ICU-22112 word break updates for @,colon; colon tailorings for fi,sv

See #2159
unicode-org · Aug 23, 2022 · 49d192f · 49d192f
1 parent 8c669a7
commit 49d192f
Show file tree

Hide file tree

Showing 18 changed files with 301 additions and 24 deletions.
diff --git a/icu4c/source/data/brkitr/fi.txt b/icu4c/source/data/brkitr/fi.txt
@@ -0,0 +1,8 @@
+// © 2016 and later: Unicode, Inc. and others.
+// License & terms of use: http://www.unicode.org/copyright.html
+// Generated using tools/cldr/cldr-to-icu/build-icu-data.xml
+fi{
+    boundaries{
+        word:process(dependency){"word_fi_sv.brk"}
+    }
+}
diff --git a/icu4c/source/data/brkitr/rules/word.txt b/icu4c/source/data/brkitr/rules/word.txt
@@ -11,7 +11,7 @@
 #      These rules are based on UAX #29 Revision 34 for Unicode Version 12.0
 #
 # Note:  Updates to word.txt will usually need to be merged into
-#        word_POSIX.txt also.
+#        word_POSIX.txt and word_fi_sv.txt also.
 
 ##############################################################################
 #
@@ -38,11 +38,11 @@ $Regional_Indicator = [\p{Word_Break = Regional_Indicator}];
 $Format             = [\p{Word_Break = Format}];
 $Katakana           = [\p{Word_Break = Katakana}];
 $Hebrew_Letter      = [\p{Word_Break = Hebrew_Letter}];
-$ALetter            = [\p{Word_Break = ALetter}];
+$ALetter            = [\p{Word_Break = ALetter} @];
 $Single_Quote       = [\p{Word_Break = Single_Quote}];
 $Double_Quote       = [\p{Word_Break = Double_Quote}];
 $MidNumLet          = [\p{Word_Break = MidNumLet}];
-$MidLetter          = [\p{Word_Break = MidLetter}];
+$MidLetter          = [\p{Word_Break = MidLetter} - [\: \uFE55 \uFF1A]];
 $MidNum             = [\p{Word_Break = MidNum}];
 $Numeric            = [\p{Word_Break = Numeric}];
 $ExtendNumLet       = [\p{Word_Break = ExtendNumLet}];

diff --git a/icu4c/source/data/brkitr/rules/word_POSIX.txt b/icu4c/source/data/brkitr/rules/word_POSIX.txt
@@ -38,11 +38,11 @@ $Regional_Indicator = [\p{Word_Break = Regional_Indicator}];
 $Format             = [\p{Word_Break = Format}];
 $Katakana           = [\p{Word_Break = Katakana}];
 $Hebrew_Letter      = [\p{Word_Break = Hebrew_Letter}];
-$ALetter            = [\p{Word_Break = ALetter}];
+$ALetter            = [\p{Word_Break = ALetter} @];
 $Single_Quote       = [\p{Word_Break = Single_Quote}];
 $Double_Quote       = [\p{Word_Break = Double_Quote}];
 $MidNumLet          = [\p{Word_Break = MidNumLet} - [.]];
-$MidLetter          = [\p{Word_Break = MidLetter} - [\:]];
+$MidLetter          = [\p{Word_Break = MidLetter} - [\: \uFE55 \uFF1A]];
 $MidNum             = [\p{Word_Break = MidNum} [.]];
 $Numeric            = [\p{Word_Break = Numeric}];
 $ExtendNumLet       = [\p{Word_Break = ExtendNumLet}];

