AuroraMiddleware/scuffed-code
1
0
Fork 0
Code Issues Pull Requests Releases Wiki Activity

ICU-7108 update Line Break for Unicode 5.2 rule change.

Browse Source 
X-SVN-Rev: 26546
This commit is contained in:
Andy Heninger 2009-08-25 16:52:44 +00:00
parent 8c85a0ac89
commit e3c423d06a
4 changed files with 102 additions and 53 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

44
icu4c/source/data/brkitr/line.txt
View File

@ -61,7 +61,11 @@ $BB = [:LineBreak = Break_Before:];
$BK = [:LineBreak = Mandatory_Break:];
$B2 = [:LineBreak = Break_Both:];
$CB = [:LineBreak = Contingent_Break:];
$CL = [:LineBreak = Close_Punctuation:];
# Unicode 5.2 changes. Fix once line break property data is updated.
$CP = [\u0029 \u005d]; # Right Parenthesis and right square bracket.
$CL = [[:LineBreak = Close_Punctuation:] - $CP];
$CM = [:LineBreak = Combining_Mark:];
$CR = [:LineBreak = Carriage_Return:];
$EX = [:LineBreak = Exclamation:];
@ -115,6 +119,7 @@ $BAcm = $BA $CM*;
$BBcm = $BB $CM*;
$B2cm = $B2 $CM*;
$CLcm = $CL $CM*;
$CPcm = $CP $CM*;
$EXcm = $EX $CM*;
$GLcm = $GL $CM*;
$HYcm = $HY $CM*;
@ -147,6 +152,7 @@ $BA $CM+;
$BB $CM+;
$B2 $CM+;
$CL $CM+;
$CP $CM+;
$EX $CM+;
$GL $CM+;
$HY $CM+;
@ -185,7 +191,7 @@ $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];
$AL_FOLLOW_CM = [$CL $CP $EX $IS $SY $WJ $GL $OP $QU $BA $HY $NS $IN $NU $ALPlus];
$AL_FOLLOW = [$AL_FOLLOW_NOCM $AL_FOLLOW_CM];
@ -256,6 +262,10 @@ $LB8NonBreaks $CL;
$CAN_CM $CM* $CL;
$CM+ $CL; # by rule 10, stand-alone CM behaves as AL
$LB8NonBreaks $CP;
$CAN_CM $CM* $CP;
$CM+ $CP; # 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
@ -281,7 +291,7 @@ $OPcm $SP+ $CM+ $AL_FOLLOW?; # by rule 10, stand-alone CM behaves as AL
$QUcm $SP* $OPcm;
# LB 16
$CLcm $SP* $NScm;
($CLcm | $CPcm) $SP* $NScm;
# LB 17
$B2cm $SP* $B2cm;
@ -342,7 +352,7 @@ $POcm $ALcm;
#
# LB 25 Numbers.
#
($PRcm | $POcm)? ($OPcm | $HYcm)? $NUcm ($NUcm | $SYcm | $IScm)* $CLcm? ($PRcm | $POcm)?;
($PRcm | $POcm)? ($OPcm | $HYcm)? $NUcm ($NUcm | $SYcm | $IScm)* ($CLcm | $CPcm)? ($PRcm | $POcm)?;
# LB 26 Do not break a Korean syllable
#
@ -364,6 +374,11 @@ $CM+ $ALcm; # The $CM+ is from rule 10, an unattached CM is treated as AL
# LB 29
$IScm $ALcm;
# LB 30
($ALcm | $NUcm) $OPcm;
$CM+ $OPcm; # The $CM+ is from rule 10, an unattached CM is treated as AL.
$CPcm ($ALcm | $NUcm);
#
# Reverse Rules.
@ -377,6 +392,7 @@ $CM+ $BA;
$CM+ $BB;
$CM+ $B2;
$CM+ $CL;
$CM+ $CP;
$CM+ $EX;
$CM+ $GL;
$CM+ $HY;
@ -470,21 +486,23 @@ $CM* $CAN_CM $CM* $GL;
# LB 13
$CL $CM+ $CAN_CM;
$CP $CM+ $CAN_CM;
$EX $CM+ $CAN_CM;
$IS $CM+ $CAN_CM;
$SY $CM+ $CAN_CM;
$CL [$LB8NonBreaks-$CM];
$CP [$LB8NonBreaks-$CM];
$EX [$LB8NonBreaks-$CM];
$IS [$LB8NonBreaks-$CM];
$SY [$LB8NonBreaks-$CM];
# Rule 13 & 14 taken together for an edge case.
# Match this, shown forward
# OP SP+ ($CM+ behaving as $AL) (CL | EX | IS | IY)
# OP SP+ ($CM+ behaving as $AL) (CL | CP | EX | IS | IY)
# This really wants to chain at the $CM+ (which is acting as an $AL)
# except for $CM chaining being disabled.
[$CL $EX $IS $SY] $CM+ $SP+ $CM* $OP;
[$CL $CP $EX $IS $SY] $CM+ $SP+ $CM* $OP;
# LB 14 OP SP* x
#
@ -502,7 +520,7 @@ $SY $CM $SP+ $OP; # TODO: Experiment. Remove.
$CM* $OP $SP* $CM* $QU;
# LB 16
$CM* $NS $SP* $CM* $CL;
$CM* $NS $SP* $CM* ($CL | $CP);
# LB 17
$CM* $B2 $SP* $CM* $B2;
@ -552,7 +570,7 @@ $CM* $ALPlus $CM* $PO;
# LB 25
($CM* ($PR | $PO))? ($CM* $CL)? ($CM* ($NU | $IS | $SY))* $CM* $NU ($CM* ($OP | $HY))? ($CM* ($PR | $PO))?;
($CM* ($PR | $PO))? ($CM* ($CL | $CP))? ($CM* ($NU | $IS | $SY))* $CM* $NU ($CM* ($OP | $HY))? ($CM* ($PR | $PO))?;
# LB 26
$CM* ($H3 | $H2 | $JV | $JL) $CM* $JL;
@ -571,6 +589,10 @@ $CM* $ALPlus $CM* $ALPlus;
# LB 29
$CM* $ALPlus $CM* $IS;
# LB 30
$CM* $OP $CM* ($ALPlus | $NU);
$CM* ($ALPlus | $NU) $CM* $CP;
## -------------------------------------------------
@ -587,14 +609,14 @@ $SP+ $CM* $OP;
$SP+ $CM* $QU;
# LB 16
$SP+ $CM* $CL;
$SP+ $CM* ($CL | $CP);
# LB 17
$SP+ $CM* $B2;
# LB 25
($CM* ($IS | $SY))+ $CM* $NU;
$CL $CM* ($NU | $IS | $SY);
($CL | $CP) $CM* ($NU | $IS | $SY);
# For dictionary-based break
$dictionary $dictionary;
@ -612,6 +634,6 @@ $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 $CP $B2 $PR $HY $SP $dictionary]+ [^$CM $OP $QU $CL $CP $B2 $PR $HY $dictionary];
$dictionary $dictionary;

27
icu4c/source/test/intltest/rbbitst.cpp
View File

@ -3223,6 +3223,7 @@ private:
UnicodeSet *fH2;
UnicodeSet *fH3;
UnicodeSet *fCL;
UnicodeSet *fCP;
UnicodeSet *fEX;
UnicodeSet *fIN;
UnicodeSet *fJL;
@ -3274,7 +3275,8 @@ RBBILineMonkey::RBBILineMonkey()
fHY = new UnicodeSet(UNICODE_STRING_SIMPLE("[\\p{Line_break=HY}]"), status);
fH2 = new UnicodeSet(UNICODE_STRING_SIMPLE("[\\p{Line_break=H2}]"), status);
fH3 = new UnicodeSet(UNICODE_STRING_SIMPLE("[\\p{Line_break=H3}]"), status);
fCL = new UnicodeSet(UNICODE_STRING_SIMPLE("[\\p{Line_break=CL}]"), status);
fCL = new UnicodeSet(UNICODE_STRING_SIMPLE("[[\\p{Line_break=CL}]-[\\u0029\\u005d]]"), status); // TODO: fix when props are updated.
