1<?xml version="1.0" encoding="UTF-8" ?> 2<!DOCTYPE ldml SYSTEM "../../common/dtd/ldml.dtd"> 3<!-- 4Copyright © 1991-2024 Unicode, Inc. 5CLDR data files are interpreted according to the LDML specification (https://unicode.org/reports/tr35/) 6For terms of use and license, see https://www.unicode.org/terms_of_use.html 7--> 8<ldml> 9 <identity> 10 <version number="$Revision: 13690 $"/> 11 <language type="root"/> 12 </identity> 13 <segmentations> 14 <segmentation type="GraphemeClusterBreak"> 15 <variables> 16 <!-- VARIABLES --> 17 <variable id="$CR">\p{Grapheme_Cluster_Break=CR}</variable> 18 <variable id="$LF">\p{Grapheme_Cluster_Break=LF}</variable> 19 <variable id="$Control">\p{Grapheme_Cluster_Break=Control}</variable> 20 <variable id="$Extend">\p{Grapheme_Cluster_Break=Extend}</variable> 21 <variable id="$ZWJ">\p{Grapheme_Cluster_Break=ZWJ}</variable> 22 <variable id="$RI">\p{Grapheme_Cluster_Break=Regional_Indicator}</variable> 23 <variable id="$Prepend">\p{Grapheme_Cluster_Break=Prepend}</variable> 24 <variable id="$SpacingMark">\p{Grapheme_Cluster_Break=SpacingMark}</variable> 25 <variable id="$L">\p{Grapheme_Cluster_Break=L}</variable> 26 <variable id="$V">\p{Grapheme_Cluster_Break=V}</variable> 27 <variable id="$T">\p{Grapheme_Cluster_Break=T}</variable> 28 <variable id="$LV">\p{Grapheme_Cluster_Break=LV}</variable> 29 <variable id="$LVT">\p{Grapheme_Cluster_Break=LVT}</variable> 30 <!-- Note: The following may overlap with the above --> 31 <!-- Note: ConjunctLinkingScripts is not used anymore, instead that list exists in the derivation of Indic_Conjunct_Break. --> 32 <!-- It is kept here so that the diff of the generated test cases compared to the Unicode 15.1 β is minimal. --> 33 <!-- TODO(egg): Consider removing in Unicode 16.0. --> 34 <variable id="$ConjunctLinkingScripts">[\p{Gujr}\p{sc=Telu}\p{sc=Mlym}\p{sc=Orya}\p{sc=Beng}\p{sc=Deva}]</variable> 35 <variable id="$ConjunctLinker">\p{Indic_Conjunct_Break=Linker}</variable> 36 <variable id="$LinkingConsonant">\p{Indic_Conjunct_Break=Consonant}</variable> 37 <variable id="$ExtPict">\p{Extended_Pictographic}</variable> 38 <variable id="$ExtCccZwj">[\p{Indic_Conjunct_Break=Linker}\p{Indic_Conjunct_Break=Extend}]</variable> 39 </variables> 40 <segmentRules> 41 <!-- RULES --> 42 <!-- Break at the start and end of text, unless the text is empty. --> 43 <!-- Do not break between a CR and LF. Otherwise, break before and after controls. --> 44 <rule id="3"> $CR × $LF </rule> 45 <rule id="4"> ( $Control | $CR | $LF ) ÷ </rule> 46 <rule id="5"> ÷ ( $Control | $CR | $LF ) </rule> 47 <!-- Do not break Hangul syllable sequences. --> 48 <rule id="6"> $L × ( $L | $V | $LV | $LVT ) </rule> 49 <rule id="7"> ( $LV | $V ) × ( $V | $T ) </rule> 50 <rule id="8"> ( $LVT | $T) × $T </rule> 51 <rule id="9"> × ($Extend | $ZWJ) </rule> 52 <!-- Only for extended grapheme clusters: Do not break before SpacingMarks, or after Prepend characters. --> 53 <rule id="9.1"> × $SpacingMark </rule> 54 <rule id="9.2"> $Prepend × </rule> 55 <rule id="9.3"> $LinkingConsonant $ExtCccZwj* $ConjunctLinker $ExtCccZwj* × $LinkingConsonant </rule> 56 <rule id="11"> $ExtPict $Extend* $ZWJ × $ExtPict </rule> 57 <!-- Do not break within emoji flag sequences. That is, do not break between regional indicator (RI) symbols if there is an odd number of RI characters before the break point. --> 58 <rule id="12"> ^ ($RI $RI)* $RI × $RI </rule> 59 <rule id="13"> [^$RI] ($RI $RI)* $RI × $RI </rule> 60 <!