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 +1,93 @@
|
|
1
|
+
---
|
2
|
+
:transforms:
|
3
|
+
-
|
4
|
+
:direction: forward
|
5
|
+
:rules:
|
6
|
+
- ":: [АБВГҒДЕӘЖЗИЫКҜЛМНОӨПРСТУҮФХҺЧҸШЙЭЮЯабвгғдеәжзиыкҝлмноөпрстуүфхһчҹш’йэюя] ;"
|
7
|
+
- ":: NFD (NFC) ;"
|
8
|
+
- "$prime = ’ ;"
|
9
|
+
- "$wordBoundary = [^[:L:][:M:][:N:]] ;"
|
10
|
+
- "$upperConsonants = [БВГҒДЖЗЈКҜЛМНПРСТФХҺЧҸШЙ] ;"
|
11
|
+
- "$lowerConsonants = [бвгғджзјкҝлмнпрстфхһчҹш’й] ;"
|
12
|
+
- "$consonants = [$upperConsonants $lowerConsonants] ;"
|
13
|
+
- "$upperVowels = [АЕӘИЫОӨУҮЭЮЯ] ;"
|
14
|
+
- "$lowerVowels = [аеәиыоөуүэюя] ;"
|
15
|
+
- "$vowels = [$upperVowels $lowerVowels] ;"
|
16
|
+
- "$lower = [$lowerConsonants $lowerVowels] ;"
|
17
|
+
- "А > A ; # CYRILLIC CAPITAL LETTER A"
|
18
|
+
- "а > a ; # CYRILLIC SMALL LETTER A"
|
19
|
+
- "Б > B ; # CYRILLIC CAPITAL LETTER BE"
|
20
|
+
- "б > b ; # CYRILLIC SMALL LETTER BE"
|
21
|
+
- "В > V ; # CYRILLIC CAPITAL LETTER VE"
|
22
|
+
- "в > v ; # CYRILLIC SMALL LETTER VE"
|
23
|
+
- "Г > Q ; # CYRILLIC CAPITAL LETTER GHE"
|
24
|
+
- "г > q ; # CYRILLIC SMALL LETTER GHE"
|
25
|
+
- "Ғ > Ğ ; # CYRILLIC CAPITAL LETTER GHE WITH STROKE"
|
26
|
+
- "ғ > ğ ; # CYRILLIC SMALL LETTER GHE WITH STROKE"
|
27
|
+
- "Д > D ; # CYRILLIC CAPITAL LETTER DE"
|
28
|
+
- "д > d ; # CYRILLIC SMALL LETTER DE"
|
29
|
+
- "Е > E ; # CYRILLIC CAPITAL LETTER DE"
|
30
|
+
- "е > e ; # CYRILLIC SMALL LETTER DE"
|
31
|
+
- "Ә > Ə; # CYRILLIC CAPITAL LETTER SCHWA"
|
32
|
+
- "ә > ə; # CYRILLIC SMALL LETTER SCHWA"
|
33
|
+
- "Ж > J ; # CYRILLIC CAPITAL LETTER ZHE"
|
34
|
+
- "ж > j ; # CYRILLIC SMALL LETTER ZHE"
|
35
|
+
- "З > Z ; # CYRILLIC CAPITAL LETTER ZE"
|
36
|
+
- "з > z ; # CYRILLIC SMALL LETTER ZE"
|
37
|
+
- "И > İ ; # CYRILLIC CAPITAL LETTER I"
|
38
|
+
- "и > i ; # CYRILLIC SMALL LETTER I"
|
39
|
+
- "Ы > I ; # CYRILLIC CAPITAL LETTER YERU"
|
40
|
+
- "ы > ı ; # CYRILLIC SMALL LETTER YERU"
|
41
|
+
- "Ј > Y ; # CYRILLIC CAPITAL LETTER JE"
|
42
|
+
- "ј > y ; # CYRILLIC SMALL LETTER JE"
|
43
|
+
- "К > K ; # CYRILLIC CAPITAL LETTER KA"
|
44
|
+
- "к > k ; # CYRILLIC SMALL LETTER KA"
|
45
|
+
- "Ҝ > G ; # CYRILLIC CAPITAL LETTER KA WITH VERTICAL STROKE"
|
46
|
+
- "ҝ > g ; # CYRILLIC SMALL LETTER KA WITH VERTICAL STROKE"
|
47
|
+
- "Л > L ; # CYRILLIC CAPITAL LETTER EL"
|
48
|
+
- "л > l ; # CYRILLIC SMALL LETTER EL"
|
49
|
+
- "М > M ; # CYRILLIC CAPITAL LETTER EM"
|
50
