twitter_cldr 4.0.0 → 4.1.0
Sign up to get free protection for your applications and to get access to all the features.
- checksums.yaml +4 -4
- data/Gemfile +3 -2
- data/README.md +18 -2
- data/Rakefile +39 -122
- data/lib/twitter_cldr.rb +3 -0
- data/lib/twitter_cldr/formatters/numbers/rbnf.rb +5 -1
- data/lib/twitter_cldr/resources.rb +86 -5
- data/lib/twitter_cldr/resources/bidi_test_importer.rb +50 -44
- data/lib/twitter_cldr/resources/casefolder_class_generator.rb +22 -13
- data/lib/twitter_cldr/resources/collation_tries_importer.rb +44 -0
- data/lib/twitter_cldr/resources/hyphenation_importer.rb +16 -42
- data/lib/twitter_cldr/resources/import_resolver.rb +71 -0
- data/lib/twitter_cldr/resources/importer.rb +107 -0
- data/lib/twitter_cldr/resources/language_codes_importer.rb +35 -38
- data/lib/twitter_cldr/resources/loader.rb +3 -3
- data/lib/twitter_cldr/resources/locales_resources_importer.rb +48 -35
- data/lib/twitter_cldr/resources/phone_codes_importer.rb +24 -23
- data/lib/twitter_cldr/resources/postal_codes_importer.rb +10 -11
- data/lib/twitter_cldr/resources/properties.rb +0 -4
- data/lib/twitter_cldr/resources/properties/age_property_importer.rb +13 -9
- data/lib/twitter_cldr/resources/properties/arabic_shaping_property_importer.rb +9 -11
- data/lib/twitter_cldr/resources/properties/bidi_brackets_property_importer.rb +11 -9
- data/lib/twitter_cldr/resources/properties/blocks_property_importer.rb +13 -9
- data/lib/twitter_cldr/resources/properties/derived_core_properties_importer.rb +9 -11
- data/lib/twitter_cldr/resources/properties/east_asian_width_property_importer.rb +13 -9
- data/lib/twitter_cldr/resources/properties/grapheme_break_property_importer.rb +13 -9
- data/lib/twitter_cldr/resources/properties/hangul_syllable_type_property_importer.rb +13 -9
- data/lib/twitter_cldr/resources/properties/indic_positional_category_property_importer.rb +13 -9
- data/lib/twitter_cldr/resources/properties/indic_syllabic_category_property_importer.rb +13 -9
- data/lib/twitter_cldr/resources/properties/jamo_property_importer.rb +13 -9
- data/lib/twitter_cldr/resources/properties/line_break_property_importer.rb +13 -9
- data/lib/twitter_cldr/resources/properties/prop_list_importer.rb +9 -11
- data/lib/twitter_cldr/resources/properties/property_importer.rb +13 -22
- data/lib/twitter_cldr/resources/properties/script_extensions_property_importer.rb +12 -10
- data/lib/twitter_cldr/resources/properties/script_property_importer.rb +13 -9
- data/lib/twitter_cldr/resources/properties/sentence_break_property_importer.rb +13 -9
- data/lib/twitter_cldr/resources/properties/unicode_data_properties_importer.rb +11 -9
- data/lib/twitter_cldr/resources/properties/word_break_property_importer.rb +13 -9
- data/lib/twitter_cldr/resources/rbnf_test_importer.rb +41 -38
- data/lib/twitter_cldr/resources/readme_renderer.rb +1 -2
- data/lib/twitter_cldr/resources/requirements.rb +18 -0
- data/lib/twitter_cldr/resources/requirements/cldr_requirement.rb +66 -0
- data/lib/twitter_cldr/resources/requirements/dependency_requirement.rb +23 -0
- data/lib/twitter_cldr/resources/requirements/git_requirement.rb +66 -0
- data/lib/twitter_cldr/resources/requirements/icu_requirement.rb +111 -0
- data/lib/twitter_cldr/resources/requirements/unicode_requirement.rb +51 -0
- data/lib/twitter_cldr/resources/segment_tests_importer.rb +15 -30
- data/lib/twitter_cldr/resources/tailoring_importer.rb +33 -26
- data/lib/twitter_cldr/resources/transform_test_importer.rb +15 -17
- data/lib/twitter_cldr/resources/uli/segment_exceptions_importer.rb +29 -17
- data/lib/twitter_cldr/resources/unicode_data_importer.rb +38 -31
- data/lib/twitter_cldr/resources/unicode_file_parser.rb +37 -0
