| 1 |
scarabeus 12/05/29 09:02:20 |
| 2 |
|
| 3 |
Added: libreoffice-3.5-hebrew-icu49.patch |
| 4 |
Log: |
| 5 |
Revision bump to 3.5.4.2-r1 to fix issues with hebrew. Depend on icu-49 hard. Fixes bug#418095. |
| 6 |
|
| 7 |
(Portage version: 2.2.0_alpha108/cvs/Linux x86_64) |
| 8 |
|
| 9 |
Revision Changes Path |
| 10 |
1.1 app-office/libreoffice/files/libreoffice-3.5-hebrew-icu49.patch |
| 11 |
|
| 12 |
file : http://sources.gentoo.org/viewvc.cgi/gentoo-x86/app-office/libreoffice/files/libreoffice-3.5-hebrew-icu49.patch?rev=1.1&view=markup |
| 13 |
plain: http://sources.gentoo.org/viewvc.cgi/gentoo-x86/app-office/libreoffice/files/libreoffice-3.5-hebrew-icu49.patch?rev=1.1&content-type=text/plain |
| 14 |
|
| 15 |
Index: libreoffice-3.5-hebrew-icu49.patch |
| 16 |
=================================================================== |
| 17 |
From 20c24114143d6d38774b56a142fd4ae05094308e Mon Sep 17 00:00:00 2001 |
| 18 |
From: Caolán McNamara <caolanm@××××××.com> |
| 19 |
Date: Sun, 13 May 2012 21:41:30 +0000 |
| 20 |
Subject: Resolves: fdo#49849 implement Unicode 6.1 hebrew line breaking rules |
| 21 |
|
| 22 |
i.e. sync with svn diff -c 31071 |
| 23 |
http://source.icu-project.org/repos/icu/icu/trunk/source/data/brkitr/line.txt |
| 24 |
|
| 25 |
Change-Id: I I I41b3d02f1a0da3b83a9684f29d466660d96254c6 |
| 26 |
--- |
| 27 |
diff --git a/i18npool/source/breakiterator/data/line.txt b/i18npool/source/breakiterator/data/line.txt |
| 28 |
index cbabee6..91c8f3d 100644 |
| 29 |
--- a/i18npool/source/breakiterator/data/line.txt |
| 30 |
+++ b/i18npool/source/breakiterator/data/line.txt |
| 31 |
@@ -61,11 +61,13 @@ $BB = [:LineBreak = Break_Before:]; |
| 32 |
$BK = [:LineBreak = Mandatory_Break:]; |
| 33 |
$B2 = [:LineBreak = Break_Both:]; |
| 34 |
$CB = [:LineBreak = Contingent_Break:]; |
| 35 |
+$CJ = [:LineBreak = Conditional_Japanese_Starter:]; |
| 36 |
$CL = [:LineBreak = Close_Punctuation:] ; |
| 37 |
$CM = [:LineBreak = Combining_Mark:]; |
| 38 |
$CR = [:LineBreak = Carriage_Return:]; |
| 39 |
$EX = [:LineBreak = Exclamation:]; |
| 40 |
$GL = [:LineBreak = Glue:]; |
| 41 |
+$HL = [:LineBreak = Hebrew_Letter:]; |
| 42 |
$HY = [:LineBreak = Hyphen:]; |
| 43 |
$H2 = [:LineBreak = H2:]; |
| 44 |
$H3 = [:LineBreak = H3:]; |
| 45 |
@@ -77,7 +79,7 @@ $JV = [:LineBreak = JV:]; |
| 46 |
$JT = [:LineBreak = JT:]; |
| 47 |
$LF = [:LineBreak = Line_Feed:]; |
| 48 |
$NL = [:LineBreak = Next_Line:]; |
| 49 |
-$NS = [:LineBreak = Nonstarter:]; |
| 50 |
+$NS = [[:LineBreak = Nonstarter:] $CJ]; |
| 51 |
$NU = [:LineBreak = Numeric:]; |
| 52 |
$OP = [[:LineBreak = Open_Punctuation:] - $DG]; |
| 53 |
$PO = [:LineBreak = Postfix_Numeric:]; |
| 54 |
@@ -118,6 +120,7 @@ $B2cm = $B2 $CM*; |