|
+
- "м > m ; # CYRILLIC SMALL LETTER EM"
|
51
|
+
- "Н > N ; # CYRILLIC CAPITAL LETTER EN"
|
52
|
+
- "н > n ; # CYRILLIC SMALL LETTER EN"
|
53
|
+
- "О > O ; # CYRILLIC CAPITAL LETTER O"
|
54
|
+
- "о > o ; # CYRILLIC SMALL LETTER O"
|
55
|
+
- "Ө > Ö ; # CYRILLIC CAPITAL LETTER BARRED O"
|
56
|
+
- "ө > ö ; # CYRILLIC SMALL LETTER BARRED O"
|
57
|
+
- "П > P ; # CYRILLIC CAPITAL LETTER PE"
|
58
|
+
- "п > p ; # CYRILLIC SMALL LETTER PE"
|
59
|
+
- "Р > R ; # CYRILLIC CAPITAL LETTER ER"
|
60
|
+
- "р > r ; # CYRILLIC SMALL LETTER ER"
|
61
|
+
- "С > S ; # CYRILLIC CAPITAL LETTER ES"
|
62
|
+
- "с > s ; # CYRILLIC SMALL LETTER ES"
|
63
|
+
- "Т > T ; # CYRILLIC CAPITAL LETTER TE"
|
64
|
+
- "т > t ; # CYRILLIC SMALL LETTER TE"
|
65
|
+
- "У > U ; # CYRILLIC CAPITAL LETTER U"
|
66
|
+
- "у > u ; # CYRILLIC SMALL LETTER U"
|
67
|
+
- "Ү > Ü ; # CYRILLIC CAPITAL LETTER STRAIGHT U"
|
68
|
+
- "ү > ü ; # CYRILLIC SMALL LETTER STRAIGHT U"
|
69
|
+
- "Ф > F ; # CYRILLIC CAPITAL LETTER EF"
|
70
|
+
- "ф > f ; # CYRILLIC SMALL LETTER EF"
|
71
|
+
- "Х > X ; # CYRILLIC CAPITAL LETTER HA"
|
72
|
+
- "х > x ; # CYRILLIC SMALL LETTER HA"
|
73
|
+
- "Һ > H ; # CYRILLIC CAPITAL LETTER SHHA"
|
74
|
+
- "һ > h ; # CYRILLIC SMALL LETTER SHHA"
|
75
|
+
- "Ч > Ç ; # CYRILLIC CAPITAL LETTER CHE"
|
76
|
+
- "ч > ç ; # CYRILLIC SMALL LETTER CHE"
|
77
|
+
- "Ҹ > C ; # CYRILLIC CAPITAL LETTER CHE WITH VERTICAL STROKE"
|
78
|
+
- "ҹ > c ; # CYRILLIC SMALL LETTER CHE WITH VERTICAL STROKE"
|
79
|
+
- "Ш > Ş ; # CYRILLIC CAPITAL LETTER SHA"
|
80
|
+
- "ш > ş ; # CYRILLIC SMALL LETTER SHA"
|
81
|
+
- "Й > Ẏ ; # CYRILLIC CAPITAL LETTER HARD SIGN"
|
82
|
+
- "й > ẏ ; # CYRILLIC SMALL LETTER HARD SIGN"
|
83
|
+
- "Э > Ė ; # CYRILLIC CAPITAL LETTER SOFT SIGN"
|
84
|
+
- "э > ė ; # CYRILLIC SMALL LETTER SOFT SIGN"
|
85
|
+
- "Ю} $lower > Yu̇ ; # CYRILLIC CAPITAL LETTER YU"
|
86
|
+
- "Ю > YU̇ ; # CYRILLIC CAPITAL LETTER YU"
|
87
|
+
- "ю > yu̇ ; # CYRILLIC SMALL LETTER YU"
|
88
|
+
- "Я} $lower > Yȧ ; # CYRILLIC CAPITAL LETTER YA"
|
89
|
+
- "Я > YȦ ; # CYRILLIC CAPITAL LETTER YA"
|
90
|
+
- "я > yȧ ; # CYRILLIC SMALL LETTER YA"
|
91
|
+
:source: az_Cyrl
|
92
|
+
:target: az
|
93
|
+
:variant: BGN
|
@@ -0,0 +1,108 @@
|
|
1
|
+
---
|
2
|
+
:transforms:
|
3
|
+
-
|
4
|
+
:direction: forward
|
5
|
+
:rules:
|
6
|
+
- ":: [АБВГДЕЁЖЗІЙКЛМНОПРСТУЎФХЦЧШЩЪЫЬЭЮЯҐабвгдеёжзійклмнопрстуўфхцчшщъыьэюя’ґ] ;"
|
7
|
+
- ":: NFD (NFC) ;"
