219 lines
5.2 KiB
Diff
219 lines
5.2 KiB
Diff
|
https://bugs.gentoo.org/917618
|
||
|
|
https://bugs.documentfoundation.org/show_bug.cgi?id=158108
|
||
|
|
|
||
|
|
From bcd5d851ebe91fc22edd3ea92be4a674bd13acba Mon Sep 17 00:00:00 2001
|
||
|
|
From: Alfred Wingate <parona@protonmail.com>
|
||
|
|
Date: Mon, 20 Nov 2023 14:47:28 +0200
|
||
|
|
Subject: [PATCH] Remove use of the now removed LBCMNoChain options
|
||
|
|
|
||
|
|
* This change removes its use and explicitly prevents chaining where
|
||
|
|
the rule would have applied.
|
||
|
|
|
||
|
|
https://github.com/unicode-org/icu/commit/84e47620692be90950d090f2f4722494b020ad96
|
||
|
|
https://github.com/unicode-org/icu/commit/9d9256f3b792100cda697c7bcf52bacfbc3bca87
|
||
|
|
|
||
|
|
Signed-off-by: Alfred Wingate <parona@protonmail.com>
|
||
|
|
--- a/i18npool/source/breakiterator/data/line.txt
|
||
|
|
+++ b/i18npool/source/breakiterator/data/line.txt
|
||
|
|
@@ -14,7 +14,6 @@
|
||
|
|
#
|
||
|
|
|
||
|
|
!!chain;
|
||
|
|
-!!LBCMNoChain;
|
||
|
|
|
||
|
|
|
||
|
|
!!lookAheadHardBreak;
|
||
|
|
@@ -206,13 +205,13 @@ $CR $LF {100};
|
||
|
|
#
|
||
|
|
$LB4NonBreaks? $LB4Breaks {100}; # LB 5 do not break before hard breaks.
|
||
|
|
$CAN_CM $CM* $LB4Breaks {100};
|
||
|
|
-$CM+ $LB4Breaks {100};
|
||
|
|
+^$CM+ $LB4Breaks {100};
|
||
|
|
|
||
|
|
# LB 7 x SP
|
||
|
|
# x ZW
|
||
|
|
$LB4NonBreaks [$SP $ZW];
|
||
|
|
$CAN_CM $CM* [$SP $ZW];
|
||
|
|
-$CM+ [$SP $ZW];
|
||
|
|
+^$CM+ [$SP $ZW];
|
||
|
|
|
||
|
|
#
|
||
|
|
# LB 8 Break after zero width space
|
||
|
|
@@ -226,14 +225,14 @@ $LB8NonBreaks = [[$LB4NonBreaks] - [$ZW]];
|
||
|
|
# See definition of $CAN_CM.
|
||
|
|
|
||
|
|
$CAN_CM $CM+; # Stick together any combining sequences that don't match other rules.
|
||
|
|
-$CM+;
|
||
|
|
+^$CM+;