diff --git a/icu4c/source/data/brkitr/rules/word_fi_sv.txt b/icu4c/source/data/brkitr/rules/word_fi_sv.txt
@@ -0,0 +1,172 @@
+#
+# Copyright (C) 2016 and later: Unicode, Inc. and others.
+# License & terms of use: http://www.unicode.org/copyright.html
+# Copyright (C) 2002-2016, International Business Machines Corporation
+# and others. All Rights Reserved.
+#
+# file:  word_fi_sv.txt
+#
+# ICU Word Break Rules
+#      See Unicode Standard Annex #29.
+#      These rules are based on UAX #29 Revision 34 for Unicode Version 12.0
+#
+# Note:  Updates to word.txt will usually need to be merged into
+#        word_fi_sv.txt also.
+
+##############################################################################
+#
+#  Character class definitions from TR 29
+#
+##############################################################################
+
+!!chain;
+!!quoted_literals_only;
+
+
+#
+#  Character Class Definitions.
+#
+
+$Han                = [:Han:];
+
+$CR                 = [\p{Word_Break = CR}];
+$LF                 = [\p{Word_Break = LF}];
+$Newline            = [\p{Word_Break = Newline}];
+$Extend             = [\p{Word_Break = Extend}-$Han];
+$ZWJ                = [\p{Word_Break = ZWJ}];
+$Regional_Indicator = [\p{Word_Break = Regional_Indicator}];
+$Format             = [\p{Word_Break = Format}];
+$Katakana           = [\p{Word_Break = Katakana}];
+$Hebrew_Letter      = [\p{Word_Break = Hebrew_Letter}];
+$ALetter            = [\p{Word_Break = ALetter} @];
+$Single_Quote       = [\p{Word_Break = Single_Quote}];
+$Double_Quote       = [\p{Word_Break = Double_Quote}];
+$MidNumLet          = [\p{Word_Break = MidNumLet}];
+$MidLetter          = [\p{Word_Break = MidLetter}];
+$MidNum             = [\p{Word_Break = MidNum}];
+$Numeric            = [\p{Word_Break = Numeric}];
+$ExtendNumLet       = [\p{Word_Break = ExtendNumLet}];
+$WSegSpace          = [\p{Word_Break = WSegSpace}];
+$Extended_Pict      = [\p{Extended_Pictographic}];
+
+$Hiragana           = [:Hiragana:];
+$Ideographic        = [\p{Ideographic}];
+
+
+#   Dictionary character set, for triggering language-based break engines. Currently
+#   limited to LineBreak=Complex_Context. Note that this set only works in Unicode
+#   5.0 or later as the definition of Complex_Context was corrected to include all
+#   characters requiring dictionary break.
+
+$Control        = [\p{Grapheme_Cluster_Break = Control}];
+$HangulSyllable = [\uac00-\ud7a3];
+$ComplexContext = [:LineBreak = Complex_Context:];
+$KanaKanji      = [$Han $Hiragana $Katakana];
+$dictionaryCJK  = [$KanaKanji $HangulSyllable];
+$dictionary     = [$ComplexContext $dictionaryCJK];
+
+# TODO: check if handling of katakana in dictionary makes rules incorrect/void
+
+# leave CJK scripts out of ALetterPlus
+$ALetterPlus  = [$ALetter-$dictionaryCJK [$ComplexContext-$Extend-$Control]];
+
+
+## -------------------------------------------------
+
+# Rule 3 - CR x LF
+#
+$CR $LF;
+
+# Rule 3c   Do not break within emoji zwj sequences.
+#             ZWJ ×  \p{Extended_Pictographic}.  Precedes WB4, so no intervening Extend chars allowed.
+#
+$ZWJ $Extended_Pict;
+
+# Rule 3d - Keep horizontal whitespace together.
+#
+$WSegSpace $WSegSpace;
+
+# Rule 4 - ignore Format and Extend characters, except when they appear at the beginning
+#          of a region of Text.
+
+$ExFm  = [$Extend $Format $ZWJ];
+
+^$ExFm+;            # This rule fires only when there are format or extend characters at the
+                    # start of text, or immediately following another boundary. It groups them, in
+                    # the event there are more than one.
+
+[^$CR $LF $Newline $ExFm] $ExFm*;   # This rule rule attaches trailing format/extends to words,
+                                    # with no special rule status value.
+
+$Numeric $ExFm* {100};              # This group of rules also attach trailing format/extends, but
+$ALetterPlus $ExFm* {200};          # with rule status set based on the word's final base character.
+$HangulSyllable {200};
+$Hebrew_Letter $ExFm* {200};
+$Katakana $ExFm* {400};             # note:  these status values override those from rule 5
+$Hiragana $ExFm* {400};             #        by virtue of being numerically larger.
+$Ideographic $ExFm* {400};          #
+
+#
+# rule 5
+#    Do not break between most letters.
+#
+($ALetterPlus | $Hebrew_Letter) $ExFm* ($ALetterPlus | $Hebrew_Letter);
+
+# rule 6 and 7
+($ALetterPlus | $Hebrew_Letter)  $ExFm* ($MidLetter | $MidNumLet | $Single_Quote) $ExFm* ($ALetterPlus | $Hebrew_Letter) {200};
+
+# rule 7a
