| 1 |
.\" -*- mode: troff; coding: utf-8 -*- |
| 2 |
.\" Automatically generated by Pod::Man 5.0102 (Pod::Simple 3.45) |
| 3 |
.\" |
| 4 |
.\" Standard preamble: |
| 5 |
.\" ======================================================================== |
| 6 |
.de Sp \" Vertical space (when we can't use .PP) |
| 7 |
.if t .sp .5v |
| 8 |
.if n .sp |
| 9 |
.. |
| 10 |
.de Vb \" Begin verbatim text |
| 11 |
.ft CW |
| 12 |
.nf |
| 13 |
.ne \\$1 |
| 14 |
.. |
| 15 |
.de Ve \" End verbatim text |
| 16 |
.ft R |
| 17 |
.fi |
| 18 |
.. |
| 19 |
.\" \*(C` and \*(C' are quotes in nroff, nothing in troff, for use with C<>. |
| 20 |
.ie n \{\ |
| 21 |
. ds C` "" |
| 22 |
. ds C' "" |
| 23 |
'br\} |
| 24 |
.el\{\ |
| 25 |
. ds C` |
| 26 |
. ds C' |
| 27 |
'br\} |
| 28 |
.\" |
| 29 |
.\" Escape single quotes in literal strings from groff's Unicode transform. |
| 30 |
.ie \n(.g .ds Aq \(aq |
| 31 |
.el .ds Aq ' |
| 32 |
.\" |
| 33 |
.\" If the F register is >0, we'll generate index entries on stderr for |
| 34 |
.\" titles (.TH), headers (.SH), subsections (.SS), items (.Ip), and index |
| 35 |
.\" entries marked with X<> in POD. Of course, you'll have to process the |
| 36 |
.\" output yourself in some meaningful fashion. |
| 37 |
.\" |
| 38 |
.\" Avoid warning from groff about undefined register 'F'. |
| 39 |
.de IX |
| 40 |
.. |
| 41 |
.nr rF 0 |
| 42 |
.if \n(.g .if rF .nr rF 1 |
| 43 |
.if (\n(rF:(\n(.g==0)) \{\ |
| 44 |
. if \nF \{\ |
| 45 |
. de IX |
| 46 |
. tm Index:\\$1\t\\n%\t"\\$2" |
| 47 |
.. |
| 48 |
. if !\nF==2 \{\ |
| 49 |
. nr % 0 |
| 50 |
. nr F 2 |
| 51 |
. \} |
| 52 |
. \} |
| 53 |
.\} |
| 54 |
.rr rF |
| 55 |
.\" ======================================================================== |
| 56 |
.\" |
| 57 |
.IX Title "Unicode::Collate::Locale 3perl" |
| 58 |
.TH Unicode::Collate::Locale 3perl 2025-11-16 "perl v5.40.1" "Perl Programmers Reference Guide" |
| 59 |
.\" For nroff, turn off justification. Always turn off hyphenation; it makes |
| 60 |
.\" way too many mistakes in technical documents. |
| 61 |
.if n .ad l |
| 62 |
.nh |
| 63 |
.SH NAME |
| 64 |
Unicode::Collate::Locale \- Linguistic tailoring for DUCET via Unicode::Collate |
| 65 |
.SH SYNOPSIS |
| 66 |
.IX Header "SYNOPSIS" |
| 67 |
.Vb 1 |
| 68 |
\& use Unicode::Collate::Locale; |
| 69 |
\& |
| 70 |
\& #construct |
| 71 |
\& $Collator = Unicode::Collate::Locale\-> |
| 72 |
\& new(locale => $locale_name, %tailoring); |
| 73 |
\& |
| 74 |
\& #sort |
| 75 |
\& @sorted = $Collator\->sort(@not_sorted); |
| 76 |
\& |
| 77 |
\& #compare |
| 78 |
\& $result = $Collator\->cmp($a, $b); # returns 1, 0, or \-1. |
| 79 |
.Ve |
| 80 |
.PP |
| 81 |
\&\fBNote:\fR Strings in \f(CW@not_sorted\fR, \f(CW$a\fR and \f(CW$b\fR are interpreted |
| 82 |
according to Perl's Unicode support. See perlunicode, |
| 83 |
perluniintro, perlunitut, perlunifaq, utf8. |
| 84 |
Otherwise you can use \f(CW\*(C`preprocess\*(C'\fR (cf. \f(CW\*(C`Unicode::Collate\*(C'\fR) |
