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 +1,132 @@
|
|
1
|
+
---
|
2
|
+
:transforms:
|
3
|
+
-
|
4
|
+
:direction: forward
|
5
|
+
:rules:
|
6
|
+
- "$inword = [[:L:][:M:]];"
|
7
|
+
- "ᱹᱸ > ᱺ ;"
|
8
|
+
- "ᱸᱹ > ᱺ ;"
|
9
|
+
- "::null();"
|
10
|
+
- "ᱻᱹ > ᱹᱻ ;"
|
11
|
+
- "ᱻᱸ > ᱸᱻ ;"
|
12
|
+
- "ᱻᱺ > ᱺᱻ ;"
|
13
|
+
- "ᱼᱹ > ᱹᱼ ;"
|
14
|
+
- "ᱼᱸ > ᱸᱼ ;"
|
15
|
+
- "ᱼᱺ > ᱺᱼ ;"
|
16
|
+
- "::null();"
|
17
|
+
- "[ᱚᱟᱤᱩᱮᱳᱶᱢᱝᱞᱱ] [ᱹᱸᱺ]* {ᱼ} > ᱻ ;"
|
18
|
+
- "::null();"
|
19
|
+
- "ᱚᱹᱻ > ɔː ;"
|
20
|
+
- "ᱚᱹ > ɔ ;"
|
21
|
+
- "ᱚᱸᱻ > ɔ̃ː ;"
|
22
|
+
- "ᱚᱸ > ɔ̃ ;"
|
23
|
+
- "ᱚᱺᱻ > ɔ̃ː ;"
|
24
|
+
- "ᱚᱺ > ɔ̃ ;"
|
25
|
+
- "ᱚᱻ > ɔː ;"
|
26
|
+
- "ᱚ > ɔ ;"
|
27
|
+
- "ᱛᱼ > t ;"
|
28
|
+
- "ᱛᱷ > tʰ ;"
|
29
|
+
- "ᱛᱽ > d ;"
|
30
|
+
- "$inword {ᱛ} > d ;"
|
31
|
+
- "ᱛ > t ;"
|
32
|
+
- "ᱜᱼ > kʼ ;"
|
33
|
+
- "ᱜᱷ > kʰ ;"
|
34
|
+
- "ᱜᱽ > ɡ ;"
|
35
|
+
- "$inword {ᱜ} > ɡ ;"
|
36
|
+
- "ᱜ > kʼ ;"
|
37
|
+
- "ᱝᱻ > ŋː ;"
|
38
|
+
- "ᱝ > ŋ ;"
|
39
|
+
- "ᱞᱻ > lː ;"
|
40
|
+
- "ᱞ > l ;"
|
41
|
+
- "ᱟᱹᱻ > əː ;"
|
42
|
+
- "ᱟᱹ > ə ;"
|
43
|
+
- "ᱟᱸᱻ > ãː ;"
|
44
|
+
- "ᱟᱸ > ã ;"
|
45
|
+
- "ᱟᱺᱻ > ə̃ː ;"
|
46
|
+
- "ᱟᱺ > ə̃ ;"
|
47
|
+
- "ᱟᱻ > aː ;"
|
48
|
+
- "ᱟ > a ;"
|
49
|
+
- "ᱠᱼ > k ;"
|
50
|
+
- "ᱠᱷ > kʰ ;"
|
51
|
+
- "ᱠᱽ > ɡ ;"
|
52
|
+
- "ᱠ > k ;"
|
53
|
+
- "ᱡᱼ > cʼ ;"
|
54
|
+
- "ᱡᱷ > cʰ ;"
|
55
|
+
- "ᱡᱽ > d͡ʒ ;"
|
56
|
+
- "$inword {ᱡ} > d͡ʒ ;"
|
57
|
+
- "ᱡ > cʼ ;"
|
58
|
+
- "ᱢᱻ > mː ;"
|
59
|
+
- "ᱢ > m ;"
|
60
|
+
- "ᱣᱸ > w̃ ;"
|
61
|
+
- "ᱣ > w ;"
|
62
|
+
- "ᱤᱹᱻ > iː ;"
|
63
|
+
- "ᱤᱹ > i ;"
|
64
|
+
- "ᱤᱸᱻ > ĩː ;"
|
65
|
+
- "ᱤᱸ > ĩ ;"
|
66
