[sword-svn] r188 - trunk/source/data/brkitr

chrislit at crosswire.org chrislit at crosswire.org
Fri May 8 19:32:20 MST 2009


Author: chrislit
Date: 2009-05-08 19:32:20 -0700 (Fri, 08 May 2009)
New Revision: 188

Added:
   trunk/source/data/brkitr/char_th.txt
   trunk/source/data/brkitr/el.txt
   trunk/source/data/brkitr/sent_el.txt
   trunk/source/data/brkitr/th.txt
Modified:
   trunk/source/data/brkitr/brkfiles.mk
   trunk/source/data/brkitr/char.txt
   trunk/source/data/brkitr/en.txt
   trunk/source/data/brkitr/en_US.txt
   trunk/source/data/brkitr/en_US_POSIX.txt
   trunk/source/data/brkitr/ja.txt
   trunk/source/data/brkitr/line.txt
   trunk/source/data/brkitr/root.txt
   trunk/source/data/brkitr/sent.txt
   trunk/source/data/brkitr/word.txt
   trunk/source/data/brkitr/word_POSIX.txt
   trunk/source/data/brkitr/word_ja.txt
Log:
ICU 4.2 update, first pass


Modified: trunk/source/data/brkitr/brkfiles.mk
===================================================================
--- trunk/source/data/brkitr/brkfiles.mk	2009-05-09 02:32:01 UTC (rev 187)
+++ trunk/source/data/brkitr/brkfiles.mk	2009-05-09 02:32:20 UTC (rev 188)
@@ -1,6 +1,6 @@
-# *   Copyright (C) 1998-2008, International Business Machines
+# *   Copyright (C) 1998-2009, International Business Machines
 # *   Corporation and others.  All Rights Reserved.
-BRK_RES_CLDR_VERSION = 1.6.1
+BRK_RES_CLDR_VERSION = 1.7
 # A list of txt's to build
 # Note: 
 #
@@ -38,9 +38,9 @@
 
 
 # List of break iterator files (brk).
-BRK_SOURCE = word_POSIX.txt word_ja.txt char.txt word.txt line.txt sent.txt title.txt 
+BRK_SOURCE = word_POSIX.txt word_ja.txt sent_el.txt char_th.txt char.txt word.txt line.txt sent.txt title.txt 
 
 
 # Ordinary resources
-BRK_RES_SOURCE = en.txt en_US.txt en_US_POSIX.txt ja.txt
+BRK_RES_SOURCE = el.txt en.txt en_US.txt en_US_POSIX.txt ja.txt th.txt
 

Modified: trunk/source/data/brkitr/char.txt
===================================================================
--- trunk/source/data/brkitr/char.txt	2009-05-09 02:32:01 UTC (rev 187)
+++ trunk/source/data/brkitr/char.txt	2009-05-09 02:32:20 UTC (rev 188)
@@ -1,12 +1,12 @@
 #
-#   Copyright (C) 2002-2008, International Business Machines Corporation and others.
+#   Copyright (C) 2002-2009, International Business Machines Corporation and others.
 #       All Rights Reserved.
 #
 #   file:  char.txt 
 #
 #   ICU Character Break Rules, also known as Grapheme Cluster Boundaries
 #      See Unicode Standard Annex #29.
-#      These rules are based on TR29 Revision 12, for Unicode Version 5.1
+#      These rules are based on TR29 Revision 13, for Unicode Version 5.1
 #
 