-- Otherwise, break everywhere. --> 61 </segmentRules> 62 </segmentation> 63 <segmentation type="LineBreak"> 64 <variables> 65 <!-- VARIABLES --> 66 <variable id="$AI">\p{Line_Break=Ambiguous}</variable> 67 <variable id="$AK">\p{Line_Break=Aksara}</variable> 68 <variable id="$AL">\p{Line_Break=Alphabetic}</variable> 69 <variable id="$AP">\p{Line_Break=Aksara_Prebase}</variable> 70 <variable id="$AS">\p{Line_Break=Aksara_Start}</variable> 71 <variable id="$B2">\p{Line_Break=Break_Both}</variable> 72 <variable id="$BA">\p{Line_Break=Break_After}</variable> 73 <variable id="$BB">\p{Line_Break=Break_Before}</variable> 74 <variable id="$BK">\p{Line_Break=Mandatory_Break}</variable> 75 <variable id="$CB">\p{Line_Break=Contingent_Break}</variable> 76 <variable id="$CL">\p{Line_Break=Close_Punctuation}</variable> 77 <variable id="$CP">\p{Line_Break=CP}</variable> 78 <variable id="$CM1">\p{Line_Break=Combining_Mark}</variable> 79 <variable id="$CR">\p{Line_Break=Carriage_Return}</variable> 80 <variable id="$EX">\p{Line_Break=Exclamation}</variable> 81 <variable id="$GL">\p{Line_Break=Glue}</variable> 82 <variable id="$H2">\p{Line_Break=H2}</variable> 83 <variable id="$H3">\p{Line_Break=H3}</variable> 84 <variable id="$HL">\p{Line_Break=HL}</variable> 85 <variable id="$HY">\p{Line_Break=Hyphen}</variable> 86 <variable id="$ID">\p{Line_Break=Ideographic}</variable> 87 <variable id="$IN">\p{Line_Break=Inseparable}</variable> 88 <variable id="$IS">\p{Line_Break=Infix_Numeric}</variable> 89 <variable id="$JL">\p{Line_Break=JL}</variable> 90 <variable id="$JT">\p{Line_Break=JT}</variable> 91 <variable id="$JV">\p{Line_Break=JV}</variable> 92 <variable id="$LF">\p{Line_Break=Line_Feed}</variable> 93 <variable id="$NL">\p{Line_Break=Next_Line}</variable> 94 <variable id="$NS">\p{Line_Break=Nonstarter}</variable> 95 <variable id="$NU">\p{Line_Break=Numeric}</variable> 96 <variable id="$OP">\p{Line_Break=Open_Punctuation}</variable> 97 <variable id="$PO">\p{Line_Break=Postfix_Numeric}</variable> 98 <variable id="$PR">\p{Line_Break=Prefix_Numeric}</variable> 99 <variable id="$QU">\p{Line_Break=Quotation}</variable> 100 <variable id="$SA">\p{Line_Break=Complex_Context}</variable> 101 <variable id="$SG">\p{Line_Break=Surrogate}</variable> 102 <variable id="$SP">\p{Line_Break=Space}</variable> 103 <variable id="$SY">\p{Line_Break=Break_Symbols}</variable> 104 <variable id="$VF">\p{Line_Break=Virama_Final}</variable> 105 <variable id="$VI">\p{Line_Break=Virama}</variable> 106 <variable id="$WJ">\p{Line_Break=Word_Joiner}</variable> 107 <variable id="$XX">\p{Line_Break=Unknown}</variable> 108 <variable id="$ZW">\p{Line_Break=ZWSpace}</variable> 109 <variable id="$CJ">\p{Line_Break=Conditional_Japanese_Starter}</variable> 110 <variable id="$RI">\p{Line_Break=Regional_Indicator}</variable> 111 <variable id="$EB">\p{Line_Break=E_Base}</variable> 112 <variable id="$EM">\p{Line_Break=E_Modifier}</variable> 113 <variable id="$ZWJ_O">\p{Line_Break=ZWJ}</variable> 114 <variable id="$ZWJ">\p{Line_Break=ZWJ}</variable> 115 <variable id="$QU_Pi">[$QU & \p{gc=Pi}]</variable> 116 <variable id="$QU_Pf">[$QU & \p{gc=Pf}]</variable> 117 <variable id="$QUmPi">[$QU - \p{gc=Pi}]</variable> 118 <variable id="$QUmPf">[$QU - \p{gc=Pf}]</variable> 119 <variable id="$NotEastAsian">[^\p{ea=F}\p{ea=W}\p{ea=H}]</variable> 120 <variable id="$NonEastAsianBA">[$BA & $NotEastAsian]</variable> 121 <variable id="$DottedCircle">◌</variable> 122 <variable id="$Hyphen">[\u2010]</variable> 123 <variable id="$CP30">[$CP-[\p{ea=F}\p{ea=W}\p{ea=H}]]</variable> 124 <variable id="$OP30">[$OP-[\p{ea=F}\p{ea=W}\p{ea=H}]]</variable> 125 <variable id="$ExtPictUnassigned">[\p{Extended_Pictographic}&\p{gc=Cn}]</variable> 126 <!