| 85 |
or should decode them before. |
| 86 |
.SH DESCRIPTION |
| 87 |
.IX Header "DESCRIPTION" |
| 88 |
This module provides linguistic tailoring for it |
| 89 |
taking advantage of \f(CW\*(C`Unicode::Collate\*(C'\fR. |
| 90 |
.SS Constructor |
| 91 |
.IX Subsection "Constructor" |
| 92 |
The \f(CW\*(C`new\*(C'\fR method returns a collator object. |
| 93 |
.PP |
| 94 |
A parameter list for the constructor is a hash, which can include |
| 95 |
a special key \f(CW\*(C`locale\*(C'\fR and its value (case-insensitive) standing |
| 96 |
for a Unicode base language code (two or three-letter). |
| 97 |
For example, \f(CW\*(C`Unicode::Collate::Locale\->new(locale => \*(AqES\*(Aq)\*(C'\fR |
| 98 |
returns a collator tailored for Spanish. |
| 99 |
.PP |
| 100 |
\&\f(CW$locale_name\fR may be suffixed with a Unicode script code (four-letter), |
| 101 |
a Unicode region (territory) code, a Unicode language variant code. |
| 102 |
These codes are case-insensitive, and separated with \f(CW\*(Aq_\*(Aq\fR or \f(CW\*(Aq\-\*(Aq\fR. |
| 103 |
E.g. \f(CW\*(C`en_US\*(C'\fR for English in USA, |
| 104 |
\&\f(CW\*(C`az_Cyrl\*(C'\fR for Azerbaijani in the Cyrillic script, |
| 105 |
\&\f(CW\*(C`es_ES_traditional\*(C'\fR for Spanish in Spain (Traditional). |
| 106 |
.PP |
| 107 |
If \f(CW$locale_name\fR is not available, |
| 108 |
fallback is selected in the following order: |
| 109 |
.PP |
| 110 |
.Vb 5 |
| 111 |
\& 1. language with a variant code |
| 112 |
\& 2. language with a script code |
| 113 |
\& 3. language with a region code |
| 114 |
\& 4. language |
| 115 |
\& 5. default |
| 116 |
.Ve |
| 117 |
.PP |
| 118 |
Tailoring tags provided by \f(CW\*(C`Unicode::Collate\*(C'\fR are allowed as long as |
| 119 |
they are not used for \f(CW\*(C`locale\*(C'\fR support. Esp. the \f(CW\*(C`table\*(C'\fR tag |
| 120 |
is always untailorable, since it is reserved for DUCET. |
| 121 |
.PP |
| 122 |
However \f(CW\*(C`entry\*(C'\fR is allowed, even if it is used for \f(CW\*(C`locale\*(C'\fR support, |
| 123 |
to add or override mappings. |
| 124 |
.PP |
| 125 |
E.g. a collator for Spanish, which ignores diacritics and case difference |
| 126 |
(i.e. level 1), with reversed case ordering and no normalization. |
| 127 |
.PP |
| 128 |
.Vb 6 |
| 129 |
\& Unicode::Collate::Locale\->new( |
| 130 |
\& level => 1, |
| 131 |
\& locale => \*(Aqes\*(Aq, |
| 132 |
\& upper_before_lower => 1, |
| 133 |
\& normalization => undef |
| 134 |
\& ) |
| 135 |
.Ve |
| 136 |
.PP |
| 137 |
Overriding a behavior already tailored by \f(CW\*(C`locale\*(C'\fR is disallowed |
| 138 |
if such a tailoring is passed to \f(CWnew()\fR. |
| 139 |
.PP |
| 140 |
.Vb 4 |
| 141 |
\& Unicode::Collate::Locale\->new( |
| 142 |
\& locale => \*(Aqda\*(Aq, |
| 143 |
\& upper_before_lower => 0, # causes error as reserved by \*(Aqda\*(Aq |
| 144 |
\& ) |
| 145 |
.Ve |
| 146 |
.PP |
| 147 |
