifndef _lucene_index_termvector_h
#define _lucene_index_termvector_h
@@ -126,7 +117,7 @@
int32_t termTextLen; //textlen cache
public:
int32_t freq;
- const TCHAR* getTermText();
+ const TCHAR* getTermText() const;
size_t getTermTextLen();
void setTermText(const TCHAR* val);
TVTerm();
@@ -174,7 +165,7 @@
/** Close all streams. */
void close();
- bool isDocumentOpen();
+ bool isDocumentOpen() const;
/** Start processing a field. This can be followed by a number of calls to
* addTerm, and a final call to closeField to indicate the end of
@@ -189,7 +180,7 @@
void closeField();
/** Return true if a field is currently open. */
- bool isFieldOpen();
+ bool isFieldOpen() const;
/** Add specified vectors to the document.
*/
@@ -231,7 +222,7 @@
* @return The number of the field this vector is associated with
*/
const TCHAR* getField();
- TCHAR* toString();
+ TCHAR* toString() const;
int32_t size();
const TCHAR** getTerms();
const int32_t* getTermFrequencies();
@@ -283,12 +274,12 @@
TermVectorOffsetInfo();
~TermVectorOffsetInfo();
TermVectorOffsetInfo(int32_t startOffset, int32_t endOffset);
- int32_t getEndOffset();
+ int32_t getEndOffset() const;
void setEndOffset(int32_t endOffset);
- int32_t getStartOffset();
+ int32_t getStartOffset() const;
void setStartOffset(int32_t startOffset);
bool equals(TermVectorOffsetInfo* o);
- size_t hashCode();
+ size_t hashCode() const;
};
Modified: trunk/clucene/src/CLucene/index/TermVectorReader.cpp
===================================================================
--- trunk/clucene/src/CLucene/index/TermVectorReader.cpp 2006-06-11 07:16:00 UTC (rev 427)
+++ trunk/clucene/src/CLucene/index/TermVectorReader.cpp 2006-06-26 00:39:24 UTC (rev 428)
@@ -1,18 +1,9 @@
-/**
- * Copyright 2003-2006 The Apache Software Foundation
- *
- * Licensed under the Apache License, Version 2.0 (the "License");
- * you may not use this file except in compliance with the License.
- * You may obtain a copy of the License at
- *
- * http://www.apache.org/licenses/LICENSE-2.0
- *
- * Unless required by applicable law or agreed to in writing, software
- * distributed under the License is distributed on an "AS IS" BASIS,
- * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
- * See the License for the specific language governing permissions and
- * limitations under the License.
- */
+/*------------------------------------------------------------------------------
+* Copyright (C) 2003-2006 Ben van Klinken and the CLucene Team
+*
+* Distributable under the terms of either the Apache License (Version 2.0) or
+* the GNU Lesser General Public License, as specified in the COPYING file.
+------------------------------------------------------------------------------*/
#include "CLucene/StdHeader.h"
#include "TermVector.h"
#include "CLucene/util/StringBuffer.h"
@@ -21,21 +12,21 @@
CL_NS_DEF(index)
TermVectorsReader::TermVectorsReader(CL_NS(store)::Directory* d, const char* segment, FieldInfos* fieldInfos){
- char fbuf[CL_MAX_DIR];
+ char fbuf[CL_MAX_NAME];
strcpy(fbuf,segment);
char* fpbuf=fbuf+strlen(fbuf);
strcpy(fpbuf,LUCENE_TVX_EXTENSION);
if (d->fileExists(fbuf)) {
- tvx = d->openFile(fbuf);
+ tvx = d->openInput(fbuf);
checkValidFormat(tvx);
strcpy(fpbuf,LUCENE_TVD_EXTENSION);
- tvd = d->openFile(fbuf);
+ tvd = d->openInput(fbuf);
checkValidFormat(tvd);
strcpy(fpbuf,LUCENE_TVF_EXTENSION);
- tvf = d->openFile(fbuf);
+ tvf = d->openInput(fbuf);
checkValidFormat(tvf);
_size = tvx->length() / 8;
@@ -295,7 +286,7 @@
this->startOffset = startOffset;
}
-int32_t TermVectorOffsetInfo::getEndOffset() {
+int32_t TermVectorOffsetInfo::getEndOffset() const{
return endOffset;
}
@@ -303,7 +294,7 @@
this->endOffset = endOffset;
}
-int32_t TermVectorOffsetInfo::getStartOffset() {
+int32_t TermVectorOffsetInfo::getStartOffset() const{
return startOffset;
}
@@ -325,7 +316,7 @@
return true;
}
-size_t TermVectorOffsetInfo::hashCode() {
+size_t TermVectorOffsetInfo::hashCode() const{
size_t result;
result = startOffset;
result = 29 * result + endOffset;
Modified: trunk/clucene/src/CLucene/index/TermVectorWriter.cpp
===================================================================
--- trunk/clucene/src/CLucene/index/TermVectorWriter.cpp 2006-06-11 07:16:00 UTC (rev 427)
+++ trunk/clucene/src/CLucene/index/TermVectorWriter.cpp 2006-06-26 00:39:24 UTC (rev 428)
@@ -1,21 +1,11 @@
-/**
- * Copyright 2003-2006 The Apache Software Foundation
- *
- * Licensed under the Apache License, Version 2.0 (the "License");
- * you may not use this file except in compliance with the License.
- * You may obtain a copy of the License at
- *
- * http://www.apache.org/licenses/LICENSE-2.0
- *
- * Unless required by applicable law or agreed to in writing, software
- * distributed under the License is distributed on an "AS IS" BASIS,
- * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
- * See the License for the specific language governing permissions and
- * limitations under the License.
- */
+/*------------------------------------------------------------------------------
+* Copyright (C) 2003-2006 Ben van Klinken and the CLucene Team
+*
+* Distributable under the terms of either the Apache License (Version 2.0) or
+* the GNU Lesser General Public License, as specified in the COPYING file.
+------------------------------------------------------------------------------*/
#include "CLucene/StdHeader.h"
#include "TermVector.h"
-#include "CLucene/util/StringBuffer.h"
#include "CLucene/util/Misc.h"
CL_NS_USE(util)
@@ -25,20 +15,20 @@
const char* segment,FieldInfos* fieldInfos)
{
// Open files for TermVector storage
- char fbuf[CL_MAX_DIR];
+ char fbuf[CL_MAX_NAME];
strcpy(fbuf,segment);
char* fpbuf=fbuf+strlen(fbuf);
strcpy(fpbuf,LUCENE_TVX_EXTENSION);
- tvx = directory->createFile(fbuf);
+ tvx = directory->createOutput(fbuf);
tvx->writeInt(FORMAT_VERSION);
strcpy(fpbuf,LUCENE_TVD_EXTENSION);
- tvd = directory->createFile(fbuf);
+ tvd = directory->createOutput(fbuf);
tvd->writeInt(FORMAT_VERSION);
strcpy(fpbuf,LUCENE_TVF_EXTENSION);
- tvf = directory->createFile(fbuf);
+ tvf = directory->createOutput(fbuf);
tvf->writeInt(FORMAT_VERSION);
this->fieldInfos = fieldInfos;
@@ -80,7 +70,7 @@
}
- bool TermVectorsWriter::isDocumentOpen() {
+ bool TermVectorsWriter::isDocumentOpen() const{
return currentDocPointer != -1;
}
@@ -107,7 +97,7 @@
}
}
- bool TermVectorsWriter::isFieldOpen() {
+ bool TermVectorsWriter::isFieldOpen() const{
return currentField != NULL;
}
@@ -255,7 +245,7 @@
}
- const TCHAR* TermVectorsWriter::TVTerm::getTermText(){
+ const TCHAR* TermVectorsWriter::TVTerm::getTermText() const{
return termText;
}
size_t TermVectorsWriter::TVTerm::getTermTextLen(){
Modified: trunk/clucene/src/CLucene/index/Terms.h
===================================================================
--- trunk/clucene/src/CLucene/index/Terms.h 2006-06-11 07:16:00 UTC (rev 427)
+++ trunk/clucene/src/CLucene/index/Terms.h 2006-06-26 00:39:24 UTC (rev 428)
@@ -1,18 +1,9 @@
-/**
- * Copyright 2003-2006 The Apache Software Foundation
- *
- * Licensed under the Apache License, Version 2.0 (the "License");
- * you may not use this file except in compliance with the License.
- * You may obtain a copy of the License at
- *
- * http://www.apache.org/licenses/LICENSE-2.0
- *
- * Unless required by applicable law or agreed to in writing, software
- * distributed under the License is distributed on an "AS IS" BASIS,
- * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
- * See the License for the specific language governing permissions and
- * limitations under the License.
- */
+/*------------------------------------------------------------------------------
+* Copyright (C) 2003-2006 Ben van Klinken and the CLucene Team
+*
+* Distributable under the terms of either the Apache License (Version 2.0) or
+* the GNU Lesser General Public License, as specified in the COPYING file.
+------------------------------------------------------------------------------*/
#ifndef _lucene_index_Terms_
#define _lucene_index_Terms_
@@ -23,140 +14,156 @@
#include "Term.h"
CL_NS_DEF(index)
- class TermEnum; //predefine
- class TermPositions;
+class TermEnum; //predefine
+class TermPositions;
- class TermDocs: LUCENE_BASE {
- public:
- virtual ~TermDocs(){
- }
+/** TermDocs provides an interface for enumerating <document, frequency>
+ pairs for a term. <p> The document portion names each document containing
+ the term. Documents are indicated by number. The frequency portion gives
+ the number of times the term occurred in each document. <p> The pairs are
+ ordered by document number.
- // Sets this to the data for a term.
- // The enumeration is reset to the start of the data for this term.
- virtual void seek(Term* term)=0;
+ @see IndexReader#termDocs()
+ */
+class TermDocs: LUCENE_BASE {
+public:
+ virtual ~TermDocs(){
+ }
- /** Sets this to the data for the current term in a {@link TermEnum}.
- * This may be optimized in some implementations.
- */
- virtual void seek(TermEnum* termEnum)=0;
+ // Sets this to the data for a term.
+ // The enumeration is reset to the start of the data for this term.
+ virtual void seek(Term* term)=0;
- // Returns the current document number. <p> This is invalid until {@link
- // #next()} is called for the first time.
- virtual int32_t doc() const=0;
+ /** Sets this to the data for the current term in a {@link TermEnum}.
+ * This may be optimized in some implementations.
+ */
+ virtual void seek(TermEnum* termEnum)=0;
- // Returns the frequency of the term within the current document. <p> This
- // is invalid until {@link #next()} is called for the first time.
- virtual int32_t freq() const=0;
+ // Returns the current document number. <p> This is invalid until {@link
+ // #next()} is called for the first time.
+ virtual int32_t doc() const=0;
- // Moves to the next pair in the enumeration. <p> Returns true iff there is
- // such a next pair in the enumeration.
- virtual bool next() =0;
+ // Returns the frequency of the term within the current document. <p> This
+ // is invalid until {@link #next()} is called for the first time.
+ virtual int32_t freq() const=0;
- // Attempts to read multiple entries from the enumeration, up to length of
- // <i>docs</i>. Document numbers are stored in <i>docs</i>, and term
- // frequencies are stored in <i>freqs</i>. The <i>freqs</i> array must be as
- // int64_t as the <i>docs</i> array.
- //
- // <p>Returns the number of entries read. Zero is only returned when the
- // stream has been exhausted.
- virtual int32_t read(int32_t* docs, int32_t* freqs, int32_t length)=0;
+ // Moves to the next pair in the enumeration. <p> Returns true iff there is
+ // such a next pair in the enumeration.
+ virtual bool next() =0;
- // Skips entries to the first beyond the current whose document number is
- // greater than or equal to <i>target</i>. <p>Returns true iff there is such
- // an entry. <p>Behaves as if written: <pre>
- // bool skipTo(int32_t target) {
- // do {
- // if (!next())
- // return false;
- // } while (target > doc());
- // return true;
- // }
- // </pre>
- // Some implementations are considerably more efficient than that.
- virtual bool skipTo(const int32_t target)=0;
+ // Attempts to read multiple entries from the enumeration, up to length of
+ // <i>docs</i>. Document numbers are stored in <i>docs</i>, and term
+ // frequencies are stored in <i>freqs</i>. The <i>freqs</i> array must be as
+ // int64_t as the <i>docs</i> array.
+ //
+ // <p>Returns the number of entries read. Zero is only returned when the
+ // stream has been exhausted.
+ virtual int32_t read(int32_t* docs, int32_t* freqs, int32_t length)=0;
- // Frees associated resources.
- virtual void close() = 0;
+ // Skips entries to the first beyond the current whose document number is
+ // greater than or equal to <i>target</i>. <p>Returns true iff there is such
+ // an entry. <p>Behaves as if written: <pre>
+ // bool skipTo(int32_t target) {
+ // do {
+ // if (!next())
+ // return false;
+ // } while (target > doc());
+ // return true;
+ // }
+ // </pre>
+ // Some implementations are considerably more efficient than that.
+ virtual bool skipTo(const int32_t target)=0;
-
- /** Solve the diamond inheritence problem by providing a reinterpret function.
- * No dynamic casting is required and no RTTI data is needed to do this
- */
- virtual TermPositions* __asTermPositions()=0;
- };
+ // Frees associated resources.
+ virtual void close() = 0;
+
+ /** Solve the diamond inheritence problem by providing a reinterpret function.
+ * No dynamic casting is required and no RTTI data is needed to do this
+ */
+ virtual TermPositions* __asTermPositions()=0;
+};
- // Abstract class for enumerating terms.
- //
- //<p>Term enumerations are always ordered by Term.compareTo(). Each term in
- //the enumeration is greater than all that precede it.
- class TermEnum: LUCENE_BASE {
- public:
- // Increments the enumeration to the next element. True if one exists.
- virtual bool next()=0;
- // Returns the current Term in the enumeration.
- virtual Term* term(const bool pointer=true)=0;
+// Abstract class for enumerating terms.
+//
+//<p>Term enumerations are always ordered by Term.compareTo(). Each term in
+//the enumeration is greater than all that precede it.
+class TermEnum: LUCENE_BASE {
+public:
+ // Increments the enumeration to the next element. True if one exists.
+ virtual bool next()=0;
- // Returns the docFreq of the current Term in the enumeration.
- virtual int32_t docFreq() const=0;
+ // Returns a pointer to the current Term in the enumeration.
+ virtual Term* term()=0;
+
+ // Returns the current Term in the enumeration.
+ virtual Term* term(bool pointer){
+ Term* ret = term();
+ if ( !pointer )
+ ret->__cl_decref();
+ return ret;
+ }
- // Closes the enumeration to further activity, freeing resources.
- virtual void close() =0;
+ // Returns the docFreq of the current Term in the enumeration.
+ virtual int32_t docFreq() const=0;
- virtual ~TermEnum(){
- }
+ // Closes the enumeration to further activity, freeing resources.
+ virtual void close() =0;
- // Term Vector support
- /** Skips terms to the first beyond the current whose value is
- * greater or equal to <i>target</i>. <p>Returns true iff there is such
- * an entry. <p>Behaves as if written: <pre>
- * public boolean skipTo(Term target) {
- * do {
- * if (!next())
- * return false;
- * } while (target > term());
- * return true;
- * }
- * </pre>
- * Some implementations are considerably more efficient than that.
- */
- virtual bool skipTo(Term* target){
- do {
- if (!next())
- return false;
- } while (target->compareTo(term(false)) > 0);
- return true;
- }
- };
+ virtual ~TermEnum(){
+ }
+
+ // Term Vector support
+ /** Skips terms to the first beyond the current whose value is
+ * greater or equal to <i>target</i>. <p>Returns true iff there is such
+ * an entry. <p>Behaves as if written: <pre>
+ * public boolean skipTo(Term target) {
+ * do {
+ * if (!next())
+ * return false;
+ * } while (target > term());
+ * return true;
+ * }
+ * </pre>
+ * Some implementations are considerably more efficient than that.
+ */
+ virtual bool skipTo(Term* target){
+ do {
+ if (!next())
+ return false;
+ } while (target->compareTo(term(false)) > 0);
+ return true;
+ }
+};
- /**
- * TermPositions provides an interface for enumerating the <document,
- * frequency, <position>* > tuples for a term. <p> The document and
- * frequency are the same as for a TermDocs. The positions portion lists the ordinal
- * positions of each occurrence of a term in a document.
- *
- * @see IndexReader#termPositions
- */
- class TermPositions: public virtual TermDocs {
- public:
- // Returns next position in the current document. It is an error to call
- // this more than {@link #freq()} times
- // without calling {@link #next()}<p> This is
- // invalid until {@link #next()} is called for
- // the first time.
- virtual int32_t nextPosition() = 0;
+/**
+ * TermPositions provides an interface for enumerating the <document,
+ * frequency, <position>* > tuples for a term. <p> The document and
+ * frequency are the same as for a TermDocs. The positions portion lists the ordinal
+ * positions of each occurrence of a term in a document.
+ *
+ * @see IndexReader#termPositions()
+ */
+class TermPositions: public virtual TermDocs {
+public:
+ // Returns next position in the current document. It is an error to call
+ // this more than {@link #freq()} times
+ // without calling {@link #next()}<p> This is
+ // invalid until {@link #next()} is called for
+ // the first time.
+ virtual int32_t nextPosition() = 0;
- virtual ~TermPositions(){
- }
+ virtual ~TermPositions(){
+ }
- /** Solve the diamond inheritence problem by providing a reinterpret function.
- * No dynamic casting is required and no RTTI data is needed to do this
- */
- virtual TermDocs* __asTermDocs()=0;
- virtual TermPositions* __asTermPositions()=0;
- };
+ /** Solve the diamond inheritence problem by providing a reinterpret function.
+ * No dynamic casting is required and no RTTI data is needed to do this
+ */
+ virtual TermDocs* __asTermDocs()=0;
+ virtual TermPositions* __asTermPositions()=0;
+};
CL_NS_END
#endif
Modified: trunk/clucene/src/CLucene/queryParser/Lexer.cpp
===================================================================
--- trunk/clucene/src/CLucene/queryParser/Lexer.cpp 2006-06-11 07:16:00 UTC (rev 427)
+++ trunk/clucene/src/CLucene/queryParser/Lexer.cpp 2006-06-26 00:39:24 UTC (rev 428)
@@ -1,18 +1,9 @@
-/**
- * Copyright 2003-2006 The Apache Software Foundation
- *
- * Licensed under the Apache License, Version 2.0 (the "License");
- * you may not use this file except in compliance with the License.
- * You may obtain a copy of the License at
- *
- * http://www.apache.org/licenses/LICENSE-2.0
- *
- * Unless required by applicable law or agreed to in writing, software
- * distributed under the License is distributed on an "AS IS" BASIS,
- * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
- * See the License for the specific language governing permissions and
- * limitations under the License.
- */
+/*------------------------------------------------------------------------------
+* Copyright (C) 2003-2006 Ben van Klinken and the CLucene Team
+*
+* Distributable under the terms of either the Apache License (Version 2.0) or
+* the GNU Lesser General Public License, as specified in the COPYING file.
+------------------------------------------------------------------------------*/
#include "CLucene/StdHeader.h"
#include "Lexer.h"
@@ -165,6 +156,7 @@
case '*':
QueryParserBase::throwParserException( _T("Unrecognized TCHAR %d at %d::%d."),
ch, reader->Column(), reader->Line() );
+ return NULL;
default:
return ReadTerm(ch);
Modified: trunk/clucene/src/CLucene/queryParser/Lexer.h
===================================================================
--- trunk/clucene/src/CLucene/queryParser/Lexer.h 2006-06-11 07:16:00 UTC (rev 427)
+++ trunk/clucene/src/CLucene/queryParser/Lexer.h 2006-06-26 00:39:24 UTC (rev 428)
@@ -1,18 +1,9 @@
-/**
- * Copyright 2003-2006 The Apache Software Foundation
- *
- * Licensed under the Apache License, Version 2.0 (the "License");
- * you may not use this file except in compliance with the License.
- * You may obtain a copy of the License at
- *
- * http://www.apache.org/licenses/LICENSE-2.0
- *
- * Unless required by applicable law or agreed to in writing, software
- * distributed under the License is distributed on an "AS IS" BASIS,
- * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
- * See the License for the specific language governing permissions and
- * limitations under the License.
- */
+/*------------------------------------------------------------------------------
+* Copyright (C) 2003-2006 Ben van Klinken and the CLucene Team
+*
+* Distributable under the terms of either the Apache License (Version 2.0) or
+* the GNU Lesser General Public License, as specified in the COPYING file.
+------------------------------------------------------------------------------*/
#ifndef _lucene_queryParser_Lexer_
#define _lucene_queryParser_Lexer_
Modified: trunk/clucene/src/CLucene/queryParser/MultiFieldQueryParser.cpp
===================================================================
--- trunk/clucene/src/CLucene/queryParser/MultiFieldQueryParser.cpp 2006-06-11 07:16:00 UTC (rev 427)
+++ trunk/clucene/src/CLucene/queryParser/MultiFieldQueryParser.cpp 2006-06-26 00:39:24 UTC (rev 428)
@@ -1,18 +1,9 @@
-/**
- * Copyright 2003-2006 The Apache Software Foundation
- *
- * Licensed under the Apache License, Version 2.0 (the "License");
- * you may not use this file except in compliance with the License.
- * You may obtain a copy of the License at
- *
- * http://www.apache.org/licenses/LICENSE-2.0
- *
- * Unless required by applicable law or agreed to in writing, software
- * distributed under the License is distributed on an "AS IS" BASIS,
- * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
- * See the License for the specific language governing permissions and
- * limitations under the License.
- */
+/*------------------------------------------------------------------------------
+* Copyright (C) 2003-2006 Ben van Klinken and the CLucene Team
+*
+* Distributable under the terms of either the Apache License (Version 2.0) or
+* the GNU Lesser General Public License, as specified in the COPYING file.
+------------------------------------------------------------------------------*/
#include "CLucene/StdHeader.h"
#include "MultiFieldQueryParser.h"
#include "CLucene/analysis/AnalysisHeader.h"
@@ -52,10 +43,10 @@
uint8_t flag = flags[i];
switch (flag)
{
- case queryParser_REQUIRED_FIELD:
+ case MultiFieldQueryParser::REQUIRED_FIELD:
bQuery->add(q, true, true, false);
break;
- case queryParser_PROHIBITED_FIELD:
+ case MultiFieldQueryParser::PROHIBITED_FIELD:
bQuery->add(q, true, false, true);
break;
default:
Modified: trunk/clucene/src/CLucene/queryParser/MultiFieldQueryParser.h
===================================================================
--- trunk/clucene/src/CLucene/queryParser/MultiFieldQueryParser.h 2006-06-11 07:16:00 UTC (rev 427)
+++ trunk/clucene/src/CLucene/queryParser/MultiFieldQueryParser.h 2006-06-26 00:39:24 UTC (rev 428)
@@ -1,18 +1,9 @@
-/**
- * Copyright 2003-2006 The Apache Software Foundation
- *
- * Licensed under the Apache License, Version 2.0 (the "License");
- * you may not use this file except in compliance with the License.
- * You may obtain a copy of the License at
- *
- * http://www.apache.org/licenses/LICENSE-2.0
- *
- * Unless required by applicable law or agreed to in writing, software
- * distributed under the License is distributed on an "AS IS" BASIS,
- * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
- * See the License for the specific language governing permissions and
- * limitations under the License.
- */
+/*------------------------------------------------------------------------------
+* Copyright (C) 2003-2006 Ben van Klinken and the CLucene Team
+*
+* Distributable under the terms of either the Apache License (Version 2.0) or
+* the GNU Lesser General Public License, as specified in the COPYING file.
+------------------------------------------------------------------------------*/
#ifndef MultiFieldQueryParser_H
#define MultiFieldQueryParser_H
@@ -27,9 +18,6 @@
CL_NS_DEF(queryParser)
-#define queryParser_NORMAL_FIELD 0
-#define queryParser_REQUIRED_FIELD 1
-#define queryParser_PROHIBITED_FIELD 2
/**
* A QueryParser which constructs queries to search multiple fields.
*
@@ -37,6 +25,9 @@
class MultiFieldQueryParser: public QueryParser
{
public:
+ LUCENE_STATIC_CONSTANT(uint8_t, NORMAL_FIELD=0);
+ LUCENE_STATIC_CONSTANT(uint8_t, REQUIRED_FIELD=1);
+ LUCENE_STATIC_CONSTANT(uint8_t, PROHIBITED_FIELD=2);
/*MultiFieldQueryParser(QueryParserTokenManager tm)
{
Modified: trunk/clucene/src/CLucene/queryParser/QueryParser.cpp
===================================================================
--- trunk/clucene/src/CLucene/queryParser/QueryParser.cpp 2006-06-11 07:16:00 UTC (rev 427)
+++ trunk/clucene/src/CLucene/queryParser/QueryParser.cpp 2006-06-26 00:39:24 UTC (rev 428)
@@ -1,18 +1,9 @@
-/**
- * Copyright 2003-2006 The Apache Software Foundation
- *
- * Licensed under the Apache License, Version 2.0 (the "License");
- * you may not use this file except in compliance with the License.
- * You may obtain a copy of the License at
- *
- * http://www.apache.org/licenses/LICENSE-2.0
- *
- * Unless required by applicable law or agreed to in writing, software
- * distributed under the License is distributed on an "AS IS" BASIS,
- * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
- * See the License for the specific language governing permissions and
- * limitations under the License.
- */
+/*------------------------------------------------------------------------------
+* Copyright (C) 2003-2006 Ben van Klinken and the CLucene Team
+*
+* Distributable under the terms of either the Apache License (Version 2.0) or
+* the GNU Lesser General Public License, as specified in the COPYING file.
+------------------------------------------------------------------------------*/
#include "CLucene/StdHeader.h"
#include "QueryParser.h"
@@ -154,20 +145,17 @@
CND_PRECONDITION(tokens != NULL, "tokens is NULL");
switch(tokens->peek()->Type){
- case CL_NS(queryParser)::AND_ :{
+ case CL_NS(queryParser)::AND_ :
//Delete the first token of tokenlist
ExtractAndDeleteToken();
return CONJ_AND;
- }
- case CL_NS(queryParser)::OR :{
+ case CL_NS(queryParser)::OR :
//Delete the first token of tokenlist
ExtractAndDeleteToken();
return CONJ_OR;
- }
- default : {
+ default :
return CONJ_NONE;
- }
- }
+ }
}
int32_t QueryParser::MatchModifier(){
@@ -180,22 +168,18 @@
CND_PRECONDITION(tokens != NULL, "tokens is NULL");
switch(tokens->peek()->Type){
- case CL_NS(queryParser)::PLUS :{
+ case CL_NS(queryParser)::PLUS :
//Delete the first token of tokenlist
ExtractAndDeleteToken();
return MOD_REQ;
- }
-
case CL_NS(queryParser)::MINUS :
- case CL_NS(queryParser)::NOT :{
+ case CL_NS(queryParser)::NOT :
//Delete the first token of tokenlist
ExtractAndDeleteToken();
return MOD_NOT;
- }
- default :{
+ default :
return MOD_NONE;
- }
- }
+ }
}
Query* QueryParser::MatchQuery(const TCHAR* field){
@@ -566,7 +550,7 @@
_sntprintf(buf,200,_T("Error: Unexpected QueryToken: %d, expected: %d"),t->Type,expectedType);
_CLDELETE(t);
QueryParserBase::throwParserException(buf,' ',0,0);
- }
+ }
//Return the matched token
return t;
Modified: trunk/clucene/src/CLucene/queryParser/QueryParser.h
===================================================================
--- trunk/clucene/src/CLucene/queryParser/QueryParser.h 2006-06-11 07:16:00 UTC (rev 427)
+++ trunk/clucene/src/CLucene/queryParser/QueryParser.h 2006-06-26 00:39:24 UTC (rev 428)
@@ -1,18 +1,9 @@
-/**
- * Copyright 2003-2006 The Apache Software Foundation
- *
- * Licensed under the Apache License, Version 2.0 (the "License");
- * you may not use this file except in compliance with the License.
- * You may obtain a copy of the License at
- *
- * http://www.apache.org/licenses/LICENSE-2.0
- *
- * Unless required by applicable law or agreed to in writing, software
- * distributed under the License is distributed on an "AS IS" BASIS,
- * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
- * See the License for the specific language governing permissions and
- * limitations under the License.
- */
+/*------------------------------------------------------------------------------
+* Copyright (C) 2003-2006 Ben van Klinken and the CLucene Team
+*
+* Distributable under the terms of either the Apache License (Version 2.0) or
+* the GNU Lesser General Public License, as specified in the COPYING file.
+------------------------------------------------------------------------------*/
#ifndef _lucene_queryParser_QueryParser_
#define _lucene_queryParser_QueryParser_
@@ -91,11 +82,11 @@
- void setLowercaseWildcardTerms(bool lowercaseWildcardTerms)
- { this->lowercaseWildcardTerms = lowercaseWildcardTerms;}
+ void setLowercaseWildcardTerms(bool lowercaseWildcardTerms){
+ this->lowercaseWildcardTerms = lowercaseWildcardTerms;
+ }
- bool getLowercaseWildcardTerms()
- { return lowercaseWildcardTerms; }
+ bool getLowercaseWildcardTerms() const { return lowercaseWildcardTerms; }
private:
// matches for CONJUNCTION
Modified: trunk/clucene/src/CLucene/queryParser/QueryParserBase.cpp
===================================================================
--- trunk/clucene/src/CLucene/queryParser/QueryParserBase.cpp 2006-06-11 07:16:00 UTC (rev 427)
+++ trunk/clucene/src/CLucene/queryParser/QueryParserBase.cpp 2006-06-26 00:39:24 UTC (rev 428)
@@ -1,18 +1,9 @@
-/**
- * Copyright 2003-2006 The Apache Software Foundation
- *
- * Licensed under the Apache License, Version 2.0 (the "License");
- * you may not use this file except in compliance with the License.
- * You may obtain a copy of the License at
- *
- * http://www.apache.org/licenses/LICENSE-2.0
- *
- * Unless required by applicable law or agreed to in writing, software
- * distributed under the License is distributed on an "AS IS" BASIS,
- * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
- * See the License for the specific language governing permissions and
- * limitations under the License.
- */
+/*------------------------------------------------------------------------------
+* Copyright (C) 2003-2006 Ben van Klinken and the CLucene Team
+*
+* Distributable under the terms of either the Apache License (Version 2.0) or
+* the GNU Lesser General Public License, as specified in the COPYING file.
+------------------------------------------------------------------------------*/
#include "CLucene/StdHeader.h"
#include "QueryParserBase.h"
@@ -27,14 +18,10 @@
#include "CLucene/search/PrefixQuery.h"
#include "CLucene/search/FuzzyQuery.h"
-#include "CLucene/analysis/standard/StandardFilter.h"
-#include "CLucene/analysis/standard/StandardTokenizer.h"
-
CL_NS_USE(search)
CL_NS_USE(util)
CL_NS_USE(analysis)
-CL_NS_USE2(analysis,standard)
CL_NS_USE(index)
CL_NS_DEF(queryParser)
@@ -55,7 +42,7 @@
}
- TCHAR* QueryParserBase::discardEscapeChar(const TCHAR* source){
+ TCHAR* QueryParserBase::discardEscapeChar(const TCHAR* source) const{
int len = _tcslen(source);
TCHAR* dest = _CL_NEWARRAY(TCHAR, len+1);
@@ -189,7 +176,7 @@
Term* t = _CLNEW Term(field, data);
q->add(t);
_CLDECDELETE(t);
- itr++;
+ ++itr;
}
_CLDELETE(source);
return q;
@@ -213,7 +200,7 @@
* Gets implicit operator setting, which will be either OPERATOR_AND
* or OPERATOR_OR.
*/
- int QueryParserBase::getOperator() {
+ int QueryParserBase::getOperator() const{
return oper;
}
Modified: trunk/clucene/src/CLucene/queryParser/QueryParserBase.h
===================================================================
--- trunk/clucene/src/CLucene/queryParser/QueryParserBase.h 2006-06-11 07:16:00 UTC (rev 427)
+++ trunk/clucene/src/CLucene/queryParser/QueryParserBase.h 2006-06-26 00:39:24 UTC (rev 428)
@@ -1,18 +1,9 @@
-/**
- * Copyright 2003-2006 The Apache Software Foundation
- *
- * Licensed under the Apache License, Version 2.0 (the "License");
- * you may not use this file except in compliance with the License.
- * You may obtain a copy of the License at
- *
- * http://www.apache.org/licenses/LICENSE-2.0
- *
- * Unless required by applicable law or agreed to in writing, software
- * distributed under the License is distributed on an "AS IS" BASIS,
- * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
- * See the License for the specific language governing permissions and
- * limitations under the License.
- */
+/*------------------------------------------------------------------------------
+* Copyright (C) 2003-2006 Ben van Klinken and the CLucene Team
+*
+* Distributable under the terms of either the Apache License (Version 2.0) or
+* the GNU Lesser General Public License, as specified in the COPYING file.
+------------------------------------------------------------------------------*/
#ifndef _lucene_queryParser_QueryParserBase_
#define _lucene_queryParser_QueryParserBase_
@@ -67,7 +58,7 @@
static void throwParserException(const TCHAR* message, TCHAR ch, int32_t col, int32_t line );
void setOperator(int oper);
- int getOperator();
+ int getOperator() const;
protected:
//todo: we should make these virtual so that users can override the QueryParser
@@ -111,7 +102,7 @@
* Returns a String where the escape char has been
* removed, or kept only once if there was a double escape.
*/
- TCHAR* discardEscapeChar(const TCHAR* token);
+ TCHAR* discardEscapeChar(const TCHAR* token) const;
};
CL_NS_END
#endif
Modified: trunk/clucene/src/CLucene/queryParser/QueryParserConstants.h
===================================================================
--- trunk/clucene/src/CLucene/queryParser/QueryParserConstants.h 2006-06-11 07:16:00 UTC (rev 427)
+++ trunk/clucene/src/CLucene/queryParser/QueryParserConstants.h 2006-06-26 00:39:24 UTC (rev 428)
@@ -1,18 +1,9 @@
-/**
- * Copyright 2003-2006 The Apache Software Foundation
- *
- * Licensed under the Apache License, Version 2.0 (the "License");
- * you may not use this file except in compliance with the License.
- * You may obtain a copy of the License at
- *
- * http://www.apache.org/licenses/LICENSE-2.0
- *
- * Unless required by applicable law or agreed to in writing, software
- * distributed under the License is distributed on an "AS IS" BASIS,
- * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
- * See the License for the specific language governing permissions and
- * limitations under the License.
- */
+/*------------------------------------------------------------------------------
+* Copyright (C) 2003-2006 Ben van Klinken and the CLucene Team
+*
+* Distributable under the terms of either the Apache License (Version 2.0) or
+* the GNU Lesser General Public License, as specified in the COPYING file.
+------------------------------------------------------------------------------*/
#ifndef _lucene_queryParser_QueryParserConstants_
#define _lucene_queryParser_QueryParserConstants_
Modified: trunk/clucene/src/CLucene/queryParser/QueryToken.cpp
===================================================================
--- trunk/clucene/src/CLucene/queryParser/QueryToken.cpp 2006-06-11 07:16:00 UTC (rev 427)
+++ trunk/clucene/src/CLucene/queryParser/QueryToken.cpp 2006-06-26 00:39:24 UTC (rev 428)
@@ -1,18 +1,9 @@
-/**
- * Copyright 2003-2006 The Apache Software Foundation
- *
- * Licensed under the Apache License, Version 2.0 (the "License");
- * you may not use this file except in compliance with the License.
- * You may obtain a copy of the License at
- *
- * http://www.apache.org/licenses/LICENSE-2.0
- *
- * Unless required by applicable law or agreed to in writing, software
- * distributed under the License is distributed on an "AS IS" BASIS,
- * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
- * See the License for the specific language governing permissions and
- * limitations under the License.
- */
+/*------------------------------------------------------------------------------
+* Copyright (C) 2003-2006 Ben van Klinken and the CLucene Team
+*
+* Distributable under the terms of either the Apache License (Version 2.0) or
+* the GNU Lesser General Public License, as specified in the COPYING file.
+------------------------------------------------------------------------------*/
#include "CLucene/StdHeader.h"
#include "QueryToken.h"
Modified: trunk/clucene/src/CLucene/queryParser/QueryToken.h
===================================================================
--- trunk/clucene/src/CLucene/queryParser/QueryToken.h 2006-06-11 07:16:00 UTC (rev 427)
+++ trunk/clucene/src/CLucene/queryParser/QueryToken.h 2006-06-26 00:39:24 UTC (rev 428)
@@ -1,18 +1,9 @@
-/**
- * Copyright 2003-2006 The Apache Software Foundation
- *
- * Licensed under the Apache License, Version 2.0 (the "License");
- * you may not use this file except in compliance with the License.
- * You may obtain a copy of the License at
- *
- * http://www.apache.org/licenses/LICENSE-2.0
- *
- * Unless required by applicable law or agreed to in writing, software
- * distributed under the License is distributed on an "AS IS" BASIS,
- * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
- * See the License for the specific language governing permissions and
- * limitations under the License.
- */
+/*------------------------------------------------------------------------------
+* Copyright (C) 2003-2006 Ben van Klinken and the CLucene Team
+*
+* Distributable under the terms of either the Apache License (Version 2.0) or
+* the GNU Lesser General Public License, as specified in the COPYING file.
+------------------------------------------------------------------------------*/
#ifndef _lucene_queryParser_QueryToken_
#define _lucene_queryParser_QueryToken_
Modified: trunk/clucene/src/CLucene/queryParser/TokenList.cpp
===================================================================
--- trunk/clucene/src/CLucene/queryParser/TokenList.cpp 2006-06-11 07:16:00 UTC (rev 427)
+++ trunk/clucene/src/CLucene/queryParser/TokenList.cpp 2006-06-26 00:39:24 UTC (rev 428)
@@ -1,18 +1,9 @@
-/**
- * Copyright 2003-2006 The Apache Software Foundation
- *
- * Licensed under the Apache License, Version 2.0 (the "License");
- * you may not use this file except in compliance with the License.
- * You may obtain a copy of the License at
- *
- * http://www.apache.org/licenses/LICENSE-2.0
- *
- * Unless required by applicable law or agreed to in writing, software
- * distributed under the License is distributed on an "AS IS" BASIS,
- * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
- * See the License for the specific language governing permissions and
- * limitations under the License.
- */
+/*------------------------------------------------------------------------------
+* Copyright (C) 2003-2006 Ben van Klinken and the CLucene Team
+*
+* Distributable under the terms of either the Apache License (Version 2.0) or
+* the GNU Lesser General Public License, as specified in the COPYING file.
+------------------------------------------------------------------------------*/
#include "CLucene/StdHeader.h"
#include "TokenList.h"
@@ -81,7 +72,7 @@
return token;
}
- int32_t TokenList::count()
+ int32_t TokenList::count() const
{
return tokens.size();
}
Modified: trunk/clucene/src/CLucene/queryParser/TokenList.h
===================================================================
--- trunk/clucene/src/CLucene/queryParser/TokenList.h 2006-06-11 07:16:00 UTC (rev 427)
+++ trunk/clucene/src/CLucene/queryParser/TokenList.h 2006-06-26 00:39:24 UTC (rev 428)
@@ -1,18 +1,9 @@
-/**
- * Copyright 2003-2006 The Apache Software Foundation
- *
- * Licensed under the Apache License, Version 2.0 (the "License");
- * you may not use this file except in compliance with the License.
- * You may obtain a copy of the License at
- *
- * http://www.apache.org/licenses/LICENSE-2.0
- *
- * Unless required by applicable law or agreed to in writing, software
- * distributed under the License is distributed on an "AS IS" BASIS,
- * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
- * See the License for the specific language governing permissions and
- * limitations under the License.
- */
+/*------------------------------------------------------------------------------
+* Copyright (C) 2003-2006 Ben van Klinken and the CLucene Team
+*
+* Distributable under the terms of either the Apache License (Version 2.0) or
+* the GNU Lesser General Public License, as specified in the COPYING file.
+------------------------------------------------------------------------------*/
#ifndef _lucene_queryParser_TokenList_
#define _lucene_queryParser_TokenList_
@@ -41,7 +32,7 @@
QueryToken* extract();
- int32_t count();
+ int32_t count() const;
};
CL_NS_END
#endif
Modified: trunk/clucene/src/CLucene/search/BooleanClause.h
===================================================================
--- trunk/clucene/src/CLucene/search/BooleanClause.h 2006-06-11 07:16:00 UTC (rev 427)
+++ trunk/clucene/src/CLucene/search/BooleanClause.h 2006-06-26 00:39:24 UTC (rev 428)
@@ -1,18 +1,9 @@
-/**
- * Copyright 2003-2006 The Apache Software Foundation
- *
- * Licensed under the Apache License, Version 2.0 (the "License");
- * you may not use this file except in compliance with the License.
- * You may obtain a copy of the License at
- *
- * http://www.apache.org/licenses/LICENSE-2.0
- *
- * Unless required by applicable law or agreed to in writing, software
- * distributed under the License is distributed on an "AS IS" BASIS,
- * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
- * See the License for the specific language governing permissions and
- * limitations under the License.
- */
+/*------------------------------------------------------------------------------
+* Copyright (C) 2003-2006 Ben van Klinken and the CLucene Team
+*
+* Distributable under the terms of either the Apache License (Version 2.0) or
+* the GNU Lesser General Public License, as specified in the COPYING file.