|
+
- "ᱤᱺᱻ > ĩː ;"
|
67
|
+
- "ᱤᱺ > ĩ ;"
|
68
|
+
- "ᱤᱻ > iː ;"
|
69
|
+
- "ᱤ > i ;"
|
70
|
+
- "ᱥᱻ > sː ;"
|
71
|
+
- "ᱥ > s ;"
|
72
|
+
- "ᱦ > h ;"
|
73
|
+
- "ᱧᱻ > ɲː ;"
|
74
|
+
- "ᱧ > ɲ ;"
|
75
|
+
- "ᱨᱻ > r ;"
|
76
|
+
- "ᱨ > r ;"
|
77
|
+
- "ᱩᱹᱻ > uː ;"
|
78
|
+
- "ᱩᱹ > u ;"
|
79
|
+
- "ᱩᱸᱻ > ũː ;"
|
80
|
+
- "ᱩᱸ > ũ ;"
|
81
|
+
- "ᱩᱺᱻ > ũː ;"
|
82
|
+
- "ᱩᱺ > ũ ;"
|
83
|
+
- "ᱩᱻ > uː ;"
|
84
|
+
- "ᱩ > u ;"
|
85
|
+
- "ᱪᱼ > c ;"
|
86
|
+
- "ᱪᱷ > cʰ ;"
|
87
|
+
- "ᱪᱽ > d͡ʒ ;"
|
88
|
+
- "ᱪ > c ;"
|
89
|
+
- "ᱫᱼ > tʼ ;"
|
90
|
+
- "ᱫᱷ > tʰ ;"
|
91
|
+
- "ᱫᱽ > d ;"
|
92
|
+
- "$inword {ᱫ} > d ;"
|
93
|
+
- "ᱫ > tʼ ;"
|
94
|
+
- "ᱬᱻ > ɳː ;"
|
95
|
+
- "ᱬ > ɳ ;"
|
96
|
+
- "ᱭ > h ;"
|
97
|
+
- "ᱮᱹᱻ > ɛː ;"
|
98
|
+
- "ᱮᱹ > ɛ ;"
|
99
|
+
- "ᱮᱺᱻ > ɛ̃ː ;"
|
100
|
+
- "ᱮᱺ > ɛ̃ ;"
|
101
|
+
- "ᱮᱸᱻ > ẽː ;"
|
102
|
+
- "ᱮᱸ > ẽ ;"
|
103
|
+
- "ᱮᱻ > eː ;"
|
104
|
+
- "ᱮ > e ;"
|
105
|
+
- "ᱯᱼ > p ;"
|
106
|
+
- "ᱯᱷ > pʰ ;"
|
107
|
+
- "ᱯᱽ > b ;"
|
108
|
+
- "ᱯ > p ;"
|
109
|
+
- "ᱰᱷ > ɖʰ ;"
|
110
|
+
- "ᱰ > ɖ ;"
|
111
|
+
- "ᱱᱻ > nː ;"
|
112
|
+
- "ᱱ > n ;"
|
113
|
+
- "ᱲᱻ > ɽ ;"
|
114
|
+
- "ᱲ > ɽ ;"
|
115
|
+
- "ᱳᱸᱻ > õː ;"
|
116
|
+
- "ᱳᱸ > õ ;"
|
117
|
+
- "ᱳᱻ > oː ;"
|
118
|
+
- "ᱳ > o ;"
|
119
|
+
- "ᱴᱼ > ʈ ;"
|
120
|
+
- "ᱴᱷ > ʈʰ ;"
|
121
|
+
- "ᱴᱽ > ɖ ;"
|
122
|
+
- "ᱴ > ʈ ;"
|
123
|
+
- "ᱵᱼ > pʼ ;"
|
124
|
+
- "ᱵᱷ > bʰ ;"
|
125
|
+
- "ᱵᱽ > b ;"
|
126
|
+
- "$inword {ᱵ} > b ;"
|
127
|
+
- "ᱵ > pʼ ;"
|
128
|
+
- "ᱶᱻ > w̃ː ;"
|
129
|
+
- "ᱶ > w̃ ;"
|
130
|
+
:source: sat_Olck
|
131
|
+
:target: sat_FONIPA
|
132
|
+
:variant: ~
|
@@ -0,0 +1,128 @@
|
|