fCP = new UnicodeSet(UNICODE_STRING_SIMPLE("[\\u0029\\u005d]"), status);
fEX = new UnicodeSet(UNICODE_STRING_SIMPLE("[\\p{Line_break=EX}]"), status);
fIN = new UnicodeSet(UNICODE_STRING_SIMPLE("[\\p{Line_break=IN}]"), status);
fJL = new UnicodeSet(UNICODE_STRING_SIMPLE("[\\p{Line_break=JL}]"), status);
@ -3324,6 +3326,7 @@ RBBILineMonkey::RBBILineMonkey()
fSets->addElement(fH2, status);
fSets->addElement(fH3, status);
fSets->addElement(fCL, status);
fSets->addElement(fCP, status);
fSets->addElement(fEX, status);
fSets->addElement(fIN, status);
fSets->addElement(fJL, status);
@ -3349,7 +3352,7 @@ RBBILineMonkey::RBBILineMonkey()
"((\\p{Line_Break=OP}|\\p{Line_Break=HY})\\p{Line_Break=CM}*)?"
"\\p{Line_Break=NU}\\p{Line_Break=CM}*"
"((\\p{Line_Break=NU}|\\p{Line_Break=IS}|\\p{Line_Break=SY})\\p{Line_Break=CM}*)*"
"(\\p{Line_Break=CL}\\p{Line_Break=CM}*)?"
"((\\p{Line_Break=CL}|[\\u0029\\u005d])\\p{Line_Break=CM}*)?" // TODO: p{Line_Break=CP}
"((\\p{Line_Break=PR}|\\p{Line_Break=PO})\\p{Line_Break=CM}*)?";
fNumberMatcher = new RegexMatcher(
@ -3552,10 +3555,11 @@ int32_t RBBILineMonkey::next(int32_t startPos) {
// LB 13 Don't break before closings.
// NU x CL and NU x IS are not matched here so that they will
// NU x CL, NU x CP and NU x IS are not matched here so that they will
// fall into LB 17 and the more general number regular expression.
//
if (!fNU->contains(prevChar) && fCL->contains(thisChar) ||
!fNU->contains(prevChar) && fCP->contains(thisChar) ||
fEX->contains(thisChar) ||
!fNU->contains(prevChar) && fIS->contains(thisChar) ||
!fNU->contains(prevChar) && fSY->contains(thisChar)) {
@ -3601,8 +3605,8 @@ int32_t RBBILineMonkey::next(int32_t startPos) {
// LB 16 CL SP* x NS
// Scan backwards for SP* CM* CL
// LB 16 (CL | CP) SP* x NS
// Scan backwards for SP* CM* (CL | CP)
if (fNS->contains(thisChar)) {
int tPos = prevPos;
while (tPos>0 && fSP->contains(fText->char32At(tPos))) {
@ -3611,7 +3615,7 @@ int32_t RBBILineMonkey::next(int32_t startPos) {
while (tPos>0 && fCM->contains(fText->char32At(tPos))) {
tPos = fText->moveIndex32(tPos, -1);
}
if (fCL->contains(fText->char32At(tPos))) {
if (fCL->contains(fText->char32At(tPos)) || fCP->contains(fText->char32At(tPos))) {
continue;
}
}
@ -3761,6 +3765,16 @@ int32_t RBBILineMonkey::next(int32_t startPos) {
continue;
}
// LB 30 Do not break between letters, numbers, or ordinary symbols and opening or closing punctuation.
// (AL | NU) x OP
// CP x (AL | NU)
if ((fAL->contains(prevChar) || fNU->contains(prevChar)) && fOP->contains(thisChar)) {
continue;
}
if (fCP->contains(prevChar) && (fAL->contains(thisChar) || fNU->contains(thisChar))) {
continue;
}
// LB 31 Break everywhere else
break;
@ -3795,6 +3809,7 @@ RBBILineMonkey::~RBBILineMonkey() {
delete fH2;
delete fH3;
delete fCL;
delete fCP;
delete fEX;
delete fIN;
delete fJL;

66
icu4c/source/test/testdata/LineBreakTest.txt vendored
View File

@ -2,12 +2,16 @@
# Date: 2008-03-11, 02:19:24 GMT [MD]
#
# Unicode Character Database
# Copyright (c) 1991-2008 Unicode, Inc.
# Copyright (c) 1991-2009 Unicode, Inc.
# For terms of use, see http://www.unicode.org/terms_of_use.html
# For documentation, see UCD.html
#
# Default Line Break Test
#
# ######## CAUTION Hacked version for Unicode 5.2 changes.
# To be replaced as soon as a new machine generated file is available.
# Comments are out of sync with the data itsef.
#
# Format:
# <string> (# <comment>)?
# <string> contains hex Unicode code points, with
@ -116,9 +120,9 @@
÷ 0023 × 0020 ÷ 0030 ÷ # ÷ [0.2] NUMBER SIGN (AL) × [7.01] SPACE (SP) ÷ [18.0] DIGIT ZERO (NU) ÷ [0.3]
÷ 0023 × 0308 × 0030 ÷ # ÷ [0.2] NUMBER SIGN (AL) × [9.0] COMBINING DIAERESIS (CM) × [23.02] DIGIT ZERO (NU) ÷ [0.3]
÷ 0023 × 0308 × 0020 ÷ 0030 ÷ # ÷ [0.2] NUMBER SIGN (AL) × [9.0] COMBINING DIAERESIS (CM) × [7.01] SPACE (SP) ÷ [18.0] DIGIT ZERO (NU) ÷ [0.3]
÷ 0023 ÷ 0028 ÷ # ÷ [0.2] NUMBER SIGN (AL) ÷ [999.0] LEFT PARENTHESIS (OP) ÷ [0.3]