| 55 |
$CLcm = $CL $CM*; |
| 56 |
$EXcm = $EX $CM*; |
| 57 |
$GLcm = $GL $CM*; |
| 58 |
+$HLcm = $HL $CM*; |
| 59 |
$HYcm = $HY $CM*; |
| 60 |
$H2cm = $H2 $CM*; |
| 61 |
$H3cm = $H3 $CM*; |
| 62 |
@@ -150,6 +153,7 @@ $B2 $CM+; |
| 63 |
$CL $CM+; |
| 64 |
$EX $CM+; |
| 65 |
$GL $CM+; |
| 66 |
+$HL $CM+; |
| 67 |
$HY $CM+; |
| 68 |
$H2 $CM+; |
| 69 |
$H3 $CM+; |
| 70 |
@@ -186,7 +190,7 @@ $CANT_CM = [ $SP $BK $CR $LF $NL $ZW $CM]; # Bases that can't take CMs |
| 71 |
# so for this one case we need to manually list out longer sequences. |
| 72 |
# |
| 73 |
$AL_FOLLOW_NOCM = [$BK $CR $LF $NL $ZW $SP]; |
| 74 |
-$AL_FOLLOW_CM = [$CL $EX $IS $SY $WJ $GL $QU $BA $HY $NS $IN $NU $ALPlus $OP]; |
| 75 |
+$AL_FOLLOW_CM = [$CL $EX $HL $IS $SY $WJ $GL $QU $BA $HY $NS $IN $NU $ALPlus $OP]; |
| 76 |
$AL_FOLLOW = [$AL_FOLLOW_NOCM $AL_FOLLOW_CM]; |
| 77 |
|
| 78 |
|
| 79 |
@@ -320,8 +324,13 @@ $LB20NonBreaks $CM* ($BAcm | $HYcm | $NScm); |
| 80 |
$BBcm [^$CB]; # $BB x |
| 81 |
$BBcm $LB20NonBreaks $CM*; |
| 82 |
|
| 83 |
+# LB 21a Don't break after Hebrew + Hyphen |
| 84 |
+# HL (HY | BA) x |
| 85 |
+# |
| 86 |
+$HLcm ($HYcm | $BAcm) [^$CB]?; |
| 87 |
+ |
| 88 |
# LB 22 |
| 89 |
-$ALcm $INcm; |
| 90 |
+($ALcm | $HLcm) $INcm; |
| 91 |
$CM+ $INcm; # by rule 10, any otherwise unattached CM behaves as AL |
| 92 |
$IDcm $INcm; |
| 93 |
$INcm $INcm; |
| 94 |
@@ -331,16 +340,18 @@ $NUcm $INcm; |
| 95 |
# $LB 23 |
| 96 |
$IDcm $POcm; |
| 97 |
$ALcm $NUcm; # includes $LB19 |
| 98 |
+$HLcm $NUcm; |
| 99 |
$CM+ $NUcm; # Rule 10, any otherwise unattached CM behaves as AL |
| 100 |
$NUcm $ALcm; |
| 101 |
+$NUcm $HLcm; |
| 102 |
|
| 103 |
# |
| 104 |
# LB 24 |
| 105 |
# |
| 106 |
$PRcm $IDcm; |
| 107 |
$ALcm $PRcm; |
| 108 |
-$PRcm $ALcm; |
| 109 |
-$POcm $ALcm; |
| 110 |
+$PRcm ($ALcm | $HLcm); |
| 111 |
+$POcm ($ALcm | $HLcm); |
| 112 |
|
| 113 |
# |
| 114 |
# LB 25 Numbers. |
| 115 |
@@ -361,8 +372,8 @@ $PRcm ($JLcm | $JVcm | $JTcm | $H2cm | $H3cm); |
| 116 |
|
| 117 |
# LB 28 Do not break between alphabetics |
| 118 |
# |
| 119 |
-$ALcm $ALcm; |
| 120 |
-$CM+ $ALcm; # The $CM+ is from rule 10, and unattached CM is treated as AL |
| 121 |
+($ALcm | $HLcm) ($ALcm | $HLcm); |
| 122 |
+$CM+ ($ALcm | $HLcm); # The $CM+ is from rule 10, an unattached CM is treated as AL |
| 123 |
|
| 124 |
# LB 29 |
| 125 |
$IScm ($ALcm | $NUcm); |
| 126 |
@@ -371,11 +382,9 @@ $IScm ($ALcm | $NUcm); |
| 127 |
# Rule 30 Do not break between letters, numbers or ordinary symbols |
| 128 |
# and opening or closing punctuation |
| 129 |
# |
| 130 |
-($ALcm | $NUcm) $OPcm; |
| 131 |
+($ALcm | $HLcm | $NUcm) $OPcm; |
| 132 |
$CM+ $OPcm; |
| 133 |
-$CLcm ($ALcm | $NUcm); |
| 134 |
- |