+------------------------------------------------------------------------------*/
#ifndef _lucene_search_BooleanClause_
#define _lucene_search_BooleanClause_
@@ -28,14 +19,11 @@
class Compare:public CL_NS_STD(binary_function)<const BooleanClause*,const BooleanClause*,bool>
{
public:
- bool operator()( const BooleanClause* val1, const BooleanClause* val2 ){
+ bool operator()( const BooleanClause* val1, const BooleanClause* val2 ) const{
return val1->equals(val2);
}
};
-
- bool deleteQuery;
-
// The query whose matching documents are combined by the boolean query.
Query* query;
@@ -48,6 +36,8 @@
// If true, documents documents which <i>do</i>
// match this sub-query will <i>not</i> match the boolean query.
bool prohibited;
+
+ bool deleteQuery;
// Constructs a BooleanClause with query <code>q</code>, required
// <code>r</code> and prohibited <code>p</code>.
@@ -84,7 +74,7 @@
&& (this->prohibited == other->prohibited);
}
- size_t hashCode(){
+ size_t hashCode() const{
return query->hashCode() ^ (this->required?1:0) ^ (this->prohibited?2:0);
}
};
Modified: trunk/clucene/src/CLucene/search/BooleanQuery.cpp
===================================================================
--- trunk/clucene/src/CLucene/search/BooleanQuery.cpp 2006-06-11 07:16:00 UTC (rev 427)
+++ trunk/clucene/src/CLucene/search/BooleanQuery.cpp 2006-06-26 00:39:24 UTC (rev 428)
@@ -1,18 +1,9 @@
-/**
- * Copyright 2003-2006 The Apache Software Foundation
- *
- * Licensed under the Apache License, Version 2.0 (the "License");
- * you may not use this file except in compliance with the License.
- * You may obtain a copy of the License at
- *
- * http://www.apache.org/licenses/LICENSE-2.0
- *
- * Unless required by applicable law or agreed to in writing, software
- * distributed under the License is distributed on an "AS IS" BASIS,
- * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
- * See the License for the specific language governing permissions and
- * limitations under the License.
- */
+/*------------------------------------------------------------------------------
+* Copyright (C) 2003-2006 Ben van Klinken and the CLucene Team
+*
+* Distributable under the terms of either the Apache License (Version 2.0) or
+* the GNU Lesser General Public License, as specified in the COPYING file.
+------------------------------------------------------------------------------*/
#include "CLucene/StdHeader.h"
#include "BooleanQuery.h"
@@ -95,58 +86,11 @@
clauses.push_back(clause);
}
- /*void BooleanQuery::prepare(IndexReader* reader) {
- for (uint32_t i = 0 ; i < clauses.size(); i++) {
- BooleanClause* c = clauses[i];
- c->query->prepare(reader);
- }
- }
- void BooleanQuery::normalize(const float_t norm) {
- for (uint32_t i = 0 ; i < clauses.size(); i++) {
- BooleanClause* c = clauses[i];
- if (!c->prohibited)
- c->query->normalize(norm);
- }
- }
- float_t BooleanQuery::sumOfSquaredWeights(Searcher* searcher){
- float_t sum = 0.0f;
-
- for (uint32_t i = 0 ; i < clauses.size(); i++) {
- BooleanClause* c = clauses[i];
- if (!c->prohibited)
- sum += c->query->sumOfSquaredWeights(searcher); // sum sub-query weights
- }
-
- return sum;
- }
-*/
-
-
size_t BooleanQuery::getClauseCount() const {
return (int32_t) clauses.size();
}
- /*Scorer* BooleanQuery::scorer(IndexReader* reader){
- if (clauses.size() == 1) { // optimize 1-term queries
- BooleanClause* c = clauses[0];
- if (!c->prohibited) // just return term scorer
- return c->query->scorer(reader);
- }
-
- BooleanScorer* result = _CLNEW BooleanScorer;
- for (uint32_t i = 0 ; i < clauses.size(); i++) {
- BooleanClause* c = clauses[i];
- Scorer* subScorer = c->query->scorer(reader);
- if (subScorer != NULL)
- result->add(subScorer, c->required, c->prohibited);
- else if (c->required)
- return NULL;
- }
-
- return result;
- }*/
-
TCHAR* BooleanQuery::toString(const TCHAR* field) const{
StringBuffer buffer;
if (getBoost() != 1.0) {
@@ -163,13 +107,13 @@
if ( c->query->instanceOf(BooleanQuery::getClassName()) ) { // wrap sub-bools in parens
buffer.append(_T("("));
- const TCHAR* buf = c->query->toString(field);
+ TCHAR* buf = c->query->toString(field);
buffer.append(buf);
_CLDELETE_CARRAY( buf );
buffer.append(_T(")"));
} else {
- const TCHAR* buf = c->query->toString(field);
+ TCHAR* buf = c->query->toString(field);
buffer.append(buf);
_CLDELETE_CARRAY( buf );
}
@@ -270,7 +214,6 @@
this->parentQuery = parentQuery;
this->clauses = clauses;
for (uint32_t i = 0 ; i < clauses->size(); i++) {
- BooleanClause* c = (*clauses)[i];
weights.push_back((*clauses)[i]->query->createWeight(searcher));
}
}
Modified: trunk/clucene/src/CLucene/search/BooleanQuery.h
===================================================================
--- trunk/clucene/src/CLucene/search/BooleanQuery.h 2006-06-11 07:16:00 UTC (rev 427)
+++ trunk/clucene/src/CLucene/search/BooleanQuery.h 2006-06-26 00:39:24 UTC (rev 428)
@@ -1,18 +1,9 @@
-/**
- * Copyright 2003-2006 The Apache Software Foundation
- *
- * Licensed under the Apache License, Version 2.0 (the "License");
- * you may not use this file except in compliance with the License.
- * You may obtain a copy of the License at
- *
- * http://www.apache.org/licenses/LICENSE-2.0
- *
- * Unless required by applicable law or agreed to in writing, software
- * distributed under the License is distributed on an "AS IS" BASIS,
- * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
- * See the License for the specific language governing permissions and
- * limitations under the License.
- */
+/*------------------------------------------------------------------------------
+* Copyright (C) 2003-2006 Ben van Klinken and the CLucene Team
+*
+* Distributable under the terms of either the Apache License (Version 2.0) or
+* the GNU Lesser General Public License, as specified in the COPYING file.
+------------------------------------------------------------------------------*/
#ifndef _lucene_search_BooleanQuery_
#define _lucene_search_BooleanQuery_
Modified: trunk/clucene/src/CLucene/search/BooleanScorer.cpp
===================================================================
--- trunk/clucene/src/CLucene/search/BooleanScorer.cpp 2006-06-11 07:16:00 UTC (rev 427)
+++ trunk/clucene/src/CLucene/search/BooleanScorer.cpp 2006-06-26 00:39:24 UTC (rev 428)
@@ -1,18 +1,9 @@
-/**
- * Copyright 2003-2006 The Apache Software Foundation
- *
- * Licensed under the Apache License, Version 2.0 (the "License");
- * you may not use this file except in compliance with the License.
- * You may obtain a copy of the License at
- *
- * http://www.apache.org/licenses/LICENSE-2.0
- *
- * Unless required by applicable law or agreed to in writing, software
- * distributed under the License is distributed on an "AS IS" BASIS,
- * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
- * See the License for the specific language governing permissions and
- * limitations under the License.
- */
+/*------------------------------------------------------------------------------
+* Copyright (C) 2003-2006 Ben van Klinken and the CLucene Team
+*
+* Distributable under the terms of either the Apache License (Version 2.0) or
+* the GNU Lesser General Public License, as specified in the COPYING file.
+------------------------------------------------------------------------------*/
#include "CLucene/StdHeader.h"
#include "BooleanScorer.h"
@@ -24,14 +15,14 @@
BooleanScorer::BooleanScorer(Similarity* similarity):
Scorer(similarity),
- coordFactors (NULL),
+ scorers(NULL),
maxCoord (1),
- requiredMask (0),
- prohibitedMask (0),
nextMask (1),
- scorers(NULL),
end(0),
- current(NULL)
+ current(NULL),
+ requiredMask (0),
+ prohibitedMask (0),
+ coordFactors (NULL)
{
bucketTable = _CLNEW BucketTable(this);
}
@@ -148,7 +139,13 @@
- BooleanScorer::SubScorer::SubScorer(Scorer* scr, const bool r, const bool p, HitCollector* c, SubScorer* nxt){
+ BooleanScorer::SubScorer::SubScorer(Scorer* scr, const bool r, const bool p, HitCollector* c, SubScorer* nxt):
+ scorer(scr),
+ required(r),
+ prohibited(p),
+ collector(c),
+ next(nxt)
+ {
//Func - Constructor
//Pre - scr != NULL,
// c != NULL
@@ -158,11 +155,6 @@
CND_PRECONDITION(scr != NULL,"scr is NULL");
CND_PRECONDITION(c != NULL,"c is NULL");
- scorer = scr;
- collector = c;
- required = r;
- prohibited = p;
- next = nxt;
done = !scorer->next();
}
@@ -182,12 +174,14 @@
}
BooleanScorer::Bucket::Bucket():
- doc(-1)
- {
+ doc(-1),
+ score(0.0),
+ bits(0),
+ coord(0),
+ next(NULL)
+ {
}
BooleanScorer::Bucket::~Bucket(){
- //if ( next != NULL )
- // delete next;
}
@@ -208,36 +202,6 @@
//delete first;
first = NULL;
}
- /*void BucketTable::collectHits(HitCollector* results){
- int32_t required = scorer->requiredMask;
- int32_t prohibited = scorer.prohibitedMask;
- float_t* coord = scorer.coordFactors;
-
- for (Bucket* bucket = first; bucket!=NULL; bucket = bucket.next) {
- if ((bucket->bits & prohibited) == 0 && // check prohibited
- (bucket->bits & required) == required){// check required
- results.collect(bucket.doc, // add to results
- bucket->score * coord[bucket.coord]);
- }
- }
- first = NULL; // reset for next round
- }
- void BucketTable::collectHits(HitCollector* results){
- const int32_t required = scorer->requiredMask;
- const int32_t prohibited = scorer->prohibitedMask;
- const float_t* coord = scorer->coordFactors;
-
- for (Bucket* bucket = first; bucket!=NULL; bucket = bucket->next) {
- if ((bucket->bits & prohibited) == 0 && // check prohibited
- (bucket->bits & required) == required){// check required
-
- results->collect(bucket->doc, // add to results
- bucket->score * coord[bucket->coord]);
- }
- }
- clear(); //first = NULL; // reset for next round
- }*/
-
int32_t BooleanScorer::BucketTable::size() const { return BooleanScorer::BucketTable_SIZE; }
HitCollector* BooleanScorer::BucketTable::newCollector(const int32_t mask) {
@@ -253,8 +217,8 @@
BooleanScorer::Collector::Collector(const int32_t msk, BucketTable* bucketTbl):
- mask(msk),
- bucketTable(bucketTbl)
+ bucketTable(bucketTbl),
+ mask(msk)
{
}
Modified: trunk/clucene/src/CLucene/search/BooleanScorer.h
===================================================================
--- trunk/clucene/src/CLucene/search/BooleanScorer.h 2006-06-11 07:16:00 UTC (rev 427)
+++ trunk/clucene/src/CLucene/search/BooleanScorer.h 2006-06-26 00:39:24 UTC (rev 428)
@@ -1,18 +1,9 @@
-/**
- * Copyright 2003-2006 The Apache Software Foundation
- *
- * Licensed under the Apache License, Version 2.0 (the "License");
- * you may not use this file except in compliance with the License.
- * You may obtain a copy of the License at
- *
- * http://www.apache.org/licenses/LICENSE-2.0
- *
- * Unless required by applicable law or agreed to in writing, software
- * distributed under the License is distributed on an "AS IS" BASIS,
- * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
- * See the License for the specific language governing permissions and
- * limitations under the License.
- */
+/*------------------------------------------------------------------------------
+* Copyright (C) 2003-2006 Ben van Klinken and the CLucene Team
+*
+* Distributable under the terms of either the Apache License (Version 2.0) or
+* the GNU Lesser General Public License, as specified in the COPYING file.
+------------------------------------------------------------------------------*/
#ifndef _lucene_search_BooleanScorer_
#define _lucene_search_BooleanScorer_
@@ -41,14 +32,14 @@
class SubScorer: LUCENE_BASE {
public:
- bool done;
- Scorer* scorer;
- bool required;
- bool prohibited;
- HitCollector* collector;
- SubScorer* next;
- SubScorer(Scorer* scr, const bool r, const bool p, HitCollector* c, SubScorer* nxt);
- ~SubScorer();
+ bool done;
+ Scorer* scorer;
+ bool required;
+ bool prohibited;
+ HitCollector* collector;
+ SubScorer* next;
+ SubScorer(Scorer* scr, const bool r, const bool p, HitCollector* c, SubScorer* nxt);
+ ~SubScorer();
};
class BucketTable:LUCENE_BASE {
@@ -56,14 +47,11 @@
BooleanScorer* scorer;
public:
Bucket* buckets;
+ Bucket* first; // head of valid list
BucketTable(BooleanScorer* scr);
- //void collectHits(HitCollector* results);
int32_t size() const;
HitCollector* newCollector(const int32_t mask);
-
- Bucket* first; // head of valid list
-
void clear();
~BucketTable();
@@ -84,28 +72,23 @@
int32_t maxCoord;
int32_t nextMask;
+
+ void computeCoordFactors();
+ //void score(HitCollector* results, const int32_t maxDoc);
+
+ int32_t end;
+ Bucket* current;
public:
LUCENE_STATIC_CONSTANT(int32_t,BucketTable_SIZE=1024);
int32_t requiredMask;
int32_t prohibitedMask;
float_t* coordFactors;
- BooleanScorer(Similarity* similarity);
+ BooleanScorer(Similarity* similarity);
~BooleanScorer();
void add(Scorer* scorer, const bool required, const bool prohibited);
-
- private:
- void computeCoordFactors();
- //void score(HitCollector* results, const int32_t maxDoc);
-
- int32_t end;
- Bucket* current;
-
- public:
int32_t doc() { return current->doc; }
-
bool next();
-
float_t score();
bool skipTo(int32_t target);
Explanation* explain(int32_t doc);
Modified: trunk/clucene/src/CLucene/search/CachingWrapperFilter.cpp
===================================================================
--- trunk/clucene/src/CLucene/search/CachingWrapperFilter.cpp 2006-06-11 07:16:00 UTC (rev 427)
+++ trunk/clucene/src/CLucene/search/CachingWrapperFilter.cpp 2006-06-26 00:39:24 UTC (rev 428)
@@ -1,18 +1,9 @@
-/**
- * Copyright 2003-2006 The Apache Software Foundation
- *
- * Licensed under the Apache License, Version 2.0 (the "License");
- * you may not use this file except in compliance with the License.
- * You may obtain a copy of the License at
- *
- * http://www.apache.org/licenses/LICENSE-2.0
- *
- * Unless required by applicable law or agreed to in writing, software
- * distributed under the License is distributed on an "AS IS" BASIS,
- * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
- * See the License for the specific language governing permissions and
- * limitations under the License.
- */
+/*------------------------------------------------------------------------------
+* Copyright (C) 2003-2006 Ben van Klinken and the CLucene Team
+*
+* Distributable under the terms of either the Apache License (Version 2.0) or
+* the GNU Lesser General Public License, as specified in the COPYING file.
+------------------------------------------------------------------------------*/
#include "CLucene/StdHeader.h"
#include "CachingWrapperFilter.h"
@@ -50,7 +41,7 @@
cache.put(reader,bsh);
return bs;
}
-void AbstractCachingFilter::closeCallback(CL_NS(index)::IndexReader* reader, void* param){
+void AbstractCachingFilter::closeCallback(CL_NS(index)::IndexReader* reader, void*){
SCOPED_LOCK_MUTEX(cache.THIS_LOCK)
cache.remove(reader);
}
Modified: trunk/clucene/src/CLucene/search/CachingWrapperFilter.h
===================================================================
--- trunk/clucene/src/CLucene/search/CachingWrapperFilter.h 2006-06-11 07:16:00 UTC (rev 427)
+++ trunk/clucene/src/CLucene/search/CachingWrapperFilter.h 2006-06-26 00:39:24 UTC (rev 428)
@@ -1,18 +1,9 @@
-/**
- * Copyright 2003-2006 The Apache Software Foundation
- *
- * Licensed under the Apache License, Version 2.0 (the "License");
- * you may not use this file except in compliance with the License.
- * You may obtain a copy of the License at
- *
- * http://www.apache.org/licenses/LICENSE-2.0
- *
- * Unless required by applicable law or agreed to in writing, software
- * distributed under the License is distributed on an "AS IS" BASIS,
- * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
- * See the License for the specific language governing permissions and
- * limitations under the License.
- */
+/*------------------------------------------------------------------------------
+* Copyright (C) 2003-2006 Ben van Klinken and the CLucene Team
+*
+* Distributable under the terms of either the Apache License (Version 2.0) or
+* the GNU Lesser General Public License, as specified in the COPYING file.
+------------------------------------------------------------------------------*/
#ifndef _lucene_search_CachingWrapperFilter_
#define _lucene_search_CachingWrapperFilter_
@@ -72,8 +63,8 @@
private:
Filter* filter;
bool deleteFilter;
- CachingWrapperFilter( const CachingWrapperFilter& copy );
protected:
+ CachingWrapperFilter( const CachingWrapperFilter& copy );
CL_NS(util)::BitSet* doBits( CL_NS(index)::IndexReader* reader );
bool doShouldDeleteBitSet( CL_NS(util)::BitSet* bits );
public:
Modified: trunk/clucene/src/CLucene/search/ChainedFilter.cpp
===================================================================
--- trunk/clucene/src/CLucene/search/ChainedFilter.cpp 2006-06-11 07:16:00 UTC (rev 427)
+++ trunk/clucene/src/CLucene/search/ChainedFilter.cpp 2006-06-26 00:39:24 UTC (rev 428)
@@ -1,96 +1,48 @@
-/**
- * Copyright 2003-2006 The Apache Software Foundation
- *
- * Licensed under the Apache License, Version 2.0 (the "License");
- * you may not use this file except in compliance with the License.
- * You may obtain a copy of the License at
- *
- * http://www.apache.org/licenses/LICENSE-2.0
- *
- * Unless required by applicable law or agreed to in writing, software
- * distributed under the License is distributed on an "AS IS" BASIS,
- * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
- * See the License for the specific language governing permissions and
- * limitations under the License.
- */
+/*------------------------------------------------------------------------------
+* Copyright (C) 2003-2006 Ben van Klinken and the CLucene Team
+*
+* Distributable under the terms of either the Apache License (Version 2.0) or
+* the GNU Lesser General Public License, as specified in the COPYING file.
+------------------------------------------------------------------------------*/
#include <CLucene/StdHeader.h>
#include <CLucene/util/Misc.h>
#include "ChainedFilter.h"
-/*
- Discussion - brian at unixpoet.com
-
- From ChainedFilter.java:
-
- ...
-
- /*
- * First AND operation takes place against a completely false
- * bitset and will always return zero results. Thanks to
- * Daniel Armbrust for pointing this out and suggesting workaround.
- *//*
- if (logic[0] == AND)
- {
- result = (BitSet) chain[i].bits(reader).clone();
- ++i;
- }
-
- ...
-
- The observation is correct and it was buggy. The problem is that the same
- issue remains for the ANDNOT logic op but with the inverse result: all bits
- set to 1. The result of the other ops, i.e. OR, AND, XOR for the first filter
- ends up just copying the bitset of the first filter (explicitly in the case of the AND).
-
- Why not do the same for the NAND? This will have the side effect of rendering the first op
- in the logic array superflous - not a big problem.
-
- The only "problem" is that we will return different results then the Java
- Lucene code - though I prefer CLucene to be a correct implementation and only maintain
- API compat rather than full 100% compat with Lucene.
-*/
CL_NS_DEF(search)
CL_NS_USE(index)
CL_NS_USE(util)
CL_NS_USE(document)
-ChainedFilter::ChainedFilter( Filter ** filters, int _op )
+ChainedFilter::ChainedFilter( Filter ** _filters, int _op ):
+ filters(_filters),
+ logicArray(NULL),
+ logic(_op)
{
- this->filters = filters;
- this->logic = _op;
- this->logicArray = NULL;
}
-
-
-ChainedFilter::ChainedFilter( Filter** filters, int* _array )
+ChainedFilter::ChainedFilter( Filter** _filters, int* _array ):
+ filters(_filters),
+ logicArray(_array),
+ logic(-1)
{
- this->filters = filters;
- this->logic = -1;
- this->logicArray = _array;
}
-
-
+ChainedFilter::ChainedFilter( const ChainedFilter& copy ) :
+ logicArray( copy.logicArray ),
+ logic( copy.logic )
+{
+ filters = copy.filters;
+}
ChainedFilter::~ChainedFilter(void)
{
}
-
-ChainedFilter::ChainedFilter( const ChainedFilter& copy ) :
- filters( copy.filters ),
- logic( copy.logic ),
- logicArray( copy.logicArray )
-{
-}
-
-
Filter* ChainedFilter::clone() const {
return _CLNEW ChainedFilter(*this );
}
-TCHAR* ChainedFilter::getLogicString(int logic){
+const TCHAR* ChainedFilter::getLogicString(int logic){
if ( logic == ChainedFilter::OR )
return _T("OR");
else if ( logic == ChainedFilter::AND )
@@ -233,19 +185,19 @@
{
case OR:
for( i=0; i < maxDoc; i++ )
- resultset->set( i, resultset->get(i) || (filterbits==NULL || filterbits->get(i) ) );
+ resultset->set( i, (resultset->get(i) || (filterbits==NULL || filterbits->get(i) ))?1:0 );
break;
case AND:
for( i=0; i < maxDoc; i++ )
- resultset->set( i, resultset->get(i) && (filterbits==NULL || filterbits->get(i) ) );
+ resultset->set( i, (resultset->get(i) && (filterbits==NULL || filterbits->get(i) ))?1:0 );
break;
case ANDNOT:
for( i=0; i < maxDoc; i++ )
- resultset->set( i, !(resultset->get(i) && (filterbits==NULL || filterbits->get(i) ) ) );
+ resultset->set( i, (resultset->get(i) && (filterbits==NULL || filterbits->get(i)))?0:1 );
break;
case XOR:
for( i=0; i < maxDoc; i++ )
- resultset->set( i, resultset->get(i) ^ (filterbits==NULL || filterbits->get(i) ) );
+ resultset->set( i, resultset->get(i) ^ ((filterbits==NULL || filterbits->get(i) )?1:0) );
break;
default:
doChain( resultset, reader, DEFAULT, filter );
Modified: trunk/clucene/src/CLucene/search/ChainedFilter.h
===================================================================
--- trunk/clucene/src/CLucene/search/ChainedFilter.h 2006-06-11 07:16:00 UTC (rev 427)
+++ trunk/clucene/src/CLucene/search/ChainedFilter.h 2006-06-26 00:39:24 UTC (rev 428)
@@ -1,18 +1,9 @@
-/**
- * Copyright 2003-2006 The Apache Software Foundation
- *
- * Licensed under the Apache License, Version 2.0 (the "License");
- * you may not use this file except in compliance with the License.
- * You may obtain a copy of the License at
- *
- * http://www.apache.org/licenses/LICENSE-2.0
- *
- * Unless required by applicable law or agreed to in writing, software
- * distributed under the License is distributed on an "AS IS" BASIS,
- * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
- * See the License for the specific language governing permissions and
- * limitations under the License.
- */
+/*------------------------------------------------------------------------------
+* Copyright (C) 2003-2006 Ben van Klinken and the CLucene Team
+*
+* Distributable under the terms of either the Apache License (Version 2.0) or
+* the GNU Lesser General Public License, as specified in the COPYING file.
+------------------------------------------------------------------------------*/
#ifndef _lucene_search_ChainedFilter_
#define _lucene_search_ChainedFilter_
@@ -22,6 +13,37 @@
CL_NS_DEF(search)
+/*
+Discussion - brian at unixpoet.com
+
+From ChainedFilter.java:
+
+...
+
+// First AND operation takes place against a completely false
+// bitset and will always return zero results. Thanks to
+// Daniel Armbrust for pointing this out and suggesting workaround.
+
+if (logic[0] == AND)
+{
+ result = (BitSet) chain[i].bits(reader).clone();
+ ++i;
+}
+
+...
+
+The observation is correct and it was buggy. The problem is that the same
+issue remains for the ANDNOT logic op but with the inverse result: all bits
+set to 1. The result of the other ops, i.e. OR, AND, XOR for the first filter
+ends up just copying the bitset of the first filter (explicitly in the case of the AND).
+
+Why not do the same for the NAND? This will have the side effect of rendering the first op
+in the logic array superflous - not a big problem.
+
+The only "problem" is that we will return different results then the Java
+Lucene code - though I prefer CLucene to be a correct implementation and only maintain
+API compat rather than full 100% compat with Lucene.
+*/
class ChainedFilter: public Filter
{
public:
@@ -45,7 +67,7 @@
CL_NS(util)::BitSet* doChain( CL_NS(util)::BitSet* result, CL_NS(index)::IndexReader* reader, int logic, Filter* filter );
virtual void doUserChain( CL_NS(util)::BitSet* chain, CL_NS(util)::BitSet* filter, int logic );
- virtual TCHAR* getLogicString(int logic);
+ virtual const TCHAR* getLogicString(int logic);
public:
ChainedFilter( Filter** filters, int op = DEFAULT );
ChainedFilter( Filter** filters, int* _array );
Modified: trunk/clucene/src/CLucene/search/Compare.h
===================================================================
--- trunk/clucene/src/CLucene/search/Compare.h 2006-06-11 07:16:00 UTC (rev 427)
+++ trunk/clucene/src/CLucene/search/Compare.h 2006-06-26 00:39:24 UTC (rev 428)
@@ -1,18 +1,9 @@
-/**
- * Copyright 2003-2006 The Apache Software Foundation
- *
- * Licensed under the Apache License, Version 2.0 (the "License");
- * you may not use this file except in compliance with the License.
- * You may obtain a copy of the License at
- *
- * http://www.apache.org/licenses/LICENSE-2.0
- *
- * Unless required by applicable law or agreed to in writing, software
- * distributed under the License is distributed on an "AS IS" BASIS,
- * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
- * See the License for the specific language governing permissions and
- * limitations under the License.
- */
+/*------------------------------------------------------------------------------
+* Copyright (C) 2003-2006 Ben van Klinken and the CLucene Team
+*
+* Distributable under the terms of either the Apache License (Version 2.0) or
+* the GNU Lesser General Public License, as specified in the COPYING file.
+------------------------------------------------------------------------------*/
#ifndef _lucene_search_Compare_
#define _lucene_search_Compare_
@@ -26,6 +17,8 @@
class ScoreDocComparators:LUCENE_BASE {
+protected:
+ ScoreDocComparators(){}
public:
~ScoreDocComparators(){
}
@@ -41,7 +34,7 @@
return _CLNEW CL_NS(util)::Compare::Float (i->score);
}
int32_t sortType() {
- return SortField::SCORE;
+ return SortField::DOCSCORE;
}
};
Modified: trunk/clucene/src/CLucene/search/ConjunctionScorer.cpp
===================================================================
--- trunk/clucene/src/CLucene/search/ConjunctionScorer.cpp 2006-06-11 07:16:00 UTC (rev 427)
+++ trunk/clucene/src/CLucene/search/ConjunctionScorer.cpp 2006-06-26 00:39:24 UTC (rev 428)
@@ -1,18 +1,9 @@
-/**
- * Copyright 2003-2006 The Apache Software Foundation
- *
- * Licensed under the Apache License, Version 2.0 (the "License");
- * you may not use this file except in compliance with the License.
- * You may obtain a copy of the License at
- *
- * http://www.apache.org/licenses/LICENSE-2.0
- *
- * Unless required by applicable law or agreed to in writing, software
- * distributed under the License is distributed on an "AS IS" BASIS,
- * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
- * See the License for the specific language governing permissions and
- * limitations under the License.
- */
+/*------------------------------------------------------------------------------
+* Copyright (C) 2003-2006 Ben van Klinken and the CLucene Team
+*
+* Distributable under the terms of either the Apache License (Version 2.0) or
+* the GNU Lesser General Public License, as specified in the COPYING file.
+------------------------------------------------------------------------------*/
#include "CLucene/StdHeader.h"
#include "ConjunctionScorer.h"
#include "CLucene/util/Arrays.h"
@@ -31,12 +22,13 @@
if ( scorers.end() == scorers.begin() )
return NULL;
- CL_NS_STD(list)<Scorer*>::iterator i = scorers.end();
- i--;
+ CL_NS_STD(list)<Scorer*>::iterator i = scorers.end();
+ --i;
return *i;
} //get Last
class _ScorerSorter:public CL_NS(util)::Arrays::_Arrays<Scorer*>{
+ public:
bool equals(Scorer* o1,Scorer* o2) const{
return o1->doc() == o2->doc();
}
@@ -84,7 +76,7 @@
CL_NS_STD(list)<Scorer*>::iterator i = scorers.begin();
while (more && i!=scorers.end()) {
more = ((Scorer*)*i)->next();
- i++;
+ ++i;
}
if (more)
@@ -94,10 +86,11 @@
}
ConjunctionScorer::ConjunctionScorer(Similarity* similarity):
+ Scorer(similarity),
+ scorers(false),
firstTime(true),
more(true),
- Scorer(similarity),
- scorers(false)
+ coord(0.0)
{
}
ConjunctionScorer::~ConjunctionScorer(){
@@ -105,7 +98,7 @@
}
TCHAR *CL_NS(search)::Scorer::toString(void){
- return _T("ConjunctionScorer");
+ return STRDUP_TtoT(_T("ConjunctionScorer"));
}
@@ -129,8 +122,7 @@
CL_NS_STD(list)<Scorer*>::iterator i = scorers.begin();
while (more && i!=scorers.end()) {
more = ((Scorer*)*i)->skipTo(target);
-
- i++;
+ ++i;
}
if (more)
sortScorers(); // re-sort scorers
@@ -142,8 +134,7 @@
CL_NS_STD(list)<Scorer*>::iterator i = scorers.begin();
while (i!=scorers.end()){
score += (*i)->score();
-
- i++;
+ ++i;
}
score *= coord;
return score;
Modified: trunk/clucene/src/CLucene/search/ConjunctionScorer.h
===================================================================
--- trunk/clucene/src/CLucene/search/ConjunctionScorer.h 2006-06-11 07:16:00 UTC (rev 427)
+++ trunk/clucene/src/CLucene/search/ConjunctionScorer.h 2006-06-26 00:39:24 UTC (rev 428)
@@ -1,18 +1,9 @@
-/**
- * Copyright 2003-2006 The Apache Software Foundation
- *
- * Licensed under the Apache License, Version 2.0 (the "License");
- * you may not use this file except in compliance with the License.
- * You may obtain a copy of the License at
- *
- * http://www.apache.org/licenses/LICENSE-2.0
- *
- * Unless required by applicable law or agreed to in writing, software
- * distributed under the License is distributed on an "AS IS" BASIS,
- * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
- * See the License for the specific language governing permissions and
- * limitations under the License.
- */
+/*------------------------------------------------------------------------------
+* Copyright (C) 2003-2006 Ben van Klinken and the CLucene Team
+*
+* Distributable under the terms of either the Apache License (Version 2.0) or
+* the GNU Lesser General Public License, as specified in the COPYING file.
+------------------------------------------------------------------------------*/
#ifndef _lucene_search_ConjunctionScorer_
#define _lucene_search_ConjunctionScorer_
@@ -41,7 +32,7 @@
ConjunctionScorer(Similarity* similarity);
virtual ~ConjunctionScorer();
TCHAR* toString(void){
- return _T("ConjunctionScorer");
+ return STRDUP_TtoT(_T("ConjunctionScorer"));
}
void add(Scorer* scorer);
int32_t doc();
Modified: trunk/clucene/src/CLucene/search/DateFilter.cpp
===================================================================
--- trunk/clucene/src/CLucene/search/DateFilter.cpp 2006-06-11 07:16:00 UTC (rev 427)
+++ trunk/clucene/src/CLucene/search/DateFilter.cpp 2006-06-26 00:39:24 UTC (rev 428)
@@ -1,18 +1,9 @@
-/**
- * Copyright 2003-2006 The Apache Software Foundation
- *
- * Licensed under the Apache License, Version 2.0 (the "License");
- * you may not use this file except in compliance with the License.
- * You may obtain a copy of the License at
- *
- * http://www.apache.org/licenses/LICENSE-2.0
- *
- * Unless required by applicable law or agreed to in writing, software
- * distributed under the License is distributed on an "AS IS" BASIS,
- * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
- * See the License for the specific language governing permissions and
- * limitations under the License.
- */
+/*------------------------------------------------------------------------------
+* Copyright (C) 2003-2006 Ben van Klinken and the CLucene Team
+*
+* Distributable under the terms of either the Apache License (Version 2.0) or
+* the GNU Lesser General Public License, as specified in the COPYING file.
+------------------------------------------------------------------------------*/
#include "CLucene/StdHeader.h"
#include "DateFilter.h"
Modified: trunk/clucene/src/CLucene/search/DateFilter.h
===================================================================
--- trunk/clucene/src/CLucene/search/DateFilter.h 2006-06-11 07:16:00 UTC (rev 427)
+++ trunk/clucene/src/CLucene/search/DateFilter.h 2006-06-26 00:39:24 UTC (rev 428)
@@ -1,18 +1,9 @@
-/**
- * Copyright 2003-2006 The Apache Software Foundation
- *
- * Licensed under the Apache License, Version 2.0 (the "License");
- * you may not use this file except in compliance with the License.
- * You may obtain a copy of the License at
- *
- * http://www.apache.org/licenses/LICENSE-2.0
- *
- * Unless required by applicable law or agreed to in writing, software
- * distributed under the License is distributed on an "AS IS" BASIS,
- * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
- * See the License for the specific language governing permissions and
- * limitations under the License.
- */
+/*------------------------------------------------------------------------------
+* Copyright (C) 2003-2006 Ben van Klinken and the CLucene Team
+*
+* Distributable under the terms of either the Apache License (Version 2.0) or
+* the GNU Lesser General Public License, as specified in the COPYING file.
+------------------------------------------------------------------------------*/
#ifndef _lucene_search_DateFilter_
#define _lucene_search_DateFilter_
@@ -40,7 +31,8 @@
TCHAR* start;
TCHAR* end;
-
+
+ protected:
DateFilter(const DateFilter& copy);
public:
~DateFilter();
Modified: trunk/clucene/src/CLucene/search/ExactPhraseScorer.cpp
===================================================================
--- trunk/clucene/src/CLucene/search/ExactPhraseScorer.cpp 2006-06-11 07:16:00 UTC (rev 427)
+++ trunk/clucene/src/CLucene/search/ExactPhraseScorer.cpp 2006-06-26 00:39:24 UTC (rev 428)
@@ -1,18 +1,9 @@
-/**
- * Copyright 2003-2006 The Apache Software Foundation
- *
- * Licensed under the Apache License, Version 2.0 (the "License");
- * you may not use this file except in compliance with the License.
- * You may obtain a copy of the License at
- *
- * http://www.apache.org/licenses/LICENSE-2.0
- *
- * Unless required by applicable law or agreed to in writing, software
- * distributed under the License is distributed on an "AS IS" BASIS,
- * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
- * See the License for the specific language governing permissions and
- * limitations under the License.
- */
+/*------------------------------------------------------------------------------
+* Copyright (C) 2003-2006 Ben van Klinken and the CLucene Team
+*
+* Distributable under the terms of either the Apache License (Version 2.0) or
+* the GNU Lesser General Public License, as specified in the COPYING file.
+------------------------------------------------------------------------------*/
#include "CLucene/StdHeader.h"
#include "ExactPhraseScorer.h"
Modified: trunk/clucene/src/CLucene/search/ExactPhraseScorer.h
===================================================================
--- trunk/clucene/src/CLucene/search/ExactPhraseScorer.h 2006-06-11 07:16:00 UTC (rev 427)
+++ trunk/clucene/src/CLucene/search/ExactPhraseScorer.h 2006-06-26 00:39:24 UTC (rev 428)
@@ -1,18 +1,9 @@
-/**
- * Copyright 2003-2006 The Apache Software Foundation
- *
- * Licensed under the Apache License, Version 2.0 (the "License");
- * you may not use this file except in compliance with the License.
- * You may obtain a copy of the License at
- *
- * http://www.apache.org/licenses/LICENSE-2.0
- *
- * Unless required by applicable law or agreed to in writing, software
- * distributed under the License is distributed on an "AS IS" BASIS,
- * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
- * See the License for the specific language governing permissions and
- * limitations under the License.
- */
+/*------------------------------------------------------------------------------
+* Copyright (C) 2003-2006 Ben van Klinken and the CLucene Team
+*
+* Distributable under the terms of either the Apache License (Version 2.0) or
+* the GNU Lesser General Public License, as specified in the COPYING file.
+------------------------------------------------------------------------------*/
#ifndef _lucene_search_ExactPhraseScorer_
#define _lucene_search_ExactPhraseScorer_
Modified: trunk/clucene/src/CLucene/search/Explanation.cpp
===================================================================
--- trunk/clucene/src/CLucene/search/Explanation.cpp 2006-06-11 07:16:00 UTC (rev 427)
+++ trunk/clucene/src/CLucene/search/Explanation.cpp 2006-06-26 00:39:24 UTC (rev 428)
@@ -1,18 +1,9 @@
-/**
- * Copyright 2003-2006 The Apache Software Foundation
- *
- * Licensed under the Apache License, Version 2.0 (the "License");
- * you may not use this file except in compliance with the License.
- * You may obtain a copy of the License at
- *
- * http://www.apache.org/licenses/LICENSE-2.0
- *
- * Unless required by applicable law or agreed to in writing, software
- * distributed under the License is distributed on an "AS IS" BASIS,
- * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
- * See the License for the specific language governing permissions and
- * limitations under the License.
- */
+/*------------------------------------------------------------------------------
+* Copyright (C) 2003-2006 Ben van Klinken and the CLucene Team
+*
+* Distributable under the terms of either the Apache License (Version 2.0) or
+* the GNU Lesser General Public License, as specified in the COPYING file.
+------------------------------------------------------------------------------*/
#include "CLucene/StdHeader.h"
#include "Explanation.h"
#include "CLucene/util/StringBuffer.h"
@@ -21,6 +12,16 @@
CL_NS_DEF(search)
+Explanation::Explanation(float_t value, const TCHAR* description) {
+ this->value = value;
+ _tcsncpy(this->description,description,LUCENE_SEARCH_EXPLANATION_DESC_LEN);
+}
+
+Explanation::Explanation() {
+ this->value = 0;
+ this->description[0]=0;
+}
+
Explanation::Explanation(const Explanation& copy){
this->value = copy.value;
STRCPY_TtoT(description,copy.description,LUCENE_SEARCH_EXPLANATION_DESC_LEN);
@@ -29,14 +30,14 @@
itr = details.begin();
while ( itr != details.end() ){
details.push_back( (*itr)->clone() );
- itr++;
+ ++itr;
}
}
Explanation::~Explanation(){
}
-void Explanation::setDescription(TCHAR* description) {
+void Explanation::setDescription(const TCHAR* description) {
_tcsncpy(this->description,description,LUCENE_SEARCH_EXPLANATION_DESC_LEN);
}
@@ -45,7 +46,7 @@
return _CLNEW Explanation(*this);
}
-float_t Explanation::getValue() {
+float_t Explanation::getValue() const{
return value;
}
@@ -53,7 +54,7 @@
this->value = value;
}
-TCHAR* Explanation::getDescription() {
+const TCHAR* Explanation::getDescription() const {
return description;
}
@@ -82,11 +83,6 @@
return buffer.toString();
}
-Explanation::Explanation(float_t value, TCHAR* description) {
- this->value = value;
- _tcsncpy(this->description,description,LUCENE_SEARCH_EXPLANATION_DESC_LEN);
-}
-
/** The sub-nodes of this explanation node. */
Explanation** Explanation::getDetails() {
Explanation** ret = _CL_NEWARRAY(Explanation*,details.size()+1);
Modified: trunk/clucene/src/CLucene/search/Explanation.h
===================================================================
--- trunk/clucene/src/CLucene/search/Explanation.h 2006-06-11 07:16:00 UTC (rev 427)
+++ trunk/clucene/src/CLucene/search/Explanation.h 2006-06-26 00:39:24 UTC (rev 428)
@@ -1,18 +1,9 @@
-/**
- * Copyright 2003-2006 The Apache Software Foundation
- *
- * Licensed under the Apache License, Version 2.0 (the "License");
- * you may not use this file except in compliance with the License.
- * You may obtain a copy of the License at
- *
- * http://www.apache.org/licenses/LICENSE-2.0
- *
- * Unless required by applicable law or agreed to in writing, software
- * distributed under the License is distributed on an "AS IS" BASIS,
- * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
- * See the License for the specific language governing permissions and
- * limitations under the License.
- */
+/*------------------------------------------------------------------------------
+* Copyright (C) 2003-2006 Ben van Klinken and the CLucene Team
+*
+* Distributable under the terms of either the Apache License (Version 2.0) or
+* the GNU Lesser General Public License, as specified in the COPYING file.