+$Hebrew_Letter $ExFm* $Single_Quote {200};
+
+# rule 7b and 7c
+$Hebrew_Letter $ExFm* $Double_Quote $ExFm* $Hebrew_Letter;
+
+# rule 8
+
+$Numeric $ExFm* $Numeric;
+
+# rule 9
+
+($ALetterPlus | $Hebrew_Letter)  $ExFm* $Numeric;
+
+# rule 10
+
+$Numeric $ExFm* ($ALetterPlus | $Hebrew_Letter);
+
+# rule 11 and 12
+
+$Numeric $ExFm* ($MidNum | $MidNumLet | $Single_Quote) $ExFm* $Numeric;
+
+# rule 13
+# to be consistent with $KanaKanji $KanaKanhi, changed
+# from 300 to 400.
+# See also TestRuleStatus in intltest/rbbiapts.cpp
+$Katakana $ExFm*  $Katakana {400};
+
+# rule 13a/b
+
+$ALetterPlus   $ExFm* $ExtendNumLet {200};    #  (13a)
+$Hebrew_Letter $ExFm* $ExtendNumLet {200};    #  (13a)
+$Numeric       $ExFm* $ExtendNumLet {100};    #  (13a)
+$Katakana      $ExFm* $ExtendNumLet {400};    #  (13a)
+$ExtendNumLet  $ExFm* $ExtendNumLet {200};    #  (13a)
+
+$ExtendNumLet  $ExFm* $ALetterPlus  {200};    #  (13b)
+$ExtendNumLet  $ExFm* $Hebrew_Letter {200};    #  (13b)
+$ExtendNumLet  $ExFm* $Numeric      {100};    #  (13b)
+$ExtendNumLet  $ExFm* $Katakana     {400};    #  (13b)
+
+# rules 15 - 17
+#    Pairs of Regional Indicators stay together.
+#    With incoming rule chaining disabled by ^, this rule will match exactly two of them.
+#    No other rule begins with a Regional_Indicator, so chaining cannot extend the match.
+#
+^$Regional_Indicator $ExFm* $Regional_Indicator;
+
+# special handling for CJK characters: chain for later dictionary segmentation
+$HangulSyllable $HangulSyllable {200};
+$KanaKanji $KanaKanji {400}; # different rule status if both kana and kanji found
+
+# Rule 999
+#     Match a single code point if no other rule applies.
+.;
diff --git a/icu4c/source/data/brkitr/sv.txt b/icu4c/source/data/brkitr/sv.txt
@@ -0,0 +1,8 @@
+// © 2016 and later: Unicode, Inc. and others.
+// License & terms of use: http://www.unicode.org/copyright.html
+// Generated using tools/cldr/cldr-to-icu/build-icu-data.xml
+sv{
+    boundaries{
+        word:process(dependency){"word_fi_sv.brk"}
+    }
+}
diff --git a/icu4c/source/data/xml/brkitr/fi.xml b/icu4c/source/data/xml/brkitr/fi.xml
@@ -0,0 +1,26 @@
+<?xml version="1.0" encoding="UTF-8" ?>
+<!--
+ Copyright (C) 2016 and later: Unicode, Inc. and others.
+ License & terms of use: http://www.unicode.org/copyright.html
+ Copyright (c) 2010-2015 International Business Machines Corporation and others. All rights reserved.
+-->
+<!DOCTYPE ldml SYSTEM "../../dtd/cldr/common/dtd/ldml.dtd"
+[
+   <!ENTITY % icu SYSTEM "../../dtd/cldr/common/dtd/ldmlICU.dtd">
+   %icu;
+]
+>
+<ldml>
+    <identity>
+        <version number="$Revision$"/>
+        <language type="fi"/> 
+    </identity>
+    <special xmlns:icu="http://www.icu-project.org/">
+        <icu:breakIteratorData>
+            <icu:boundaries>
+                <icu:word icu:dependency="word_fi_sv.brk"/>
+            </icu:boundaries>
+        </icu:breakIteratorData>
+    </special>
+</ldml>
+
diff --git a/icu4c/source/data/xml/brkitr/sv.xml b/icu4c/source/data/xml/brkitr/sv.xml
@@ -0,0 +1,26 @@
+<?xml version="1.0" encoding="UTF-8" ?>
+<!--
+ Copyright (C) 2016 and later: Unicode, Inc. and others.
+ License & terms of use: http://www.unicode.org/copyright.html
+ Copyright (c) 2010-2015 International Business Machines Corporation and others. All rights reserved.
+-->
+<!DOCTYPE ldml SYSTEM "../../dtd/cldr/common/dtd/ldml.dtd"
+[
+   <!ENTITY % icu SYSTEM "../../dtd/cldr/common/dtd/ldmlICU.dtd">
+   %icu;
+]
+>
+<ldml>
+    <identity>
+        <version number="$Revision$"/>
+        <language type="sv"/> 
+    </identity>
+    <special xmlns:icu="http://www.icu-project.org/">
+        <icu:breakIteratorData>
+            <icu:boundaries>
+                <icu:word icu:dependency="word_fi_sv.brk"/>
+            </icu:boundaries>
+        </icu:breakIteratorData>
+    </special>
+</ldml>
+
diff --git a/icu4c/source/test/intltest/rbbitst.cpp b/icu4c/source/test/intltest/rbbitst.cpp
@@ -1264,12 +1264,17 @@ UBool RBBITest::testCaseIsKnownIssue(const UnicodeString &testCase, const char *
         {"21097", "LineBreakTest.txt", u"\uBD10\uC694\u002E\u0020\u0041\u002E\u0033\u0020\uBABB"},
         {"21097", "LineBreakTest.txt", u"\uC694\u002E\u0020\u0041\u002E\u0034\u0020\uBABB"},
         {"21097", "LineBreakTest.txt", u"a.2\u3000\u300C"},
+
+        // ICU-22127 until UAX #29 wordbreak is update for the colon changes in ICU-22112,
+        // need to skip some tests in WordBreakTest.txt
+        {"22127", "WordBreakTest.txt", u"a:"},
+        {"22127", "WordBreakTest.txt", u"A:"},
     };
 