- data/lib/twitter_cldr/resources/unicode_property_aliases_importer.rb +23 -27
- data/lib/twitter_cldr/shared/casefolder.rb +139 -115
- data/lib/twitter_cldr/version.rb +1 -1
- data/lib/twitter_cldr/versions.rb +0 -4
- data/resources/collation/tailoring/bo.yml +4 -0
- data/resources/collation/tries/bo.dump +0 -0
- data/resources/locales/bo/calendars.yml +247 -0
- data/resources/locales/bo/currencies.yml +208 -0
- data/resources/locales/bo/fields.yml +31 -0
- data/resources/locales/bo/languages.yml +24 -0
- data/resources/locales/bo/layout.yml +5 -0
- data/resources/locales/bo/lists.yml +12 -0
- data/resources/locales/bo/numbers.yml +111 -0
- data/resources/locales/bo/plural_rules.yml +6 -0
- data/resources/locales/bo/plurals.yml +12 -0
- data/resources/locales/bo/territories.yml +14 -0
- data/resources/locales/bo/units.yml +283 -0
- data/resources/shared/transforms/Arab-Latn.yml +109 -0
- data/resources/shared/transforms/Beng-Deva.yml +13 -0
- data/resources/shared/transforms/Beng-Gujr.yml +13 -0
- data/resources/shared/transforms/Beng-Guru.yml +13 -0
- data/resources/shared/transforms/Beng-Knda.yml +13 -0
- data/resources/shared/transforms/Beng-Latn.yml +13 -0
- data/resources/shared/transforms/Beng-Mlym.yml +13 -0
- data/resources/shared/transforms/Beng-Orya.yml +13 -0
- data/resources/shared/transforms/Beng-Taml.yml +13 -0
- data/resources/shared/transforms/Beng-Telu.yml +13 -0
- data/resources/shared/transforms/Cyrl-Latn.yml +128 -0
- data/resources/shared/transforms/Deva-Beng.yml +13 -0
- data/resources/shared/transforms/Deva-Gujr.yml +13 -0
- data/resources/shared/transforms/Deva-Guru.yml +13 -0
- data/resources/shared/transforms/Deva-Knda.yml +13 -0
- data/resources/shared/transforms/Deva-Latn.yml +13 -0
- data/resources/shared/transforms/Deva-Mlym.yml +13 -0
- data/resources/shared/transforms/Deva-Orya.yml +13 -0
- data/resources/shared/transforms/Deva-Taml.yml +13 -0
- data/resources/shared/transforms/Deva-Telu.yml +13 -0
- data/resources/shared/transforms/Geor-Latn.yml +43 -0
- data/resources/shared/transforms/Grek-Latn-UNGEGN.yml +160 -0
- data/resources/shared/transforms/Grek-Latn.yml +206 -0
- data/resources/shared/transforms/Gujr-Beng.yml +13 -0
- data/resources/shared/transforms/Gujr-Deva.yml +13 -0
- data/resources/shared/transforms/Gujr-Guru.yml +13 -0
- data/resources/shared/transforms/Gujr-Knda.yml +13 -0
- data/resources/shared/transforms/Gujr-Latn.yml +13 -0
- data/resources/shared/transforms/Gujr-Mlym.yml +13 -0
- data/resources/shared/transforms/Gujr-Orya.yml +13 -0
- data/resources/shared/transforms/Gujr-Taml.yml +13 -0
- data/resources/shared/transforms/Gujr-Telu.yml +13 -0
- data/resources/shared/transforms/Guru-Beng.yml +13 -0
- data/resources/shared/transforms/Guru-Deva.yml +13 -0
- data/resources/shared/transforms/Guru-Gujr.yml +13 -0
- data/resources/shared/transforms/Guru-Knda.yml +13 -0
- data/resources/shared/transforms/Guru-Latn.yml +13 -0
- data/resources/shared/transforms/Guru-Mlym.yml +13 -0
- data/resources/shared/transforms/Guru-Orya.yml +13 -0
- data/resources/shared/transforms/Guru-Taml.yml +13 -0
- data/resources/shared/transforms/Guru-Telu.yml +13 -0
- data/resources/shared/transforms/Han-Spacedhan.yml +1 -1
- data/resources/shared/transforms/Hang-Latn.yml +12 -0
- data/resources/shared/transforms/Hani-Latn.yml +1605 -0
- data/resources/shared/transforms/Hans-Hant.yml +3982 -0
- data/resources/shared/transforms/Hebr-Latn.yml +72 -0
- data/resources/shared/transforms/Hira-Kana.yml +114 -0
- data/resources/shared/transforms/Hira-Latn.yml +15 -0
- data/resources/shared/transforms/InterIndic-Latin.yml +2 -2
- data/resources/shared/transforms/Jamo-Latn.yml +12 -0
- data/resources/shared/transforms/Knda-Beng.yml +13 -0
- data/resources/shared/transforms/Knda-Deva.yml +13 -0
