summaryrefslogtreecommitdiff
path: root/extra/libreoffice/fix_broken_hebrew_wordwrapping.diff
blob: ba4850c77790865942d6eee048acf96e0425bd0a (plain)
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
From 20c24114143d6d38774b56a142fd4ae05094308e Mon Sep 17 00:00:00 2001
From: Caolán McNamara <caolanm@redhat.com>
Date: Sun, 13 May 2012 21:41:30 +0000
Subject: Resolves: fdo#49849 implement Unicode 6.1 hebrew line breaking rules

i.e.  sync with svn diff -c 31071
http://source.icu-project.org/repos/icu/icu/trunk/source/data/brkitr/line.txt

Change-Id: I I I41b3d02f1a0da3b83a9684f29d466660d96254c6
---
diff --git a/i18npool/qa/cppunit/test_breakiterator.cxx b/i18npool/qa/cppunit/test_breakiterator.cxx
index 14051d4..ffd590c 100644
--- a/i18npool/qa/cppunit/test_breakiterator.cxx
+++ b/i18npool/qa/cppunit/test_breakiterator.cxx
@@ -42,6 +42,7 @@
 #include <unotest/bootstrapfixturebase.hxx>
 
 #include <rtl/strbuf.hxx>
+#include <rtl/ustrbuf.hxx>
 
 #include <string.h>
 
@@ -58,6 +59,9 @@ public:
     void testWeak();
     void testAsian();
     void testThai();
+#if TODO
+    void testNorthernThai();
+#endif
 
     CPPUNIT_TEST_SUITE(TestBreakIterator);
     CPPUNIT_TEST(testLineBreaking);
@@ -71,6 +71,9 @@
     CPPUNIT_TEST(testWeak);
     CPPUNIT_TEST(testAsian);
     CPPUNIT_TEST(testThai);
+#if TODO
+    CPPUNIT_TEST(testNorthernThai);
+#endif
     CPPUNIT_TEST_SUITE_END();
 
 private:
@@ -80,28 +83,46 @@
     uno::Reference<i18n::XBreakIterator> m_xBreak;
 };
 
-//See https://bugs.freedesktop.org/show_bug.cgi?id=31271 for motivation
 void TestBreakIterator::testLineBreaking()
 {
-    ::rtl::OUString aTest1(RTL_CONSTASCII_USTRINGPARAM("(some text here)"));
-
     i18n::LineBreakHyphenationOptions aHyphOptions;
     i18n::LineBreakUserOptions aUserOptions;
     lang::Locale aLocale;
 
-    aLocale.Language = ::rtl::OUString(RTL_CONSTASCII_USTRINGPARAM("en"));
-    aLocale.Country = ::rtl::OUString(RTL_CONSTASCII_USTRINGPARAM("US"));
-
+    //See https://bugs.freedesktop.org/show_bug.cgi?id=31271
     {
-        //Here we want the line break to leave text here) on the next line
-        i18n::LineBreakResults aResult = m_xBreak->getLineBreak(aTest1, strlen("(some tex"), aLocale, 0, aHyphOptions, aUserOptions);
-        CPPUNIT_ASSERT_MESSAGE("Expected a break at the the start of the word", aResult.breakIndex == 6);
+         ::rtl::OUString aTest(RTL_CONSTASCII_USTRINGPARAM("(some text here)"));
+
+        aLocale.Language = ::rtl::OUString(RTL_CONSTASCII_USTRINGPARAM("en"));
+        aLocale.Country = ::rtl::OUString(RTL_CONSTASCII_USTRINGPARAM("US"));
+
+        {
+            //Here we want the line break to leave text here) on the next line
+            i18n::LineBreakResults aResult = m_xBreak->getLineBreak(aTest, strlen("(some tex"), aLocale, 0, aHyphOptions, aUserOptions);
+            CPPUNIT_ASSERT_MESSAGE("Expected a break at the the start of the word", aResult.breakIndex == 6);
+        }
+
+        {
+            //Here we want the line break to leave "here)" on the next line
+            i18n::LineBreakResults aResult = m_xBreak->getLineBreak(aTest, strlen("(some text here"), aLocale, 0, aHyphOptions, aUserOptions);
+            CPPUNIT_ASSERT_MESSAGE("Expected a break at the the start of the word", aResult.breakIndex == 11);
+        }
     }
 
