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 +1,208 @@
|
|
1
|
+
---
|
2
|
+
:transforms:
|
3
|
+
-
|
4
|
+
:direction: forward
|
5
|
+
:rules:
|
6
|
+
- ":: [ΆΈΉΊΌΎΏΐΑΒΓΔΕΖΗΘΙΚΛΜΝΞΟΠΡΣΤΥΦΧΨΩΪΫάέήίΰαβγδεζηθικλμνξοπρςστυφχψωϊϋόύώἀἁἂἃἄἅἆἇἈἉἊἋἌἍἎἏἐἑἒἓἔἕἘἙἚἛἜἝἠἡἢἣἤἥἦἧἨἩἪἫἬἭἮἯἰἱἲἳἴἵἶἷἸἹἺἻἼἽἾἿὀὁὂὃὄὅὈὉὊὋὌὍὐὑὒὓὔὕὖὗὙὛὝὟὠὡὢὣὤὥὦὧὨὩὫὬὭὮὯὰάὲέὴήὶίὸόὺύὼώᾀᾁᾂᾃᾄᾅᾆᾇᾈᾉᾊᾋᾌᾍᾎᾏᾐᾑᾒᾓᾔᾕᾖᾗᾘᾙᾚᾛᾜᾝᾞᾟᾠᾡᾢᾣᾤᾥᾦᾧᾨᾩᾪᾫᾬᾭᾮᾯᾲᾳᾴᾶᾷᾺΆᾼῂῃῄῆῇῈΈῊΉῌῖῚΊῤῥῦῪΎῲῳῴῶῷῸΌῺΏῼ῾] ;"
|
7
|
+
- ":: NFD (NFC) ;"
|
8
|
+
- "$upperConsonants = [ΒΓΔΖΘΚΛΜΝΞΠΡΣΤΦΧΨ] ;"
|
9
|
+
- "$lowerConsonants = [βγδζθκλμνξπρσςτφχψ] ;"
|
10
|
+
- "$consonants = [$upperConsonants $lowerConsonants] ;"
|
11
|
+
- "$upperVowels = [ΑΕΗΙΟΥΩ] ;"
|
12
|
+
- "$lowerVowels = [αεηιουω] ;"
|
13
|
+
- "$vowels = [$upperVowels $lowerVowels] ;"
|
14
|
+
- "$lower = [$lowerConsonants $lowerVowels] ;"
|
15
|
+
- "$wordBoundary = [^[:L:][:M:][:N:]] ;"
|
16
|
+
- "[ἈἉᾼᾈᾉ] > Α ; # GREEK CAPITAL LETTER ALPHA"
|
17
|
+
- "[ἀἁᾳᾀᾁ] > α ; # GREEK SMALL LETTER ALPHA"
|
18
|
+
- "[ἊἋἌἍἎἏᾊᾋᾌᾍᾎᾏᾺΆ] > Ά ; # GREEK CAPITAL LETTER ALPHA WITH TONOS"
|
19
|
+
- "[ἂἃἄἅἆἇὰάᾂᾃᾄᾅᾆᾇᾲᾴᾶᾷ] > ά ; # GREEK SMALL LETTER ALPHA WITH TONOS"
|
20
|
+
- "[ἘἙ] > Ε ; # GREEK CAPITAL LETTER EPSILON"
|
21
|
+
- "[ἐἑὲέ] > ε ; # GREEK SMALL LETTER EPSILON"
|
22
|
+
- "[ἚἛἜἝῈΈ] > Έ ; # GREEK CAPITAL LETTER EPSILON WITH TONOS"
|
23
|
+
- "[ἒἓἔἕ] > έ ; # GREEK SMALL LETTER EPSILON WITH TONOS"
|
24
|
+
- "[ἨἩᾘᾙῌ] > Η ; # GREEK CAPITAL LETTER ETA"
|
25
|
+
- "[ἠἡᾐᾑῃ] > η ; # GREEK SMALL LETTER ETA"
|
26
|
+
- "[ἪἫἬἭἮἯᾚᾛᾜᾝᾞᾟῊΉ] > Ή ; # GREEK CAPITAL LETTER ETA WITH TONOS"
|
27
|
+
- "[ἢἣἤἥἦἧὴήᾒᾓᾔᾕᾖᾗῂῄῆῇ] > ή ; # GREEK SMALL LETTER ETA WITH TONOS"
|
28
|
+
- "[ἸἹ] > Ι ; # GREEK CAPITAL LETTER IOTA"
|
29
|
+
- "[ἰἱ] > ι ; # GREEK SMALL LETTER IOTA"
|
30
|
+
- "[ἺἻἼἽἾἿῚΊ] > Ί ; # GREEK CAPITAL LETTER IOTA WITH TONOS"
|
31
|
+
- "[ἲἳἴἵἶἷὶίῖ] > ί ; # GREEK SMALL LETTER IOTA WITH TONOS"
|
32
|
+
- "[ὈὉ] > Ο ; # GREEK CAPITAL LETTER OMICRON"
|
33
|
+
- "[ὀὁ] > ο ; # GREEK SMALL LETTER OMICRON"
|
34
|
+
- "[ὊὋὌὍῸΌ] > Ό ; # GREEK CAPITAL LETTER OMICRON WITH TONOS"
|
35
|
+
- "[ὂὃὄὅὸό] > ό ; # GREEK SMALL LETTER OMICRON WITH TONOS"
|
36
|
+
- "Ὑ > Υ ; # GREEK CAPITAL LETTER UPSILON"
|
37
|
+
- "[ὐὑ] > υ ; # GREEK SMALL LETTER UPSILON"
|
38
|
+
- "[ὛὝὟῪΎ] > Ύ ; # GREEK CAPITAL LETTER UPSILON WITH TONOS"
|
39
|
+
- "[ὒὓὔὕὖὗὺύῦ] > ύ ; # GREEK SMALL LETTER UPSILON WITH TONOS"
|
40
|
+
- "[ὨὩᾨᾩῼ] > Ω ; # GREEK CAPITAL LETTER OMEGA"