÷ 0023 × 0028 ÷ # ÷ [0.2] NUMBER SIGN (AL) ÷ [999.0] LEFT PARENTHESIS (OP) ÷ [0.3]
÷ 0023 × 0020 ÷ 0028 ÷ # ÷ [0.2] NUMBER SIGN (AL) × [7.01] SPACE (SP) ÷ [18.0] LEFT PARENTHESIS (OP) ÷ [0.3]
÷ 0023 × 0308 ÷ 0028 ÷ # ÷ [0.2] NUMBER SIGN (AL) × [9.0] COMBINING DIAERESIS (CM) ÷ [999.0] LEFT PARENTHESIS (OP) ÷ [0.3]
÷ 0023 × 0308 × 0028 ÷ # ÷ [0.2] NUMBER SIGN (AL) × [9.0] COMBINING DIAERESIS (CM) ÷ [999.0] LEFT PARENTHESIS (OP) ÷ [0.3]
÷ 0023 × 0308 × 0020 ÷ 0028 ÷ # ÷ [0.2] NUMBER SIGN (AL) × [9.0] COMBINING DIAERESIS (CM) × [7.01] SPACE (SP) ÷ [18.0] LEFT PARENTHESIS (OP) ÷ [0.3]
÷ 0023 ÷ 0025 ÷ # ÷ [0.2] NUMBER SIGN (AL) ÷ [999.0] PERCENT SIGN (PO) ÷ [0.3]
÷ 0023 × 0020 ÷ 0025 ÷ # ÷ [0.2] NUMBER SIGN (AL) × [7.01] SPACE (SP) ÷ [18.0] PERCENT SIGN (PO) ÷ [0.3]
@ -678,7 +682,7 @@
÷ 000B ÷ 0308 × 0020 ÷ 0030 ÷ # ÷ [0.2] <LINE TABULATION> (BK) ÷ [4.0] COMBINING DIAERESIS (CM) × [7.01] SPACE (SP) ÷ [18.0] DIGIT ZERO (NU) ÷ [0.3]
÷ 000B ÷ 0028 ÷ # ÷ [0.2] <LINE TABULATION> (BK) ÷ [4.0] LEFT PARENTHESIS (OP) ÷ [0.3]
÷ 000B ÷ 0020 ÷ 0028 ÷ # ÷ [0.2] <LINE TABULATION> (BK) ÷ [4.0] SPACE (SP) ÷ [18.0] LEFT PARENTHESIS (OP) ÷ [0.3]
÷ 000B ÷ 0308 ÷ 0028 ÷ # ÷ [0.2] <LINE TABULATION> (BK) ÷ [4.0] COMBINING DIAERESIS (CM) ÷ [999.0] LEFT PARENTHESIS (OP) ÷ [0.3]
÷ 000B ÷ 0308 × 0028 ÷ # ÷ [0.2] <LINE TABULATION> (BK) ÷ [4.0] COMBINING DIAERESIS (CM) ÷ [999.0] LEFT PARENTHESIS (OP) ÷ [0.3]
÷ 000B ÷ 0308 × 0020 ÷ 0028 ÷ # ÷ [0.2] <LINE TABULATION> (BK) ÷ [4.0] COMBINING DIAERESIS (CM) × [7.01] SPACE (SP) ÷ [18.0] LEFT PARENTHESIS (OP) ÷ [0.3]
÷ 000B ÷ 0025 ÷ # ÷ [0.2] <LINE TABULATION> (BK) ÷ [4.0] PERCENT SIGN (PO) ÷ [0.3]
÷ 000B ÷ 0020 ÷ 0025 ÷ # ÷ [0.2] <LINE TABULATION> (BK) ÷ [4.0] SPACE (SP) ÷ [18.0] PERCENT SIGN (PO) ÷ [0.3]
@ -860,9 +864,9 @@
÷ FFFC × 0020 ÷ 0E01 ÷ # ÷ [0.2] OBJECT REPLACEMENT CHARACTER (CB) × [7.01] SPACE (SP) ÷ [18.0] THAI CHARACTER KO KAI (SA_AL) ÷ [0.3]
÷ FFFC × 0308 ÷ 0E01 ÷ # ÷ [0.2] OBJECT REPLACEMENT CHARACTER (CB) × [9.0] COMBINING DIAERESIS (CM) ÷ [20.02] THAI CHARACTER KO KAI (SA_AL) ÷ [0.3]
÷ FFFC × 0308 × 0020 ÷ 0E01 ÷ # ÷ [0.2] OBJECT REPLACEMENT CHARACTER (CB) × [9.0] COMBINING DIAERESIS (CM) × [7.01] SPACE (SP) ÷ [18.0] THAI CHARACTER KO KAI (SA_AL) ÷ [0.3]
÷ 0029 ÷ 0023 ÷ # ÷ [0.2] RIGHT PARENTHESIS (CL) ÷ [999.0] NUMBER SIGN (AL) ÷ [0.3]
÷ 0029 × 0023 ÷ # ÷ [0.2] RIGHT PARENTHESIS (CL) ÷ [999.0] NUMBER SIGN (AL) ÷ [0.3]
÷ 0029 × 0020 ÷ 0023 ÷ # ÷ [0.2] RIGHT PARENTHESIS (CL) × [7.01] SPACE (SP) ÷ [18.0] NUMBER SIGN (AL) ÷ [0.3]
÷ 0029 × 0308 ÷ 0023 ÷ # ÷ [0.2] RIGHT PARENTHESIS (CL) × [9.0] COMBINING DIAERESIS (CM) ÷ [999.0] NUMBER SIGN (AL) ÷ [0.3]
÷ 0029 × 0308 × 0023 ÷ # ÷ [0.2] RIGHT PARENTHESIS (CL) × [9.0] COMBINING DIAERESIS (CM) ÷ [999.0] NUMBER SIGN (AL) ÷ [0.3]
÷ 0029 × 0308 × 0020 ÷ 0023 ÷ # ÷ [0.2] RIGHT PARENTHESIS (CL) × [9.0] COMBINING DIAERESIS (CM) × [7.01] SPACE (SP) ÷ [18.0] NUMBER SIGN (AL) ÷ [0.3]
÷ 0029 ÷ 2014 ÷ # ÷ [0.2] RIGHT PARENTHESIS (CL) ÷ [999.0] EM DASH (B2) ÷ [0.3]
÷ 0029 × 0020 ÷ 2014 ÷ # ÷ [0.2] RIGHT PARENTHESIS (CL) × [7.01] SPACE (SP) ÷ [18.0] EM DASH (B2) ÷ [0.3]
@ -952,9 +956,9 @@
÷ 0029 × 0020 × 17D6 ÷ # ÷ [0.2] RIGHT PARENTHESIS (CL) × [7.01] SPACE (SP) × [16.0] KHMER SIGN CAMNUC PII KUUH (NS) ÷ [0.3]
÷ 0029 × 0308 × 17D6 ÷ # ÷ [0.2] RIGHT PARENTHESIS (CL) × [9.0] COMBINING DIAERESIS (CM) × [16.0] KHMER SIGN CAMNUC PII KUUH (NS) ÷ [0.3]
÷ 0029 × 0308 × 0020 × 17D6 ÷ # ÷ [0.2] RIGHT PARENTHESIS (CL) × [9.0] COMBINING DIAERESIS (CM) × [7.01] SPACE (SP) × [16.0] KHMER SIGN CAMNUC PII KUUH (NS) ÷ [0.3]
÷ 0029 ÷ 0030 ÷ # ÷ [0.2] RIGHT PARENTHESIS (CL) ÷ [999.0] DIGIT ZERO (NU) ÷ [0.3]
÷ 0029 × 0030 ÷ # ÷ [0.2] RIGHT PARENTHESIS (CL) ÷ [999.0] DIGIT ZERO (NU) ÷ [0.3]
÷ 0029 × 0020 ÷ 0030 ÷ # ÷ [0.2] RIGHT PARENTHESIS (CL) × [7.01] SPACE (SP) ÷ [18.0] DIGIT ZERO (NU) ÷ [0.3]
÷ 0029 × 0308 ÷ 0030 ÷ # ÷ [0.2] RIGHT PARENTHESIS (CL) × [9.0] COMBINING DIAERESIS (CM) ÷ [999.0] DIGIT ZERO (NU) ÷ [0.3]
÷ 0029 × 0308 × 0030 ÷ # ÷ [0.2] RIGHT PARENTHESIS (CL) × [9.0] COMBINING DIAERESIS (CM) ÷ [999.0] DIGIT ZERO (NU) ÷ [0.3]