| 135 |
- |
| 136 |
+$CLcm ($ALcm | $HLcm | $NUcm); |
| 137 |
|
| 138 |
# |
| 139 |
# Reverse Rules. |
| 140 |
@@ -391,6 +400,7 @@ $CM+ $B2; |
| 141 |
$CM+ $CL; |
| 142 |
$CM+ $EX; |
| 143 |
$CM+ $GL; |
| 144 |
+$CM+ $HL; |
| 145 |
$CM+ $HY; |
| 146 |
$CM+ $H2; |
| 147 |
$CM+ $H3; |
| 148 |
@@ -544,24 +554,25 @@ $CM* ($BA | $HY | $NS) $CM* [$LB20NonBreaks-$CM]; # . x (BA | HY | NS) |
| 149 |
$CM* [$LB20NonBreaks-$CM] $CM* $BB; # BB x . |
| 150 |
[^$CB] $CM* $BB; # |
| 151 |
|
| 152 |
- |
| 153 |
+# LB21a |
| 154 |
+[^$CB] $CM* ($HY | $BA) $CM* $HL; |
| 155 |
|
| 156 |
# LB 22 |
| 157 |
-$CM* $IN $CM* $ALPlus; |
| 158 |
+$CM* $IN $CM* ($ALPlus | $HL); |
| 159 |
$CM* $IN $CM* $ID; |
| 160 |
$CM* $IN $CM* $IN; |
| 161 |
$CM* $IN $CM* $NU; |
| 162 |
|
| 163 |
# LB 23 |
| 164 |
$CM* $PO $CM* $ID; |
| 165 |
-$CM* $NU $CM* $ALPlus; |
| 166 |
-$CM* $ALPlus $CM* $NU; |
| 167 |
+$CM* $NU $CM* ($ALPlus | $HL); |
| 168 |
+$CM* ($ALPlus | $HL) $CM* $NU; |
| 169 |
|
| 170 |
# LB 24 |
| 171 |
$CM* $ID $CM* $PR; |
| 172 |
$CM* $PR $CM* $ALPlus; |
| 173 |
-$CM* $ALPlus $CM* $PR; |
| 174 |
-$CM* $ALPlus $CM* $PO; |
| 175 |
+$CM* ($ALPlus | $HL) $CM* $PR; |
| 176 |
+$CM* ($ALPlus | $HL) $CM* $PO; |
| 177 |
|
| 178 |
$CM* $ALPlus $CM* ($IS | $SY | $HY)+ / $SP; |
| 179 |
$CM* $NU+ $CM* $HY+ / $SP; |
| 180 |
@@ -580,15 +591,14 @@ $CM* $PO $CM* ($H3 | $H2 | $JT | $JV | $JL); |
| 181 |
$CM* ($H3 | $H2 | $JT | $JV | $JL) $CM* $PR; |
| 182 |
|
| 183 |
# LB 28 |
| 184 |
-$CM* $ALPlus $CM* $ALPlus; |
| 185 |
- |
| 186 |
+$CM* ($ALPlus | $HL) $CM* ($ALPlus | $HL); |
| 187 |
|
| 188 |
# LB 29 |
| 189 |
$CM* ($NU | $ALPlus) $CM* $IS+ [^$SP]; |
| 190 |
|
| 191 |
# LB 30 |
| 192 |
-$CM* $OP $CM* ($NU | $ALPlus); |
| 193 |
-$CM* ($NU | $ALPlus) $CM* ($CL | $SY)+ [^$SP]; |
| 194 |
+$CM* $OP $CM* ($ALPlus | $HL | $NU); |
| 195 |
+$CM* ($ALPlus | $HL | $NU) $CM* ($CL | $SY)+ [^$SP]; |
| 196 |
|
| 197 |
|
| 198 |
## ------------------------------------------------- |
| 199 |
@@ -609,6 +619,9 @@ $SP+ $CM* $QU; |
| 200 |
$SP+ $CM* $CL; |
| 201 |
$SP+ $CM* $B2; |
| 202 |
|
| 203 |
+# LB 21 |
| 204 |
+$CM* ($HY | $BA) $CM* $HL; |
| 205 |
+ |
| 206 |
# LB 18 |
| 207 |
($CM* ($IS | $SY))+ $CM* $NU; |
| 208 |
$CL $CM* ($NU | $IS | $SY); |
| 209 |
@@ -629,6 +642,6 @@ $dictionary $dictionary; |
| 210 |
# turn off rule chaining. We don't want to move more |
| 211 |
# than necessary. |
| 212 |
# |
| 213 |
-[$CM $OP $QU $CL $B2 $PR $HY $SP $dictionary]+ [^$CM $OP $QU $CL $B2 $PR $HY $dictionary]; |
| 214 |
+[$CM $OP $QU $CL $B2 $PR $HY $BA $SP $dictionary]+ [^$CM $OP $QU $CL $B2 $PR $HY $BA $dictionary]; |
| 215 |
$dictionary $dictionary; |
| 216 |
|
| 217 |
-- |
| 218 |
cgit v0.9.0.2-2-gbebe |
Archives