+------------------------------------------------------------------------------*/
#ifndef _lucene_search_Explanation
#define _lucene_search_Explanation
@@ -30,26 +21,27 @@
CL_NS(util)::CLArrayList<Explanation*,CL_NS(util)::Deletor::Object<Explanation> > details; // sub-explanations
TCHAR* toString(int32_t depth);
+ protected:
Explanation(const Explanation& copy);
public:
- Explanation() {}
+ Explanation();
~Explanation();
- Explanation(float_t value, TCHAR* description);
+ Explanation(float_t value, const TCHAR* description);
Explanation* clone() const;
/** The value assigned to this explanation node. */
- float_t getValue();
+ float_t getValue() const;
/** Sets the value assigned to this explanation node. */
void setValue(float_t value);
/** A description of this explanation node. */
- TCHAR* getDescription(); ///<returns reference
+ const TCHAR* getDescription() const; ///<returns reference
/** Sets the description of this explanation node. */
- void setDescription(TCHAR* description);
+ void setDescription(const TCHAR* description);
/** The sub-nodes of this explanation node. */
Explanation** getDetails();
Modified: trunk/clucene/src/CLucene/search/FieldCache.cpp
===================================================================
--- trunk/clucene/src/CLucene/search/FieldCache.cpp 2006-06-11 07:16:00 UTC (rev 427)
+++ trunk/clucene/src/CLucene/search/FieldCache.cpp 2006-06-26 00:39:24 UTC (rev 428)
@@ -1,18 +1,9 @@
-/**
- * Copyright 2003-2006 The Apache Software Foundation
- *
- * Licensed under the Apache License, Version 2.0 (the "License");
- * you may not use this file except in compliance with the License.
- * You may obtain a copy of the License at
- *
- * http://www.apache.org/licenses/LICENSE-2.0
- *
- * Unless required by applicable law or agreed to in writing, software
- * distributed under the License is distributed on an "AS IS" BASIS,
- * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
- * See the License for the specific language governing permissions and
- * limitations under the License.
- */
+/*------------------------------------------------------------------------------
+* Copyright (C) 2003-2006 Ben van Klinken and the CLucene Team
+*
+* Distributable under the terms of either the Apache License (Version 2.0) or
+* the GNU Lesser General Public License, as specified in the COPYING file.
+------------------------------------------------------------------------------*/
#include "CLucene/StdHeader.h"
#include "FieldCache.h"
#include "FieldCacheImpl.h"
@@ -26,6 +17,14 @@
contentType = type;
contentLen = len;
ownContents = false;
+
+ intArray=NULL;
+ floatArray=NULL;
+ stringIndex=NULL;
+ stringArray=NULL;
+ comparableArray=NULL;
+ sortComparator=NULL;
+ scoreDocComparator=NULL;
}
FieldCacheAuto::~FieldCacheAuto(){
if ( contentType == FieldCacheAuto::INT_ARRAY ){
Modified: trunk/clucene/src/CLucene/search/FieldCache.h
===================================================================
--- trunk/clucene/src/CLucene/search/FieldCache.h 2006-06-11 07:16:00 UTC (rev 427)
+++ trunk/clucene/src/CLucene/search/FieldCache.h 2006-06-26 00:39:24 UTC (rev 428)
@@ -1,18 +1,9 @@
-/**
- * Copyright 2003-2006 The Apache Software Foundation
- *
- * Licensed under the Apache License, Version 2.0 (the "License");
- * you may not use this file except in compliance with the License.
- * You may obtain a copy of the License at
- *
- * http://www.apache.org/licenses/LICENSE-2.0
- *
- * Unless required by applicable law or agreed to in writing, software
- * distributed under the License is distributed on an "AS IS" BASIS,
- * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
- * See the License for the specific language governing permissions and
- * limitations under the License.
- */
+/*------------------------------------------------------------------------------
+* Copyright (C) 2003-2006 Ben van Klinken and the CLucene Team
+*
+* Distributable under the terms of either the Apache License (Version 2.0) or
+* the GNU Lesser General Public License, as specified in the COPYING file.
+------------------------------------------------------------------------------*/
#ifndef _lucene_search_FieldCache_
#define _lucene_search_FieldCache_
Modified: trunk/clucene/src/CLucene/search/FieldCacheImpl.cpp
===================================================================
--- trunk/clucene/src/CLucene/search/FieldCacheImpl.cpp 2006-06-11 07:16:00 UTC (rev 427)
+++ trunk/clucene/src/CLucene/search/FieldCacheImpl.cpp 2006-06-26 00:39:24 UTC (rev 428)
@@ -1,18 +1,9 @@
-/**
- * Copyright 2003-2006 The Apache Software Foundation
- *
- * Licensed under the Apache License, Version 2.0 (the "License");
- * you may not use this file except in compliance with the License.
- * You may obtain a copy of the License at
- *
- * http://www.apache.org/licenses/LICENSE-2.0
- *
- * Unless required by applicable law or agreed to in writing, software
- * distributed under the License is distributed on an "AS IS" BASIS,
- * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
- * See the License for the specific language governing permissions and
- * limitations under the License.
- */
+/*------------------------------------------------------------------------------
+* Copyright (C) 2003-2006 Ben van Klinken and the CLucene Team
+*
+* Distributable under the terms of either the Apache License (Version 2.0) or
+* the GNU Lesser General Public License, as specified in the COPYING file.
+------------------------------------------------------------------------------*/
#include "CLucene/StdHeader.h"
#include "FieldCacheImpl.h"
@@ -530,7 +521,7 @@
if ( f->getType() != SortField::AUTO )
_CLDELETE( itr->second );
_CLDELETE( f );
- itr++;
+ ++itr;
}
clear();
}
Modified: trunk/clucene/src/CLucene/search/FieldCacheImpl.h
===================================================================
--- trunk/clucene/src/CLucene/search/FieldCacheImpl.h 2006-06-11 07:16:00 UTC (rev 427)
+++ trunk/clucene/src/CLucene/search/FieldCacheImpl.h 2006-06-26 00:39:24 UTC (rev 428)
@@ -1,18 +1,9 @@
-/**
- * Copyright 2003-2006 The Apache Software Foundation
- *
- * Licensed under the Apache License, Version 2.0 (the "License");
- * you may not use this file except in compliance with the License.
- * You may obtain a copy of the License at
- *
- * http://www.apache.org/licenses/LICENSE-2.0
- *
- * Unless required by applicable law or agreed to in writing, software
- * distributed under the License is distributed on an "AS IS" BASIS,
- * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
- * See the License for the specific language governing permissions and
- * limitations under the License.
- */
+/*------------------------------------------------------------------------------
+* Copyright (C) 2003-2006 Ben van Klinken and the CLucene Team
+*
+* Distributable under the terms of either the Apache License (Version 2.0) or
+* the GNU Lesser General Public License, as specified in the COPYING file.
+------------------------------------------------------------------------------*/
#ifndef _lucene_search_FieldCacheImpl_
#define _lucene_search_FieldCacheImpl_
@@ -49,10 +40,10 @@
FileEntry (const TCHAR* field, SortComparatorSource* custom);
~FileEntry();
- int32_t getType(){ return type; }
+ int32_t getType() const{ return type; }
/** Two of these are equal iff they reference the same field and type. */
- bool equals (FileEntry* other);
+ bool equals (FileEntry* other) const;
/** Composes a hashcode based on the field and type. */
size_t hashCode();
Modified: trunk/clucene/src/CLucene/search/FieldDoc.h
===================================================================
--- trunk/clucene/src/CLucene/search/FieldDoc.h 2006-06-11 07:16:00 UTC (rev 427)
+++ trunk/clucene/src/CLucene/search/FieldDoc.h 2006-06-26 00:39:24 UTC (rev 428)
@@ -1,18 +1,9 @@
-/**
- * Copyright 2003-2006 The Apache Software Foundation
- *
- * Licensed under the Apache License, Version 2.0 (the "License");
- * you may not use this file except in compliance with the License.
- * You may obtain a copy of the License at
- *
- * http://www.apache.org/licenses/LICENSE-2.0
- *
- * Unless required by applicable law or agreed to in writing, software
- * distributed under the License is distributed on an "AS IS" BASIS,
- * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
- * See the License for the specific language governing permissions and
- * limitations under the License.
- */
+/*------------------------------------------------------------------------------
+* Copyright (C) 2003-2006 Ben van Klinken and the CLucene Team
+*
+* Distributable under the terms of either the Apache License (Version 2.0) or
+* the GNU Lesser General Public License, as specified in the COPYING file.
+------------------------------------------------------------------------------*/
#ifndef _lucene_search_FieldDoc_
#define _lucene_search_FieldDoc_
Modified: trunk/clucene/src/CLucene/search/FieldDocSortedHitQueue.cpp
===================================================================
--- trunk/clucene/src/CLucene/search/FieldDocSortedHitQueue.cpp 2006-06-11 07:16:00 UTC (rev 427)
+++ trunk/clucene/src/CLucene/search/FieldDocSortedHitQueue.cpp 2006-06-26 00:39:24 UTC (rev 428)
@@ -1,18 +1,9 @@
-/**
- * Copyright 2003-2006 The Apache Software Foundation
- *
- * Licensed under the Apache License, Version 2.0 (the "License");
- * you may not use this file except in compliance with the License.
- * You may obtain a copy of the License at
- *
- * http://www.apache.org/licenses/LICENSE-2.0
- *
- * Unless required by applicable law or agreed to in writing, software
- * distributed under the License is distributed on an "AS IS" BASIS,
- * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
- * See the License for the specific language governing permissions and
- * limitations under the License.
- */
+/*------------------------------------------------------------------------------
+* Copyright (C) 2003-2006 Ben van Klinken and the CLucene Team
+*
+* Distributable under the terms of either the Apache License (Version 2.0) or
+* the GNU Lesser General Public License, as specified in the COPYING file.
+------------------------------------------------------------------------------*/
#include "CLucene/StdHeader.h"
#include "FieldDocSortedHitQueue.h"
@@ -31,22 +22,22 @@
int32_t type = fields[i]->getType();
if (fields[i]->getReverse()) {
switch (type) {
- case SortField::SCORE:
- r1 = ((Compare::Float*)docA->fields[i])->getValue();
- r2 = ((Compare::Float*)docB->fields[i])->getValue();
+ case SortField::DOCSCORE:
+ r1 = __REINTERPRET_CAST(Compare::Float*, docA->fields[i])->getValue();
+ r2 = __REINTERPRET_CAST(Compare::Float*, docB->fields[i])->getValue();
if (r1 < r2) c = -1;
if (r1 > r2) c = 1;
break;
case SortField::DOC:
case SortField::INT:
- i1 = ((Compare::Int32*)docA->fields[i])->getValue();
- i2 = ((Compare::Int32*)docB->fields[i])->getValue();
+ i1 = __REINTERPRET_CAST(Compare::Int32*, docA->fields[i])->getValue();
+ i2 = __REINTERPRET_CAST(Compare::Int32*, docB->fields[i])->getValue();
if (i1 > i2) c = -1;
if (i1 < i2) c = 1;
break;
case SortField::STRING:
- s1 = ((Compare::TChar*) docA->fields[i])->getValue();
- s2 = ((Compare::TChar*) docB->fields[i])->getValue();
+ s1 = __REINTERPRET_CAST(Compare::TChar*, docA->fields[i])->getValue();
+ s2 = __REINTERPRET_CAST(Compare::TChar*, docB->fields[i])->getValue();
if (s2 == NULL) c = -1; // could be NULL if there are
else if (s1 == NULL) c = 1; // no terms in the given field
else c = _tcscmp(s2,s1); //else if (fields[i].getLocale() == NULL) {
@@ -57,8 +48,8 @@
}*/
break;
case SortField::FLOAT:
- f1 = ((Compare::Float*)docA->fields[i])->getValue();
- f2 = ((Compare::Float*)docB->fields[i])->getValue();
+ f1 = __REINTERPRET_CAST(Compare::Float*, docA->fields[i])->getValue();
+ f2 = __REINTERPRET_CAST(Compare::Float*, docB->fields[i])->getValue();
if (f1 > f2) c = -1;
if (f1 < f2) c = 1;
break;
@@ -76,22 +67,22 @@
}
} else {
switch (type) {
- case SortField::SCORE:
- r1 = ((Compare::Float*)docA->fields[i])->getValue();
- r2 = ((Compare::Float*)docB->fields[i])->getValue();
+ case SortField::DOCSCORE:
+ r1 = __REINTERPRET_CAST(Compare::Float*, docA->fields[i])->getValue();
+ r2 = __REINTERPRET_CAST(Compare::Float*, docB->fields[i])->getValue();
if (r1 > r2) c = -1;
if (r1 < r2) c = 1;
break;
case SortField::DOC:
case SortField::INT:
- i1 = ((Compare::Int32*)docA->fields[i])->getValue();
- i2 = ((Compare::Int32*)docB->fields[i])->getValue();
+ i1 = __REINTERPRET_CAST(Compare::Int32*, docA->fields[i])->getValue();
+ i2 = __REINTERPRET_CAST(Compare::Int32*, docB->fields[i])->getValue();
if (i1 < i2) c = -1;
if (i1 > i2) c = 1;
break;
case SortField::STRING:
- s1 = ((Compare::TChar*) docA->fields[i])->getValue();
- s2 = ((Compare::TChar*) docB->fields[i])->getValue();
+ s1 = __REINTERPRET_CAST(Compare::TChar*, docA->fields[i])->getValue();
+ s2 = __REINTERPRET_CAST(Compare::TChar*, docB->fields[i])->getValue();
// NULL values need to be sorted first, because of how FieldCache.getStringIndex()
// works - in that routine, any documents without a value in the given field are
// put first.
@@ -104,8 +95,8 @@
}*/
break;
case SortField::FLOAT:
- f1 = ((Compare::Float*)docA->fields[i])->getValue();
- f2 = ((Compare::Float*)docB->fields[i])->getValue();
+ f1 = __REINTERPRET_CAST(Compare::Float*, docA->fields[i])->getValue();
+ f2 = __REINTERPRET_CAST(Compare::Float*, docB->fields[i])->getValue();
if (f1 < f2) c = -1;
if (f1 > f2) c = 1;
break;
@@ -126,7 +117,7 @@
return c > 0;
}
-void FieldDocSortedHitQueue::setFields (SortField** fields) {
+void FieldDocSortedHitQueue::setFields (const SortField** fields) {
SCOPED_LOCK_MUTEX(THIS_LOCK)
if (this->fields == NULL) {
this->fields = fields;
Modified: trunk/clucene/src/CLucene/search/FieldDocSortedHitQueue.h
===================================================================
--- trunk/clucene/src/CLucene/search/FieldDocSortedHitQueue.h 2006-06-11 07:16:00 UTC (rev 427)
+++ trunk/clucene/src/CLucene/search/FieldDocSortedHitQueue.h 2006-06-26 00:39:24 UTC (rev 428)
@@ -1,18 +1,9 @@
-/**
- * Copyright 2003-2006 The Apache Software Foundation
- *
- * Licensed under the Apache License, Version 2.0 (the "License");
- * you may not use this file except in compliance with the License.
- * You may obtain a copy of the License at
- *
- * http://www.apache.org/licenses/LICENSE-2.0
- *
- * Unless required by applicable law or agreed to in writing, software
- * distributed under the License is distributed on an "AS IS" BASIS,
- * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
- * See the License for the specific language governing permissions and
- * limitations under the License.
- */
+/*------------------------------------------------------------------------------
+* Copyright (C) 2003-2006 Ben van Klinken and the CLucene Team
+*
+* Distributable under the terms of either the Apache License (Version 2.0) or
+* the GNU Lesser General Public License, as specified in the COPYING file.
+------------------------------------------------------------------------------*/
#ifndef _lucene_search_FieldDocSortedHitQueue_
#define _lucene_search_FieldDocSortedHitQueue_
@@ -44,7 +35,7 @@
// this cannot contain AUTO fields - any AUTO fields should
// have been resolved by the time this class is used.
- SortField** fields; //volatile
+ const SortField** fields; //volatile
int32_t fieldsLen;
void _countsize(){
@@ -64,7 +55,7 @@
* @param fields Field names, in priority order (highest priority first).
* @param size The number of hits to retain. Must be greater than zero.
*/
- FieldDocSortedHitQueue (SortField** fields, int32_t size) {
+ FieldDocSortedHitQueue (const SortField** fields, int32_t size) {
this->fields = fields;
_countsize();
//this->collators = hasCollators (fields);
@@ -82,11 +73,11 @@
* This method is thread safe.
* @param fields
*/
- void setFields (SortField** fields);
+ void setFields (const SortField** fields);
/** Returns the fields being used to sort. */
- SortField** getFields() {
+ const SortField** getFields() {
return fields;
}
Modified: trunk/clucene/src/CLucene/search/FieldSortedHitQueue.cpp
===================================================================
--- trunk/clucene/src/CLucene/search/FieldSortedHitQueue.cpp 2006-06-11 07:16:00 UTC (rev 427)
+++ trunk/clucene/src/CLucene/search/FieldSortedHitQueue.cpp 2006-06-26 00:39:24 UTC (rev 428)
@@ -1,18 +1,9 @@
-/**
- * Copyright 2003-2006 The Apache Software Foundation
- *
- * Licensed under the Apache License, Version 2.0 (the "License");
- * you may not use this file except in compliance with the License.
- * You may obtain a copy of the License at
- *
- * http://www.apache.org/licenses/LICENSE-2.0
- *
- * Unless required by applicable law or agreed to in writing, software
- * distributed under the License is distributed on an "AS IS" BASIS,
- * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
- * See the License for the specific language governing permissions and
- * limitations under the License.
- */
+/*------------------------------------------------------------------------------
+* Copyright (C) 2003-2006 Ben van Klinken and the CLucene Team
+*
+* Distributable under the terms of either the Apache License (Version 2.0) or
+* the GNU Lesser General Public License, as specified in the COPYING file.
+------------------------------------------------------------------------------*/
#include "CLucene/StdHeader.h"
#include "FieldSortedHitQueue.h"
#include "Compare.h"
@@ -23,24 +14,25 @@
FieldSortedHitQueue::hitqueueCacheType FieldSortedHitQueue::Comparators(false,true);
-FieldSortedHitQueue::FieldSortedHitQueue (IndexReader* reader, SortField** fields, int32_t size):
- maxscore(1.0f),
- fieldsLen(0)
+FieldSortedHitQueue::FieldSortedHitQueue (IndexReader* reader, SortField** _fields, int32_t size):
+ fieldsLen(0),
+ maxscore(1.0f)
{
- while ( fields[fieldsLen] != 0 )
+ while ( _fields[fieldsLen] != 0 )
fieldsLen++;
comparators = _CL_NEWARRAY(ScoreDocComparator*,fieldsLen+1);
- this->fields = _CL_NEWARRAY(SortField*,fieldsLen+1);
+ SortField** tmp = _CL_NEWARRAY(SortField*,fieldsLen+1);
for (int32_t i=0; i<fieldsLen; ++i) {
- const TCHAR* fieldname = fields[i]->getField();
+ const TCHAR* fieldname = _fields[i]->getField();
//todo: fields[i].getLocale(), not implemented
- comparators[i] = getCachedComparator (reader, fieldname, fields[i]->getType(), fields[i]->getFactory());
- this->fields[i] = _CLNEW SortField (fieldname, comparators[i]->sortType(), fields[i]->getReverse());
+ comparators[i] = getCachedComparator (reader, fieldname, _fields[i]->getType(), _fields[i]->getFactory());
+ tmp[i] = _CLNEW SortField (fieldname, comparators[i]->sortType(), _fields[i]->getReverse());
}
comparatorsLen = fieldsLen;
comparators[fieldsLen]=NULL;
- this->fields[fieldsLen] = NULL;
+ tmp[fieldsLen] = NULL;
+ this->fields = tmp;
initialize(size,true);
}
@@ -99,7 +91,7 @@
ScoreDocComparator* FieldSortedHitQueue::getCachedComparator (IndexReader* reader, const TCHAR* fieldname, int32_t type, SortComparatorSource* factory){
if (type == SortField::DOC)
return ScoreDocComparator::INDEXORDER;
- if (type == SortField::SCORE)
+ if (type == SortField::DOCSCORE)
return ScoreDocComparator::RELEVANCE;
ScoreDocComparator* comparator = lookup (reader, fieldname, type, factory);
if (comparator == NULL) {
@@ -133,7 +125,7 @@
}
- FieldDoc* FieldSortedHitQueue::fillFields (FieldDoc* doc) {
+ FieldDoc* FieldSortedHitQueue::fillFields (FieldDoc* doc) const{
int32_t n = comparatorsLen;
Comparable** fields = _CL_NEWARRAY(Comparable*,n+1);
for (int32_t i=0; i<n; ++i)
@@ -165,7 +157,7 @@
return sdc;
}
- void FieldSortedHitQueue::closeCallback(CL_NS(index)::IndexReader* reader, void* param){
+ void FieldSortedHitQueue::closeCallback(CL_NS(index)::IndexReader* reader, void*){
SCOPED_LOCK_MUTEX(Comparators.THIS_LOCK)
Comparators.remove(reader);
}
Modified: trunk/clucene/src/CLucene/search/FieldSortedHitQueue.h
===================================================================
--- trunk/clucene/src/CLucene/search/FieldSortedHitQueue.h 2006-06-11 07:16:00 UTC (rev 427)
+++ trunk/clucene/src/CLucene/search/FieldSortedHitQueue.h 2006-06-26 00:39:24 UTC (rev 428)
@@ -1,18 +1,9 @@
-/**
- * Copyright 2003-2006 The Apache Software Foundation
- *
- * Licensed under the Apache License, Version 2.0 (the "License");
- * you may not use this file except in compliance with the License.
- * You may obtain a copy of the License at
- *
- * http://www.apache.org/licenses/LICENSE-2.0
- *
- * Unless required by applicable law or agreed to in writing, software
- * distributed under the License is distributed on an "AS IS" BASIS,
- * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
- * See the License for the specific language governing permissions and
- * limitations under the License.
- */
+/*------------------------------------------------------------------------------
+* Copyright (C) 2003-2006 Ben van Klinken and the CLucene Team
+*
+* Distributable under the terms of either the Apache License (Version 2.0) or
+* the GNU Lesser General Public License, as specified in the COPYING file.
+------------------------------------------------------------------------------*/
#ifndef _lucene_search_FieldSortedHitQueue_
#define _lucene_search_FieldSortedHitQueue_
@@ -131,7 +122,7 @@
* @return The same FieldDoc passed in.
* @see Searchable#search(Query,Filter,int32_t,Sort)
*/
- FieldDoc* fillFields (FieldDoc* doc);
+ FieldDoc* fillFields (FieldDoc* doc) const;
/** Returns the SortFields being used by this hit queue. */
Modified: trunk/clucene/src/CLucene/search/Filter.h
===================================================================
--- trunk/clucene/src/CLucene/search/Filter.h 2006-06-11 07:16:00 UTC (rev 427)
+++ trunk/clucene/src/CLucene/search/Filter.h 2006-06-26 00:39:24 UTC (rev 428)
@@ -1,18 +1,9 @@
-/**
- * Copyright 2003-2006 The Apache Software Foundation
- *
- * Licensed under the Apache License, Version 2.0 (the "License");
- * you may not use this file except in compliance with the License.
- * You may obtain a copy of the License at
- *
- * http://www.apache.org/licenses/LICENSE-2.0
- *
- * Unless required by applicable law or agreed to in writing, software
- * distributed under the License is distributed on an "AS IS" BASIS,
- * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
- * See the License for the specific language governing permissions and
- * limitations under the License.
- */
+/*------------------------------------------------------------------------------
+* Copyright (C) 2003-2006 Ben van Klinken and the CLucene Team
+*
+* Distributable under the terms of either the Apache License (Version 2.0) or
+* the GNU Lesser General Public License, as specified in the COPYING file.
+------------------------------------------------------------------------------*/
#ifndef _lucene_search_Filter_
#define _lucene_search_Filter_
Modified: trunk/clucene/src/CLucene/search/FilteredTermEnum.cpp
===================================================================
--- trunk/clucene/src/CLucene/search/FilteredTermEnum.cpp 2006-06-11 07:16:00 UTC (rev 427)
+++ trunk/clucene/src/CLucene/search/FilteredTermEnum.cpp 2006-06-26 00:39:24 UTC (rev 428)
@@ -1,18 +1,9 @@
-/**
- * Copyright 2003-2006 The Apache Software Foundation
- *
- * Licensed under the Apache License, Version 2.0 (the "License");
- * you may not use this file except in compliance with the License.
- * You may obtain a copy of the License at
- *
- * http://www.apache.org/licenses/LICENSE-2.0
- *
- * Unless required by applicable law or agreed to in writing, software
- * distributed under the License is distributed on an "AS IS" BASIS,
- * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
- * See the License for the specific language governing permissions and
- * limitations under the License.
- */
+/*------------------------------------------------------------------------------
+* Copyright (C) 2003-2006 Ben van Klinken and the CLucene Team
+*
+* Distributable under the terms of either the Apache License (Version 2.0) or
+* the GNU Lesser General Public License, as specified in the COPYING file.
+------------------------------------------------------------------------------*/
#include "CLucene/StdHeader.h"
#include "FilteredTermEnum.h"
@@ -76,9 +67,8 @@
//Get a reference to the matched term
currentTerm = _CL_POINTER(term);
return true;
- }
}
- else
+ }else
return false;
}
_CLDECDELETE(currentTerm);
@@ -87,17 +77,20 @@
return false;
}
- Term* FilteredTermEnum::term(const bool pointer) {
+ Term* FilteredTermEnum::term() {
//Func - Returns the current Term in the enumeration.
//Pre - next() must have been called at least once
// pointer is true or false
//Post - if pre(pointer) is true the reference counter of currentTerm is increased
// and current Term is returned otherwise currentTerm is only returned
- if ( pointer && currentTerm!=NULL )
- return _CL_POINTER(currentTerm);
+ return _CL_POINTER(currentTerm);
+ }
+ Term* FilteredTermEnum::term(bool pointer) {
+ if ( pointer )
+ return _CL_POINTER(currentTerm);
else
- return currentTerm;
+ return currentTerm;
}
void FilteredTermEnum::close(){
@@ -137,7 +130,7 @@
currentTerm = _CL_POINTER(term);
}else{
next();
- }
+ }
}
CL_NS_END
Modified: trunk/clucene/src/CLucene/search/FilteredTermEnum.h
===================================================================
--- trunk/clucene/src/CLucene/search/FilteredTermEnum.h 2006-06-11 07:16:00 UTC (rev 427)
+++ trunk/clucene/src/CLucene/search/FilteredTermEnum.h 2006-06-26 00:39:24 UTC (rev 428)
@@ -1,18 +1,9 @@
-/**
- * Copyright 2003-2006 The Apache Software Foundation
- *
- * Licensed under the Apache License, Version 2.0 (the "License");
- * you may not use this file except in compliance with the License.
- * You may obtain a copy of the License at
- *
- * http://www.apache.org/licenses/LICENSE-2.0
- *
- * Unless required by applicable law or agreed to in writing, software
- * distributed under the License is distributed on an "AS IS" BASIS,
- * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
- * See the License for the specific language governing permissions and
- * limitations under the License.
- */
+/*------------------------------------------------------------------------------
+* Copyright (C) 2003-2006 Ben van Klinken and the CLucene Team
+*
+* Distributable under the terms of either the Apache License (Version 2.0) or
+* the GNU Lesser General Public License, as specified in the COPYING file.
+------------------------------------------------------------------------------*/
#ifndef _lucene_search_FilteredTermEnum_
#define _lucene_search_FilteredTermEnum_
@@ -30,7 +21,7 @@
//the enumeration is greater than all that precede it.
class FilteredTermEnum: public CL_NS(index)::TermEnum {
- public:
+ public:
//Constructor
FilteredTermEnum();
//Destructor
@@ -45,8 +36,9 @@
//Increments the enumeration to the next element
bool next() ;
- //Returns the current Term in the enumeration.
- CL_NS(index)::Term* term(const bool pointer=true) ;
+ //Returns a pointer to the current Term in the enumeration.
+ CL_NS(index)::Term* term();
+ CL_NS(index)::Term* term(bool pointer);
//Closes the enumeration to further activity, freeing resources.
void close();
Modified: trunk/clucene/src/CLucene/search/FuzzyQuery.cpp
===================================================================
--- trunk/clucene/src/CLucene/search/FuzzyQuery.cpp 2006-06-11 07:16:00 UTC (rev 427)
+++ trunk/clucene/src/CLucene/search/FuzzyQuery.cpp 2006-06-26 00:39:24 UTC (rev 428)
@@ -1,18 +1,9 @@
-/**
- * Copyright 2003-2006 The Apache Software Foundation
- *
- * Licensed under the Apache License, Version 2.0 (the "License");
- * you may not use this file except in compliance with the License.
- * You may obtain a copy of the License at
- *
- * http://www.apache.org/licenses/LICENSE-2.0
- *
- * Unless required by applicable law or agreed to in writing, software
- * distributed under the License is distributed on an "AS IS" BASIS,
- * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
- * See the License for the specific language governing permissions and
- * limitations under the License.
- */
+/*------------------------------------------------------------------------------
+* Copyright (C) 2003-2006 Ben van Klinken and the CLucene Team
+*
+* Distributable under the terms of either the Apache License (Version 2.0) or
+* the GNU Lesser General Public License, as specified in the COPYING file.
+------------------------------------------------------------------------------*/
#include "CLucene/StdHeader.h"
#include "FuzzyQuery.h"
#ifndef NO_FUZZY_QUERY
@@ -32,11 +23,11 @@
* @param prefixLength Length of required common prefix. Default value is 0.
* @throws IOException
*/
- FuzzyTermEnum::FuzzyTermEnum(IndexReader* reader, Term* term, float_t minSimilarity, int32_t prefixLength):
+ FuzzyTermEnum::FuzzyTermEnum(const IndexReader* reader, Term* term, float_t minSimilarity, size_t prefixLength):
+ distance(0),
_endEnum(false),
prefix(LUCENE_BLANK_STRING),
prefixLength(0),
- distance(0),
minimumSimilarity(minSimilarity)
{ //todo: check, used to pass (reader,term)
@@ -45,36 +36,36 @@
// term != NULL
//Post - The instance has been created
- CND_PRECONDITION(term != NULL,"term is NULL");
-
- scale_factor = 1.0f / (1.0f - minimumSimilarity);
- searchTerm = _CL_POINTER(term);
-
- text = STRDUP_TtoT(term->text());
- textLen = term->textLength();
-
-
- //Initialize e to NULL
- e = NULL;
- eWidth = 0;
- eHeight = 0;
-
- if(prefixLength > 0 && prefixLength < textLen){
- this->prefixLength = prefixLength;
-
- prefix = _CL_NEWARRAY(TCHAR,prefixLength+1);
- _tcsncpy(prefix,text,prefixLength);
- prefix[prefixLength]='\0';
-
- textLen = prefixLength;
- text[textLen]='\0';
- }
-
-
- //Set the enumeration
- Term* trm = _CLNEW Term(term->field(), prefix,false);
- setEnum(reader->terms(trm));
- _CLDECDELETE(trm);
+ CND_PRECONDITION(term != NULL,"term is NULL");
+
+ scale_factor = 1.0f / (1.0f - minimumSimilarity);
+ searchTerm = _CL_POINTER(term);
+
+ text = STRDUP_TtoT(term->text());
+ textLen = term->textLength();
+
+
+ //Initialize e to NULL
+ e = NULL;
+ eWidth = 0;
+ eHeight = 0;
+
+ if(prefixLength > 0 && prefixLength < textLen){
+ this->prefixLength = prefixLength;
+
+ prefix = _CL_NEWARRAY(TCHAR,prefixLength+1);
+ _tcsncpy(prefix,text,prefixLength);
+ prefix[prefixLength]='\0';
+
+ textLen = prefixLength;
+ text[textLen]='\0';
+ }
+
+
+ //Set the enumeration
+ Term* trm = _CLNEW Term(term->field(), prefix,false);
+ setEnum(reader->terms(trm));
+ _CLDECDELETE(trm);
}
FuzzyTermEnum::~FuzzyTermEnum(){
@@ -132,7 +123,7 @@
(prefixLength==0 || _tcsncmp(termText,prefix,prefixLength)==0 )) {
const TCHAR* target = termText+prefixLength;
- int32_t targetLen = termTextLen-prefixLength;
+ size_t targetLen = termTextLen-prefixLength;
//Calculate the Levenshtein distance
int32_t dist = editDistance(text, target, textLen, targetLen);
@@ -210,10 +201,10 @@
s_i = s[i - 1];
for (j = 1; j <= m; j++) {
if (s_i != t[j-1]){
- min3(e[i-1 + (j*eWidth)], e[i + ((j-1)*eWidth)], e[i-1 + ((j-1)*eWidth)]);
+ min3(e[i + (j*eWidth) - 1], e[i + ((j-1)*eWidth)], e[i + ((j-1)*eWidth)-1]);
e[i + (j*eWidth)] = __t+1;
}else{
- min3(e[i-1 + (j*eWidth)]+1, e[i + ((j-1)*eWidth)]+1, e[i-1 + ((j-1)*eWidth)]);
+ min3(e[i + (j*eWidth) -1]+1, e[i + ((j-1)*eWidth)]+1, e[i + ((j-1)*eWidth)-1]);
e[i + (j*eWidth)] = __t;
}
}
@@ -240,7 +231,7 @@
* @throws IllegalArgumentException if minimumSimilarity is > 1 or < 0
* or if prefixLength < 0 or > <code>term.text().length()</code>.
*/
- FuzzyQuery::FuzzyQuery(Term* term, float_t minimumSimilarity, int32_t prefixLength):
+ FuzzyQuery::FuzzyQuery(Term* term, float_t minimumSimilarity, size_t prefixLength):
MultiTermQuery(term)
{
//Func - Constructor
@@ -256,9 +247,7 @@
this->minimumSimilarity = minimumSimilarity;
- if(prefixLength < 0)
- _CLTHROWA(CL_ERR_IllegalArgument,"prefixLength < 0");
- else if(prefixLength >= term->textLength())
+ if(prefixLength >= term->textLength())
_CLTHROWA(CL_ERR_IllegalArgument,"prefixLength >= term.textLength()");
this->prefixLength = prefixLength;
@@ -322,9 +311,10 @@
this->minimumSimilarity = clone.getMinSimilarity();
this->prefixLength = clone.getPrefixLength();
- if(prefixLength < 0)
- _CLTHROWA(CL_ERR_IllegalArgument,"prefixLength < 0");
- else if(prefixLength >= clone.getTerm()->textLength())
+ //if(prefixLength < 0)
+ // _CLTHROWA(CL_ERR_IllegalArgument,"prefixLength < 0");
+ //else
+ if(prefixLength >= clone.getTerm()->textLength())
_CLTHROWA(CL_ERR_IllegalArgument,"prefixLength >= term.textLength()");
}
@@ -356,7 +346,7 @@
* of a term that must be identical (not fuzzy) to the query term if the query
* is to match that term.
*/
- int32_t FuzzyQuery::getPrefixLength() const {
+ size_t FuzzyQuery::getPrefixLength() const {
return prefixLength;
}
Modified: trunk/clucene/src/CLucene/search/FuzzyQuery.h
===================================================================
--- trunk/clucene/src/CLucene/search/FuzzyQuery.h 2006-06-11 07:16:00 UTC (rev 427)
+++ trunk/clucene/src/CLucene/search/FuzzyQuery.h 2006-06-26 00:39:24 UTC (rev 428)
@@ -1,18 +1,9 @@
-/**
- * Copyright 2003-2006 The Apache Software Foundation
- *
- * Licensed under the Apache License, Version 2.0 (the "License");
- * you may not use this file except in compliance with the License.
- * You may obtain a copy of the License at
- *
- * http://www.apache.org/licenses/LICENSE-2.0
- *
- * Unless required by applicable law or agreed to in writing, software
- * distributed under the License is distributed on an "AS IS" BASIS,
- * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
- * See the License for the specific language governing permissions and
- * limitations under the License.
- */
+/*------------------------------------------------------------------------------
+* Copyright (C) 2003-2006 Ben van Klinken and the CLucene Team
+*
+* Distributable under the terms of either the Apache License (Version 2.0) or
+* the GNU Lesser General Public License, as specified in the COPYING file.
+------------------------------------------------------------------------------*/
#ifndef _lucene_search_FuzzyQuery_
#define _lucene_search_FuzzyQuery_
@@ -33,7 +24,7 @@
class FuzzyQuery: public MultiTermQuery {
private:
float_t minimumSimilarity;
- int32_t prefixLength;
+ size_t prefixLength;
protected:
FuzzyQuery(const FuzzyQuery& clone);
public:
@@ -55,11 +46,10 @@
* @throws IllegalArgumentException if minimumSimilarity is > 1 or < 0
* or if prefixLength < 0 or > <code>term.text().length()</code>.
*/
- FuzzyQuery(CL_NS(index)::Term* term, float_t minimumSimilarity=defaultMinSimilarity, int32_t prefixLength=0);
+ FuzzyQuery(CL_NS(index)::Term* term, float_t minimumSimilarity=defaultMinSimilarity, size_t prefixLength=0);
//Destructor
~FuzzyQuery();
- //Prepares a fuzzy query
TCHAR* toString(const TCHAR* field) const;
//Returns the name "FuzzyQuery"
@@ -81,7 +71,7 @@
* of a term that must be identical (not fuzzy) to the query term if the query
* is to match that term.
*/
- int32_t getPrefixLength() const;
+ size_t getPrefixLength() const;
protected:
FilteredTermEnum* getEnum(CL_NS(index)::IndexReader* reader);
@@ -100,9 +90,9 @@
CL_NS(index)::Term* searchTerm;
TCHAR* text;
- int32_t textLen;
+ size_t textLen;
TCHAR* prefix;
- int32_t prefixLength;
+ size_t prefixLength;
float_t minimumSimilarity;
double scale_factor;
@@ -131,34 +121,35 @@
int32_t editDistance(const TCHAR* s, const TCHAR* t, const int32_t n, const int32_t m) ;
protected:
- /**
+ /**
The termCompare method in FuzzyTermEnum uses Levenshtein distance to
calculate the distance between the given term and the comparing term.
*/
- bool termCompare(CL_NS(index)::Term* term) ;
-
- /** Returns the difference between the distance and the fuzzy threshold
- * multiplied by the scale factor
- */
- float_t difference();
-
+ bool termCompare(CL_NS(index)::Term* term) ;
+
+ ///Returns the fact if the current term in the enumeration has reached the end
+ bool endEnum();
public:
-
- /**
- * Empty prefix and minSimilarity of 0.5f are used.
- *
- * @param reader
- * @param term
- * @throws IOException
- * @see #FuzzyTermEnum(IndexReader, Term, float_t, int32_t)
- */
- FuzzyTermEnum(CL_NS(index)::IndexReader* reader, CL_NS(index)::Term* term, float_t minSimilarity=FuzzyQuery::defaultMinSimilarity, int32_t prefixLength=0);
- /** Destructor */
- ~FuzzyTermEnum();
- //Returns the fact if the current term in the enumeration has reached the end
- bool endEnum();
- /** Close the enumeration */
- void close();
+
+ /**
+ * Empty prefix and minSimilarity of 0.5f are used.
+ *
+ * @param reader
+ * @param term
+ * @throws IOException
+ * @see #FuzzyTermEnum(IndexReader, Term, float_t, int32_t)
+ */
+ FuzzyTermEnum(const CL_NS(index)::IndexReader* reader, CL_NS(index)::Term* term, float_t minSimilarity=FuzzyQuery::defaultMinSimilarity, size_t prefixLength=0);
+ /** Destructor */
+ ~FuzzyTermEnum();
+ /** Close the enumeration */
+ void close();
+
+ /** Returns the difference between the distance and the fuzzy threshold
+ * multiplied by the scale factor
+ */
+ float_t difference();
+
};
CL_NS_END
#endif
Modified: trunk/clucene/src/CLucene/search/HitQueue.cpp
===================================================================
--- trunk/clucene/src/CLucene/search/HitQueue.cpp 2006-06-11 07:16:00 UTC (rev 427)
+++ trunk/clucene/src/CLucene/search/HitQueue.cpp 2006-06-26 00:39:24 UTC (rev 428)
@@ -1,18 +1,9 @@
-/**
- * Copyright 2003-2006 The Apache Software Foundation
- *
- * Licensed under the Apache License, Version 2.0 (the "License");
- * you may not use this file except in compliance with the License.
- * You may obtain a copy of the License at
- *
- * http://www.apache.org/licenses/LICENSE-2.0
- *
- * Unless required by applicable law or agreed to in writing, software
- * distributed under the License is distributed on an "AS IS" BASIS,
- * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
- * See the License for the specific language governing permissions and
- * limitations under the License.
- */
+/*------------------------------------------------------------------------------
+* Copyright (C) 2003-2006 Ben van Klinken and the CLucene Team
+*
+* Distributable under the terms of either the Apache License (Version 2.0) or
+* the GNU Lesser General Public License, as specified in the COPYING file.
+------------------------------------------------------------------------------*/
#include "CLucene/StdHeader.h"
#include "HitQueue.h"
Modified: trunk/clucene/src/CLucene/search/HitQueue.h
===================================================================
--- trunk/clucene/src/CLucene/search/HitQueue.h 2006-06-11 07:16:00 UTC (rev 427)
+++ trunk/clucene/src/CLucene/search/HitQueue.h 2006-06-26 00:39:24 UTC (rev 428)
@@ -1,18 +1,9 @@
-/**
- * Copyright 2003-2006 The Apache Software Foundation
- *
- * Licensed under the Apache License, Version 2.0 (the "License");
- * you may not use this file except in compliance with the License.
- * You may obtain a copy of the License at
- *
- * http://www.apache.org/licenses/LICENSE-2.0
- *
- * Unless required by applicable law or agreed to in writing, software
- * distributed under the License is distributed on an "AS IS" BASIS,
- * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
- * See the License for the specific language governing permissions and
- * limitations under the License.
