ICU-9353 fix windows makefile, remove mentions of word_ja.txt

X-SVN-Rev: 32191

diff --git a/icu4c/source/common/brkeng.cpp b/icu4c/source/common/brkeng.cpp
index abc201e9f5411466bedd026044b2406d161408b1..381ce7dd3d1db9747e9cf11f0d3307ffbcc8c951 100644 (file)
--- a/icu4c/source/common/brkeng.cpp
+++ b/icu4c/source/common/brkeng.cpp
@@ -288,10 +288,15 @@ ICULanguageBreakFactory::loadDictionaryMatcherFor(UScriptCode script, int32_t /*
     }
     if (U_SUCCESS(status) && dictfname) {
         UChar *extStart = u_strchr(dictfname, 0x002e);
+        int32_t extLen = u_strlen(extStart+1);
+        if (extLen > sizeof(ext) - 1) {
+            ures_close(b);
+            return NULL;
+        }
         int len = 0;
         if (extStart != NULL) {
             len = (int)(extStart - dictfname);
-            u_UCharsToChars(extStart+1, ext, sizeof(ext)-1); // null-terminates the buffer
+            u_UCharsToChars(extStart+1, ext, extLen); // null-terminates the buffer
             u_UCharsToChars(dictfname, dictnbuf, len);
         }
         dictnbuf[len] = '\0'; // null-terminate

diff --git a/icu4c/source/data/brkitr/ja.txt b/icu4c/source/data/brkitr/ja.txt
index 898c696d647331b76c054593def93c32ba94547b..161b1982f938f80544456764b3fbacdae1f1ab9a 100644 (file)
--- a/icu4c/source/data/brkitr/ja.txt
+++ b/icu4c/source/data/brkitr/ja.txt
@@ -10,6 +10,5 @@ ja{
     Version{"1.1"}
     boundaries{
         line:process(dependency){"line_ja.brk"}
-        word:process(dependency){"word_ja.brk"}
     }
 }