÷ 0029 × 0308 × 0020 ÷ 0030 ÷ # ÷ [0.2] RIGHT PARENTHESIS (CL) × [9.0] COMBINING DIAERESIS (CM) × [7.01] SPACE (SP) ÷ [18.0] DIGIT ZERO (NU) ÷ [0.3]
÷ 0029 ÷ 0028 ÷ # ÷ [0.2] RIGHT PARENTHESIS (CL) ÷ [999.0] LEFT PARENTHESIS (OP) ÷ [0.3]
÷ 0029 × 0020 ÷ 0028 ÷ # ÷ [0.2] RIGHT PARENTHESIS (CL) × [7.01] SPACE (SP) ÷ [18.0] LEFT PARENTHESIS (OP) ÷ [0.3]
@ -988,17 +992,17 @@
÷ 0029 × 0020 × 200B ÷ # ÷ [0.2] RIGHT PARENTHESIS (CL) × [7.01] SPACE (SP) × [7.02] ZERO WIDTH SPACE (ZW) ÷ [0.3]
÷ 0029 × 0308 × 200B ÷ # ÷ [0.2] RIGHT PARENTHESIS (CL) × [9.0] COMBINING DIAERESIS (CM) × [7.02] ZERO WIDTH SPACE (ZW) ÷ [0.3]
÷ 0029 × 0308 × 0020 × 200B ÷ # ÷ [0.2] RIGHT PARENTHESIS (CL) × [9.0] COMBINING DIAERESIS (CM) × [7.01] SPACE (SP) × [7.02] ZERO WIDTH SPACE (ZW) ÷ [0.3]
÷ 0029 ÷ 00A7 ÷ # ÷ [0.2] RIGHT PARENTHESIS (CL) ÷ [999.0] SECTION SIGN (AI_AL) ÷ [0.3]
÷ 0029 × 00A7 ÷ # ÷ [0.2] RIGHT PARENTHESIS (CL) ÷ [999.0] SECTION SIGN (AI_AL) ÷ [0.3]
÷ 0029 × 0020 ÷ 00A7 ÷ # ÷ [0.2] RIGHT PARENTHESIS (CL) × [7.01] SPACE (SP) ÷ [18.0] SECTION SIGN (AI_AL) ÷ [0.3]
÷ 0029 × 0308 ÷ 00A7 ÷ # ÷ [0.2] RIGHT PARENTHESIS (CL) × [9.0] COMBINING DIAERESIS (CM) ÷ [999.0] SECTION SIGN (AI_AL) ÷ [0.3]
÷ 0029 × 0308 × 00A7 ÷ # ÷ [0.2] RIGHT PARENTHESIS (CL) × [9.0] COMBINING DIAERESIS (CM) ÷ [999.0] SECTION SIGN (AI_AL) ÷ [0.3]
÷ 0029 × 0308 × 0020 ÷ 00A7 ÷ # ÷ [0.2] RIGHT PARENTHESIS (CL) × [9.0] COMBINING DIAERESIS (CM) × [7.01] SPACE (SP) ÷ [18.0] SECTION SIGN (AI_AL) ÷ [0.3]
÷ 0029 ÷ E000 ÷ # ÷ [0.2] RIGHT PARENTHESIS (CL) ÷ [999.0] <private-use-E000> (XX_AL) ÷ [0.3]
÷ 0029 × E000 ÷ # ÷ [0.2] RIGHT PARENTHESIS (CL) ÷ [999.0] <private-use-E000> (XX_AL) ÷ [0.3]
÷ 0029 × 0020 ÷ E000 ÷ # ÷ [0.2] RIGHT PARENTHESIS (CL) × [7.01] SPACE (SP) ÷ [18.0] <private-use-E000> (XX_AL) ÷ [0.3]
÷ 0029 × 0308 ÷ E000 ÷ # ÷ [0.2] RIGHT PARENTHESIS (CL) × [9.0] COMBINING DIAERESIS (CM) ÷ [999.0] <private-use-E000> (XX_AL) ÷ [0.3]
÷ 0029 × 0308 × E000 ÷ # ÷ [0.2] RIGHT PARENTHESIS (CL) × [9.0] COMBINING DIAERESIS (CM) ÷ [999.0] <private-use-E000> (XX_AL) ÷ [0.3]
÷ 0029 × 0308 × 0020 ÷ E000 ÷ # ÷ [0.2] RIGHT PARENTHESIS (CL) × [9.0] COMBINING DIAERESIS (CM) × [7.01] SPACE (SP) ÷ [18.0] <private-use-E000> (XX_AL) ÷ [0.3]
÷ 0029 ÷ 0E01 ÷ # ÷ [0.2] RIGHT PARENTHESIS (CL) ÷ [999.0] THAI CHARACTER KO KAI (SA_AL) ÷ [0.3]
÷ 0029 × 0E01 ÷ # ÷ [0.2] RIGHT PARENTHESIS (CL) ÷ [999.0] THAI CHARACTER KO KAI (SA_AL) ÷ [0.3]
÷ 0029 × 0020 ÷ 0E01 ÷ # ÷ [0.2] RIGHT PARENTHESIS (CL) × [7.01] SPACE (SP) ÷ [18.0] THAI CHARACTER KO KAI (SA_AL) ÷ [0.3]
÷ 0029 × 0308 ÷ 0E01 ÷ # ÷ [0.2] RIGHT PARENTHESIS (CL) × [9.0] COMBINING DIAERESIS (CM) ÷ [999.0] THAI CHARACTER KO KAI (SA_AL) ÷ [0.3]
÷ 0029 × 0308 × 0E01 ÷ # ÷ [0.2] RIGHT PARENTHESIS (CL) × [9.0] COMBINING DIAERESIS (CM) ÷ [999.0] THAI CHARACTER KO KAI (SA_AL) ÷ [0.3]
÷ 0029 × 0308 × 0020 ÷ 0E01 ÷ # ÷ [0.2] RIGHT PARENTHESIS (CL) × [9.0] COMBINING DIAERESIS (CM) × [7.01] SPACE (SP) ÷ [18.0] THAI CHARACTER KO KAI (SA_AL) ÷ [0.3]
÷ 0001 × 0023 ÷ # ÷ [0.2] <START OF HEADING> (CM) × [28.0] NUMBER SIGN (AL) ÷ [0.3]
÷ 0001 × 0020 ÷ 0023 ÷ # ÷ [0.2] <START OF HEADING> (CM) × [7.01] SPACE (SP) ÷ [18.0] NUMBER SIGN (AL) ÷ [0.3]
@ -1096,9 +1100,9 @@
÷ 0001 × 0020 ÷ 0030 ÷ # ÷ [0.2] <START OF HEADING> (CM) × [7.01] SPACE (SP) ÷ [18.0] DIGIT ZERO (NU) ÷ [0.3]
÷ 0001 × 0308 × 0030 ÷ # ÷ [0.2] <START OF HEADING> (CM) × [9.0] COMBINING DIAERESIS (CM) × [23.02] DIGIT ZERO (NU) ÷ [0.3]
÷ 0001 × 0308 × 0020 ÷ 0030 ÷ # ÷ [0.2] <START OF HEADING> (CM) × [9.0] COMBINING DIAERESIS (CM) × [7.01] SPACE (SP) ÷ [18.0] DIGIT ZERO (NU) ÷ [0.3]
÷ 0001 ÷ 0028 ÷ # ÷ [0.2] <START OF HEADING> (CM) ÷ [999.0] LEFT PARENTHESIS (OP) ÷ [0.3]
÷ 0001 × 0028 ÷ # ÷ [0.2] <START OF HEADING> (CM) ÷ [999.0] LEFT PARENTHESIS (OP) ÷ [0.3]
÷ 0001 × 0020 ÷ 0028 ÷ # ÷ [0.2] <START OF HEADING> (CM) × [7.01] SPACE (SP) ÷ [18.0] LEFT PARENTHESIS (OP) ÷ [0.3]