However \f(CWchange()\fR inherited from \f(CW\*(C`Unicode::Collate\*(C'\fR allows |
| 148 |
such a tailoring that is reserved by \f(CW\*(C`locale\*(C'\fR. Examples: |
| 149 |
.PP |
| 150 |
.Vb 3 |
| 151 |
\& new(locale => \*(Aqfr_ca\*(Aq)\->change(backwards => undef) |
| 152 |
\& new(locale => \*(Aqda\*(Aq)\->change(upper_before_lower => 0) |
| 153 |
\& new(locale => \*(Aqja\*(Aq)\->change(overrideCJK => undef) |
| 154 |
.Ve |
| 155 |
.SS Methods |
| 156 |
.IX Subsection "Methods" |
| 157 |
\&\f(CW\*(C`Unicode::Collate::Locale\*(C'\fR is a subclass of \f(CW\*(C`Unicode::Collate\*(C'\fR |
| 158 |
and methods other than \f(CW\*(C`new\*(C'\fR are inherited from \f(CW\*(C`Unicode::Collate\*(C'\fR. |
| 159 |
.PP |
| 160 |
Here is a list of additional methods: |
| 161 |
.ie n .IP """$Collator\->getlocale""" 4 |
| 162 |
.el .IP \f(CW$Collator\->getlocale\fR 4 |
| 163 |
.IX Item "$Collator->getlocale" |
| 164 |
Returns a language code accepted and used actually on collation. |
| 165 |
If linguistic tailoring is not provided for a language code you passed |
| 166 |
(intensionally for some languages, or due to the incomplete implementation), |
| 167 |
this method returns a string \f(CW\*(Aqdefault\*(Aq\fR meaning no special tailoring. |
| 168 |
.ie n .IP """$Collator\->locale_version""" 4 |
| 169 |
.el .IP \f(CW$Collator\->locale_version\fR 4 |
| 170 |
.IX Item "$Collator->locale_version" |
| 171 |
(Since Unicode::Collate::Locale 0.87) |
| 172 |
Returns the version number (perhaps \f(CW\*(C`/\ed\e.\ed\ed/\*(C'\fR) of the locale, as that |
| 173 |
of \fILocale/*.pl\fR. |
| 174 |
.Sp |
| 175 |
\&\fBNote:\fR \fILocale/*.pl\fR that a collator uses should be identified by |
| 176 |
a combination of return values from \f(CW\*(C`getlocale\*(C'\fR and \f(CW\*(C`locale_version\*(C'\fR. |
| 177 |
.SS "A list of tailorable locales" |
| 178 |
.IX Subsection "A list of tailorable locales" |
| 179 |
.Vb 10 |
| 180 |
\& locale name description |
| 181 |
\& \-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\- |
| 182 |
\& af Afrikaans |
| 183 |
\& ar Arabic |
| 184 |
\& as Assamese |
| 185 |
\& az Azerbaijani (Azeri) |
| 186 |
\& be Belarusian |
| 187 |
\& bn Bengali |
| 188 |
\& bs Bosnian (tailored as Croatian) |
| 189 |
\& bs_Cyrl Bosnian in Cyrillic (tailored as Serbian) |
| 190 |
\& ca Catalan |
| 191 |
\& cs Czech |
| 192 |
\& cu Church Slavic |
| 193 |
\& cy Welsh |
| 194 |
\& da Danish |
| 195 |
\& de_\|_phonebook German (umlaut as \*(Aqae\*(Aq, \*(Aqoe\*(Aq, \*(Aque\*(Aq) |
| 196 |
\& de_AT_phonebook Austrian German (umlaut primary greater) |
| 197 |
\& dsb Lower Sorbian |
| 198 |
\& ee Ewe |
| 199 |
\& eo Esperanto |
| 200 |
\& es Spanish |
| 201 |
\& es_\|_traditional Spanish (\*(Aqch\*(Aq and \*(Aqll\*(Aq as a grapheme) |
| 202 |
\& et Estonian |
| 203 |
\& fa Persian |
| 204 |
\& fi Finnish (v and w are primary equal) |
| 205 |
\& fi_\|_phonebook Finnish (v and w as separate characters) |
| 206 |
\& fil Filipino |