- */
+/*------------------------------------------------------------------------------
+* Copyright (C) 2003-2006 Ben van Klinken and the CLucene Team
+*
+* Distributable under the terms of either the Apache License (Version 2.0) or
+* the GNU Lesser General Public License, as specified in the COPYING file.
+------------------------------------------------------------------------------*/
#ifndef _lucene_search_HitQueue_
#define _lucene_search_HitQueue_
Modified: trunk/clucene/src/CLucene/search/Hits.cpp
===================================================================
--- trunk/clucene/src/CLucene/search/Hits.cpp 2006-06-11 07:16:00 UTC (rev 427)
+++ trunk/clucene/src/CLucene/search/Hits.cpp 2006-06-26 00:39:24 UTC (rev 428)
@@ -1,18 +1,9 @@
-/**
- * Copyright 2003-2006 The Apache Software Foundation
- *
- * Licensed under the Apache License, Version 2.0 (the "License");
- * you may not use this file except in compliance with the License.
- * You may obtain a copy of the License at
- *
- * http://www.apache.org/licenses/LICENSE-2.0
- *
- * Unless required by applicable law or agreed to in writing, software
- * distributed under the License is distributed on an "AS IS" BASIS,
- * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
- * See the License for the specific language governing permissions and
- * limitations under the License.
- */
+/*------------------------------------------------------------------------------
+* Copyright (C) 2003-2006 Ben van Klinken and the CLucene Team
+*
+* Distributable under the terms of either the Apache License (Version 2.0) or
+* the GNU Lesser General Public License, as specified in the COPYING file.
+------------------------------------------------------------------------------*/
#include "CLucene/StdHeader.h"
#include "SearchHeader.h"
@@ -76,12 +67,6 @@
return _length;
}
- /** Returns the stored fields of the n<sup>th</sup> document in this set.
- <p>Documents are cached, so that repeated requests for the same element may
- return the same Document object.
- *
- * @memory Memory belongs to the hits object. Don't delete the return value.
- */
Document& Hits::doc(const int32_t n){
HitDoc* hitDoc = getHitDoc(n);
@@ -102,7 +87,6 @@
return *hitDoc->doc;
}
- /** Returns the id for the nth document in this set. */
int32_t Hits::id (const int32_t n){
return getHitDoc(n)->id;
}
@@ -173,7 +157,7 @@
numDocs++;
}
- void Hits::remove(HitDoc* hitDoc) { // remove from cache
+ void Hits::remove(const HitDoc* hitDoc) { // remove from cache
if (hitDoc->doc == NULL) // it's not in the list
return; // abort
Modified: trunk/clucene/src/CLucene/search/IndexSearcher.cpp
===================================================================
--- trunk/clucene/src/CLucene/search/IndexSearcher.cpp 2006-06-11 07:16:00 UTC (rev 427)
+++ trunk/clucene/src/CLucene/search/IndexSearcher.cpp 2006-06-26 00:39:24 UTC (rev 428)
@@ -1,18 +1,9 @@
-/**
- * Copyright 2003-2006 The Apache Software Foundation
- *
- * Licensed under the Apache License, Version 2.0 (the "License");
- * you may not use this file except in compliance with the License.
- * You may obtain a copy of the License at
- *
- * http://www.apache.org/licenses/LICENSE-2.0
- *
- * Unless required by applicable law or agreed to in writing, software
- * distributed under the License is distributed on an "AS IS" BASIS,
- * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
- * See the License for the specific language governing permissions and
- * limitations under the License.
- */
+/*------------------------------------------------------------------------------
+* Copyright (C) 2003-2006 Ben van Klinken and the CLucene Team
+*
+* Distributable under the terms of either the Apache License (Version 2.0) or
+* the GNU Lesser General Public License, as specified in the COPYING file.
+------------------------------------------------------------------------------*/
#include "CLucene/StdHeader.h"
#include "IndexSearcher.h"
@@ -34,12 +25,12 @@
CL_NS_DEF(search)
- SimpleTopDocsCollector::SimpleTopDocsCollector(const CL_NS(util)::BitSet* bs, HitQueue* hitQueue, int32_t* totalhits,const int32_t ndocs, const float_t minScore):
+ SimpleTopDocsCollector::SimpleTopDocsCollector(const CL_NS(util)::BitSet* bs, HitQueue* hitQueue, int32_t* totalhits, size_t ndocs, const float_t ms):
+ minScore(ms),
bits(bs),
hq(hitQueue),
nDocs(ndocs),
- totalHits(totalhits),
- ms(minScore)
+ totalHits(totalhits)
{
}
SimpleTopDocsCollector::~SimpleTopDocsCollector(){
@@ -48,20 +39,20 @@
if (score > 0.0f && // ignore zeroed buckets
(bits==NULL || bits->get(doc))) { // skip docs not in bits
totalHits[0]++;
- if (hq->size() < nDocs || (ms==-1.0f || score >= ms)) {
+ if (hq->size() < nDocs || (minScore==-1.0f || score >= minScore)) {
//todo: could use a struct for scoredoc and then
//set the value, then call reorder...?
ScoreDoc* sd = _CLNEW ScoreDoc(doc, score);
if ( !hq->insert(sd) ) // update hit queue
_CLDELETE(sd);
- if ( ms != -1.0f )
- minScore = ((ScoreDoc*)hq->top())->score; // maintain minScore
+ if ( minScore != -1.0f )
+ minScore = hq->top()->score; // maintain minScore
}
}
}
- SortedTopDocsCollector::SortedTopDocsCollector(const CL_NS(util)::BitSet* bs, FieldSortedHitQueue* hitQueue, int32_t* totalhits,const int32_t ndocs):
+ SortedTopDocsCollector::SortedTopDocsCollector(const CL_NS(util)::BitSet* bs, FieldSortedHitQueue* hitQueue, int32_t* totalhits,const size_t ndocs):
bits(bs),
hq(hitQueue),
nDocs(ndocs),
@@ -233,14 +224,14 @@
}
// inherit javadoc
- TopFieldDocs* IndexSearcher::_search(Query* query, Filter* filter, int32_t nDocs,
+ TopFieldDocs* IndexSearcher::_search(Query* query, Filter* filter, const int32_t nDocs,
const Sort* sort) {
Weight* weight = query->weight(this);
Scorer* scorer = weight->scorer(reader);
if (scorer == NULL){
ScoreDoc** sds = _CL_NEWARRAY(ScoreDoc*,1);
sds[0]=NULL;
- return _CLNEW TopFieldDocs(0, sds, 0, sort->getSort());
+ return _CLNEW TopFieldDocs(0, sds, 0, __CONST_CAST(const SortField**,sort->getSort()) );
}
BitSet* bits = filter != NULL ? filter->bits(reader) : NULL;
@@ -270,7 +261,7 @@
if ( bits != NULL && filter->shouldDeleteBitSet(bits) )
_CLDELETE(bits);
_CLDELETE_ARRAY(totalHits);
- return _CLNEW TopFieldDocs(totalHits0, scoreDocs, hqLen, hqFields);
+ return _CLNEW TopFieldDocs(totalHits0, scoreDocs, hqLen, __CONST_CAST(const SortField**,hqFields) );
}
void IndexSearcher::_search(Query* query, Filter* filter, HitCollector* results){
Modified: trunk/clucene/src/CLucene/search/IndexSearcher.h
===================================================================
--- trunk/clucene/src/CLucene/search/IndexSearcher.h 2006-06-11 07:16:00 UTC (rev 427)
+++ trunk/clucene/src/CLucene/search/IndexSearcher.h 2006-06-26 00:39:24 UTC (rev 428)
@@ -1,18 +1,9 @@
-/**
- * Copyright 2003-2006 The Apache Software Foundation
- *
- * Licensed under the Apache License, Version 2.0 (the "License");
- * you may not use this file except in compliance with the License.
- * You may obtain a copy of the License at
- *
- * http://www.apache.org/licenses/LICENSE-2.0
- *
- * Unless required by applicable law or agreed to in writing, software
- * distributed under the License is distributed on an "AS IS" BASIS,
- * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
- * See the License for the specific language governing permissions and
- * limitations under the License.
- */
+/*------------------------------------------------------------------------------
+* Copyright (C) 2003-2006 Ben van Klinken and the CLucene Team
+*
+* Distributable under the terms of either the Apache License (Version 2.0) or
+* the GNU Lesser General Public License, as specified in the COPYING file.
+------------------------------------------------------------------------------*/
#ifndef _lucene_search_IndexSearcher_
#define _lucene_search_IndexSearcher_
@@ -37,11 +28,10 @@
float_t minScore;
const CL_NS(util)::BitSet* bits;
HitQueue* hq;
- const int32_t nDocs;
+ size_t nDocs;
int32_t* totalHits;
- const float_t ms;
public:
- SimpleTopDocsCollector(const CL_NS(util)::BitSet* bs, HitQueue* hitQueue, int32_t* totalhits,const int32_t ndocs, const float_t minScore=-1.0f);
+ SimpleTopDocsCollector(const CL_NS(util)::BitSet* bs, HitQueue* hitQueue, int32_t* totalhits, size_t ndocs, const float_t minScore=-1.0f);
~SimpleTopDocsCollector();
void collect(const int32_t doc, const float_t score);
};
@@ -50,10 +40,10 @@
private:
const CL_NS(util)::BitSet* bits;
FieldSortedHitQueue* hq;
- const int32_t nDocs;
+ size_t nDocs;
int32_t* totalHits;
public:
- SortedTopDocsCollector(const CL_NS(util)::BitSet* bs, FieldSortedHitQueue* hitQueue, int32_t* totalhits,const int32_t ndocs);
+ SortedTopDocsCollector(const CL_NS(util)::BitSet* bs, FieldSortedHitQueue* hitQueue, int32_t* totalhits, size_t ndocs);
~SortedTopDocsCollector();
void collect(const int32_t doc, const float_t score);
};
Modified: trunk/clucene/src/CLucene/search/MultiSearcher.cpp
===================================================================
--- trunk/clucene/src/CLucene/search/MultiSearcher.cpp 2006-06-11 07:16:00 UTC (rev 427)
+++ trunk/clucene/src/CLucene/search/MultiSearcher.cpp 2006-06-26 00:39:24 UTC (rev 428)
@@ -1,18 +1,9 @@
-/**
- * Copyright 2003-2006 The Apache Software Foundation
- *
- * Licensed under the Apache License, Version 2.0 (the "License");
- * you may not use this file except in compliance with the License.
- * You may obtain a copy of the License at
- *
- * http://www.apache.org/licenses/LICENSE-2.0
- *
- * Unless required by applicable law or agreed to in writing, software
- * distributed under the License is distributed on an "AS IS" BASIS,
- * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
- * See the License for the specific language governing permissions and
- * limitations under the License.
- */
+/*------------------------------------------------------------------------------
+* Copyright (C) 2003-2006 Ben van Klinken and the CLucene Team
+*
+* Distributable under the terms of either the Apache License (Version 2.0) or
+* the GNU Lesser General Public License, as specified in the COPYING file.
+------------------------------------------------------------------------------*/
#include "CLucene/StdHeader.h"
#include "MultiSearcher.h"
@@ -74,13 +65,13 @@
return searchables[i]->doc(n - starts[i]); // dispatch to searcher
}
- int32_t MultiSearcher::searcherIndex(int32_t n){
+ int32_t MultiSearcher::searcherIndex(int32_t n) const{
return subSearcher(n);
}
/** Returns index of the searcher for document <code>n</code> in the array
* used to construct this searcher. */
- int32_t MultiSearcher::subSearcher(int32_t n) {
+ int32_t MultiSearcher::subSearcher(int32_t n) const{
// replace w/ call to Arrays.binarySearch in Java 1.2
int32_t lo = 0; // search starts array
int32_t hi = searchablesLen - 1; // for first element less
@@ -104,7 +95,7 @@
/** Returns the document number of document <code>n</code> within its
* sub-index. */
- int32_t MultiSearcher::subDoc(int32_t n) {
+ int32_t MultiSearcher::subDoc(int32_t n) const{
return n - starts[subSearcher(n)];
}
@@ -217,7 +208,7 @@
scoreDocs[j] = hq->pop();
scoreDocs[hqlen]=NULL;
- SortField** hqFields = hq->getFields();
+ const SortField** hqFields = hq->getFields();
_CLDELETE(hq);
return _CLNEW TopFieldDocs (totalHits, scoreDocs, hqlen, hqFields);
}
Modified: trunk/clucene/src/CLucene/search/MultiSearcher.h
===================================================================
--- trunk/clucene/src/CLucene/search/MultiSearcher.h 2006-06-11 07:16:00 UTC (rev 427)
+++ trunk/clucene/src/CLucene/search/MultiSearcher.h 2006-06-26 00:39:24 UTC (rev 428)
@@ -1,18 +1,9 @@
-/**
- * Copyright 2003-2006 The Apache Software Foundation
- *
- * Licensed under the Apache License, Version 2.0 (the "License");
- * you may not use this file except in compliance with the License.
- * You may obtain a copy of the License at
- *
- * http://www.apache.org/licenses/LICENSE-2.0
- *
- * Unless required by applicable law or agreed to in writing, software
- * distributed under the License is distributed on an "AS IS" BASIS,
- * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
- * See the License for the specific language governing permissions and
- * limitations under the License.
- */
+/*------------------------------------------------------------------------------
+* Copyright (C) 2003-2006 Ben van Klinken and the CLucene Team
+*
+* Distributable under the terms of either the Apache License (Version 2.0) or
+* the GNU Lesser General Public License, as specified in the COPYING file.
+------------------------------------------------------------------------------*/
#ifndef _lucene_search_multisearcher
#define _lucene_search_multisearcher
@@ -70,12 +61,12 @@
/** For use by {@link HitCollector} implementations to identify the
* index of the sub-searcher that a particular hit came from. */
- int32_t searcherIndex(int32_t n);
-
- int32_t subSearcher(int32_t n);
-
- int32_t subDoc(int32_t n);
+ int32_t searcherIndex(int32_t n) const;
+ int32_t subSearcher(int32_t n) const;
+
+ int32_t subDoc(int32_t n) const;
+
int32_t maxDoc() const;
TopDocs* _search(Query* query, Filter* filter, const int32_t nDocs) ;
Modified: trunk/clucene/src/CLucene/search/MultiTermQuery.cpp
===================================================================
--- trunk/clucene/src/CLucene/search/MultiTermQuery.cpp 2006-06-11 07:16:00 UTC (rev 427)
+++ trunk/clucene/src/CLucene/search/MultiTermQuery.cpp 2006-06-26 00:39:24 UTC (rev 428)
@@ -1,18 +1,9 @@
-/**
- * Copyright 2003-2006 The Apache Software Foundation
- *
- * Licensed under the Apache License, Version 2.0 (the "License");
- * you may not use this file except in compliance with the License.
- * You may obtain a copy of the License at
- *
- * http://www.apache.org/licenses/LICENSE-2.0
- *
- * Unless required by applicable law or agreed to in writing, software
- * distributed under the License is distributed on an "AS IS" BASIS,
- * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
- * See the License for the specific language governing permissions and
- * limitations under the License.
- */
+/*------------------------------------------------------------------------------
+* Copyright (C) 2003-2006 Ben van Klinken and the CLucene Team
+*
+* Distributable under the terms of either the Apache License (Version 2.0) or
+* the GNU Lesser General Public License, as specified in the COPYING file.
+------------------------------------------------------------------------------*/
#include "CLucene/StdHeader.h"
#include "MultiTermQuery.h"
Modified: trunk/clucene/src/CLucene/search/MultiTermQuery.h
===================================================================
--- trunk/clucene/src/CLucene/search/MultiTermQuery.h 2006-06-11 07:16:00 UTC (rev 427)
+++ trunk/clucene/src/CLucene/search/MultiTermQuery.h 2006-06-26 00:39:24 UTC (rev 428)
@@ -1,18 +1,9 @@
-/**
- * Copyright 2003-2006 The Apache Software Foundation
- *
- * Licensed under the Apache License, Version 2.0 (the "License");
- * you may not use this file except in compliance with the License.
- * You may obtain a copy of the License at
- *
- * http://www.apache.org/licenses/LICENSE-2.0
- *
- * Unless required by applicable law or agreed to in writing, software
- * distributed under the License is distributed on an "AS IS" BASIS,
- * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
- * See the License for the specific language governing permissions and
- * limitations under the License.
- */
+/*------------------------------------------------------------------------------
+* Copyright (C) 2003-2006 Ben van Klinken and the CLucene Team
+*
+* Distributable under the terms of either the Apache License (Version 2.0) or
+* the GNU Lesser General Public License, as specified in the COPYING file.
+------------------------------------------------------------------------------*/
#ifndef _lucene_search_MultiTermQuery_
#define _lucene_search_MultiTermQuery_
Modified: trunk/clucene/src/CLucene/search/PhrasePositions.cpp
===================================================================
--- trunk/clucene/src/CLucene/search/PhrasePositions.cpp 2006-06-11 07:16:00 UTC (rev 427)
+++ trunk/clucene/src/CLucene/search/PhrasePositions.cpp 2006-06-26 00:39:24 UTC (rev 428)
@@ -1,18 +1,9 @@
-/**
- * Copyright 2003-2006 The Apache Software Foundation
- *
- * Licensed under the Apache License, Version 2.0 (the "License");
- * you may not use this file except in compliance with the License.
- * You may obtain a copy of the License at
- *
- * http://www.apache.org/licenses/LICENSE-2.0
- *
- * Unless required by applicable law or agreed to in writing, software
- * distributed under the License is distributed on an "AS IS" BASIS,
- * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
- * See the License for the specific language governing permissions and
- * limitations under the License.
- */
+/*------------------------------------------------------------------------------
+* Copyright (C) 2003-2006 Ben van Klinken and the CLucene Team
+*
+* Distributable under the terms of either the Apache License (Version 2.0) or
+* the GNU Lesser General Public License, as specified in the COPYING file.
+------------------------------------------------------------------------------*/
#include "CLucene/StdHeader.h"
#include "PhrasePositions.h"
Modified: trunk/clucene/src/CLucene/search/PhrasePositions.h
===================================================================
--- trunk/clucene/src/CLucene/search/PhrasePositions.h 2006-06-11 07:16:00 UTC (rev 427)
+++ trunk/clucene/src/CLucene/search/PhrasePositions.h 2006-06-26 00:39:24 UTC (rev 428)
@@ -1,18 +1,9 @@
-/**
- * Copyright 2003-2006 The Apache Software Foundation
- *
- * Licensed under the Apache License, Version 2.0 (the "License");
- * you may not use this file except in compliance with the License.
- * You may obtain a copy of the License at
- *
- * http://www.apache.org/licenses/LICENSE-2.0
- *
- * Unless required by applicable law or agreed to in writing, software
- * distributed under the License is distributed on an "AS IS" BASIS,
- * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
- * See the License for the specific language governing permissions and
- * limitations under the License.
- */
+/*------------------------------------------------------------------------------
+* Copyright (C) 2003-2006 Ben van Klinken and the CLucene Team
+*
+* Distributable under the terms of either the Apache License (Version 2.0) or
+* the GNU Lesser General Public License, as specified in the COPYING file.
+------------------------------------------------------------------------------*/
#ifndef _lucene_search_PhrasePositions_
#define _lucene_search_PhrasePositions_
Modified: trunk/clucene/src/CLucene/search/PhraseQuery.cpp
===================================================================
--- trunk/clucene/src/CLucene/search/PhraseQuery.cpp 2006-06-11 07:16:00 UTC (rev 427)
+++ trunk/clucene/src/CLucene/search/PhraseQuery.cpp 2006-06-26 00:39:24 UTC (rev 428)
@@ -1,18 +1,9 @@
-/**
- * Copyright 2003-2006 The Apache Software Foundation
- *
- * Licensed under the Apache License, Version 2.0 (the "License");
- * you may not use this file except in compliance with the License.
- * You may obtain a copy of the License at
- *
- * http://www.apache.org/licenses/LICENSE-2.0
- *
- * Unless required by applicable law or agreed to in writing, software
- * distributed under the License is distributed on an "AS IS" BASIS,
- * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
- * See the License for the specific language governing permissions and
- * limitations under the License.
- */
+/*------------------------------------------------------------------------------
+* Copyright (C) 2003-2006 Ben van Klinken and the CLucene Team
+*
+* Distributable under the terms of either the Apache License (Version 2.0) or
+* the GNU Lesser General Public License, as specified in the COPYING file.
+------------------------------------------------------------------------------*/
#include "CLucene/StdHeader.h"
#include "PhraseQuery.h"
@@ -202,8 +193,8 @@
TermPositions* p = NULL;
//Iterate through all terms
- uint32_t size = _this->terms.size();
- for (uint32_t i = 0; i < size; i++) {
+ int32_t size = _this->terms.size();
+ for (int32_t i = 0; i < size; i++) {
//Get the termPostitions for the i-th term
p = reader->termPositions(_this->terms[i]);
@@ -215,7 +206,7 @@
}
_CLDELETE_ARRAY(tps);
return NULL;
- }
+ }
//Store p at i in tps
tps[i] = p;
Modified: trunk/clucene/src/CLucene/search/PhraseQuery.h
===================================================================
--- trunk/clucene/src/CLucene/search/PhraseQuery.h 2006-06-11 07:16:00 UTC (rev 427)
+++ trunk/clucene/src/CLucene/search/PhraseQuery.h 2006-06-26 00:39:24 UTC (rev 428)
@@ -1,18 +1,9 @@
-/**
- * Copyright 2003-2006 The Apache Software Foundation
- *
- * Licensed under the Apache License, Version 2.0 (the "License");
- * you may not use this file except in compliance with the License.
- * You may obtain a copy of the License at
- *
- * http://www.apache.org/licenses/LICENSE-2.0
- *
- * Unless required by applicable law or agreed to in writing, software
- * distributed under the License is distributed on an "AS IS" BASIS,
- * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
- * See the License for the specific language governing permissions and
- * limitations under the License.
- */
+/*------------------------------------------------------------------------------
+* Copyright (C) 2003-2006 Ben van Klinken and the CLucene Team
+*
+* Distributable under the terms of either the Apache License (Version 2.0) or
+* the GNU Lesser General Public License, as specified in the COPYING file.
+------------------------------------------------------------------------------*/
#ifndef _lucene_search_PhraseQuery_
#define _lucene_search_PhraseQuery_
@@ -106,11 +97,11 @@
void setSlop(const int32_t s) { slop = s; }
//Returns the slop. See setSlop().
- int32_t getSlop() { return slop; }
+ int32_t getSlop() const { return slop; }
//Adds a term to the end of the query phrase.
void add(CL_NS(index)::Term* term);
- void add(CL_NS(index)::Term* term, int32_t position);
+ void add(CL_NS(index)::Term* term, int32_t position);
@@ -130,7 +121,6 @@
//Prints a user-readable version of this query.
TCHAR* toString(const TCHAR* f) const;
- void prepare(CL_NS(index)::IndexReader* reader){}
Query* clone() const;
bool equals(CL_NS(search)::Query *) const;
Modified: trunk/clucene/src/CLucene/search/PhraseQueue.h
===================================================================
--- trunk/clucene/src/CLucene/search/PhraseQueue.h 2006-06-11 07:16:00 UTC (rev 427)
+++ trunk/clucene/src/CLucene/search/PhraseQueue.h 2006-06-26 00:39:24 UTC (rev 428)
@@ -1,18 +1,9 @@
-/**
- * Copyright 2003-2006 The Apache Software Foundation
- *
- * Licensed under the Apache License, Version 2.0 (the "License");
- * you may not use this file except in compliance with the License.
- * You may obtain a copy of the License at
- *
- * http://www.apache.org/licenses/LICENSE-2.0
- *
- * Unless required by applicable law or agreed to in writing, software
- * distributed under the License is distributed on an "AS IS" BASIS,
- * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
- * See the License for the specific language governing permissions and
- * limitations under the License.
- */
+/*------------------------------------------------------------------------------
+* Copyright (C) 2003-2006 Ben van Klinken and the CLucene Team
+*
+* Distributable under the terms of either the Apache License (Version 2.0) or
+* the GNU Lesser General Public License, as specified in the COPYING file.
+------------------------------------------------------------------------------*/
#ifndef _lucene_search_PriorityQueue_
#define _lucene_search_PriorityQueue_
Modified: trunk/clucene/src/CLucene/search/PhraseScorer.cpp
===================================================================
--- trunk/clucene/src/CLucene/search/PhraseScorer.cpp 2006-06-11 07:16:00 UTC (rev 427)
+++ trunk/clucene/src/CLucene/search/PhraseScorer.cpp 2006-06-26 00:39:24 UTC (rev 428)
@@ -1,18 +1,9 @@
-/**
- * Copyright 2003-2006 The Apache Software Foundation
- *
- * Licensed under the Apache License, Version 2.0 (the "License");
- * you may not use this file except in compliance with the License.
- * You may obtain a copy of the License at
- *
- * http://www.apache.org/licenses/LICENSE-2.0
- *
- * Unless required by applicable law or agreed to in writing, software
- * distributed under the License is distributed on an "AS IS" BASIS,
- * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
- * See the License for the specific language governing permissions and
- * limitations under the License.
- */
+/*------------------------------------------------------------------------------
+* Copyright (C) 2003-2006 Ben van Klinken and the CLucene Team
+*
+* Distributable under the terms of either the Apache License (Version 2.0) or
+* the GNU Lesser General Public License, as specified in the COPYING file.
+------------------------------------------------------------------------------*/
#include "CLucene/StdHeader.h"
#include "PhraseScorer.h"
Modified: trunk/clucene/src/CLucene/search/PhraseScorer.h
===================================================================
--- trunk/clucene/src/CLucene/search/PhraseScorer.h 2006-06-11 07:16:00 UTC (rev 427)
+++ trunk/clucene/src/CLucene/search/PhraseScorer.h 2006-06-26 00:39:24 UTC (rev 428)
@@ -1,18 +1,9 @@
-/**
- * Copyright 2003-2006 The Apache Software Foundation
- *
- * Licensed under the Apache License, Version 2.0 (the "License");
- * you may not use this file except in compliance with the License.
- * You may obtain a copy of the License at
- *
- * http://www.apache.org/licenses/LICENSE-2.0
- *
- * Unless required by applicable law or agreed to in writing, software
- * distributed under the License is distributed on an "AS IS" BASIS,
- * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
- * See the License for the specific language governing permissions and
- * limitations under the License.
- */
+/*------------------------------------------------------------------------------
+* Copyright (C) 2003-2006 Ben van Klinken and the CLucene Team
+*
+* Distributable under the terms of either the Apache License (Version 2.0) or
+* the GNU Lesser General Public License, as specified in the COPYING file.
+------------------------------------------------------------------------------*/
#ifndef _lucene_search_PhraseScorer_
#define _lucene_search_PhraseScorer_
Modified: trunk/clucene/src/CLucene/search/PrefixQuery.cpp
===================================================================
--- trunk/clucene/src/CLucene/search/PrefixQuery.cpp 2006-06-11 07:16:00 UTC (rev 427)
+++ trunk/clucene/src/CLucene/search/PrefixQuery.cpp 2006-06-26 00:39:24 UTC (rev 428)
@@ -1,28 +1,13 @@
-/**
- * Copyright 2003-2006 The Apache Software Foundation
- *
- * Licensed under the Apache License, Version 2.0 (the "License");
- * you may not use this file except in compliance with the License.
- * You may obtain a copy of the License at
- *
- * http://www.apache.org/licenses/LICENSE-2.0
- *
- * Unless required by applicable law or agreed to in writing, software
- * distributed under the License is distributed on an "AS IS" BASIS,
- * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
- * See the License for the specific language governing permissions and
- * limitations under the License.
- */
+/*------------------------------------------------------------------------------
+* Copyright (C) 2003-2006 Ben van Klinken and the CLucene Team
+*
+* Distributable under the terms of either the Apache License (Version 2.0) or
+* the GNU Lesser General Public License, as specified in the COPYING file.
+------------------------------------------------------------------------------*/
#include "CLucene/StdHeader.h"
#ifndef NO_PREFIX_QUERY
#include "PrefixQuery.h"
-/*
-- reader set to NULL in constructor
-- delete query protected in destructor
-- delete query in prepare
-
-*/
CL_NS_USE(index)
CL_NS_DEF(search)
Modified: trunk/clucene/src/CLucene/search/PrefixQuery.h
===================================================================
--- trunk/clucene/src/CLucene/search/PrefixQuery.h 2006-06-11 07:16:00 UTC (rev 427)
+++ trunk/clucene/src/CLucene/search/PrefixQuery.h 2006-06-26 00:39:24 UTC (rev 428)
@@ -1,18 +1,9 @@
-/**
- * Copyright 2003-2006 The Apache Software Foundation
- *
- * Licensed under the Apache License, Version 2.0 (the "License");
- * you may not use this file except in compliance with the License.
- * You may obtain a copy of the License at
- *
- * http://www.apache.org/licenses/LICENSE-2.0
- *
- * Unless required by applicable law or agreed to in writing, software
- * distributed under the License is distributed on an "AS IS" BASIS,
- * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
- * See the License for the specific language governing permissions and
- * limitations under the License.
- */
+/*------------------------------------------------------------------------------
+* Copyright (C) 2003-2006 Ben van Klinken and the CLucene Team
+*
+* Distributable under the terms of either the Apache License (Version 2.0) or
+* the GNU Lesser General Public License, as specified in the COPYING file.
+------------------------------------------------------------------------------*/
#ifndef _lucene_search_PrefixQuery
#define _lucene_search_PrefixQuery
#if defined(_LUCENE_PRAGMA_ONCE)
Modified: trunk/clucene/src/CLucene/search/QueryFilter.cpp
===================================================================
--- trunk/clucene/src/CLucene/search/QueryFilter.cpp 2006-06-11 07:16:00 UTC (rev 427)
+++ trunk/clucene/src/CLucene/search/QueryFilter.cpp 2006-06-26 00:39:24 UTC (rev 428)
@@ -1,18 +1,9 @@
-/**
- * Copyright 2003-2006 The Apache Software Foundation
- *
- * Licensed under the Apache License, Version 2.0 (the "License");
- * you may not use this file except in compliance with the License.
- * You may obtain a copy of the License at
- *
- * http://www.apache.org/licenses/LICENSE-2.0
- *
- * Unless required by applicable law or agreed to in writing, software
- * distributed under the License is distributed on an "AS IS" BASIS,
- * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
- * See the License for the specific language governing permissions and
- * limitations under the License.
- */
+/*------------------------------------------------------------------------------
+* Copyright (C) 2003-2006 Ben van Klinken and the CLucene Team
+*
+* Distributable under the terms of either the Apache License (Version 2.0) or
+* the GNU Lesser General Public License, as specified in the COPYING file.
+------------------------------------------------------------------------------*/
#include "CLucene/StdHeader.h"
#include "QueryFilter.h"
#include "IndexSearcher.h"
@@ -22,7 +13,7 @@
CL_NS_USE(index)
-QueryFilter::QueryFilter( Query* query )
+QueryFilter::QueryFilter( const Query* query )
{
this->query = query->clone();
}
Modified: trunk/clucene/src/CLucene/search/QueryFilter.h
===================================================================
--- trunk/clucene/src/CLucene/search/QueryFilter.h 2006-06-11 07:16:00 UTC (rev 427)
+++ trunk/clucene/src/CLucene/search/QueryFilter.h 2006-06-26 00:39:24 UTC (rev 428)
@@ -1,18 +1,9 @@
-/**
- * Copyright 2003-2006 The Apache Software Foundation
- *
- * Licensed under the Apache License, Version 2.0 (the "License");
- * you may not use this file except in compliance with the License.
- * You may obtain a copy of the License at
- *
- * http://www.apache.org/licenses/LICENSE-2.0
- *
- * Unless required by applicable law or agreed to in writing, software
- * distributed under the License is distributed on an "AS IS" BASIS,
- * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
- * See the License for the specific language governing permissions and
- * limitations under the License.
- */
+/*------------------------------------------------------------------------------
+* Copyright (C) 2003-2006 Ben van Klinken and the CLucene Team
+*
+* Distributable under the terms of either the Apache License (Version 2.0) or
+* the GNU Lesser General Public License, as specified in the COPYING file.
+------------------------------------------------------------------------------*/
#ifndef _lucene_search_QueryFilter_
#define _lucene_search_QueryFilter_
@@ -27,7 +18,6 @@
{
private:
Query* query;
- QueryFilter( const QueryFilter& copy );
class QFHitCollector: public HitCollector{
CL_NS(util)::BitSet* bits;
@@ -35,8 +25,11 @@
QFHitCollector(CL_NS(util)::BitSet* bits);
void collect(const int32_t doc, const float_t score);
};
+
+protected:
+ QueryFilter( const QueryFilter& copy );
public:
- QueryFilter( Query* query );
+ QueryFilter( const Query* query );
~QueryFilter();
Modified: trunk/clucene/src/CLucene/search/RangeFilter.cpp
===================================================================
--- trunk/clucene/src/CLucene/search/RangeFilter.cpp 2006-06-11 07:16:00 UTC (rev 427)
+++ trunk/clucene/src/CLucene/search/RangeFilter.cpp 2006-06-26 00:39:24 UTC (rev 428)
@@ -1,18 +1,9 @@
-/**
- * Copyright 2003-2006 The Apache Software Foundation
- *
- * Licensed under the Apache License, Version 2.0 (the "License");
- * you may not use this file except in compliance with the License.
- * You may obtain a copy of the License at
- *
- * http://www.apache.org/licenses/LICENSE-2.0
- *
- * Unless required by applicable law or agreed to in writing, software
- * distributed under the License is distributed on an "AS IS" BASIS,
- * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
- * See the License for the specific language governing permissions and
- * limitations under the License.
- */
+/*------------------------------------------------------------------------------
+* Copyright (C) 2003-2006 Ben van Klinken and the CLucene Team
+*
+* Distributable under the terms of either the Apache License (Version 2.0) or
+* the GNU Lesser General Public License, as specified in the COPYING file.
+------------------------------------------------------------------------------*/
#include "CLucene/StdHeader.h"
#include "RangeFilter.h"
Modified: trunk/clucene/src/CLucene/search/RangeFilter.h
===================================================================
--- trunk/clucene/src/CLucene/search/RangeFilter.h 2006-06-11 07:16:00 UTC (rev 427)
+++ trunk/clucene/src/CLucene/search/RangeFilter.h 2006-06-26 00:39:24 UTC (rev 428)
@@ -1,18 +1,9 @@
-/**
- * Copyright 2003-2006 The Apache Software Foundation
- *
- * Licensed under the Apache License, Version 2.0 (the "License");
- * you may not use this file except in compliance with the License.
- * You may obtain a copy of the License at
- *
- * http://www.apache.org/licenses/LICENSE-2.0
- *
- * Unless required by applicable law or agreed to in writing, software
- * distributed under the License is distributed on an "AS IS" BASIS,
- * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
- * See the License for the specific language governing permissions and
- * limitations under the License.
- */
+/*------------------------------------------------------------------------------
+* Copyright (C) 2003-2006 Ben van Klinken and the CLucene Team
+*
+* Distributable under the terms of either the Apache License (Version 2.0) or
+* the GNU Lesser General Public License, as specified in the COPYING file.
+------------------------------------------------------------------------------*/
#ifndef _lucene_search_RangeFilter_
#define _lucene_search_RangeFilter_
@@ -35,14 +26,15 @@
bool includeLower;
bool includeUpper;
+protected:
RangeFilter( const RangeFilter& copy );
public:
RangeFilter( const TCHAR* fieldName, const TCHAR* lowerTerm, const TCHAR* upperTerm, bool includeLower, bool includeUpper );
- static RangeFilter* RangeFilter::Less( TCHAR* fieldName, TCHAR* upperTerm );
+ static RangeFilter* Less( TCHAR* fieldName, TCHAR* upperTerm );
- static RangeFilter* RangeFilter::More( TCHAR* fieldName, TCHAR* lowerTerm );
+ static RangeFilter* More( TCHAR* fieldName, TCHAR* lowerTerm );
~RangeFilter();
Modified: trunk/clucene/src/CLucene/search/RangeQuery.cpp
===================================================================
--- trunk/clucene/src/CLucene/search/RangeQuery.cpp 2006-06-11 07:16:00 UTC (rev 427)
+++ trunk/clucene/src/CLucene/search/RangeQuery.cpp 2006-06-26 00:39:24 UTC (rev 428)
@@ -1,18 +1,9 @@
-/**
- * Copyright 2003-2006 The Apache Software Foundation
- *
- * Licensed under the Apache License, Version 2.0 (the "License");
- * you may not use this file except in compliance with the License.
- * You may obtain a copy of the License at
- *
- * http://www.apache.org/licenses/LICENSE-2.0
- *
- * Unless required by applicable law or agreed to in writing, software
- * distributed under the License is distributed on an "AS IS" BASIS,
- * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
- * See the License for the specific language governing permissions and
- * limitations under the License.
- */
+/*------------------------------------------------------------------------------
+* Copyright (C) 2003-2006 Ben van Klinken and the CLucene Team
+*
+* Distributable under the terms of either the Apache License (Version 2.0) or
+* the GNU Lesser General Public License, as specified in the COPYING file.
+------------------------------------------------------------------------------*/
#include "CLucene/StdHeader.h"
#ifndef NO_RANGE_QUERY
#include "RangeQuery.h"
Modified: trunk/clucene/src/CLucene/search/RangeQuery.h
===================================================================
--- trunk/clucene/src/CLucene/search/RangeQuery.h 2006-06-11 07:16:00 UTC (rev 427)
+++ trunk/clucene/src/CLucene/search/RangeQuery.h 2006-06-26 00:39:24 UTC (rev 428)
@@ -1,18 +1,9 @@
-/**
- * Copyright 2003-2006 The Apache Software Foundation
- *
- * Licensed under the Apache License, Version 2.0 (the "License");
- * you may not use this file except in compliance with the License.
- * You may obtain a copy of the License at
- *
- * http://www.apache.org/licenses/LICENSE-2.0
- *
- * Unless required by applicable law or agreed to in writing, software
- * distributed under the License is distributed on an "AS IS" BASIS,
- * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
- * See the License for the specific language governing permissions and
- * limitations under the License.
- */
+/*------------------------------------------------------------------------------
+* Copyright (C) 2003-2006 Ben van Klinken and the CLucene Team
+*
+* Distributable under the terms of either the Apache License (Version 2.0) or
+* the GNU Lesser General Public License, as specified in the COPYING file.
+------------------------------------------------------------------------------*/
#ifndef _lucene_search_RangeQuery_
#define _lucene_search_RangeQuery_
#if defined(_LUCENE_PRAGMA_ONCE)
Modified: trunk/clucene/src/CLucene/search/ScoreDoc.h
===================================================================
--- trunk/clucene/src/CLucene/search/ScoreDoc.h 2006-06-11 07:16:00 UTC (rev 427)
+++ trunk/clucene/src/CLucene/search/ScoreDoc.h 2006-06-26 00:39:24 UTC (rev 428)
@@ -1,18 +1,9 @@
-/**
- * Copyright 2003-2006 The Apache Software Foundation
- *
- * Licensed under the Apache License, Version 2.0 (the "License");
- * you may not use this file except in compliance with the License.
- * You may obtain a copy of the License at
- *
- * http://www.apache.org/licenses/LICENSE-2.0
- *
- * Unless required by applicable law or agreed to in writing, software
- * distributed under the License is distributed on an "AS IS" BASIS,
- * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
- * See the License for the specific language governing permissions and
- * limitations under the License.
- */
+/*------------------------------------------------------------------------------
+* Copyright (C) 2003-2006 Ben van Klinken and the CLucene Team
+*
+* Distributable under the terms of either the Apache License (Version 2.0) or
+* the GNU Lesser General Public License, as specified in the COPYING file.
+------------------------------------------------------------------------------*/
#ifndef _lucene_search_ScoreDoc_
#define _lucene_search_ScoreDoc_
Modified: trunk/clucene/src/CLucene/search/Scorer.h
===================================================================
--- trunk/clucene/src/CLucene/search/Scorer.h 2006-06-11 07:16:00 UTC (rev 427)
+++ trunk/clucene/src/CLucene/search/Scorer.h 2006-06-26 00:39:24 UTC (rev 428)
@@ -1,18 +1,9 @@
-/**
- * Copyright 2003-2006 The Apache Software Foundation
- *
- * Licensed under the Apache License, Version 2.0 (the "License");
- * you may not use this file except in compliance with the License.
- * You may obtain a copy of the License at
- *
- * http://www.apache.org/licenses/LICENSE-2.0
- *
- * Unless required by applicable law or agreed to in writing, software
- * distributed under the License is distributed on an "AS IS" BASIS,
- * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
- * See the License for the specific language governing permissions and
- * limitations under the License.
- */
+/*------------------------------------------------------------------------------
+* Copyright (C) 2003-2006 Ben van Klinken and the CLucene Team
+*
+* Distributable under the terms of either the Apache License (Version 2.0) or
+* the GNU Lesser General Public License, as specified in the COPYING file.
+------------------------------------------------------------------------------*/
#ifndef _lucene_search_Scorer_
#define _lucene_search_Scorer_
Modified: trunk/clucene/src/CLucene/search/SearchHeader.cpp
===================================================================
--- trunk/clucene/src/CLucene/search/SearchHeader.cpp 2006-06-11 07:16:00 UTC (rev 427)
+++ trunk/clucene/src/CLucene/search/SearchHeader.cpp 2006-06-26 00:39:24 UTC (rev 428)
@@ -1,18 +1,9 @@
-/**
- * Copyright 2003-2006 The Apache Software Foundation
- *
- * Licensed under the Apache License, Version 2.0 (the "License");
- * you may not use this file except in compliance with the License.