 #

Added: trunk/source/data/brkitr/char_th.txt
===================================================================
--- trunk/source/data/brkitr/char_th.txt	                        (rev 0)
+++ trunk/source/data/brkitr/char_th.txt	2009-05-09 02:32:20 UTC (rev 188)
@@ -0,0 +1,68 @@
+#
+#   Copyright (C) 2002-2009, International Business Machines Corporation and others.
+#       All Rights Reserved.
+#
+#   file:  char_th.txt 
+#
+#   ICU Character Break Rules, also known as Grapheme Cluster Boundaries
+#      See Unicode Standard Annex #29.
+#      These rules are based on TR29 Revision 13, for Unicode Version 5.1
+#
+
+#
+#  Character Class Definitions.
+#
+$CR          = [\p{Grapheme_Cluster_Break = CR}];
+$LF          = [\p{Grapheme_Cluster_Break = LF}];
+$Control     = [\p{Grapheme_Cluster_Break = Control}];
+$Extend      = [\p{Grapheme_Cluster_Break = Extend} - [\u0E30 \u0E32 \u0E45 \u0EB0 \u0EB2]];
+$SpacingMark = [\p{Grapheme_Cluster_Break = SpacingMark}];
+
+#
+# Korean Syllable Definitions
+#
+$L       = [\p{Grapheme_Cluster_Break = L}];
+$V       = [\p{Grapheme_Cluster_Break = V}];
+$T       = [\p{Grapheme_Cluster_Break = T}];
+
+$LV      = [\p{Grapheme_Cluster_Break = LV}];
+$LVT     = [\p{Grapheme_Cluster_Break = LVT}];
+
+
+## -------------------------------------------------
+!!chain;
+
+!!forward;
+
+$CR $LF;
+
+$L ($L | $V | $LV | $LVT);
+($LV | $V) ($V | $T);
+($LVT | $T) $T;
+
+[^$Control $CR $LF] $Extend;
+
+[^$Control $CR $LF] $SpacingMark;
+
+
+## -------------------------------------------------
+
+!!reverse;
+$LF $CR;
+($L | $V | $LV | $LVT) $L;
+($V | $T) ($LV | $V);
+$T ($LVT | $T);
+
+$Extend      [^$Control $CR $LF];
+$SpacingMark [^$Control $CR $LF];
+
+
+## -------------------------------------------------
+
+!!safe_reverse;
+
+
+## -------------------------------------------------
+
+!!safe_forward;
+

Added: trunk/source/data/brkitr/el.txt
===================================================================
--- trunk/source/data/brkitr/el.txt	                        (rev 0)
+++ trunk/source/data/brkitr/el.txt	2009-05-09 02:32:20 UTC (rev 188)
@@ -0,0 +1,14 @@
+// ***************************************************************************
+// *
+// * Copyright (C) 2009 International Business Machines
+// * Corporation and others.  All Rights Reserved.
+// * Tool: com.ibm.icu.dev.tool.cldr.LDML2ICUConverter.java
+// * Source File:<path>/xml/brkitr/el.xml
+// *
+// ***************************************************************************
+el{
+    Version{"1.1"}
+    boundaries{
+        sentence:process(dependency){"sent_el.brk"}
+    }
+}

Modified: trunk/source/data/brkitr/en.txt
===================================================================
--- trunk/source/data/brkitr/en.txt	2009-05-09 02:32:01 UTC (rev 187)
+++ trunk/source/data/brkitr/en.txt	2009-05-09 02:32:20 UTC (rev 188)
@@ -1,6 +1,6 @@
 // ***************************************************************************
 // *
-// * Copyright (C) 2008 International Business Machines
+// * Copyright (C) 2009 International Business Machines
 // * Corporation and others.  All Rights Reserved.
 // * Tool: com.ibm.icu.dev.tool.cldr.LDML2ICUConverter.java
 // * Source File:<path>/xml/brkitr/en.xml

Modified: trunk/source/data/brkitr/en_US.txt
===================================================================
--- trunk/source/data/brkitr/en_US.txt	2009-05-09 02:32:01 UTC (rev 187)
+++ trunk/source/data/brkitr/en_US.txt	2009-05-09 02:32:20 UTC (rev 188)
@@ -1,6 +1,6 @@
 // ***************************************************************************
 // *
-// * Copyright (C) 2008 International Business Machines
+// * Copyright (C) 2009 International Business Machines
 // * Corporation and others.  All Rights Reserved.
 // * Tool: com.ibm.icu.dev.tool.cldr.LDML2ICUConverter.java
 // * Source File:<path>/xml/brkitr/en_US.xml

Modified: trunk/source/data/brkitr/en_US_POSIX.txt
===================================================================
--- trunk/source/data/brkitr/en_US_POSIX.txt	2009-05-09 02:32:01 UTC (rev 187)
+++ trunk/source/data/brkitr/en_US_POSIX.txt	2009-05-09 02:32:20 UTC (rev 188)
@@ -1,6 +1,6 @@
 // ***************************************************************************
 // *
-// * Copyright (C) 2008 International Business Machines
+// * Copyright (C) 2009 International Business Machines
 // * Corporation and others.  All Rights Reserved.
 // * Tool: com.ibm.icu.dev.tool.cldr.LDML2ICUConverter.java
 // * Source File:<path>/xml/brkitr/en_US_POSIX.xml

Modified: trunk/source/data/brkitr/ja.txt
===================================================================
--- trunk/source/data/brkitr/ja.txt	2009-05-09 02:32:01 UTC (rev 187)
+++ trunk/source/data/brkitr/ja.txt	2009-05-09 02:32:20 UTC (rev 188)
@@ -1,6 +1,6 @@
 // ***************************************************************************
 // *
-// * Copyright (C) 2008 International Business Machines
+// * Copyright (C) 2009 International Business Machines
 // * Corporation and others.  All Rights Reserved.
 // * Tool: com.ibm.icu.dev.tool.cldr.LDML2ICUConverter.java
 // * Source File:<path>/xml/brkitr/ja.xml