|
41
|
+
- "[ὠὡᾠᾡῳ] > ω ; # GREEK SMALL LETTER OMEGA"
|
42
|
+
- "[ὬὫὬὭὮὯᾪᾫᾬᾭᾮᾯῺΏ] > Ώ ; # GREEK CAPITAL LETTER OMEGA WITH TONOS"
|
43
|
+
- "[ὢὣὤὥὦὧὼώᾢᾣᾤᾥᾦᾧῲῴῶῷ] > ώ ; # GREEK SMALL LETTER OMEGA WITH TONOS"
|
44
|
+
- "Ῥ > Ρ ; # GREEK CAPITAL LETTER RHO"
|
45
|
+
- "[ῤῥ] > ρ ; # GREEK SMALL LETTER RHO"
|
46
|
+
- "Αί > Aí ;"
|
47
|
+
- "αί > aí ;"
|
48
|
+
- "Οί > Oí ;"
|
49
|
+
- "οί > Oí ;"
|
50
|
+
- "Ού > Oú ;"
|
51
|
+
- "ού > oú ;"
|
52
|
+
- "Αύ > Άυ ;"
|
53
|
+
- "αύ > άυ ;"
|
54
|
+
- "Εύ > Έυ ;"
|
55
|
+
- "εύ > έυ ;"
|
56
|
+
- "Ηύ > Ήυ ;"
|
57
|
+
- "ηύ > ήυ ;"
|
58
|
+
- "[ΪΫ] > Ï ;"
|
59
|
+
- "[ϊϋ] > ï ;"
|
60
|
+
- "[ΐΰ] > ḯ ;"
|
61
|
+
- "Αε > Aë ;"
|
62
|
+
- "αε > aë ;"
|
63
|
+
- "Αη > Aï ;"
|
64
|
+
- "αη > aï ;"
|
65
|
+
- "Οη > Oï ;"
|
66
|
+
- "οη > oï ;"
|
67
|
+
- "Ωο > Oö ;"
|
68
|
+
- "ωο > oö ;"
|
69
|
+
- "Άε > Áë ;"
|
70
|
+
- "άε > áë ;"
|
71
|
+
- "Άη > Áï ;"
|
72
|
+
- "άη > áï ;"
|
73
|
+
- "Όη > Óï ;"
|
74
|
+
- "όη > óï ;"
|
75
|
+
- "Ώο > Óö ;"
|
76
|
+
- "ώο > óö ;"
|
77
|
+
- "ΑΙ > AI ; # GREEK CAPITAL LETTER ALPHA + CAPITAL IOTA"
|
78
|
+
- "Αι > Ai ; # GREEK CAPITAL LETTER ALPHA + SMALL IOTA"
|
79
|
+
- "αι > ai ; # GREEK SMALL LETTER ALPHA + SMALL IOTA"
|
80
|
+
- "ΑΥ > AV ; # GREEK CAPITAL LETTER ALPHA + CAPITAL UPSILON"
|
81
|
+
- "Αυ > Av ; # GREEK CAPITAL LETTER ALPHA + SMALL UPSILON"
|
82
|
+
- "αυ > av ; # GREEK SMALL LETTER ALPHA + SMALL UPSILON"
|
83
|
+
- "Α > A ; # GREEK CAPITAL LETTER ALPHA"
|
84
|
+
- "α > a ; # GREEK SMALL LETTER ALPHA"
|
85
|
+
- "Ά > Á ; # GREEK CAPITAL LETTER ALPHA WITH TONOS"
|
86
|
+
- "ά > á ; # GREEK SMALL LETTER ALPHA WITH TONOS"
|
87
|
+
- "Β > V ; # GREEK CAPITAL LETTER BETA"
|
88
|
+
- "β > v ; # GREEK SMALL LETTER BETA"
|
89
|
+
- "ΓΓ > NG ; # GREEK CAPITAL LETTER GAMMA + CAPITAL GAMMA"
|
90
|
+
- "Γγ > Ng ; # GREEK CAPITAL LETTER GAMMA + SMALL GAMMA"
|
91
|
+
- "γγ > ng ; # GREEK SMALL LETTER GAMMA + SMALL GAMMA"
|
92
|
+
- "$wordBoundary{ΓΚ > G ; # GREEK CAPITAL LETTER GAMMA + CAPITAL KAPPA"
|
93
|
+
- "$wordBoundary{Γκ > G ; # GREEK CAPITAL LETTER GAMMA + SMALL KAPPA"
|
94
|
+
- "$wordBoundary{γκ > g ; # GREEK SMALL LETTER GAMMA + SMALL KAPPA"
|
95
|
+
- "ΓΚ > NG ; # GREEK CAPITAL LETTER GAMMA + CAPITAL KAPPA"
|
96
|
+
- "Γκ > Ng ; # GREEK CAPITAL LETTER GAMMA + SMALL KAPPA"
|
97
|
+
- "γκ > ng ; # GREEK SMALL LETTER GAMMA + SMALL KAPPA"
|
98
|
+
- "Γ}[ΑΟΩ [$upperConsonants - [ΓΞΧ]]] > G ; # GREEK CAPITAL LETTER GAMMA"