- * You may obtain a copy of the License at
- *
- * http://www.apache.org/licenses/LICENSE-2.0
- *
- * Unless required by applicable law or agreed to in writing, software
- * distributed under the License is distributed on an "AS IS" BASIS,
- * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
- * See the License for the specific language governing permissions and
- * limitations under the License.
- */
+/*------------------------------------------------------------------------------
+* Copyright (C) 2003-2006 Ben van Klinken and the CLucene Team
+*
+* Distributable under the terms of either the Apache License (Version 2.0) or
+* the GNU Lesser General Public License, as specified in the COPYING file.
+------------------------------------------------------------------------------*/
#include "CLucene/StdHeader.h"
#include "SearchHeader.h"
#include "BooleanQuery.h"
@@ -50,7 +41,6 @@
}
Weight* Query::createWeight(Searcher* searcher){
_CLTHROWA(CL_ERR_UnsupportedOperation,"UnsupportedOperationException");
- return NULL;
}
Query::Query():
@@ -68,7 +58,6 @@
Query* Query::combine(Query** queries){
_CLTHROWA(CL_ERR_UnsupportedOperation,"UnsupportedOperationException");
- return NULL;
}
Similarity* Query::getSimilarity(Searcher* searcher) {
return searcher->getSimilarity();
Modified: trunk/clucene/src/CLucene/search/SearchHeader.h
===================================================================
--- trunk/clucene/src/CLucene/search/SearchHeader.h 2006-06-11 07:16:00 UTC (rev 427)
+++ trunk/clucene/src/CLucene/search/SearchHeader.h 2006-06-26 00:39:24 UTC (rev 428)
@@ -1,18 +1,9 @@
-/**
- * Copyright 2003-2006 The Apache Software Foundation
- *
- * Licensed under the Apache License, Version 2.0 (the "License");
- * you may not use this file except in compliance with the License.
- * You may obtain a copy of the License at
- *
- * http://www.apache.org/licenses/LICENSE-2.0
- *
- * Unless required by applicable law or agreed to in writing, software
- * distributed under the License is distributed on an "AS IS" BASIS,
- * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
- * See the License for the specific language governing permissions and
- * limitations under the License.
- */
+/*------------------------------------------------------------------------------
+* Copyright (C) 2003-2006 Ben van Klinken and the CLucene Team
+*
+* Distributable under the terms of either the Apache License (Version 2.0) or
+* the GNU Lesser General Public License, as specified in the COPYING file.
+------------------------------------------------------------------------------*/
#ifndef _lucene_search_SearchHeader_
#define _lucene_search_SearchHeader_
@@ -34,7 +25,6 @@
//predefine classes
class Scorer;
- class Searcher;
class Query;
class Hits;
class Sort;
@@ -105,14 +95,14 @@
class TopFieldDocs: public TopDocs {
public:
/// The fields which were used to sort results by.
- SortField** fields;
+ const SortField** fields;
/** Creates one of these objects.
* @param totalHits Total number of hits for the query.
* @param scoreDocs The top hits for the query.
* @param fields The sort criteria used to find the top hits.
*/
- TopFieldDocs (int32_t totalHits, ScoreDoc** scoreDocs, int32_t scoreDocsLen, SortField** fields):
+ TopFieldDocs (int32_t totalHits, ScoreDoc** scoreDocs, int32_t scoreDocsLen, const SortField** fields):
TopDocs (totalHits, scoreDocs, scoreDocsLen)
{
this->fields = fields;
@@ -153,7 +143,7 @@
virtual Explanation* explain(CL_NS(index)::IndexReader* reader, int32_t doc) = 0;
virtual TCHAR* toString(){
- return _T("Weight");
+ return STRDUP_TtoT(_T("Weight"));
}
};
@@ -193,14 +183,21 @@
Hits(Searcher* s, Query* q, Filter* f, const Sort* sort=NULL);
~Hits();
- // Returns the total number of hits available in this set.
+ /** Returns the total number of hits available in this set. */
int32_t length() const;
+ /** Returns the stored fields of the n<sup>th</sup> document in this set.
+ <p>Documents are cached, so that repeated requests for the same element may
+ return the same Document object.
+ *
+ * @memory Memory belongs to the hits object. Don't delete the return value.
+ */
CL_NS(document)::Document& doc(const int32_t n);
+ /** Returns the id for the nth document in this set. */
int32_t id (const int32_t n);
- // Returns the score for the nth document in this set.
+ /** Returns the score for the nth document in this set. */
float_t score(const int32_t n);
private:
@@ -212,7 +209,7 @@
void addToFront(HitDoc* hitDoc);
- void remove(HitDoc* hitDoc);
+ void remove(const HitDoc* hitDoc);
};
@@ -371,7 +368,7 @@
*
* <p>This defaults to the current value of {@link Similarity#getDefault()}.
*/
- Similarity* getSimilarity() {
+ Similarity* getSimilarity(){
return this->similarity;
}
};
@@ -400,17 +397,8 @@
// query boost factor
float_t boost;
protected:
-
Query(const Query& clone);
public:
-#ifndef LUCENE_HIDE_INTERNAL
- /** Expert: Constructs an appropriate Weight implementation for this query.
- *
- * <p>Only implemented by primitive queries, which re-write to themselves.
- * <i>Internal, should be protected</i>
- */
- virtual Weight* createWeight(Searcher* searcher);
-#endif
Query();
virtual ~Query();
@@ -426,6 +414,15 @@
*/
float_t getBoost() const;
+ /** Expert: Constructs an appropriate Weight implementation for this query.
+ *
+ * <p>Only implemented by primitive queries, which re-write to themselves.
+ * <i>Internal, should be protected</i>
+ *
+ * todo: this should actually be protected...
+ */
+ virtual Weight* createWeight(Searcher* searcher);
+
/** Expert: Constructs an initializes a Weight for a top-level query. */
Weight* weight(Searcher* searcher);
Modified: trunk/clucene/src/CLucene/search/Similarity.cpp
===================================================================
--- trunk/clucene/src/CLucene/search/Similarity.cpp 2006-06-11 07:16:00 UTC (rev 427)
+++ trunk/clucene/src/CLucene/search/Similarity.cpp 2006-06-26 00:39:24 UTC (rev 428)
@@ -1,18 +1,9 @@
-/**
- * Copyright 2003-2006 The Apache Software Foundation
- *
- * Licensed under the Apache License, Version 2.0 (the "License");
- * you may not use this file except in compliance with the License.
- * You may obtain a copy of the License at
- *
- * http://www.apache.org/licenses/LICENSE-2.0
- *
- * Unless required by applicable law or agreed to in writing, software
- * distributed under the License is distributed on an "AS IS" BASIS,
- * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
- * See the License for the specific language governing permissions and
- * limitations under the License.
- */
+/*------------------------------------------------------------------------------
+* Copyright (C) 2003-2006 Ben van Klinken and the CLucene Team
+*
+* Distributable under the terms of either the Apache License (Version 2.0) or
+* the GNU Lesser General Public License, as specified in the COPYING file.
+------------------------------------------------------------------------------*/
#include "CLucene/StdHeader.h"
#include "Similarity.h"
Modified: trunk/clucene/src/CLucene/search/Similarity.h
===================================================================
--- trunk/clucene/src/CLucene/search/Similarity.h 2006-06-11 07:16:00 UTC (rev 427)
+++ trunk/clucene/src/CLucene/search/Similarity.h 2006-06-26 00:39:24 UTC (rev 428)
@@ -1,18 +1,9 @@
-/**
- * Copyright 2003-2006 The Apache Software Foundation
- *
- * Licensed under the Apache License, Version 2.0 (the "License");
- * you may not use this file except in compliance with the License.
- * You may obtain a copy of the License at
- *
- * http://www.apache.org/licenses/LICENSE-2.0
- *
- * Unless required by applicable law or agreed to in writing, software
- * distributed under the License is distributed on an "AS IS" BASIS,
- * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
- * See the License for the specific language governing permissions and
- * limitations under the License.
- */
+/*------------------------------------------------------------------------------
+* Copyright (C) 2003-2006 Ben van Klinken and the CLucene Team
+*
+* Distributable under the terms of either the Apache License (Version 2.0) or
+* the GNU Lesser General Public License, as specified in the COPYING file.
+------------------------------------------------------------------------------*/
#ifndef _lucene_search_Similarity_
#define _lucene_search_Similarity_
Modified: trunk/clucene/src/CLucene/search/SloppyPhraseScorer.cpp
===================================================================
--- trunk/clucene/src/CLucene/search/SloppyPhraseScorer.cpp 2006-06-11 07:16:00 UTC (rev 427)
+++ trunk/clucene/src/CLucene/search/SloppyPhraseScorer.cpp 2006-06-26 00:39:24 UTC (rev 428)
@@ -1,18 +1,9 @@
-/**
- * Copyright 2003-2006 The Apache Software Foundation
- *
- * Licensed under the Apache License, Version 2.0 (the "License");
- * you may not use this file except in compliance with the License.
- * You may obtain a copy of the License at
- *
- * http://www.apache.org/licenses/LICENSE-2.0
- *
- * Unless required by applicable law or agreed to in writing, software
- * distributed under the License is distributed on an "AS IS" BASIS,
- * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
- * See the License for the specific language governing permissions and
- * limitations under the License.
- */
+/*------------------------------------------------------------------------------
+* Copyright (C) 2003-2006 Ben van Klinken and the CLucene Team
+*
+* Distributable under the terms of either the Apache License (Version 2.0) or
+* the GNU Lesser General Public License, as specified in the COPYING file.
+------------------------------------------------------------------------------*/
#include "CLucene/StdHeader.h"
#ifndef NO_FUZZY_QUERY
#include "SloppyPhraseScorer.h"
Modified: trunk/clucene/src/CLucene/search/SloppyPhraseScorer.h
===================================================================
--- trunk/clucene/src/CLucene/search/SloppyPhraseScorer.h 2006-06-11 07:16:00 UTC (rev 427)
+++ trunk/clucene/src/CLucene/search/SloppyPhraseScorer.h 2006-06-26 00:39:24 UTC (rev 428)
@@ -1,18 +1,9 @@
-/**
- * Copyright 2003-2006 The Apache Software Foundation
- *
- * Licensed under the Apache License, Version 2.0 (the "License");
- * you may not use this file except in compliance with the License.
- * You may obtain a copy of the License at
- *
- * http://www.apache.org/licenses/LICENSE-2.0
- *
- * Unless required by applicable law or agreed to in writing, software
- * distributed under the License is distributed on an "AS IS" BASIS,
- * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
- * See the License for the specific language governing permissions and
- * limitations under the License.
- */
+/*------------------------------------------------------------------------------
+* Copyright (C) 2003-2006 Ben van Klinken and the CLucene Team
+*
+* Distributable under the terms of either the Apache License (Version 2.0) or
+* the GNU Lesser General Public License, as specified in the COPYING file.
+------------------------------------------------------------------------------*/
#ifndef _lucene_search_SloppyPhraseScorer_
#define _lucene_search_SloppyPhraseScorer_
#if defined(_LUCENE_PRAGMA_ONCE)
Modified: trunk/clucene/src/CLucene/search/Sort.cpp
===================================================================
--- trunk/clucene/src/CLucene/search/Sort.cpp 2006-06-11 07:16:00 UTC (rev 427)
+++ trunk/clucene/src/CLucene/search/Sort.cpp 2006-06-26 00:39:24 UTC (rev 428)
@@ -1,18 +1,9 @@
-/**
- * Copyright 2003-2006 The Apache Software Foundation
- *
- * Licensed under the Apache License, Version 2.0 (the "License");
- * you may not use this file except in compliance with the License.
- * You may obtain a copy of the License at
- *
- * http://www.apache.org/licenses/LICENSE-2.0
- *
- * Unless required by applicable law or agreed to in writing, software
- * distributed under the License is distributed on an "AS IS" BASIS,
- * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
- * See the License for the specific language governing permissions and
- * limitations under the License.
- */
+/*------------------------------------------------------------------------------
+* Copyright (C) 2003-2006 Ben van Klinken and the CLucene Team
+*
+* Distributable under the terms of either the Apache License (Version 2.0) or
+* the GNU Lesser General Public License, as specified in the COPYING file.
+------------------------------------------------------------------------------*/
#include "CLucene/StdHeader.h"
#include "Sort.h"
#include "Compare.h"
@@ -23,7 +14,7 @@
/** Represents sorting by document score (relevancy). */
- SortField* SortField::FIELD_SCORE = _CLNEW SortField (NULL, SCORE,false);
+ SortField* SortField::FIELD_SCORE = _CLNEW SortField (NULL, DOCSCORE,false);
/** Represents sorting by document number (index order). */
SortField* SortField::FIELD_DOC = _CLNEW SortField (NULL, DOC,false);
@@ -127,11 +118,34 @@
SortField::~SortField(){
CLStringIntern::unintern(field);
}
+
+ const TCHAR* SortField::toString() const {
+ CL_NS(util)::StringBuffer buffer;
+ switch (type) {
+ case DOCSCORE: buffer.append(_T("<score>"));
+ break;
+ case DOC: buffer.append(_T("<doc>"));
+ break;
+ case CUSTOM: buffer.append (_T("<custom:\""));
+ buffer.append( field );
+ buffer.append( _T("\": "));
+ buffer.append(factory->getName());
+ buffer.append(_T(">"));
+ break;
+ default: buffer.append( _T("\""));
+ buffer.append( field );
+ buffer.append( _T("\"") );
+ break;
+ }
+ //if (locale != null) buffer.append ("("+locale+")"); todo:
+ if (reverse) buffer.appendChar('!');
+ return buffer.toString();
+ }
@@ -140,6 +154,11 @@
+
+
+
+
+
/** Sorts by computed relevance. This is the same sort criteria as
* calling {@link Searcher#search(Query) Searcher#search()} without a sort criteria, only with
* slightly more overhead. */
@@ -292,5 +311,11 @@
}*/
+ SortComparator::SortComparator(ScoreDocComparator* _this):SortComparatorSource(){
+ this->_this = _this;
+ }
+ SortComparator::~SortComparator(){
+ }
+
CL_NS_END
Modified: trunk/clucene/src/CLucene/search/Sort.h
===================================================================
--- trunk/clucene/src/CLucene/search/Sort.h 2006-06-11 07:16:00 UTC (rev 427)
+++ trunk/clucene/src/CLucene/search/Sort.h 2006-06-26 00:39:24 UTC (rev 428)
@@ -1,18 +1,9 @@
-/**
- * Copyright 2003-2006 The Apache Software Foundation
- *
- * Licensed under the Apache License, Version 2.0 (the "License");
- * you may not use this file except in compliance with the License.
- * You may obtain a copy of the License at
- *
- * http://www.apache.org/licenses/LICENSE-2.0
- *
- * Unless required by applicable law or agreed to in writing, software
- * distributed under the License is distributed on an "AS IS" BASIS,
- * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
- * See the License for the specific language governing permissions and
- * limitations under the License.
- */
+/*------------------------------------------------------------------------------
+* Copyright (C) 2003-2006 Ben van Klinken and the CLucene Team
+*
+* Distributable under the terms of either the Apache License (Version 2.0) or
+* the GNU Lesser General Public License, as specified in the COPYING file.
+------------------------------------------------------------------------------*/
#ifndef _lucene_search_Sort_
#define _lucene_search_Sort_
@@ -34,6 +25,8 @@
*
*/
class ScoreDocComparator:LUCENE_BASE {
+ protected:
+ ScoreDocComparator(){}
public:
virtual ~ScoreDocComparator();
// CL_NS(util)::Comparable** cachedValues;
@@ -85,8 +78,10 @@
virtual ~SortComparatorSource(){
}
- //return a reference to a string describing the name of the comparator
- //this is used in the explanation
+ /**
+ * return a reference to a string describing the name of the comparator
+ * this is used in the explanation
+ */
virtual TCHAR* getName() = 0;
virtual size_t hashCode() = 0;
@@ -120,11 +115,8 @@
public:
ScoreDocComparator* newComparator (CL_NS(index)::IndexReader* reader, TCHAR* fieldname);
- SortComparator(ScoreDocComparator* _this):SortComparatorSource(){
- this->_this = _this;
- }
- virtual ~SortComparator(){
- }
+ SortComparator(ScoreDocComparator* _this);
+ virtual ~SortComparator();
/**
* Returns an object which, when sorted according to natural order,
@@ -151,12 +143,24 @@
*
*/
class SortField:LUCENE_BASE {
+private:
+ const TCHAR* field;
+ int32_t type; // defaults to determining type dynamically
+ //Locale* locale; // defaults to "natural order" (no Locale)
+ bool reverse; // defaults to natural order
+ SortComparatorSource* factory;
+
+protected:
+ SortField (const SortField& clone);
public:
virtual ~SortField();
/** Sort by document score (relevancy). Sort values are Float and higher
- * values are at the front. */
- LUCENE_STATIC_CONSTANT(int32_t, SCORE=0);
+ * values are at the front.
+ * PORTING: this is the same as SCORE in java, it had to be renamed because
+ * SCORE is a system macro on some platforms (AIX).
+ */
+ LUCENE_STATIC_CONSTANT(int32_t, DOCSCORE=0);
/** Sort by document number (index order). Sort values are Integer and lower
* values are at the front. */
@@ -194,16 +198,6 @@
/** Represents sorting by document number (index order). */
static SortField* FIELD_DOC;
-
-private:
- const TCHAR* field;
- int32_t type; // defaults to determining type dynamically
- //Locale* locale; // defaults to "natural order" (no Locale)
- bool reverse; // defaults to natural order
- SortComparatorSource* factory;
-
- SortField (const SortField& clone);
-public:
SortField (const TCHAR* field);
//SortField (const TCHAR* field, bool reverse);
//todo: we cannot make reverse use default field of =false.
@@ -220,18 +214,14 @@
* if the sort is by SCORE or DOC.
* @return Name of field, possibly <code>null</code>.
*/
- const TCHAR* getField() {
- return field;
- }
+ const TCHAR* getField() const { return field; }
SortField* clone() const;
/** Returns the type of contents in the field.
* @return One of the constants SCORE, DOC, AUTO, STRING, INT or FLOAT.
*/
- int32_t getType() {
- return type;
- }
+ int32_t getType() const { return type; }
/** Returns the Locale by which term values are interpreted.
* May return <code>null</code> if no Locale was specified.
@@ -244,41 +234,11 @@
/** Returns whether the sort should be reversed.
* @return True if natural order should be reversed.
*/
- bool getReverse() {
- return reverse;
- }
+ bool getReverse() const { return reverse; }
- SortComparatorSource* getFactory() {
- return factory;
- }
+ SortComparatorSource* getFactory() { return factory; }
- const TCHAR* toString() const {
- CL_NS(util)::StringBuffer buffer;
- switch (type) {
- case SCORE: buffer.append(_T("<score>"));
- break;
-
- case DOC: buffer.append(_T("<doc>"));
- break;
-
- case CUSTOM: buffer.append (_T("<custom:\""));
- buffer.append( field );
- buffer.append( _T("\": "));
- buffer.append(factory->getName());
- buffer.append(_T(">"));
- break;
-
- default: buffer.append( _T("\""));
- buffer.append( field );
- buffer.append( _T("\"") );
- break;
- }
-
- //if (locale != null) buffer.append ("("+locale+")"); todo:
- if (reverse) buffer.appendChar('!');
-
- return buffer.toString();
- }
+ const TCHAR* toString() const;
};
@@ -383,13 +343,11 @@
const TCHAR* toString() const;
- /**
+ /**
* Representation of the sort criteria.
* @return a pointer to the of SortField array used in this sort criteria
*/
- SortField** getSort() const{
- return fields;
- }
+ SortField** getSort() const{ return fields; }
};
Modified: trunk/clucene/src/CLucene/search/TermQuery.cpp
===================================================================
--- trunk/clucene/src/CLucene/search/TermQuery.cpp 2006-06-11 07:16:00 UTC (rev 427)
+++ trunk/clucene/src/CLucene/search/TermQuery.cpp 2006-06-26 00:39:24 UTC (rev 428)
@@ -1,18 +1,9 @@
-/**
- * Copyright 2003-2006 The Apache Software Foundation
- *
- * Licensed under the Apache License, Version 2.0 (the "License");
- * you may not use this file except in compliance with the License.
- * You may obtain a copy of the License at
- *
- * http://www.apache.org/licenses/LICENSE-2.0
- *
- * Unless required by applicable law or agreed to in writing, software
- * distributed under the License is distributed on an "AS IS" BASIS,
- * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
- * See the License for the specific language governing permissions and
- * limitations under the License.
- */
+/*------------------------------------------------------------------------------
+* Copyright (C) 2003-2006 Ben van Klinken and the CLucene Team
+*
+* Distributable under the terms of either the Apache License (Version 2.0) or
+* the GNU Lesser General Public License, as specified in the COPYING file.
+------------------------------------------------------------------------------*/
#include "CLucene/StdHeader.h"
#include "TermQuery.h"
@@ -109,7 +100,7 @@
TCHAR* TermQuery::TermWeight::toString() {
int32_t size=_tcslen(_this->getQueryName()) + 10;
TCHAR* tmp = _CL_NEWARRAY(TCHAR, size);//_tcslen(weight())
- _sntprintf(_T("weight(%s)"),size,_this->getQueryName());
+ _sntprintf(tmp,size,_T("weight(%s)"),_this->getQueryName());
return tmp;
}
Modified: trunk/clucene/src/CLucene/search/TermQuery.h
===================================================================
--- trunk/clucene/src/CLucene/search/TermQuery.h 2006-06-11 07:16:00 UTC (rev 427)
+++ trunk/clucene/src/CLucene/search/TermQuery.h 2006-06-26 00:39:24 UTC (rev 428)
@@ -1,18 +1,9 @@
-/**
- * Copyright 2003-2006 The Apache Software Foundation
- *
- * Licensed under the Apache License, Version 2.0 (the "License");
- * you may not use this file except in compliance with the License.
- * You may obtain a copy of the License at
- *
- * http://www.apache.org/licenses/LICENSE-2.0
- *
- * Unless required by applicable law or agreed to in writing, software
- * distributed under the License is distributed on an "AS IS" BASIS,
- * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
- * See the License for the specific language governing permissions and
- * limitations under the License.
- */
+/*------------------------------------------------------------------------------
+* Copyright (C) 2003-2006 Ben van Klinken and the CLucene Team
+*
+* Distributable under the terms of either the Apache License (Version 2.0) or
+* the GNU Lesser General Public License, as specified in the COPYING file.
+------------------------------------------------------------------------------*/
#ifndef _lucene_search_TermQuery_
#define _lucene_search_TermQuery_
Modified: trunk/clucene/src/CLucene/search/TermScorer.cpp
===================================================================
--- trunk/clucene/src/CLucene/search/TermScorer.cpp 2006-06-11 07:16:00 UTC (rev 427)
+++ trunk/clucene/src/CLucene/search/TermScorer.cpp 2006-06-26 00:39:24 UTC (rev 428)
@@ -1,18 +1,9 @@
-/**
- * Copyright 2003-2006 The Apache Software Foundation
- *
- * Licensed under the Apache License, Version 2.0 (the "License");
- * you may not use this file except in compliance with the License.
- * You may obtain a copy of the License at
- *
- * http://www.apache.org/licenses/LICENSE-2.0
- *
- * Unless required by applicable law or agreed to in writing, software
- * distributed under the License is distributed on an "AS IS" BASIS,
- * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
- * See the License for the specific language governing permissions and
- * limitations under the License.
- */
+/*------------------------------------------------------------------------------
+* Copyright (C) 2003-2006 Ben van Klinken and the CLucene Team
+*
+* Distributable under the terms of either the Apache License (Version 2.0) or
+* the GNU Lesser General Public License, as specified in the COPYING file.
+------------------------------------------------------------------------------*/
#include "CLucene/StdHeader.h"
#include "TermScorer.h"
@@ -24,27 +15,21 @@
//TermScorer takes TermDocs and delets it when TermScorer is cleaned up
TermScorer::TermScorer(Weight* w, CL_NS(index)::TermDocs* td,
- Similarity* similarity,uint8_t* _norms):
+ Similarity* similarity,uint8_t* _norms):
Scorer(similarity),
termDocs(td),
norms(_norms),
weight(w),
weightValue(w->getValue()),
+ _doc(0),
pointer(0),
- pointerMax(0),
- _doc(0)
+ pointerMax(0)
{
+ memset(docs,0,32*sizeof(int32_t));
+ memset(freqs,0,32*sizeof(int32_t));
+
for (int32_t i = 0; i < LUCENE_SCORE_CACHE_SIZE; i++)
scoreCache[i] = getSimilarity()->tf(i) * weightValue;
-
- /*pointerMax = termDocs->read(docs, freqs); // fill buffers
-
- if (pointerMax != 0)
- doc = docs[0];
- else {
- termDocs->close(); // close stream
- doc = INT_MAX; // set to sentinel value
- }*/
}
TermScorer::~TermScorer(){
Modified: trunk/clucene/src/CLucene/search/TermScorer.h
===================================================================
--- trunk/clucene/src/CLucene/search/TermScorer.h 2006-06-11 07:16:00 UTC (rev 427)
+++ trunk/clucene/src/CLucene/search/TermScorer.h 2006-06-26 00:39:24 UTC (rev 428)
@@ -1,18 +1,9 @@
-/**
- * Copyright 2003-2006 The Apache Software Foundation
- *
- * Licensed under the Apache License, Version 2.0 (the "License");
- * you may not use this file except in compliance with the License.
- * You may obtain a copy of the License at
- *
- * http://www.apache.org/licenses/LICENSE-2.0
- *
- * Unless required by applicable law or agreed to in writing, software
- * distributed under the License is distributed on an "AS IS" BASIS,
- * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
- * See the License for the specific language governing permissions and
- * limitations under the License.
- */
+/*------------------------------------------------------------------------------
+* Copyright (C) 2003-2006 Ben van Klinken and the CLucene Team
+*
+* Distributable under the terms of either the Apache License (Version 2.0) or
+* the GNU Lesser General Public License, as specified in the COPYING file.
+------------------------------------------------------------------------------*/
#ifndef _lucene_search_TermScorer_
#define _lucene_search_TermScorer_
Modified: trunk/clucene/src/CLucene/search/WildcardQuery.cpp
===================================================================
--- trunk/clucene/src/CLucene/search/WildcardQuery.cpp 2006-06-11 07:16:00 UTC (rev 427)
+++ trunk/clucene/src/CLucene/search/WildcardQuery.cpp 2006-06-26 00:39:24 UTC (rev 428)
@@ -1,18 +1,9 @@
-/**
- * Copyright 2003-2006 The Apache Software Foundation
- *
- * Licensed under the Apache License, Version 2.0 (the "License");
- * you may not use this file except in compliance with the License.
- * You may obtain a copy of the License at
- *
- * http://www.apache.org/licenses/LICENSE-2.0
- *
- * Unless required by applicable law or agreed to in writing, software
- * distributed under the License is distributed on an "AS IS" BASIS,
- * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
- * See the License for the specific language governing permissions and
- * limitations under the License.
- */
+/*------------------------------------------------------------------------------
+* Copyright (C) 2003-2006 Ben van Klinken and the CLucene Team
+*
+* Distributable under the terms of either the Apache License (Version 2.0) or
+* the GNU Lesser General Public License, as specified in the COPYING file.
+------------------------------------------------------------------------------*/
#include "CLucene/StdHeader.h"
#ifndef NO_WILDCARD_QUERY
#include "WildcardQuery.h"
Modified: trunk/clucene/src/CLucene/search/WildcardQuery.h
===================================================================
--- trunk/clucene/src/CLucene/search/WildcardQuery.h 2006-06-11 07:16:00 UTC (rev 427)
+++ trunk/clucene/src/CLucene/search/WildcardQuery.h 2006-06-26 00:39:24 UTC (rev 428)
@@ -1,18 +1,9 @@
-/**
- * Copyright 2003-2006 The Apache Software Foundation
- *
- * Licensed under the Apache License, Version 2.0 (the "License");
- * you may not use this file except in compliance with the License.
- * You may obtain a copy of the License at
- *
- * http://www.apache.org/licenses/LICENSE-2.0
- *
- * Unless required by applicable law or agreed to in writing, software
- * distributed under the License is distributed on an "AS IS" BASIS,
- * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
- * See the License for the specific language governing permissions and
- * limitations under the License.
- */
+/*------------------------------------------------------------------------------
+* Copyright (C) 2003-2006 Ben van Klinken and the CLucene Team
+*
+* Distributable under the terms of either the Apache License (Version 2.0) or
+* the GNU Lesser General Public License, as specified in the COPYING file.
+------------------------------------------------------------------------------*/
#ifndef _lucene_search_WildcardQuery_
#define _lucene_search_WildcardQuery_
#if defined(_LUCENE_PRAGMA_ONCE)
Modified: trunk/clucene/src/CLucene/search/WildcardTermEnum.cpp
===================================================================
--- trunk/clucene/src/CLucene/search/WildcardTermEnum.cpp 2006-06-11 07:16:00 UTC (rev 427)
+++ trunk/clucene/src/CLucene/search/WildcardTermEnum.cpp 2006-06-26 00:39:24 UTC (rev 428)
@@ -1,18 +1,9 @@
-/**
- * Copyright 2003-2006 The Apache Software Foundation
- *
- * Licensed under the Apache License, Version 2.0 (the "License");
- * you may not use this file except in compliance with the License.
- * You may obtain a copy of the License at
- *
- * http://www.apache.org/licenses/LICENSE-2.0
- *
- * Unless required by applicable law or agreed to in writing, software
- * distributed under the License is distributed on an "AS IS" BASIS,
- * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
- * See the License for the specific language governing permissions and
- * limitations under the License.
- */
+/*------------------------------------------------------------------------------
+* Copyright (C) 2003-2006 Ben van Klinken and the CLucene Team
+*
+* Distributable under the terms of either the Apache License (Version 2.0) or
+* the GNU Lesser General Public License, as specified in the COPYING file.
+------------------------------------------------------------------------------*/
#include "CLucene/StdHeader.h"
#ifndef NO_WILDCARD_QUERY
#include "WildcardTermEnum.h"
@@ -34,10 +25,10 @@
/** Creates new WildcardTermEnum */
WildcardTermEnum::WildcardTermEnum(IndexReader* reader, Term* term):
- FilteredTermEnum(),
+ FilteredTermEnum(),
+ __term(_CL_POINTER(term)),
fieldMatch(false),
- _endEnum(false),
- __term(_CL_POINTER(term))
+ _endEnum(false)
{
pre = stringDuplicate(term->text());
Modified: trunk/clucene/src/CLucene/search/WildcardTermEnum.h
===================================================================
--- trunk/clucene/src/CLucene/search/WildcardTermEnum.h 2006-06-11 07:16:00 UTC (rev 427)
+++ trunk/clucene/src/CLucene/search/WildcardTermEnum.h 2006-06-26 00:39:24 UTC (rev 428)
@@ -1,18 +1,9 @@
-/**
- * Copyright 2003-2006 The Apache Software Foundation
- *
- * Licensed under the Apache License, Version 2.0 (the "License");
- * you may not use this file except in compliance with the License.
- * You may obtain a copy of the License at
- *
- * http://www.apache.org/licenses/LICENSE-2.0
- *
- * Unless required by applicable law or agreed to in writing, software
- * distributed under the License is distributed on an "AS IS" BASIS,
- * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
- * See the License for the specific language governing permissions and
- * limitations under the License.
- */
+/*------------------------------------------------------------------------------
+* Copyright (C) 2003-2006 Ben van Klinken and the CLucene Team
+*
+* Distributable under the terms of either the Apache License (Version 2.0) or
+* the GNU Lesser General Public License, as specified in the COPYING file.
+------------------------------------------------------------------------------*/
#ifndef _lucene_search_WildcardTermEnum_
#define _lucene_search_WildcardTermEnum_
#if defined(_LUCENE_PRAGMA_ONCE)
Modified: trunk/clucene/src/CLucene/store/Directory.h
===================================================================
--- trunk/clucene/src/CLucene/store/Directory.h 2006-06-11 07:16:00 UTC (rev 427)
+++ trunk/clucene/src/CLucene/store/Directory.h 2006-06-26 00:39:24 UTC (rev 428)
@@ -1,18 +1,9 @@
-/**
- * Copyright 2003-2006 The Apache Software Foundation
- *
- * Licensed under the Apache License, Version 2.0 (the "License");
- * you may not use this file except in compliance with the License.
- * You may obtain a copy of the License at
- *
- * http://www.apache.org/licenses/LICENSE-2.0
- *
- * Unless required by applicable law or agreed to in writing, software
- * distributed under the License is distributed on an "AS IS" BASIS,
- * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
- * See the License for the specific language governing permissions and
- * limitations under the License.
- */
+/*------------------------------------------------------------------------------
+* Copyright (C) 2003-2006 Ben van Klinken and the CLucene Team
+*
+* Distributable under the terms of either the Apache License (Version 2.0) or
+* the GNU Lesser General Public License, as specified in the COPYING file.
+------------------------------------------------------------------------------*/
#ifndef _lucene_store_Directory
#define _lucene_store_Directory
@@ -64,14 +55,23 @@
virtual int64_t fileLength(const char* name) const = 0;
// Returns a stream reading an existing file.
- virtual IndexInput* openFile(const char* name) = 0;
- virtual IndexInput* openFile(const char* name, int32_t bufferSize){ return openFile(name); }
+ virtual IndexInput* openInput(const char* name) = 0;
+ virtual IndexInput* openInput(const char* name, int32_t bufferSize){
+ return openInput(name); //todo: bufferSize was ignored!
+ }
/// Set the modified time of an existing file to now. */
virtual void touchFile(const char* name) = 0;
// Removes an existing file in the directory.
- virtual void deleteFile(const char* name, const bool throwError = true) = 0;
+ virtual bool deleteFile(const char* name) = 0;
+ virtual void deleteFile(const char* name, const bool throwError){
+ if ( !deleteFile(name) && throwError ){
+ char buffer[200];
+ _snprintf(buffer,200,"couldn't delete %s",name);
+ _CLTHROWA(CL_ERR_IO, buffer );
+ }
+ }
// Renames an existing file in the directory.
// If a file already exists with the new name, then it is replaced.
@@ -80,7 +80,7 @@
// Creates a new, empty file in the directory with the given name.
// Returns a stream writing this file.
- virtual IndexOutput* createFile(const char* name) = 0;
+ virtual IndexOutput* createOutput(const char* name) = 0;
// Construct a {@link Lock}.
// @param name the name of the lock file
Modified: trunk/clucene/src/CLucene/store/FSDirectory.cpp
===================================================================
--- trunk/clucene/src/CLucene/store/FSDirectory.cpp 2006-06-11 07:16:00 UTC (rev 427)
+++ trunk/clucene/src/CLucene/store/FSDirectory.cpp 2006-06-26 00:39:24 UTC (rev 428)
@@ -1,18 +1,9 @@
-/**
- * Copyright 2003-2006 The Apache Software Foundation
- *
- * Licensed under the Apache License, Version 2.0 (the "License");
- * you may not use this file except in compliance with the License.
- * You may obtain a copy of the License at
- *
- * http://www.apache.org/licenses/LICENSE-2.0
- *
- * Unless required by applicable law or agreed to in writing, software
- * distributed under the License is distributed on an "AS IS" BASIS,
- * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
- * See the License for the specific language governing permissions and
- * limitations under the License.
- */
+/*------------------------------------------------------------------------------
+* Copyright (C) 2003-2006 Ben van Klinken and the CLucene Team
+*
+* Distributable under the terms of either the Apache License (Version 2.0) or
+* the GNU Lesser General Public License, as specified in the COPYING file.
+------------------------------------------------------------------------------*/
#include "CLucene/StdHeader.h"
#include "FSDirectory.h"
#include "CLucene/util/Misc.h"
@@ -30,8 +21,8 @@
*/
static CL_NS(util)::CLHashMap<const char*,FSDirectory*,CL_NS(util)::Compare::Char> DIRECTORIES(false,false);
- FSDirectory::FSIndexInput::FSIndexInput(const char* path, int32_t bufferSize):
- BufferedIndexInput(bufferSize)
+ FSDirectory::FSIndexInput::FSIndexInput(const char* path, int32_t __bufferSize):
+ BufferedIndexInput(__bufferSize)
{
//Func - Constructor.
// Opens the file named path
@@ -40,7 +31,7 @@
CND_PRECONDITION(path != NULL, "path is NULL");
- handle = _CLNEW SharedHandle;
+ handle = _CLNEW SharedHandle();
strcpy(handle->path,path);
//Open the file
@@ -63,18 +54,26 @@
this->_pos = 0;
}
- FSDirectory::FSIndexInput::FSIndexInput(const FSIndexInput& clone): BufferedIndexInput(clone){
+ FSDirectory::FSIndexInput::FSIndexInput(const FSIndexInput& other): BufferedIndexInput(other){
//Func - Constructor
// Uses clone for its initialization
//Pre - clone is a valide instance of FSIndexInput
//Post - The instance has been created and initialized by clone
+ if ( other.handle == NULL )
+ _CLTHROWA(CL_ERR_NullPointer, "other handle is null");
- SCOPED_LOCK_MUTEX(clone.handle->THIS_LOCK)
- handle = _CL_POINTER(clone.handle);
- _pos = handle->_fpos; //note where we are currently...
+ SCOPED_LOCK_MUTEX(other.handle->THIS_LOCK)
+ handle = _CL_POINTER(other.handle);
+ _pos = other.handle->_fpos; //note where we are currently...
}
- FSDirectory::FSIndexInput::SharedHandle::~SharedHandle(){
+ FSDirectory::FSIndexInput::SharedHandle::SharedHandle(){
+ fhandle = 0;
+ _length = 0;
+ _fpos = 0;
+ path[0]=0;
+ }
+ FSDirectory::FSIndexInput::SharedHandle::~SharedHandle() throw(CLuceneError&){
if ( fhandle >= 0 ){
if ( _close(fhandle) != 0 )
_CLTHROWA(CL_ERR_IO, "File IO Close error");
@@ -89,7 +88,7 @@
//Post - The file for which this instance is responsible has been closed.
// The instance has been destroyed
- close();
+ FSIndexInput::close();
}
IndexInput* FSDirectory::FSIndexInput::clone() const
@@ -153,7 +152,7 @@
FSDirectory::FSIndexOutput::~FSIndexOutput(){
if ( fhandle >= 0 ){
try {
- close();
+ FSIndexOutput::close();
}catch(...){ //todo: only catch IO Err???