- data/resources/shared/transforms/Knda-Gujr.yml +13 -0
- data/resources/shared/transforms/Knda-Guru.yml +13 -0
- data/resources/shared/transforms/Knda-Latn.yml +13 -0
- data/resources/shared/transforms/Knda-Mlym.yml +13 -0
- data/resources/shared/transforms/Knda-Orya.yml +13 -0
- data/resources/shared/transforms/Knda-Taml.yml +13 -0
- data/resources/shared/transforms/Knda-Telu.yml +13 -0
- data/resources/shared/transforms/Latin-ASCII.yml +16 -1
- data/resources/shared/transforms/Latin-InterIndic.yml +2 -2
- data/resources/shared/transforms/Latn-Armn.yml +90 -0
- data/resources/shared/transforms/Latn-Beng.yml +14 -0
- data/resources/shared/transforms/Latn-Bopo.yml +1336 -0
- data/resources/shared/transforms/Latn-Cans.yml +190 -0
- data/resources/shared/transforms/Latn-Deva.yml +14 -0
- data/resources/shared/transforms/Latn-Ethi.yml +278 -0
- data/resources/shared/transforms/Latn-Gujr.yml +14 -0
- data/resources/shared/transforms/Latn-Guru.yml +14 -0
- data/resources/shared/transforms/Latn-Hang.yml +13 -0
- data/resources/shared/transforms/Latn-Jamo.yml +13 -0
- data/resources/shared/transforms/Latn-Kana.yml +274 -0
- data/resources/shared/transforms/Latn-Knda.yml +14 -0
- data/resources/shared/transforms/Latn-Mlym.yml +14 -0
- data/resources/shared/transforms/Latn-Orya.yml +14 -0
- data/resources/shared/transforms/Latn-Taml.yml +14 -0
- data/resources/shared/transforms/Latn-Telu.yml +14 -0
- data/resources/shared/transforms/Latn-Thaa.yml +439 -0
- data/resources/shared/transforms/Latn-Thai.yml +13 -0
- data/resources/shared/transforms/Mlym-Beng.yml +13 -0
- data/resources/shared/transforms/Mlym-Deva.yml +13 -0
- data/resources/shared/transforms/Mlym-Gujr.yml +13 -0
- data/resources/shared/transforms/Mlym-Guru.yml +13 -0
- data/resources/shared/transforms/Mlym-Knda.yml +13 -0
- data/resources/shared/transforms/Mlym-Latn.yml +13 -0
- data/resources/shared/transforms/Mlym-Orya.yml +13 -0
- data/resources/shared/transforms/Mlym-Taml.yml +13 -0
- data/resources/shared/transforms/Mlym-Telu.yml +13 -0
- data/resources/shared/transforms/Orya-Beng.yml +13 -0
- data/resources/shared/transforms/Orya-Deva.yml +13 -0
- data/resources/shared/transforms/Orya-Gujr.yml +13 -0
- data/resources/shared/transforms/Orya-Guru.yml +13 -0
- data/resources/shared/transforms/Orya-Knda.yml +13 -0
- data/resources/shared/transforms/Orya-Latn.yml +13 -0
- data/resources/shared/transforms/Orya-Mlym.yml +13 -0
- data/resources/shared/transforms/Orya-Taml.yml +13 -0
- data/resources/shared/transforms/Orya-Telu.yml +13 -0
- data/resources/shared/transforms/Syrc-Latn.yml +55 -0
- data/resources/shared/transforms/Taml-Beng.yml +13 -0
- data/resources/shared/transforms/Taml-Deva.yml +13 -0
- data/resources/shared/transforms/Taml-Gujr.yml +13 -0
- data/resources/shared/transforms/Taml-Guru.yml +13 -0
- data/resources/shared/transforms/Taml-Knda.yml +13 -0
- data/resources/shared/transforms/Taml-Latn.yml +13 -0
- data/resources/shared/transforms/Taml-Mlym.yml +13 -0
- data/resources/shared/transforms/Taml-Orya.yml +13 -0
- data/resources/shared/transforms/Taml-Telu.yml +13 -0
- data/resources/shared/transforms/Telu-Beng.yml +13 -0
- data/resources/shared/transforms/Telu-Deva.yml +13 -0
- data/resources/shared/transforms/Telu-Gujr.yml +13 -0
- data/resources/shared/transforms/Telu-Guru.yml +13 -0
- data/resources/shared/transforms/Telu-Knda.yml +13 -0
- data/resources/shared/transforms/Telu-Latn.yml +13 -0
- data/resources/shared/transforms/Telu-Mlym.yml +13 -0
- data/resources/shared/transforms/Telu-Orya.yml +13 -0
- data/resources/shared/transforms/Telu-Taml.yml +13 -0
- data/resources/shared/transforms/Thai-Latn.yml +15 -0
- data/resources/shared/transforms/am-am_FONIPA.yml +609 -0