| 207 |
\& fo Faroese |
| 208 |
\& fr_CA Canadian French |
| 209 |
\& gu Gujarati |
| 210 |
\& ha Hausa |
| 211 |
\& haw Hawaiian |
| 212 |
\& he Hebrew |
| 213 |
\& hi Hindi |
| 214 |
\& hr Croatian |
| 215 |
\& hu Hungarian |
| 216 |
\& hy Armenian |
| 217 |
\& ig Igbo |
| 218 |
\& is Icelandic |
| 219 |
\& ja Japanese [1] |
| 220 |
\& kk Kazakh |
| 221 |
\& kl Kalaallisut |
| 222 |
\& kn Kannada |
| 223 |
\& ko Korean [2] |
| 224 |
\& kok Konkani |
| 225 |
\& lkt Lakota |
| 226 |
\& ln Lingala |
| 227 |
\& lt Lithuanian |
| 228 |
\& lv Latvian |
| 229 |
\& mk Macedonian |
| 230 |
\& ml Malayalam |
| 231 |
\& mr Marathi |
| 232 |
\& mt Maltese |
| 233 |
\& nb Norwegian Bokmal |
| 234 |
\& nn Norwegian Nynorsk |
| 235 |
\& nso Northern Sotho |
| 236 |
\& om Oromo |
| 237 |
\& or Oriya |
| 238 |
\& pa Punjabi |
| 239 |
\& pl Polish |
| 240 |
\& ro Romanian |
| 241 |
\& sa Sanskrit |
| 242 |
\& se Northern Sami |
| 243 |
\& si Sinhala |
| 244 |
\& si_\|_dictionary Sinhala (U+0DA5 = U+0DA2,0DCA,0DA4) |
| 245 |
\& sk Slovak |
| 246 |
\& sl Slovenian |
| 247 |
\& sq Albanian |
| 248 |
\& sr Serbian |
| 249 |
\& sr_Latn Serbian in Latin (tailored as Croatian) |
| 250 |
\& sv Swedish (v and w are primary equal) |
| 251 |
\& sv_\|_reformed Swedish (v and w as separate characters) |
| 252 |
\& ta Tamil |
| 253 |
\& te Telugu |
| 254 |
\& th Thai |
| 255 |
\& tn Tswana |
| 256 |
\& to Tonga |
| 257 |
\& tr Turkish |
| 258 |
\& ug_Cyrl Uyghur in Cyrillic |
| 259 |
\& uk Ukrainian |
| 260 |
\& ur Urdu |
| 261 |
\& vi Vietnamese |
| 262 |
\& vo Volapu"k |
| 263 |
\& wae Walser |
| 264 |
\& wo Wolof |
| 265 |
\& yo Yoruba |
| 266 |
\& zh Chinese |
| 267 |
\& zh_\|_big5han Chinese (ideographs: big5 order) |
| 268 |
\& zh_\|_gb2312han Chinese (ideographs: GB\-2312 order) |
| 269 |
\& zh_\|_pinyin Chinese (ideographs: pinyin order) [3] |
| 270 |
\& zh_\|_stroke Chinese (ideographs: stroke order) [3] |
| 271 |
\& zh_\|_zhuyin Chinese (ideographs: zhuyin order) [3] |
| 272 |
\& \-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\- |
| 273 |
.Ve |
| 274 |
.PP |
| 275 |
Locales according to the default UCA rules include |
| 276 |
am (Amharic) without \f(CW\*(C`[reorder Ethi]\*(C'\fR, |
| 277 |
bg (Bulgarian) without \f(CW\*(C`[reorder Cyrl]\*(C'\fR, |
| 278 |
chr (Cherokee) without \f(CW\*(C`[reorder Cher]\*(C'\fR, |
| 279 |
de (German), |
| 280 |
en (English), |
| 281 |
fr (French), |
| 282 |
ga (Irish), |
| 283 |
id (Indonesian), |
| 284 |
it (Italian), |
| 285 |
ka (Georgian) without \f(CW\*(C`[reorder Geor]\*(C'\fR, |
| 286 |
mn (Mongolian) without \f(CW\*(C`[reorder Cyrl Mong]\*(C'\fR, |
| 287 |
ms (Malay), |
| 288 |
nl (Dutch), |
| 289 |
pt (Portuguese), |
| 290 |
ru (Russian) without \f(CW\*(C`[reorder Cyrl]\*(C'\fR, |
| 291 |
sw (Swahili), |
| 292 |
zu (Zulu). |
| 293 |
.PP |
| 294 |
\&\fBNote\fR |
| 295 |
.PP |
| 296 |
[1] ja: Ideographs are sorted in JIS X 0208 order. |