|
8
|
+
- "$prime = ʹ ;"
|
9
|
+
- "$doublePrime = ʺ ;"
|
10
|
+
- "$upperConsonants = [БВГДЖЗЙКЛМНПРСТЎФХЦЧШЬҐ] ;"
|
11
|
+
- "$lowerConsonants = [бвгджзйклмнпрстўфхцчшь’ґ] ;"
|
12
|
+
- "$consonants = [$upperConsonants $lowerConsonants] ;"
|
13
|
+
- "$upperVowels = [АЕЁІОУЫЭЮЯ] ;"
|
14
|
+
- "$lowerVowels = [аеёіоуыэюя] ;"
|
15
|
+
- "$vowels = [$upperVowels $lowerVowels] ;"
|
16
|
+
- "$lower = [$lowerConsonants $lowerVowels] ;"
|
17
|
+
- "$wordBoundary = [^[:L:][:M:][:N:]] ;"
|
18
|
+
- "А > A ; # CYRILLIC CAPITAL LETTER A"
|
19
|
+
- "а > a ; # CYRILLIC SMALL LETTER A"
|
20
|
+
- "Б > B ; # CYRILLIC CAPITAL LETTER BE"
|
21
|
+
- "б > b ; # CYRILLIC SMALL LETTER BE"
|
22
|
+
- "В > V ; # CYRILLIC CAPITAL LETTER VE"
|
23
|
+
- "в > v ; # CYRILLIC SMALL LETTER VE"
|
24
|
+
- "Г > H ; # CYRILLIC CAPITAL LETTER GHE"
|
25
|
+
- "г > h ; # CYRILLIC SMALL LETTER GHE"
|
26
|
+
- "Д > D ; # CYRILLIC CAPITAL LETTER DE"
|
27
|
+
- "д > d ; # CYRILLIC SMALL LETTER DE"
|
28
|
+
- "Е} $lower > Ye ; # CYRILLIC CAPITAL LETTER IE"
|
29
|
+
- "Е > YE ; # CYRILLIC CAPITAL LETTER IE"
|
30
|
+
- "е > ye ; # CYRILLIC SMALL LETTER IE"
|
31
|
+
- "Ё} $lower > Yo ; # CYRILLIC CAPITAL LETTER IO"
|
32
|
+
- "Ё > YO ; # CYRILLIC CAPITAL LETTER IO"
|
33
|
+
- "ё > yo ; # CYRILLIC SMALL LETTER IO"
|
34
|
+
- "Ж} $lower > Zh ; # CYRILLIC CAPITAL LETTER ZHE"
|
35
|
+
- "Ж > ZH ; # CYRILLIC CAPITAL LETTER ZHE"
|
36
|
+
- "ж > zh ; # CYRILLIC SMALL LETTER ZHE"
|
37
|
+
- "ЗГ > Z·H ; # CYRILLIC CAPITAL LETTER ZE"
|
38
|
+
- "Зг > Z·h ; # CYRILLIC CAPITAL LETTER ZE"
|
39
|
+
- "зг > z·h ; # CYRILLIC SMALL LETTER ZE"
|
40
|
+
- "З > Z ; # CYRILLIC CAPITAL LETTER ZE"
|
41
|
+
- "з > z ; # CYRILLIC SMALL LETTER ZE"
|
42
|
+
- "І > I ; # CYRILLIC CAPITAL LETTER BYELORUSSIAN-UKRAINIAN I"
|
43
|
+
- "і > i ; # CYRILLIC SMALL LETTER BYELORUSSIAN-UKRAINIAN I"
|
44
|
+
- "Й > Y ; # CYRILLIC CAPITAL LETTER I"
|
45
|
+
- "й > y ; # CYRILLIC SMALL LETTER I"
|
46
|
+
- "КГ > K·H ; # CYRILLIC CAPITAL LETTER KA"
|
47
|
+
- "Кг > K·h ; # CYRILLIC CAPITAL LETTER KA"
|
48
|
+
- "кг > k·h ; # CYRILLIC SMALL LETTER KA"
|
49
|
+
- "К > K ; # CYRILLIC CAPITAL LETTER KA"
|
50
|
+
- "к > k ; # CYRILLIC SMALL LETTER KA"
|
51
|
+
- "Л > L ; # CYRILLIC CAPITAL LETTER EL"
|
52
|
+
- "л > l ; # CYRILLIC SMALL LETTER EL"
|
53
|
+
- "М > M ; # CYRILLIC CAPITAL LETTER EM"
|
54
|
+
- "м > m ; # CYRILLIC SMALL LETTER EM"
|
55
|
+