}
}
@@ -184,14 +183,14 @@
_CLTHROWA(CL_ERR_IO, "File IO Seek error");
}
}
- int64_t FSDirectory::FSIndexOutput::Length(){
+ int64_t FSDirectory::FSIndexOutput::length(){
CND_PRECONDITION(fhandle>=0,"file is not open");
return fileSize(fhandle);
}
- char* FSDirectory::LOCK_DIR=NULL;
- char* FSDirectory::getLockDir(){
+ const char* FSDirectory::LOCK_DIR=NULL;
+ const char* FSDirectory::getLockDir(){
#ifdef LUCENE_LOCK_DIR
LOCK_DIR = LUCENE_LOCK_DIR
#else
@@ -218,9 +217,9 @@
refCount(0),
useMMap(false)
{
- strcpy(directory,path);
+ _realpath(path,directory);//set a realpath so that if we change directory, we can still function
- char* tmplockdir = getLockDir();
+ const char* tmplockdir = getLockDir();
if ( tmplockdir == NULL ) {
strcpy(lockDir,directory);
} else {
@@ -274,7 +273,7 @@
closedir(dir);
char* lockPrefix = getLockPrefix(); // clear old locks
- int32_t lockPrefixLen = strlen(lockPrefix);
+ size_t lockPrefixLen = strlen(lockPrefix);
dir = opendir(lockDir);
fl = readdir(dir);
@@ -300,12 +299,6 @@
strcat(buffer,name);
}
- int32_t FSDirectory::priv_getStat(const char* name, struct fileStat* ret) const{
- char buffer[CL_MAX_DIR];
- priv_getFN(buffer,name);
- return fileStat( buffer, ret );
- }
-
FSDirectory::~FSDirectory(){
}
@@ -332,12 +325,12 @@
}
closedir(dir);
- int32_t size = names.size();
- char** list = _CL_NEWARRAY(char*,size+1);
- for ( int32_t i=0;i<size;i++ )
- list[i] = names[i];
- list[size]=NULL;
- return list;
+ size_t size = names.size();
+ char** ret = _CL_NEWARRAY(char*,size+1);
+ for ( size_t i=0;i<size;i++ )
+ ret[i] = names[i];
+ ret[size]=NULL;
+ return ret;
}
bool FSDirectory::fileExists(const char* name) const {
@@ -352,16 +345,19 @@
}
//static
- FSDirectory* FSDirectory::getDirectory(const char* file, const bool create){
+ FSDirectory* FSDirectory::getDirectory(const char* file, const bool _create){
FSDirectory* dir = NULL;
{
+ if ( !file || !*file )
+ _CLTHROWA(CL_ERR_IO,"Invalid directory");
+
SCOPED_LOCK_MUTEX(DIRECTORIES.THIS_LOCK)
dir = DIRECTORIES.get(file);
if ( dir == NULL ){
- dir = _CLNEW FSDirectory(file,create);
+ dir = _CLNEW FSDirectory(file,_create);
DIRECTORIES.put( dir->directory, dir);
- }else if ( create ){
- dir->create();
+ }else if ( _create ){
+ dir->create();
}
}
@@ -376,7 +372,9 @@
int64_t FSDirectory::fileModified(const char* name) const {
CND_PRECONDITION(directory[0]!=0,"directory is not open");
struct fileStat buf;
- if ( priv_getStat(name,&buf) == -1 )
+ char buffer[CL_MAX_DIR];
+ priv_getFN(buffer,name);
+ if (fileStat( buffer, &buf ) == -1 )
return 0;
else
return buf.st_mtime;
@@ -406,14 +404,16 @@
int64_t FSDirectory::fileLength(const char* name) const {
CND_PRECONDITION(directory[0]!=0,"directory is not open");
struct fileStat buf;
- if ( priv_getStat(name, &buf) == -1 )
+ char buffer[CL_MAX_DIR];
+ priv_getFN(buffer,name);
+ if ( fileStat( buffer, &buf ) == -1 )
return 0;
else
return buf.st_size;
}
- IndexInput* FSDirectory::openFile(const char* name ) {
- return openFile(name, LUCENE_STREAM_BUFFER_SIZE);
+ IndexInput* FSDirectory::openInput(const char* name ) {
+ return openInput(name, LUCENE_STREAM_BUFFER_SIZE);
}
#ifdef LUCENE_FS_MMAP
@@ -427,7 +427,7 @@
}
#endif
- IndexInput* FSDirectory::openFile(const char* name, int32_t bufferSize ){
+ IndexInput* FSDirectory::openInput(const char* name, int32_t bufferSize ){
CND_PRECONDITION(directory[0]!=0,"directory is not open")
char fl[CL_MAX_DIR];
priv_getFN(fl, name);
@@ -463,37 +463,32 @@
char HEX_DIGITS[] =
{'0','1','2','3','4','5','6','7','8','9','a','b','c','d','e','f'};
- char* FSDirectory::getLockPrefix() {
+ char* FSDirectory::getLockPrefix() const{
char dirName[CL_MAX_PATH]; // name to be hashed
- if ( _fullpath(dirName,directory,CL_MAX_PATH) == NULL ){
+ if ( _realpath(directory,dirName) == NULL ){
_CLTHROWA(CL_ERR_Runtime,"Invalid directory path");
}
- int dirNameLen = strlen(dirName);
//to make a compatible name with jlucene, we need to make some changes...
if ( dirName[1] == ':' )
dirName[0] = (char)_totupper((char)dirName[0]);
- char* md5 = MD5String(dirName);
+ char* smd5 = MD5String(dirName);
char* ret=_CL_NEWARRAY(char,32+7+1); //32=2*16, 7=strlen("lucene-")
strcpy(ret,"lucene-");
- strcat(ret,md5);
+ strcat(ret,smd5);
- _CLDELETE_CaARRAY(md5);
+ _CLDELETE_CaARRAY(smd5);
return ret;
}
- void FSDirectory::deleteFile(const char* name, const bool throwError) {
+ bool FSDirectory::deleteFile(const char* name) {
CND_PRECONDITION(directory[0]!=0,"directory is not open");
char fl[CL_MAX_DIR];
priv_getFN(fl, name);
- if ( _unlink(fl) == -1 && throwError){
- char buffer[200];
- _snprintf(buffer,200,"couldn't delete %s",name);
- _CLTHROWA(CL_ERR_IO, buffer );
- }
+ return _unlink(fl) != -1;
}
void FSDirectory::renameFile(const char* from, const char* to){
@@ -529,7 +524,7 @@
}
}
- IndexOutput* FSDirectory::createFile(const char* name) {
+ IndexOutput* FSDirectory::createOutput(const char* name) {
CND_PRECONDITION(directory[0]!=0,"directory is not open");
char fl[CL_MAX_DIR];
priv_getFN(fl, name);
@@ -554,10 +549,10 @@
- FSDirectory::FSLock::FSLock ( const char* lockDir, const char* name )
+ FSDirectory::FSLock::FSLock ( const char* _lockDir, const char* name )
{
- this->lockDir = STRDUP_AtoA(lockDir);
- strcpy(lockFile,lockDir);
+ this->lockDir = STRDUP_AtoA(_lockDir);
+ strcpy(lockFile,_lockDir);
strcat(lockFile,PATH_DELIMITERA);
strcat(lockFile,name);
}
@@ -565,7 +560,7 @@
_CLDELETE_LCaARRAY( lockDir );
}
TCHAR* FSDirectory::FSLock::toString(){
- int lflen = strlen(lockFile);
+ size_t lflen = strlen(lockFile);
TCHAR* ret = _CL_NEWARRAY(TCHAR,lflen+6);
_tcscpy(ret,_T("Lock@"));
STRCPY_AtoT(ret+5,lockFile,lflen+1);
Modified: trunk/clucene/src/CLucene/store/FSDirectory.h
===================================================================
--- trunk/clucene/src/CLucene/store/FSDirectory.h 2006-06-11 07:16:00 UTC (rev 427)
+++ trunk/clucene/src/CLucene/store/FSDirectory.h 2006-06-26 00:39:24 UTC (rev 428)
@@ -1,18 +1,9 @@
-/**
- * Copyright 2003-2006 The Apache Software Foundation
- *
- * Licensed under the Apache License, Version 2.0 (the "License");
- * you may not use this file except in compliance with the License.
- * You may obtain a copy of the License at
- *
- * http://www.apache.org/licenses/LICENSE-2.0
- *
- * Unless required by applicable law or agreed to in writing, software
- * distributed under the License is distributed on an "AS IS" BASIS,
- * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
- * See the License for the specific language governing permissions and
- * limitations under the License.
- */
+/*------------------------------------------------------------------------------
+* Copyright (C) 2003-2006 Ben van Klinken and the CLucene Team
+*
+* Distributable under the terms of either the Apache License (Version 2.0) or
+* the GNU Lesser General Public License, as specified in the COPYING file.
+------------------------------------------------------------------------------*/
#ifndef _lucene_store_FSDirectory_
#define _lucene_store_FSDirectory_
@@ -74,7 +65,7 @@
int32_t readVInt();
void readBytes(uint8_t* b, const int32_t offset, const int32_t len);
void close();
- int64_t getFilePointer();
+ int64_t getFilePointer() const;
void seek(const int64_t pos);
int64_t length(){ return _length; }
};
@@ -94,13 +85,13 @@
int64_t _fpos;
DEFINE_MUTEX(THIS_LOCK)
char path[CL_MAX_DIR]; //todo: this is only used for cloning, better to get information from the fhandle
- ~SharedHandle();
+ SharedHandle();
+ ~SharedHandle() throw(CLuceneError&);
};
SharedHandle* handle;
int64_t _pos;
protected:
FSIndexInput(const FSIndexInput& clone);
- DEFINE_MUTEX(THIS_LOCK)
public:
FSIndexInput(const char* path, int32_t bufferSize=LUCENE_STREAM_BUFFER_SIZE);
~FSIndexInput();
@@ -118,17 +109,19 @@
class FSIndexOutput: public IndexOutput {
private:
int32_t fhandle;
+ protected:
+ // output methods:
+ void flushBuffer(const uint8_t* b, const int32_t size);
public:
FSIndexOutput(const char* path);
~FSIndexOutput();
- // output methods:
- void flushBuffer(const uint8_t* b, const int32_t size);
+ // output methods:
void close();
// Random-access methods
void seek(const int64_t pos);
- int64_t Length();
+ int64_t length();
};
#endif //LUCENE_HIDE_INTERNAL
@@ -136,19 +129,16 @@
protected:
FSDirectory(const char* path, const bool createDir);
private:
- char directory[CL_MAX_DIR];
+ char directory[CL_MAX_PATH];
int refCount;
void create();
- static char* LOCK_DIR;
- static char* getLockDir();
+ static const char* LOCK_DIR;
+ static const char* getLockDir();
char lockDir[CL_MAX_PATH];
- char* getLockPrefix();
+ char* getLockPrefix() const;
void priv_getFN(char* buffer, const char* name) const;
- int32_t priv_getStat(const char* name, struct fileStat* ret) const;
-
-
bool useMMap;
public:
///Destructor - only call this if you are sure the directory
@@ -194,15 +184,15 @@
int64_t fileLength(const char* name) const;
/// Returns a stream reading an existing file.
- IndexInput* openFile(const char* name);
- IndexInput* openFile(const char* name, int32_t bufferSize);
+ IndexInput* openInput(const char* name);
+ IndexInput* openInput(const char* name, int32_t bufferSize);
#ifdef LUCENE_FS_MMAP
IndexInput* openMMapFile(const char* name, int32_t bufferSize=LUCENE_STREAM_BUFFER_SIZE);
#endif
/// Removes an existing file in the directory.
- void deleteFile(const char* name, const bool throwError=true);
+ bool deleteFile(const char* name);
/// Renames an existing file in the directory.
void renameFile(const char* from, const char* to);
@@ -212,7 +202,7 @@
/// Creates a new, empty file in the directory with the given name.
/// Returns a stream writing this file.
- IndexOutput* createFile(const char* name);
+ IndexOutput* createOutput(const char* name);
/// Construct a {@link Lock}.
/// @param name the name of the lock file
@@ -231,7 +221,7 @@
/**
* Gets whether the directory is using MMap for inputstreams.
*/
- bool getUseMMap(){ return useMMap; }
+ bool getUseMMap() const{ return useMMap; }
TCHAR* toString() const;
Modified: trunk/clucene/src/CLucene/store/IndexInput.cpp
===================================================================
--- trunk/clucene/src/CLucene/store/IndexInput.cpp 2006-06-11 07:16:00 UTC (rev 427)
+++ trunk/clucene/src/CLucene/store/IndexInput.cpp 2006-06-26 00:39:24 UTC (rev 428)
@@ -1,21 +1,11 @@
-/**
- * Copyright 2003-2006 The Apache Software Foundation
- *
- * Licensed under the Apache License, Version 2.0 (the "License");
- * you may not use this file except in compliance with the License.
- * You may obtain a copy of the License at
- *
- * http://www.apache.org/licenses/LICENSE-2.0
- *
- * Unless required by applicable law or agreed to in writing, software
- * distributed under the License is distributed on an "AS IS" BASIS,
- * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
- * See the License for the specific language governing permissions and
- * limitations under the License.
- */
+ /*------------------------------------------------------------------------------
+* Copyright (C) 2003-2006 Ben van Klinken and the CLucene Team
+*
+* Distributable under the terms of either the Apache License (Version 2.0) or
+* the GNU Lesser General Public License, as specified in the COPYING file.
+------------------------------------------------------------------------------*/
#include "CLucene/StdHeader.h"
#include "IndexInput.h"
-#include "CLucene/util/Arrays.h"
CL_NS_USE(util)
CL_NS_DEF(store)
@@ -23,7 +13,7 @@
IndexInput::IndexInput()
{
}
- IndexInput::IndexInput(const IndexInput& clone)
+ IndexInput::IndexInput(const IndexInput& other)
{
}
@@ -47,9 +37,9 @@
}
int64_t IndexInput::readLong() {
- int32_t i1 = readInt();
- int32_t i2 = readInt();
- return (((int64_t)i1) << 32) | (i2 & 0xFFFFFFFFL);
+ int64_t i1 = readInt();
+ int64_t i2 = readInt();
+ return (i1 << 32) | (i2 & 0xFFFFFFFFL);
}
int64_t IndexInput::readVLong() {
@@ -79,11 +69,11 @@
}
}
- TCHAR* IndexInput::readString(const bool unique){
+ TCHAR* IndexInput::readString(const bool _unique){
int32_t len = readVInt();
- if ( len == 0){
- if ( unique )
+ if ( len == 0){
+ if ( _unique ) //todo: does non unique ever occur?
return stringDuplicate(LUCENE_BLANK_STRING);
else
return LUCENE_BLANK_STRING;
@@ -121,28 +111,29 @@
- BufferedIndexInput::BufferedIndexInput(int32_t _bufferSize):
+BufferedIndexInput::BufferedIndexInput(int32_t _bufferSize):
+ buffer(NULL),
+ bufferSize(_bufferSize),
bufferStart(0),
bufferLength(0),
- bufferPosition(0),
- bufferSize(_bufferSize),
- buffer(NULL)
+ bufferPosition(0)
{
}
- BufferedIndexInput::BufferedIndexInput(const BufferedIndexInput& clone):
- bufferStart(clone.bufferStart),
- bufferLength(clone.bufferLength),
- bufferPosition(clone.bufferPosition),
- bufferSize(clone.bufferSize),
- buffer(NULL)
+ BufferedIndexInput::BufferedIndexInput(const BufferedIndexInput& other):
+ IndexInput(other),
+ buffer(NULL),
+ bufferSize(other.bufferSize),
+ bufferStart(other.bufferStart),
+ bufferLength(other.bufferLength),
+ bufferPosition(other.bufferPosition)
{
/* DSR: Does the fact that sometime clone.buffer is not NULL even when
** clone.bufferLength is zero indicate memory corruption/leakage?
** if ( clone.buffer != NULL) { */
- if (clone.bufferLength != 0 && clone.buffer != NULL) {
+ if (other.bufferLength != 0 && other.buffer != NULL) {
buffer = _CL_NEWARRAY(uint8_t,bufferLength);
- memcpy(buffer,clone.buffer,bufferLength * sizeof(uint8_t));
+ memcpy(buffer,other.buffer,bufferLength * sizeof(uint8_t));
}
}
@@ -161,7 +152,7 @@
}
}
- int64_t BufferedIndexInput::getFilePointer() {
+ int64_t BufferedIndexInput::getFilePointer() const{
return bufferStart + bufferPosition;
}
@@ -178,10 +169,7 @@
}
}
void BufferedIndexInput::close(){
- if ( buffer != NULL ) {
- _CLDELETE_ARRAY(buffer);
- }
-
+ _CLDELETE_ARRAY(buffer);
bufferLength = 0;
bufferPosition = 0;
bufferStart = 0;
@@ -189,7 +177,7 @@
BufferedIndexInput::~BufferedIndexInput(){
- close();
+ BufferedIndexInput::close();
}
void BufferedIndexInput::refill() {
Modified: trunk/clucene/src/CLucene/store/IndexInput.h
===================================================================
--- trunk/clucene/src/CLucene/store/IndexInput.h 2006-06-11 07:16:00 UTC (rev 427)
+++ trunk/clucene/src/CLucene/store/IndexInput.h 2006-06-26 00:39:24 UTC (rev 428)
@@ -1,18 +1,9 @@
-/**
- * Copyright 2003-2006 The Apache Software Foundation
- *
- * Licensed under the Apache License, Version 2.0 (the "License");
- * you may not use this file except in compliance with the License.
- * You may obtain a copy of the License at
- *
- * http://www.apache.org/licenses/LICENSE-2.0
- *
- * Unless required by applicable law or agreed to in writing, software
- * distributed under the License is distributed on an "AS IS" BASIS,
- * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
- * See the License for the specific language governing permissions and
- * limitations under the License.
- */
+/*------------------------------------------------------------------------------
+* Copyright (C) 2003-2006 Ben van Klinken and the CLucene Team
+*
+* Distributable under the terms of either the Apache License (Version 2.0) or
+* the GNU Lesser General Public License, as specified in the COPYING file.
+------------------------------------------------------------------------------*/
#ifndef _lucene_store_IndexInput_
#define _lucene_store_IndexInput_
@@ -105,7 +96,7 @@
* occur.
* @see #seek(long)
*/
- virtual int64_t getFilePointer() =0;
+ virtual int64_t getFilePointer() const =0;
/** Sets current position in this file, where the next read will occur.
* @see #getFilePointer()
@@ -149,12 +140,12 @@
void close();
inline uint8_t readByte(){
if (bufferPosition >= bufferLength)
- refill();
+ refill();
return buffer[bufferPosition++];
}
void readBytes(uint8_t* b, const int32_t offset, const int32_t len);
- int64_t getFilePointer();
+ int64_t getFilePointer() const;
void seek(const int64_t pos);
protected:
Modified: trunk/clucene/src/CLucene/store/IndexOutput.cpp
===================================================================
--- trunk/clucene/src/CLucene/store/IndexOutput.cpp 2006-06-11 07:16:00 UTC (rev 427)
+++ trunk/clucene/src/CLucene/store/IndexOutput.cpp 2006-06-26 00:39:24 UTC (rev 428)
@@ -1,23 +1,12 @@
-/**
- * Copyright 2003-2006 The Apache Software Foundation
- *
- * Licensed under the Apache License, Version 2.0 (the "License");
- * you may not use this file except in compliance with the License.
- * You may obtain a copy of the License at
- *
- * http://www.apache.org/licenses/LICENSE-2.0
- *
- * Unless required by applicable law or agreed to in writing, software
- * distributed under the License is distributed on an "AS IS" BASIS,
- * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
- * See the License for the specific language governing permissions and
- * limitations under the License.
- */
+/*------------------------------------------------------------------------------
+* Copyright (C) 2003-2006 Ben van Klinken and the CLucene Team
+*
+* Distributable under the terms of either the Apache License (Version 2.0) or
+* the GNU Lesser General Public License, as specified in the COPYING file.
+------------------------------------------------------------------------------*/
#include "CLucene/StdHeader.h"
#include "IndexOutput.h"
-#include "CLucene/util/Arrays.h"
-
CL_NS_USE(util)
CL_NS_DEF(store)
@@ -30,6 +19,8 @@
}
IndexOutput::~IndexOutput(){
+ if ( buffer != NULL )
+ close();
}
bool IndexOutput::isClosed() const { /* DSR:PROPOSED */
@@ -45,6 +36,7 @@
}
void IndexOutput::writeByte(const uint8_t b) {
+ CND_PRECONDITION(buffer!=NULL,"IndexOutput is closed")
if (bufferPosition >= LUCENE_STREAM_BUFFER_SIZE)
flush();
buffer[bufferPosition++] = b;
@@ -116,7 +108,7 @@
}
- int64_t IndexOutput::getFilePointer() {
+ int64_t IndexOutput::getFilePointer() const{
return bufferStart + bufferPosition;
}
Modified: trunk/clucene/src/CLucene/store/IndexOutput.h
===================================================================
--- trunk/clucene/src/CLucene/store/IndexOutput.h 2006-06-11 07:16:00 UTC (rev 427)
+++ trunk/clucene/src/CLucene/store/IndexOutput.h 2006-06-26 00:39:24 UTC (rev 428)
@@ -1,18 +1,9 @@
-/**
- * Copyright 2003-2006 The Apache Software Foundation
- *
- * Licensed under the Apache License, Version 2.0 (the "License");
- * you may not use this file except in compliance with the License.
- * You may obtain a copy of the License at
- *
- * http://www.apache.org/licenses/LICENSE-2.0
- *
- * Unless required by applicable law or agreed to in writing, software
- * distributed under the License is distributed on an "AS IS" BASIS,
- * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
- * See the License for the specific language governing permissions and
- * limitations under the License.
- */
+/*------------------------------------------------------------------------------
+* Copyright (C) 2003-2006 Ben van Klinken and the CLucene Team
+*
+* Distributable under the terms of either the Apache License (Version 2.0) or
+* the GNU Lesser General Public License, as specified in the COPYING file.
+------------------------------------------------------------------------------*/
#ifndef _lucene_store_IndexOutput_
#define _lucene_store_IndexOutput_
#if defined(_LUCENE_PRAGMA_ONCE)
@@ -97,7 +88,7 @@
* occur.
* @see #seek(long)
*/
- int64_t getFilePointer();
+ int64_t getFilePointer() const;
/** Sets current position in this file, where the next write will occur.
* @see #getFilePointer()
@@ -105,7 +96,7 @@
virtual void seek(const int64_t pos);
/** The number of bytes in the file. */
- virtual int64_t Length() = 0;
+ virtual int64_t length() = 0;
/** Forces any buffered output to be written. */
void flush();
Modified: trunk/clucene/src/CLucene/store/InputStream.h
===================================================================
--- trunk/clucene/src/CLucene/store/InputStream.h 2006-06-11 07:16:00 UTC (rev 427)
+++ trunk/clucene/src/CLucene/store/InputStream.h 2006-06-26 00:39:24 UTC (rev 428)
@@ -1,18 +1,9 @@
-/**
- * Copyright 2003-2006 The Apache Software Foundation
- *
- * Licensed under the Apache License, Version 2.0 (the "License");
- * you may not use this file except in compliance with the License.
- * You may obtain a copy of the License at
- *
- * http://www.apache.org/licenses/LICENSE-2.0
- *
- * Unless required by applicable law or agreed to in writing, software
- * distributed under the License is distributed on an "AS IS" BASIS,
- * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
- * See the License for the specific language governing permissions and
- * limitations under the License.
- */
+/*------------------------------------------------------------------------------
+* Copyright (C) 2003-2006 Ben van Klinken and the CLucene Team
+*
+* Distributable under the terms of either the Apache License (Version 2.0) or
+* the GNU Lesser General Public License, as specified in the COPYING file.
+------------------------------------------------------------------------------*/
#ifndef _lucene_store_InputStream_
#define _lucene_store_InputStream_
Modified: trunk/clucene/src/CLucene/store/Lock.cpp
===================================================================
--- trunk/clucene/src/CLucene/store/Lock.cpp 2006-06-11 07:16:00 UTC (rev 427)
+++ trunk/clucene/src/CLucene/store/Lock.cpp 2006-06-26 00:39:24 UTC (rev 428)
@@ -1,18 +1,9 @@
-/**
- * Copyright 2003-2006 The Apache Software Foundation
- *
- * Licensed under the Apache License, Version 2.0 (the "License");
- * you may not use this file except in compliance with the License.
- * You may obtain a copy of the License at
- *
- * http://www.apache.org/licenses/LICENSE-2.0
- *
- * Unless required by applicable law or agreed to in writing, software
- * distributed under the License is distributed on an "AS IS" BASIS,
- * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
- * See the License for the specific language governing permissions and
- * limitations under the License.
- */
+/*------------------------------------------------------------------------------
+* Copyright (C) 2003-2006 Ben van Klinken and the CLucene Team
+*
+* Distributable under the terms of either the Apache License (Version 2.0) or
+* the GNU Lesser General Public License, as specified in the COPYING file.
+------------------------------------------------------------------------------*/
#include "CLucene/StdHeader.h"
#include "Lock.h"
Modified: trunk/clucene/src/CLucene/store/Lock.h
===================================================================
--- trunk/clucene/src/CLucene/store/Lock.h 2006-06-11 07:16:00 UTC (rev 427)
+++ trunk/clucene/src/CLucene/store/Lock.h 2006-06-26 00:39:24 UTC (rev 428)
@@ -1,18 +1,9 @@
-/**
- * Copyright 2003-2006 The Apache Software Foundation
- *
- * Licensed under the Apache License, Version 2.0 (the "License");
- * you may not use this file except in compliance with the License.
- * You may obtain a copy of the License at
- *
- * http://www.apache.org/licenses/LICENSE-2.0
- *
- * Unless required by applicable law or agreed to in writing, software
- * distributed under the License is distributed on an "AS IS" BASIS,
- * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
- * See the License for the specific language governing permissions and
- * limitations under the License.
- */
+/*------------------------------------------------------------------------------
+* Copyright (C) 2003-2006 Ben van Klinken and the CLucene Team
+*
+* Distributable under the terms of either the Apache License (Version 2.0) or
+* the GNU Lesser General Public License, as specified in the COPYING file.
+------------------------------------------------------------------------------*/
#ifndef _lucene_store_Lock_
#define _lucene_store_Lock_
Modified: trunk/clucene/src/CLucene/store/MMapInput.cpp
===================================================================
--- trunk/clucene/src/CLucene/store/MMapInput.cpp 2006-06-11 07:16:00 UTC (rev 427)
+++ trunk/clucene/src/CLucene/store/MMapInput.cpp 2006-06-26 00:39:24 UTC (rev 428)
@@ -1,18 +1,9 @@
-/**
- * Copyright 2003-2006 The Apache Software Foundation
- *
- * Licensed under the Apache License, Version 2.0 (the "License");
- * you may not use this file except in compliance with the License.
- * You may obtain a copy of the License at
- *
- * http://www.apache.org/licenses/LICENSE-2.0
- *
- * Unless required by applicable law or agreed to in writing, software
- * distributed under the License is distributed on an "AS IS" BASIS,
- * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
- * See the License for the specific language governing permissions and
- * limitations under the License.
- */
+/*------------------------------------------------------------------------------
+* Copyright (C) 2003-2006 Ben van Klinken and the CLucene Team
+*
+* Distributable under the terms of either the Apache License (Version 2.0) or
+* the GNU Lesser General Public License, as specified in the COPYING file.
+------------------------------------------------------------------------------*/
#include "CLucene/StdHeader.h"
#if defined(LUCENE_FS_MMAP)
@@ -152,7 +143,7 @@
}
return i;
}
- int64_t FSDirectory::MMapIndexInput::getFilePointer(){
+ int64_t FSDirectory::MMapIndexInput::getFilePointer() const{
return pos;
}
void FSDirectory::MMapIndexInput::seek(const int64_t pos){
Modified: trunk/clucene/src/CLucene/store/OutputStream.h
===================================================================
--- trunk/clucene/src/CLucene/store/OutputStream.h 2006-06-11 07:16:00 UTC (rev 427)
+++ trunk/clucene/src/CLucene/store/OutputStream.h 2006-06-26 00:39:24 UTC (rev 428)
@@ -1,18 +1,9 @@
-/**
- * Copyright 2003-2006 The Apache Software Foundation
- *
- * Licensed under the Apache License, Version 2.0 (the "License");
- * you may not use this file except in compliance with the License.
- * You may obtain a copy of the License at
- *
- * http://www.apache.org/licenses/LICENSE-2.0
- *
- * Unless required by applicable law or agreed to in writing, software
- * distributed under the License is distributed on an "AS IS" BASIS,
- * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
- * See the License for the specific language governing permissions and
- * limitations under the License.
- */
+/*------------------------------------------------------------------------------
+* Copyright (C) 2003-2006 Ben van Klinken and the CLucene Team
+*
+* Distributable under the terms of either the Apache License (Version 2.0) or
+* the GNU Lesser General Public License, as specified in the COPYING file.
+------------------------------------------------------------------------------*/
#ifndef _lucene_store_IndexOutput_
#define _lucene_store_IndexOutput_
#if defined(_LUCENE_PRAGMA_ONCE)
Modified: trunk/clucene/src/CLucene/store/RAMDirectory.cpp
===================================================================
--- trunk/clucene/src/CLucene/store/RAMDirectory.cpp 2006-06-11 07:16:00 UTC (rev 427)
+++ trunk/clucene/src/CLucene/store/RAMDirectory.cpp 2006-06-26 00:39:24 UTC (rev 428)
@@ -1,18 +1,9 @@
-/**
- * Copyright 2003-2006 The Apache Software Foundation
- *
- * Licensed under the Apache License, Version 2.0 (the "License");
- * you may not use this file except in compliance with the License.
- * You may obtain a copy of the License at
- *
- * http://www.apache.org/licenses/LICENSE-2.0
- *
- * Unless required by applicable law or agreed to in writing, software
- * distributed under the License is distributed on an "AS IS" BASIS,
- * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
- * See the License for the specific language governing permissions and
- * limitations under the License.
- */
+/*------------------------------------------------------------------------------
+* Copyright (C) 2003-2006 Ben van Klinken and the CLucene Team
+*
+* Distributable under the terms of either the Apache License (Version 2.0) or
+* the GNU Lesser General Public License, as specified in the COPYING file.
+------------------------------------------------------------------------------*/
#include "CLucene/StdHeader.h"
#include "RAMDirectory.h"
@@ -36,13 +27,14 @@
RAMDirectory::RAMLock::RAMLock(const char* name, RAMDirectory* dir):
- fname ( STRDUP_AtoA(name) ),
directory(dir)
{
+ fname = STRDUP_AtoA(name);
}
RAMDirectory::RAMLock::~RAMLock()
{
_CLDELETE_LCaARRAY( fname );
+ directory = NULL;
}
TCHAR* RAMDirectory::RAMLock::toString(){
return STRDUP_TtoT(_T("LockFile at RAM"));
@@ -53,7 +45,7 @@
bool RAMDirectory::RAMLock::obtain(){
SCOPED_LOCK_MUTEX(directory->files_mutex);
if (!directory->fileExists(fname)) {
- IndexOutput* tmp = directory->createFile(fname);
+ IndexOutput* tmp = directory->createOutput(fname);
tmp->close();
_CLDELETE(tmp);
@@ -68,8 +60,10 @@
RAMIndexOutput::~RAMIndexOutput(){
- if ( deleteFile )
+ if ( deleteFile ){
_CLDELETE(file);
+ }else
+ file = NULL;
}
RAMIndexOutput::RAMIndexOutput(RAMFile* f):file(f) {
pointer = 0;
@@ -87,49 +81,43 @@
flush();
int64_t end = file->length;
int64_t pos = 0;
- int32_t buffer = 0;
+ int32_t p = 0;
while (pos < end) {
int32_t length = LUCENE_STREAM_BUFFER_SIZE;
int64_t nextPos = pos + length;
if (nextPos > end) { // at the last buffer
length = (int32_t)(end - pos);
}
- out->writeBytes((uint8_t*)file->buffers[buffer++], length);
+ out->writeBytes((uint8_t*)file->buffers[p++], length);
pos = nextPos;
}
}
void RAMIndexOutput::reset(){
- seek(0);
- file->length = 0;
+ seek(_ILONGLONG(0));
+ file->length = _ILONGLONG(0);
}
void RAMIndexOutput::flushBuffer(const uint8_t* src, const int32_t len) {
- uint32_t bufferNumber = pointer/LUCENE_STREAM_BUFFER_SIZE;
- int32_t bufferOffset = pointer%LUCENE_STREAM_BUFFER_SIZE;
- int32_t bytesInBuffer = LUCENE_STREAM_BUFFER_SIZE - bufferOffset;
- int32_t bytesToCopy = bytesInBuffer >= len ? len : bytesInBuffer;
-
+ uint8_t* b = NULL;
+ int32_t bufferPos = 0;
+ while (bufferPos != len) {
+ uint32_t bufferNumber = pointer/LUCENE_STREAM_BUFFER_SIZE;
+ int32_t bufferOffset = pointer%LUCENE_STREAM_BUFFER_SIZE;
+ int32_t bytesInBuffer = LUCENE_STREAM_BUFFER_SIZE - bufferOffset;
+ int32_t remainInSrcBuffer = len - bufferPos;
+ int32_t bytesToCopy = bytesInBuffer >= remainInSrcBuffer ? remainInSrcBuffer : bytesInBuffer;
+
if (bufferNumber == file->buffers.size()){
- uint8_t* tmp = _CL_NEWARRAY(uint8_t,LUCENE_STREAM_BUFFER_SIZE);
- file->buffers.push_back( tmp );
+ b = _CL_NEWARRAY(uint8_t, LUCENE_STREAM_BUFFER_SIZE);
+ file->buffers.push_back( b );
+ }else{
+ b = file->buffers[bufferNumber];
}
-
- uint8_t* buffer = file->buffers[bufferNumber];
- memcpy(buffer+bufferOffset, src,bytesToCopy * sizeof(uint8_t));
-
- if (bytesToCopy < len) { // not all in one buffer
- int32_t srcOffset = bytesToCopy;
- bytesToCopy = len - bytesToCopy; // remaining bytes
- bufferNumber++;
- if (bufferNumber == file->buffers.size()){
- uint8_t* tmp = _CL_NEWARRAY(uint8_t,LUCENE_STREAM_BUFFER_SIZE);
- file->buffers.push_back(tmp);
- }
- buffer = file->buffers[bufferNumber];
- memcpy(buffer,src+srcOffset,bytesToCopy * sizeof(uint8_t));
- }
- pointer += len;
+ memcpy(b+bufferOffset, src+bufferPos, bytesToCopy * sizeof(uint8_t));
+ bufferPos += bytesToCopy;
+ pointer += bytesToCopy;
+ }
if (pointer > file->length)
file->length = pointer;
@@ -145,24 +133,25 @@
IndexOutput::seek(pos);
pointer = (int32_t)pos;
}
- int64_t RAMIndexOutput::Length() {
+ int64_t RAMIndexOutput::length() {
return file->length;
}
- RAMIndexInput::RAMIndexInput(RAMFile* f):file(f) {
+ RAMIndexInput::RAMIndexInput(RAMFile* f):
+ file(f) {
pointer = 0;
_length = f->length;
}
- RAMIndexInput::RAMIndexInput(const RAMIndexInput& clone):
- file(clone.file),
- BufferedIndexInput(clone)
+ RAMIndexInput::RAMIndexInput(const RAMIndexInput& other):
+ BufferedIndexInput(other)
{
- pointer = clone.pointer;
- _length = clone._length;
+ file = other.file;
+ pointer = other.pointer;
+ _length = other._length;
}
RAMIndexInput::~RAMIndexInput(){
- close();
+ RAMIndexInput::close();
}
IndexInput* RAMIndexInput::clone() const
{
@@ -187,10 +176,9 @@
** buffer won't exceed the the capacity of int32_t. Therefore, the
** int64_t->int32_t cast on the next line is safe. */
int32_t bytesToCopy = bytesInBuffer >= remainder ? static_cast<int32_t>(remainder) : bytesInBuffer;
- uint8_t* buffer = (uint8_t*)file->buffers[bufferNumber];
+ uint8_t* b = file->buffers[bufferNumber];
+ memcpy(dest+destOffset,b+bufferOffset,bytesToCopy * sizeof(uint8_t));
- memcpy(dest+destOffset,buffer+bufferOffset,bytesToCopy * sizeof(uint8_t));
-
destOffset += bytesToCopy;
start += bytesToCopy;
remainder -= bytesToCopy;
@@ -215,16 +203,16 @@
char** RAMDirectory::list() const{
SCOPED_LOCK_MUTEX(files_mutex);
int32_t size = 0;
- char** list = _CL_NEWARRAY(char*,files.size()+1);
+ char** lst = _CL_NEWARRAY(char*,files.size()+1);
FileMap::const_iterator itr = files.begin();
while (itr != files.end()){
- list[size] = lucenestrdup((char*)itr->first CL_FILELINE);
- itr++;
+ lst[size] = STRDUP_AtoA(itr->first);
+ ++itr;
size++;
}
- list[size]=NULL;
- return list;
+ lst[size]=NULL;
+ return lst;
}
RAMDirectory::RAMDirectory():
@@ -238,22 +226,25 @@
void RAMDirectory::_copyFromDir(Directory* dir, bool closeDir)
{
- char** files = dir->list();
+ char** fls = dir->list();
int i=0;
- while ( files[i] != NULL ){
+ uint8_t* buf = _CL_NEWARRAY(uint8_t, LUCENE_STREAM_BUFFER_SIZE);
+
+ while ( fls[i] != NULL ){
// make place on ram disk
- IndexOutput* os = createFile(files[i]);
+ IndexOutput* os = createOutput(fls[i]);
// read current file
- IndexInput* is = dir->openFile(files[i]);
+ IndexInput* is = dir->openInput(fls[i]);
// and copy to ram disk
- //todo: this could be a problem when copying from big indexes... but what's
- //the chance that someone's going to copy more than 2gb from disk into RAM...
- //actually, it is possible...
- int32_t len = is->length();
- uint8_t* buf = _CL_NEWARRAY(uint8_t,len);
- is->readBytes(buf, 0, len);
- os->writeBytes(buf, len);
- _CLDELETE_ARRAY(buf);
+ //todo: this could be a problem when copying from big indexes...
+ int64_t len = is->length();
+ int64_t readCount = 0;
+ while (readCount < len) {
+ int32_t toRead = (int32_t)(readCount + LUCENE_STREAM_BUFFER_SIZE > len ? len - readCount : LUCENE_STREAM_BUFFER_SIZE);
+ is->readBytes(buf, 0, toRead);
+ os->writeBytes(buf, toRead);
+ readCount += toRead;
+ }
// graceful cleanup
is->close();
@@ -261,10 +252,11 @@
os->close();
_CLDELETE(os);
- _CLDELETE_LCaARRAY(files[i]);
+ _CLDELETE_LCaARRAY(fls[i]);
i++;
}
- _CLDELETE_ARRAY(files);
+ _CLDELETE_ARRAY(buf);
+ _CLDELETE_ARRAY(fls);
if (closeDir)
dir->close();
@@ -304,7 +296,7 @@
}
- IndexInput* RAMDirectory::openFile(const char* name) {
+ IndexInput* RAMDirectory::openInput(const char* name) {
SCOPED_LOCK_MUTEX(files_mutex);
RAMFile* file = files.get(name);
if (file == NULL) { /* DSR:PROPOSED: Better error checking. */
@@ -318,9 +310,10 @@
files.clear();
}
- void RAMDirectory::deleteFile(const char* name, const bool throwError) {
+ bool RAMDirectory::deleteFile(const char* name) {
SCOPED_LOCK_MUTEX(files_mutex);
files.remove(name);
+ return true;
}
void RAMDirectory::renameFile(const char* from, const char* to) {
@@ -335,7 +328,13 @@
if (files.exists(to)) {
files.remove(to);
}
- RAMFile* file = itr->second;
+ if ( itr == files.end() ){
+ char tmp[1024];
+ _snprintf(tmp,1024,"cannot rename %s, file does not exist");
+ _CLTHROWT(CL_ERR_IO,tmp);
+ }
+ CND_PRECONDITION(itr != files.end(), "itr==files.end()")
+ RAMFile* file = itr->second;
files.removeitr(itr,false,true);
files.put(STRDUP_AtoA(to), file);
}
@@ -359,7 +358,7 @@
file->lastModified = ts2;
}
- IndexOutput* RAMDirectory::createFile(const char* name) {
+ IndexOutput* RAMDirectory::createOutput(const char* name) {
/* Check the $files VoidMap to see if there was a previous file named
** $name. If so, delete the old RAMFile object, but reuse the existing
** char buffer ($n) that holds the filename. If not, duplicate the
Modified: trunk/clucene/src/CLucene/store/RAMDirectory.h
===================================================================
--- trunk/clucene/src/CLucene/store/RAMDirectory.h 2006-06-11 07:16:00 UTC (rev 427)
+++ trunk/clucene/src/CLucene/store/RAMDirectory.h 2006-06-26 00:39:24 UTC (rev 428)
@@ -1,18 +1,9 @@
-/**
- * Copyright 2003-2006 The Apache Software Foundation
- *
- * Licensed under the Apache License, Version 2.0 (the "License");
- * you may not use this file except in compliance with the License.
- * You may obtain a copy of the License at
- *
- * http://www.apache.org/licenses/LICENSE-2.0
- *
- * Unless required by applicable law or agreed to in writing, software
- * distributed under the License is distributed on an "AS IS" BASIS,
- * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
- * See the License for the specific language governing permissions and
- * limitations under the License.
- */
+/*------------------------------------------------------------------------------
+* Copyright (C) 2003-2006 Ben van Klinken and the CLucene Team
+*
+* Distributable under the terms of either the Apache License (Version 2.0) or
+* the GNU Lesser General Public License, as specified in the COPYING file.
+------------------------------------------------------------------------------*/
#ifndef _lucene_store_RAMDirectory_
#define _lucene_store_RAMDirectory_
@@ -46,21 +37,20 @@
RAMFile* file;
int32_t pointer;
bool deleteFile;
+
+ // output methods:
+ void flushBuffer(const uint8_t* src, const int32_t len);
public:
-
RAMIndexOutput(RAMFile* f);
RAMIndexOutput();
/** Construct an empty output buffer. */
virtual ~RAMIndexOutput();
- // output methods:
- void flushBuffer(const uint8_t* src, const int32_t len);
-
virtual void close();
// Random-at methods
virtual void seek(const int64_t pos);
- int64_t Length();
+ int64_t length();
/** Resets this to an empty buffer. */
void reset();
/** Copy the current contents of this buffer to the named output. */
@@ -71,14 +61,10 @@
private:
RAMFile* file;
int32_t pointer;
- RAMIndexInput(const RAMIndexInput& clone);
int64_t _length;
- public:
- RAMIndexInput(RAMFile* f);
- ~RAMIndexInput();
- IndexInput* clone() const;
-
+ protected:
/** IndexInput methods */
+ RAMIndexInput(const RAMIndexInput& clone);
/** DSR:CL_BUG:
** The CLucene 0.8.11 implementation of readInternal caused invalid memory
** ops if fewer than the requested number of bytes were available and the
@@ -91,12 +77,15 @@
** it only segfaulted occasionally.
** I replaced the dysfunctional CLucene 0.8.11 impl with a fixed version. */
void readInternal(uint8_t *dest, const int32_t idestOffset, const int32_t len);
-
- void close();
-
+
/** Random-at methods */
void seekInternal(const int64_t pos);
+ public:
+ RAMIndexInput(RAMFile* f);
+ ~RAMIndexInput();
+ IndexInput* clone() const;
+ void close();
int64_t length();
};
@@ -109,7 +98,7 @@
class RAMLock: public LuceneLock{
private:
RAMDirectory* directory;
- const char* fname;
+ char* fname;
public:
RAMLock(const char* name, RAMDirectory* dir);
virtual ~RAMLock();
@@ -138,7 +127,7 @@
FileMap files; // unlike the java Hashtable, FileMap is not synchronized, and all access must be protected by a lock
public:
#ifndef _CL_DISABLE_MULTITHREADING //do this so that the mutable keyword still works without mt enabled
- mutable DEFINE_MUTEX(files_mutex); // mutable: const methods must also be able to synchronize properly
+ mutable DEFINE_MUTEX(files_mutex) // mutable: const methods must also be able to synchronize properly
#endif
/// Returns a null terminated array of strings, one for each file in the directory.