|
99
|
+
- "Γ}[αοω [$lowerConsonants - [γξχ]]] > G ; # GREEK CAPITAL LETTER GAMMA"
|
100
|
+
- "Γ}ΟΥ > G ; # GREEK CAPITAL LETTER GAMMA"
|
101
|
+
- "Γ}ου > G ; # GREEK CAPITAL LETTER GAMMA"
|
102
|
+
- "γ}[αοω [$lowerConsonants - [γξχ]]] > g ; # GREEK SMALL LETTER GAMMA"
|
103
|
+
- "γ}ου > g ; # GREEK SMALL LETTER GAMMA"
|
104
|
+
- "Γ}[ΑΕΟΥ]Ι > Y ; # GREEK CAPITAL LETTER GAMMA"
|
105
|
+
- "Γ}[ΕΗΙΥ] > Y ; # GREEK CAPITAL LETTER GAMMA"
|
106
|
+
- "Γ}[αεου]ι > Y ; # GREEK CAPITAL LETTER GAMMA"
|
107
|
+
- "Γ}[εηιυ] > Y ; # GREEK CAPITAL LETTER GAMMA"
|
108
|
+
- "γ}[αεου]ι > y ; # GREEK SMALL LETTER GAMMA"
|
109
|
+
- "γ}[εηιυ] > y ; # GREEK SMALL LETTER GAMMA"
|
110
|
+
- "Γ}[ΞΧ] > N ; # GREEK CAPITAL LETTER GAMMA"
|
111
|
+
- "Γ}[ξχ] > N ; # GREEK CAPITAL LETTER GAMMA"
|
112
|
+
- "γ}[ξχ] > n ; # GREEK SMALL LETTER GAMMA"
|
113
|
+
- "Γ > G ; # GREEK CAPITAL LETTER GAMMA"
|
114
|
+
- "γ > g ; # GREEK SMALL LETTER GAMMA"
|
115
|
+
- "Ν{Δ}Ρ > D ; # GREEK CAPITAL LETTER DELTA"
|
116
|
+
- "ν{δ}ρ > d ; # GREEK SMALL LETTER GAMMA"
|
117
|
+
- "Δ} $lower > Dh ; # GREEK CAPITAL LETTER PSI"
|
118
|
+
- "Δ > DH ; # GREEK CAPITAL LETTER DELTA"
|
119
|
+
- "δ > dh ; # GREEK SMALL LETTER DELTA"
|
120
|
+
- "ΕΙ > I ; # GREEK CAPITAL LETTER EPSILON + CAPITAL IOTA"
|
121
|
+
- "Ει > I ; # GREEK CAPITAL LETTER EPSILON + SMALL IOTA"
|
122
|
+
- "ει > i ; # GREEK SMALL LETTER EPSILON + SMALL IOTA"
|
123
|
+
- "ΕΪ > EÏ ; # GREEK CAPITAL LETTER EPSILON + CAPITAL IOTA DIAERESIS"
|
124
|
+
- "Εϊ > Eï ; # GREEK CAPITAL LETTER EPSILON + SMALL IOTA DIAERESIS"
|
125
|
+
- "εϊ > eï ; # GREEK SMALL LETTER EPSILON + SMALL IOTA DIAERESIS"
|
126
|
+
- "ΕΥ > EV ; # GREEK CAPITAL LETTER EPSILON + CAPITAL UPSILON"
|
127
|
+
- "Ευ > Ev ; # GREEK CAPITAL LETTER EPSILON + SMALL UPSILON"
|
128
|
+
- "ευ > ev ; # GREEK SMALL LETTER EPSILON + SMALL UPSILON"
|
129
|
+
- "Ε > E ; # GREEK CAPITAL LETTER EPSILON"
|
130
|
+
- "ε > e ; # GREEK SMALL LETTER EPSILON"
|
131
|
+
- "Έ > É ; # GREEK CAPITAL LETTER EPSILON WITH TONOS"
|
132
|
+
- "έ > é ; # GREEK SMALL LETTER EPSILON WITH TONOS"
|
133
|
+
- "Ζ > Z ; # GREEK CAPITAL LETTER ZETA"
|
134
|
+
- "ζ > z ; # GREEK SMALL LETTER ZETA"
|
135
|
+
- "ΗΥ > IV ; # GREEK CAPITAL LETTER ALPHA + CAPITAL UPSILON"
|
136
|
+
- "Ηυ > Iv ; # GREEK CAPITAL LETTER ALPHA + SMALL UPSILON"
|
137
|
+
- "ηυ > iv ; # GREEK SMALL LETTER ALPHA + SMALL UPSILON"
|
138
|
+
