summaryrefslogtreecommitdiff
path: root/external/icu/icu4c-khmerbreakengine.patch.1
diff options
context:
space:
mode:
Diffstat (limited to 'external/icu/icu4c-khmerbreakengine.patch.1')
-rw-r--r--external/icu/icu4c-khmerbreakengine.patch.189
1 files changed, 42 insertions, 47 deletions
diff --git a/external/icu/icu4c-khmerbreakengine.patch.1 b/external/icu/icu4c-khmerbreakengine.patch.1
index 0ce46ac473ec..719fdd846114 100644
--- a/external/icu/icu4c-khmerbreakengine.patch.1
+++ b/external/icu/icu4c-khmerbreakengine.patch.1
@@ -1,6 +1,6 @@
diff -ur icu.org/source/common/dictbe.cpp icu/source/common/dictbe.cpp
---- icu.org/source/common/dictbe.cpp 2021-04-08 02:10:27.000000000 +0200
-+++ icu/source/common/dictbe.cpp 2021-05-11 22:41:25.504455054 +0200
+--- icu.org/source/common/dictbe.cpp 2021-10-28 18:04:57.000000000 +0200
++++ icu/source/common/dictbe.cpp 2021-11-15 20:39:03.710870385 +0100
@@ -32,7 +32,19 @@
******************************************************************
*/
@@ -22,7 +22,7 @@ diff -ur icu.org/source/common/dictbe.cpp icu/source/common/dictbe.cpp
}
DictionaryBreakEngine::~DictionaryBreakEngine() {
-@@ -79,6 +91,169 @@
+@@ -81,6 +93,169 @@
fSet.compact();
}
@@ -192,7 +192,7 @@ diff -ur icu.org/source/common/dictbe.cpp icu/source/common/dictbe.cpp
/*
******************************************************************
* PossibleWord
-@@ -108,7 +283,7 @@
+@@ -110,7 +285,7 @@
~PossibleWord() {}
// Fill the list of candidates if needed, select the longest, and return the number found
@@ -201,7 +201,7 @@ diff -ur icu.org/source/common/dictbe.cpp icu/source/common/dictbe.cpp
// Select the currently marked candidate, point after it in the text, and invalidate self
int32_t acceptMarked( UText *text );
-@@ -129,12 +304,12 @@
+@@ -131,12 +306,12 @@
};
@@ -216,7 +216,7 @@ diff -ur icu.org/source/common/dictbe.cpp icu/source/common/dictbe.cpp
// Dictionary leaves text after longest prefix, not longest word. Back up.
if (count <= 0) {
utext_setNativeIndex(text, start);
-@@ -803,53 +978,30 @@
+@@ -808,53 +983,30 @@
* KhmerBreakEngine
*/
@@ -282,22 +282,13 @@ diff -ur icu.org/source/common/dictbe.cpp icu/source/common/dictbe.cpp
UTRACE_EXIT_STATUS(status);
}
-@@ -862,176 +1014,204 @@
- int32_t rangeStart,
- int32_t rangeEnd,
- UVector32 &foundBreaks ) const {
+@@ -869,175 +1021,204 @@
+ UVector32 &foundBreaks,
+ UErrorCode& status ) const {
+ if (U_FAILURE(status)) return 0;
- if ((rangeEnd - rangeStart) < KHMER_MIN_WORD_SPAN) {
- return 0; // Not enough characters for two words
-- }
--
-- uint32_t wordsFound = 0;
-- int32_t cpWordLength = 0;
-- int32_t cuWordLength = 0;
-- int32_t current;
+ uint32_t wordsFound = foundBreaks.size();
- UErrorCode status = U_ZERO_ERROR;
-- PossibleWord words[KHMER_LOOKAHEAD];
--
+ int32_t before = 0;
+ int32_t after = 0;
+ int32_t finalBefore = 0;
@@ -312,7 +303,14 @@ diff -ur icu.org/source/common/dictbe.cpp icu/source/common/dictbe.cpp
+ if (rangeStart > 0) {
+ --scanStart;
+ startZwsp = scanBeforeStart(text, scanStart, breakStart);
-+ }
+ }
+-
+- uint32_t wordsFound = 0;
+- int32_t cpWordLength = 0;
+- int32_t cuWordLength = 0;
+- int32_t current;
+- PossibleWord words[KHMER_LOOKAHEAD];
+-
utext_setNativeIndex(text, rangeStart);
+ scanFwdClusters(text, rangeEnd, initAfter);
+ bool endZwsp = scanAfterEnd(text, utext_nativeLength(text), scanEnd, breakEnd);
@@ -628,15 +626,15 @@ diff -ur icu.org/source/common/dictbe.cpp icu/source/common/dictbe.cpp
(void) foundBreaks.popi();
- wordsFound -= 1;
}
--
+
- return wordsFound;