÷ 0001 × 0308 ÷ 0028 ÷ # ÷ [0.2] <START OF HEADING> (CM) × [9.0] COMBINING DIAERESIS (CM) ÷ [999.0] LEFT PARENTHESIS (OP) ÷ [0.3]
÷ 0001 × 0308 × 0028 ÷ # ÷ [0.2] <START OF HEADING> (CM) × [9.0] COMBINING DIAERESIS (CM) ÷ [999.0] LEFT PARENTHESIS (OP) ÷ [0.3]
÷ 0001 × 0308 × 0020 ÷ 0028 ÷ # ÷ [0.2] <START OF HEADING> (CM) × [9.0] COMBINING DIAERESIS (CM) × [7.01] SPACE (SP) ÷ [18.0] LEFT PARENTHESIS (OP) ÷ [0.3]
÷ 0001 ÷ 0025 ÷ # ÷ [0.2] <START OF HEADING> (CM) ÷ [999.0] PERCENT SIGN (PO) ÷ [0.3]
÷ 0001 × 0020 ÷ 0025 ÷ # ÷ [0.2] <START OF HEADING> (CM) × [7.01] SPACE (SP) ÷ [18.0] PERCENT SIGN (PO) ÷ [0.3]
@ -1238,7 +1242,7 @@
÷ 000D ÷ 0308 × 0020 ÷ 0030 ÷ # ÷ [0.2] <CARRIAGE RETURN (CR)> (CR) ÷ [5.02] COMBINING DIAERESIS (CM) × [7.01] SPACE (SP) ÷ [18.0] DIGIT ZERO (NU) ÷ [0.3]
÷ 000D ÷ 0028 ÷ # ÷ [0.2] <CARRIAGE RETURN (CR)> (CR) ÷ [5.02] LEFT PARENTHESIS (OP) ÷ [0.3]
÷ 000D ÷ 0020 ÷ 0028 ÷ # ÷ [0.2] <CARRIAGE RETURN (CR)> (CR) ÷ [5.02] SPACE (SP) ÷ [18.0] LEFT PARENTHESIS (OP) ÷ [0.3]
÷ 000D ÷ 0308 ÷ 0028 ÷ # ÷ [0.2] <CARRIAGE RETURN (CR)> (CR) ÷ [5.02] COMBINING DIAERESIS (CM) ÷ [999.0] LEFT PARENTHESIS (OP) ÷ [0.3]
÷ 000D ÷ 0308 × 0028 ÷ # ÷ [0.2] <CARRIAGE RETURN (CR)> (CR) ÷ [5.02] COMBINING DIAERESIS (CM) ÷ [999.0] LEFT PARENTHESIS (OP) ÷ [0.3]
÷ 000D ÷ 0308 × 0020 ÷ 0028 ÷ # ÷ [0.2] <CARRIAGE RETURN (CR)> (CR) ÷ [5.02] COMBINING DIAERESIS (CM) × [7.01] SPACE (SP) ÷ [18.0] LEFT PARENTHESIS (OP) ÷ [0.3]
÷ 000D ÷ 0025 ÷ # ÷ [0.2] <CARRIAGE RETURN (CR)> (CR) ÷ [5.02] PERCENT SIGN (PO) ÷ [0.3]
÷ 000D ÷ 0020 ÷ 0025 ÷ # ÷ [0.2] <CARRIAGE RETURN (CR)> (CR) ÷ [5.02] SPACE (SP) ÷ [18.0] PERCENT SIGN (PO) ÷ [0.3]
@ -2918,7 +2922,7 @@
÷ 000A ÷ 0308 × 0020 ÷ 0030 ÷ # ÷ [0.2] <LINE FEED (LF)> (LF) ÷ [5.03] COMBINING DIAERESIS (CM) × [7.01] SPACE (SP) ÷ [18.0] DIGIT ZERO (NU) ÷ [0.3]
÷ 000A ÷ 0028 ÷ # ÷ [0.2] <LINE FEED (LF)> (LF) ÷ [5.03] LEFT PARENTHESIS (OP) ÷ [0.3]
÷ 000A ÷ 0020 ÷ 0028 ÷ # ÷ [0.2] <LINE FEED (LF)> (LF) ÷ [5.03] SPACE (SP) ÷ [18.0] LEFT PARENTHESIS (OP) ÷ [0.3]
÷ 000A ÷ 0308 ÷ 0028 ÷ # ÷ [0.2] <LINE FEED (LF)> (LF) ÷ [5.03] COMBINING DIAERESIS (CM) ÷ [999.0] LEFT PARENTHESIS (OP) ÷ [0.3]
÷ 000A ÷ 0308 × 0028 ÷ # ÷ [0.2] <LINE FEED (LF)> (LF) ÷ [5.03] COMBINING DIAERESIS (CM) ÷ [999.0] LEFT PARENTHESIS (OP) ÷ [0.3]
÷ 000A ÷ 0308 × 0020 ÷ 0028 ÷ # ÷ [0.2] <LINE FEED (LF)> (LF) ÷ [5.03] COMBINING DIAERESIS (CM) × [7.01] SPACE (SP) ÷ [18.0] LEFT PARENTHESIS (OP) ÷ [0.3]
÷ 000A ÷ 0025 ÷ # ÷ [0.2] <LINE FEED (LF)> (LF) ÷ [5.03] PERCENT SIGN (PO) ÷ [0.3]
÷ 000A ÷ 0020 ÷ 0025 ÷ # ÷ [0.2] <LINE FEED (LF)> (LF) ÷ [5.03] SPACE (SP) ÷ [18.0] PERCENT SIGN (PO) ÷ [0.3]
@ -3058,7 +3062,7 @@
÷ 0085 ÷ 0308 × 0020 ÷ 0030 ÷ # ÷ [0.2] <NEXT LINE (NEL)> (NL) ÷ [5.04] COMBINING DIAERESIS (CM) × [7.01] SPACE (SP) ÷ [18.0] DIGIT ZERO (NU) ÷ [0.3]
÷ 0085 ÷ 0028 ÷ # ÷ [0.2] <NEXT LINE (NEL)> (NL) ÷ [5.04] LEFT PARENTHESIS (OP) ÷ [0.3]
÷ 0085 ÷ 0020 ÷ 0028 ÷ # ÷ [0.2] <NEXT LINE (NEL)> (NL) ÷ [5.04] SPACE (SP) ÷ [18.0] LEFT PARENTHESIS (OP) ÷ [0.3]
÷ 0085 ÷ 0308 ÷ 0028 ÷ # ÷ [0.2] <NEXT LINE (NEL)> (NL) ÷ [5.04] COMBINING DIAERESIS (CM) ÷ [999.0] LEFT PARENTHESIS (OP) ÷ [0.3]
÷ 0085 ÷ 0308 × 0028 ÷ # ÷ [0.2] <NEXT LINE (NEL)> (NL) ÷ [5.04] COMBINING DIAERESIS (CM) ÷ [999.0] LEFT PARENTHESIS (OP) ÷ [0.3]
÷ 0085 ÷ 0308 × 0020 ÷ 0028 ÷ # ÷ [0.2] <NEXT LINE (NEL)> (NL) ÷ [5.04] COMBINING DIAERESIS (CM) × [7.01] SPACE (SP) ÷ [18.0] LEFT PARENTHESIS (OP) ÷ [0.3]
÷ 0085 ÷ 0025 ÷ # ÷ [0.2] <NEXT LINE (NEL)> (NL) ÷ [5.04] PERCENT SIGN (PO) ÷ [0.3]
÷ 0085 ÷ 0020 ÷ 0025 ÷ # ÷ [0.2] <NEXT LINE (NEL)> (NL) ÷ [5.04] SPACE (SP) ÷ [18.0] PERCENT SIGN (PO) ÷ [0.3]
@ -3336,9 +3340,9 @@
÷ 0030 × 0020 ÷ 0030 ÷ # ÷ [0.2] DIGIT ZERO (NU) × [7.01] SPACE (SP) ÷ [18.0] DIGIT ZERO (NU) ÷ [0.3]
÷ 0030 × 0308 × 0030 ÷ # ÷ [0.2] DIGIT ZERO (NU) × [9.0] COMBINING DIAERESIS (CM) × [25.03] DIGIT ZERO (NU) ÷ [0.3]
÷ 0030 × 0308 × 0020 ÷ 0030 ÷ # ÷ [0.2] DIGIT ZERO (NU) × [9.0] COMBINING DIAERESIS (CM) × [7.01] SPACE (SP) ÷ [18.0] DIGIT ZERO (NU) ÷ [0.3]