+    //See https://bugs.freedesktop.org/show_bug.cgi?id=49849
     {
-        //Here we want the line break to leave "here)" on the next line
-        i18n::LineBreakResults aResult = m_xBreak->getLineBreak(aTest1, strlen("(some text here"), aLocale, 0, aHyphOptions, aUserOptions);
-        CPPUNIT_ASSERT_MESSAGE("Expected a break at the the start of the word", aResult.breakIndex == 11);
+        const sal_Unicode HEBREW1[] = { 0x05DE, 0x05D9, 0x05DC, 0x05D9, 0x5DD };
+        ::rtl::OUString aWord(HEBREW1, SAL_N_ELEMENTS(HEBREW1));
+        ::rtl::OUString aTest(rtl::OUStringBuffer(aWord).append(' ').append(aWord).makeStringAndClear());
+
+        aLocale.Language = ::rtl::OUString(RTL_CONSTASCII_USTRINGPARAM("he"));
+        aLocale.Country = ::rtl::OUString(RTL_CONSTASCII_USTRINGPARAM("IL"));
+
+        {
+            //Here we want the line break to happen at the whitespace
+            i18n::LineBreakResults aResult = m_xBreak->getLineBreak(aTest, aTest.getLength()-1, aLocale, 0, aHyphOptions, aUserOptions);
+            CPPUNIT_ASSERT_MESSAGE("Expected a break at the the start of the word", aResult.breakIndex == aWord.getLength()+1);
+        }
     }
 }
 
@@ -295,27 +320,29 @@ void TestBreakIterator::testThai()
     aLocale.Language = ::rtl::OUString(RTL_CONSTASCII_USTRINGPARAM("th"));
     aLocale.Country = ::rtl::OUString(RTL_CONSTASCII_USTRINGPARAM("TH"));
 
-    i18n::Boundary aBounds;
-    {
-        const sal_Unicode THAI1[] = { 0x0E01, 0x0E38, 0x0E2B, 0x0E25, 0x0E32, 0x0E1A };
-        ::rtl::OUString aTest(THAI1, SAL_N_ELEMENTS(THAI1));
-        aBounds = m_xBreak->getWordBoundary(aTest, 0, aLocale,
-            i18n::WordType::DICTIONARY_WORD, true);
-        CPPUNIT_ASSERT_MESSAGE("Should skip full word",
-            aBounds.startPos == 0 && aBounds.endPos == aTest.getLength());
-    }
+    const sal_Unicode THAI1[] = { 0x0E01, 0x0E38, 0x0E2B, 0x0E25, 0x0E32, 0x0E1A };
+    ::rtl::OUString aTest(THAI1, SAL_N_ELEMENTS(THAI1));
+    i18n::Boundary aBounds = m_xBreak->getWordBoundary(aTest, 0, aLocale,
+        i18n::WordType::DICTIONARY_WORD, true);
+    CPPUNIT_ASSERT_MESSAGE("Should skip full word",
+        aBounds.startPos == 0 && aBounds.endPos == aTest.getLength());
+}
 
-#ifdef TODO
-    {
-        const sal_Unicode NORTHERN_THAI1[] = { 0x0E01, 0x0E38, 0x0E4A, 0x0E2B, 0x0E25, 0x0E32, 0x0E1A };
-        ::rtl::OUString aTest(NORTHERN_THAI1, SAL_N_ELEMENTS(NORTHERN_THAI1));
-        aBounds = m_xBreak->getWordBoundary(aTest, 0, aLocale,
-            i18n::WordType::DICTIONARY_WORD, true);
-        CPPUNIT_ASSERT_MESSAGE("Should skip full word",
-            aBounds.startPos == 0 && aBounds.endPos == aTest.getLength());
-    }
-#endif
+#if TODO
+void TestBreakIterator::testNorthernThai()
+{
+    lang::Locale aLocale;
+    aLocale.Language = ::rtl::OUString(RTL_CONSTASCII_USTRINGPARAM("nod"));
+    aLocale.Country = ::rtl::OUString(RTL_CONSTASCII_USTRINGPARAM("TH"));
+
+    const sal_Unicode NORTHERN_THAI1[] = { 0x0E01, 0x0E38, 0x0E4A, 0x0E2B, 0x0E25, 0x0E32, 0x0E1A };
+    ::rtl::OUString aTest(NORTHERN_THAI1, SAL_N_ELEMENTS(NORTHERN_THAI1));
+    i18n::Boundary aBounds = m_xBreak->getWordBoundary(aTest, 0, aLocale,
+        i18n::WordType::DICTIONARY_WORD, true);
+    CPPUNIT_ASSERT_MESSAGE("Should skip full word",
+        aBounds.startPos == 0 && aBounds.endPos == aTest.getLength());
 }
+#endif
 