1
|
+
---
|
2
|
+
:transforms:
|
3
|
+
-
|
4
|
+
:direction: forward
|
5
|
+
:rules:
|
6
|
+
- "[\\u0D9A-\\u0DC6] \\u0DCA (\\u200D)? { ය්ය > ය;"
|
7
|
+
- "\\u200C > ;"
|
8
|
+
- "\\u200D > ;"
|
9
|
+
- "::Null;"
|
10
|
+
- "([\\u0D9A-\\u0DC6]) } [^\\u0DCA-\\u0DDF \\u0DF2\\u0DF3] > $1 ə;"
|
11
|
+
- "::Null;"
|
12
|
+
- "[Ff]ප > f;"
|
13
|
+
- "[Zz]ස > z;"
|
14
|
+
- "ං > ŋ;"
|
15
|
+
- "o > ŋ; # common substitution for anusvaraya"
|
16
|
+
- "ඃ ([\\u0D9A-\\u0DC6]) > | $1 \\u0DCA $1; # TODO: check which consonants geminate"
|
17
|
+
- "ඃ > h;"
|
18
|
+
- "අ > a;"
|
19
|
+
- "ආ > aː;"
|
20
|
+
- "ඇ > æ;"
|
21
|
+
- "ඈ > æː;"
|
22
|
+
- "ඉ > i;"
|
23
|
+
- "ඊ > iː;"
|
24
|
+
- "උ > u;"
|
25
|
+
- "ඌ > uː;"
|
26
|
+
- "ඍ > ri;"
|
27
|
+
- "ඎ > ruː;"
|
28
|
+
- "ඏ > ilu;"
|
29
|
+
- "ඐ > iluː;"
|
30
|
+
- "එ > e;"
|
31
|
+
- "ඒ > eː;"
|
32
|
+
- "ඓ > aj;"
|
33
|
+
- "ඔ > o;"
|
34
|
+
- "ඕ > oː;"
|
35
|
+
- "ඖ > aw; # TODO: check if this is correct"
|
36
|
+
- "ක > k;"
|
37
|
+
- "ඛ > k;"
|
38
|
+
- "ග > ɡ;"
|
39
|
+
- "ඝ > ɡ;"
|
40
|
+
- "ඞ > ŋ;"
|
41
|
+
- "ඟ > ᵑɡ;"
|
42
|
+
- "ච > c;"
|
43
|
+
- "ඡ > c;"
|
44
|
+
- "ජ > ɟ;"
|
45
|
+
- "ඣ > ɟ;"
|
46
|
+
- "ඤ > ɲ;"
|
47
|
+
- "ඥ > kɲ; # TODO: double-check"
|
48
|
+
- "ඦ > ɟ;"
|
49
|
+
- "ට > ʈ;"
|
50
|
+
- "ඨ > ʈ;"
|
51
|
+
- "ඩ > ɖ;"
|
52
|
+
- "ඪ > ɖ;"
|
53
|
+
- "ණ > n;"
|
54
|
+
- "ඬ > ⁿɖ;"
|
55
|
+
- "ත > t;"
|
56
|
+
- "ථ > t;"
|
57
|
+
- "ද > d;"
|
58
|
+
- "ධ > d;"
|
59
|
+
- "න > n;"
|
60
|
+
- "ඳ > ⁿd;"
|
61
|
+
- "ප > p;"
|
62
|
+
- "ඵ > p;"
|
63
|
+
- "බ > b;"
|
64
|
+
- "භ > b;"
|
65
|
+