- "Η > I ; # GREEK CAPITAL LETTER ETA"
|
139
|
+
- "η > i ; # GREEK SMALL LETTER ETA"
|
140
|
+
- "Ή > Í ; # GREEK CAPITAL LETTER ETA WITH TONOS"
|
141
|
+
- "ή > í ; # GREEK SMALL LETTER ETA WITH TONOS"
|
142
|
+
- "Θ} $lower > Th ; # GREEK CAPITAL LETTER THETA"
|
143
|
+
- "Θ > TH ; # GREEK CAPITAL LETTER THETA"
|
144
|
+
- "θ > th ; # GREEK SMALL LETTER THETA"
|
145
|
+
- "Ι > I ; # GREEK CAPITAL LETTER IOTA"
|
146
|
+
- "ι > i ; # GREEK SMALL LETTER IOTA"
|
147
|
+
- "Ί > Í ; # GREEK CAPITAL LETTER IOTA WITH TONOS"
|
148
|
+
- "ί > í ; # GREEK SMALL LETTER IOTA WITH TONOS"
|
149
|
+
- "Κ > K ; # GREEK CAPITAL LETTER KAPPA"
|
150
|
+
- "κ > k ; # GREEK SMALL LETTER KAPPA"
|
151
|
+
- "Λ > L ; # GREEK CAPITAL LETTER LAMDA"
|
152
|
+
- "λ > l ; # GREEK SMALL LETTER LAMDA"
|
153
|
+
- "$wordBoundary{ΜΠ > B ; # GREEK CAPITAL LETTER MU + CAPITAL PI"
|
154
|
+
- "$wordBoundary{Μπ > B ; # GREEK CAPITAL LETTER MU + SMALL PI"
|
155
|
+
- "$wordBoundary{μπ > b ; # GREEK SMALL LETTER MU + SMALL PI"
|
156
|
+
- "ΜΠ > MB ; # GREEK CAPITAL LETTER MU + CAPITAL PI"
|
157
|
+
- "Μπ > Mb ; # GREEK CAPITAL LETTER MU + SMALL PI"
|
158
|
+
- "μπ > mb ; # GREEK SMALL LETTER MU + SMALL PI"
|
159
|
+
- "Μ > M ; # GREEK CAPITAL LETTER MU"
|
160
|
+
- "μ > m ; # GREEK SMALL LETTER MU"
|
161
|
+
- "$wordBoundary{ΝΤ > D ; # GREEK CAPITAL LETTER NU + CAPITAL TAU"
|
162
|
+
- "$wordBoundary{Ντ > D ; # GREEK CAPITAL LETTER NU + SMALL TAU"
|
163
|
+
- "$wordBoundary{ντ > d ; # GREEK SMALL LETTER NU + SMALL TAU"
|
164
|
+
- "ΝΤ > ND ; # GREEK CAPITAL LETTER NU + CAPITAL TAU"
|
165
|
+
- "Ντ > Nd ; # GREEK CAPITAL LETTER NU + SMALL TAU"
|
166
|
+
- "ντ > nd ; # GREEK SMALL LETTER NU + SMALL TAU"
|
167
|
+
- "Ν > N ; # GREEK CAPITAL LETTER NU"
|
168
|
+
- "ν > n ; # GREEK SMALL LETTER NU"
|
169
|
+
- "Ξ > X ; # GREEK CAPITAL LETTER KSI"
|
170
|
+
- "ξ > x ; # GREEK SMALL LETTER KSI"
|
171
|
+
- "ΟΙ > OI ; # GREEK CAPITAL LETTER OMICRON + CAPITAL IOTA"
|
172
|
+
- "Οι > Oi ; # GREEK CAPITAL LETTER OMICRON + SMALL IOTA"
|
173
|
+
- "οι > oi ; # GREEK SMALL LETTER OMICRON + SMALL IOTA"
|
174
|
+
- "ΟΥ > OU ; # GREEK CAPITAL LETTER OMICRON + CAPITAL UPSILON"
|
175
|
+
- "Ου > Ou ; # GREEK CAPITAL LETTER OMICRON + SMALL UPSILON"
|
176
|
+
- "ου > ou ; # GREEK SMALL LETTER OMICRON + SMALL UPSILON"
|
177
|
+
- "Ο > O ; # GREEK CAPITAL LETTER OMICRON"
|
178
|
+
- "ο > o ; # GREEK SMALL LETTER OMICRON"
|
179
|
+
