organicmaps/icu
13
Fork 0
mirror of https://github.com/unicode-org/icu.git synced 2025-04-15 09:45:26 +00:00
Code Issues 1 Projects Releases Wiki Activity Actions 1

ICU-22360 revert portions of #2159 which included @ in ALetter for wordbreak, update tests

Browse source 
(cherry picked from commit 5618203821)
This commit is contained in:
Peter Edberg 2023-05-05 10:29:54 -07:00 • committed by Peter Edberg
parent 6342f9140a
commit 6e72d90866
15 changed files with 19 additions and 19 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

2
icu4c/source/data/brkitr/rules/word.txt
View file

@ -38,7 +38,7 @@ $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}];

2
icu4c/source/data/brkitr/rules/word_POSIX.txt
View file

@ -38,7 +38,7 @@ $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} - [.]];

2
icu4c/source/data/brkitr/rules/word_fi_sv.txt
View file

@ -38,7 +38,7 @@ $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}];

2
icu4c/source/test/intltest/rbbitst.cpp
View file

@ -1937,7 +1937,7 @@ 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);

2
icu4c/source/test/testdata/break_rules/word.txt vendored
View file

@ -25,7 +25,7 @@ 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}];

8
icu4c/source/test/testdata/rbbitst.txt vendored
View file

@ -1586,7 +1586,7 @@ Bangkok)•</data>
<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>
<data>•xx<200>@•yy<200>.•</data>
<locale en_US_POSIX>
<word>
@ -1594,21 +1594,21 @@ Bangkok)•</data>
•for<200> •CS<200>-•types<200>.•</data>
<data>•\u06c9<200>\uc799\ufffa•</data>
<data>•\uFF92\uFF76\uFF9E<400> •</data>
<data>•xx@yy<200>.•</data>
<data>•xx<200>@•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>
<data>•xx<200>@•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>
<data>•xx<200>@•yy<200>.•</data>
# UBreakIteratorType UBRK_CHARACTER, Locale "th"

4
icu4j/main/shared/data/icudata.jar
View file

@ -1,3 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:88808b997ca13e786f5f6bdd95d05d7d9ba3fe6b12f6356b8b15bb4eb49d644e
size 14330312
oid sha256:9b764b3c6af6c9e8ed18770a1c758f9740aede42bdb435fe6cb3fa3f8a7846af
size 14330291

2
icu4j/main/shared/data/icutzdata.jar
View file

@ -1,3 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:affd9c4e150caed2894d4912763ef2cb95249f94e859d2b3298c5636ab124f50
oid sha256:57224bd406c99dd7242f9aeac1db8beaf6e0e1520646b4bedab404aa02c896a3
size 94829

2
icu4j/main/shared/data/testdata.jar
View file

@ -1,3 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:d5c5dd3ac8fca302041ec888963b800c61dd4003a8647515e193cec72967f871
oid sha256:0e466f0476161bdf5b82d33e164e44d2f0912156436057d53d949ee386bdc79d
size 831605

2
icu4j/main/tests/core/src/com/ibm/icu/dev/test/rbbi/RBBITestMonkey.java
View file

@ -400,7 +400,7 @@ public class RBBITestMonkey extends TestFmwk {
fRegionalIndicatorSet = new UnicodeSet("[\\p{Word_Break = Regional_Indicator}]");
fKatakanaSet = new UnicodeSet("[\\p{Word_Break = Katakana}]");
fHebrew_LetterSet = new UnicodeSet("[\\p{Word_Break = Hebrew_Letter}]");
fALetterSet = new UnicodeSet("[\\p{Word_Break = ALetter} @]");
fALetterSet = new UnicodeSet("[\\p{Word_Break = ALetter}]");
fSingle_QuoteSet = new UnicodeSet("[\\p{Word_Break = Single_Quote}]");
fDouble_QuoteSet = new UnicodeSet("[\\p{Word_Break = Double_Quote}]");
fMidNumLetSet = new UnicodeSet("[\\p{Word_Break = MidNumLet}]");

2
icu4j/main/tests/core/src/com/ibm/icu/dev/test/rbbi/break_rules/word.txt
View file

@ -25,7 +25,7 @@ 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}];

8
icu4j/main/tests/core/src/com/ibm/icu/dev/test/rbbi/rbbitst.txt
View file

@ -1586,7 +1586,7 @@ Bangkok)•</data>
<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>
<data>•xx<200>@•yy<200>.•</data>
<locale en_US_POSIX>
<word>
@ -1594,21 +1594,21 @@ Bangkok)•</data>
•for<200> •CS<200>-•types<200>.•</data>
<data>•\u06c9<200>\uc799\ufffa•</data>
<data>•\uFF92\uFF76\uFF9E<400> •</data>
<data>•xx@yy<200>.•</data>
<data>•xx<200>@•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>
<data>•xx<200>@•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>
<data>•xx<200>@•yy<200>.•</data>
# UBreakIteratorType UBRK_CHARACTER, Locale "th"

BIN
icu4j/maven-build/maven-icu4j-datafiles/src/main/resources/com/ibm/icu/impl/data/icudt73b/brkitr/word.brk
View file

Binary file not shown.

BIN
icu4j/maven-build/maven-icu4j-datafiles/src/main/resources/com/ibm/icu/impl/data/icudt73b/brkitr/word_POSIX.brk
View file

Binary file not shown.

BIN
icu4j/maven-build/maven-icu4j-datafiles/src/main/resources/com/ibm/icu/impl/data/icudt73b/brkitr/word_fi_sv.brk
View file

Binary file not shown.