[sword-svn] r209 - trunk/source/data/brkitr
chrislit at crosswire.org
chrislit at crosswire.org
Thu Jul 2 12:25:02 MST 2009
Author: chrislit
Date: 2009-07-02 12:25:02 -0700 (Thu, 02 Jul 2009)
New Revision: 209
Modified:
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
Log:
ICU 4.2.1 update, first pass
Modified: trunk/source/data/brkitr/char_th.txt
===================================================================
--- trunk/source/data/brkitr/char_th.txt 2009-06-02 05:06:53 UTC (rev 208)
+++ trunk/source/data/brkitr/char_th.txt 2009-07-02 19:25:02 UTC (rev 209)
@@ -1,68 +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 $LF];
-
-
-## -------------------------------------------------
-
-!!safe_reverse;
-
-
-## -------------------------------------------------
-
-!!safe_forward;
-
+#
+# Copyright (C) 2002-2009, International Business Machines Corporation and others.
+# All Rights Reserved.
+#
+# file: char_th.txt
+#
+# ICU Character Break Rules, also known as Grapheme Cluster Boundaries
+# See Unicode Standard Annex #29.
+# These rules are based on TR29 Revision 13, for Unicode Version 5.1
+#
+
+#
+# Character Class Definitions.
+#
+$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 $LF];
+
+
+## -------------------------------------------------
+
+!!safe_reverse;
+
+
+## -------------------------------------------------
+
+!!safe_forward;
+
Modified: trunk/source/data/brkitr/el.txt
===================================================================
--- trunk/source/data/brkitr/el.txt 2009-06-02 05:06:53 UTC (rev 208)
+++ trunk/source/data/brkitr/el.txt 2009-07-02 19:25:02 UTC (rev 209)
@@ -1,14 +1,14 @@
-// ***************************************************************************
-// *
-// * Copyright (C) 2009 International Business Machines
-// * Corporation and others. All Rights Reserved.
-// * Tool: com.ibm.icu.dev.tool.cldr.LDML2ICUConverter.java
-// * Source File:<path>/xml/brkitr/el.xml
-// *
-// ***************************************************************************
-el{
- Version{"1.1"}
- boundaries{
- sentence:process(dependency){"sent_el.brk"}
- }
-}
+// ***************************************************************************
+// *
+// * Copyright (C) 2009 International Business Machines
+// * Corporation and others. All Rights Reserved.
+// * Tool: com.ibm.icu.dev.tool.cldr.LDML2ICUConverter.java
+// * Source File:<path>/xml/brkitr/el.xml
+// *
+// ***************************************************************************
+el{
+ Version{"1.1"}
+ boundaries{
+ sentence:process(dependency){"sent_el.brk"}
+ }
+}
Modified: trunk/source/data/brkitr/sent_el.txt
===================================================================
--- trunk/source/data/brkitr/sent_el.txt 2009-06-02 05:06:53 UTC (rev 208)
+++ trunk/source/data/brkitr/sent_el.txt 2009-07-02 19:25:02 UTC (rev 209)
@@ -1,119 +1,119 @@
-#
-# Copyright (C) 2002-2009, International Business Machines Corporation and others.
-# All Rights Reserved.
-#
-# file: sent_el.txt
-#
-# ICU Sentence Break Rules
-# See Unicode Standard Annex #29.
-# These rules are based on UAX 29 Revision 13 for Unicode Version 5.1.0
-#
-
-
-#
-# Character categories as defined in TR 29
-#
-$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 $Sep because position might be
-# at the beginning of the string at this point, and we don't want to fail.
-# Can only use {eof} once, and it is used later.
-#
+#
+# Copyright (C) 2002-2009, International Business Machines Corporation and others.
+# All Rights Reserved.
+#
+# file: sent_el.txt
+#
+# ICU Sentence Break Rules
+# See Unicode Standard Annex #29.
+# These rules are based on UAX 29 Revision 13 for Unicode Version 5.1.0
+#
+
+
+#
+# Character categories as defined in TR 29
+#
+$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.
+#
Modified: trunk/source/data/brkitr/th.txt
===================================================================
--- trunk/source/data/brkitr/th.txt 2009-06-02 05:06:53 UTC (rev 208)
+++ trunk/source/data/brkitr/th.txt 2009-07-02 19:25:02 UTC (rev 209)
@@ -1,14 +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"}
- }
-}
+// ***************************************************************************
+// *
+// * 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"}
+ }
+}
More information about the sword-cvs
mailing list