Modified: trunk/source/data/brkitr/line.txt
===================================================================
--- trunk/source/data/brkitr/line.txt	2009-05-09 02:32:01 UTC (rev 187)
+++ trunk/source/data/brkitr/line.txt	2009-05-09 02:32:20 UTC (rev 188)
@@ -1,11 +1,11 @@
-# Copyright (c) 2002-2008  International Business Machines Corporation and
+# Copyright (c) 2002-2009  International Business Machines Corporation and
 # others. All Rights Reserved.
 #
 #  file:  line.txt
 #
 #         Line Breaking Rules
 #         Implement default line breaking as defined by 
-#         Unicode Standard Annex #14 Revision 21 for Unicode 5.1
+#         Unicode Standard Annex #14 Revision 22 for Unicode 5.1
 #         http://www.unicode.org/reports/tr14/
 
 
@@ -23,7 +23,7 @@
 #  !!lookAheadHardBreak    Described here because it is (as yet) undocumented elsewhere
 #                          and only used for the line break rules.
 #
-#           It is used in the implementation of the incredibly annoying rule LB 10
+#           It is used in the implementation of rule LB 10
 #           which says to treat any combining mark that is not attached to a base
 #           character as if it were of class AL  (alphabetic).
 #
@@ -359,7 +359,7 @@
 # LB 28   Do not break between alphabetics
 #
 $ALcm $ALcm;
-$CM+ $ALcm;      # The $CM+ is from rule 10, and unattached CM is treated as AL
+$CM+ $ALcm;      # The $CM+ is from rule 10, an unattached CM is treated as AL
 
 # LB 29
 $IScm $ALcm;

Modified: trunk/source/data/brkitr/root.txt
===================================================================
--- trunk/source/data/brkitr/root.txt	2009-05-09 02:32:01 UTC (rev 187)
+++ trunk/source/data/brkitr/root.txt	2009-05-09 02:32:20 UTC (rev 188)
@@ -1,6 +1,6 @@
 // ***************************************************************************
 // *
-// * Copyright (C) 2008 International Business Machines
+// * Copyright (C) 2009 International Business Machines
 // * Corporation and others.  All Rights Reserved.
 // * Tool: com.ibm.icu.dev.tool.cldr.LDML2ICUConverter.java
 // * Source File:<path>/xml/brkitr/root.xml

Modified: trunk/source/data/brkitr/sent.txt
===================================================================
--- trunk/source/data/brkitr/sent.txt	2009-05-09 02:32:01 UTC (rev 187)
+++ trunk/source/data/brkitr/sent.txt	2009-05-09 02:32:20 UTC (rev 188)
@@ -1,12 +1,12 @@
 #
-#   Copyright (C) 2002-2008, International Business Machines Corporation and others.
+#   Copyright (C) 2002-2009, International Business Machines Corporation and others.
 #       All Rights Reserved.
 #
 #   file:  sent.txt
 #
 #   ICU Sentence Break Rules
 #      See Unicode Standard Annex #29.
-#      These rules are based on SA 29 version 5.1.0
+#      These rules are based on UAX 29 Revision 13 for Unicode Version 5.1.0
 #
 
 