- "Н > N ; # CYRILLIC CAPITAL LETTER EN"
|
56
|
+
- "н > n ; # CYRILLIC SMALL LETTER EN"
|
57
|
+
- "О > O ; # CYRILLIC CAPITAL LETTER O"
|
58
|
+
- "о > o ; # CYRILLIC SMALL LETTER O"
|
59
|
+
- "П > P ; # CYRILLIC CAPITAL LETTER PE"
|
60
|
+
- "п > p ; # CYRILLIC SMALL LETTER PE"
|
61
|
+
- "Р > R ; # CYRILLIC CAPITAL LETTER ER"
|
62
|
+
- "р > r ; # CYRILLIC SMALL LETTER ER"
|
63
|
+
- "СГ > S·H ; # CYRILLIC CAPITAL LETTER ES"
|
64
|
+
- "Сг > S·h ; # CYRILLIC CAPITAL LETTER ES"
|
65
|
+
- "сг > s·h ; # CYRILLIC SMALL LETTER ES"
|
66
|
+
- "С > S ; # CYRILLIC CAPITAL LETTER ES"
|
67
|
+
- "с > s ; # CYRILLIC SMALL LETTER ES"
|
68
|
+
- "ТС > T·S ; # CYRILLIC CAPITAL LETTER TE"
|
69
|
+
- "Тс > T·s ; # CYRILLIC CAPITAL LETTER TE"
|
70
|
+
- "тс > t·s ; # CYRILLIC SMALL LETTER TE"
|
71
|
+
- "Т > T ; # CYRILLIC CAPITAL LETTER TE"
|
72
|
+
- "т > t ; # CYRILLIC SMALL LETTER TE"
|
73
|
+
- "У > U ; # CYRILLIC CAPITAL LETTER U"
|
74
|
+
- "у > u ; # CYRILLIC SMALL LETTER U"
|
75
|
+
- "Ў > W ; # CYRILLIC CAPITAL LETTER SHORT U"
|
76
|
+
- "ў > w ; # CYRILLIC SMALL LETTER SHORT U"
|
77
|
+
- "Ф > F ; # CYRILLIC CAPITAL LETTER EF"
|
78
|
+
- "ф > f ; # CYRILLIC SMALL LETTER EF"
|
79
|
+
- "Х} $lower > Kh ; # CYRILLIC CAPITAL LETTER HA"
|
80
|
+
- "Х > KH ; # CYRILLIC CAPITAL LETTER HA"
|
81
|
+
- "х > kh ; # CYRILLIC SMALL LETTER HA"
|
82
|
+
- "ЦГ > TS·H ; # CYRILLIC CAPITAL LETTER TSE"
|
83
|
+
- "Цг > Ts·h ; # CYRILLIC CAPITAL LETTER TSE"
|
84
|
+
- "цг > ts·h ; # CYRILLIC SMALL LETTER TSE"
|
85
|
+
- "Ц} $lower > Ts ; # CYRILLIC CAPITAL LETTER TSE"
|
86
|
+
- "Ц > TS ; # CYRILLIC CAPITAL LETTER TSE"
|
87
|
+
- "ц > ts ; # CYRILLIC SMALL LETTER TSE"
|
88
|
+
- "Ч} $lower > Ch ; # CYRILLIC CAPITAL LETTER CHE"
|
89
|
+
- "Ч > CH ; # CYRILLIC CAPITAL LETTER CHE"
|
90
|
+
- "ч > ch ; # CYRILLIC SMALL LETTER CHE"
|
91
|
+
- "Ы > Y ; # CYRILLIC CAPITAL LETTER YERU"
|
92
|
+
- "ы > y ; # CYRILLIC SMALL LETTER YERU"
|
93
|
+
- "Ь > $prime ; # CYRILLIC CAPITAL LETTER SOFT SIGN"
|
94
|
+
- "ь > $prime ; # CYRILLIC SMALL LETTER SOFT SIGN"
|
95
|
+
- "Э > E ; # CYRILLIC CAPITAL LETTER E"
|
96
|
+
- "э > e ; # CYRILLIC SMALL LETTER E"
|
97
|
+
- "Ю} $lower > Yu ; # CYRILLIC CAPITAL LETTER YU"
|
98
|
+
- "Ю > YU ; # CYRILLIC CAPITAL LETTER YU"
|
99
|
+
- "ю > yu ; # CYRILLIC SMALL LETTER YU"
|
100
|
+
- "Я} $lower > Ya ; # CYRILLIC CAPITAL LETTER YA"
|
101
|
+
- "Я > YA ; # CYRILLIC CAPITAL LETTER YA"
|
102
|
+