÷ 0030 ÷ 0028 ÷ # ÷ [0.2] DIGIT ZERO (NU) ÷ [999.0] LEFT PARENTHESIS (OP) ÷ [0.3]
÷ 0030 × 0028 ÷ # ÷ [0.2] DIGIT ZERO (NU) ÷ [999.0] LEFT PARENTHESIS (OP) ÷ [0.3]
÷ 0030 × 0020 ÷ 0028 ÷ # ÷ [0.2] DIGIT ZERO (NU) × [7.01] SPACE (SP) ÷ [18.0] LEFT PARENTHESIS (OP) ÷ [0.3]
÷ 0030 × 0308 ÷ 0028 ÷ # ÷ [0.2] DIGIT ZERO (NU) × [9.0] COMBINING DIAERESIS (CM) ÷ [999.0] LEFT PARENTHESIS (OP) ÷ [0.3]
÷ 0030 × 0308 × 0028 ÷ # ÷ [0.2] DIGIT ZERO (NU) × [9.0] COMBINING DIAERESIS (CM) ÷ [999.0] LEFT PARENTHESIS (OP) ÷ [0.3]
÷ 0030 × 0308 × 0020 ÷ 0028 ÷ # ÷ [0.2] DIGIT ZERO (NU) × [9.0] COMBINING DIAERESIS (CM) × [7.01] SPACE (SP) ÷ [18.0] LEFT PARENTHESIS (OP) ÷ [0.3]
÷ 0030 × 0025 ÷ # ÷ [0.2] DIGIT ZERO (NU) × [25.05] PERCENT SIGN (PO) ÷ [0.3]
÷ 0030 × 0020 ÷ 0025 ÷ # ÷ [0.2] DIGIT ZERO (NU) × [7.01] SPACE (SP) ÷ [18.0] PERCENT SIGN (PO) ÷ [0.3]
@ -4038,7 +4042,7 @@
÷ 0020 ÷ 0308 × 0020 ÷ 0030 ÷ # ÷ [0.2] SPACE (SP) ÷ [18.0] COMBINING DIAERESIS (CM) × [7.01] SPACE (SP) ÷ [18.0] DIGIT ZERO (NU) ÷ [0.3]
÷ 0020 ÷ 0028 ÷ # ÷ [0.2] SPACE (SP) ÷ [18.0] LEFT PARENTHESIS (OP) ÷ [0.3]
÷ 0020 × 0020 ÷ 0028 ÷ # ÷ [0.2] SPACE (SP) × [7.01] SPACE (SP) ÷ [18.0] LEFT PARENTHESIS (OP) ÷ [0.3]
÷ 0020 ÷ 0308 ÷ 0028 ÷ # ÷ [0.2] SPACE (SP) ÷ [18.0] COMBINING DIAERESIS (CM) ÷ [999.0] LEFT PARENTHESIS (OP) ÷ [0.3]
÷ 0020 ÷ 0308 × 0028 ÷ # ÷ [0.2] SPACE (SP) ÷ [18.0] COMBINING DIAERESIS (CM) ÷ [999.0] LEFT PARENTHESIS (OP) ÷ [0.3]
÷ 0020 ÷ 0308 × 0020 ÷ 0028 ÷ # ÷ [0.2] SPACE (SP) ÷ [18.0] COMBINING DIAERESIS (CM) × [7.01] SPACE (SP) ÷ [18.0] LEFT PARENTHESIS (OP) ÷ [0.3]
÷ 0020 ÷ 0025 ÷ # ÷ [0.2] SPACE (SP) ÷ [18.0] PERCENT SIGN (PO) ÷ [0.3]
÷ 0020 × 0020 ÷ 0025 ÷ # ÷ [0.2] SPACE (SP) × [7.01] SPACE (SP) ÷ [18.0] PERCENT SIGN (PO) ÷ [0.3]
@ -4458,7 +4462,7 @@
÷ 200B ÷ 0308 × 0020 ÷ 0030 ÷ # ÷ [0.2] ZERO WIDTH SPACE (ZW) ÷ [8.0] COMBINING DIAERESIS (CM) × [7.01] SPACE (SP) ÷ [18.0] DIGIT ZERO (NU) ÷ [0.3]
÷ 200B ÷ 0028 ÷ # ÷ [0.2] ZERO WIDTH SPACE (ZW) ÷ [8.0] LEFT PARENTHESIS (OP) ÷ [0.3]
÷ 200B × 0020 ÷ 0028 ÷ # ÷ [0.2] ZERO WIDTH SPACE (ZW) × [7.01] SPACE (SP) ÷ [18.0] LEFT PARENTHESIS (OP) ÷ [0.3]
÷ 200B ÷ 0308 ÷ 0028 ÷ # ÷ [0.2] ZERO WIDTH SPACE (ZW) ÷ [8.0] COMBINING DIAERESIS (CM) ÷ [999.0] LEFT PARENTHESIS (OP) ÷ [0.3]
÷ 200B ÷ 0308 × 0028 ÷ # ÷ [0.2] ZERO WIDTH SPACE (ZW) ÷ [8.0] COMBINING DIAERESIS (CM) ÷ [999.0] LEFT PARENTHESIS (OP) ÷ [0.3]
÷ 200B ÷ 0308 × 0020 ÷ 0028 ÷ # ÷ [0.2] ZERO WIDTH SPACE (ZW) ÷ [8.0] COMBINING DIAERESIS (CM) × [7.01] SPACE (SP) ÷ [18.0] LEFT PARENTHESIS (OP) ÷ [0.3]
÷ 200B ÷ 0025 ÷ # ÷ [0.2] ZERO WIDTH SPACE (ZW) ÷ [8.0] PERCENT SIGN (PO) ÷ [0.3]
÷ 200B × 0020 ÷ 0025 ÷ # ÷ [0.2] ZERO WIDTH SPACE (ZW) × [7.01] SPACE (SP) ÷ [18.0] PERCENT SIGN (PO) ÷ [0.3]
@ -4596,9 +4600,9 @@
÷ 00A7 × 0020 ÷ 0030 ÷ # ÷ [0.2] SECTION SIGN (AI_AL) × [7.01] SPACE (SP) ÷ [18.0] DIGIT ZERO (NU) ÷ [0.3]
÷ 00A7 × 0308 × 0030 ÷ # ÷ [0.2] SECTION SIGN (AI_AL) × [9.0] COMBINING DIAERESIS (CM) × [23.02] DIGIT ZERO (NU) ÷ [0.3]
÷ 00A7 × 0308 × 0020 ÷ 0030 ÷ # ÷ [0.2] SECTION SIGN (AI_AL) × [9.0] COMBINING DIAERESIS (CM) × [7.01] SPACE (SP) ÷ [18.0] DIGIT ZERO (NU) ÷ [0.3]
÷ 00A7 ÷ 0028 ÷ # ÷ [0.2] SECTION SIGN (AI_AL) ÷ [999.0] LEFT PARENTHESIS (OP) ÷ [0.3]
÷ 00A7 × 0028 ÷ # ÷ [0.2] SECTION SIGN (AI_AL) ÷ [999.0] LEFT PARENTHESIS (OP) ÷ [0.3]
÷ 00A7 × 0020 ÷ 0028 ÷ # ÷ [0.2] SECTION SIGN (AI_AL) × [7.01] SPACE (SP) ÷ [18.0] LEFT PARENTHESIS (OP) ÷ [0.3]
÷ 00A7 × 0308 ÷ 0028 ÷ # ÷ [0.2] SECTION SIGN (AI_AL) × [9.0] COMBINING DIAERESIS (CM) ÷ [999.0] LEFT PARENTHESIS (OP) ÷ [0.3]
÷ 00A7 × 0308 × 0028 ÷ # ÷ [0.2] SECTION SIGN (AI_AL) × [9.0] COMBINING DIAERESIS (CM) ÷ [999.0] LEFT PARENTHESIS (OP) ÷ [0.3]
÷ 00A7 × 0308 × 0020 ÷ 0028 ÷ # ÷ [0.2] SECTION SIGN (AI_AL) × [9.0] COMBINING DIAERESIS (CM) × [7.01] SPACE (SP) ÷ [18.0] LEFT PARENTHESIS (OP) ÷ [0.3]
÷ 00A7 ÷ 0025 ÷ # ÷ [0.2] SECTION SIGN (AI_AL) ÷ [999.0] PERCENT SIGN (PO) ÷ [0.3]
÷ 00A7 × 0020 ÷ 0025 ÷ # ÷ [0.2] SECTION SIGN (AI_AL) × [7.01] SPACE (SP) ÷ [18.0] PERCENT SIGN (PO) ÷ [0.3]