Added: trunk/source/data/brkitr/sent_el.txt
===================================================================
--- trunk/source/data/brkitr/sent_el.txt	                        (rev 0)
+++ trunk/source/data/brkitr/sent_el.txt	2009-05-09 02:32:20 UTC (rev 188)
@@ -0,0 +1,119 @@
+#
+#   Copyright (C) 2002-2009, International Business Machines Corporation and others.
+#       All Rights Reserved.
+#
+#   file:  sent_el.txt
+#
+#   ICU Sentence Break Rules
+#      See Unicode Standard Annex #29.
+#      These rules are based on UAX 29 Revision 13 for Unicode Version 5.1.0
+#
+
+
+#
+# Character categories as defined in TR 29
+#
+$CR        = [\p{Sentence_Break = CR}];
+$LF        = [\p{Sentence_Break = LF}];
+$Extend    = [\p{Sentence_Break = Extend}];
+$Sep       = [\p{Sentence_Break = Sep}];
+$Format    = [\p{Sentence_Break = Format}];
+$Sp        = [\p{Sentence_Break = Sp}];
+$Lower     = [\p{Sentence_Break = Lower}];
+$Upper     = [\p{Sentence_Break = Upper}];
+$OLetter   = [\p{Sentence_Break = OLetter}];
+$Numeric   = [\p{Sentence_Break = Numeric}];
+$ATerm     = [\p{Sentence_Break = ATerm}];
+$SContinue = [\p{Sentence_Break = SContinue}];
+$STerm     = [\p{Sentence_Break = STerm} [\u003B \u037E]];
+$Close     = [\p{Sentence_Break = Close}];
+
+#
+# Define extended forms of the character classes,
+#   incorporate trailing Extend or Format chars.
+#   Rules 4 and 5.  
+
+$SpEx       = $Sp      ($Extend | $Format)*;
+$LowerEx    = $Lower   ($Extend | $Format)*;
+$UpperEx    = $Upper   ($Extend | $Format)*;
+$OLetterEx  = $OLetter ($Extend | $Format)*;
+$NumericEx  = $Numeric ($Extend | $Format)*;
+$ATermEx    = $ATerm   ($Extend | $Format)*;
+$SContinueEx= $SContinue ($Extend | $Format)*;
+$STermEx    = $STerm   ($Extend | $Format)*;
+$CloseEx    = $Close   ($Extend | $Format)*;
+
+
+## -------------------------------------------------
+
+!!chain;
+!!forward;
+
+# Rule 3 - break after separators.  Keep CR/LF together.
+#
+$CR $LF;
+
+
+# Rule 4 - Break after $Sep.
+# Rule 5 - Ignore $Format and $Extend
+#
+[^$Sep $CR $LF]? ($Extend | $Format)*;
+
+
+# Rule 6
+$ATermEx $NumericEx;
+
+# Rule 7
+$UpperEx $ATermEx $UpperEx;
+
+#Rule 8
+$NotLettersEx = [^$OLetter $Upper $Lower $Sep $CR $LF $ATerm $STerm] ($Extend | $Format)*;
+$ATermEx $CloseEx* $SpEx* $NotLettersEx* $Lower;
+
+# Rule 8a
+($STermEx | $ATermEx) $CloseEx* $SpEx* ($SContinueEx | $STermEx | $ATermEx);
+
+#Rule 9, 10, 11
+($STermEx | $ATermEx) $CloseEx* $SpEx* ($Sep | $CR | $LF)?;
+
+#Rule 12
+[[^$STerm $ATerm $Close $Sp $Sep $LF $CR $Format $Extend]{bof}] ($Extend | $Format | $Close | $Sp)* .;
+[[^$STerm $ATerm $Close $Sp $Sep $LF $CR $Format $Extend]{bof}] ($Extend | $Format | $Close | $Sp)* ([$Sep $LF $CR {eof}] | $CR $LF){100};
+
+## -------------------------------------------------
+
+!!reverse;
+
+$SpEx_R       = ($Extend | $Format)* $Sp;
+$ATermEx_R    = ($Extend | $Format)* $ATerm;
+$STermEx_R    = ($Extend | $Format)* $STerm;
+$CloseEx_R    = ($Extend | $Format)* $Close;
+
+#
+#  Reverse rules.
+#     For now, use the old style inexact reverse rules, which are easier
+#     to write, but less efficient.
+#     TODO:  exact reverse rules.  It appears that exact reverse rules
+#            may require improving support for look-ahead breaks in the
+#            builder.  Needs more investigation.
+#
+
+[{bof}] (.? | $LF $CR) [^$Sep $CR $LF]* [$Sep $CR $LF {eof}] ($SpEx_R* $CloseEx_R* ($STermEx_R | $ATermEx_R))*;
+#.*;
+
+# Explanation for this rule:
+#
+#    It needs to back over
+#        The $Sep at which we probably begin
+#        All of the non $Sep chars leading to the preceding $Sep
+#        The preceding $Sep, which will be the second one that the rule matches.
+#        Any immediately preceding STerm or ATerm sequences.  We need to see these
+#              to get the correct rule status when moving forwards again.
+#        
+# [{bof}]           inhibit rule chaining.  Without this, rule would loop on itself and match
+#                   the entire string.
+#
+# (.? | $LF $CR)    Match one $Sep instance.  Use .? rather than $Sep because position might be
+#                   at the beginning of the string at this point, and we don't want to fail.
+#                   Can only use {eof} once, and it is used later.
+#