- "я > ya ; # CYRILLIC SMALL LETTER YA"
|
103
|
+
- "’ > $doublePrime ; # LEFT SINGLE QUOTATION MARK"
|
104
|
+
- "Ґ > G ; # CYRILLIC CAPITAL LETTER GHE WITH UPTURN"
|
105
|
+
- "ґ > g ; # CYRILLIC SMALL LETTER GHE WITH UPTURN"
|
106
|
+
:source: be
|
107
|
+
:target: be_Latn
|
108
|
+
:variant: BGN
|
@@ -0,0 +1,99 @@
|
|
1
|
+
---
|
2
|
+
:transforms:
|
3
|
+
-
|
4
|
+
:direction: forward
|
5
|
+
:rules:
|
6
|
+
- ":: [АБВГДЕЖЗИЙКЛМНОПРСТУФХЦЧШЩЪЬЮЯѪѢабвгдежзийклмнопрстуфхцчшщъьюяѫѣ] ;"
|
7
|
+
- ":: NFD (NFC) ;"
|
8
|
+
- "$upperConsonants = [БВГДЖЗЙКЛМНПРСТФХЦЧШЩЬ] ;"
|
9
|
+
- "$lowerConsonants = [бвгджзйклмнпрстфхцчшщь] ;"
|
10
|
+
- "$consonants = [$upperConsonants $lowerConsonants] ;"
|
11
|
+
- "$upperVowels = [АЕИОУЪЮЯѪѢ] ;"
|
12
|
+
- "$lowerVowels = [аеиоуъюяѫѣ] ;"
|
13
|
+
- "$vowels = [$upperVowels $lowerVowels] ;"
|
14
|
+
- "$lower = [$lowerConsonants $lowerVowels] ;"
|
15
|
+
- "$bulgarian = [ $lower $upperConsonants $upperVowels ] ;"
|
16
|
+
- "$wordBoundary = [^[:L:][:M:][:N:]] ;"
|
17
|
+
- "А > A ; # CYRILLIC CAPITAL LETTER A"
|
18
|
+
- "а > a ; # CYRILLIC SMALL LETTER A"
|
19
|
+
- "Б > B ; # CYRILLIC CAPITAL LETTER BE"
|
20
|
+
- "б > b ; # CYRILLIC SMALL LETTER BE"
|
21
|
+
- "В > V ; # CYRILLIC CAPITAL LETTER VE"
|
22
|
+
- "в > v ; # CYRILLIC SMALL LETTER VE"
|
23
|
+
- "Г > G ; # CYRILLIC CAPITAL LETTER GHE"
|
24
|
+
- "г > g ; # CYRILLIC SMALL LETTER GHE"
|
25
|
+
- "Д > D ; # CYRILLIC CAPITAL LETTER DE"
|
26
|
+
- "д > d ; # CYRILLIC SMALL LETTER DE"
|
27
|
+
- "Е > E ; # CYRILLIC CAPITAL LETTER DE"
|
28
|
+
- "е > e ; # CYRILLIC SMALL LETTER DE"
|
29
|
+
- "Ж} $lower > Zh ; # CYRILLIC CAPITAL LETTER ZHE"
|
30
|
+
- "Ж > ZH ; # CYRILLIC CAPITAL LETTER ZHE"
|
31
|
+
- "ж > zh ; # CYRILLIC SMALL LETTER ZHE"
|
32
|
+
- "З > Z ; # CYRILLIC CAPITAL LETTER ZE"
|
33
|
+
- "з > z ; # CYRILLIC SMALL LETTER ZE"
|
34
|
+
- "И > I ; # CYRILLIC CAPITAL LETTER I"
|
35
|
+
- "и > i ; # CYRILLIC SMALL LETTER I"
|
36
|
+
- "Й > Y ; # CYRILLIC CAPITAL LETTER I"
|
37
|
+
- "й > y ; # CYRILLIC SMALL LETTER I"
|
38
|
+
- "К > K ; # CYRILLIC CAPITAL LETTER KA"
|
39
|
+
- "к > k ; # CYRILLIC SMALL LETTER KA"
|
40
|
+
- "Л > L ; # CYRILLIC CAPITAL LETTER EL"
|
41
|
+
- "л > l ; # CYRILLIC SMALL LETTER EL"
|
42
|
+
- "М > M ; # CYRILLIC CAPITAL LETTER EM"
|
43
|
+
- "м > m ; # CYRILLIC SMALL LETTER EM"
|
44
|
+
- "Н > N ; # CYRILLIC CAPITAL LETTER EN"
|
45
|
+
- "н > n ; # CYRILLIC SMALL LETTER EN"