- "ම > m;"
|
66
|
+
- "ඹ > ᵐb;"
|
67
|
+
- "ය > j;"
|
68
|
+
- "ර > r;"
|
69
|
+
- "ල > l;"
|
70
|
+
- "ව > w;"
|
71
|
+
- "ශ > ʃ;"
|
72
|
+
- "ෂ > ʃ;"
|
73
|
+
- "ස > s;"
|
74
|
+
- "හ > h;"
|
75
|
+
- "ළ > l;"
|
76
|
+
- "ෆ > f;"
|
77
|
+
- "\\u0DCA > ; # delete virama"
|
78
|
+
- "ා > aː;"
|
79
|
+
- "ැ > æ;"
|
80
|
+
- "ෑ > æː;"
|
81
|
+
- "\\u0DD2 > i;"
|
82
|
+
- "\\u0DD3 > iː;"
|
83
|
+
- "\\u0DD4 > u;"
|
84
|
+
- "\\u0DD6 > uː;"
|
85
|
+
- "ෘ > ru;"
|
86
|
+
- "ෙ > e;"
|
87
|
+
- "ේ > eː;"
|
88
|
+
- "ෛ > aj;"
|
89
|
+
- "ො > o;"
|
90
|
+
- "ෝ > oː;"
|
91
|
+
- "ෞ > aw; # TODO: check if this is correct"
|
92
|
+
- "ෟ > lu;"
|
93
|
+
- "ෲ > ruː;"
|
94
|
+
- "ෳ > luː;"
|
95
|
+
- "$c=[k ɡ ŋ {ᵑɡ} c ɟ ɲ ʈ ɖ {ⁿɖ} t d n {ⁿd} p b m {ᵐb} j r l w ʃ s z h f];"
|
96
|
+
- "$s=[:^L:];"
|
97
|
+
- "::Null;"
|
98
|
+
- "$s sv { ə > ə; # exception (a)"
|
99
|
+
- "$s k { ə } r > ə; # exception (b)"
|
100
|
+
- "$s $c { ə } $s > ə; # exception (c)"
|
101
|
+
- "$s $c $c { ə > a;"
|
102
|
+
- "$s $c { ə > a;"
|
103
|
+
- "::Null;"
|
104
|
+
- "$c r { ə } $c > a; # clause (a) and (b)"
|
105
|
+
- "$c r { a } h > a; # clause (d), exception"
|
106
|
+
- "$c r { a } $c > ə; # clause (c)"
|
107
|
+
- "::Null;"
|
108
|
+
- "[a e æ o ə] h { ə > a;"
|
109
|
+
- "::Null;"
|
110
|
+
- "ə } $c $c > a; # Rule #4"
|
111
|
+
- "ə } [rbɖʈ] $s > ə; # Rule #5 exception"
|
112
|
+
- "ə } $c $s > a; # Rule #5"
|
113
|
+
- "ə } ji $s > a; # Rule #6"
|
114
|
+
- "k { ə } [rl] u > a; # Rule #7"
|
115
|
+
- "::Null;"
|
116
|
+
- "$s k { a } l[aeo]ːj > ə; # Typo in paper: /j/ was /y/."