     for (int n=0; n<UPRV_LENGTHOF(badTestCases); n++) {
         const TestCase &badCase = badTestCases[n];
         if (!strcmp(fileName, badCase.fFileName) &&
-                testCase == UnicodeString(badCase.fString)) {
+                testCase.startsWith(UnicodeString(badCase.fString))) {
             return logKnownIssue(badCase.fTicketNum);
         }
     }
@@ -1912,11 +1917,11 @@ RBBIWordMonkey::RBBIWordMonkey()
     fKatakanaSet      = new UnicodeSet(u"[\\p{Word_Break = Katakana}]",     status);
     fRegionalIndicatorSet =  new UnicodeSet(u"[\\p{Word_Break = Regional_Indicator}]", status);
     fHebrew_LetterSet = new UnicodeSet(u"[\\p{Word_Break = Hebrew_Letter}]", status);
-    fALetterSet       = new UnicodeSet(u"[\\p{Word_Break = ALetter}]", status);
+    fALetterSet       = new UnicodeSet(u"[\\p{Word_Break = ALetter} @]", status);
     fSingle_QuoteSet  = new UnicodeSet(u"[\\p{Word_Break = Single_Quote}]",    status);
     fDouble_QuoteSet  = new UnicodeSet(u"[\\p{Word_Break = Double_Quote}]",    status);
     fMidNumLetSet     = new UnicodeSet(u"[\\p{Word_Break = MidNumLet}]",    status);
-    fMidLetterSet     = new UnicodeSet(u"[\\p{Word_Break = MidLetter}]",    status);
+    fMidLetterSet     = new UnicodeSet(u"[\\p{Word_Break = MidLetter} - [\\: \\uFE55 \\uFF1A]]",    status);
     fMidNumSet        = new UnicodeSet(u"[\\p{Word_Break = MidNum}]",       status);
     fNumericSet       = new UnicodeSet(u"[\\p{Word_Break = Numeric}]", status);
     fFormatSet        = new UnicodeSet(u"[\\p{Word_Break = Format}]",       status);

