Based on: https://gerrit.libreoffice.org/c/core/+/158749 Modified to be applied on LibreOffice 7.6.4.1 --- diff --git a/configure.ac b/configure.ac index e41223f..ff72549 100644 --- a/configure +++ b/configure @@ -34568,2 +34568,2 @@ -ICU_MAJOR=73 -ICU_MINOR=2 +ICU_MAJOR=74 +ICU_MINOR=1 diff --git a/download.lst b/download.lst index 60ac664..faccfc7 100644 --- a/download.lst +++ b/download.lst @@ -312,10 +312,10 @@ # three static lines # so that git cherry-pick # will not run into conflicts -ICU_SHA256SUM := 818a80712ed3caacd9b652305e01afc7fa167e6f2e94996da44b90c2ab604ce1 -ICU_TARBALL := icu4c-73_2-src.tgz -ICU_DATA_SHA256SUM := ca1ee076163b438461e484421a7679fc33a64cd0a54f9d4b401893fa1eb42701 -ICU_DATA_TARBALL := icu4c-73_2-data.zip +ICU_SHA256SUM := 86ce8e60681972e60e4dcb2490c697463fcec60dd400a5f9bffba26d0b52b8d0 +ICU_TARBALL := icu4c-74_1-src.tgz +ICU_DATA_SHA256SUM := 67d5ab39c5187e1dd0fed60a3fe52794dce9784b4c045cb85e19f5d317fd783f +ICU_DATA_TARBALL := icu4c-74_1-data.zip # three static lines # so that git cherry-pick # will not run into conflicts diff --git a/external/icu/icu4c-khmerbreakengine.patch.1 b/external/icu/icu4c-khmerbreakengine.patch.1 index 6059140..db8ac50 100644 --- a/external/icu/icu4c-khmerbreakengine.patch.1 +++ b/external/icu/icu4c-khmerbreakengine.patch.1 @@ -796,7 +796,6 @@ if (wordCount < limit) { if (values != nullptr) { values[wordCount] = bt.getValue(); - diff -ur icu.org/source/common/dictionarydata.h icu/source/common/dictionarydata.h --- icu.org/source/common/dictionarydata.h 2023-06-14 06:23:55.000000000 +0900 +++ icu/source/common/dictionarydata.h 2023-06-26 17:43:53.097724900 +0900 --- a/i18npool/source/breakiterator/data/line.txt +++ b/i18npool/source/breakiterator/data/line.txt @@ -1,177 +1,112 @@ -# Copyright (c) 2002-2006 International Business Machines Corporation and +# Copyright (C) 2016 and later: Unicode, Inc. and others. +# License & terms of use: http://www.unicode.org/copyright.html +# Copyright (c) 2002-2016 International Business Machines Corporation and # others. All Rights Reserved. # # file: line.txt # # Line Breaking Rules -# Implement default line breaking as defined by Unicode Standard Annex #14 version 5.0.0 -# http://www.unicode.org/reports/tr14/ - - +# Implement default line breaking as defined by +# Unicode Standard Annex #14 (https://www.unicode.org/reports/tr14/) +# for Unicode 14.0, with the following modification: +# +# Boundaries between hyphens and following letters are suppressed when +# there is a boundary preceding the hyphen. See rule 20.9 +# +# This corresponds to CSS line-break=strict (BCP47 -u-lb-strict). +# It sets characters of class CJ to behave like NS. # # Character Classes defined by TR 14. # !!chain; -!!LBCMNoChain; - - -!!lookAheadHardBreak; -# -# !!lookAheadHardBreak Described here because it is (as yet) undocumented elsewhere -# and only used for the line break rules. -# -# It is used in the implementation of the incredibly annoying rule LB 10 -# which says to treat any combining mark that is not attached to a base -# character as if it were of class AL (alphabetic). -# -# The problem occurs in the reverse rules. -# -# Consider a sequence like, with correct breaks as shown -# LF ID CM AL AL -# ^ ^ ^ -# Then consider the sequence without the initial ID (ideographic) -# LF CM AL AL -# ^ ^ -# Our CM, which in the first example was attached to the ideograph, -# is now unattached, becomes an alpha, and joins in with the other -# alphas. -# -# When iterating forwards, these sequences do not present any problems -# When iterating backwards, we need to look ahead when