|
46
|
+
- "О > O ; # CYRILLIC CAPITAL LETTER O"
|
47
|
+
- "о > o ; # CYRILLIC SMALL LETTER O"
|
48
|
+
- "П > P ; # CYRILLIC CAPITAL LETTER PE"
|
49
|
+
- "п > p ; # CYRILLIC SMALL LETTER PE"
|
50
|
+
- "Р > R ; # CYRILLIC CAPITAL LETTER ER"
|
51
|
+
- "р > r ; # CYRILLIC SMALL LETTER ER"
|
52
|
+
- "С > S ; # CYRILLIC CAPITAL LETTER ES"
|
53
|
+
- "с > s ; # CYRILLIC SMALL LETTER ES"
|
54
|
+
- "ТС > T·S ; # CYRILLIC CAPITAL LETTER TE"
|
55
|
+
- "Тс > T·s ; # CYRILLIC CAPITAL LETTER TE"
|
56
|
+
- "тс > t·s ; # CYRILLIC SMALL LETTER TE"
|
57
|
+
- "Т > T ; # CYRILLIC CAPITAL LETTER TE"
|
58
|
+
- "т > t ; # CYRILLIC SMALL LETTER TE"
|
59
|
+
- "У > U ; # CYRILLIC CAPITAL LETTER U"
|
60
|
+
- "у > u ; # CYRILLIC SMALL LETTER U"
|
61
|
+
- "Ф > F ; # CYRILLIC CAPITAL LETTER EF"
|
62
|
+
- "ф > f ; # CYRILLIC SMALL LETTER EF"
|
63
|
+
- "Х} $lower > Kh ; # CYRILLIC CAPITAL LETTER HA"
|
64
|
+
- "Х > KH ; # CYRILLIC CAPITAL LETTER HA"
|
65
|
+
- "х > kh ; # CYRILLIC SMALL LETTER HA"
|
66
|
+
- "Ц} $lower > Ts ; # CYRILLIC CAPITAL LETTER TSE"
|
67
|
+
- "Ц > TS ; # CYRILLIC CAPITAL LETTER TSE"
|
68
|
+
- "ц > ts ; # CYRILLIC SMALL LETTER TSE"
|
69
|
+
- "Ч} $lower > Ch ; # CYRILLIC CAPITAL LETTER CHE"
|
70
|
+
- "Ч > CH ; # CYRILLIC CAPITAL LETTER CHE"
|
71
|
+
- "ч > ch ; # CYRILLIC SMALL LETTER CHE"
|
72
|
+
- "ШТ > SH·T ; # CYRILLIC CAPITAL LETTER SHA"
|
73
|
+
- "Шт > Sh·t ; # CYRILLIC CAPITAL LETTER SHA"
|
74
|
+
- "шт > sh·t ; # CYRILLIC SMALL LETTER SHA"
|
75
|
+
- "Ш} $lower > Sh ; # CYRILLIC CAPITAL LETTER SHA"
|
76
|
+
- "Ш > SH ; # CYRILLIC CAPITAL LETTER SHA"
|
77
|
+
- "ш > sh ; # CYRILLIC SMALL LETTER SHA"
|
78
|
+
- "Щ} $lower > Sht ; # CYRILLIC CAPITAL LETTER SHCHA"
|
79
|
+
- "Щ > SHT ; # CYRILLIC CAPITAL LETTER SHCHA"
|
80
|
+
- "щ > sht ; # CYRILLIC SMALL LETTER SHCHA"
|
81
|
+
- "Ъ > Ŭ ; # CYRILLIC CAPITAL LETTER HARD SIGN"
|
82
|
+
- "ъ > ŭ ; # CYRILLIC SMALL LETTER HARD SIGN"
|
83
|
+
- "$bulgarian { [Ъъ] } $wordBoundary > ;"
|
84
|
+
- "Ь > ’ ; # CYRILLIC CAPITAL LETTER SOFT SIGN"
|
85
|
+
- "ь > ’ ; # CYRILLIC SMALL LETTER SOFT SIGN"
|
86
|
+
- "Ю} $lower > Yu ; # CYRILLIC CAPITAL LETTER YU"
|
87
|
+
- "Ю > YU ; # CYRILLIC CAPITAL LETTER YU"
|
88
|
+
- "ю > yu ; # CYRILLIC SMALL LETTER YU"
|
89
|
+
- "Я} $lower > Ya ; # CYRILLIC CAPITAL LETTER YA"
|
90
|
+
- "Я > YA ; # CYRILLIC CAPITAL LETTER YA"
|
91
|
+
- "я > ya ; # CYRILLIC SMALL LETTER YA"
|
92
|