diff --git a/icu4c/source/test/testdata/break_rules/word.txt b/icu4c/source/test/testdata/break_rules/word.txt
@@ -25,11 +25,11 @@ Regional_Indicator = [\p{Word_Break = Regional_Indicator}];
 Format             = [\p{Word_Break = Format}];
 Katakana           = [\p{Word_Break = Katakana}];
 Hebrew_Letter      = [\p{Word_Break = Hebrew_Letter}];
-ALetter            = [\p{Word_Break = ALetter}];
+ALetter            = [\p{Word_Break = ALetter} @];
 Single_Quote       = [\p{Word_Break = Single_Quote}];
 Double_Quote       = [\p{Word_Break = Double_Quote}];
 MidNumLet          = [\p{Word_Break = MidNumLet}];
-MidLetter          = [\p{Word_Break = MidLetter}];
+MidLetter          = [\p{Word_Break = MidLetter} - [\: \uFE55 \uFF1A]];
 MidNum             = [\p{Word_Break = MidNum}];
 Numeric            = [\p{Word_Break = Numeric}];
 ExtendNumLet       = [\p{Word_Break = ExtendNumLet}];

diff --git a/icu4c/source/test/testdata/break_rules/word_POSIX.txt b/icu4c/source/test/testdata/break_rules/word_POSIX.txt
@@ -28,7 +28,7 @@ ALetter            = [\p{Word_Break = ALetter}];
 Single_Quote       = [\p{Word_Break = Single_Quote}];
 Double_Quote       = [\p{Word_Break = Double_Quote}];
 MidNumLet          = [\p{Word_Break = MidNumLet} - [.]];
-MidLetter          = [\p{Word_Break = MidLetter} - [\:]];
+MidLetter          = [\p{Word_Break = MidLetter} - [\: \uFE55 \uFF1A]];
 MidNum             = [\p{Word_Break = MidNum} [.]];
 Numeric            = [\p{Word_Break = Numeric}];
 ExtendNumLet       = [\p{Word_Break = ExtendNumLet}];

diff --git a/icu4c/source/test/testdata/rbbitst.txt b/icu4c/source/test/testdata/rbbitst.txt
@@ -1583,16 +1583,32 @@ Bangkok)•</data>
 
 <locale en_US>
 <word>
-<data>•Can't<200> •have<200> •breaks<200> •in<200> •xx:yy<200> •or<200> •struct.field<200> \
+<data>•Can't<200> •have<200> •breaks<200> •in<200> •xx<200>:•yy<200> •or<200> •struct.field<200> \
 •for<200> •CS<200>-•types<200>.•</data>
 <data>•\uFF92\uFF76\uFF9E<400> •</data>
+<data>•xx@yy<200>.•</data>
 
 <locale en_US_POSIX>
 <word>
 <data>•Can't<200> •have<200> •breaks<200> •in<200> •xx<200>:•yy<200> •or<200> •struct<200>.•field<200> \
 •for<200> •CS<200>-•types<200>.•</data>
 <data>•\u06c9<200>\uc799\ufffa•</data>
 <data>•\uFF92\uFF76\uFF9E<400> •</data>
+<data>•xx@yy<200>.•</data>
+
+<locale fi>
+<word>
+<data>•Can't<200> •have<200> •breaks<200> •in<200> •xx:yy<200> •or<200> •struct.field<200> \
+•for<200> •CS<200>-•types<200>.•</data>
+<data>•\uFF92\uFF76\uFF9E<400> •</data>
+<data>•xx@yy<200>.•</data>
+
+<locale sv>
+<word>
+<data>•Can't<200> •have<200> •breaks<200> •in<200> •xx:yy<200> •or<200> •struct.field<200> \
+•for<200> •CS<200>-•types<200>.•</data>
+<data>•\uFF92\uFF76\uFF9E<400> •</data>
+<data>•xx@yy<200>.•</data>
 
 
 # UBreakIteratorType UBRK_CHARACTER, Locale "th"

diff --git a/icu4j/main/shared/data/icudata.jar b/icu4j/main/shared/data/icudata.jar
diff --git a/icu4j/main/shared/data/icutzdata.jar b/icu4j/main/shared/data/icutzdata.jar
diff --git a/icu4j/main/shared/data/testdata.jar b/icu4j/main/shared/data/testdata.jar