- "Ό > Ó ; # GREEK CAPITAL LETTER OMICRON WITH TONOS"
|
180
|
+
- "ό > ó ; # GREEK SMALL LETTER OMICRON WITH TONOS"
|
181
|
+
- "Π > P ; # GREEK CAPITAL LETTER PI"
|
182
|
+
- "π > p ; # GREEK SMALL LETTER PI"
|
183
|
+
- "Ρ > R ; # GREEK CAPITAL LETTER RHO"
|
184
|
+
- "ρ > r ; # GREEK SMALL LETTER RHO"
|
185
|
+
- "Σ > S ; # GREEK CAPITAL LETTER SIGMA"
|
186
|
+
- "σ > s ; # GREEK SMALL LETTER SIGMA"
|
187
|
+
- "ς > s ; # GREEK SMALL LETTER FINAL SIGMA"
|
188
|
+
- "Τ > T ; # GREEK CAPITAL LETTER TAU"
|
189
|
+
- "τ > t ; # GREEK SMALL LETTER TAU"
|
190
|
+
- "Υ > I ; # GREEK CAPITAL LETTER UPSILON"
|
191
|
+
- "υ > i ; # GREEK SMALL LETTER UPSILON"
|
192
|
+
- "Ύ > Í ; # GREEK CAPITAL LETTER UPSILON WITH TONOS"
|
193
|
+
- "ύ > í ; # GREEK SMALL LETTER UPSILON WITH TONOS"
|
194
|
+
- "Φ > F ; # GREEK CAPITAL LETTER PHI"
|
195
|
+
- "φ > f ; # GREEK SMALL LETTER PHI"
|
196
|
+
- "Χ} $lower > Kh ; # GREEK CAPITAL LETTER CHI"
|
197
|
+
- "Χ > KH ; # GREEK CAPITAL LETTER CHI"
|
198
|
+
- "χ > kh ; # GREEK SMALL LETTER CHI"
|
199
|
+
- "Ψ} $lower > Ps ; # GREEK CAPITAL LETTER PSI"
|
200
|
+
- "Ψ > PS ; # GREEK CAPITAL LETTER PSI"
|
201
|
+
- "ψ > ps ; # GREEK SMALL LETTER PSI"
|
202
|
+
- "Ω > O ; # GREEK CAPITAL LETTER OMEGA"
|
203
|
+
- "ω > o ; # GREEK SMALL LETTER OMEGA"
|
204
|
+
- "Ώ > Ó ; # GREEK CAPITAL LETTER OMEGA WITH TONOS"
|
205
|
+
- "ώ > ó ; # GREEK SMALL LETTER OMEGA WITH TONOS"
|
206
|
+
:source: el
|
207
|
+
:target: el_Latn
|
208
|
+
:variant: BGN
|
@@ -0,0 +1,52 @@
|
|
1
|
+
---
|
2
|
+
:transforms:
|
3
|
+
-
|
4
|
+
:direction: forward
|
5
|
+
:rules:
|
6
|
+
- "::NFC;"
|
7
|
+
- "::Lower;"
|
8
|
+
- "[\\-\\'’] > ; # eg. vorto-provizo, famili’"
|
9
|
+
- "aj > ai̯;"
|
10
|
+
- "aŭ > au̯;"
|
11
|
+
- "á > a;"
|
12
|
+
- "a > a;"
|
13
|
+
- "b > b;"
|
14
|
+
- "ĉ > t͡ʃ;"
|
15
|
+
- "c > t͡s;"
|
16
|
+
- "dz > d͡z;"
|
17
|
+
- "d > d;"
|
18
|
+
- "ej > ei̯;"
|
19
|
+
- "eŭ > eu̯;"
|
20
|
+
- "é > e;"
|
21
|
+
- "e > e;"
|
22
|
+
- "f > f;"
|
23
|
+
- "ĝ > d͡ʒ;"
|
24
|
+
- "g > ɡ;"
|
25
|
+
- "ĥ > x;"
|
26
|
+
- "h > h;"
|
27
|
+
- "í > i;"
|
28
|
+
- "i > i;"
|
29
|
+
- "ĵ > ʒ;"
|
30
|
+
- "j > j;"
|
31
|
+
- "k > k;"
|
32
|
+
- "l > l;"
|
33
|
+
- "m > m;"
|
34
|
+
- "n > n;"
|
35
|
+
- "oj > oi̯;"
|
36
|
+
- "ó > o;"
|
37
|
+
- "o > o;"
|
38
|
+
- "p > p;"
|
39
|
+
- "r > r;"
|
40
|
+
- "ŝ > ʃ;"
|
41
|
+
- "s > s;"
|
42
|
+
- "t > t;"
|
43
|
+
- "uj > ui̯;"
|
44
|
+
- "ŭ > w; # eg. ŭa!"