- data/resources/shared/transforms/am-am_Latn-BGN.yml +336 -0
- data/resources/shared/transforms/am-ar.yml +11 -0
- data/resources/shared/transforms/am-fa.yml +10 -0
- data/resources/shared/transforms/ar-ar_Latn-BGN.yml +122 -0
- data/resources/shared/transforms/az_Cyrl-az-BGN.yml +93 -0
- data/resources/shared/transforms/be-be_Latn-BGN.yml +108 -0
- data/resources/shared/transforms/bg-bg_Latn-BGN.yml +99 -0
- data/resources/shared/transforms/ch-am.yml +10 -0
- data/resources/shared/transforms/ch-ar.yml +10 -0
- data/resources/shared/transforms/ch-ch_FONIPA.yml +0 -8
- data/resources/shared/transforms/ch-fa.yml +10 -0
- data/resources/shared/transforms/cs-am.yml +10 -0
- data/resources/shared/transforms/cs-ar.yml +10 -0
- data/resources/shared/transforms/cs-fa.yml +10 -0
- data/resources/shared/transforms/dsb-dsb_FONIPA.yml +0 -5
- data/resources/shared/transforms/dv-dv_Latn-BGN.yml +112 -0
- data/resources/shared/transforms/el-el_Latn-BGN.yml +208 -0
- data/resources/shared/transforms/eo-am.yml +10 -0
- data/resources/shared/transforms/eo-ar.yml +10 -0
- data/resources/shared/transforms/eo-eo_FONIPA.yml +52 -0
- data/resources/shared/transforms/eo-fa.yml +10 -0
- data/resources/shared/transforms/es-ar.yml +13 -0
- data/resources/shared/transforms/es-fa.yml +13 -0
- data/resources/shared/transforms/es_419-am.yml +11 -0
- data/resources/shared/transforms/es_419-ar.yml +14 -0
- data/resources/shared/transforms/es_419-fa.yml +14 -0
- data/resources/shared/transforms/fa-fa_Latn-BGN.yml +123 -0
- data/resources/shared/transforms/he-he_Latn-BGN.yml +62 -0
- data/resources/shared/transforms/hy-am.yml +10 -0
- data/resources/shared/transforms/hy-ar.yml +10 -0
- data/resources/shared/transforms/hy-fa.yml +10 -0
- data/resources/shared/transforms/hy-hy_FONIPA.yml +56 -0
- data/resources/shared/transforms/hy-hy_Latn-BGN.yml +133 -0
- data/resources/shared/transforms/hy_AREVMDA-am.yml +10 -0
- data/resources/shared/transforms/hy_AREVMDA-ar.yml +10 -0
- data/resources/shared/transforms/hy_AREVMDA-fa.yml +10 -0
- data/resources/shared/transforms/hy_AREVMDA-hy_AREVMDA_FONIPA.yml +82 -0
- data/resources/shared/transforms/ia-am.yml +10 -0
- data/resources/shared/transforms/ia-ar.yml +10 -0
- data/resources/shared/transforms/ia-fa.yml +10 -0
- data/resources/shared/transforms/ia-ia_FONIPA.yml +69 -0
- data/resources/shared/transforms/ja_Hrkt-ja_Latn-BGN.yml +310 -0
- data/resources/shared/transforms/ka-ka_Latn-BGN.yml +44 -0
- data/resources/shared/transforms/kk-am.yml +10 -0
- data/resources/shared/transforms/kk-ar.yml +10 -0
- data/resources/shared/transforms/kk-fa.yml +10 -0
- data/resources/shared/transforms/kk-kk_FONIPA.yml +53 -0
- data/resources/shared/transforms/kk-kk_Latn-BGN.yml +136 -0
- data/resources/shared/transforms/ko-ko_Latn-BGN.yml +282 -0
- data/resources/shared/transforms/ky-am.yml +10 -0
- data/resources/shared/transforms/ky-ar.yml +10 -0
- data/resources/shared/transforms/ky-fa.yml +10 -0
- data/resources/shared/transforms/ky-ky_FONIPA.yml +73 -0
- data/resources/shared/transforms/ky-ky_Latn-BGN.yml +107 -0
- data/resources/shared/transforms/la-la_FONIPA.yml +0 -8
- data/resources/shared/transforms/mk-mk_Latn-BGN.yml +89 -0
- data/resources/shared/transforms/mn-mn_Latn-BGN.yml +101 -0
- data/resources/shared/transforms/mn-mn_Latn-MNS.yml +89 -0
- data/resources/shared/transforms/my-am.yml +10 -0
- data/resources/shared/transforms/my-ar.yml +10 -0
- data/resources/shared/transforms/my-fa.yml +10 -0
- data/resources/shared/transforms/my-my_FONIPA.yml +260 -0
- data/resources/shared/transforms/pl-am.yml +10 -0
- data/resources/shared/transforms/pl-ar.yml +10 -0
- data/resources/shared/transforms/pl-fa.yml +10 -0
- data/resources/shared/transforms/ps-ps_Latn-BGN.yml +151 -0