-- Some rules refer to the start and end of text. We could just use a literal ^ for sot, but naming --> 127 <!-- it as in the spec makes it easier to compare. The parser will eat (and choke on) $, so we play a --> 128 <!-- stupid trick instead. --> 129 <variable id="$sot">^</variable> 130 <variable id="$eot">(?!.)</variable> 131 <!-- SPECIAL EXTENSIONS --> 132 <variable id="$CM">[$CM1 $ZWJ]</variable> 133 <!-- LB 1 Assign a line breaking class to each code point of the input. --> 134 <!-- Resolve AI, CB, SA, SG, and XX into other line breaking classes depending on criteria outside the scope of this algorithm. --> 135 <!-- NOTE: CB is ok to fall through, but must handle others here. --> 136 <variable id="$AL">[$AI $AL $SG $XX $SA]</variable> 137 <variable id="$NS">[$NS $CJ]</variable> 138 <!-- WARNING: Fixes for Rule 9 --> 139 <!-- Treat X (CM|ZWJ* as if it were X. --> 140 <!-- Where X is any line break class except SP, BK, CR, LF, NL or ZW. --> 141 <variable id="$X">$CM*</variable> 142 <!-- MACROS --> 143 <variable id="$Spec1_">[$SP $BK $CR $LF $NL $ZW]</variable> 144 <variable id="$Spec2_">[^ $SP $BK $CR $LF $NL $ZW]</variable> 145 <variable id="$Spec3a_">[^ $SP $BA $HY $CM]</variable> 146 <variable id="$Spec3b_">[^ $BA $HY $CM]</variable> 147 <variable id="$Spec4_">[^ $NU $CM]</variable> 148 <variable id="$AI">($AI $X)</variable> 149 <variable id="$AK">($AK $X)</variable> 150 <variable id="$AL">($AL $X)</variable> 151 <variable id="$AP">($AP $X)</variable> 152 <variable id="$AS">($AS $X)</variable> 153 <variable id="$B2">($B2 $X)</variable> 154 <variable id="$BA">($BA $X)</variable> 155 <variable id="$BB">($BB $X)</variable> 156 <variable id="$CB">($CB $X)</variable> 157 <variable id="$CL">($CL $X)</variable> 158 <variable id="$CP">($CP $X)</variable> 159 <variable id="$CM">($CM $X)</variable> 160 <variable id="$EX">($EX $X)</variable> 161 <variable id="$GL">($GL $X)</variable> 162 <variable id="$H2">($H2 $X)</variable> 163 <variable id="$H3">($H3 $X)</variable> 164 <variable id="$HL">($HL $X)</variable> 165 <variable id="$HY">($HY $X)</variable> 166 <variable id="$ID">($ID $X)</variable> 167 <variable id="$IN">($IN $X)</variable> 168 <variable id="$IS">($IS $X)</variable> 169 <variable id="$JL">($JL $X)</variable> 170 <variable id="$JT">($JT $X)</variable> 171 <variable id="$JV">($JV $X)</variable> 172 <variable id="$NS">($NS $X)</variable> 173 <variable id="$NU">($NU $X)</variable> 174 <variable id="$OP">($OP $X)</variable> 175 <variable id="$PO">($PO $X)</variable> 176 <variable id="$PR">($PR $X)</variable> 177 <variable id="$QU">($QU $X)</variable> 178 <variable id="$SA">($SA $X)</variable> 179 <variable id="$SG">($SG $X)</variable> 180 <variable id="$SY">($SY $X)</variable> 181 <variable id="$VF">($VF $X)</variable> 182 <variable id="$VI">($VI $X)</variable> 183 <variable id="$WJ">($WJ $X)</variable> 184 <variable id="$XX">($XX $X)</variable> 185 <variable id="$RI">($RI $X)</variable> 186 <variable id="$EB">($EB $X)</variable> 187 <variable id="$EM">($EM $X)</variable> 188 <variable id="$ZWJ">($ZWJ $X)</variable> 189 <variable id="$QU_Pi">($QU_Pi $X)</variable> 190 <variable id="$QU_Pf">($QU_Pf $X)</variable> 191 <variable id="$QUmPi">($QUmPi $X)</variable> 192 <variable id="$QUmPf">($QUmPf $X)</variable> 193 <variable id="$NotEastAsian">( $NotEastAsian | [$NotEastAsian - $Spec1_] $X)</variable> 194 <variable id="$NonEastAsianBA">(NonEastAsianBA $X)</variable> 195 <variable id="$DottedCircle">($DottedCircle $X)</variable> 196 <variable id="$Hyphen">($Hyphen $X)</variable> 197 <variable id="$CP30">($CP30 $X)</variable> 198 <variable id="$OP30">($OP30 $X)</variable> 199 <!