| 297 |
Fullwidth and halfwidth forms are identical to their regular form. |
| 298 |
The difference between hiragana and katakana is at the 4th level, |
| 299 |
the comparison also requires \f(CW\*(C`(variable => \*(AqNon\-ignorable\*(Aq)\*(C'\fR, |
| 300 |
and then \f(CW\*(C`katakana_before_hiragana\*(C'\fR has no effect. |
| 301 |
.PP |
| 302 |
[2] ko: Plenty of ideographs are sorted by their reading. Such |
| 303 |
an ideograph is primary (level 1) equal to, and secondary (level 2) |
| 304 |
greater than, the corresponding hangul syllable. |
| 305 |
.PP |
| 306 |
[3] zh_\|_pinyin, zh_\|_stroke and zh_\|_zhuyin: implemented alt='short', |
| 307 |
where a smaller number of ideographs are tailored. |
| 308 |
.SS "A list of variant codes and their aliases" |
| 309 |
.IX Subsection "A list of variant codes and their aliases" |
| 310 |
.Vb 10 |
| 311 |
\& variant code alias |
| 312 |
\& \-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\- |
| 313 |
\& dictionary dict |
| 314 |
\& phonebook phone phonebk |
| 315 |
\& reformed reform |
| 316 |
\& traditional trad |
| 317 |
\& \-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\- |
| 318 |
\& big5han big5 |
| 319 |
\& gb2312han gb2312 |
| 320 |
\& pinyin |
| 321 |
\& stroke |
| 322 |
\& zhuyin |
| 323 |
\& \-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\- |
| 324 |
.Ve |
| 325 |
.PP |
| 326 |
Note: 'pinyin' is Han in Latin, 'zhuyin' is Han in Bopomofo. |
| 327 |
.SH INSTALL |
| 328 |
.IX Header "INSTALL" |
| 329 |
Installation of \f(CW\*(C`Unicode::Collate::Locale\*(C'\fR requires \fICollate/Locale.pm\fR, |
| 330 |
\&\fICollate/Locale/*.pm\fR, \fICollate/CJK/*.pm\fR and \fICollate/allkeys.txt\fR. |
| 331 |
On building, \f(CW\*(C`Unicode::Collate::Locale\*(C'\fR doesn't require |
| 332 |
any of \fIdata/*.txt\fR, \fIgendata/*\fR, and \fImklocale\fR. |
| 333 |
Tests for \f(CW\*(C`Unicode::Collate::Locale\*(C'\fR are named \fIt/loc_*.t\fR. |
| 334 |
.SH CAVEAT |
| 335 |
.IX Header "CAVEAT" |
| 336 |
.IP "Tailoring is not maximum" 4 |
| 337 |
.IX Item "Tailoring is not maximum" |
| 338 |
Even if a certain letter is tailored, its equivalent would not always |
| 339 |
tailored as well as it. For example, even though W is tailored, |
| 340 |
fullwidth W (\f(CW\*(C`U+FF37\*(C'\fR), W with acute (\f(CW\*(C`U+1E82\*(C'\fR), etc. are not |
| 341 |
tailored. The result may depend on whether source strings are |
| 342 |
normalized or not, and whether decomposed or composed. |
| 343 |
Thus \f(CW\*(C`(normalization => undef)\*(C'\fR is less preferred. |
| 344 |
.IP "Collation reordering is not supported" 4 |
| 345 |
.IX Item "Collation reordering is not supported" |
| 346 |
The order of any groups including scripts is not changed. |
| 347 |
.SS Reference |
| 348 |
.IX Subsection "Reference" |
| 349 |
.Vb 10 |
| 350 |
\& locale based CLDR or other reference |
| 351 |
\& \-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\- |