- data/resources/shared/transforms/rm_SURSILV-am.yml +10 -0
- data/resources/shared/transforms/rm_SURSILV-ar.yml +10 -0
- data/resources/shared/transforms/rm_SURSILV-fa.yml +10 -0
- data/resources/shared/transforms/rm_SURSILV-rm_FONIPA_SURSILV.yml +84 -0
- data/resources/shared/transforms/ro-am.yml +10 -0
- data/resources/shared/transforms/ro-ar.yml +10 -0
- data/resources/shared/transforms/ro-fa.yml +10 -0
- data/resources/shared/transforms/ro-ro_FONIPA.yml +38 -6
- data/resources/shared/transforms/ro_FONIPA-ja.yml +1 -0
- data/resources/shared/transforms/ru-ru_Latn-BGN.yml +121 -0
- data/resources/shared/transforms/ru_Latn-ru-BGN.yml +101 -0
- data/resources/shared/transforms/sat-am.yml +10 -0
- data/resources/shared/transforms/sat-ar.yml +10 -0
- data/resources/shared/transforms/sat-fa.yml +10 -0
- data/resources/shared/transforms/sat_Olck-sat_FONIPA.yml +132 -0
- data/resources/shared/transforms/si-am.yml +10 -0
- data/resources/shared/transforms/si-ar.yml +10 -0
- data/resources/shared/transforms/si-fa.yml +10 -0
- data/resources/shared/transforms/si-si_FONIPA.yml +128 -0
- data/resources/shared/transforms/si-si_Latn.yml +96 -0
- data/resources/shared/transforms/sk-am.yml +10 -0
- data/resources/shared/transforms/sk-ar.yml +10 -0
- data/resources/shared/transforms/sk-fa.yml +10 -0
- data/resources/shared/transforms/sk-sk_FONIPA.yml +18 -2
- data/resources/shared/transforms/sk_FONIPA-ja.yml +2 -0
- data/resources/shared/transforms/sr-sr_Latn-BGN.yml +81 -0
- data/resources/shared/transforms/tk_Cyrl-tk-BGN.yml +122 -0
- data/resources/shared/transforms/tlh-am.yml +10 -0
- data/resources/shared/transforms/tlh-ar.yml +10 -0
- data/resources/shared/transforms/tlh-fa.yml +10 -0
- data/resources/shared/transforms/tlh-tlh_FONIPA.yml +0 -8
- data/resources/shared/transforms/uk-uk_Latn-BGN.yml +115 -0
- data/resources/shared/transforms/und_FONIPA-ar.yml +96 -0
- data/resources/shared/transforms/und_FONIPA-fa.yml +88 -0
- data/resources/shared/transforms/und_FONIPA-und_FONXSAMP.yml +198 -0
- data/resources/shared/transforms/uz_Cyrl-uz-BGN.yml +117 -0
- data/resources/shared/transforms/xh-am.yml +10 -0
- data/resources/shared/transforms/xh-ar.yml +10 -0
- data/resources/shared/transforms/xh-fa.yml +10 -0
- data/resources/shared/transforms/xh-xh_FONIPA.yml +71 -0
- data/resources/shared/transforms/zu-am.yml +10 -0
- data/resources/shared/transforms/zu-ar.yml +10 -0
- data/resources/shared/transforms/zu-fa.yml +10 -0
- data/resources/shared/transforms/zu-zu_FONIPA.yml +58 -0
- data/spec/formatters/numbers/rbnf/rbnf_spec.rb +3 -1
- data/spec/resources/loader_spec.rb +12 -5
- data/spec/spec_helper.rb +1 -1
- metadata +242 -10
- data/History.txt +0 -282
- data/lib/twitter_cldr/resources/collation_tries_dumper.rb +0 -43
- data/lib/twitter_cldr/resources/custom_locales_resources_importer.rb +0 -80
- data/lib/twitter_cldr/resources/download.rb +0 -64
- data/lib/twitter_cldr/resources/icu_based_importer.rb +0 -18
- data/lib/twitter_cldr/resources/properties/properties_importer.rb +0 -59
- data/lib/twitter_cldr/resources/unicode_importer.rb +0 -37
@@ -0,0 +1,109 @@
|
|
1
|
+
---
|
2
|
+
:transforms:
|
3
|
+
-
|
4
|
+
:direction: both
|
5
|
+
:rules:
|
6
|
+
- ":: [[:Arabic:][:block=ARABIC:][ⁿ،؛؟ـً-ٕ٠-٬۰-۹﷼ښ]] ;"
|
7
|
+
- ":: NFKD (NFC);"
|
8
|
+
- "$disambig = ̱ ;"
|
9
|
+
- "$disambig2 = ̰ ;"
|
10
|
+
- "$under = ̣ ;"
|
11
|
+
- "$descender = ˌ;"
|
12
|
+
- "$notAbove = [[:^ccc=0:] & [:^ccc=230:]];"
|
13
|
+
- "[:Nd:]{٫}[:Nd:] <> [:Nd:]{','}[:Nd:] ; # ARABIC DECIMAL SEPARATOR"
|
14
|
+
- "[:Nd:]{٬}[:Nd:] <> [:Nd:]{'.'}[:Nd:] ; # ARABIC THOUSANDS SEPARATOR"
|
15
|
+
- "٫ <> ',' $disambig ; # ARABIC DECIMAL SEPARATOR"
|
16
|
+
- "٬ <> '.' $disambig ; # ARABIC THOUSANDS SEPARATOR"