 void TestBreakIterator::setUp()
 {
diff --git a/i18npool/source/breakiterator/data/README b/i18npool/source/breakiterator/data/README
new file mode 100644
index 0000000..8d7598d
--- a/dev/null
+++ b/i18npool/source/breakiterator/data/README
@@ -0,0 +1,12 @@
+The originals of these come from svn checkout
+http://source.icu-project.org/repos/icu/icu/trunk/source/data/brkitr they no
+longer appear in the icu tarballs, but are in icu's svn
+
+At various stages these copies have been customized and are not horribly out of
+sync. It unclear which diffs from the base versions are deliberate and which
+are now accidental :-(
+
+We need to review the various issues referenced in the commits that caused
+custimizations and see if they're still relevant or not, write regression tests
+for them, if any are still relavant then apply the changes back on top of the
+latest versions.
diff --git a/i18npool/source/breakiterator/data/line.txt b/i18npool/source/breakiterator/data/line.txt
index cbabee6..91c8f3d 100644
--- a/i18npool/source/breakiterator/data/line.txt
+++ b/i18npool/source/breakiterator/data/line.txt
@@ -61,11 +61,13 @@ $BB = [:LineBreak =  Break_Before:];
 $BK = [:LineBreak =  Mandatory_Break:];
 $B2 = [:LineBreak =  Break_Both:];
 $CB = [:LineBreak =  Contingent_Break:];
+$CJ = [:LineBreak =  Conditional_Japanese_Starter:];
 $CL = [:LineBreak =  Close_Punctuation:] ;
 $CM = [:LineBreak =  Combining_Mark:];
 $CR = [:LineBreak =  Carriage_Return:];
 $EX = [:LineBreak =  Exclamation:];
 $GL = [:LineBreak =  Glue:];
+$HL = [:LineBreak =  Hebrew_Letter:];
 $HY = [:LineBreak =  Hyphen:];
 $H2 = [:LineBreak =  H2:];
 $H3 = [:LineBreak =  H3:];
@@ -77,7 +79,7 @@ $JV = [:LineBreak =  JV:];
 $JT = [:LineBreak =  JT:];
 $LF = [:LineBreak =  Line_Feed:];
 $NL = [:LineBreak =  Next_Line:];
-$NS = [:LineBreak =  Nonstarter:];
+$NS = [[:LineBreak =  Nonstarter:] $CJ];
 $NU = [:LineBreak =  Numeric:];
 $OP = [[:LineBreak =  Open_Punctuation:] - $DG];
 $PO = [:LineBreak =  Postfix_Numeric:];
@@ -118,6 +120,7 @@ $B2cm = $B2 $CM*;
 $CLcm = $CL $CM*;
 $EXcm = $EX $CM*;
 $GLcm = $GL $CM*;
+$HLcm = $HL $CM*;
 $HYcm = $HY $CM*;
 $H2cm = $H2 $CM*;
 $H3cm = $H3 $CM*;
@@ -150,6 +153,7 @@ $B2 $CM+;
 $CL $CM+;
 $EX $CM+;
 $GL $CM+;
+$HL $CM+;
 $HY $CM+;
 $H2 $CM+;
 $H3 $CM+;
@@ -186,7 +190,7 @@ $CANT_CM = [ $SP $BK $CR $LF $NL $ZW $CM];       # Bases that can't take CMs
 #            so for this one case we need to manually list out longer sequences.
 #
 $AL_FOLLOW_NOCM = [$BK $CR $LF $NL $ZW $SP];
-$AL_FOLLOW_CM   = [$CL $EX $IS $SY $WJ $GL $QU $BA $HY $NS $IN $NU $ALPlus $OP];
+$AL_FOLLOW_CM   = [$CL $EX $HL $IS $SY $WJ $GL $QU $BA $HY $NS $IN $NU $ALPlus $OP];
 $AL_FOLLOW      = [$AL_FOLLOW_NOCM $AL_FOLLOW_CM];
 
 
@@ -320,8 +324,13 @@ $LB20NonBreaks $CM* ($BAcm | $HYcm | $NScm);
 $BBcm [^$CB];                                  #  $BB  x
 $BBcm $LB20NonBreaks $CM*;
 
+# LB 21a Don't break after Hebrew + Hyphen
+#   HL (HY | BA) x
+#  
+$HLcm ($HYcm | $BAcm) [^$CB]?;
+
 # LB 22
-$ALcm    $INcm;
+($ALcm | $HLcm) $INcm;
 $CM+     $INcm;     #  by rule 10, any otherwise unattached CM behaves as AL
 $IDcm    $INcm;
 $INcm    $INcm;
@@ -331,16 +340,18 @@ $NUcm    $INcm;
 # $LB 23
 $IDcm  $POcm;
 $ALcm  $NUcm;       # includes $LB19
+$HLcm  $NUcm;
 $CM+   $NUcm;       # Rule 10, any otherwise unattached CM behaves as AL
 $NUcm  $ALcm;
+$NUcm  $HLcm;
 