|
45
|
+
- "ú > u;"
|
46
|
+
- "u > u;"
|
47
|
+
- "v > v;"
|
48
|
+
- "z > z;"
|
49
|
+
- "::NFC;"
|
50
|
+
:source: eo
|
51
|
+
:target: eo_FONIPA
|
52
|
+
:variant: ~
|
@@ -0,0 +1,13 @@
|
|
1
|
+
---
|
2
|
+
:transforms:
|
3
|
+
-
|
4
|
+
:direction: forward
|
5
|
+
:rules:
|
6
|
+
- "$Boundary = [^[:L:][:M:][:N:]];"
|
7
|
+
- "$Vowel = [i e o u a];"
|
8
|
+
- "::es-es_FONIPA;"
|
9
|
+
- "$Boundary [^Vowel] {e} [^$Vowel]* $Vowel > ə;"
|
10
|
+
- "::und_FONIPA-ar;"
|
11
|
+
:source: es
|
12
|
+
:target: ar
|
13
|
+
:variant: ~
|
@@ -0,0 +1,13 @@
|
|
1
|
+
---
|
2
|
+
:transforms:
|
3
|
+
-
|
4
|
+
:direction: forward
|
5
|
+
:rules:
|
6
|
+
- "$Boundary = [^[:L:][:M:][:N:]];"
|
7
|
+
- "$Vowel = [i e o u a];"
|
8
|
+
- "::es-es_FONIPA;"
|
9
|
+
- "$Boundary [^Vowel] {e} [^$Vowel]* $Vowel > ə;"
|
10
|
+
- "::und_FONIPA-fa;"
|
11
|
+
:source: es
|
12
|
+
:target: fa
|
13
|
+
:variant: ~
|
@@ -0,0 +1,14 @@
|
|
1
|
+
---
|
2
|
+
:transforms:
|
3
|
+
-
|
4
|
+
:direction: forward
|
5
|
+
:rules:
|
6
|
+
- "$Boundary = [^[:L:][:M:][:N:]];"
|
7
|
+
- "$Vowel = [i e o u a];"
|
8
|
+
- "::es-es_FONIPA;"
|
9
|
+
- "::es_FONIPA-es_419_FONIPA;"
|
10
|
+
- "$Boundary [^Vowel] {e} [^$Vowel]* $Vowel > ə;"
|
11
|
+
- "::und_FONIPA-ar;"
|
12
|
+
:source: es_419
|
13
|
+
:target: ar
|
14
|
+
:variant: ~
|
@@ -0,0 +1,14 @@
|
|
1
|
+
---
|
2
|
+
:transforms:
|
3
|
+
-
|
4
|
+
:direction: forward
|
5
|
+
:rules:
|
6
|
+
- "$Boundary = [^[:L:][:M:][:N:]];"
|
7
|
+
- "$Vowel = [i e o u a];"
|
8
|
+
- "::es-es_FONIPA;"
|
9
|
+
- "::es_FONIPA-es_419_FONIPA;"
|
10
|
+
- "$Boundary [^Vowel] {e} [^$Vowel]* $Vowel > ə;"
|
11
|
+
- "::und_FONIPA-fa;"
|
12
|
+
:source: es_419
|
13
|
+
:target: fa
|
14
|
+
:variant: ~
|
@@ -0,0 +1,123 @@
|
|
1
|
+
---
|
2
|
+
:transforms:
|
3
|
+
-
|
4
|
+
:direction: forward
|
5
|
+
:rules:
|
6
|
+
- ":: [[:arabic:][:block=ARABIC:][ءآابةتثجحخدذرزسشصضطظعغفقكلمنهویيَُِّْ٠١٢٣٤٥٦٧٨٩پچژگی]] ;"
|
7
|
+
- ":: NFKD (NFC) ;"
|
8
|
+
- "$alef = ’;"
|
9
|
+
- "$ayin = ‘;"
|
10
|
+
- "$disambig = ̱ ;"
|
11
|
+
- "$wordBoundary = [^[:L:][:M:][:N:]] ;"
|
12
|
+
- "[:Nd:]{٫}[:Nd:] <> [:Nd:]{','}[:Nd:] ; # ARABIC DECIMAL SEPARATOR"
|
13
|
+
- "[:Nd:]{٬}[:Nd:] <> [:Nd:]{'.'}[:Nd:] ; # ARABIC THOUSANDS SEPARATOR"
|
14
|
+
- "٫ <> ',' $disambig ; # ARABIC DECIMAL SEPARATOR"
|
15
|
+
- "٬ <> '.' $disambig ; # ARABIC THOUSANDS SEPARATOR"
|
16
|
+
- "، <> ',' ; # ARABIC COMMA"
|
17
|
+
- "؛ <> ';' ; # ARABIC SEMICOLON"
|
18
|
+
- "؟ <> '?' ; # ARABIC QUESTION MARK"
|
19
|
+
- "٪ <> '%' ; # ARABIC PERCENT SIGN"