|
17
|
+
- "، <> ',' ; # ARABIC COMMA"
|
18
|
+
- "؛ <> ';' ; # ARABIC SEMICOLON"
|
19
|
+
- "؟ <> '?' ; # ARABIC QUESTION MARK"
|
20
|
+
- "٪ <> '%' ; # ARABIC PERCENT SIGN"
|
21
|
+
- "۰ <> 0 $disambig ; # EXTENDED ARABIC-INDIC DIGIT ZERO"
|
22
|
+
- "۱ <> 1 $disambig ; # EXTENDED ARABIC-INDIC DIGIT ONE"
|
23
|
+
- "۲ <> 2 $disambig ; # EXTENDED ARABIC-INDIC DIGIT TWO"
|
24
|
+
- "۳ <> 3 $disambig ; # EXTENDED ARABIC-INDIC DIGIT THREE"
|
25
|
+
- "۴ <> 4 $disambig ; # EXTENDED ARABIC-INDIC DIGIT FOUR"
|
26
|
+
- "۵ <> 5 $disambig ; # EXTENDED ARABIC-INDIC DIGIT FIVE"
|
27
|
+
- "۶ <> 6 $disambig ; # EXTENDED ARABIC-INDIC DIGIT SIX"
|
28
|
+
- "۷ <> 7 $disambig ; # EXTENDED ARABIC-INDIC DIGIT SEVEN"
|
29
|
+
- "۸ <> 8 $disambig ; # EXTENDED ARABIC-INDIC DIGIT EIGHT"
|
30
|
+
- "۹ <> 9 $disambig ; # EXTENDED ARABIC-INDIC DIGIT NINE"
|
31
|
+
- "٠ <> 0 ; # ARABIC-INDIC DIGIT ZERO"
|
32
|
+
- "١ <> 1 ; # ARABIC-INDIC DIGIT ONE"
|
33
|
+
- "٢ <> 2 ; # ARABIC-INDIC DIGIT TWO"
|
34
|
+
- "٣ <> 3 ; # ARABIC-INDIC DIGIT THREE"
|
35
|
+
- "٤ <> 4 ; # ARABIC-INDIC DIGIT FOUR"
|
36
|
+
- "٥ <> 5 ; # ARABIC-INDIC DIGIT FIVE"
|
37
|
+
- "٦ <> 6 ; # ARABIC-INDIC DIGIT SIX"
|
38
|
+
- "٧ <> 7 ; # ARABIC-INDIC DIGIT SEVEN"
|
39
|
+
- "٨ <> 8 ; # ARABIC-INDIC DIGIT EIGHT"
|
40
|
+
- "٩ <> 9 ; # ARABIC-INDIC DIGIT NINE"
|
41
|
+
- "َا<> ā ; # ARABIC FATHA, ARABIC LETTER ALEF"
|
42
|
+
- "ُو <> ū ; # ARABIC DAMMA, ARABIC LETTER WAW"
|
43
|
+
- "ِي <> ī ; # ARABIC KASRA, ARABIC LETTER YEH"
|
44
|
+
- "ث <> t h $disambig ; # ARABIC LETTER THEH"
|
45
|
+
- "ذ <> d h $disambig ; # ARABIC LETTER THAL"
|
46
|
+
- "ش <> s h $disambig ; # ARABIC LETTER SHEEN"
|
47
|
+
- "ص <> s $under ; # ARABIC LETTER SAD"
|
48
|
+
- "ض <> d $under ; # ARABIC LETTER DAD"
|
49
|
+
- "ط <> t $under ; # ARABIC LETTER TAH"
|
50
|
+
- "ظ <> z $under ; # ARABIC LETTER ZAH"
|
51
|
+
- "غ <> g h $disambig ; # ARABIC LETTER GHAIN"
|
52
|
+
- "ة <> t ̈ ; # ARABIC LETTER TEH MARBUTA"
|
53
|
+
- "ة | $1 < t ($notAbove+) ̈ ; # ARABIC LETTER TEH MARBUTA"
|
54
|
+
- "ژ <> z h $disambig ; # ARABIC LETTER JEH"
|
55
|
+
- "ڭ <> n $disambig g ; # ARABIC LETTER NG"
|
56
|
+
- "ۋ <> v $disambig ; # ARABIC LETTER VE"
|
57
|
+
- "ی <> y $disambig2 ; # ARABIC LETTER FARSI YEH"
|
58
|
+
- "ښ <> s $descender;"
|
59
|
+
- "ء <> ʾ ; # ARABIC LETTER HAMZA"
|
60
|
+
- "ا <> a $under; # ARABIC LETTER ALEF"
|
61
|
+
- "ب <> b ; # ARABIC LETTER BEH"
|
62
|
+
- "ت <> t ; # ARABIC LETTER TEH"
|
63
|
+
- "ج <> j ; # ARABIC LETTER JEEM"
|
64
|
+
- "ح <> h $under ; # ARABIC LETTER HAH"
|
65
|
+
- "خ <> k h $disambig ; # ARABIC LETTER KHAH"
|
66
|
+
- "د <> d ; # ARABIC LETTER DAL"
|
67
|
+
- "ر <> r ; # ARABIC LETTER REH"
|
68
|
+
- "ز <> z ; # ARABIC LETTER ZAIN"
|
69
|
+
- "س <> s ; # ARABIC LETTER SEEN"
|
70
|
+
- "ع <> ʿ ; # ARABIC LETTER AIN"
|
71
|
+
- "ـ > ; # ARABIC TATWEEL"
|
72
|
+
- "ف <> f ; # ARABIC LETTER FEH"
|
73
|
+
- "ق <> q ; # ARABIC LETTER QAF"
|
74
|
+
- "ک <> k $disambig ; # ARABIC LETTER KEHEH"
|
75
|
+
- "ك <> k ; # ARABIC LETTER KAF"
|
76
|
+
- "ل <> l ; # ARABIC LETTER LAM"
|
77
|
+
- "م <> m ; # ARABIC LETTER MEEM"
|
78
|
+
- "ن <> n ; # ARABIC LETTER NOON"
|
79
|
+
- "ه <> h ; # ARABIC LETTER HEH"
|
80
|
+
- "و <> w ; # ARABIC LETTER WAW"
|
81
|
+
- "ى <> y $disambig ; # ARABIC LETTER ALEF MAKSURA"
|
82
|
+
- "ي <> y ; # ARABIC LETTER YEH"
|
83
|
+
- "ً <> aⁿ ; # ARABIC FATHATAN"
|
84
|
+
- "ٌ <> uⁿ ; # ARABIC DAMMATAN"
|
85
|
+
- "ٍ <> iⁿ ; # ARABIC KASRATAN"
|
86
|
+
- "َ <> a ; # ARABIC FATHA"
|
87
|
+
- "ُ <> u ; # ARABIC DAMMA"
|
88
|
+
- "ِ <> i ; # ARABIC KASRA"
|
89
|
+
- "ّ <> ̃ ; # ARABIC SHADDA"
|
90
|
+
- "ْ <> ̊ ; # ARABIC SUKUN"
|
91
|
+
- "ٓ <> ̂ ; # ARABIC MADDAH ABOVE"
|
92
|
+
- "ٔ <> ̉ ; # ARABIC HAMZA ABOVE"