-- OUT OF ORDER ON PURPOSE --> 200 <!-- LB 10 Treat any remaining combining mark as AL and non-$EastAsian. --> 201 <variable id="$AL">($AL | ^ $CM | (?<=$Spec1_) $CM)</variable> 202 <variable id="$NotEastAsian">( $NotEastAsian | ^ $CM | (?<=$Spec1_) $CM )</variable> 203 </variables> 204 <segmentRules> 205 <!-- RULES --> 206 <!-- LB 4 Always break after hard line breaks (but never between CR and LF). --> 207 <rule id="4"> $BK ÷ </rule> 208 <!-- LB 5 Treat CR followed by LF, as well as CR, LF and NL as hard line breaks. --> 209 <rule id="5.01"> $CR × $LF </rule> 210 <rule id="5.02"> $CR ÷ </rule> 211 <rule id="5.03"> $LF ÷ </rule> 212 <rule id="5.04"> $NL ÷ </rule> 213 <!-- LB 6 Do not break before hard line breaks. --> 214 <rule id="6"> × ( $BK | $CR | $LF | $NL ) </rule> 215 <!-- LB 7 Do not break before spaces or zero-width space. --> 216 <rule id="7.01"> × $SP </rule> 217 <rule id="7.02"> × $ZW </rule> 218 <!-- LB 8 Break before any character following a zero-width space, even if one or more spaces intervene. --> 219 <rule id="8"> $ZW $SP* ÷ </rule> 220 <!-- LB 8a Don't break between ZWJ and IDs (for use in Emoji ZWJ sequences) --> 221 <rule id="8.1"> $ZWJ_O × </rule> 222 <!-- LB 9 Do not break a combining character sequence; treat it as if it has the LB class of the base character --> 223 <!-- in all of the following rules. (Where X is any line break class except SP, BK, CR, LF, NL or ZW.) --> 224 <rule id="9"> $Spec2_ × $CM </rule> 225 <rule id="11.01"> × $WJ </rule> 226 <rule id="11.02"> $WJ × </rule> 227 <!-- LB 12 Do not break after NBSP and related characters. --> 228 <rule id="12"> $GL × </rule> 229 <rule id="12.1"> $Spec3a_ × $GL </rule> 230 <rule id="12.2"> $Spec3b_ $CM+ × $GL </rule> 231 <rule id="12.3"> ^ $CM+ × $GL </rule> 232 <!-- LB 13 Do not break before \u2018]\u2019 or \u2018!\u2019 or \u2018;\u2019 or \u2018/\u2019, even after spaces. --> 233 <rule id="13.01"> × $EX </rule> 234 <rule id="13.02"> × $CL </rule> 235 <rule id="13.03"> × $CP </rule> 236 <rule id="13.04"> × $SY </rule> 237 <!-- LB 14 Do not break after \u2018[\u2019, even after spaces. --> 238 <rule id="14"> $OP $SP* × </rule> 239 <!-- LB 15a Do not break after an unresolved initial punctuation that lies at the start of the line, --> 240 <!-- after a space, after opening punctuation, or after an unresolved quotation mark, even after --> 241 <!-- spaces. --> 242 <rule id="15.11"> ( $sot | $BK | $CR | $LF | $NL | $OP | $QU | $GL | $SP | $ZW ) $QU_Pi $SP* × </rule> 243 <!-- LB 15b Do not break before an unresolved final punctuation that lies at the end of the line, before --> 244 <!-- a space, before a prohibited break, or before an unresolved quotation mark, even before spaces. --> 245 <rule id="15.21"> × $QU_Pf ( $SP | $GL | $WJ | $CL | $QU | $CP | $EX | $IS | $SY | $BK | $CR | $LF | $NL | $ZW | $eot ) </rule> 246 <!-- LB 15c Break before numbers starting with a decimal mark. --> 247 <rule id="15.3"> $SP ÷ $IS $NU </rule> 248 <!-- LB 15d Otherwise, do not break before commas or full stops. --> 249 <rule id="15.4"> × $IS </rule> 250 <!