|
||
|
|
|
||
|
|
#
|
||
|
|
# LB 11 Do not break before or after WORD JOINER & related characters.
|
||
|
|
#
|
||
|
|
$CAN_CM $CM* $WJcm;
|
||
|
|
$LB8NonBreaks $WJcm;
|
||
|
|
-$CM+ $WJcm;
|
||
|
|
+^$CM+ $WJcm;
|
||
|
|
|
||
|
|
$WJcm [^$CAN_CM];
|
||
|
|
$WJcm $CAN_CM $CM*;
|
||
|
|
@@ -243,7 +242,7 @@ $WJcm $CAN_CM $CM*;
|
||
|
|
#
|
||
|
|
# (!SP) x GL
|
||
|
|
[$LB8NonBreaks-$SP] $CM* $GLcm;
|
||
|
|
-$CM+ $GLcm;
|
||
|
|
+^$CM+ $GLcm;
|
||
|
|
|
||
|
|
# GL x
|
||
|
|
$GLcm ($LB8Breaks | $SP);
|
||
|
|
@@ -260,19 +259,19 @@ $GLcm [$LB8NonBreaks-$SP] $CM*; # Don't let a combining mark go onto $CR, $B
|
||
|
|
#
|
||
|
|
$LB8NonBreaks $CL;
|
||
|
|
$CAN_CM $CM* $CL;
|
||
|
|
-$CM+ $CL; # by rule 10, stand-alone CM behaves as AL
|
||
|
|
+^$CM+ $CL; # by rule 10, stand-alone CM behaves as AL
|
||
|
|
|
||
|
|
$LB8NonBreaks $EX;
|
||
|
|
$CAN_CM $CM* $EX;
|
||
|
|
-$CM+ $EX; # by rule 10, stand-alone CM behaves as AL
|
||
|
|
+^$CM+ $EX; # by rule 10, stand-alone CM behaves as AL
|
||
|
|
|
||
|
|
$LB8NonBreaks $IS;
|
||
|
|
$CAN_CM $CM* $IS;
|
||
|
|
-$CM+ $IS; # by rule 10, stand-alone CM behaves as AL
|
||
|
|
+^$CM+ $IS; # by rule 10, stand-alone CM behaves as AL
|
||
|
|
|
||
|
|
$LB8NonBreaks $SY;
|
||
|
|
$CAN_CM $CM* $SY;
|
||
|
|
-$CM+ $SY; # by rule 10, stand-alone CM behaves as AL
|
||
|
|
+^$CM+ $SY; # by rule 10, stand-alone CM behaves as AL
|
||
|
|
|
||
|
|
|
||
|
|
#
|
||
|
|
@@ -302,7 +301,7 @@ $LB18Breaks = [$LB8Breaks $SP];
|
||
|
|
# LB 19
|
||
|
|
# x QU
|
||
|
|
$LB18NonBreaks $CM* $QUcm;
|
||
|
|
-$CM+ $QUcm;
|
||
|
|
+^$CM+ $QUcm;
|
||
|
|
|
||
|
|
# QU x
|
||
|
|
$QUcm .?;
|
||
|
|
@@ -331,7 +330,7 @@ $HLcm ($HYcm | $BAcm) [^$CB]?;
|
||
|
|
|
||
|
|
# LB 22
|
||
|
|
($ALcm | $HLcm) $INcm;
|
||
|
|
-$CM+ $INcm; # by rule 10, any otherwise unattached CM behaves as AL
|
||
|
|
+^$CM+ $INcm; # by rule 10, any otherwise unattached CM behaves as AL
|
||
|
|
$IDcm $INcm;
|
||
|
|
$INcm $INcm;
|
||
|
|
$NUcm $INcm;
|
||
|
|
@@ -341,7 +340,7 @@ $NUcm $INcm;
|
||
|
|
$IDcm $POcm;
|
||
|
|
$ALcm $NUcm; # includes $LB19
|
||
|
|
$HLcm $NUcm;
|
||
|
|
-$CM+ $NUcm; # Rule 10, any otherwise unattached CM behaves as AL
|
||
|
|
+^$CM+ $NUcm; # Rule 10, any otherwise unattached CM behaves as AL
|
||
|
|
$NUcm $ALcm;
|
||
|
|
$NUcm $HLcm;
|
||
|
|
|
||
|
|
@@ -373,7 +372,7 @@ $PRcm ($JLcm | $JVcm | $JTcm | $H2cm | $H3cm);
|
||
|
|
# LB 28 Do not break between alphabetics
|
||
|
|
#
|