@@ -173,21 +162,21 @@
virtual void renameFile(const char* from, const char* to);
/// Removes an existing file in the directory.
- virtual void deleteFile(const char* name, const bool throwError = true);
+ virtual bool deleteFile(const char* name);
/** Set the modified time of an existing file to now. */
void touchFile(const char* name);
/// Creates a new, empty file in the directory with the given name.
/// Returns a stream writing this file.
- virtual IndexOutput* createFile(const char* name);
+ virtual IndexOutput* createOutput(const char* name);
/// Construct a {@link Lock}.
/// @param name the name of the lock file
LuceneLock* makeLock(const char* name);
/// Returns a stream reading an existing file.
- IndexInput* openFile(const char* name);
+ IndexInput* openInput(const char* name);
virtual void close();
Modified: trunk/clucene/src/CLucene/store/TransactionalRAMDirectory.cpp
===================================================================
--- trunk/clucene/src/CLucene/store/TransactionalRAMDirectory.cpp 2006-06-11 07:16:00 UTC (rev 427)
+++ trunk/clucene/src/CLucene/store/TransactionalRAMDirectory.cpp 2006-06-26 00:39:24 UTC (rev 428)
@@ -1,21 +1,14 @@
-/**
- * Copyright 2003-2006 The Apache Software Foundation
- *
- * Licensed under the Apache License, Version 2.0 (the "License");
- * you may not use this file except in compliance with the License.
- * You may obtain a copy of the License at
- *
- * http://www.apache.org/licenses/LICENSE-2.0
- *
- * Unless required by applicable law or agreed to in writing, software
- * distributed under the License is distributed on an "AS IS" BASIS,
- * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
- * See the License for the specific language governing permissions and
- * limitations under the License.
- */
+/*------------------------------------------------------------------------------
+* Copyright (C) 2003-2006 Ben van Klinken and the CLucene Team
+*
+* Distributable under the terms of either the Apache License (Version 2.0) or
+* the GNU Lesser General Public License, as specified in the COPYING file.
+------------------------------------------------------------------------------*/
+#include "CLucene/StdHeader.h"
#include "TransactionalRAMDirectory.h"
CL_NS_DEF(store)
+CL_NS_USE(util)
TransactionalRAMDirectory::TransactionalRAMDirectory():
RAMDirectory(),
@@ -60,7 +53,7 @@
filesToRestoreOnAbort.remove(name, true, true);
files.put(origName, origFile);
}
- bool TransactionalRAMDirectory::transIsOpen() {
+ bool TransactionalRAMDirectory::transIsOpen() const {
return transOpen;
}
@@ -109,7 +102,7 @@
)
{
const char* name = itrDel->first;
- const int32_t nameLength = strlen(name);
+ size_t nameLength = strlen(name);
// Special exception:
// Refrain from deleting a lock's flag file, as that would interfere with
@@ -125,8 +118,8 @@
// Now that any new-since-trans-start files with the same names as
// already-present-at-trans-start files are out of the way, restore each
// file in filesToRestoreOnAbort.
- CL_NS(util)::AStringArrayConst removeTheseWithoutDeletingMem;
- for (FileMap::const_iterator itr = filesToRestoreOnAbort.begin();
+ AStringArrayConst removeTheseWithoutDeletingMem;
+ for (TransFileMap::const_iterator itr = filesToRestoreOnAbort.begin();
itr != filesToRestoreOnAbort.end();
++itr
)
@@ -140,8 +133,7 @@
removeTheseWithoutDeletingMem.push_back(name);
}
- CL_NS(util)::AStringArrayConst::iterator itrRem;
- for (itrRem = removeTheseWithoutDeletingMem.begin();
+ for (AStringArrayConst::iterator itrRem = removeTheseWithoutDeletingMem.begin();
itrRem != removeTheseWithoutDeletingMem.end();
++itrRem
)
@@ -153,11 +145,9 @@
transResolved();
}
- void TransactionalRAMDirectory::deleteFile(const char* name, const bool throwError) {
+ bool TransactionalRAMDirectory::deleteFile(const char* name) {
if (!transOpen) {
-
- RAMDirectory::deleteFile(name, throwError);
- return;
+ return RAMDirectory::deleteFile(name);
}
bool wasOriginalAndWasArchived = archiveOrigFileIfNecessary(name);
@@ -167,8 +157,9 @@
// erase its record in filesToRemoveOnAbort if it was listed there.
filesToRemoveOnAbort.remove(name);
- RAMDirectory::deleteFile(name, throwError);
+ return RAMDirectory::deleteFile(name);
}
+ return true;
}
void TransactionalRAMDirectory::renameFile(const char* from, const char* to) {
@@ -192,14 +183,14 @@
RAMDirectory::renameFile(from, to);
}
- IndexOutput* TransactionalRAMDirectory::createFile(const char* name) {
+ IndexOutput* TransactionalRAMDirectory::createOutput(const char* name) {
if (!transOpen) {
- return RAMDirectory::createFile(name);
+ return RAMDirectory::createOutput(name);
}
bool wasOriginalAndWasArchived = archiveOrigFileIfNecessary(name);
try {
- IndexOutput* ret = RAMDirectory::createFile(name);
+ IndexOutput* ret = RAMDirectory::createOutput(name);
// Importantly, we store a pointer to the filename memory managed by
// files, rather than that passed in by the client (name). We don't make
// an additional copy of the filename's memory because the transactional
Modified: trunk/clucene/src/CLucene/store/TransactionalRAMDirectory.h
===================================================================
--- trunk/clucene/src/CLucene/store/TransactionalRAMDirectory.h 2006-06-11 07:16:00 UTC (rev 427)
+++ trunk/clucene/src/CLucene/store/TransactionalRAMDirectory.h 2006-06-26 00:39:24 UTC (rev 428)
@@ -1,19 +1,9 @@
-/**
- * Copyright 2003-2006 The Apache Software Foundation
- *
- * Licensed under the Apache License, Version 2.0 (the "License");
- * you may not use this file except in compliance with the License.
- * You may obtain a copy of the License at
- *
- * http://www.apache.org/licenses/LICENSE-2.0
- *
- * Unless required by applicable law or agreed to in writing, software
- * distributed under the License is distributed on an "AS IS" BASIS,
- * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
- * See the License for the specific language governing permissions and
- * limitations under the License.
- */
-#include "CLucene/StdHeader.h"
+/*------------------------------------------------------------------------------
+* Copyright (C) 2003-2006 Ben van Klinken and the CLucene Team
+*
+* Distributable under the terms of either the Apache License (Version 2.0) or
+* the GNU Lesser General Public License, as specified in the COPYING file.
+------------------------------------------------------------------------------*/
#ifndef _lucene_store_TransactionalRAMDirectory_
#define _lucene_store_TransactionalRAMDirectory_
@@ -40,8 +30,8 @@
typedef CL_NS(util)::CLSet<const char*, void*, CL_NS(util)::Compare::Char> FilenameSet;
FilenameSet filesToRemoveOnAbort;
- typedef CL_NS(util)::CLSet<const char*, RAMFile*, CL_NS(util)::Compare::Char,CL_NS(util)::Deletor::acArray,CL_NS(util)::Deletor::Object<RAMFile> > FileMap;
- FileMap filesToRestoreOnAbort;
+ typedef CL_NS(util)::CLSet<const char*, RAMFile*, CL_NS(util)::Compare::Char,CL_NS(util)::Deletor::acArray,CL_NS(util)::Deletor::Object<RAMFile> > TransFileMap;
+ TransFileMap filesToRestoreOnAbort;
bool transOpen;
@@ -53,15 +43,15 @@
TransactionalRAMDirectory();
virtual ~TransactionalRAMDirectory();
- bool transIsOpen();
+ bool transIsOpen() const;
void transStart();
void transCommit();
void transAbort();
// Constrained operations:
- void deleteFile(const char* name, const bool throwError = true);
+ bool deleteFile(const char* name);
void renameFile(const char* from, const char* to);
- IndexOutput* createFile(const char* name);
+ IndexOutput* createOutput(const char* name);
void close();
};
Modified: trunk/clucene/src/CLucene/util/Arrays.h
===================================================================
--- trunk/clucene/src/CLucene/util/Arrays.h 2006-06-11 07:16:00 UTC (rev 427)
+++ trunk/clucene/src/CLucene/util/Arrays.h 2006-06-26 00:39:24 UTC (rev 428)
@@ -1,18 +1,9 @@
-/**
- * Copyright 2003-2006 The Apache Software Foundation
- *
- * Licensed under the Apache License, Version 2.0 (the "License");
- * you may not use this file except in compliance with the License.
- * You may obtain a copy of the License at
- *
- * http://www.apache.org/licenses/LICENSE-2.0
- *
- * Unless required by applicable law or agreed to in writing, software
- * distributed under the License is distributed on an "AS IS" BASIS,
- * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
- * See the License for the specific language governing permissions and
- * limitations under the License.
- */
+/*------------------------------------------------------------------------------
+* Copyright (C) 2003-2006 Ben van Klinken and the CLucene Team
+*
+* Distributable under the terms of either the Apache License (Version 2.0) or
+* the GNU Lesser General Public License, as specified in the COPYING file.
+------------------------------------------------------------------------------*/
#ifndef _lucene_util_Arrays_
#define _lucene_util_Arrays_
Modified: trunk/clucene/src/CLucene/util/BitSet.h
===================================================================
--- trunk/clucene/src/CLucene/util/BitSet.h 2006-06-11 07:16:00 UTC (rev 427)
+++ trunk/clucene/src/CLucene/util/BitSet.h 2006-06-26 00:39:24 UTC (rev 428)
@@ -1,18 +1,9 @@
-/**
- * Copyright 2003-2006 The Apache Software Foundation
- *
- * Licensed under the Apache License, Version 2.0 (the "License");
- * you may not use this file except in compliance with the License.
- * You may obtain a copy of the License at
- *
- * http://www.apache.org/licenses/LICENSE-2.0
- *
- * Unless required by applicable law or agreed to in writing, software
- * distributed under the License is distributed on an "AS IS" BASIS,
- * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
- * See the License for the specific language governing permissions and
- * limitations under the License.
- */
+/*------------------------------------------------------------------------------
+* Copyright (C) 2003-2006 Ben van Klinken and the CLucene Team
+*
+* Distributable under the terms of either the Apache License (Version 2.0) or
+* the GNU Lesser General Public License, as specified in the COPYING file.
+------------------------------------------------------------------------------*/
#ifndef _lucene_util_BitSet_
#define _lucene_util_BitSet_
@@ -20,62 +11,42 @@
# pragma once
#endif
+#include "CLucene/store/Directory.h"
CL_NS_DEF(util)
- class BitSet:LUCENE_BASE {
- typedef unsigned long wordType; // base type for a storage word
- int32_t bitsperword; // bits in each word
+class BitSet:LUCENE_BASE {
+ int32_t _size;
+ int32_t _count;
+ uint8_t *bits;
+
+protected:
+ BitSet( const BitSet& copy );
- int32_t _size;
- BitSet::wordType *bits;
-
- BitSet( const BitSet& copy ) :
- bitsperword( copy.bitsperword ),
- _size( copy._size )
- {
- int32_t nwords = _size == 0 ? 0 : (_size - 1) / bitsperword;
- bits = _CL_NEWARRAY(BitSet::wordType, nwords+1);
- memcpy( bits, copy.bits, sizeof(BitSet::wordType)*(nwords+1) );
+public:
+ ///Create a bitset with the specified size
+ BitSet ( int32_t size );
+ BitSet(CL_NS(store)::Directory* d, const char* name);
+ void write(CL_NS(store)::Directory* d, const char* name);
+
+ ///Destructor for the bit set
+ ~BitSet();
+
+ ///get the value of the specified bit
+ inline bool get(const int32_t bit) const{
+ return (bits[bit >> 3] & (1 << (bit & 7))) != 0;
}
-
- public:
- ///Create a bitset with the specified size
- BitSet ( int32_t size ):
- _size(size)
- {
- bitsperword = sizeof(char) * sizeof (BitSet::wordType);
- int32_t nwords = size == 0 ? 0 : (size - 1) / bitsperword;
- bits = _CL_NEWARRAY(BitSet::wordType,nwords+1);
- memset(bits,0,sizeof(BitSet::wordType) * nwords+1);
- }
- ///Destructor for the bit set
- ~BitSet(){
- _CLDELETE_ARRAY(bits);
- }
- ///get the value of the specified bit
- inline bool get(const int32_t bit) const{
- if ( bit < 0 || bit > _size-1 )
- _CLTHROWA(CL_ERR_IllegalArgument, "bit out of range" );
-
- return ((bits[bit / bitsperword] & ((BitSet::wordType)1 << bit % bitsperword)) != 0);
- }
- ///set the value of the specified bit
- void set(const int32_t bit, bool val=true){
- if ( bit < 0 || bit >= _size )
- _CLTHROWA(CL_ERR_IllegalArgument, "bit out of range" );
-
- if (val)
- bits[bit / bitsperword] |= (BitSet::wordType)1 << bit % bitsperword;
- else
- bits[bit / bitsperword] &= ~((BitSet::wordType)1 << bit % bitsperword);
- }
- ///returns the size of the bitset
- int32_t size() const {
- return _size;
- }
- BitSet *clone() const {
- return _CLNEW BitSet( *this );
- }
- };
+
+ ///set the value of the specified bit
+ void set(const int32_t bit, bool val=true);
+
+ ///returns the size of the bitset
+ int32_t size() const;
+
+ /// Returns the total number of one bits in this BitSet. This is efficiently
+ /// computed and cached, so that, if the BitSet is not changed, no
+ /// recomputation is done for repeated calls.
+ int32_t count();
+ BitSet *clone() const;
+};
CL_NS_END
#endif
Modified: trunk/clucene/src/CLucene/util/Equators.cpp
===================================================================
--- trunk/clucene/src/CLucene/util/Equators.cpp 2006-06-11 07:16:00 UTC (rev 427)
+++ trunk/clucene/src/CLucene/util/Equators.cpp 2006-06-26 00:39:24 UTC (rev 428)
@@ -1,18 +1,9 @@
-/**
- * Copyright 2003-2006 The Apache Software Foundation
- *
- * Licensed under the Apache License, Version 2.0 (the "License");
- * you may not use this file except in compliance with the License.
- * You may obtain a copy of the License at
- *
- * http://www.apache.org/licenses/LICENSE-2.0
- *
- * Unless required by applicable law or agreed to in writing, software
- * distributed under the License is distributed on an "AS IS" BASIS,
- * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
- * See the License for the specific language governing permissions and
- * limitations under the License.
- */
+/*------------------------------------------------------------------------------
+* Copyright (C) 2003-2006 Ben van Klinken and the CLucene Team
+*
+* Distributable under the terms of either the Apache License (Version 2.0) or
+* the GNU Lesser General Public License, as specified in the COPYING file.
+------------------------------------------------------------------------------*/
#include "CLucene/StdHeader.h"
#include "Equators.h"
CL_NS_DEF(util)
@@ -43,7 +34,7 @@
// Comparors
////////////////////////////////////////////////////////////////////////////////
-int32_t Compare::Int32::getValue(){ return value; }
+int32_t Compare::Int32::getValue() const{ return value; }
Compare::Int32::Int32(int32_t val){
value = val;
}
@@ -70,7 +61,7 @@
}
-float_t Compare::Float::getValue(){
+float_t Compare::Float::getValue() const{
return value;
}
Compare::Float::Float(float_t val){
@@ -111,7 +102,7 @@
}
#endif
-const TCHAR* Compare::TChar::getValue(){ return s; }
+const TCHAR* Compare::TChar::getValue() const{ return s; }
Compare::TChar::TChar(){
s=NULL;
}
Modified: trunk/clucene/src/CLucene/util/Equators.h
===================================================================
--- trunk/clucene/src/CLucene/util/Equators.h 2006-06-11 07:16:00 UTC (rev 427)
+++ trunk/clucene/src/CLucene/util/Equators.h 2006-06-26 00:39:24 UTC (rev 428)
@@ -1,18 +1,9 @@
-/**
- * Copyright 2003-2006 The Apache Software Foundation
- *
- * Licensed under the Apache License, Version 2.0 (the "License");
- * you may not use this file except in compliance with the License.
- * You may obtain a copy of the License at
- *
- * http://www.apache.org/licenses/LICENSE-2.0
- *
- * Unless required by applicable law or agreed to in writing, software
- * distributed under the License is distributed on an "AS IS" BASIS,
- * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
- * See the License for the specific language governing permissions and
- * limitations under the License.
- */
+/*------------------------------------------------------------------------------
+* Copyright (C) 2003-2006 Ben van Klinken and the CLucene Team
+*
+* Distributable under the terms of either the Apache License (Version 2.0) or
+* the GNU Lesser General Public License, as specified in the COPYING file.
+------------------------------------------------------------------------------*/
#ifndef _lucene_util_Equators_
#define _lucene_util_Equators_
@@ -94,9 +85,9 @@
};
class Int32:public _base, public Comparable{
- int32_t value;
+ int32_t value;
public:
- int32_t getValue();
+ int32_t getValue() const;
Int32(int32_t val);
Int32();
int32_t compareTo(void* o);
@@ -108,7 +99,7 @@
class Float:public Comparable{
float_t value;
public:
- float_t getValue();
+ float_t getValue() const;
Float(float_t val);
int32_t compareTo(void* o);
};
@@ -133,7 +124,7 @@
class TChar: public _base, public Comparable{
const TCHAR* s;
public:
- const TCHAR* getValue();
+ const TCHAR* getValue() const;
TChar();
TChar(const TCHAR* str);
Modified: trunk/clucene/src/CLucene/util/FastCharStream.cpp
===================================================================
--- trunk/clucene/src/CLucene/util/FastCharStream.cpp 2006-06-11 07:16:00 UTC (rev 427)
+++ trunk/clucene/src/CLucene/util/FastCharStream.cpp 2006-06-26 00:39:24 UTC (rev 428)
@@ -1,18 +1,9 @@
-/**
- * Copyright 2003-2006 The Apache Software Foundation
- *
- * Licensed under the Apache License, Version 2.0 (the "License");
- * you may not use this file except in compliance with the License.
- * You may obtain a copy of the License at
- *
- * http://www.apache.org/licenses/LICENSE-2.0
- *
- * Unless required by applicable law or agreed to in writing, software
- * distributed under the License is distributed on an "AS IS" BASIS,
- * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
- * See the License for the specific language governing permissions and
- * limitations under the License.
- */
+/*------------------------------------------------------------------------------
+* Copyright (C) 2003-2006 Ben van Klinken and the CLucene Team
+*
+* Distributable under the terms of either the Apache License (Version 2.0) or
+* the GNU Lesser General Public License, as specified in the COPYING file.
+------------------------------------------------------------------------------*/
#include "CLucene/StdHeader.h"
#include "FastCharStream.h"
@@ -20,22 +11,23 @@
CL_NS_DEF(util)
-const int32_t FastCharStream::maxRewindSize = 8;
+const int32_t FastCharStream::maxRewindSize = LUCENE_MAX_WORD_LEN*2;
FastCharStream::FastCharStream(Reader* reader):
- input(reader),
+ pos(0),
+ rewindPos(0),
+ resetPos(0),
col(1),
- line(1)
+ line(1),
+ input(reader)
{
- pos = 0;
- rewindPos = 0;
input->mark(maxRewindSize);
}
void FastCharStream::readChar(TCHAR &c) {
try{
- int r = input->read();
+ int32_t r = input->read();
if ( r == -1 )
- input = 0;
+ input = NULL;
c = r;
}catch(CLuceneError& err){
if ( err.number() == CL_ERR_IO )
@@ -53,17 +45,19 @@
// this is rather inefficient
// implementing the functions from the java version of
// charstream will be much more efficient.
- if (++pos > maxRewindSize && rewindPos == 0) {
+ ++pos;
+ if ( pos > resetPos + maxRewindSize && rewindPos == 0) {
// move the marker one position (~expensive)
- input->reset();
- input->skip(1);
+ resetPos = pos-(maxRewindSize/2);
+ if ( resetPos != input->reset(resetPos) )
+ _CLTHROWA(CL_ERR_IO,"Unexpected reset() result");
input->mark(maxRewindSize);
- input->skip(maxRewindSize - 1);
+ input->skip((maxRewindSize/2) - 1);
}
TCHAR ch;
readChar(ch);
- if (input == 0) { // eof
+ if (input == NULL) { // eof
return -1;
}
if (rewindPos == 0) {
@@ -86,12 +80,8 @@
_CLTHROWA(CL_ERR_IO,"error : No character can be UnGet");
}
rewindPos++;
- input->reset();
- if (pos > maxRewindSize) {
- input->skip(maxRewindSize - 1);
- } else {
- input->skip(pos - 1);
- }
+
+ input->reset(pos-1);
pos--;
}
@@ -101,15 +91,15 @@
return c;
}
- bool FastCharStream::Eos() {
+ bool FastCharStream::Eos() const {
return input==NULL;
}
- int32_t FastCharStream::Column() {
+ int32_t FastCharStream::Column() const {
return col;
}
- int32_t FastCharStream::Line() {
+ int32_t FastCharStream::Line() const {
return line;
}
CL_NS_END
Modified: trunk/clucene/src/CLucene/util/FastCharStream.h
===================================================================
--- trunk/clucene/src/CLucene/util/FastCharStream.h 2006-06-11 07:16:00 UTC (rev 427)
+++ trunk/clucene/src/CLucene/util/FastCharStream.h 2006-06-26 00:39:24 UTC (rev 428)
@@ -1,18 +1,9 @@
-/**
- * Copyright 2003-2006 The Apache Software Foundation
- *
- * Licensed under the Apache License, Version 2.0 (the "License");
- * you may not use this file except in compliance with the License.
- * You may obtain a copy of the License at
- *
- * http://www.apache.org/licenses/LICENSE-2.0
- *
- * Unless required by applicable law or agreed to in writing, software
- * distributed under the License is distributed on an "AS IS" BASIS,
- * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
- * See the License for the specific language governing permissions and
- * limitations under the License.
- */
+/*------------------------------------------------------------------------------
+* Copyright (C) 2003-2006 Ben van Klinken and the CLucene Team
+*
+* Distributable under the terms of either the Apache License (Version 2.0) or
+* the GNU Lesser General Public License, as specified in the COPYING file.
+------------------------------------------------------------------------------*/
#ifndef _lucene_util_FastCharStream_
#define _lucene_util_FastCharStream_
@@ -30,6 +21,7 @@
static const int32_t maxRewindSize;
int32_t pos;
int32_t rewindPos;
+ int64_t resetPos;
int32_t col;
int32_t line;
// read character from stream return false on error
@@ -50,13 +42,13 @@
/// Returns <b>True</b> if the end of stream was reached.
- bool Eos();
+ bool Eos() const;
/// Gets the current column.
- int32_t Column();
+ int32_t Column() const;
/// Gets the current line.
- int32_t Line();
+ int32_t Line() const;
};
CL_NS_END
#endif
Modified: trunk/clucene/src/CLucene/util/MD5Digester.cpp
===================================================================
--- trunk/clucene/src/CLucene/util/MD5Digester.cpp 2006-06-11 07:16:00 UTC (rev 427)
+++ trunk/clucene/src/CLucene/util/MD5Digester.cpp 2006-06-26 00:39:24 UTC (rev 428)
@@ -32,6 +32,14 @@
// These notices must be retained in any copies of any part of this
// documentation and/or software.
/////////////////////////////////////////////////////////////////////////
+
+/*------------------------------------------------------------------------------
+* Copyright (C) 2003-2006 Ben van Klinken and the CLucene Team
+*
+* Distributable under the terms of either the Apache License (Version 2.0) or
+* the GNU Lesser General Public License, as specified in the COPYING file.
+------------------------------------------------------------------------------*/
+
#include "CLucene/StdHeader.h"
#include "MD5Digester.h"
CL_NS_DEF(util)
@@ -174,7 +182,8 @@
i = 0;
// Buffer remaining input
- memcpy( &m_Buffer[index], &chInput[i], nInputLen-i );
+ if (nInputLen > i)
+ memcpy( &m_Buffer[index], &chInput[i], nInputLen-i );
}
// md5::Finalize
Modified: trunk/clucene/src/CLucene/util/MD5Digester.h
===================================================================
--- trunk/clucene/src/CLucene/util/MD5Digester.h 2006-06-11 07:16:00 UTC (rev 427)
+++ trunk/clucene/src/CLucene/util/MD5Digester.h 2006-06-26 00:39:24 UTC (rev 428)
@@ -33,24 +33,13 @@
// documentation and/or software.
/////////////////////////////////////////////////////////////////////////
+/*------------------------------------------------------------------------------
+* Copyright (C) 2003-2006 Ben van Klinken and the CLucene Team
+*
+* Distributable under the terms of either the Apache License (Version 2.0) or
+* the GNU Lesser General Public License, as specified in the COPYING file.
+------------------------------------------------------------------------------*/
-/* Copyright 2003-2006 The Apache Software Foundation or its licensors, as
- * applicable.
- *
- * Licensed under the Apache License, Version 2.0 (the "License");
- * you may not use this file except in compliance with the License.
- * You may obtain a copy of the License at
- *
- * http://www.apache.org/licenses/LICENSE-2.0
- *
- * Unless required by applicable law or agreed to in writing, software
- * distributed under the License is distributed on an "AS IS" BASIS,
- * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
- * See the License for the specific language governing permissions and
- * limitations under the License.
- */
-
-
#ifndef _lucene_util_MD5Digester_H
#define _lucene_util_MD5Digester_H
Modified: trunk/clucene/src/CLucene/util/Misc.cpp
===================================================================
--- trunk/clucene/src/CLucene/util/Misc.cpp 2006-06-11 07:16:00 UTC (rev 427)
+++ trunk/clucene/src/CLucene/util/Misc.cpp 2006-06-26 00:39:24 UTC (rev 428)
@@ -1,22 +1,13 @@
-/**
- * Copyright 2003-2006 The Apache Software Foundation
- *
- * Licensed under the Apache License, Version 2.0 (the "License");
- * you may not use this file except in compliance with the License.
- * You may obtain a copy of the License at
- *
- * http://www.apache.org/licenses/LICENSE-2.0
- *
- * Unless required by applicable law or agreed to in writing, software
- * distributed under the License is distributed on an "AS IS" BASIS,
- * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
- * See the License for the specific language governing permissions and
- * limitations under the License.
- */
+/*------------------------------------------------------------------------------
+* Copyright (C) 2003-2006 Ben van Klinken and the CLucene Team
+*
+* Distributable under the terms of either the Apache License (Version 2.0) or
+* the GNU Lesser General Public License, as specified in the COPYING file.
+------------------------------------------------------------------------------*/
#include "CLucene/StdHeader.h"
#include "Misc.h"
-#if _CL_TIME_WITH_SYS_TIME
+#ifdef _CL_TIME_WITH_SYS_TIME
# include <sys/time.h>
# include <time.h>
#else
@@ -31,9 +22,6 @@
# include <sys/timeb.h>
#endif
-#include "CLucene/util/StringIntern.h"
-#include "StringBuffer.h"
-
CL_NS_DEF(util)
size_t Misc::ahashCode(const char* str){
@@ -83,12 +71,12 @@
void Misc::_cpywideToChar(const wchar_t* s, char* d, size_t len){
size_t sLen = wcslen(s);
for ( uint32_t i=0;i<len&&i<sLen+1;i++ )
- d[i] = ((uint32_t)s[i]>0x80?LUCENE_OOR_CHAR:(char)s[i]);
+ d[i] = LUCENE_OOR_CHAR(s[i]);
}
void Misc::_cpycharToWide(const char* s, wchar_t* d, size_t len){
size_t sLen = strlen(s);
for ( uint32_t i=0;i<len&&i<sLen+1;i++ )
- d[i] = (TCHAR)s[i];
+ d[i] = s[i];
}
#endif
Modified: trunk/clucene/src/CLucene/util/Misc.h
===================================================================
--- trunk/clucene/src/CLucene/util/Misc.h 2006-06-11 07:16:00 UTC (rev 427)
+++ trunk/clucene/src/CLucene/util/Misc.h 2006-06-26 00:39:24 UTC (rev 428)
@@ -1,18 +1,9 @@
-/**
- * Copyright 2003-2006 The Apache Software Foundation
- *
- * Licensed under the Apache License, Version 2.0 (the "License");
- * you may not use this file except in compliance with the License.
- * You may obtain a copy of the License at
- *
- * http://www.apache.org/licenses/LICENSE-2.0
- *
- * Unless required by applicable law or agreed to in writing, software
- * distributed under the License is distributed on an "AS IS" BASIS,
- * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
- * See the License for the specific language governing permissions and
- * limitations under the License.
- */
+/*------------------------------------------------------------------------------
+* Copyright (C) 2003-2006 Ben van Klinken and the CLucene Team
+*
+* Distributable under the terms of either the Apache License (Version 2.0) or
+* the GNU Lesser General Public License, as specified in the COPYING file.
+------------------------------------------------------------------------------*/
#ifndef _lucene_util_Misc_H
#define _lucene_util_Misc_H
Modified: trunk/clucene/src/CLucene/util/PriorityQueue.h
===================================================================
--- trunk/clucene/src/CLucene/util/PriorityQueue.h 2006-06-11 07:16:00 UTC (rev 427)
+++ trunk/clucene/src/CLucene/util/PriorityQueue.h 2006-06-26 00:39:24 UTC (rev 428)
@@ -1,18 +1,9 @@
-/**
- * Copyright 2003-2006 The Apache Software Foundation
- *
- * Licensed under the Apache License, Version 2.0 (the "License");
- * you may not use this file except in compliance with the License.
- * You may obtain a copy of the License at
- *
- * http://www.apache.org/licenses/LICENSE-2.0
- *
- * Unless required by applicable law or agreed to in writing, software
- * distributed under the License is distributed on an "AS IS" BASIS,
- * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
- * See the License for the specific language governing permissions and
- * limitations under the License.
- */
+/*------------------------------------------------------------------------------
+* Copyright (C) 2003-2006 Ben van Klinken and the CLucene Team
+*
+* Distributable under the terms of either the Apache License (Version 2.0) or
+* the GNU Lesser General Public License, as specified in the COPYING file.
+------------------------------------------------------------------------------*/
#ifndef _lucene_util_PriorityQueue_
#define _lucene_util_PriorityQueue_
Modified: trunk/clucene/src/CLucene/util/Reader.cpp
===================================================================
--- trunk/clucene/src/CLucene/util/Reader.cpp 2006-06-11 07:16:00 UTC (rev 427)
+++ trunk/clucene/src/CLucene/util/Reader.cpp 2006-06-26 00:39:24 UTC (rev 428)
@@ -1,18 +1,9 @@
-/**
- * Copyright 2003-2006 The Apache Software Foundation
- *
- * Licensed under the Apache License, Version 2.0 (the "License");
- * you may not use this file except in compliance with the License.
- * You may obtain a copy of the License at
- *
- * http://www.apache.org/licenses/LICENSE-2.0
- *
- * Unless required by applicable law or agreed to in writing, software
- * distributed under the License is distributed on an "AS IS" BASIS,
- * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
- * See the License for the specific language governing permissions and
- * limitations under the License.
- */
+/*------------------------------------------------------------------------------
+* Copyright (C) 2003-2006 Ben van Klinken and the CLucene Team
+*
+* Distributable under the terms of either the Apache License (Version 2.0) or
+* the GNU Lesser General Public License, as specified in the COPYING file.
+------------------------------------------------------------------------------*/
#include "CLucene/StdHeader.h"
#include "Reader.h"
@@ -26,11 +17,169 @@
Reader(NULL,true){
reader = new jstreams::StringReader<TCHAR>(value,length);
}
-StringReader::StringReader ( TCHAR* value, const int32_t length, bool copyData ):
+StringReader::StringReader ( const TCHAR* value, const int32_t length, bool copyData ):
Reader(NULL,true){
reader = new jstreams::StringReader<TCHAR>(value,length, copyData);
}
StringReader::~StringReader(){
}
+
+FileReader::FileReader ( const char* path, const char* enc,
+ const int32_t cachelen, const int32_t /*cachebuff*/ ):
+ Reader(NULL, true)
+{
+ this->input = new jstreams::FileInputStream(path, cachelen);
+ this->reader = new SimpleInputStreamReader(this->input,enc); //(this is a jstream object)
+}
+
+FileReader::~FileReader (){
+ if (input)
+ delete input;
+}
+int32_t FileReader::read(const TCHAR*& start, int32_t _min, int32_t _max) {
+ return reader->read(start, _min, _max);
+}
+int64_t FileReader::mark(int32_t readlimit) {
+ return reader->mark(readlimit);
+}
+int64_t FileReader::reset(int64_t newpos) {
+ return reader->reset(newpos);
+}
+
+
+
+SimpleInputStreamReader::SimpleInputStreamReader(jstreams::StreamBase<char> *i, const char* enc)
+{
+ finishedDecoding = false;
+ input = i;
+ charbuf.setSize(262);
+ mark(262);
+ charsLeft = 0;
+
+ if ( strcmp(enc,"ASCII")==0 )
+ encoding = ASCII;
+#ifdef _UCS2
+ else if ( strcmp(enc,"UTF-8")==0 )
+ encoding = UTF8;
+ else if ( strcmp(enc,"UCS-2LE")==0 )
+ encoding = UCS2_LE;
+#endif
+ else
+ _CLTHROWA(CL_ERR_IllegalArgument,"Unsupported encoding, use jstreams iconv based instead");
+}
+SimpleInputStreamReader::~SimpleInputStreamReader(){
+ input = NULL;
+}
+int32_t SimpleInputStreamReader::decode(TCHAR* start, int32_t space){
+ // decode from charbuf
+ const char *inbuf = charbuf.readPos;
+ const char *inbufend = charbuf.readPos + charbuf.avail;
+ TCHAR *outbuf = start;
+ const TCHAR *outbufend = outbuf + space;
+
+ if ( encoding == ASCII ){
+ while ( outbuf<outbufend && inbuf<inbufend ){
+ *outbuf = *inbuf;
+ outbuf++;
+ inbuf++;
+ }
+
+#ifdef _UCS2
+ }
+ else if ( encoding == UCS2_LE ){
+ while ( outbuf<outbufend && (inbuf+1)<inbufend ){
+ uint8_t c1 = *inbuf;
+ uint8_t c2 = *(inbuf+1);
+ unsigned short c = c1 | (c2<<8);
+
+ #ifdef _UCS2
+ *outbuf = c;
+ #else
+ *outbuf = LUCENE_OOR_CHAR(c);
+ #endif
+ outbuf++;
+ inbuf+=2;
+ }
+
+ }else if ( encoding == UTF8 ){
+ while ( outbuf<outbufend && inbuf<inbufend ){
+ size_t utflen = lucene_utf8charlen(inbuf);
+ if ( utflen==0 ){
+ error = "Invalid multibyte sequence.";
+ status = jstreams::Error;
+ return -1;
+ }else if ( inbuf+utflen > inbufend ){
+ break; //character incomplete
+ }else{
+ size_t rd = lucene_utf8towc(outbuf,inbuf,inbufend-inbuf);
+ if ( rd == 0 ){
+ error = "Invalid multibyte sequence.";
+ status = jstreams::Error;
+ return -1;
+ }else{
+ inbuf+=rd;
+ outbuf++;
+ }
+ }
+ }
+#endif //_UCS2
+ }else
+ _CLTHROWA(CL_ERR_Runtime,"Unexpected encoding");
+
+ if ( outbuf < outbufend ) {
+ //we had enough room to convert the entire input
+ if ( inbuf < inbufend ) {
+ // last character is incomplete
+ // move from inbuf to the end to the start of
+ // the buffer
+ memmove(charbuf.start, inbuf, inbufend-inbuf);
+ charbuf.readPos = charbuf.start;
+ charbuf.avail = inbufend-inbuf;
+ } else if ( outbuf < outbufend ) { //input sequence was completely converted
+ charbuf.readPos = charbuf.start;
+ charbuf.avail = 0;
+ if (input == NULL) {
+ finishedDecoding = true;
+ }
+ }
+ } else {
+ charbuf.readPos += charbuf.avail - (inbufend-inbuf);
+ charbuf.avail = inbufend-inbuf;
+ }
+ return outbuf-start;
+}
+
+int32_t SimpleInputStreamReader::fillBuffer(TCHAR* start, int32_t space) {
+ // fill up charbuf
+ if (input && charbuf.readPos == charbuf.start) {
+ const char *begin;
+ int32_t numRead;
+ numRead = input->read(begin, 1, charbuf.size - charbuf.avail);
+ //printf("filled up charbuf\n");
+ if (numRead < -1) {
+ error = input->getError();
+ status = jstreams::Error;
+ input = 0;
+ return numRead;
+ }
+ if (numRead < 1) {
+ // signal end of input buffer
+ input = 0;
+ if (charbuf.avail) {
+ error = "stream ends on incomplete character";
+ status = jstreams::Error;
+ }
+ return -1;
+ }
+ // copy data into other buffer
+ memmove( charbuf.start + charbuf.avail, begin, numRead * sizeof(char));
+ charbuf.avail = numRead + charbuf.avail;
+ }
+ // decode
+ int32_t n = decode(start, space);
+ //printf("decoded %i\n", n);
+ return n;
+}
+
CL_NS_END
Modified: trunk/clucene/src/CLucene/util/Reader.h
===================================================================
--- trunk/clucene/src/CLucene/util/Reader.h 2006-06-11 07:16:00 UTC (rev 427)
+++ trunk/clucene/src/CLucene/util/Reader.h 2006-06-26 00:39:24 UTC (rev 428)
@@ -1,18 +1,9 @@
-/**
- * Copyright 2003-2006 The Apache Software Foundation
- *
- * Licensed under the Apache License, Version 2.0 (the "License");
- * you may not use this file except in compliance with the License.
- * You may obtain a copy of the License at
- *
- * http://www.apache.org/licenses/LICENSE-2.0
- *
- * Unless required by applicable law or agreed to in writing, software
- * distributed under the License is distributed on an "AS IS" BASIS,
- * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
- * See the License for the specific language governing permissions and
- * limitations under the License.
- */
+/*------------------------------------------------------------------------------
+* Copyright (C) 2003-2006 Ben van Klinken and the CLucene Team
+*
+* Distributable under the terms of either the Apache License (Version 2.0) or
+* the GNU Lesser General Public License, as specified in the COPYING file.
+------------------------------------------------------------------------------*/
#ifndef _lucene_util_Reader_
#define _lucene_util_Reader_
@@ -22,6 +13,8 @@
#include "streambase.h"
#include "stringreader.h"
+#include "fileinputstream.h"
+#include "bufferedstream.h"
CL_NS_DEF(util)
/**
@@ -32,7 +25,7 @@
public:
bool deleteReader;
jsReader* reader;
-
+
Reader(jsReader* reader, bool deleteReader){
this->reader = reader;
this->deleteReader = deleteReader;
@@ -44,47 +37,51 @@
}
inline int read(){
const TCHAR*b;
- int32_t nread = reader->read(b, 1);
- if ( nread == 0 ) {
+ int32_t nread = reader->read(b, 1,1);
+ if ( nread < -1 ) //if not eof
+ _CLTHROWA(CL_ERR_IO,reader->getError() );
+ else if ( nread == -1 )
return -1;
- } else if ( nread == -1 ) {
- _CLTHROWA(CL_ERR_IO,reader->getError());
- } else {
+ else
return b[0];
- }
}
+ /**
+ * Read at least 1 character, and as much as is conveniently available
+ */
inline int32_t read(const TCHAR*& start){
- int32_t nread = reader->read(start);
- if ( nread == 0 )
- return -1;
- else if ( nread == -1 )
+ int32_t nread = reader->read(start,1,0);
+ if ( nread < -1 ) //if not eof
_CLTHROWA(CL_ERR_IO,reader->getError());
else
return nread;
}
inline int32_t read(const TCHAR*& start, int32_t len){
- int32_t nread = reader->read(start, len);
- if ( nread == 0 )
- return -1;
- else if ( nread == -1 )
+ int32_t nread = reader->read(start, len, len);
+ if ( nread < -1 ) //if not eof
_CLTHROWA(CL_ERR_IO,reader->getError());
else
return nread;
}
inline int64_t skip(int64_t ntoskip){
int64_t skipped = reader->skip(ntoskip);
- if ( skipped == -1 )
+ if ( skipped < 0 )
_CLTHROWA(CL_ERR_IO,reader->getError());
- return skipped;
+ else
+ return skipped;
}
- inline void mark(int32_t readAheadlimit){
- reader->mark(readAheadlimit);
+ inline int64_t mark(int32_t readAheadlimit){
+ int64_t pos = reader->mark(readAheadlimit);
+ if ( pos < 0 )
+ _CLTHROWA(CL_ERR_IO,reader->getError());
+ else
+ return pos;
}
- jstreams::StreamStatus reset(){
- jstreams::StreamStatus s = reader->reset();
- if ( s == jstreams::Error )
+ int64_t reset(int64_t pos){
+ int64_t r = reader->reset(pos);
+ if ( r < 0 )
_CLTHROWA(CL_ERR_IO,reader->getError());
- return s;
+ else
+ return r;
}
};
@@ -93,9 +90,49 @@
public:
StringReader ( const TCHAR* value );
StringReader ( const TCHAR* value, const int32_t length );
- StringReader ( TCHAR* value, const int32_t length, bool copyData );
+ StringReader ( const TCHAR* value, const int32_t length, bool copyData );
~StringReader();
};
+/** A very simple inputstreamreader implementation. For a
+* more complete InputStreamReader, use the jstreams version
+* located in the contrib package
+*/
+class SimpleInputStreamReader: public jstreams::BufferedInputStream<TCHAR>{
+ int32_t decode(TCHAR* start, int32_t space);
+ int encoding;
+ enum{
+ ASCII=1,
+ UTF8=2,
+ UCS2_LE=3
+ };
+ bool finishedDecoding;
+ jstreams::StreamBase<char>* input;
+ int32_t charsLeft;
+
+ jstreams::InputStreamBuffer<char> charbuf;
+ int32_t fillBuffer(TCHAR* start, int32_t space);
+public:
+ SimpleInputStreamReader(jstreams::StreamBase<char> *i, const char* encoding);
+ ~SimpleInputStreamReader();
+};
+
+/**
+* A helper class which constructs a FileReader with a specified
+* simple encodings, or a given inputstreamreader
+*/
+class FileReader: public Reader{
+ jstreams::FileInputStream* input;
+public:
+ FileReader ( const char* path, const char* enc,
+ const int32_t cachelen = 13,
+ const int32_t cachebuff = 14 ); //todo: optimise these cache values
+ ~FileReader ();
+
+ int32_t read(const TCHAR*& start, int32_t _min, int32_t _max);
+ int64_t mark(int32_t readlimit);
+ int64_t reset(int64_t);
+};
+
CL_NS_END
#endif
Modified: trunk/clucene/src/CLucene/util/StringBuffer.cpp
===================================================================
--- trunk/clucene/src/CLucene/util/StringBuffer.cpp 2006-06-11 07:16:00 UTC (rev 427)
+++ trunk/clucene/src/CLucene/util/StringBuffer.cpp 2006-06-26 00:39:24 UTC (rev 428)
@@ -1,18 +1,9 @@
-/**
- * Copyright 2003-2006 The Apache Software Foundation
- *
- * Licensed under the Apache License, Version 2.0 (the "License");
- * you may not use this file except in compliance with the License.