+ return foundBreaks.size() - wordsFound;
}
#if !UCONFIG_NO_NORMALIZATION
diff -ur icu.org/source/common/dictbe.h icu/source/common/dictbe.h
---- icu.org/source/common/dictbe.h 2021-04-08 02:10:27.000000000 +0200
-+++ icu/source/common/dictbe.h 2021-05-11 22:37:49.753857647 +0200
+--- icu.org/source/common/dictbe.h 2021-10-28 18:04:57.000000000 +0200
++++ icu/source/common/dictbe.h 2021-11-15 20:41:53.052317579 +0100
@@ -34,7 +34,8 @@
* threads without synchronization.</p>
*/
@@ -733,28 +731,25 @@ diff -ur icu.org/source/common/dictbe.h icu/source/common/dictbe.h
* <p>Virtual destructor.</p>
*/
virtual ~DictionaryBreakEngine();
-@@ -293,11 +364,13 @@
- */
-
- UnicodeSet fKhmerWordSet;
-- UnicodeSet fEndWordSet;
-- UnicodeSet fBeginWordSet;
-- UnicodeSet fMarkSet;
-- DictionaryMatcher *fDictionary;
--
-+ UnicodeSet fBeginWordSet;
+@@ -303,10 +374,12 @@
+ */
+
+ UnicodeSet fKhmerWordSet;
+- UnicodeSet fEndWordSet;
+ UnicodeSet fBeginWordSet;
+- UnicodeSet fMarkSet;
+- DictionaryMatcher *fDictionary;
+ UnicodeSet fPuncSet;
+ DictionaryMatcher *fDictionary;
+
+ const uint32_t BADSNLP = 256 * 20;
+ const uint32_t kuint32max = 0x7FFFFFFF;
-+
- public:
-
- /**
+
+ public:
+
diff -ur icu.org/source/common/dictionarydata.cpp icu/source/common/dictionarydata.cpp
---- icu.org/source/common/dictionarydata.cpp 2021-04-08 02:10:27.000000000 +0200
-+++ icu/source/common/dictionarydata.cpp 2021-05-11 22:37:49.754857645 +0200
+--- icu.org/source/common/dictionarydata.cpp 2021-10-28 18:04:57.000000000 +0200
++++ icu/source/common/dictionarydata.cpp 2021-11-15 19:25:00.583694898 +0100
@@ -44,7 +44,7 @@
int32_t UCharsDictionaryMatcher::matches(UText *text, int32_t maxLength, int32_t limit,
@@ -802,8 +797,8 @@ diff -ur icu.org/source/common/dictionarydata.cpp icu/source/common/dictionaryda
if (values != NULL) {
values[wordCount] = bt.getValue();
diff -ur icu.org/source/common/dictionarydata.h icu/source/common/dictionarydata.h
---- icu.org/source/common/dictionarydata.h 2021-04-08 02:10:27.000000000 +0200
-+++ icu/source/common/dictionarydata.h 2021-05-11 22:37:49.754857645 +0200
+--- icu.org/source/common/dictionarydata.h 2021-10-28 18:04:57.000000000 +0200
++++ icu/source/common/dictionarydata.h 2021-11-15 20:44:34.484790590 +0100
@@ -21,6 +21,7 @@
#include "unicode/utext.h"
#include "unicode/udata.h"
@@ -825,17 +820,17 @@ diff -ur icu.org/source/common/dictionarydata.h icu/source/common/dictionarydata
virtual ~UCharsDictionaryMatcher();
virtual int32_t matches(UText *text, int32_t maxLength, int32_t limit,
int32_t *lengths, int32_t *cpLengths, int32_t *values,
-- int32_t *prefix) const;
-+ int32_t *prefix, UnicodeSet const* ignoreSet = NULL, int32_t minLength = 0) const;
- virtual int32_t getType() const;
+- int32_t *prefix) const override;
++ int32_t *prefix, UnicodeSet const* ignoreSet = NULL, int32_t minLength = 0) const override;
+ virtual int32_t getType() const override;
private:
const UChar *characters;
@@ -125,7 +126,7 @@
virtual ~BytesDictionaryMatcher();
virtual int32_t matches(UText *text, int32_t maxLength, int32_t limit,
int32_t *lengths, int32_t *cpLengths, int32_t *values,
-- int32_t *prefix) const;
-+ int32_t *prefix, UnicodeSet const* ignoreSet = NULL, int32_t minLength = 0) const;
- virtual int32_t getType() const;
+- int32_t *prefix) const override;
++ int32_t *prefix, UnicodeSet const* ignoreSet = NULL, int32_t minLength = 0) const override;
+ virtual int32_t getType() const override;
private:
UChar32 transform(UChar32 c) const;
generated by cgit (git 2.34.1) at 2024-08-10 22:30:16 +0000