| 352 |
\& af 30 = 1.8.1 |
| 353 |
\& ar 30 = 28 ("compat" wo [reorder Arab]) = 1.9.0 |
| 354 |
\& as 30 = 28 (without [reorder Beng..]) = 23 |
| 355 |
\& az 30 = 24 ("standard" wo [reorder Latn Cyrl]) |
| 356 |
\& be 30 = 28 (without [reorder Cyrl]) |
| 357 |
\& bn 30 = 28 ("standard" wo [reorder Beng..]) = 2.0.1 |
| 358 |
\& bs 30 = 28 (type="standard": [import hr]) |
| 359 |
\& bs_Cyrl 30 = 28 (type="standard": [import sr]) |
| 360 |
\& ca 30 = 23 (alt="proposed" type="standard") |
| 361 |
\& cs 30 = 1.8.1 (type="standard") |
| 362 |
\& cu 34 = 30 (without [reorder Cyrl]) |
| 363 |
\& cy 30 = 1.8.1 |
| 364 |
\& da 22.1 = 1.8.1 (type="standard") |
| 365 |
\& de_\|_phonebook 30 = 2.0 (type="phonebook") |
| 366 |
\& de_AT_phonebook 30 = 27 (type="phonebook") |
| 367 |
\& dsb 30 = 26 |
| 368 |
\& ee 30 = 21 |
| 369 |
\& eo 30 = 1.8.1 |
| 370 |
\& es 30 = 1.9.0 (type="standard") |
| 371 |
\& es_\|_traditional 30 = 1.8.1 (type="traditional") |
| 372 |
\& et 30 = 26 |
| 373 |
\& fa 22.1 = 1.8.1 |
| 374 |
\& fi 22.1 = 1.8.1 (type="standard" alt="proposed") |
| 375 |
\& fi_\|_phonebook 22.1 = 1.8.1 (type="phonebook") |
| 376 |
\& fil 30 = 1.9.0 (type="standard") = 1.8.1 |
| 377 |
\& fo 22.1 = 1.8.1 (alt="proposed" type="standard") |
| 378 |
\& fr_CA 30 = 1.9.0 |
| 379 |
\& gu 30 = 28 ("standard" wo [reorder Gujr..]) = 1.9.0 |
| 380 |
\& ha 30 = 1.9.0 |
| 381 |
\& haw 30 = 24 |
| 382 |
\& he 30 = 28 (without [reorder Hebr]) = 23 |
| 383 |
\& hi 30 = 28 (without [reorder Deva..]) = 1.9.0 |
| 384 |
\& hr 30 = 28 ("standard" wo [reorder Latn Cyrl]) = 1.9.0 |
| 385 |
\& hu 22.1 = 1.8.1 (alt="proposed" type="standard") |
| 386 |
\& hy 30 = 28 (without [reorder Armn]) = 1.8.1 |
| 387 |
\& ig 30 = 1.8.1 |
| 388 |
\& is 22.1 = 1.8.1 (type="standard") |
| 389 |
\& ja 22.1 = 1.8.1 (type="standard") |
| 390 |
\& kk 30 = 28 (without [reorder Cyrl]) |
| 391 |
\& kl 22.1 = 1.8.1 (type="standard") |
| 392 |
\& kn 30 = 28 ("standard" wo [reorder Knda..]) = 1.9.0 |
| 393 |
\& ko 22.1 = 1.8.1 (type="standard") |
| 394 |
\& kok 30 = 28 (without [reorder Deva..]) = 1.8.1 |
| 395 |
\& lkt 30 = 25 |
| 396 |
\& ln 30 = 2.0 (type="standard") = 1.8.1 |
| 397 |
\& lt 22.1 = 1.9.0 |
| 398 |
\& lv 22.1 = 1.9.0 (type="standard") = 1.8.1 |
| 399 |
\& mk 30 = 28 (without [reorder Cyrl]) |
| 400 |
\& ml 22.1 = 1.9.0 |
| 401 |
\& mr 30 = 28 (without [reorder Deva..]) = 1.8.1 |
| 402 |
\& mt 22.1 = 1.9.0 |
| 403 |
\& nb 22.1 = 2.0 (type="standard") |
| 404 |
\& nn 22.1 = 2.0 (type="standard") |
| 405 |
\& nso [*] 26 = 1.8.1 |
| 406 |
\& om 22.1 = 1.8.1 |
| 407 |
\& or 30 = 28 (without [reorder Orya..]) = 1.9.0 |
| 408 |
\& pa 22.1 = 1.8.1 |
| 409 |
\& pl 30 = 1.8.1 |
| 410 |
\& ro 30 = 1.9.0 (type="standard") |
| 411 |
\& sa [*] 1.9.1 = 1.8.1 (type="standard" alt="proposed") |
| 412 |
\& se 22.1 = 1.8.1 (type="standard") |
| 413 |
\& si 30 = 28 ("standard" wo [reorder Sinh..]) = 1.9.0 |
| 414 |