 #
 # LB 24
 #
 $PRcm $IDcm;
 $ALcm $PRcm;
-$PRcm $ALcm;
-$POcm $ALcm;
+$PRcm ($ALcm | $HLcm);
+$POcm ($ALcm | $HLcm);
 
 #
 # LB 25   Numbers.
@@ -361,8 +372,8 @@ $PRcm ($JLcm | $JVcm | $JTcm | $H2cm | $H3cm);
 
 # LB 28   Do not break between alphabetics
 #
-$ALcm $ALcm;
-$CM+ $ALcm;      # The $CM+ is from rule 10, and unattached CM is treated as AL
+($ALcm | $HLcm) ($ALcm | $HLcm);
+$CM+ ($ALcm | $HLcm);      # The $CM+ is from rule 10, an unattached CM is treated as AL
 
 # LB 29
 $IScm ($ALcm | $NUcm);
@@ -371,11 +382,9 @@ $IScm ($ALcm | $NUcm);
 # Rule 30   Do not break between letters, numbers or ordinary symbols
 #           and opening or closing punctuation
 #
-($ALcm | $NUcm) $OPcm;
+($ALcm | $HLcm | $NUcm) $OPcm;
 $CM+ $OPcm;
-$CLcm ($ALcm | $NUcm);
-
-
+$CLcm ($ALcm | $HLcm | $NUcm);
 
 #
 #  Reverse Rules.
@@ -391,6 +400,7 @@ $CM+ $B2;
 $CM+ $CL;
 $CM+ $EX;
 $CM+ $GL;
+$CM+ $HL;
 $CM+ $HY;
 $CM+ $H2;
 $CM+ $H3;
@@ -544,24 +554,25 @@ $CM* ($BA | $HY | $NS) $CM* [$LB20NonBreaks-$CM];     #  . x (BA | HY | NS)
 $CM* [$LB20NonBreaks-$CM] $CM* $BB;                   #  BB x .
 [^$CB] $CM* $BB;                                      # 
 
-
+# LB21a
+[^$CB] $CM* ($HY | $BA) $CM* $HL;
 
 # LB 22
-$CM* $IN $CM* $ALPlus;
+$CM* $IN $CM* ($ALPlus | $HL);
 $CM* $IN $CM* $ID;
 $CM* $IN $CM* $IN;
 $CM* $IN $CM* $NU;
 
 # LB 23
 $CM* $PO $CM* $ID;
-$CM* $NU $CM* $ALPlus;
-$CM* $ALPlus $CM* $NU;
+$CM* $NU $CM* ($ALPlus | $HL);
+$CM* ($ALPlus | $HL) $CM* $NU;
 
 # LB 24
 $CM* $ID $CM* $PR;
 $CM* $PR $CM* $ALPlus;
-$CM* $ALPlus $CM* $PR;
-$CM* $ALPlus $CM* $PO;
+$CM* ($ALPlus | $HL) $CM* $PR;
+$CM* ($ALPlus | $HL) $CM* $PO;
 
 $CM* $ALPlus $CM* ($IS | $SY | $HY)+ / $SP;
 $CM* $NU+ $CM* $HY+ / $SP;
@@ -580,15 +591,14 @@ $CM* $PO $CM* ($H3 | $H2 | $JT | $JV | $JL);
 $CM* ($H3 | $H2 | $JT | $JV | $JL) $CM* $PR;
 
 # LB 28
-$CM* $ALPlus $CM* $ALPlus;
-
+$CM* ($ALPlus | $HL) $CM* ($ALPlus | $HL);
 
 # LB 29
 $CM* ($NU | $ALPlus) $CM* $IS+ [^$SP];
 
 # LB 30
-$CM* $OP $CM* ($NU | $ALPlus);
-$CM* ($NU | $ALPlus) $CM* ($CL | $SY)+ [^$SP];
+$CM* $OP $CM* ($ALPlus | $HL | $NU);
+$CM* ($ALPlus | $HL | $NU) $CM* ($CL | $SY)+ [^$SP];
 
 
 ## -------------------------------------------------
@@ -609,6 +619,9 @@ $SP+ $CM* $QU;
 $SP+ $CM* $CL;
 $SP+ $CM* $B2;
 
+# LB 21
+$CM* ($HY | $BA) $CM* $HL;
+
 # LB 18
 ($CM* ($IS | $SY))+ $CM* $NU;
 $CL $CM* ($NU | $IS | $SY);
@@ -629,6 +642,6 @@ $dictionary $dictionary;
 #  turn off rule chaining.  We don't want to move more
 #  than necessary.
 #
-[$CM $OP $QU $CL $B2 $PR $HY $SP $dictionary]+ [^$CM $OP $QU $CL $B2 $PR $HY $dictionary];
+[$CM $OP $QU $CL $B2 $PR $HY $BA $SP $dictionary]+ [^$CM $OP $QU $CL $B2 $PR $HY $BA $dictionary];
 $dictionary $dictionary;
 
--
cgit v0.9.0.2-2-gbebe