-- LB 16 Do not break between closing punctuation and a nonstarter (lb=NS), even with intervening spaces. --> 251 <rule id="16"> ($CL | $CP) $SP* × $NS </rule> 252 <!-- LB 17 Do not break within \u2018\u2014\u2014\u2019, even with intervening spaces. --> 253 <rule id="17"> $B2 $SP* × $B2 </rule> 254 <!-- LB 18 Break after spaces. --> 255 <rule id="18"> $SP ÷ </rule> 256 <!-- LB 19 Do not break before or after \u2018\"\u2019. --> 257 <rule id="19.01"> × $QUmPi </rule> 258 <rule id="19.02"> $QUmPf × </rule> 259 <!-- LB 19a Unless surrounded by East Asian Characters, do not break either side of any unresolved quotation marks. --> 260 <rule id="19.1"> $NotEastAsian × $QU </rule> 261 <rule id="19.11"> × $QU ( $NotEastAsian | $eot ) </rule> 262 <rule id="19.12"> $QU × $NotEastAsian </rule> 263 <rule id="19.13"> ( $sot | $NotEastAsian ) $QU × </rule> 264 <!-- LB 20 Break before and after unresolved CB. --> 265 <rule id="20.01"> ÷ $CB </rule> 266 <rule id="20.02"> $CB ÷ </rule> 267 <!-- LB 20a Do not break after a hyphen that follows break opportunity, a space, or the start of text. --> 268 <rule id="20.1"> ( $sot | $BK | $CR | $LF | $NL | $SP | $ZW | $CB | $GL ) ( $HY | $Hyphen ) × $AL </rule> 269 <!-- LB 21 Do not break before hyphen-minus, other hyphens, fixed-width spaces, small kana and other non-starters, or after acute accents. --> 270 <rule id="21.01"> × $BA </rule> 271 <rule id="21.02"> × $HY </rule> 272 <rule id="21.03"> × $NS </rule> 273 <rule id="21.04"> $BB × </rule> 274 <!-- LB 21a Do not break after the hyphen in Hebrew-hyphen-non-Hebrew. --> 275 <rule id="21.1"> $HL ($HY | $NonEastAsianBA) × [^$HL] </rule> 276 <!-- LB 21b Don’t break between Solidus and Hebrew letters. --> 277 <rule id="21.2"> $SY × $HL </rule> 278 <!-- LB 22 Do not break before ellipses. --> 279 <rule id="22"> × $IN </rule> 280 <!-- LB 23 Do not break between digits and letters. --> 281 <rule id="23.02"> ($AL | $HL) × $NU </rule> 282 <rule id="23.03"> $NU × ($AL | $HL) </rule> 283 <!-- LB 24 Do not break between prefix and letters or ideographs. --> 284 <rule id="23.12"> $PR × ($ID | $EB | $EM) </rule> 285 <rule id="23.13"> ($ID | $EB | $EM) × $PO </rule> 286 <!-- LB24 Do not break between numeric prefix/postfix and letters, or between letters and prefix/postfix. --> 287 <rule id="24.02"> ($PR | $PO) × ($AL | $HL) </rule> 288 <rule id="24.03"> ($AL | $HL) × ($PR | $PO) </rule> 289 <!-- LB 25 Do not break numbers. --> 290 <rule id="25.01"> $NU ( $SY | $IS )* $CL × $PO </rule> 291 <rule id="25.02"> $NU ( $SY | $IS )* $CP × $PO </rule> 292 <rule id="25.03"> $NU ( $SY | $IS )* $CL × $PR </rule> 293 <rule id="25.04"> $NU ( $SY | $IS )* $CP × $PR </rule> 294 <rule id="25.05"> $NU ( $SY | $IS )* × $PO </rule> 295 <rule id="25.06"> $NU ( $SY | $IS )* × $PR </rule> 296 <rule id="25.07"> $PO × $OP $NU </rule> 297 <rule id="25.08"> $PO × $OP $IS $NU </rule> 298 <rule id="25.09"> $PO × $NU </rule> 299 <rule id="25.1"> $PR × $OP $NU </rule> 300 <rule id="25.11"> $PR × $OP $IS $NU </rule> 301 <rule id="25.12"> $PR × $NU </rule> 302 <rule id="25.13"> $HY × $NU </rule> 303 <rule id="25.14"> $IS × $NU </rule> 304 <rule id="25.15"> $NU ( $SY | $IS )* × $NU </rule> 305 <!-- LB 26 Do not break a Korean syllable. --> 306 <rule id="26.01"> $JL × $JL | $JV | $H2 | $H3 </rule> 307 <rule id="26.02"> $JV | $H2 × $JV | $JT </rule> 308 <rule id="26.03"> $JT | $H3 × $JT </rule> 309 <!-- LB 27 Treat a Korean Syllable Block the same as ID. --> 310 <rule id="27.01"> $JL | $JV | $JT | $H2 | $H3 × $PO </rule> 311 <rule id="27.02"> $PR × $JL | $JV | $JT | $H2 | $H3 </rule> 312 <!