|
20
|
+
- "٠ <> 0 $disambig ; # ARABIC-INDIC DIGIT ZERO"
|
21
|
+
- "١ <> 1 $disambig ; # ARABIC-INDIC DIGIT ONE"
|
22
|
+
- "٢ <> 2 $disambig ; # ARABIC-INDIC DIGIT TWO"
|
23
|
+
- "٣ <> 3 $disambig ; # ARABIC-INDIC DIGIT THREE"
|
24
|
+
- "٤ <> 4 $disambig ; # ARABIC-INDIC DIGIT FOUR"
|
25
|
+
- "٥ <> 5 $disambig ; # ARABIC-INDIC DIGIT FIVE"
|
26
|
+
- "٦ <> 6 $disambig ; # ARABIC-INDIC DIGIT SIX"
|
27
|
+
- "٧ <> 7 $disambig ; # ARABIC-INDIC DIGIT SEVEN"
|
28
|
+
- "٨ <> 8 $disambig ; # ARABIC-INDIC DIGIT EIGHT"
|
29
|
+
- "٩ <> 9 $disambig ; # ARABIC-INDIC DIGIT NINE"
|
30
|
+
- "۰ <> 0 ; # EXTENDED ARABIC-INDIC DIGIT ZERO"
|
31
|
+
- "۱ <> 1 ; # EXTENDED ARABIC-INDIC DIGIT ONE"
|
32
|
+
- "۲ <> 2 ; # EXTENDED ARABIC-INDIC DIGIT TWO"
|
33
|
+
- "۳ <> 3 ; # EXTENDED ARABIC-INDIC DIGIT THREE"
|
34
|
+
- "۴ <> 4 ; # EXTENDED ARABIC-INDIC DIGIT FOUR"
|
35
|
+
- "۵ <> 5 ; # EXTENDED ARABIC-INDIC DIGIT FIVE"
|
36
|
+
- "۶ <> 6 ; # EXTENDED ARABIC-INDIC DIGIT SIX"
|
37
|
+
- "۷ <> 7 ; # EXTENDED ARABIC-INDIC DIGIT SEVEN"
|
38
|
+
- "۸ <> 8 ; # EXTENDED ARABIC-INDIC DIGIT EIGHT"
|
39
|
+
- "۹ <> 9 ; # EXTENDED ARABIC-INDIC DIGIT NINE"
|
40
|
+
- "كه > k·h ; # ARABIC LETTER KAF + HEH"
|
41
|
+
- "زه > z·h ; # ARABIC LETTER ZAIN + HEH"
|
42
|
+
- "سه > s·h ; # ARABIC LETTER SEEN + HEH"
|
43
|
+
- "گه > g·h ; # ARABIC LETTER GAF + HEH"
|
44
|
+
- "بّ > bb ; # ARABIC LETTER BEH + SHADDA"
|
45
|
+
- "پّ > pp ; # ARABIC LETTER PEH + SHADDA"
|
46
|
+
- "تّ > tt ; # ARABIC LETTER TEH + SHADDA"
|
47
|
+
- "ثّ > s̄s̄ ; # ARABIC LETTER THEH + SHADDA"
|
48
|
+
- "جّ > jj ; # ARABIC LETTER JEEM + SHADDA"
|
49
|
+
- "چّ > chch ; # ARABIC LETTER TCHEH + SHADDA"
|
50
|
+
- "حّ > ḥḥ ; # ARABIC LETTER HAH + SHADDA"
|
51
|
+
- "خّ > khkh ; # ARABIC LETTER KHAH + SHADDA"
|
52
|
+
- "دّ > dd ; # ARABIC LETTER DAL + SHADDA"
|
53
|
+
- "ذّ > z̄z̄ ; # ARABIC LETTER THAL + SHADDA"
|
54
|
+
- "رّ > rr ; # ARABIC LETTER REH + SHADDA"
|
55
|
+
- "زّ > zz ; # ARABIC LETTER ZAIN + SHADDA"
|
56
|
+
- "ژّ > zhzh ; # ARABIC LETTER JEH + SHADDA"
|
57
|
+
- "سّ > ss ; # ARABIC LETTER SEEN + SHADDA"
|
58
|
+
- "شّ > shsh ; # ARABIC LETTER SHEEN + SHADDA"
|
59
|
+
- "صّ > ṣṣ ; # ARABIC LETTER SAD + SHADDA"
|
60
|
+
- "ضّ > ḍḍ ; # ARABIC LETTER DAD + SHADDA"
|
61
|
+
- "طّ > ṭṭ ; # ARABIC LETTER TAH + SHADDA"
|
62
|
+
- "ظّ > ẓẓ ; # ARABIC LETTER ZAH + SHADDA"
|
63
|
+
- "عّ > $ayin $ayin ; # ARABIC LETTER AIN + SHADDA"
|
64
|
+
- "غّ > ghgh ; # ARABIC LETTER GHAIN + SHADDA"
|
65
|
+
- "فّ > ff ; # ARABIC LETTER FEH + SHADDA"
|
66
|