\& si_\|_dictionary 30 = 28 ("dictionary" wo [reorder Sinh..]) = 1.9.0 |
| 415 |
\& sk 22.1 = 1.9.0 (type="standard") |
| 416 |
\& sl 22.1 = 1.8.1 (type="standard" alt="proposed") |
| 417 |
\& sq 22.1 = 1.8.1 (alt="proposed" type="standard") |
| 418 |
\& sr 30 = 28 (without [reorder Cyrl]) |
| 419 |
\& sr_Latn 30 = 28 (type="standard": [import hr]) |
| 420 |
\& sv 22.1 = 1.9.0 (type="standard") |
| 421 |
\& sv_\|_reformed 22.1 = 1.8.1 (type="reformed") |
| 422 |
\& ta 22.1 = 1.9.0 |
| 423 |
\& te 30 = 28 (without [reorder Telu..]) = 1.9.0 |
| 424 |
\& th 22.1 = 22 |
| 425 |
\& tn [*] 26 = 1.8.1 |
| 426 |
\& to 22.1 = 22 |
| 427 |
\& tr 22.1 = 1.8.1 (type="standard") |
| 428 |
\& uk 30 = 28 (without [reorder Cyrl]) |
| 429 |
\& ug_Cyrl https://en.wikipedia.org/wiki/Uyghur_Cyrillic_alphabet |
| 430 |
\& ur 22.1 = 1.9.0 |
| 431 |
\& vi 22.1 = 1.8.1 |
| 432 |
\& vo 30 = 25 |
| 433 |
\& wae 30 = 2.0 |
| 434 |
\& wo [*] 1.9.1 = 1.8.1 |
| 435 |
\& yo 30 = 1.8.1 |
| 436 |
\& zh 22.1 = 1.8.1 (type="standard") |
| 437 |
\& zh_\|_big5han 22.1 = 1.8.1 (type="big5han") |
| 438 |
\& zh_\|_gb2312han 22.1 = 1.8.1 (type="gb2312han") |
| 439 |
\& zh_\|_pinyin 22.1 = 2.0 (type=\*(Aqpinyin\*(Aq alt=\*(Aqshort\*(Aq) |
| 440 |
\& zh_\|_stroke 22.1 = 1.9.1 (type=\*(Aqstroke\*(Aq alt=\*(Aqshort\*(Aq) |
| 441 |
\& zh_\|_zhuyin 22.1 = 22 (type=\*(Aqzhuyin\*(Aq alt=\*(Aqshort\*(Aq) |
| 442 |
\& \-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\- |
| 443 |
.Ve |
| 444 |
.PP |
| 445 |
[*] http://www.unicode.org/repos/cldr/tags/latest/seed/collation/ |
| 446 |
.SH AUTHOR |
| 447 |
.IX Header "AUTHOR" |
| 448 |
The Unicode::Collate::Locale module for perl was written |
| 449 |
by SADAHIRO Tomoyuki, <[email protected]>. |
| 450 |
This module is Copyright(C) 2004\-2020, SADAHIRO Tomoyuki. Japan. |
| 451 |
All rights reserved. |
| 452 |
.PP |
| 453 |
This module is free software; you can redistribute it and/or |
| 454 |
modify it under the same terms as Perl itself. |
| 455 |
.SH "SEE ALSO" |
| 456 |
.IX Header "SEE ALSO" |
| 457 |
.IP "Unicode Collation Algorithm \- UTS #10" 4 |
| 458 |
.IX Item "Unicode Collation Algorithm - UTS #10" |
| 459 |
<http://www.unicode.org/reports/tr10/> |
| 460 |
.IP "The Default Unicode Collation Element Table (DUCET)" 4 |
| 461 |
.IX Item "The Default Unicode Collation Element Table (DUCET)" |
| 462 |
<http://www.unicode.org/Public/UCA/latest/allkeys.txt> |
| 463 |
.IP "Unicode Locale Data Markup Language (LDML) \- UTS #35" 4 |
| 464 |
.IX Item "Unicode Locale Data Markup Language (LDML) - UTS #35" |
| 465 |
<http://www.unicode.org/reports/tr35/> |
| 466 |
.IP "CLDR \- Unicode Common Locale Data Repository" 4 |
| 467 |
.IX Item "CLDR - Unicode Common Locale Data Repository" |
| 468 |
<http://cldr.unicode.org/> |
| 469 |
.IP Unicode::Collate 4 |
| 470 |
.IX Item "Unicode::Collate" |
| 471 |
.PD 0 |
| 472 |
.IP Unicode::Normalize 4 |
| 473 |
.IX Item "Unicode::Normalize" |