-- LB 28 Do not break between alphabetics (\"at\"). --> 313 <rule id="28"> ($AL | $HL) × ($AL | $HL) </rule> 314 <!-- LB28a Do not break inside the orthographic syllables of Brahmic scripts. --> 315 <rule id="28.11"> $AP × ($AK | $DottedCircle | $AS) </rule> 316 <rule id="28.12"> ($AK | $DottedCircle | $AS) × ($VF | $VI) </rule> 317 <rule id="28.13"> ($AK | $DottedCircle | $AS) $VI × ($AK | $DottedCircle) </rule> 318 <rule id="28.14"> ($AK | $DottedCircle | $AS) × ($AK | $DottedCircle | $AS) $VF </rule> 319 <!-- LB 29 Do not break between numeric punctuation and alphabetics (\"e.g.\"). --> 320 <rule id="29"> $IS × ($AL | $HL) </rule> 321 <!-- LB 30 Do not break between letters, numbers or ordinary symbols and opening or closing punctuation. --> 322 <rule id="30.01"> ($AL | $HL | $NU) × $OP30 </rule> 323 <rule id="30.02"> $CP30 × ($AL | $HL | $NU) </rule> 324 <!-- LB 30a Break between two Regional Indicators if and only if there is an even number of them before the point being considered. --> 325 <rule id="30.11"> $sot ($RI $RI)* $RI × $RI </rule> 326 <rule id="30.12"> [^$RI] ($RI $RI)* $RI × $RI </rule> 327 <rule id="30.13"> $RI ÷ $RI </rule> 328 <!-- LB 30b Do not break between an emoji base (or potential emoji) and an emoji modifier. --> 329 <rule id="30.21"> $EB × $EM </rule> 330 <rule id="30.22"> $ExtPictUnassigned × $EM </rule> 331 </segmentRules> 332 </segmentation> 333 <segmentation type="SentenceBreak"> 334 <variables> 335 <!-- VARIABLES --> 336 <variable id="$CR">\p{Sentence_Break=CR}</variable> 337 <variable id="$LF">\p{Sentence_Break=LF}</variable> 338 <variable id="$Extend">\p{Sentence_Break=Extend}</variable> 339 <variable id="$Format">\p{Sentence_Break=Format}</variable> 340 <variable id="$Sep">\p{Sentence_Break=Sep}</variable> 341 <variable id="$Sp">\p{Sentence_Break=Sp}</variable> 342 <variable id="$Lower">\p{Sentence_Break=Lower}</variable> 343 <variable id="$Upper">\p{Sentence_Break=Upper}</variable> 344 <variable id="$OLetter">\p{Sentence_Break=OLetter}</variable> 345 <variable id="$Numeric">\p{Sentence_Break=Numeric}</variable> 346 <variable id="$ATerm">\p{Sentence_Break=ATerm}</variable> 347 <variable id="$STerm">\p{Sentence_Break=STerm}</variable> 348 <variable id="$Close">\p{Sentence_Break=Close}</variable> 349 <variable id="$SContinue">\p{Sentence_Break=SContinue}</variable> 350 <variable id="$Any">.</variable> 351 <!-- SPECIAL EXTENSIONS --> 352 <!-- WARNING: For Rule 5, now add format and extend to everything but Sep, Format, and Extend --> 353 <variable id="$FE">[$Format $Extend]</variable> 354 <variable id="$NotPreLower_">[^ $OLetter $Upper $Lower $Sep $CR $LF $STerm $ATerm]</variable> 355 <variable id="$Sp">($Sp $FE*)</variable> 356 <variable id="$Lower">($Lower $FE*)</variable> 357 <variable id="$Upper">($Upper $FE*)</variable> 358 <variable id="$OLetter">($OLetter $FE*)</variable> 359 <variable id="$Numeric">($Numeric $FE*)</variable> 360 <variable id="$ATerm">($ATerm $FE*)</variable> 361 <variable id="$STerm">($STerm $FE*)</variable> 362 <variable id="$Close">($Close $FE*)</variable> 363 <variable id="$SContinue">($SContinue $FE*)</variable> 364 <!-- MACROS --> 365 <variable id="$ParaSep">($Sep | $CR | $LF)</variable> 366 <variable id="$SATerm">($STerm | $ATerm)</variable> 367 </variables> 368 <segmentRules> 369 <!-- RULES --> 370 <!-- Break at the start and end of text, unless the text is empty. --> 371 <!-- Do not break within CRLF. --> 372 <rule id="3"> $CR × $LF </rule> 373 <!