|
93
|
+
- "ٕ <> ̹ ; # ARABIC HAMZA BELOW"
|
94
|
+
- "پ <> p ; # ARABIC LETTER PEH"
|
95
|
+
- "چ <> c h $disambig ; # ARABIC LETTER TCHEH"
|
96
|
+
- "ڤ <> v ; # ARABIC LETTER VEH"
|
97
|
+
- "گ <> g ; # ARABIC LETTER GAF"
|
98
|
+
- "| s < c } [eiy];"
|
99
|
+
- "| k < c ;"
|
100
|
+
- "| i < e ;"
|
101
|
+
- "| u < o ;"
|
102
|
+
- "| ks < x ;"
|
103
|
+
- "| n < ⁿ;"
|
104
|
+
- ":: (lower) ;"
|
105
|
+
- "::NFC (NFD);"
|
106
|
+
- ":: ( [[:Latin:] [%,.0-9;?ʾ-ʿ̂-̄̈-̣̰̊-̱̹;ˌ]] );"
|
107
|
+
:source: Arab
|
108
|
+
:target: Latn
|
109
|
+
:variant: ~
|
@@ -0,0 +1,13 @@
|
|
1
|
+
---
|
2
|
+
:transforms:
|
3
|
+
-
|
4
|
+
:direction: forward
|
5
|
+
:rules:
|
6
|
+
- "::[[:script=bengali:][।-॥ঁ-ঃঅ-ঌএ-ঐও-নপ-রলশ-হ়-ৄে-ৈো-্ৗড়-ঢ়য়-ৣ০-৺ৎ]];"
|
7
|
+
- "::NFD;"
|
8
|
+
- "::Bengali-InterIndic;"
|
9
|
+
- "::InterIndic-Latin;"
|
10
|
+
- "::NFC;"
|
11
|
+
:source: Beng
|
12
|
+
:target: Latn
|
13
|
+
:variant: ~
|
@@ -0,0 +1,128 @@
|
|
1
|
+
---
|
2
|
+
:transforms:
|
3
|
+
-
|
4
|
+
:direction: both
|
5
|
+
:rules:
|
6
|
+
- ":: [Ққ̈Ă-ăĔ-ĕĞ-ğĬ-ĭŎ-ŏŬ-ŭ̆Ѐ-џҐ-ҕҘ-ҙӁ-ӂӐ-ӟӢ-ӧӬ-ӵӸ-ӹḜ-ḝẮ-ặᾰᾸῐῘῠῨ] ;"
|
7
|
+
- ":: NFD (NFC) ;"
|
8
|
+
- "$modprime = ʹ;"
|
9
|
+
- "$modprime2 = ʺ;"
|
10
|
+
- "$grave = ̀;"
|
11
|
+
- "$acute = ́;"
|
12
|
+
- "$hat = ̂;"
|
13
|
+
- "$breve = ̆ ;"
|
14
|
+
- "$dot = ̇ ;"
|
15
|
+
- "$caron = ̌ ;"
|
16
|
+
- "$comma = ̦ ;"
|
17
|
+
- "$under = ̱ ;"
|
18
|
+
- "$descender = ˌ;"
|
19
|
+
- "я <> a $hat ; # CYRILLIC SMALL LETTER YA"
|
20
|
+
- "Я <> A $hat ; # CYRILLIC CAPITAL LETTER YA"
|
21
|
+
- "ч <> c $caron ; # CYRILLIC SMALL LETTER CHE"
|
22
|
+
- "Ч <> C $caron; # CYRILLIC CAPITAL LETTER CHE"
|
23
|
+
- "э <> e $acute; # CYRILLIC SMALL LETTER E"
|
24
|
+
- "Э <> E $acute; # CYRILLIC CAPITAL LETTER E"
|
25
|
+
- "є <> e $hat; # CYRILLIC SMALL LETTER UKRAINIAN IE"
|
26
|
+
- "Є <> E $hat; # CYRILLIC CAPITAL LETTER UKRAINIAN IE"
|
27
|
+
- "ш <> s $caron ; # CYRILLIC SMALL LETTER SHA"
|
28
|
+
- "Ш <> S $caron ; # CYRILLIC CAPITAL LETTER SHA"
|
29
|
+
- "щ <> s $hat ; # CYRILLIC SMALL LETTER SHCHA"
|
30
|
+
- "Щ <> S $hat; # CYRILLIC CAPITAL LETTER SHCHA"
|
31
|
+
- "ѕ <> z $hat ; # CYRILLIC SMALL LETTER DZE"
|
32
|
+
- "Ѕ <> Z $hat; # CYRILLIC CAPITAL LETTER DZE"
|
33
|
+
- "ю <> u $hat ; # CYRILLIC SMALL LETTER YU"
|
34
|
+
- "Ю <> U $hat ; # CYRILLIC CAPITAL LETTER YU"
|
35
|
+
- "і <> i $acute; # CYRILLIC SMALL LETTER BYELORUSSIAN-UKRAINIAN I"
|
36
|
+
- "І <> I $acute; # CYRILLIC CAPITAL LETTER BYELORUSSIAN-UKRAINIAN I"
|
37
|
+
- "ј <> j $caron; # CYRILLIC SMALL LETTER JE"
|
38
|
+
- "Ј <> J $caron; # CYRILLIC CAPITAL LETTER JE"
|
39
|
+
- "љ <> l $hat ; # CYRILLIC SMALL LETTER LJE"
|
40
|
+
- "Љ <> L $hat ; # CYRILLIC CAPITAL LETTER LJE"
|
41
|
+
- "њ <> n $hat ; # CYRILLIC SMALL LETTER NJE"
|
42
|
+
- "Њ <> N $hat ; # CYRILLIC CAPITAL LETTER NJE"
|
43
|
+
- "ћ <> c $acute ; # CYRILLIC SMALL LETTER TSHE"
|
44
|
+
- "Ћ <> C $acute ; # CYRILLIC CAPITAL LETTER TSHE"
|
45
|
+
- "џ <> d $hat ; # CYRILLIC SMALL LETTER DZHE"
|
46
|
+
- "Џ <> D $hat ; # CYRILLIC CAPITAL LETTER DZHE"
|
47
|
+
- "а <> a ; # CYRILLIC SMALL LETTER A"
|
48
|
+
- "А <> A ; # CYRILLIC CAPITAL LETTER A"
|
49
|
+
- "ә <> ə ; # CYRILLIC SMALL LETTER SCHWA"
|
50
|
+
- "Ә <> Ə ; # CYRILLIC CAPITAL LETTER SCHWA"
|
51
|
+
- "ӕ <> æ ; # CYRILLIC SMALL LIGATURE A IE"
|
52
|
+
- "Ӕ <> Æ ; # CYRILLIC CAPITAL LIGATURE A IE"
|
53
|
+
- "б <> b ; # CYRILLIC SMALL LETTER BE"
|
54
|
+
- "Б <> B ; # CYRILLIC CAPITAL LETTER BE"
|
55
|
+
- "в <> v ; # CYRILLIC SMALL LETTER VE"
|
56
|
+
- "В <> V ; # CYRILLIC CAPITAL LETTER VE"
|
57
|
+
- "ґ <> g $grave ; # CYRILLIC SMALL LETTER GHE WITH UPTURN"
|
58
|
+
- "Ґ <> G $grave ; # CYRILLIC CAPITAL LETTER GHE WITH UPTURN"
|
59
|
+