encountering -# a CM to see whether it attaches to something further on or not. -# (Look-ahead in a reverse rule is looking towards the start) -# -# If the CM is unattached, we need to force a break. -# -# !!lookAheadHardBreak forces the run time state machine to -# stop immediately when a look ahead rule ( '/' operator) matches, -# and set the match position to that of the look-ahead operator, -# no matter what other rules may be in play at the time. -# -# See rule LB 19 for an example. -# +!!quoted_literals_only; $AI = [:LineBreak = Ambiguous:]; -$DG = \u00B0; -$AL = [[:LineBreak = Alphabetic:] $DG]; +$AK = [:LineBreak = Aksara:]; +$AL = [:LineBreak = Alphabetic:]; +$AP = [:LineBreak = Aksara_Prebase:]; +$AS = [:LineBreak = Aksara_Start:]; $BA = [:LineBreak = Break_After:]; +$HH = [\u2010]; # \u2010 is HYPHEN, default line break is BA. $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:] ; -$CM = [:LineBreak = Combining_Mark:]; +$CL = [:LineBreak = Close_Punctuation:]; +# $CM = [:LineBreak = Combining_Mark:]; +$CP = [:LineBreak = Close_Parenthesis:]; $CR = [:LineBreak = Carriage_Return:]; +$EB = [:LineBreak = EB:]; +$EM = [:LineBreak = EM:]; $EX = [:LineBreak = Exclamation:]; $GL = [:LineBreak = Glue:]; $HL = [:LineBreak = Hebrew_Letter:]; $HY = [:LineBreak = Hyphen:]; $H2 = [:LineBreak = H2:]; $H3 = [:LineBreak = H3:]; -$ID = [[:LineBreak = Ideographic:] - [\ufe30]]; -$IN = [:LineBreak = Inseparable:]; -$IS = [[:LineBreak = Infix_Numeric:] [\ufe30]]; +$ID = [:LineBreak = Ideographic:]; +$IN = [:LineBreak = Inseperable:]; +$IS = [:LineBreak = Infix_Numeric:]; $JL = [:LineBreak = JL:]; $JV = [:LineBreak = JV:]; $JT = [:LineBreak = JT:]; $LF = [:LineBreak = Line_Feed:]; $NL = [:LineBreak = Next_Line:]; +# NS includes CJ for CSS strict line breaking. $NS = [[:LineBreak = Nonstarter:] $CJ]; $NU = [:LineBreak = Numeric:]; -$OP = [[:LineBreak = Open_Punctuation:] - $DG]; +$OP = [:LineBreak = Open_Punctuation:]; $PO = [:LineBreak = Postfix_Numeric:]; -$BS = \u005C; -$PR = [[:LineBreak = Prefix_Numeric:] - $BS]; +$PR = [:LineBreak = Prefix_Numeric:]; $QU = [:LineBreak = Quotation:]; +$RI = [:LineBreak = Regional_Indicator:]; $SA = [:LineBreak = Complex_Context:]; $SG = [:LineBreak = Surrogate:]; $SP = [:LineBreak = Space:]; -$SY = [[:LineBreak = Break_Symbols:] $BS]; +$SY = [:LineBreak = Break_Symbols:]; +$VF = [:LineBreak = Virama_Final:]; +$VI = [:LineBreak = Virama:]; $WJ = [:LineBreak = Word_Joiner:]; $XX = [:LineBreak = Unknown:]; $ZW = [:LineBreak = ZWSpace:]; +$ZWJ = [:LineBreak = ZWJ:]; + +# OP30 and CP30 are variants of OP and CP that appear in-line in rule LB30 from UAX 14, +# without a formal name. Because ICU rules require multiple uses of the expressions, +# give them a single definition with a name + +$OP30 = [$OP - [\p{ea=F}\p{ea=W}\p{ea=H}]]; +$CP30 = [$CP - [\p{ea=F}\p{ea=W}\p{ea=H}]]; + +$ExtPictUnassigned = [\p{Extended_Pictographic} & \p{Cn}]; + +# By LB9, a ZWJ also behaves as a CM. Including it in the definition of CM avoids having to explicitly +# list it in the numerous rules that use CM. +# By LB1, SA characters with general categor of Mn or Mc also resolve to CM. + +$CM = [[:LineBreak = Combining_Mark:] $ZWJ [$SA & [[:Mn:][:Mc:]]]]; +$CMX = [[$CM] - [$ZWJ]]; # Dictionary character set, for triggering language-based break engines. Currently -# limited to LineBreak=Complex_Context. Note that this set only works in Unicode -# 5.0 or later as the definition of Complex_Context was corrected to include all -# characters requiring dictionary break. +# limited to LineBreak=Complex_Context (SA). -$dictionary = [:LineBreak = Complex_Context:]; +$dictionary = [$SA]; # # Rule LB1. By default, treat AI (characters with ambiguous east Asian width), -# SA (South East Asian: Thai, Lao, Khmer) +# SA (Dictionary chars, excluding Mn and Mc) # SG (Unpaired Surrogates) # XX (Unknown, unassigned) # as $AL (Alphabetic) # -$ALPlus = [$AL $AI $SA $SG $XX]; +$ALPlus = [$AL $AI $SG $XX [$SA-[[:Mn:][:Mc:]]]]; -# -# Combining Marks. X $CM* behaves as if it were X. Rule LB6. -# -$ALcm = $ALPlus $CM*; -$BAcm = $BA $CM*; -$BBcm = $BB $CM*; -$B2cm = $B2 $CM*; -$CLcm = $CL $CM*; -$EXcm = $EX $CM*; -$GLcm = $GL $CM*; -$HLcm = $HL $CM*; -$HYcm = $HY $CM*; -$H2cm = $H2 $CM*; -$H3cm = $H3 $CM*; -$IDcm = $ID $CM*; -$INcm = $IN $CM*; -$IScm = $IS $CM*; -$JLcm = $JL $CM*; -$JVcm = $JV $CM*; -$JTcm = $JT $CM*; -$NScm = $NS $CM*; -$NUcm = $NU $CM*; -$OPcm = $OP $CM*; -$POcm = $PO $CM*; -$PRcm = $PR $CM*; -$QUcm = $QU $CM*; -$SYcm = $SY $CM*; -$WJcm = $WJ $CM*; ## ------------------------------------------------- -!!forward; - -# -# Each class of character can stand by itself as an unbroken token, with trailing combining stuff -# -$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+; - # # CAN_CM is the set of characters that may combine with CM combining chars. # Note that Linebreak UAX 14's concept of a combining char and the rules @@ -186,19 +121,15 @@ # # AL_FOLLOW set of chars that can unconditionally follow an AL # Needed in rules where stand-alone $CM s are treated as AL. -# Chaining is disabled with CM because it causes other failures, -# so for this one case we need to manually list out longer sequences. # -$AL_FOLLOW_NOCM = [$BK $CR $LF $NL $ZW $SP]; -$AL_FOLLOW_CM = [$CL $EX $HL $IS $SY $WJ $GL $QU $BA $HY $NS $IN $NU $ALPlus $OP]; -$AL_FOLLOW = [$AL_FOLLOW_NOCM $AL_FOLLOW_CM]; +$AL_FOLLOW = [$BK $CR $LF $NL $ZW $SP $CL $CP $EX $HL $IS $SY $WJ $GL $OP30 $QU $BA $HY $NS $IN $NU $PR $PO $ALPlus]; # # Rule LB 4, 5 Mandatory (Hard) breaks. # $LB4Breaks = [$BK $CR $LF $NL]; -$LB4NonBreaks = [^$BK $CR $LF $NL]; +$LB4NonBreaks = [^$BK $CR $LF $NL $CM]; $CR $LF {100}; # @@ -206,91 +137,134 @@ # $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 +# ZW SP* รท # $LB8Breaks = [$LB4Breaks $ZW]; $LB8NonBreaks = [[$LB4NonBreaks] - [$ZW]]; +$ZW $SP* / [^$SP $ZW $LB4Breaks]; +# LB 8a ZWJ x Do not break Emoji ZWJ sequences. +# +$ZWJ [^$CM]; -# LB 9 Combining marks. X $CM needs to behave like X, where X is not $SP, $BK $CR $LF $NL -# $CM not covered by the above needs to behave like $AL +# LB 9 Combining marks. X $CM needs to behave like X, where X is not $SP, $BK $CR $LF $NL +# $CM not covered by the above needs to behave like $AL # 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+ $WJcm; +$CAN_CM $CM* $WJ; +$LB8NonBreaks $WJ; +^$CM+ $WJ; -$WJcm [^$CAN_CM]; -$WJcm $CAN_CM $CM*; +$WJ $CM* .; # -# LB 12 Do not break before or after NBSP and related characters. -# -# (!SP) x GL -[$LB8NonBreaks-$SP] $CM* $GLcm; -$CM+ $GLcm; - +# LB 12 Do not break after NBSP and related characters. # GL x -$GLcm ($LB8Breaks | $SP); -$GLcm [$LB8NonBreaks-$SP] $CM*; # Don't let a combining mark go onto $CR, $BK, etc. - # TODO: I don't think we need this rule. - # All but $CM will chain off of preceding rule. - # $GLcm will pick up the CM case by itself. - - - +# +$GL $CM* .; # -# LB 13 Don't break before ']' or '!' or ';' or '/', even after spaces. +# LB 12a Do not break before NBSP and related characters ... +# [^SP BA HY] x GL +# +[[$LB8NonBreaks] - [$SP $BA $HY]] $CM* $GL; +^$CM+ $GL; + + + + +# LB 13 Don't break before ']' or '!' or '/', even after spaces. # $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 $CP; +$CAN_CM $CM* $CP; +^$CM+ $CP; # by rule 10, stand-alone CM behaves as AL $LB8NonBreaks $EX; $CAN_CM $CM* $EX; -$CM+ $EX; # by rule 10, stand-alone CM behaves as AL - -$LB8NonBreaks $IS; -$CAN_CM $CM* $IS; -$CM+ $IS; # by rule 10, stand-alone CM behaves as AL +^$CM+ $EX; # 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+ $SY; # by rule 10, stand-alone CM behaves as AL # -# LB 14 Do not break after OP, even after spaced +# LB 14 Do not break after OP, even after spaces +# Note subtle interaction with "SP IS /" rules in LB14a. +# This rule consumes the SP, chaining happens on the IS, effectivley overriding the SP IS rules, +# which is the desired behavior. # -$OPcm $SP* $CAN_CM $CM*; -$OPcm $SP* $CANT_CM; +$OP $CM* $SP* .; -$OPcm $SP+ $CM+ $AL_FOLLOW?; # by rule 10, stand-alone CM behaves as AL +$OP $CM* $SP+ $CM+ $AL_FOLLOW?; # by rule 10, stand-alone CM behaves as AL + # by rule 8, CM following a SP is stand-alone. -# LB 15 -# $QUcm $SP* $OPcm; + +# LB 15a +($OP $CM* $SP+ | [$OP $QU $GL] $CM*) ([\p{Pi} & $QU] $CM* $SP*)+ .; +($OP $CM* $SP+ | [$OP $QU $GL] $CM*) ([\p{Pi} & $QU] $CM* $SP*)+ $SP $CM+ $AL_FOLLOW?; +^([\p{Pi} & $QU] $CM* $SP*)+ .; +^([\p{Pi} & $QU] $CM* $SP*)+ $SP $CM+ $AL_FOLLOW?; + +# LB 15b +$LB8NonBreaks [\p{Pf} & $QU] $CM* [$SP $GL $WJ $CL $QU $CP $EX $IS $SY $BK $CR $LF $NL $ZW {eof}]; +$CAN_CM $CM* [\p{Pf} & $QU] $CM* [$SP $GL $WJ $CL $QU $CP $EX $IS $SY $BK $CR $LF $NL $ZW {eof}]; +^$CM+ [\p{Pf} & $QU] $CM* [$SP $GL $WJ $CL $QU $CP $EX $IS $SY $BK $CR $LF $NL $ZW {eof}]; + +# Messy interaction: manually chain between LB 15b and LB 15a on Pf Pi. +$LB8NonBreaks [\p{Pf} & $QU] $CM* ([\p{Pi} & $QU] $CM* $SP*)+ .; +$LB8NonBreaks [\p{Pf} & $QU] $CM* ([\p{Pi} & $QU] $CM* $SP*)+ $SP $CM+ $AL_FOLLOW?; +$CAN_CM $CM* [\p{Pf} & $QU] $CM* ([\p{Pi} & $QU] $CM* $SP*)+ .; +$CAN_CM $CM* [\p{Pf} & $QU] $CM* ([\p{Pi} & $QU] $CM* $SP*)+ $SP $CM+ $AL_FOLLOW?; +^$CM+ [\p{Pf} & $QU] $CM* ([\p{Pi} & $QU] $CM* $SP*)+ .; +^$CM+ [\p{Pf} & $QU] $CM* ([\p{Pi} & $QU] $CM* $SP*)+ $SP $CM+ $AL_FOLLOW?; + + +# LB 15c Force a break before start of a number with a leading decimal pt, e.g. " .23" +# Note: would be simpler to express as "$SP / $IS $CM* $NU;", but ICU rules have limitations. +# See issue ICU-20303 + + +$CanFollowIS = [$BK $CR $LF $NL $SP $ZW $WJ $GL $CL $CP $EX $IS $SY $QU $BA $HY $NS $ALPlus $HL $IN]; +$SP $IS / [^ $CanFollowIS $NU $CM]; +$SP $IS $CM* $CMX / [^ $CanFollowIS $NU $CM]; + +# +# LB 15d Do not break before numeric separators (IS), even after spaces. + +[$LB8NonBreaks - $SP] $IS; +$SP $IS $CM* [$CanFollowIS {eof}]; +$SP $IS $CM* $ZWJ [^$CM $NU]; + +$CAN_CM $CM* $IS; +^$CM+ $IS; # by rule 10, stand-alone CM behaves as AL + # LB 16 -$CLcm $SP* $NScm; +($CL | $CP) $CM* $SP* $NS; # LB 17 -$B2cm $SP* $B2cm; +$B2 $CM* $SP* $B2; # # LB 18 Break after spaces. @@ -301,347 +275,115 @@ # LB 19 # x QU -$LB18NonBreaks $CM* $QUcm; -$CM+ $QUcm; +$LB18NonBreaks $CM* $QU; +^$CM+ $QU; # QU x -$QUcm .?; -$QUcm $LB18NonBreaks $CM*; # Don't let a combining mark go onto $CR, $BK, etc. - # TODO: I don't think this rule is needed. - +$QU $CM* .; # LB 20 # $CB # $CB - +# $LB20NonBreaks = [$LB18NonBreaks - $CB]; +# LB 20.09 Don't break between Hyphens and Letters when there is a break preceding the hyphen. +# Originally added as a Finnish tailoring, now promoted to default ICU behavior. +# Note: this is not default UAX-14 behaviour. See issue ICU-8151. +# +^($HY | $HH) $CM* $ALPlus; + # LB 21 x (BA | HY | NS) # BB x # -$LB20NonBreaks $CM* ($BAcm | $HYcm | $NScm); +$LB20NonBreaks $CM* ($BA | $HY | $NS); -$BBcm [^$CB]; # $BB x -$BBcm $LB20NonBreaks $CM*; + +^$CM+ ($BA | $HY | $NS); + +$BB $CM* [^$CB]; # $BB x +$BB $CM* $LB20NonBreaks; # LB 21a Don't break after Hebrew + Hyphen # HL (HY | BA) x -# -$HLcm ($HYcm | $BAcm) [^$CB]?; +# +$HL $CM* ($HY | $BA) $CM* [^$CB]?; -# LB 22 -($ALcm | $HLcm) $INcm; -$CM+ $INcm; # by rule 10, any otherwise unattached CM behaves as AL -$IDcm $INcm; -$INcm $INcm; -$NUcm $INcm; +# LB 21b (forward) Don't break between SY and HL +# (break between HL and SY already disallowed by LB 13 above) +$SY $CM* $HL; + +# LB 22 Do not break before ellipses +# +$LB20NonBreaks $CM* $IN; +^$CM+ $IN; -# $LB 23 -$IDcm $POcm; -$ALcm $NUcm; # includes $LB19 -$HLcm $NUcm; -$CM+ $NUcm; # Rule 10, any otherwise unattached CM behaves as AL -$NUcm $ALcm; -$NUcm $HLcm; +# LB 23 +# +($ALPlus | $HL) $CM* $NU; +^$CM+ $NU; # Rule 10, any otherwise unattached CM behaves as AL +$NU $CM* ($ALPlus | $HL); + +# LB 23a +# +$PR $CM* ($ID | $EB | $EM); +($ID | $EB | $EM) $CM* $PO; + # # LB 24 # -$PRcm $IDcm; -$ALcm $PRcm; -$PRcm ($ALcm | $HLcm); -$POcm ($ALcm | $HLcm); +($PR | $PO) $CM* ($ALPlus | $HL); +($ALPlus | $HL) $CM* ($PR | $PO); +^$CM+ ($PR | $PO); # Rule 10, any otherwise unattached CM behaves as AL # # LB 25 Numbers. # -($PRcm | $POcm)? ($OPcm)? $NUcm ($NUcm | $SYcm | $IScm)* $CLcm? ($PRcm | $POcm)?; +(($PR | $PO) $CM*)? (($OP | $HY) $CM*)? ($IS $CM*)? $NU ($CM* ($NU | $SY | $IS))* + ($CM* ($CL | $CP))? ($CM* ($PR | $PO))?; # LB 26 Do not break a Korean syllable # -$JLcm ($JLcm | $JVcm | $H2cm | $H3cm); -($JVcm | $H2cm) ($JVcm | $JTcm); -($JTcm | $H3cm) $JTcm; +$JL $CM* ($JL | $JV | $H2 | $H3); +($JV | $H2) $CM* ($JV | $JT); +($JT | $H3) $CM* $JT; # LB 27 Treat korean Syllable Block the same as ID (don't break it) -($JLcm | $JVcm | $JTcm | $H2cm | $H3cm) $INcm; -($JLcm | $JVcm | $JTcm | $H2cm | $H3cm) $POcm; -$PRcm ($JLcm | $JVcm | $JTcm | $H2cm | $H3cm); +($JL | $JV | $JT | $H2 | $H3) $CM* $PO; +$PR $CM* ($JL | $JV | $JT | $H2 | $H3); # LB 28 Do not break between alphabetics # -($ALcm | $HLcm) ($ALcm | $HLcm); -$CM+ ($ALcm | $HLcm); # The $CM+ is from rule 10, an unattached CM is treated as AL +($ALPlus | $HL) $CM* ($ALPlus | $HL); +^$CM+ ($ALPlus | $HL); # The $CM+ is from rule 10, an unattached CM is treated as AL + +#LB 28a Do not break Orthographic syllables +($AP $CM*)? ($AS | $AK | [โ—Œ] ) ($CM* $VI $CM* ($AK | [โ—Œ] ))* ($CM* $VI | (($CM* ($AS | $AK | [โ—Œ] ) )? $CM* $VF))?; # LB 29 -$IScm ($ALcm | $NUcm); - -# -# Rule 30 Do not break between letters, numbers or ordinary symbols -# and opening or closing punctuation -# -($ALcm | $HLcm | $NUcm) $OPcm; -$CM+ $OPcm; -$CLcm ($ALcm | $HLcm | $NUcm); - -# -# Reverse Rules. -# -## ------------------------------------------------- - -!!reverse; - -$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+; - - -# -# Sequences of the form (shown forwards) -# [CANT_CM] [CM] [whatever] -# The CM needs to behave as an AL -# -$AL_FOLLOW $CM+ / ( - [$BK $CR $LF $NL $ZW {eof}] | - $SP+ $CM+ $SP | - $SP+ $CM* ([^$OP $CM $SP] | [$AL {eof}])); # if LB 14 will match, need to suppress this break. - # LB14 says OP SP* x . - # becomes OP SP* x AL - # becomes OP SP* x CM+ AL_FOLLOW - # - # Further note: the $AL in [$AL {eof}] is only to work around - # a rule compiler bug which complains about - # empty sets otherwise. - -# -# Sequences of the form (shown forwards) -# [CANT_CM] [CM] [PR] -# The CM needs to behave as an AL -# This rule is concerned about getting the second of the two in place. -# - -[$PR ] / $CM+ [$BK $CR $LF $NL $ZW $SP {eof}]; - - - -# LB 4, 5, 5 - -$LB4Breaks [$LB4NonBreaks-$CM]; -$LB4Breaks $CM+ $CAN_CM; -$LF $CR; - - -# LB 7 x SP -# x ZW -[$SP $ZW] [$LB4NonBreaks-$CM]; -[$SP $ZW] $CM+ $CAN_CM; - -# LB 8 Break after zero width space - - -# LB 9,10 Combining marks. -# 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+ $CAN_CM; - - -# LB 11 -$CM* $WJ $CM* $CAN_CM; -$CM* $WJ [$LB8NonBreaks-$CM]; - - $CANT_CM $CM* $WJ; -$CM* $CAN_CM $CM* $WJ; - -# LB 12 -# x GL -# -$CM* $GL $CM* [$LB8NonBreaks-$CM-$SP]; - -# -# GL x -# -$CANT_CM $CM* $GL; -$CM* $CAN_CM $CM* $GL; - - -# LB 13 -$CL $CM+ $CAN_CM; -$EX $CM+ $CAN_CM; -$IS $CM+ $CAN_CM; -$SY $CM+ $CAN_CM; - -$CL [$LB8NonBreaks-$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) -# 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* $OP; - -# LB 14 OP SP* x -# -$CM* $CAN_CM $SP* $CM* $OP; - $CANT_CM $SP* $CM* $OP; -$AL_FOLLOW? $CM+ $SP $SP* $CM* $OP; # by LB 10, behaves like $AL_FOLLOW? $AL $SP* $CM* $OP - - $AL_FOLLOW_NOCM $CM+ $SP+ $CM* $OP; -$CM* $AL_FOLLOW_CM $CM+ $SP+ $CM* $OP; -$SY $CM $SP+ $OP; # TODO: Experiment. Remove. - - - -# LB 15 -# $CM* $OP $SP* $CM* $QU; - -# LB 16 -$CM* $NS $SP* $CM* $CL; - -# LB 17 -$CM* $B2 $SP* $CM* $B2; - -# LB 18 break after spaces -# Nothing explicit needed here. - - -# -# LB 19 -# -$CM* $QU $CM* $CAN_CM; # . x QU -$CM* $QU $LB18NonBreaks; - - -$CM* $CAN_CM $CM* $QU; # QU x . - $CANT_CM $CM* $QU; - -# -# LB 20 Break before and after CB. -# nothing needed here. -# - -# LB 21 -$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 | $HL); -$CM* $IN $CM* $ID; -$CM* $IN $CM* $IN; -$CM* $IN $CM* $NU; - -# LB 23 -$CM* $PO $CM* $ID; -$CM* $NU $CM* ($ALPlus | $HL); -$CM* ($ALPlus | $HL) $CM* $NU; - -# LB 24 -$CM* $ID $CM* $PR; -$CM* $PR $CM* $ALPlus; -$CM* ($ALPlus | $HL) $CM* $PR; -$CM* ($ALPlus | $HL) $CM* $PO; - -$CM* $ALPlus $CM* ($IS | $SY | $HY)+ / $SP; -$CM* $NU+ $CM* $HY+ / $SP; - -# LB 25 -($CM* ($PR | $PO))? ($CM* $CL)? ($CM* ($NU | $IS | $SY))* $CM* $NU ($CM* ($OP))? ($CM* ($PR | $PO))?; - -# LB 26 -$CM* ($H3 | $H2 | $JV | $JL) $CM* $JL; -$CM* ($JT | $JV) $CM* ($H2 | $JV); -$CM* $JT $CM* ($H3 | $JT); - -# LB 27 -$CM* $IN $CM* ($H3 | $H2 | $JT | $JV | $JL); -$CM* $PO $CM* ($H3 | $H2 | $JT | $JV | $JL); -$CM* ($H3 | $H2 | $JT | $JV | $JL) $CM* $PR; - -# LB 28 -$CM* ($ALPlus | $HL) $CM* ($ALPlus | $HL); - -# LB 29 -$CM* ($NU | $ALPlus) $CM* $IS+ [^$SP]; +$IS $CM* ($ALPlus | $HL); # LB 30 -$CM* $OP $CM* ($ALPlus | $HL | $NU); -$CM* ($ALPlus | $HL | $NU) $CM* ($CL | $SY)+ [^$SP]; +($ALPlus | $HL | $NU) $CM* $OP30; +^$CM+ $OP30; # The $CM+ is from rule 10, an unattached CM is treated as AL. +$CP30 $CM* ($ALPlus | $HL | $NU); +# LB 30a Do not break between regional indicators. Break after pairs of them. +# Tricky interaction with LB8a: ZWJ x . together with ZWJ acting like a CM. +$RI $CM* $RI / [[^$BK $CR $LF $NL $SP $ZW $WJ $CL $CP $EX $IS $SY $GL $QU $BA $HY $NS $IN $CM]]; +$RI $CM* $RI $CM* [$CM-$ZWJ] / [[^$BK $CR $LF $NL $SP $ZW $WJ $CL $CP $EX $IS $SY $GL $QU $BA $HY $NS $IN $CM]]; +$RI $CM* $RI $CM* [$BK $CR $LF $NL $SP $ZW $WJ $CL $CP $EX $IS $SY $GL $QU $BA $HY $NS $IN $ZWJ {eof}]; +# note: the preceding rule includes {eof} rather than having the last [set] term qualified with '?' +# because of the chain-out behavior difference. The rule must chain out only from the [set characters], +# not from the preceding $RI or $CM, which it would be able to do if the set were optional. -## ------------------------------------------------- +# LB30b Do not break between an emoji base (or potential emoji) and an emoji modifier. +$EB $CM* $EM; +$ExtPictUnassigned $CM* $EM; -!!safe_reverse; - -# LB 7 -$CM+ [^$CM $BK $CR $LF $NL $ZW $SP]; -$CM+ $SP / .; - -# LB 9 -$SP+ $CM* $OP; - -# LB 10 -$SP+ $CM* $QU; - -# LB 11 -$SP+ $CM* $CL; -$SP+ $CM* $B2; - -# LB 21 -$CM* ($HY | $BA) $CM* $HL; - -# LB 18 -($CM* ($IS | $SY))+ $CM* $NU; -$CL $CM* ($NU | $IS | $SY); - -# For dictionary-based break -$dictionary $dictionary; - -## ------------------------------------------------- - -!!safe_forward; - -# Skip forward over all character classes that are involved in -# rules containing patterns with possibly more than one char -# of context. -# -# It might be slightly more efficient to have specific rules -# instead of one generic one, but only if we could -# turn off rule chaining. We don't want to move more -# than necessary. -# -[$CM $OP $QU $CL $B2 $PR $HY $BA $SP $dictionary]+ [^$CM $OP $QU $CL $B2 $PR $HY $BA $dictionary]; -$dictionary $dictionary; - +# LB 31 Break everywhere else. +# Match a single code point if no other rule applies. +.; diff --git a/i18npool/source/breakiterator/data/sent.txt b/i18npool/source/breakiterator/data/sent.txt index 7fada89..eb1224e 100644 --- a/i18npool/source/breakiterator/data/sent.txt +++ b/i18npool/source/breakiterator/data/sent.txt @@ -1,43 +1,40 @@ +# Copyright (C) 2016 and later: Unicode, Inc. and others. +# License & terms of use: http://www.unicode.org/copyright.html # -# Copyright (C) 2002-2006, International Business Machines Corporation and others. +# Copyright (C) 2002-2015, International Business Machines Corporation and others. # All Rights Reserved. # # file: sent.txt # # ICU Sentence Break Rules # See Unicode Standard Annex #29. -# These rules are based on SA 29 version 5.0.0 -# Includes post 5.0 changes to treat Japanese half width voicing marks -# as Grapheme Extend. +# These rules are based on UAX #29 Revision 34 for Unicode Version 12.0 # - -$VoiceMarks = [\uff9e\uff9f]; -$Thai = [:Script = Thai:]; +!!quoted_literals_only; # # Character categories as defined in TR 29 # +$CR = [\p{Sentence_Break = CR}]; +$LF = [\p{Sentence_Break = LF}]; +$Extend = [\p{Sentence_Break = Extend}]; $Sep = [\p{Sentence_Break = Sep}]; $Format = [\p{Sentence_Break = Format}]; $Sp = [\p{Sentence_Break = Sp}]; $Lower = [\p{Sentence_Break = Lower}]; $Upper = [\p{Sentence_Break = Upper}]; -$OLetter = [\p{Sentence_Break = OLetter}-$VoiceMarks]; +$OLetter = [\p{Sentence_Break = OLetter}]; $Numeric = [\p{Sentence_Break = Numeric}]; $ATerm = [\p{Sentence_Break = ATerm}]; +$SContinue = [\p{Sentence_Break = SContinue}]; $STerm = [\p{Sentence_Break = STerm}]; $Close = [\p{Sentence_Break = Close}]; # # Define extended forms of the character classes, -# incorporate grapheme cluster + format chars. -# Rules 4 and 5. - - -$CR = \u000d; -$LF = \u000a; -$Extend = [[:Grapheme_Extend = TRUE:]$VoiceMarks]; +# incorporate trailing Extend or Format chars. +# Rules 4 and 5. $SpEx = $Sp ($Extend | $Format)*; $LowerEx = $Lower ($Extend | $Format)*; @@ -45,6 +42,7 @@ $OLetterEx = $OLetter ($Extend | $Format)*; $NumericEx = $Numeric ($Extend | $Format)*; $ATermEx = $ATerm ($Extend | $Format)*; +$SContinueEx= $SContinue ($Extend | $Format)*; $STermEx = $STerm ($Extend | $Format)*; $CloseEx = $Close ($Extend | $Format)*; @@ -52,77 +50,34 @@ ## ------------------------------------------------- !!chain; -!!forward; # Rule 3 - break after separators. Keep CR/LF together. # $CR $LF; -$LettersEx = [$OLetter $Upper $Lower $Numeric $Close $STerm] ($Extend | $Format)*; -$LettersEx* $Thai $LettersEx* ($ATermEx | $SpEx)*; # Rule 4 - Break after $Sep. # Rule 5 - Ignore $Format and $Extend # -[^$Sep]? ($Extend | $Format)*; +[^$Sep $CR $LF]? ($Extend | $Format)*; # Rule 6 $ATermEx $NumericEx; # Rule 7 -$UpperEx $ATermEx $UpperEx; +($UpperEx | $LowerEx) $ATermEx $UpperEx; #Rule 8 -# Note: follows errata for Unicode 5.0 boundary rules. -$NotLettersEx = [^$OLetter $Upper $Lower $Sep $ATerm $STerm] ($Extend | $Format)*; +$NotLettersEx = [^$OLetter $Upper $Lower $Sep $CR $LF $ATerm $STerm] ($Extend | $Format)*; $ATermEx $CloseEx* $SpEx* $NotLettersEx* $Lower; # Rule 8a -($STermEx | $ATermEx) $CloseEx* $SpEx* ($STermEx | $ATermEx); +($STermEx | $ATermEx) $CloseEx* $SpEx* ($SContinueEx | $STermEx | $ATermEx); #Rule 9, 10, 11 -($STermEx | $ATermEx) $CloseEx* $SpEx* $Sep?; +($STermEx | $ATermEx) $CloseEx* $SpEx* ($Sep | $CR | $LF)?; -#Rule 12 -[[^$STerm $ATerm $Close $Sp $Sep $Format $Extend $Thai]{bof}] ($Extend | $Format | $Close | $Sp)* [^$Thai]; -[[^$STerm $ATerm $Close $Sp $Sep $Format $Extend]{bof}] ($Extend | $Format | $Close | $Sp)* ([$Sep{eof}] | $CR $LF){100}; - -## ------------------------------------------------- - -!!reverse; - -$SpEx_R = ($Extend | $Format)* $Sp; -$ATermEx_R = ($Extend | $Format)* $ATerm; -$STermEx_R = ($Extend | $Format)* $STerm; -$CloseEx_R = ($Extend | $Format)* $Close; - -# -# Reverse rules. -# For now, use the old style inexact reverse rules, which are easier -# to write, but less efficient. -# TODO: exact reverse rules. It appears that exact reverse rules -# may require improving support for look-ahead breaks in the -# builder. Needs more investigation. -# - -[{bof}] (.? | $LF $CR) [^$Sep]* [$Sep {eof}] ($SpEx_R* $CloseEx_R* ($STermEx_R | $ATermEx_R))*; -#.*; - -# Explanation for this rule: -# -# It needs to back over -# The $Sep at which we probably begin -# All of the non $Sep chars leading to the preceding $Sep -# The preceding $Sep, which will be the second one that the rule matches. -# Any immediately preceding STerm or ATerm sequences. We need to see these -# to get the correct rule status when moving forwards again. -# -# [{bof}] inhibit rule chaining. Without this, rule would loop on itself and match -# the entire string. -# -# (.? | $LF $CR) Match one $Sep instance. Use .? rather than $Sep because position might be -# at the beginning of the string at this point, and we don't want to fail. -# Can only use {eof} once, and it is used later. -# - +#Rule 998 +[[^$STerm $ATerm $Close $Sp $Sep $LF $CR $Format $Extend]{bof}] ($Extend | $Format | $Close | $Sp)* .; +[[^$STerm $ATerm $Close $Sp $Sep $LF $CR $Format $Extend]{bof}] ($Extend | $Format | $Close | $Sp)* ([$Sep $LF $CR {eof}] | $CR $LF){100}; diff --git a/include/svx/strings.hrc b/include/svx/strings.hrc index 8dc2aa0..b294bdf 100644 --- a/include/svx/strings.hrc +++ b/include/svx/strings.hrc @@ -1800,6 +1800,7 @@ #define RID_SUBSETSTR_KAKTOVIK_NUMERALS NC_("RID_SUBSETMAP", "Kaktovik Numerals") #define RID_SUBSETSTR_KAWI NC_("RID_SUBSETMAP", "Kawi") #define RID_SUBSETSTR_NAG_MUNDARI NC_("RID_SUBSETMAP", "Nag Mundari") +#define RID_SUBSETSTR_CJK_UNIFIED_IDEOGRAPHS_EXTENSION_I NC_("RID_SUBSETMAP", "CJK Unified Ideographs Extension I") #define RID_SVXSTR_FRAMEDIR_LTR NC_("RID_SVXSTR_FRAMEDIR_LTR", "Left-to-right (LTR)") #define RID_SVXSTR_FRAMEDIR_RTL NC_("RID_SVXSTR_FRAMEDIR_RTL", "Right-to-left (RTL)") diff --git a/svx/source/dialog/charmap.cxx b/svx/source/dialog/charmap.cxx index dcb1205..a5c84a7 100644 --- a/svx/source/dialog/charmap.cxx +++ b/svx/source/dialog/charmap.cxx @@ -1924,6 +1924,11 @@ aAllSubsets.emplace_back( 0x1E4D0, 0x1E4FF, SvxResId(RID_SUBSETSTR_NAG_MUNDARI) ); break; #endif +#if (U_ICU_VERSION_MAJOR_NUM >= 74) + case UBLOCK_CJK_UNIFIED_IDEOGRAPHS_EXTENSION_I: + aAllSubsets.emplace_back( 0x2EBF0, 0x2EE5F, SvxResId(RID_SUBSETSTR_CJK_UNIFIED_IDEOGRAPHS_EXTENSION_I) ); + break; +#endif } #if OSL_DEBUG_LEVEL > 0 && !defined NDEBUG