diff --git a/icu4c/source/data/brkitr/word_ja.txt b/icu4c/source/data/brkitr/word_ja.txt
deleted file mode 100644 (file)
index a870345..0000000
--- a/icu4c/source/data/brkitr/word_ja.txt
+++ /dev/null
@@ -1,223 +0,0 @@
-#
-# Copyright (C) 2002-2011, 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 19 for Unicode Version 6.1
-#
-# Note:  Updates to word.txt will usually need to be merged into
-#        word_POSIX.txt and word_ja.txt also.
-
-##############################################################################
-#
-#  Character class definitions from TR 29
-#
-##############################################################################
-
-!!chain;
-
-
-#
-#  Character Class Definitions.
-#
-
-$CR           = [\p{Word_Break = CR}];
-$LF           = [\p{Word_Break = LF}];
-$Newline      = [\p{Word_Break = Newline}];
-$Extend       = [\p{Word_Break = Extend}];
-$Format       = [\p{Word_Break = Format}];
-$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}];
-$Numeric      = [\p{Word_Break = Numeric}];
-$ExtendNumLet = [\p{Word_Break = ExtendNumLet}];
-
-
-#   Dictionary character set, for triggering language-based break engines. Currently
-#   limited to LineBreak=Complex_Context. Note that this set only works in Unicode
-#   5.0 or later as the definition of Complex_Context was corrected to include all
-#   characters requiring dictionary break.
-
-$dictionary   = [:LineBreak = Complex_Context:];
-$Control        = [\p{Grapheme_Cluster_Break = Control}]; 
-$ALetterPlus  = [$ALetter [$dictionary-$Extend-$Control]];   # Note:  default ALetter does not
-                                                             #  include the dictionary characters.
-
-#
-#  Rules 4    Ignore Format and Extend characters, 
-#             except when they appear at the beginning of a region of text.
-#
-$KatakanaEx     = $Katakana     ($Extend |  $Format)*;
-$ALetterEx      = $ALetterPlus  ($Extend |  $Format)*;
-$MidNumLetEx    = $MidNumLet    ($Extend |  $Format)*;
-$MidLetterEx    = $MidLetter    ($Extend |  $Format)*;
-$MidNumEx       = $MidNum       ($Extend |  $Format)*;
-$NumericEx      = $Numeric      ($Extend |  $Format)*;
-$ExtendNumLetEx = $ExtendNumLet ($Extend |  $Format)*;
-
-$Hiragana       = [\p{script=Hiragana}];
-$Ideographic    = [\p{Ideographic} [\u3005 \u3007 \u303B]];
-$HiraganaEx     = $Hiragana     ($Extend |  $Format)*;
-$IdeographicEx  = $Ideographic  ($Extend |  $Format)*;
-
-## -------------------------------------------------
-
-!!forward;
-
-
-# Rule 3 - CR x LF
-#
-$CR $LF;
-
-# Rule 4 - ignore Format and Extend characters, except when they appear at the beginning
-#          of a region of Text.   The rule here comes into play when the start of text
-#          begins with a group of Format chars, or with a "word" consisting of a single
-#          char that is not in any of the listed word break categories followed by
-#          format char(s).
-[^$CR $LF $Newline]? ($Extend |  $Format)+;
-
-$NumericEx {100};
-$ALetterEx {200};
-$KatakanaEx {300};       # note:  these status values override those from rule 5
-$HiraganaEx {300};       #        by virtual of being numerically larger.
-$IdeographicEx {400};    #
-
-#
-# rule 5
-#    Do not break between most letters.
-#
-$ALetterEx $ALetterEx {200};
-
-# rule 6 and 7
-$ALetterEx ($MidLetterEx | $MidNumLetEx) $ALetterEx {200};
-
-# rule 8
-
-$NumericEx $NumericEx {100};
-
-# rule 9
-
-$ALetterEx $NumericEx {200};
-
-# rule 10
-
-$NumericEx $ALetterEx {200};
-
-# rule 11 and 12 
-
-$NumericEx ($MidNumEx | $MidNumLetEx) $NumericEx {100};
-
-# rule 13
-
-$KatakanaEx  $KatakanaEx {300};
-$HiraganaEx    $HiraganaEx {300};
-$IdeographicEx $IdeographicEx {400};
-
-
-# rule 13a/b
-
-$ALetterEx      $ExtendNumLetEx {200};    #  (13a)
-$NumericEx      $ExtendNumLetEx {100};    #  (13a)
-$KatakanaEx     $ExtendNumLetEx {300};    #  (13a)
-$ExtendNumLetEx $ExtendNumLetEx {200};    #  (13a)
-
-$ExtendNumLetEx $ALetterEx  {200};    #  (13b)
-$ExtendNumLetEx $NumericEx  {100};    #  (13b)
-$ExtendNumLetEx $KatakanaEx {300};    #  (13b)
- 
-
-
-## -------------------------------------------------
-
-!!reverse;
-
-$BackALetterEx     = ($Format | $Extend)* $ALetterPlus;
-$BackMidNumLetEx   = ($Format | $Extend)* $MidNumLet;
-$BackNumericEx     = ($Format | $Extend)* $Numeric;
-$BackMidNumEx      = ($Format | $Extend)* $MidNum;
-$BackMidLetterEx   = ($Format | $Extend)* $MidLetter;
-$BackKatakanaEx    = ($Format | $Extend)* $Katakana;
-$BackHiraganaEx    = ($Format | $Extend)* $Hiragana;
-$BackIdeographicEx = ($Format | $Extend)* $Ideographic;
-$BackExtendNumLetEx= ($Format | $Extend)* $ExtendNumLet;
-
-# rule 3
-$LF $CR;
-
-# rule 4
-($Format | $Extend)*  [^$CR $LF $Newline]?;
-
-# rule 5
-
-$BackALetterEx $BackALetterEx;
-
-# rule 6 and 7
-
-$BackALetterEx ($BackMidLetterEx | $BackMidNumLetEx) $BackALetterEx;
-
-
-# rule 8
-
-$BackNumericEx $BackNumericEx;
-
-# rule 9
-
-$BackNumericEx $BackALetterEx;
-
-# rule 10
-
-$BackALetterEx $BackNumericEx;
-
-# rule 11 and 12
-
-$BackNumericEx ($BackMidNumEx | $BackMidNumLetEx) $BackNumericEx;
-
-# rule 13
-
-$BackKatakanaEx $BackKatakanaEx;
-$BackHiraganaEx $BackHiraganaEx;
-$BackIdeographicEx $BackIdeographicEx;
-
-
-
-# rules 13 a/b
-#
-$BackExtendNumLetEx ($BackALetterEx | $BackNumericEx | $BackKatakanaEx | $BackExtendNumLetEx);
-($BackALetterEx | $BackNumericEx | $BackKatakanaEx) $BackExtendNumLetEx; 
-
-## -------------------------------------------------
-
-!!safe_reverse;
-
-# rule 3
-($Extend | $Format)+ .?;
-
-# rule 6
-($MidLetter | $MidNumLet) $BackALetterEx;
-
-# rule 11
-($MidNum | $MidNumLet) $BackNumericEx;
-
-# For dictionary-based break
-$dictionary $dictionary;
-
-## -------------------------------------------------
-
-!!safe_forward;
-
-# rule 4
-($Extend | $Format)+ .?;
-
-# rule 6
-($MidLetterEx | $MidNumLetEx) $ALetterEx;
-
-# rule 11
-($MidNumEx | $MidNumLetEx) $NumericEx;
-
-# For dictionary-based break
-$dictionary $dictionary;