- "ғ <> g $dot ; # CYRILLIC SMALL LETTER GHE WITH STROKE"
|
60
|
+
- "Ғ <> G $dot; # CYRILLIC CAPITAL LETTER GHE WITH STROKE"
|
61
|
+
- "ҕ <> g $breve; # CYRILLIC SMALL LETTER GHE WITH MIDDLE HOOK"
|
62
|
+
- "Ҕ <> G $breve; # CYRILLIC CAPITAL LETTER GHE WITH MIDDLE HOOK"
|
63
|
+
- "г <> g ; # CYRILLIC SMALL LETTER GHE"
|
64
|
+
- "Г <> G ; # CYRILLIC CAPITAL LETTER GHE"
|
65
|
+
- "д <> d; # CYRILLIC SMALL LETTER DE"
|
66
|
+
- "Д <> D; # CYRILLIC CAPITAL LETTER DE"
|
67
|
+
- "ђ <> đ ; # CYRILLIC SMALL LETTER DJE"
|
68
|
+
- "Ђ <> Đ ; # CYRILLIC CAPITAL LETTER DJE"
|
69
|
+
- "ҙ <> z $comma ; # CYRILLIC SMALL LETTER ZE WITH DESCENDER"
|
70
|
+
- "Ҙ <> Z $comma ; # CYRILLIC CAPITAL LETTER ZE WITH DESCENDER"
|
71
|
+
- "е <> e ; # CYRILLIC SMALL LETTER IE"
|
72
|
+
- "Е <> E; # CYRILLIC CAPITAL LETTER IE"
|
73
|
+
- "ж <> z $caron; # CYRILLIC SMALL LETTER ZHE"
|
74
|
+
- "Ж <> Z $caron; # CYRILLIC CAPITAL LETTER ZHE"
|
75
|
+
- "з <> z ; # CYRILLIC SMALL LETTER ZE"
|
76
|
+
- "З <> Z; # CYRILLIC CAPITAL LETTER ZE"
|
77
|
+
- "й <> j ; # CYRILLIC SMALL LETTER I"
|
78
|
+
- "Й <> J ; # CYRILLIC CAPITAL LETTER I"
|
79
|
+
- "и <> i ; # CYRILLIC SMALL LETTER I"
|
80
|
+
- "И <> I ; # CYRILLIC CAPITAL LETTER I"
|
81
|
+
- "қ <> k $descender ; # CYRILLIC SMALL LETTER KA WITH DESCENDER"
|
82
|
+
- "Қ <> K $descender ; # CYRILLIC CAPITAL LETTER KA WITH DESCENDER"
|
83
|
+
- "к <> k ; # CYRILLIC SMALL LETTER KA"
|
84
|
+
- "К <> K; # CYRILLIC CAPITAL LETTER KA"
|
85
|
+
- "л <> l ; # CYRILLIC SMALL LETTER EL"
|
86
|
+
- "Л <> L; # CYRILLIC CAPITAL LETTER EL"
|
87
|
+
- "м <> m ; # CYRILLIC SMALL LETTER EM"
|
88
|
+
- "М <> M ; # CYRILLIC CAPITAL LETTER EM"
|
89
|
+
- "н <> n ; # CYRILLIC SMALL LETTER EN"
|
90
|
+
- "Н <> N; # CYRILLIC CAPITAL LETTER EN"
|
91
|
+
- "о <> o ; # CYRILLIC SMALL LETTER O"
|
92
|
+
- "О <> O ; # CYRILLIC CAPITAL LETTER O"
|
93
|
+
- "п <> p ; # CYRILLIC SMALL LETTER PE"
|
94
|
+
- "П <> P ; # CYRILLIC CAPITAL LETTER PE"
|
95
|
+
- "р <> r ; # CYRILLIC SMALL LETTER ER"
|
96
|
+
- "Р <> R ; # CYRILLIC CAPITAL LETTER ER"
|
97
|
+
- "с <> s ; # CYRILLIC SMALL LETTER ES"
|
98
|
+
- "С <> S ; # CYRILLIC CAPITAL LETTER ES"
|
99
|
+
- "т <> t ; # CYRILLIC SMALL LETTER TE"
|
100
|
+
- "Т <> T ; # CYRILLIC CAPITAL LETTER TE"
|
101
|
+
- "у <> u ; # CYRILLIC SMALL LETTER U"
|
102
|
+
- "У <> U ; # CYRILLIC CAPITAL LETTER U"
|
103
|
+
- "ф <> f ; # CYRILLIC SMALL LETTER EF"
|
104
|
+
- "Ф <> F ; # CYRILLIC CAPITAL LETTER EF"
|
105
|
+
- "х <> h ; # CYRILLIC SMALL LETTER HA"
|
106
|
+
- "Х <> H; # CYRILLIC CAPITAL LETTER HA"
|
107
|
+
- "ц <> c ; # CYRILLIC SMALL LETTER TSE"
|
108
|
+
- "Ц <> C; # CYRILLIC CAPITAL LETTER TSE"
|
109
|
+
- "Ъ <> $modprime2 $under ; # CYRILLIC CAPITAL LETTER HARD SIGN"
|
110
|
+
- "ъ <> $modprime2 ; # CYRILLIC SMALL LETTER HARD SIGN"
|
111
|
+
- "Ь <> $modprime $under ; # CYRILLIC CAPITAL LETTER SOFT SIGN"
|
112
|
+
- "ь <> $modprime ; # CYRILLIC SMALL LETTER SOFT SIGN"
|
113
|
+
- "ы <> y ; # CYRILLIC SMALL LETTER YERU"
|
114
|
+
- "Ы <> Y ; # CYRILLIC CAPITAL LETTER YERU"
|
115
|
+
- "$ignore = [[:Mark:]''] * ;"
|
116
|
+
- "| k < q ;"
|
117
|
+
- "| K < Q ;"
|
118
|
+
- "| u < w ;"
|
119
|
+
- "| U < W ;"
|
120
|
+
- "| KS < X } $ignore [:UppercaseLetter:] ;"
|
121
|
+
- "| KS < [:UppercaseLetter:] $ignore { X ;"
|
122
|
+
- "| Ks < X ;"
|
123
|
+
- "| ks < x ;"
|
124
|
+
- ":: NFC (NFD) ;"
|
125
|
+
- ":: ( [ˌ̈A-Za-zÀ-ÏÑ-ÖÙ-Ýà-ïñ-öù-ýÿ-ĥĨ-İĴ-ķĹ-ľŃ-ňŌ-őŔ-ťŨ-žƏƠ-ơƯ-ưǍ-ǜǞ-ǣǦ-ǰǴ-ǵǸ-țȞ-ȟȦ-ȳəʹ-ʺ̀-̂̆-̦̱̇̌̀-́̈́ʹ΅-ΆΈ-ΊΌΎ-ΐά-ΰό-ώϓЀЃЌ-ЎЙйѐѓќ-ўӁ-ӂӐ-ӑӖ-ӗḀ-ẙẛẠ-ỹἂ-ἅἊ-Ἅἒ-ἕἚ-Ἕἢ-ἥἪ-Ἥἲ-ἵἺ-Ἵὂ-ὅὊ-Ὅὒ-ὕὛὝὢ-ὥὪ-Ὥὰ-ώᾂ-ᾅᾊ-ᾍᾒ-ᾕᾚ-ᾝᾢ-ᾥᾪ-ᾭᾰᾲᾴᾸᾺ-ΆῂῄῈ-Ή῍-῎ῐῒ-ΐῘῚ-Ί῝-῞ῠῢ-ΰῨῪ-Ύ῭-΅ῲῴῸ-ΏK-Å] ) ;"
|
126
|
+
:source: Cyrl
|
127
|
+
:target: Latn
|
128
|
+
:variant: ~
|