-- Break after paragraph separators. --> 374 <rule id="4"> $ParaSep ÷ </rule> 375 <!-- Ignore Format and Extend characters, except after sot, ParaSep, and within CRLF. (See Section 6.2, Replacing Ignore Rules.) This also has the effect of: Any × (Format | Extend) --> 376 <!-- WARNING: Implemented as don't break before format (except after linebreaks), --> 377 <!-- AND add format and extend in all variables definitions that appear after this point! --> 378 <rule id="5"> × [$Format $Extend] </rule> 379 <!-- Do not break after full stop in certain contexts. [See note below.] --> 380 <!-- Do not break after ambiguous terminators like period, if immediately followed by a number or lowercase letter, --> 381 <!-- is between uppercase letters, or if the first following letter (optionally after certain punctuation) is lowercase. --> 382 <!-- For example, a period may be an abbreviation or numeric period, and not mark the end of a sentence. --> 383 <rule id="6"> $ATerm × $Numeric </rule> 384 <rule id="7"> ($Upper | $Lower) $ATerm × $Upper </rule> 385 <rule id="8"> $ATerm $Close* $Sp* × $NotPreLower_* $Lower </rule> 386 <rule id="8.1"> $SATerm $Close* $Sp* × ($SContinue | $SATerm) </rule> 387 <!-- Break after sentence terminators, but include closing punctuation, trailing spaces, and any paragraph separator. [See note below.] Include closing punctuation, trailing spaces, and (optionally) a paragraph separator. --> 388 <rule id="9"> $SATerm $Close* × ( $Close | $Sp | $ParaSep ) </rule> 389 <!-- Note the fix to $Sp*, $Sep? --> 390 <rule id="10"> $SATerm $Close* $Sp* × ( $Sp | $ParaSep ) </rule> 391 <rule id="11"> $SATerm $Close* $Sp* $ParaSep? ÷ </rule> 392 <!-- Otherwise, do not break --> 393 <rule id="998"> × $Any </rule> 394 </segmentRules> 395 </segmentation> 396 <segmentation type="WordBreak"> 397 <variables> 398 <!-- VARIABLES --> 399 <variable id="$CR">\p{Word_Break=CR}</variable> 400 <variable id="$LF">\p{Word_Break=LF}</variable> 401 <variable id="$Newline">\p{Word_Break=Newline}</variable> 402 <variable id="$Extend">\p{Word_Break=Extend}</variable> 403 <!-- Now normal variables --> 404 <variable id="$Format">[\p{Word_Break=Format}]</variable> 405 <variable id="$Katakana">\p{Word_Break=Katakana}</variable> 406 <variable id="$ALetter">\p{Word_Break=ALetter}</variable> 407 <variable id="$MidLetter">\p{Word_Break=MidLetter}</variable> 408 <variable id="$MidNum">\p{Word_Break=MidNum}</variable> 409 <variable id="$MidNumLet">\p{Word_Break=MidNumLet}</variable> 410 <variable id="$Numeric">\p{Word_Break=Numeric}</variable> 411 <variable id="$ExtendNumLet">\p{Word_Break=ExtendNumLet}</variable> 412 <variable id="$RI">\p{Word_Break=Regional_Indicator}</variable> 413 <variable id="$Hebrew_Letter">\p{Word_Break=Hebrew_Letter}</variable> 414 <variable id="$Double_Quote">\p{Word_Break=Double_Quote}</variable> 415 <variable id="$Single_Quote">\p{Word_Break=Single_Quote}</variable> 416 <variable id="$ZWJ">\p{Word_Break=ZWJ}</variable> 417 <!-- Note: The following may overlap with the above --> 418 <variable id="$ExtPict">\p{Extended_Pictographic}</variable> 419 <variable id="$WSegSpace">\p{Word_Break=WSegSpace}</variable> 420 <!-- MACROS --> 421 <variable id="$AHLetter">($ALetter | $Hebrew_Letter)</variable> 422 <variable id="$MidNumLetQ">($MidNumLet | $Single_Quote)</variable> 423 <!-- SPECIAL EXTENSIONS --> 424 <!