+
- "Ѫ > Ŭ ; # CYRILLIC CAPITAL LETTER BIG YUS"
|
93
|
+
- "ѫ > ŭ ; # CYRILLIC SMALL LETTER BIG YUS"
|
94
|
+
- "Ѣ} $lower > Ye ; # CYRILLIC CAPITAL LETTER YAT"
|
95
|
+
- "Ѣ > YE ; # CYRILLIC CAPITAL LETTER YAT"
|
96
|
+
- "ѣ > ye ; # CYRILLIC SMALL LETTER YAT"
|
97
|
+
:source: bg
|
98
|
+
:target: bg_Latn
|
99
|
+
:variant: BGN
|
@@ -3,16 +3,12 @@
|
|
3
3
|
-
|
4
4
|
:direction: forward
|
5
5
|
:rules:
|
6
|
-
- ""
|
7
6
|
- "::Lower;"
|
8
7
|
- "::NFC;"
|
9
|
-
- ""
|
10
8
|
- "\\' > ʔ;"
|
11
9
|
- "’ > ʔ;"
|
12
|
-
- ""
|
13
10
|
- "a > æ;"
|
14
11
|
- "å > ɑ;"
|
15
|
-
- ""
|
16
12
|
- "b > b;"
|
17
13
|
- "ch > t͡s;"
|
18
14
|
- "{c} [eéií] > θ; # loanwords"
|
@@ -45,11 +41,8 @@
|
|
45
41
|
- "{x} h?[aáåeéiíoóuú$] > ks; # loanwords"
|
46
42
|
- "{x} [^aáåeéiíoóuú$] > s; # loanwords"
|
47
43
|
- "x > ks ; # loanwords"
|
48
|
-
- ""
|
49
44
|
- "y > d͡z;"
|
50
|
-
- ""
|
51
45
|
- "\\- > \\.; # hyphen is a syllable boundary, eg ‹sena-ta›"
|
52
|
-
- ""
|
53
46
|
- "::Null;"
|
54
47
|
- "bb > bː;"
|
55
48
|
- "dd > dː;"
|
@@ -64,7 +57,6 @@
|
|
64
57
|
- "rr > rː;"
|
65
58
|
- "ss > sː;"
|
66
59
|
- "tt > tː;"
|
67
|
-
- ""
|
68
60
|
- "::NFC;"
|
69
61
|
:source: ch
|
70
62
|
:target: ch_FONIPA
|
@@ -3,10 +3,8 @@
|
|
3
3
|
-
|
4
4
|
:direction: forward
|
5
5
|
:rules:
|
6
|
-
- ""
|
7
6
|
- "::NFC;"
|
8
7
|
- "::Lower;"
|
9
|
-
- ""
|
10
8
|
- "a > a ;"
|
11
9
|
- "b́ > bʲ ; # old spelling"
|
12
10
|
- "bj > bʲ ; # modern spelling"
|
@@ -52,13 +50,10 @@
|
|
52
50
|
- "ž > ʒ ;"
|
53
51
|
- "ź > ʑ ;"
|
54
52
|
- "z > z ;"
|
55
|
-
- ""
|
56
53
|
- "::NFC;"
|
57
|
-
- ""
|
58
54
|
- "b } [k] > p ;"
|
59
55
|
- "d } [k] > t ;"
|
60
56
|
- "ʃt͡ɕ > ɕt͡ɕ ;"
|
61
|
-
- ""
|
62
57
|
- "b } [$] > p ;"
|
63
58
|
- "d \\u0361 z } [$] > t \\u0361 s ;"
|
64
59
|
- "d } [$] > t ;"
|
@@ -0,0 +1,112 @@
|
|
1
|
+
---
|
2
|
+
:transforms:
|
3
|
+
-
|
4
|
+
:direction: forward
|
5
|
+
:rules:
|
6
|
+
- "::[[:block=thaana:]\\uFDF2] ;"
|
7
|
+
- ":: NFD (NFC) ;"
|
8
|
+
- "$wordBoundary = [^[:L:][:M:][:N:]] ;"
|
9
|
+
- "$vowel = [\\u07A6-\\u07AF] ;"
|
10
|
+
- "$sukun = \\u07B0 ;"
|
11
|
+
- "$sign = [$sukun $vowel] ;"
|
12
|
+
- "$rule4 = [އށ] $sukun ; # see note 4"
|
13
|
+
- "$rule4 ހ > hh ;"
|
14
|
+
- "ހ > h ;"
|
15
|
+
- "$rule4 ނ } $sign > nn ;"
|
16
|
+
- "$rule4 ނ > nn\\' ;"
|
17
|
+
- "ނ } $sign > n ;"
|
18
|
+
- "ނ > n\\' ;"
|
19
|
+
- "$rule4 ރ > rr ;"
|
20
|
+
- "ރ > r ;"
|
21
|
+
- "$rule4 ބ > bb ;"