||
|
|
($ALcm | $HLcm) ($ALcm | $HLcm);
|
||
|
|
-$CM+ ($ALcm | $HLcm); # The $CM+ is from rule 10, an unattached CM is treated as AL
|
||
|
|
+^$CM+ ($ALcm | $HLcm); # The $CM+ is from rule 10, an unattached CM is treated as AL
|
||
|
|
|
||
|
|
# LB 29
|
||
|
|
$IScm ($ALcm | $NUcm);
|
||
|
|
@@ -383,7 +382,7 @@ $IScm ($ALcm | $NUcm);
|
||
|
|
# and opening or closing punctuation
|
||
|
|
#
|
||
|
|
($ALcm | $HLcm | $NUcm) $OPcm;
|
||
|
|
-$CM+ $OPcm;
|
||
|
|
+^$CM+ $OPcm;
|
||
|
|
$CLcm ($ALcm | $HLcm | $NUcm);
|
||
|
|
|
||
|
|
#
|
||
|
|
@@ -393,32 +392,32 @@ $CLcm ($ALcm | $HLcm | $NUcm);
|
||
|
|
|
||
|
|
!!reverse;
|
||
|
|
|
||
|
|
-$CM+ $ALPlus;
|
||
|
|
-$CM+ $BA;
|
||
|
|
-$CM+ $BB;
|
||
|
|
-$CM+ $B2;
|
||
|
|
-$CM+ $CL;
|
||
|
|
-$CM+ $EX;
|
||
|
|
-$CM+ $GL;
|
||
|
|
-$CM+ $HL;
|
||
|
|
-$CM+ $HY;
|
||
|
|
-$CM+ $H2;
|
||
|
|
-$CM+ $H3;
|
||
|
|
-$CM+ $ID;
|
||
|
|
-$CM+ $IN;
|
||
|
|
-$CM+ $IS;
|
||
|
|
-$CM+ $JL;
|
||
|
|
-$CM+ $JV;
|
||
|
|
-$CM+ $JT;
|
||
|
|
-$CM+ $NS;
|
||
|
|
-$CM+ $NU;
|
||
|
|
-$CM+ $OP;
|
||
|
|
-$CM+ $PO;
|
||
|
|
-$CM+ $PR;
|
||
|
|
-$CM+ $QU;
|
||
|
|
-$CM+ $SY;
|
||
|
|
-$CM+ $WJ;
|
||
|
|
-$CM+;
|
||
|
|
+^$CM+ $ALPlus;
|
||
|
|
+^$CM+ $BA;
|
||
|
|
+^$CM+ $BB;
|
||
|
|
+^$CM+ $B2;
|
||
|
|
+^$CM+ $CL;
|
||
|
|
+^$CM+ $EX;
|
||
|
|
+^$CM+ $GL;
|
||
|
|
+^$CM+ $HL;
|
||
|
|
+^$CM+ $HY;
|
||
|
|
+^$CM+ $H2;
|
||
|
|
+^$CM+ $H3;
|
||
|
|
+^$CM+ $ID;
|
||
|
|
+^$CM+ $IN;
|
||
|
|
+^$CM+ $IS;
|
||
|
|
+^$CM+ $JL;
|
||
|
|
+^$CM+ $JV;
|
||
|
|
+^$CM+ $JT;
|
||
|
|
+^$CM+ $NS;
|
||
|
|
+^$CM+ $NU;
|
||
|
|
+^$CM+ $OP;
|
||
|
|
+^$CM+ $PO;
|
||
|
|
+^$CM+ $PR;
|
||
|
|
+^$CM+ $QU;
|
||
|
|
+^$CM+ $SY;
|
||
|
|
+^$CM+ $WJ;
|
||
|
|
+^$CM+;
|
||
|
|
|
||
|
|
|
||
|
|
#
|
||
|
|
@@ -468,7 +467,7 @@ $LF $CR;
|
||
|
|
# X $CM needs to behave like X, where X is not $SP or controls.
|
||
|
|
# $CM not covered by the above needs to behave like $AL
|
||
|
|
# Stick together any combining sequences that don't match other rules.
|
||
|
|
-$CM+ $CAN_CM;
|
||
|
|
+^$CM+ $CAN_CM;
|
||
|
|
|
||
|
|
|
||
|
|
# LB 11
|
||
|
|
@@ -606,8 +605,8 @@ $CM* ($ALPlus | $HL | $NU) $CM* ($CL | $SY)+ [^$SP];
|
||
|
|
!!safe_reverse;
|
||
|
|
|
||
|
|
# LB 7
|
||
|
|
-$CM+ [^$CM $BK $CR $LF $NL $ZW $SP];
|
||
|
|
-$CM+ $SP / .;
|
||
|
|
+^$CM+ [^$CM $BK $CR $LF $NL $ZW $SP];
|
||
|
|
+^$CM+ $SP / .;
|
||
|
|
|
||
|
|
# LB 9
|
||
|
|
$SP+ $CM* $OP;
|
||
|
|
--
|
||
|
|
2.42.1
|
||
|
|
|