@ -4736,9 +4740,9 @@
÷ E000 × 0020 ÷ 0030 ÷ # ÷ [0.2] <private-use-E000> (XX_AL) × [7.01] SPACE (SP) ÷ [18.0] DIGIT ZERO (NU) ÷ [0.3]
÷ E000 × 0308 × 0030 ÷ # ÷ [0.2] <private-use-E000> (XX_AL) × [9.0] COMBINING DIAERESIS (CM) × [23.02] DIGIT ZERO (NU) ÷ [0.3]
÷ E000 × 0308 × 0020 ÷ 0030 ÷ # ÷ [0.2] <private-use-E000> (XX_AL) × [9.0] COMBINING DIAERESIS (CM) × [7.01] SPACE (SP) ÷ [18.0] DIGIT ZERO (NU) ÷ [0.3]
÷ E000 ÷ 0028 ÷ # ÷ [0.2] <private-use-E000> (XX_AL) ÷ [999.0] LEFT PARENTHESIS (OP) ÷ [0.3]
÷ E000 × 0028 ÷ # ÷ [0.2] <private-use-E000> (XX_AL) ÷ [999.0] LEFT PARENTHESIS (OP) ÷ [0.3]
÷ E000 × 0020 ÷ 0028 ÷ # ÷ [0.2] <private-use-E000> (XX_AL) × [7.01] SPACE (SP) ÷ [18.0] LEFT PARENTHESIS (OP) ÷ [0.3]
÷ E000 × 0308 ÷ 0028 ÷ # ÷ [0.2] <private-use-E000> (XX_AL) × [9.0] COMBINING DIAERESIS (CM) ÷ [999.0] LEFT PARENTHESIS (OP) ÷ [0.3]
÷ E000 × 0308 × 0028 ÷ # ÷ [0.2] <private-use-E000> (XX_AL) × [9.0] COMBINING DIAERESIS (CM) ÷ [999.0] LEFT PARENTHESIS (OP) ÷ [0.3]
÷ E000 × 0308 × 0020 ÷ 0028 ÷ # ÷ [0.2] <private-use-E000> (XX_AL) × [9.0] COMBINING DIAERESIS (CM) × [7.01] SPACE (SP) ÷ [18.0] LEFT PARENTHESIS (OP) ÷ [0.3]
÷ E000 ÷ 0025 ÷ # ÷ [0.2] <private-use-E000> (XX_AL) ÷ [999.0] PERCENT SIGN (PO) ÷ [0.3]
÷ E000 × 0020 ÷ 0025 ÷ # ÷ [0.2] <private-use-E000> (XX_AL) × [7.01] SPACE (SP) ÷ [18.0] PERCENT SIGN (PO) ÷ [0.3]
@ -4876,9 +4880,9 @@
÷ 0E01 × 0020 ÷ 0030 ÷ # ÷ [0.2] THAI CHARACTER KO KAI (SA_AL) × [7.01] SPACE (SP) ÷ [18.0] DIGIT ZERO (NU) ÷ [0.3]
÷ 0E01 × 0308 × 0030 ÷ # ÷ [0.2] THAI CHARACTER KO KAI (SA_AL) × [9.0] COMBINING DIAERESIS (CM) × [23.02] DIGIT ZERO (NU) ÷ [0.3]
÷ 0E01 × 0308 × 0020 ÷ 0030 ÷ # ÷ [0.2] THAI CHARACTER KO KAI (SA_AL) × [9.0] COMBINING DIAERESIS (CM) × [7.01] SPACE (SP) ÷ [18.0] DIGIT ZERO (NU) ÷ [0.3]
÷ 0E01 ÷ 0028 ÷ # ÷ [0.2] THAI CHARACTER KO KAI (SA_AL) ÷ [999.0] LEFT PARENTHESIS (OP) ÷ [0.3]
÷ 0E01 × 0028 ÷ # ÷ [0.2] THAI CHARACTER KO KAI (SA_AL) ÷ [999.0] LEFT PARENTHESIS (OP) ÷ [0.3]
÷ 0E01 × 0020 ÷ 0028 ÷ # ÷ [0.2] THAI CHARACTER KO KAI (SA_AL) × [7.01] SPACE (SP) ÷ [18.0] LEFT PARENTHESIS (OP) ÷ [0.3]
÷ 0E01 × 0308 ÷ 0028 ÷ # ÷ [0.2] THAI CHARACTER KO KAI (SA_AL) × [9.0] COMBINING DIAERESIS (CM) ÷ [999.0] LEFT PARENTHESIS (OP) ÷ [0.3]
÷ 0E01 × 0308 × 0028 ÷ # ÷ [0.2] THAI CHARACTER KO KAI (SA_AL) × [9.0] COMBINING DIAERESIS (CM) ÷ [999.0] LEFT PARENTHESIS (OP) ÷ [0.3]
÷ 0E01 × 0308 × 0020 ÷ 0028 ÷ # ÷ [0.2] THAI CHARACTER KO KAI (SA_AL) × [9.0] COMBINING DIAERESIS (CM) × [7.01] SPACE (SP) ÷ [18.0] LEFT PARENTHESIS (OP) ÷ [0.3]
÷ 0E01 ÷ 0025 ÷ # ÷ [0.2] THAI CHARACTER KO KAI (SA_AL) ÷ [999.0] PERCENT SIGN (PO) ÷ [0.3]
÷ 0E01 × 0020 ÷ 0025 ÷ # ÷ [0.2] THAI CHARACTER KO KAI (SA_AL) × [7.01] SPACE (SP) ÷ [18.0] PERCENT SIGN (PO) ÷ [0.3]
@ -4924,7 +4928,7 @@
÷ 0063 × 0061 × 006E × 2019 × 0074 ÷ # ÷ [0.2] LATIN SMALL LETTER C (AL) × [28.0] LATIN SMALL LETTER A (AL) × [28.0] LATIN SMALL LETTER N (AL) × [19.01] RIGHT SINGLE QUOTATION MARK (QU) × [19.02] LATIN SMALL LETTER T (AL) ÷ [0.3]
÷ 0027 × 0063 × 0061 × 006E × 0027 × 0020 ÷ 006E × 006F × 0074 ÷ # ÷ [0.2] APOSTROPHE (QU) × [19.02] LATIN SMALL LETTER C (AL) × [28.0] LATIN SMALL LETTER A (AL) × [28.0] LATIN SMALL LETTER N (AL) × [19.01] APOSTROPHE (QU) × [7.01] SPACE (SP) ÷ [18.0] LATIN SMALL LETTER N (AL) × [28.0] LATIN SMALL LETTER O (AL) × [28.0] LATIN SMALL LETTER T (AL) ÷ [0.3]
÷ 0063 × 0061 × 006E × 0020 ÷ 0027 × 006E × 006F × 0074 × 0027 ÷ # ÷ [0.2] LATIN SMALL LETTER C (AL) × [28.0] LATIN SMALL LETTER A (AL) × [28.0] LATIN SMALL LETTER N (AL) × [7.01] SPACE (SP) ÷ [18.0] APOSTROPHE (QU) × [19.02] LATIN SMALL LETTER N (AL) × [28.0] LATIN SMALL LETTER O (AL) × [28.0] LATIN SMALL LETTER T (AL) × [19.01] APOSTROPHE (QU) ÷ [0.3]
÷ 0062 × 0075 × 0067 ÷ 0028 × 0073 × 0029 ÷ # ÷ [0.2] LATIN SMALL LETTER B (AL) × [28.0] LATIN SMALL LETTER U (AL) × [28.0] LATIN SMALL LETTER G (AL) ÷ [999.0] LEFT PARENTHESIS (OP) × [14.0] LATIN SMALL LETTER S (AL) × [13.02] RIGHT PARENTHESIS (CL) ÷ [0.3]