-- Add format and extend to everything --> 425 <variable id="$FE">[$Format $Extend $ZWJ]</variable> 426 <variable id="$NotBreak_">[^ $Newline $CR $LF ]</variable> 427 <variable id="$Katakana">($Katakana $FE*)</variable> 428 <variable id="$ALetter">($ALetter $FE*)</variable> 429 <variable id="$MidLetter">($MidLetter $FE*)</variable> 430 <variable id="$MidNum">($MidNum $FE*)</variable> 431 <variable id="$MidNumLet">($MidNumLet $FE*)</variable> 432 <variable id="$Numeric">($Numeric $FE*)</variable> 433 <variable id="$ExtendNumLet">($ExtendNumLet $FE*)</variable> 434 <variable id="$RI">($RI $FE*)</variable> 435 <variable id="$Hebrew_Letter">($Hebrew_Letter $FE*)</variable> 436 <variable id="$Double_Quote">($Double_Quote $FE*)</variable> 437 <variable id="$Single_Quote">($Single_Quote $FE*)</variable> 438 <variable id="$AHLetter">($AHLetter $FE*)</variable> 439 <variable id="$MidNumLetQ">($MidNumLetQ $FE*)</variable> 440 </variables> 441 <segmentRules> 442 <!-- RULES --> 443 <!-- Break at the start and end of text, unless the text is empty. --> 444 <!-- Do not break within CRLF. --> 445 <rule id="3"> $CR × $LF </rule> 446 <!-- Otherwise break before and after Newlines (including CR and LF) --> 447 <rule id="3.1"> ($Newline | $CR | $LF) ÷ </rule> 448 <rule id="3.2"> ÷ ($Newline | $CR | $LF) </rule> 449 <!-- Do not break within emoji zwj sequences. --> 450 <rule id="3.3"> $ZWJ × $ExtPict </rule> 451 <rule id="3.4"> $WSegSpace × $WSegSpace </rule> 452 <!-- Ignore Format and Extend characters, except after sot, CR, LF, and Newline. (See Section 6.2, Replacing Ignore Rules.) This also has the effect of: Any × (Format | Extend) --> 453 <!-- WARNING: Implemented as don't break before format (except after linebreaks), --> 454 <!-- AND add format and extend in all variables definitions that appear after this point! --> 455 <rule id="4"> $NotBreak_ × [$Format $Extend $ZWJ] </rule> 456 <!-- VANILLA RULES --> 457 <!-- Do not break between most letters. --> 458 <rule id="5"> $AHLetter × $AHLetter </rule> 459 <!-- Do not break letters across certain punctuation. --> 460 <rule id="6"> $AHLetter × ($MidLetter | $MidNumLetQ) $AHLetter </rule> 461 <rule id="7"> $AHLetter ($MidLetter | $MidNumLetQ) × $AHLetter </rule> 462 <rule id="7.1"> $Hebrew_Letter × $Single_Quote </rule> 463 <rule id="7.2"> $Hebrew_Letter × $Double_Quote $Hebrew_Letter </rule> 464 <rule id="7.3"> $Hebrew_Letter $Double_Quote × $Hebrew_Letter </rule> 465 <!-- Do not break within sequences of digits, or digits adjacent to letters (“3a”, or “A3”). --> 466 <rule id="8"> $Numeric × $Numeric </rule> 467 <rule id="9"> $AHLetter × $Numeric </rule> 468 <rule id="10"> $Numeric × $AHLetter </rule> 469 <!-- Do not break within sequences, such as “3.2” or “3,456.789”. --> 470 <rule id="11"> $Numeric ($MidNum | $MidNumLetQ) × $Numeric </rule> 471 <rule id="12"> $Numeric × ($MidNum | $MidNumLetQ) $Numeric </rule> 472 <!-- Do not break between Katakana. --> 473 <rule id="13"> $Katakana × $Katakana </rule> 474 <!-- Do not break from extenders. --> 475 <rule id="13.1"> ($AHLetter | $Numeric | $Katakana | $ExtendNumLet) × $ExtendNumLet </rule> 476 <rule id="13.2"> $ExtendNumLet × ($AHLetter | $Numeric | $Katakana) </rule> 477 <!-- Do not break within emoji flag sequences. That is, do not break between regional indicator (RI) symbols if there is an odd number of RI characters before the break point. --> 478 <rule id="15"> ^ ($RI $RI)* $RI × $RI </rule> 479 <rule id="16"> [^$RI] ($RI $RI)* $RI × $RI </rule> 480 <!-- Otherwise, break everywhere (including around ideographs). --> 481 </segmentRules> 482 </segmentation> 483 </segmentations> 484</ldml> 485