+
- "قّ > qq ; # ARABIC LETTER QAF + SHADDA"
|
67
|
+
- "كّ > kk ; # ARABIC LETTER KAF + SHADDA"
|
68
|
+
- "لّ > ll ; # ARABIC LETTER LAM + SHADDA"
|
69
|
+
- "مّ > mm ; # ARABIC LETTER MEEM + SHADDA"
|
70
|
+
- "نّ > nn ; # ARABIC LETTER NOON + SHADDA"
|
71
|
+
- "هّ > hh ; # ARABIC LETTER HEH + SHADDA"
|
72
|
+
- "وّ > ww ; # ARABIC LETTER WAW + SHADDA"
|
73
|
+
- "یّ > yy ; # ARABIC LETTER FARSI YEH + SHADDA"
|
74
|
+
- "$wordBoundary{ء > ; # ARABIC LETTER HAMZA"
|
75
|
+
- "ء > $alef ; # ARABIC LETTER HAMZA"
|
76
|
+
- "$wordBoundary{ا > ; # ARABIC LETTER ALEF"
|
77
|
+
- "آ > $alef ā ; # ARABIC FATHA ALEF WITH MADDA ABOVE"
|
78
|
+
- "ب > b ; # ARABIC LETTER BEH"
|
79
|
+
- "پ > p ; # ARABIC LETTER PEH"
|
80
|
+
- "ت > t ; # ARABIC LETTER TEH"
|
81
|
+
- "ة > h ; # ARABIC LETTER TEH MARBUTA"
|
82
|
+
- "ث > s̄ ; # ARABIC LETTER THEH"
|
83
|
+
- "ج > j ; # ARABIC LETTER JEEM"
|
84
|
+
- "چ > ch ; # ARABIC LETTER TCHEH"
|
85
|
+
- "ح > ḥ ; # ARABIC LETTER HAH"
|
86
|
+
- "خ > kh ; # ARABIC LETTER KHAH"
|
87
|
+
- "د > d ; # ARABIC LETTER DAL"
|
88
|
+
- "ذ > z̄ ; # ARABIC LETTER THAL"
|
89
|
+
- "ر > r ; # ARABIC LETTER REH"
|
90
|
+
- "ز > z ; # ARABIC LETTER ZAIN"
|
91
|
+
- "ژ > zh ; # ARABIC LETTER JEH"
|
92
|
+
- "س > s ; # ARABIC LETTER SEEN"
|
93
|
+
- "ش > sh ; # ARABIC LETTER SHEEN"
|
94
|
+
- "ص > ṣ ; # ARABIC LETTER SAD"
|
95
|
+
- "ض > ẕ ; # ARABIC LETTER DAD"
|
96
|
+
- "ط > ṭ ; # ARABIC LETTER TAH"
|
97
|
+
- "ظ > ẓ ; # ARABIC LETTER ZAH"
|
98
|
+
- "ع > $ayin ; # ARABIC LETTER AIN"
|
99
|
+
- "غ > gh ; # ARABIC LETTER GHAIN"
|
100
|
+
- "ف > f ; # ARABIC LETTER FEH"
|
101
|
+
- "ق > q ; # ARABIC LETTER QAF"
|
102
|
+
- "ک <> k ; # ARABIC LETTER KEHEH"
|
103
|
+
- "ك <> k $disambig ; # ARABIC LETTER KAF"
|
104
|
+
- "گ > g ; # ARABIC LETTER GAF"
|
105
|
+
- "ل > l ; # ARABIC LETTER LAM"
|
106
|
+
- "م > m ; # ARABIC LETTER MEEM"
|
107
|
+
- "ن > n ; # ARABIC LETTER NOON"
|
108
|
+
- "ه > h ; # ARABIC LETTER HEH"
|
109
|
+
- "و > v ; # ARABIC LETTER WAW"
|
110
|
+
- "ی > y ; # ARABIC LETTER FARSI YEH"
|
111
|
+
- "َا > ā ; # ARABIC FATHA + ALEF"
|
112
|
+
- "َی > á ; # ARABIC FATHA + FARSI YEH"
|
113
|
+
- "َوْ > ow ; # ARABIC FATHA + WAW + SUKUN"
|
114
|
+
- "َ > a ; # ARABIC FATHA"
|
115
|
+
- "ِي > ī ; # ARABIC KASRA + YEH"
|
116
|
+
- "ِ > e ; # ARABIC KASRA"
|
117
|
+
- "ُو > ū ; # ARABIC DAMMA + WAW"
|
118
|
+
- "ُ > o ; # ARABIC DAMMA"
|
119
|
+
- "ْ > ; # ARABIC SUKUN"
|
120
|
+
- "::NFC (NFD) ;"
|
121
|
+
:source: fa
|
122
|
+
:target: fa_Latn
|
123
|
+
:variant: BGN
|