÷ 0062 × 0075 × 0067 × 0028 × 0073 × 0029 ÷ # ÷ [0.2] LATIN SMALL LETTER B (AL) × [28.0] LATIN SMALL LETTER U (AL) × [28.0] LATIN SMALL LETTER G (AL) ÷ [999.0] LEFT PARENTHESIS (OP) × [14.0] LATIN SMALL LETTER S (AL) × [13.02] RIGHT PARENTHESIS (CL) ÷ [0.3]
÷ 002E × 002E ÷ 307E ÷ 3059 × 3002 ÷ 0058 × 004D × 004C ÷ 306E × 002E × 002E ÷ # ÷ [0.2] FULL STOP (IS) × [13.02] FULL STOP (IS) ÷ [999.0] HIRAGANA LETTER MA (ID) ÷ [999.0] HIRAGANA LETTER SU (ID) × [13.02] IDEOGRAPHIC FULL STOP (CL) ÷ [999.0] LATIN CAPITAL LETTER X (AL) × [28.0] LATIN CAPITAL LETTER M (AL) × [28.0] LATIN CAPITAL LETTER L (AL) ÷ [999.0] HIRAGANA LETTER NO (ID) × [13.02] FULL STOP (IS) × [13.02] FULL STOP (IS) ÷ [0.3]
÷ 0061 × 0062 × 00AD ÷ 0062 × 0079 ÷ # ÷ [0.2] LATIN SMALL LETTER A (AL) × [28.0] LATIN SMALL LETTER B (AL) × [21.01] SOFT HYPHEN (BA) ÷ [999.0] LATIN SMALL LETTER B (AL) × [28.0] LATIN SMALL LETTER Y (AL) ÷ [0.3]
÷ 002D × 0033 ÷ # ÷ [0.2] HYPHEN-MINUS (HY) × [25.02] DIGIT THREE (NU) ÷ [0.3]
@ -4933,5 +4937,5 @@
÷ 0061 × 0020 × 0020 ÷ 0062 ÷ # ÷ [0.2] LATIN SMALL LETTER A (AL) × [7.01] SPACE (SP) × [7.01] SPACE (SP) ÷ [18.0] LATIN SMALL LETTER B (AL) ÷ [0.3]
÷ 0061 × 0020 × 0020 × 200B ÷ 0062 ÷ # ÷ [0.2] LATIN SMALL LETTER A (AL) × [7.01] SPACE (SP) × [7.01] SPACE (SP) × [7.02] ZERO WIDTH SPACE (ZW) ÷ [8.0] LATIN SMALL LETTER B (AL) ÷ [0.3]
÷ 0061 × 0020 ÷ 0308 × 0062 ÷ # ÷ [0.2] LATIN SMALL LETTER A (AL) × [7.01] SPACE (SP) ÷ [18.0] COMBINING DIAERESIS (CM) × [28.0] LATIN SMALL LETTER B (AL) ÷ [0.3]
÷ 0031 × 0308 × 0062 ÷ 0028 × 0061 × 0029 × 002D ÷ 0028 × 0062 × 0029 ÷ # ÷ [0.2] DIGIT ONE (NU) × [9.0] COMBINING DIAERESIS (CM) × [23.03] LATIN SMALL LETTER B (AL) ÷ [999.0] LEFT PARENTHESIS (OP) × [14.0] LATIN SMALL LETTER A (AL) × [13.02] RIGHT PARENTHESIS (CL) × [21.02] HYPHEN-MINUS (HY) ÷ [999.0] LEFT PARENTHESIS (OP) × [14.0] LATIN SMALL LETTER B (AL) × [13.02] RIGHT PARENTHESIS (CL) ÷ [0.3]
÷ 0031 × 0308 × 0062 × 0028 × 0061 × 0029 × 002D ÷ 0028 × 0062 × 0029 ÷ # ÷ [0.2] DIGIT ONE (NU) × [9.0] COMBINING DIAERESIS (CM) × [23.03] LATIN SMALL LETTER B (AL) ÷ [999.0] LEFT PARENTHESIS (OP) × [14.0] LATIN SMALL LETTER A (AL) × [13.02] RIGHT PARENTHESIS (CL) × [21.02] HYPHEN-MINUS (HY) ÷ [999.0] LEFT PARENTHESIS (OP) × [14.0] LATIN SMALL LETTER B (AL) × [13.02] RIGHT PARENTHESIS (CL) ÷ [0.3]
# Lines: 4900

18
icu4c/source/test/testdata/rbbitst.txt vendored
View File

@ -25,8 +25,7 @@
# Temp debugging tests
<line>
# to test for bug #4097920
<data>•dog,cat,mouse •(one)•(two)\n<100></data>
<data>•\ufffc•\u30e3\u000c<100>\u1b39\u300a\u002f\u203a\u200b•\ufffc•\uaf64•\udcfb•</data>
########################################################################################
#
@ -504,9 +503,8 @@ What is the proper use of the abbreviation pp.? •Yes, I am definatelly 12" tal
# Regression for bug 836
# Note: Unicode 5.1 changed this behavior
# ICU will want to change it back before releasing,
# so there is no break preceding the '('
<data>•AAA•(AAA •</data>
# Unicode 5.2 changed it again, there is no break following the '('
<data>•AAA(AAA •</data>
# Try some words from other scripts.
# Greek, Cyrillic, Hebrew, Arabic, Arabic, Georgian, Latin
@ -518,6 +516,16 @@ What is the proper use of the abbreviation pp.? •Yes, I am definatelly 12" tal
#
<data>•abc\ud801xyz•</data>
#
# Regression tests for failures that originally came from the monkey test.
# Monkey test failure lines can, with slight reformatting, be copied into this section
# as test cases. The error display from here is more informative.
#
<data>•\ufffc•\u30e3\u000c<100>\u1b39\u300a\u002f\u203a\u200b•\ufffc•\uaf64•\udcfb•</data>
<data>•\u114d\u31f3•\ube44\u002d•\u0362\u24e2\u276e\u2014\u205f\ufe16•\uc877•\u0fd0\u000a<100>\u20a3•</data>
<data>•\u080a\u215b\U0001d7d3\u002c•\u2025\U000e012e•\u02df\u118d\u0029\ua8d6\u0085<100>\u6cc4\u2024\u202f\ufffc•</data>
########################################################################################
#
#