|
22
|
+
- "ބ > b ;"
|
23
|
+
- "$rule4 ޅ > hlh ;"
|
24
|
+
- "ޅ > lh;"
|
25
|
+
- "$rule4 ކ > kk ;"
|
26
|
+
- "ކ > k ;"
|
27
|
+
- "$rule4 ވ > vv ;"
|
28
|
+
- "ވ > v ;"
|
29
|
+
- "$rule4 މ > mm ;"
|
30
|
+
- "މ > m ;"
|
31
|
+
- "$rule4 ފ > ff ;"
|
32
|
+
- "ފ > f;"
|
33
|
+
- "$rule4 ދ > hdh ;"
|
34
|
+
- "ދ > dh;"
|
35
|
+
- "$rule4 ތ $sukun > hiy ;"
|
36
|
+
- "$rule4 ތ > hth ;"
|
37
|
+
- "ި ތ $sukun > iy ;"
|
38
|
+
- "ތ $sukun > iy ;"
|
39
|
+
- "ތ > th ;"
|
40
|
+
- "$rule4 ލ > ll ;"
|
41
|
+
- "ލ > l ;"
|
42
|
+
- "$rule4 ގ > gg ;"
|
43
|
+
- "ގ > g ;"
|
44
|
+
- "$rule4 ޏ > hgn ;"
|
45
|
+
- "ޏ > gn ;"
|
46
|
+
- "$rule4 ސ > ss ;"
|
47
|
+
- "ސ > s ;"
|
48
|
+
- "$rule4 ޑ > dd ;"
|
49
|
+
- "ޑ > d ;"
|
50
|
+
- "$rule4 ޒ > zz ;"
|
51
|
+
- "ޒ > z ;"
|
52
|
+
- "$rule4 ޓ > tt ;"
|
53
|
+
- "ޓ > t ;"
|
54
|
+
- "$rule4 ޔ > yy ;"
|
55
|
+
- "ޔ > y ;"
|
56
|
+
- "$rule4 ޕ > pp ;"
|
57
|
+
- "ޕ > p ;"
|
58
|
+
- "$rule4 ޖ > jj ;"
|
59
|
+
- "ޖ > j ;"
|
60
|
+
- "$rule4 ޗ > hch ;"
|
61
|
+
- "ޗ > ch ;"
|
62
|
+
- "$rule4 ޞ > şş ;"
|
63
|
+
- "ޞ > ş ;"
|
64
|
+
- "$rule4 ޝ > hsh ;"
|
65
|
+
- "ޝ > sh ;"
|
66
|
+
- "$rule4 ޜ > zz ;"
|
67
|
+
- "ޜ > z;"
|
68
|
+
- "$rule4 ޚ > hkh ;"
|
69
|
+
- "ޚ > kh;"
|
70
|
+
- "$rule4 ޙ > ḩḩ ;"
|
71
|
+
- "ޙ > ḩ ;"
|
72
|
+
- "$rule4 ޛ > hdh ;"
|
73
|
+
- "ޛ > dh ;"
|
74
|
+
- "$rule4 ޘ > hth ;"
|
75
|
+
- "ޘ > th ;"
|
76
|
+
- "$rule4 ޥ > ww ;"
|
77
|
+
- "ޥ > w ;"
|
78
|
+
- "$rule4 ޤ > qq ;"
|
79
|
+
- "ޤ > q ;"
|
80
|
+
- "$rule4 ޣ > hgh ;"
|
81
|
+
- "ޣ > gh ;"
|
82
|
+
- "$rule4 ޢ > \\'\\' ;"
|
83
|
+
- "ޢ > \\' ;"
|
84
|
+
- "$rule4 ޡ > z̧z̧ ;"
|
85
|
+
- "ޡ > z̧ ;"
|
86
|
+
- "$rule4 ޠ > ţţ ;"
|
87
|
+
- "ޠ > ţ ;"
|
88
|
+
- "$rule4 ޟ > ḑḑ ;"
|
89
|
+
- "ޟ > ḑ ;"
|
90
|
+
- "$rule4 ޱ > n̲n̲ ;"
|
91
|
+
- "ޱ > n̲ ;"
|
92
|
+
- "$rule4 } $wordBoundary > h;"
|
93
|
+
- "$rule4 ށ > hsh;"
|
94
|
+
- "ށ > sh;"
|
95
|
+
- "$rule4 > ;"
|
96
|
+
- "ް > ;"
|
97
|
+
- "އ > ;"
|
98
|
+
- "($vowel) \\uFDF2 > | $1 llāh ;"
|
99
|
+
- "\\uFDF2 > allāh;"
|
100
|
+
- "ަ > a; # ABAFILI"
|
101
|
+
- "ާ > aa; # AABAAFILI"
|
102
|
+
- "ެ > e; # EBEFILI"
|
103
|
+
- "ޭ > ey; # EYBEYFILI"
|
104
|
+
- "ި > i; # IBIFILI"
|
105
|
+
- "ީ > ee; # EEBEEFILI"
|
106
|
+
- "ޮ > o; # OBOFILI"
|
107
|
+
- "ޯ > oa; # OABOAFILI"
|
108
|
+
- "ު > u; # UBUFILI"
|
109
|
+
- "ޫ > oo; # OOBOOFILI"
|
110
|
+
:source: dv
|
111
|
+
:target: dv_Latn
|
112
|
+
:variant: BGN
|