diff --git a/icu4c/source/data/makedata.mak b/icu4c/source/data/makedata.mak
index b64722ff665e8cb6dbab9adc2b467fc85d7bfae1..6c66f274b50cd62772acab7595f9cdc57cf87baf 100644 (file)
--- a/icu4c/source/data/makedata.mak
+++ b/icu4c/source/data/makedata.mak
@@ -253,9 +253,9 @@ BRK_FILES=$(BRK_FILES:.txt=.brk)
 BRK_FILES=$(BRK_FILES:brkitr\ =brkitr\)
 
 !IFDEF BRK_DICT_SOURCE
-BRK_DICT_FILES = $(ICUBRK)\$(BRK_DICT_SOURCE):.txt=.dict brkitr\)
+BRK_DICT_FILES = $(ICUBRK)\$(BRK_DICT_SOURCE:.txt =.dict brkitr\)
 BRK_DICT_FILES = $(BRK_DICT_FILES:.txt=.dict)
-BRK_DICT_FILES = $(BRK_DICT_FILES:brkitr\ =)
+BRK_DICT_FILES = $(BRK_DICT_FILES:brkitr\ =brkitr\)
 !ENDIF
 
 !IFDEF BRK_RES_SOURCE
@@ -360,9 +360,6 @@ ZONE_SOURCE=$(ZONE_SOURCE) $(ZONE_SOURCE_LOCAL)
 !MESSAGE Warning: cannot find "zone\resfiles.mk"
 !ENDIF
 
-BRK_DICT_FILES = $(ICUBRK)\$(BRK_DICT_SOURCE):.txt=.dict brkitr\)
-BRK_DICT_FILES = $(BRK_DICT_FILES:.txt=.dict)
-BRK_DICT_FILES = $(BRK_DICT_FILES:brkitr\ =)
 !IFDEF ZONE_SOURCE
 ZONE_FILES = zone\root.txt $(ZONE_ALIAS_SOURCE) $(ZONE_SOURCE)
 ZONE_RES_FILES = $(ZONE_FILES:.txt =.res zone\)
@@ -640,7 +637,7 @@ $(TRANSLIT_RES_FILES:.res =.res
 )
 $(BRK_FILES:.brk =.brk
 )
-$(BRK_DICT_FILES:.dict=.dict
+$(BRK_DICT_FILES:.dict =.dict
 )
 $(BRK_RES_FILES:.res =.res
 )
@@ -740,7 +737,15 @@ CLEAN : GODATA
 #RBBI .dict file generation.
 {$(ICUSRCDATA_RELATIVE_PATH)\$(ICUBRK)}.txt.dict:
     @echo Creating $@
-    @"$(ICUTOOLS)\gendict\$(CFG)\gendict" -c --uchars -i "$(ICUBLD_PKG)" $< $(ICUBLD_PKG)\$@
+    @"$(ICUTOOLS)\gendict\$(CFG)\gendict" -c --uchars $<  $(ICUBLD_PKG)\$@
+
+$(ICUBRK)\thaidict.dict:
+       @echo Creating $(ICUBRK)\thaidict.dict
+       @"$(ICUTOOLS)\gendict\$(CFG)\gendict" -c --bytes --transform offset-0xe00 $(ICUSRCDATA_RELATIVE_PATH)\$(ICUBRK)\thaidict.txt $(ICUBLD_PKG)\$(ICUBRK)\thaidict.dict
+
+$(ICUBRK)\khmerdict.dict:
+       @echo Creating $(ICUBRK)\khmerdict.dict
+       @"$(ICUTOOLS)\gendict\$(CFG)\gendict" -c --bytes --transform offset-0x1780 $(ICUSRCDATA_RELATIVE_PATH)\$(ICUBRK)\khmerdict.txt $(ICUBLD_PKG)\$(ICUBRK)\khmerdict.dict
 
 !IFNDEF ICUDATA_SOURCE_ARCHIVE
 # Rule for creating converters