Added: trunk/source/data/brkitr/th.txt
===================================================================
--- trunk/source/data/brkitr/th.txt	                        (rev 0)
+++ trunk/source/data/brkitr/th.txt	2009-05-09 02:32:20 UTC (rev 188)
@@ -0,0 +1,14 @@
+// ***************************************************************************
+// *
+// * Copyright (C) 2009 International Business Machines
+// * Corporation and others.  All Rights Reserved.
+// * Tool: com.ibm.icu.dev.tool.cldr.LDML2ICUConverter.java
+// * Source File:<path>/xml/brkitr/th.xml
+// *
+// ***************************************************************************
+th{
+    Version{"1.1"}
+    boundaries{
+        grapheme:process(dependency){"char_th.brk"}
+    }
+}

Modified: trunk/source/data/brkitr/word.txt
===================================================================
--- trunk/source/data/brkitr/word.txt	2009-05-09 02:32:01 UTC (rev 187)
+++ trunk/source/data/brkitr/word.txt	2009-05-09 02:32:20 UTC (rev 188)
@@ -1,12 +1,12 @@
 #
-# Copyright (C) 2002-2008, International Business Machines Corporation 
+# Copyright (C) 2002-2009, International Business Machines Corporation 
 # and others. All Rights Reserved.
 #
 # file:  word.txt
 #
 # ICU Word Break Rules
 #      See Unicode Standard Annex #29.
-#      These rules are based on UAX-29 Revision 12 for Unicode 5.1
+#      These rules are based on UAX-29 Revision 13 for Unicode 5.1
 #
 # Note:  Updates to word.txt will usually need to be merged into
 #        word_POSIX.txt and word_ja.txt also.

Modified: trunk/source/data/brkitr/word_POSIX.txt
===================================================================
--- trunk/source/data/brkitr/word_POSIX.txt	2009-05-09 02:32:01 UTC (rev 187)
+++ trunk/source/data/brkitr/word_POSIX.txt	2009-05-09 02:32:20 UTC (rev 188)
@@ -1,12 +1,12 @@
 #
-# Copyright (C) 2002-2008, International Business Machines Corporation 
+# Copyright (C) 2002-2009, International Business Machines Corporation 
 # and others. All Rights Reserved.
 #
 # file:  word_POSIX.txt
 #
 # ICU Word Break Rules, POSIX locale.
 #      See Unicode Standard Annex #29.
-#      These rules are based on UAX-29 Revision 12 for Unicode 5.1
+#      These rules are based on UAX-29 Revision 13 for Unicode 5.1
 #
 # Note:  Updates to word.txt will usually need to be merged into
 #        word_POSIX.txt and word_ja.txt also.
@@ -31,9 +31,9 @@
 $Format       = [\p{Word_Break = Format}];
 $Katakana     = [\p{Word_Break = Katakana}];
 $ALetter      = [\p{Word_Break = ALetter}];
-$MidNumLet    = [\p{Word_Break = MidNumLet}];
-$MidLetter    = [\p{Word_Break = MidLetter} - [ \:]];
-$MidNum       = [\p{Word_Break = MidNum}];
+$MidNumLet    = [\p{Word_Break = MidNumLet} - [.]];
+$MidLetter    = [\p{Word_Break = MidLetter} - [\:]];
+$MidNum       = [\p{Word_Break = MidNum} [.]];
 $Numeric      = [\p{Word_Break = Numeric}];
 $ExtendNumLet = [\p{Word_Break = ExtendNumLet}];
 

Modified: trunk/source/data/brkitr/word_ja.txt
===================================================================
--- trunk/source/data/brkitr/word_ja.txt	2009-05-09 02:32:01 UTC (rev 187)
+++ trunk/source/data/brkitr/word_ja.txt	2009-05-09 02:32:20 UTC (rev 188)
@@ -1,12 +1,12 @@
 #
-# Copyright (C) 2002-2008, International Business Machines Corporation 
+# Copyright (C) 2002-2009, International Business Machines Corporation 
 # and others. All Rights Reserved.
 #
 # file:  word_ja.txt
 #
 # ICU Word Break Rules
 #      See Unicode Standard Annex #29.
-#      These rules are based on UAX-29 Revision 12 for Unicode 5.1
+#      These rules are based on UAX-29 Revision 13 for Unicode 5.1
 #
 # Note:  Updates to word.txt will usually need to be merged into
 #        word_POSIX.txt and word_ja.txt also.
@@ -61,7 +61,7 @@
 $ExtendNumLetEx = $ExtendNumLet ($Extend |  $Format)*;
 
 $Hiragana       = [\p{script=Hiragana}];
-$Ideographic    = [\p{Ideographic}];
+$Ideographic    = [\p{Ideographic} [\u3005 \u3007 \u303B]];
 $HiraganaEx     = $Hiragana     ($Extend |  $Format)*;
 $IdeographicEx  = $Ideographic  ($Extend |  $Format)*;
 




More information about the sword-cvs mailing list