- * You may obtain a copy of the License at
- *
- * http://www.apache.org/licenses/LICENSE-2.0
- *
- * Unless required by applicable law or agreed to in writing, software
- * distributed under the License is distributed on an "AS IS" BASIS,
- * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
- * See the License for the specific language governing permissions and
- * limitations under the License.
- */
+/*------------------------------------------------------------------------------
+* Copyright (C) 2003-2006 Ben van Klinken and the CLucene Team
+*
+* Distributable under the terms of either the Apache License (Version 2.0) or
+* the GNU Lesser General Public License, as specified in the COPYING file.
+------------------------------------------------------------------------------*/
#include "CLucene/StdHeader.h"
#include "StringBuffer.h"
#include "Misc.h"
@@ -80,10 +71,11 @@
// Func - Destructor
// Pre - true
// Post - Instanc has been destroyed
-
- if(buffer!=NULL && bufferOwner){
- _CLDELETE_CARRAY(buffer);
- }
+
+ if( bufferOwner ){
+ _CLDELETE_CARRAY(buffer);
+ }else
+ buffer = NULL;
}
void StringBuffer::clear(){
//Func - Clears the Stringbuffer and resets it to it default empty state
@@ -91,14 +83,8 @@
//Post - pre(buffer) has been destroyed and a new one has been allocated
//Destroy the current buffer if present
- if(buffer!=NULL && bufferOwner){
- _CLDELETE_CARRAY(buffer);
- }else if ( bufferOwner ){
- buffer[0]=0;
- len = 0;
- return;
- }
-
+ _CLDELETE_CARRAY(buffer);
+
//Initialize
len = 0;
bufferLength = LUCENE_DEFAULT_TOKEN_BUFFER_SIZE;
@@ -131,7 +117,7 @@
append(value, _tcslen(value));
}
- void StringBuffer::append(const TCHAR* value, const int32_t appendedLength) {
+ void StringBuffer::append(const TCHAR* value, size_t appendedLength) {
//Func - Appends a copy of the string value
//Pre - value != NULL
// appendedLength contains the length of the string value which is to be appended
@@ -141,7 +127,7 @@
if (len + appendedLength + 1 > bufferLength){
//Have the size of the current string buffer increased because it is too small
growBuffer(len + appendedLength + 1);
- }
+ }
//Copy the string value into the buffer at postion len
_tcsncpy(buffer + len, value, appendedLength);
@@ -204,7 +190,7 @@
prepend(value, _tcslen(value));
}
- void StringBuffer::prepend(const TCHAR* value, const int32_t prependedLength) {
+ void StringBuffer::prepend(const TCHAR* value, const size_t prependedLength) {
//Func - Puts a copy of the string value in front of the string in the StringBuffer
//Pre - value != NULL
// prependedLength contains the length of the string value which is to be prepended
@@ -226,14 +212,14 @@
len += prependedLength;
}
- int32_t StringBuffer::length() {
+ int32_t StringBuffer::length() const{
//Func - Returns the length of the string in the StringBuffer
//Pre - true
//Post - The length len of the string in the buffer has been returned
return len;
}
- TCHAR* StringBuffer::toString() {
+ TCHAR* StringBuffer::toString(){
//Func - Returns a copy of the current string in the StringBuffer sized equal to the length of the string
// in the StringBuffer.
//Pre - true
@@ -246,7 +232,7 @@
_tcsncpy(ret, buffer, len);
//terminate the string
ret[len] = '\0';
- }
+ }
//return the the copy
return ret;
}
Modified: trunk/clucene/src/CLucene/util/StringBuffer.h
===================================================================
--- trunk/clucene/src/CLucene/util/StringBuffer.h 2006-06-11 07:16:00 UTC (rev 427)
+++ trunk/clucene/src/CLucene/util/StringBuffer.h 2006-06-26 00:39:24 UTC (rev 428)
@@ -1,18 +1,9 @@
-/**
- * Copyright 2003-2006 The Apache Software Foundation
- *
- * Licensed under the Apache License, Version 2.0 (the "License");
- * you may not use this file except in compliance with the License.
- * You may obtain a copy of the License at
- *
- * http://www.apache.org/licenses/LICENSE-2.0
- *
- * Unless required by applicable law or agreed to in writing, software
- * distributed under the License is distributed on an "AS IS" BASIS,
- * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
- * See the License for the specific language governing permissions and
- * limitations under the License.
- */
+/*------------------------------------------------------------------------------
+* Copyright (C) 2003-2006 Ben van Klinken and the CLucene Team
+*
+* Distributable under the terms of either the Apache License (Version 2.0) or
+* the GNU Lesser General Public License, as specified in the COPYING file.
+------------------------------------------------------------------------------*/
#ifndef _lucene_util_StringBuffer_
#define _lucene_util_StringBuffer_
@@ -44,7 +35,7 @@
///Appends a copy of the string value
void append(const TCHAR* value);
///Appends a copy of the string value
- void append(const TCHAR* value, const int32_t appendedLength);
+ void append(const TCHAR* value, size_t appendedLength);
///Appends an integer (after conversion to a character string)
void appendInt(const int32_t value);
///Appends a float_t (after conversion to a character string)
@@ -52,13 +43,13 @@
///Puts a copy of the string value in front of the current string in the StringBuffer
void prepend(const TCHAR* value);
///Puts a copy of the string value in front of the current string in the StringBuffer
- void prepend(const TCHAR* value, const int32_t prependedLength);
+ void prepend(const TCHAR* value, size_t prependedLength);
///Contains the length of string in the StringBuffer
///Public so that analyzers can edit the length directly
int32_t len;
///Returns the length of the string in the StringBuffer
- int32_t length();
+ int32_t length() const;
///Returns a copy of the current string in the StringBuffer
TCHAR* toString();
///Returns a null terminated reference to the StringBuffer's text
Modified: trunk/clucene/src/CLucene/util/StringIntern.cpp
===================================================================
--- trunk/clucene/src/CLucene/util/StringIntern.cpp 2006-06-11 07:16:00 UTC (rev 427)
+++ trunk/clucene/src/CLucene/util/StringIntern.cpp 2006-06-26 00:39:24 UTC (rev 428)
@@ -1,18 +1,9 @@
-/**
- * Copyright 2003-2006 The Apache Software Foundation
- *
- * Licensed under the Apache License, Version 2.0 (the "License");
- * you may not use this file except in compliance with the License.
- * You may obtain a copy of the License at
- *
- * http://www.apache.org/licenses/LICENSE-2.0
- *
- * Unless required by applicable law or agreed to in writing, software
- * distributed under the License is distributed on an "AS IS" BASIS,
- * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
- * See the License for the specific language governing permissions and
- * limitations under the License.
- */
+/*------------------------------------------------------------------------------
+* Copyright (C) 2003-2006 Ben van Klinken and the CLucene Team
+*
+* Distributable under the terms of either the Apache License (Version 2.0) or
+* the GNU Lesser General Public License, as specified in the COPYING file.
+------------------------------------------------------------------------------*/
#include "CLucene/StdHeader.h"
#include "StringIntern.h"
CL_NS_DEF(util)
@@ -31,7 +22,7 @@
__strintrntype::iterator itr = stringaPool.begin();
while ( itr != stringaPool.end() ){
printf(" %s (%d)\n",(itr->first), (itr->second));
- itr++;
+ ++itr;
}
}
@@ -40,7 +31,7 @@
__wcsintrntype::iterator itr = stringPool.begin();
while ( itr != stringPool.end() ){
_tprintf(_T(" %s (%d)\n"),(itr->first), (itr->second));
- itr++;
+ ++itr;
}
}
#endif
Modified: trunk/clucene/src/CLucene/util/StringIntern.h
===================================================================
--- trunk/clucene/src/CLucene/util/StringIntern.h 2006-06-11 07:16:00 UTC (rev 427)
+++ trunk/clucene/src/CLucene/util/StringIntern.h 2006-06-26 00:39:24 UTC (rev 428)
@@ -1,18 +1,9 @@
-/**
- * Copyright 2003-2006 The Apache Software Foundation
- *
- * Licensed under the Apache License, Version 2.0 (the "License");
- * you may not use this file except in compliance with the License.
- * You may obtain a copy of the License at
- *
- * http://www.apache.org/licenses/LICENSE-2.0
- *
- * Unless required by applicable law or agreed to in writing, software
- * distributed under the License is distributed on an "AS IS" BASIS,
- * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
- * See the License for the specific language governing permissions and
- * limitations under the License.
- */
+/*------------------------------------------------------------------------------
+* Copyright (C) 2003-2006 Ben van Klinken and the CLucene Team
+*
+* Distributable under the terms of either the Apache License (Version 2.0) or
+* the GNU Lesser General Public License, as specified in the COPYING file.
+------------------------------------------------------------------------------*/
#ifndef _lucene_util_StringIntern_H
#define _lucene_util_StringIntern_H
@@ -22,8 +13,8 @@
#include "VoidMap.h"
CL_NS_DEF(util)
-typedef CL_NS(util)::CLHashMap<const TCHAR*,int,Compare::TChar,Deletor::tcArray ,Deletor::DummyInt32 > __wcsintrntype;
-typedef CL_NS(util)::CLHashMap<const char*,int,Compare::Char,Deletor::acArray ,Deletor::DummyInt32 > __strintrntype;
+typedef CL_NS(util)::CLHashMap<const TCHAR*,int,CL_NS(util)::Compare::TChar,CL_NS(util)::Deletor::tcArray, CL_NS(util)::Deletor::DummyInt32 > __wcsintrntype;
+typedef CL_NS(util)::CLHashMap<const char*,int,CL_NS(util)::Compare::Char,CL_NS(util)::Deletor::acArray, CL_NS(util)::Deletor::DummyInt32 > __strintrntype;
/** Functions for intern'ing strings. This
is a process of pooling strings thus using less memory,
Modified: trunk/clucene/src/CLucene/util/VoidList.h
===================================================================
--- trunk/clucene/src/CLucene/util/VoidList.h 2006-06-11 07:16:00 UTC (rev 427)
+++ trunk/clucene/src/CLucene/util/VoidList.h 2006-06-26 00:39:24 UTC (rev 428)
@@ -1,18 +1,9 @@
-/**
- * Copyright 2003-2006 The Apache Software Foundation
- *
- * Licensed under the Apache License, Version 2.0 (the "License");
- * you may not use this file except in compliance with the License.
- * You may obtain a copy of the License at
- *
- * http://www.apache.org/licenses/LICENSE-2.0
- *
- * Unless required by applicable law or agreed to in writing, software
- * distributed under the License is distributed on an "AS IS" BASIS,
- * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
- * See the License for the specific language governing permissions and
- * limitations under the License.
- */
+/*------------------------------------------------------------------------------
+* Copyright (C) 2003-2006 Ben van Klinken and the CLucene Team
+*
+* Distributable under the terms of either the Apache License (Version 2.0) or
+* the GNU Lesser General Public License, as specified in the COPYING file.
+------------------------------------------------------------------------------*/
#ifndef _lucene_util_VoidList_
#define _lucene_util_VoidList_
@@ -20,6 +11,8 @@
# pragma once
#endif
+#include "Equators.h"
+
CL_NS_DEF(util)
template<typename _kt,typename _base,typename _valueDeletor>
@@ -89,7 +82,7 @@
iterator itr = base::begin();
while ( itr != base::end() ){
_valueDeletor::doDelete(*itr);
- itr++;
+ ++itr;
}
}
base::clear();
Modified: trunk/clucene/src/CLucene/util/VoidMap.h
===================================================================
--- trunk/clucene/src/CLucene/util/VoidMap.h 2006-06-11 07:16:00 UTC (rev 427)
+++ trunk/clucene/src/CLucene/util/VoidMap.h 2006-06-26 00:39:24 UTC (rev 428)
@@ -1,18 +1,9 @@
-/**
- * Copyright 2003-2006 The Apache Software Foundation
- *
- * Licensed under the Apache License, Version 2.0 (the "License");
- * you may not use this file except in compliance with the License.
- * You may obtain a copy of the License at
- *
- * http://www.apache.org/licenses/LICENSE-2.0
- *
- * Unless required by applicable law or agreed to in writing, software
- * distributed under the License is distributed on an "AS IS" BASIS,
- * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
- * See the License for the specific language governing permissions and
- * limitations under the License.
- */
+/*------------------------------------------------------------------------------
+* Copyright (C) 2003-2006 Ben van Klinken and the CLucene Team
+*
+* Distributable under the terms of either the Apache License (Version 2.0) or
+* the GNU Lesser General Public License, as specified in the COPYING file.
+------------------------------------------------------------------------------*/
#ifndef _lucene_util_VoidMap_
#define _lucene_util_VoidMap_
@@ -37,7 +28,7 @@
typedef typename _base::iterator iterator;
typedef typename _base::const_iterator const_iterator;
- typedef pair<_kt, _vt> _pair;
+ typedef CL_NS_STD(pair)<_kt, _vt> _pair;
///Default constructor for the __CLMap
__CLMap ():
@@ -135,7 +126,7 @@
_KeyDeletor::doDelete(itr->first);
if ( dv )
_ValueDeletor::doDelete(itr->second);
- itr++;
+ ++itr;
}
}
base::clear();
Modified: trunk/clucene/src/CLucene/util/dirent.cpp
===================================================================
--- trunk/clucene/src/CLucene/util/dirent.cpp 2006-06-11 07:16:00 UTC (rev 427)
+++ trunk/clucene/src/CLucene/util/dirent.cpp 2006-06-26 00:39:24 UTC (rev 428)
@@ -1,30 +1,19 @@
-/**
- * Copyright 2003-2006 The Apache Software Foundation
- *
- * Licensed under the Apache License, Version 2.0 (the "License");
- * you may not use this file except in compliance with the License.
- * You may obtain a copy of the License at
- *
- * http://www.apache.org/licenses/LICENSE-2.0
- *
- * Unless required by applicable law or agreed to in writing, software
- * distributed under the License is distributed on an "AS IS" BASIS,
- * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
- * See the License for the specific language governing permissions and
- * limitations under the License.
- */
+/*------------------------------------------------------------------------------
+* Copyright (C) 2003-2006 Ben van Klinken and the CLucene Team
+*
+* Distributable under the terms of either the Apache License (Version 2.0) or
+* the GNU Lesser General Public License, as specified in the COPYING file.
+------------------------------------------------------------------------------*/
#include "CLucene/StdHeader.h"
#if !defined(_CL_HAVE_DIRENT_H) && !defined(_CL_HAVE_SYS_NDIR_H) && !defined(_CL_HAVE_SYS_DIR_H) && !defined(_CL_HAVE_NDIR_H)
#include "dirent.h"
-CL_NS_DEF(util)
-
DIR *
opendir (const char *szPath)
{
DIR *nd;
- char szFullPath[CL_MAX_DIR];
+ char szFullPath[CL_MAX_PATH];
errno = 0;
@@ -56,7 +45,7 @@
}
/* Make an absolute pathname. */
- _fullpath (szFullPath, szPath, CL_MAX_DIR);
+ _realpath(szPath,szFullPath);
/* Allocate enough space to store DIR structure and the complete
* directory path given. */
@@ -215,6 +204,5 @@
return rc;
}
-CL_NS_END
#endif //HAVE_DIRENT_H
Modified: trunk/clucene/src/CLucene/util/dirent.h
===================================================================
--- trunk/clucene/src/CLucene/util/dirent.h 2006-06-11 07:16:00 UTC (rev 427)
+++ trunk/clucene/src/CLucene/util/dirent.h 2006-06-26 00:39:24 UTC (rev 428)
@@ -1,18 +1,9 @@
-/**
- * Copyright 2003-2006 The Apache Software Foundation
- *
- * Licensed under the Apache License, Version 2.0 (the "License");
- * you may not use this file except in compliance with the License.
- * You may obtain a copy of the License at
- *
- * http://www.apache.org/licenses/LICENSE-2.0
- *
- * Unless required by applicable law or agreed to in writing, software
- * distributed under the License is distributed on an "AS IS" BASIS,
- * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
- * See the License for the specific language governing permissions and
- * limitations under the License.
- */
+/*------------------------------------------------------------------------------
+* Copyright (C) 2003-2006 Ben van Klinken and the CLucene Team
+*
+* Distributable under the terms of either the Apache License (Version 2.0) or
+* the GNU Lesser General Public License, as specified in the COPYING file.
+------------------------------------------------------------------------------*/
#ifndef lucene_util_dirent_H
#define lucene_util_dirent_H
@@ -22,7 +13,6 @@
#if !defined(_CL_HAVE_DIRENT_H) && !defined(_CL_HAVE_SYS_NDIR_H) && !defined(_CL_HAVE_SYS_DIR_H) && !defined(_CL_HAVE_NDIR_H)
-CL_NS_DEF(util)
/**
\unit
* dirent.c
@@ -94,8 +84,6 @@
int32_t closedir (DIR* dir);
-CL_NS_END
-
#elif defined (_CL_HAVE_DIRENT_H)
# include <dirent.h>
# define NAMLEN(dirent) strlen((dirent)->d_name)
Modified: trunk/clucene/src/CLucene/util/jstreamsconfig.h
===================================================================
--- trunk/clucene/src/CLucene/util/jstreamsconfig.h 2006-06-11 07:16:00 UTC (rev 427)
+++ trunk/clucene/src/CLucene/util/jstreamsconfig.h 2006-06-26 00:39:24 UTC (rev 428)
@@ -1,18 +1,9 @@
-/**
- * Copyright 2003-2006 The Apache Software Foundation
- *
- * Licensed under the Apache License, Version 2.0 (the "License");
- * you may not use this file except in compliance with the License.
- * You may obtain a copy of the License at
- *
- * http://www.apache.org/licenses/LICENSE-2.0
- *
- * Unless required by applicable law or agreed to in writing, software
- * distributed under the License is distributed on an "AS IS" BASIS,
- * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
- * See the License for the specific language governing permissions and
- * limitations under the License.
- */
+/*------------------------------------------------------------------------------
+* Copyright (C) 2003-2006 Ben van Klinken and the CLucene Team
+*
+* Distributable under the terms of either the Apache License (Version 2.0) or
+* the GNU Lesser General Public License, as specified in the COPYING file.
+------------------------------------------------------------------------------*/
//this is just a compatibility header for jstreams
#include "CLucene/StdHeader.h"
Modified: trunk/clucene/src/CLucene/util/streambase.h
===================================================================
--- trunk/clucene/src/CLucene/util/streambase.h 2006-06-11 07:16:00 UTC (rev 427)
+++ trunk/clucene/src/CLucene/util/streambase.h 2006-06-26 00:39:24 UTC (rev 428)
@@ -1,18 +1,9 @@
-/**
- * Copyright 2003-2006 The Apache Software Foundation
- *
- * Licensed under the Apache License, Version 2.0 (the "License");
- * you may not use this file except in compliance with the License.
- * You may obtain a copy of the License at
- *
- * http://www.apache.org/licenses/LICENSE-2.0
- *
- * Unless required by applicable law or agreed to in writing, software
- * distributed under the License is distributed on an "AS IS" BASIS,
- * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
- * See the License for the specific language governing permissions and
- * limitations under the License.
- */
+/*------------------------------------------------------------------------------
+* Copyright (C) 2003-2006 Jos van den Oever
+*
+* Distributable under the terms of either the Apache License (Version 2.0) or
+* the GNU Lesser General Public License, as specified in the COPYING file.
+------------------------------------------------------------------------------*/
#ifndef STREAMBASE_H
#define STREAMBASE_H
@@ -67,9 +58,9 @@
* end of the stream has been reached. If -1 is returned, an error
* has occured.
**/
- virtual int32_t read(const T*& start) = 0;
+ // virtual int32_t read(const T*& start) = 0;
/**
- * @brief Reads @p ntoread characters from the stream and sets \a start to
+ * @brief Reads characters from the stream and sets \a start to
* the first character that was read.
*
* If @p ntoread is @c 0, then at least one character will be read.
@@ -80,11 +71,15 @@
* is undefined.
* @param ntoread The number of characters to read from the stream. If
* @p is @c 0 the stream reads at least 1 character.
- * @return the number of characters that were read. If 0 is returned, the
- * end of the stream has been reached. If -1 is returned, an error
+ * @return the number of characters that were read. If -1 is returned, the
+ * end of the stream has been reached. If -2 is returned, an error
* has occured.
**/
- virtual int32_t read(const T*& start, int32_t ntoread) = 0;
+ virtual int32_t read(const T*& start, int32_t min, int32_t max) = 0;
+ /**
+ * Same as read(const T*& start, int32_t ntoread), but may read more.
+ **/
+// virtual int32_t readAtLeast(const T*& start, int32_t ntoread) = 0;
/* the available value may be greater than the actual value if
the encoding is a variable one (such as utf8 or unicode) */
/**
@@ -111,12 +106,17 @@
* When calling the method mark more than once at the same position in the
* stream, the call with the largest value for \p readlimit is defining.
**/
- virtual StreamStatus mark(int32_t readlimit) = 0;
+ virtual int64_t mark(int32_t readlimit) = 0;
/**
- * \short Repositions this stream to the position at the time the mark
- * method was last called on this input stream.
+ * \short Repositions this stream to given requested position.
* The general contract of reset is:
- * - If the method mark has not been called since the stream was created,
+ * - Reset is guaranteed to work after a successfull call to read(),
+ * when new position is in the range of the data returned by read().
+ * This means that @p pos must lie between than the position
+ * corresponding to the @p start parameter (x) of the @r read function
+ * and the position corresponding to the last position in the returned
+ * buffer (x + @p nread).
+ * if If the method mark has not been called since the stream was created,
* or the number of bytes read from the stream since mark was last
* called is larger than the argument to mark at that last call, then
* Error is returned.
@@ -127,28 +127,27 @@
* would have been the next input data as of the time of the call to
* reset.
**/
- virtual StreamStatus reset() = 0;
+ virtual int64_t reset(int64_t pos) = 0;
};
-
+#define SKIPSTEP 1024
template <class T>
int64_t
StreamBase<T>::skip(int64_t ntoskip) {
- static const int32_t skipstep = 1024;
const T *begin;
int32_t nread;
int64_t skipped = 0;
while (ntoskip) {
- int32_t step = (int32_t)((ntoskip > skipstep) ?skipstep :ntoskip);
- nread = read(begin, step);
- if (nread < 0) {
- return skipped;
- } else if (nread < step) {
- status = Eof;
+ int32_t step = (int32_t)((ntoskip > SKIPSTEP) ?SKIPSTEP :ntoskip);
+ nread = read(begin, 1, step);
+ if (nread < -1 ) {
+ // an error occurred
+ return nread;
+ } else if (nread < 1) {
ntoskip = 0;
} else {
+ skipped += nread;
ntoskip -= nread;
}
- skipped += nread;
}
return skipped;
}
Modified: trunk/clucene/src/CLucene/util/stringreader.h
===================================================================
--- trunk/clucene/src/CLucene/util/stringreader.h 2006-06-11 07:16:00 UTC (rev 427)
+++ trunk/clucene/src/CLucene/util/stringreader.h 2006-06-26 00:39:24 UTC (rev 428)
@@ -1,123 +1,103 @@
-/**
- * Copyright 2003-2006 The Apache Software Foundation
- *
- * Licensed under the Apache License, Version 2.0 (the "License");
- * you may not use this file except in compliance with the License.
- * You may obtain a copy of the License at
- *
- * http://www.apache.org/licenses/LICENSE-2.0
- *
- * Unless required by applicable law or agreed to in writing, software
- * distributed under the License is distributed on an "AS IS" BASIS,
- * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
- * See the License for the specific language governing permissions and
- * limitations under the License.
- */
-#ifndef STRINGREADER_H
-#define STRINGREADER_H
-
-#include "streambase.h"
-
-namespace jstreams {
-
-template <class T>
-class StringReader : public StreamBase<T> {
-private:
- int64_t markpt;
- T* data;
- bool dataowner;
- StringReader(const StringReader<T>&);
- void operator=(const StringReader<T>&);
-public:
- StringReader(const T* value, int32_t length = -1, bool copy = true);
- ~StringReader();
- int32_t read(const T*& start);
- int32_t read(const T*& start, int32_t ntoread);
- int64_t skip(int64_t ntoskip);
- StreamStatus mark(int32_t readlimit);
- StreamStatus reset();
-};
-
-template <class T>
-StringReader<T>::StringReader(const T* value, int32_t length, bool copy)
- : markpt(0), dataowner(copy) {
- if (length < 0) {
- if (sizeof(T) > 1) {
- length = wcslen((const wchar_t*)value);
- } else {
- length = strlen((const char*)value);
- }
- }
- StreamBase<T>::size = length;
- if (copy) {
- data = new T[length+1];
- size_t s = (size_t)(length*sizeof(T));
- memcpy(data, value, s);
- data[length] = 0;
- } else {
- // casting away const is ok, because we don't write anyway
- data = (T*)value;
- }
-}
-template <class T>
-StringReader<T>::~StringReader() {
- if (dataowner) {
- delete [] data;
- }
-}
-template <class T>
-int32_t
-StringReader<T>::read(const T*& start) {
- StreamBase<T>::status = Eof;
- int64_t left = StreamBase<T>::size - StreamBase<T>::position;
- if (left == 0) {
- return 0;
- }
- int32_t nread = (int32_t)((left > INT32MAX) ?INT32MAX :left);
- start = data + StreamBase<T>::position;
- StreamBase<T>::position = StreamBase<T>::size;
- return nread;
-}
-template <class T>
-int32_t
-StringReader<T>::read(const T*& start, int32_t ntoread) {
- int64_t left = StreamBase<T>::size - StreamBase<T>::position;
- if (left == 0) {
- StreamBase<T>::status = Eof;
- return 0;
- }
- int32_t nread = (int32_t)(ntoread > left) ?left :ntoread;
- start = data + StreamBase<T>::position;
- StreamBase<T>::position += nread;
- if (StreamBase<T>::position == StreamBase<T>::size) {
- StreamBase<T>::status = Eof;
- }
- return nread;
-}
-template <class T>
-int64_t
-StringReader<T>::skip(int64_t ntoskip) {
- const T* start;
- return read(start, ntoskip);
-}
-template <class T>
-StreamStatus
-StringReader<T>::mark(int32_t /*readlimit*/) {
- markpt = StreamBase<T>::position;
- return Ok;
-}
-template <class T>
-StreamStatus
-StringReader<T>::reset() {
- StreamBase<T>::position = markpt;
- if (markpt == StreamBase<T>::size) {
- StreamBase<T>::status = Eof;
- } else {
- StreamBase<T>::status = Ok;
- }
- return Ok;
-}
-
-} // end namespace jstreams
-
-#endif
+/*------------------------------------------------------------------------------
+* Copyright (C) 2003-2006 Jos van den Oever
+*
+* Distributable under the terms of either the Apache License (Version 2.0) or
+* the GNU Lesser General Public License, as specified in the COPYING file.
+------------------------------------------------------------------------------*/
+#ifndef STRINGREADER_H
+#define STRINGREADER_H
+
+#include "streambase.h"
+
+namespace jstreams {
+
+template <class T>
+class StringReader : public StreamBase<T> {
+private:
+ int64_t markpt;
+ T* data;
+ bool dataowner;
+ StringReader(const StringReader<T>&);
+ void operator=(const StringReader<T>&);
+public:
+ StringReader(const T* value, int32_t length = -1, bool copy = true);
+ ~StringReader();
+ int32_t read(const T*& start, int32_t min, int32_t max);
+ int64_t skip(int64_t ntoskip);
+ int64_t mark(int32_t readlimit);
+ int64_t reset(int64_t pos);
+};
+
+template <class T>
+StringReader<T>::StringReader(const T* value, int32_t length, bool copy)
+ : markpt(0), dataowner(copy) {
+ if (length < 0) {
+ length = 0;
+ while ( value[length] != '\0' )
+ length++;
+ }
+ StreamBase<T>::size = length;
+ if (copy) {
+ data = new T[length+1];
+ size_t s = (size_t)(length*sizeof(T));
+ memcpy(data, value, s);
+ data[length] = 0;
+ } else {
+ // casting away const is ok, because we don't write anyway
+ data = (T*)value;
+ }
+}
+template <class T>
+StringReader<T>::~StringReader() {
+ if (dataowner) {
+ delete [] data;
+ }
+}
+template <class T>
+int32_t
+StringReader<T>::read(const T*& start, int32_t min, int32_t max) {
+ int64_t left = StreamBase<T>::size - StreamBase<T>::position;
+ if (left == 0) {
+ StreamBase<T>::status = Eof;
+ return -1;
+ }
+ if (min < 0) min = 0;
+ int32_t nread = (int32_t)(max > left || max < 1) ?left :max;
+ start = data + StreamBase<T>::position;
+ StreamBase<T>::position += nread;
+ if (StreamBase<T>::position == StreamBase<T>::size) {
+ StreamBase<T>::status = Eof;
+ }
+ return nread;
+}
+template <class T>
+int64_t
+StringReader<T>::skip(int64_t ntoskip) {
+ const T* start;
+ return read(start, ntoskip, ntoskip);
+}
+template <class T>
+int64_t
+StringReader<T>::mark(int32_t /*readlimit*/) {
+ markpt = StreamBase<T>::position;
+ return markpt;
+}
+template <class T>
+int64_t
+StringReader<T>::reset(int64_t newpos) {
+ if (newpos < 0) {
+ StreamBase<T>::status = Ok;
+ StreamBase<T>::position = 0;
+ } else if (newpos < StreamBase<T>::size) {
+ StreamBase<T>::status = Ok;
+ StreamBase<T>::position = newpos;
+ } else {
+ StreamBase<T>::position = StreamBase<T>::size;
+ StreamBase<T>::status = Eof;
+ }
+ return StreamBase<T>::position;
+}
+
+} // end namespace jstreams
+
+#endif
Modified: trunk/clucene/src/CLucene.h
===================================================================
--- trunk/clucene/src/CLucene.h 2006-06-11 07:16:00 UTC (rev 427)
+++ trunk/clucene/src/CLucene.h 2006-06-26 00:39:24 UTC (rev 428)
@@ -1,18 +1,9 @@
-/**
- * Copyright 2003-2006 The Apache Software Foundation
- *
- * Licensed under the Apache License, Version 2.0 (the "License");
- * you may not use this file except in compliance with the License.
- * You may obtain a copy of the License at
- *
- * http://www.apache.org/licenses/LICENSE-2.0
- *
- * Unless required by applicable law or agreed to in writing, software
- * distributed under the License is distributed on an "AS IS" BASIS,
- * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
- * See the License for the specific language governing permissions and
- * limitations under the License.
- */
+/*------------------------------------------------------------------------------
+* Copyright (C) 2003-2006 Ben van Klinken and the CLucene Team
+*
+* Distributable under the terms of either the Apache License (Version 2.0) or
+* the GNU Lesser General Public License, as specified in the COPYING file.
+------------------------------------------------------------------------------*/
//Includes some standard headers for searching and indexing.
#ifndef _lucene_CLucene_
#define _lucene_CLucene_
Modified: trunk/stage/layout.conf
===================================================================
--- trunk/stage/layout.conf 2006-06-11 07:16:00 UTC (rev 427)
+++ trunk/stage/layout.conf 2006-06-26 00:39:24 UTC (rev 428)
@@ -7,17 +7,20 @@
[History]
LastComModule=JFB
-LastLDKey=5485
+LastLDKey=ABRAM
LastLDModule=CBC
LastParaMod01=
LastParaMod02=
LastParaMod03=
-LastTextModule=ChiNCVs
-LastVerse=James 1:19
+LastTextModule=WLC
+LastVerse=Genesis 1:1
LookupSaveCount=5
LookupText=James 1:19
LookupText=John 1:1
SearchSaveCount=5
+SearchText=物*
+SearchText=å„*
+SearchText=我*
[LDView]
CBC=
@@ -30,7 +33,7 @@
[ModuleOptions]
Cross-references=On
-Footnotes=Off
+Footnotes=On
Headings=Off
Hebrew Cantillation=Off
Hebrew Vowel Points=On
@@ -42,16 +45,16 @@
[Screen]
MainHeight=749
-MainLeft=22
-MainTop=22
+MainLeft=254
+MainTop=252
MainWidth=1050
Maximized=false
SearchHeight=566
-SearchLeft=675
+SearchLeft=224
SearchMaximized=false
SearchResCol0Width=175
-SearchTop=312
-SearchWidth=545
+SearchTop=351
+SearchWidth=759
TextComHeight=195
TextWidth=368
@@ -62,6 +65,7 @@
ChiUn=
ChiUns=
GerNEU=
+Jub=
KJV=
NASB=
PARALLEL=
Modified: trunk/sword.bpr
===================================================================
--- trunk/sword.bpr 2006-06-11 07:16:00 UTC (rev 427)
+++ trunk/sword.bpr 2006-06-26 00:39:24 UTC (rev 428)
@@ -43,7 +43,7 @@
<DEBUGLIBPATH value="$(BCB)\lib\debug"/>
<RELEASELIBPATH value="$(BCB)\lib\release"/>
<LINKER value="ilink32"/>
- <USERDEFINES value="_ICU_;_ICUSWORD_;USBINARY;U_HAVE_PLACEMENT_NEW=0;USELUCENE;_CL_DISABLE_MULTITHREADING"/>
+ <USERDEFINES value="_ICU_;_ICUSWORD_;USBINARY;U_HAVE_PLACEMENT_NEW=0;USELUCENE;_CL_DISABLE_MULTITHREADING;_DEBUG"/>
<SYSDEFINES value="NO_STRICT"/>
<MAINSOURCE value="sword.cpp"/>
<INCLUDEPATH value="..\sword\src\modules\filters;D:\;TntUnicodeControls;..\icu-sword\source\common;..\icu-sword\source\i18n;..\sword\include;$(BCB)\include;$(BCB)\include\vcl;rxlib"/>
@@ -57,16 +57,16 @@
-I$(BCB)\include -I$(BCB)\include\vcl -Irxlib -src_suffix cpp -D_ICU_
-D_ICUSWORD_ -DUSBINARY -DU_HAVE_PLACEMENT_NEW=0 -DUSELUCENE
-D_CL_DISABLE_MULTITHREADING"/>
- <CFLAG1 value="-O2 -Vx -X- -a8 -4 -b- -k- -vi -c -tW -tWM"/>
- <PFLAGS value="-N2obj -N0obj -$Y- -$L- -$D- -v -M -JPHNE"/>
+ <CFLAG1 value="-vGc -vGt -vGd -Od -Vx -X- -r- -a8 -4 -b- -k -y -v -vi- -c -tW -tWM"/>
+ <PFLAGS value="-N2obj -N0obj -$Y+ -$W -$O- -v -M -JPHNE"/>
<RFLAGS value=""/>
- <AFLAGS value="/mx /w2 /zn"/>
- <LFLAGS value="-Iobj -D"" -aa -Tpe -GD -s -Gn"/>
+ <AFLAGS value="/mx /w2 /zi"/>
+ <LFLAGS value="-Iobj -D"" -aa -Tpe -GD -s -Gn -v"/>
</OPTIONS>
<LINKER>
<ALLOBJ value="c0w32.obj $(OBJFILES)"/>
<ALLRES value="$(RESFILES)"/>
- <ALLLIB value="$(LIBFILES) $(LIBRARIES) import32.lib cp32mt.lib"/>
+ <ALLLIB value="cg32.lib $(LIBFILES) $(LIBRARIES) import32.lib cp32mt.lib"/>
</LINKER>
<IDEOPTIONS>
[Version Info]
@@ -75,7 +75,7 @@
MajorVer=1
MinorVer=5
Release=8
-Build=2
+Build=3
Debug=0
PreRelease=0
Special=0
@@ -87,7 +87,7 @@
[Version Info Keys]
CompanyName=CrossWire Software & Bible Society
FileDescription=Windows 32bit User Interface to The SWORD Project
-FileVersion=1.5.8.2
+FileVersion=1.5.8.3
InternalName=biblecs
LegalCopyright=(c) 1990-2005 CrossWire Bible Society under the terms of the GNU General Public License
LegalTrademarks=
@@ -140,22 +140,23 @@
Item2=$(BCB)\source\vcl
[HistoryLists\hlConditionals]
-Count=15
-Item0=_ICU_;_ICUSWORD_;USBINARY;U_HAVE_PLACEMENT_NEW=0;USELUCENE;_CL_DISABLE_MULTITHREADING
-Item1=_ICU_;_ICUSWORD_;USBINARY;U_HAVE_PLACEMENT_NEW=0;USELUCENE
-Item2=_ICU_;_ICUSWORD_;USBINARY;U_HAVE_PLACEMENT_NEW=0;USELUCENE;_DEBUG
-Item3=_ICU_;_ICUSWORD_;USBINARY;U_HAVE_PLACEMENT_NEW=0;_DEBUG;USELUCENE
-Item4=_ICU_;_ICUSWORD_;USBINARY;U_HAVE_PLACEMENT_NEW=0;_DEBUG
-Item5=_ICU_;_ICUSWORD_;USBINARY;U_HAVE_PLACEMENT_NEW=0
-Item6=_ICU_;_ICUSWORD_;USBINARY;_DEBUG;U_HAVE_PLACEMENT_NEW=0
-Item7=_ICU_;_ICUSWORD_;USBINARY;_DEBUG
-Item8=_ICU_;_ICUSWORD_;USBINARY
-Item9=_ICU_;_ICUSWORD_;_DEBUG;USBINARY
-Item10=_ICU_;_ICUSWORD_;_DEBUG
-Item11=_ICU_;_ICUSWORD_
-Item12=_ICU_
-Item13=_ICU_;_DEBUG
-Item14=_DEBUG
+Count=16
+Item0=_ICU_;_ICUSWORD_;USBINARY;U_HAVE_PLACEMENT_NEW=0;USELUCENE;_CL_DISABLE_MULTITHREADING;_DEBUG
+Item1=_ICU_;_ICUSWORD_;USBINARY;U_HAVE_PLACEMENT_NEW=0;USELUCENE;_CL_DISABLE_MULTITHREADING
+Item2=_ICU_;_ICUSWORD_;USBINARY;U_HAVE_PLACEMENT_NEW=0;USELUCENE
+Item3=_ICU_;_ICUSWORD_;USBINARY;U_HAVE_PLACEMENT_NEW=0;USELUCENE;_DEBUG
+Item4=_ICU_;_ICUSWORD_;USBINARY;U_HAVE_PLACEMENT_NEW=0;_DEBUG;USELUCENE
+Item5=_ICU_;_ICUSWORD_;USBINARY;U_HAVE_PLACEMENT_NEW=0;_DEBUG
+Item6=_ICU_;_ICUSWORD_;USBINARY;U_HAVE_PLACEMENT_NEW=0
+Item7=_ICU_;_ICUSWORD_;USBINARY;_DEBUG;U_HAVE_PLACEMENT_NEW=0
+Item8=_ICU_;_ICUSWORD_;USBINARY;_DEBUG
+Item9=_ICU_;_ICUSWORD_;USBINARY
+Item10=_ICU_;_ICUSWORD_;_DEBUG;USBINARY
+Item11=_ICU_;_ICUSWORD_;_DEBUG
+Item12=_ICU_;_ICUSWORD_
+Item13=_ICU_
+Item14=_ICU_;_DEBUG
+Item15=_DEBUG
[HistoryLists\hlIntOutputDir]
Count=2
@@ -182,13 +183,8 @@
[Compiler]
ShowInfoMsgs=0
LinkDebugVcl=0
-LinkCGLIB=0
+LinkCGLIB=1
-[CORBA]
-AddServerUnit=1
-AddClientUnit=1
-PrecompiledHeaders=1
-
[Language]
ActiveLang=
ProjectLang=
Modified: trunk/sword.res
===================================================================
(Binary files differ)
More information about the sword-cvs
mailing list