|
117
|
+
- "$s k { a } le[mh][ui] > ə;"
|
118
|
+
- "$s k { alə } h[ui] > əle;"
|
119
|
+
- "$s k { a } lə > ə;"
|
120
|
+
- "::Null;"
|
121
|
+
- "www+ > ww; # යෞව්වන"
|
122
|
+
- "[i {iː} e {eː} æ {æː} o {oː} a {aː}] { wu > w;"
|
123
|
+
- "əji > aj;"
|
124
|
+
- "iji > iː; # perhaps: ij"
|
125
|
+
- "[u {uː} e {eː} æ {æː} o {oː} a {aː}] { ji > j;"
|
126
|
+
:source: si
|
127
|
+
:target: si_FONIPA
|
128
|
+
:variant: ~
|
@@ -0,0 +1,96 @@
|
|
1
|
+
---
|
2
|
+
:transforms:
|
3
|
+
-
|
4
|
+
:direction: forward
|
5
|
+
:rules:
|
6
|
+
- "::[[:Sinh:][\\u200C\\u200D]];"
|
7
|
+
- "::NFKC;"
|
8
|
+
- "\\u200C > ;"
|
9
|
+
- "\\u200D > ;"
|
10
|
+
- "::Null;"
|
11
|
+
- "([\\u0D9A-\\u0DC6]) } [^\\u0DCA-\\u0DDF] > $1 a;"
|
12
|
+
- "::Null;"
|
13
|
+
- "ක > k;"
|
14
|
+
- "ට > ṭ;"
|
15
|
+
- "ත > t;"
|
16
|
+
- "ප > p;"
|
17
|
+
- "ග > g;"
|
18
|
+
- "ඩ > ḍ;"
|
19
|
+
- "ද > d;"
|
20
|
+
- "බ > b;"
|
21
|
+
- "[Zz]ස > z;"
|
22
|
+
- "ස > s;"
|
23
|
+
- "ච > c;"
|
24
|
+
- "ම > m;"
|
25
|
+
- "ල > l;"
|
26
|
+
- "ව > v;"
|
27
|
+
- "ණ > ṇ;"
|
28
|
+
- "හ > h;"
|
29
|
+
- "ජ > j;"
|
30
|
+
- "න > n;"
|
31
|
+
- "ර > r;"
|
32
|
+
- "ය > y;"
|
33
|
+
- "ළ > ḷ;"
|
34
|
+
- "අ > a;"
|
35
|
+
- "එ > e;"
|
36
|
+
- "ඉ > i;"
|
37
|
+
- "ඔ > o;"
|
38
|
+
- "උ > u;"
|
39
|
+
- "ඇ > æ;"
|
40
|
+
- "ෙ > e;"
|
41
|
+
- "ි > i;"
|
42
|
+
- "ො > o;"
|
43
|
+
- "ු > u;"
|
44
|
+
- "ැ > æ;"
|
45
|
+
- "ආ > ā;"
|
46
|
+
- "ඒ > ē;"
|
47
|
+
- "ඊ > ī;"
|
48
|
+
- "ඕ > ō;"
|
49
|
+
- "ඌ > ū;"
|
50
|
+
- "ඈ > ǣ;"
|
51
|
+
- "ා > ā;"
|
52
|
+
- "ේ > ē;"
|
53
|
+
- "ී > ī;"
|
54
|
+
- "ෝ > ō;"
|
55
|
+
- "ූ > ū;"
|
56
|
+
- "ෑ > ǣ;"
|
57
|
+
- "ඟ > n̆g;"
|
58
|
+
- "ඬ > n̆ḍ;"
|
59
|
+
- "ඳ > n̆d;"
|
60
|
+
- "ඹ > m̆b;"
|
61
|
+
- "ඛ > kh;"
|
62
|
+
- "ඨ > ṭh;"
|
63
|
+
- "ථ > th;"
|
64
|
+
- "ඵ > ph;"
|
65
|
+
- "ඝ > gh;"
|
66
|
+
- "ඪ > ḍh;"
|
67
|
+
- "ධ > dh;"
|
68
|
+
- "භ > bh;"
|
69
|
+
- "ශ > ś;"
|
70
|
+
- "ඡ > ch;"
|
71
|
+
- "ඤ > ñ;"
|
72
|
+
- "ඞ > ṅ;"
|
73
|
+
- "ඦ > n̆j;"
|
74
|
+
- "ෂ > ṣ;"
|
75
|
+
- "ඣ > jh;"
|
76
|
+
- "ඥ > gn;"
|
77
|
+
- "ෆ > f;"
|
78
|
+
- "[Ff]ප > f;"
|
79
|
+
- "ඓ > ai;"
|
80
|
+
- "ඍ > ṛ;"
|
81
|
+
- "ඏ > ḷ;"
|
82
|
+
- "ෛ > ai;"
|
83
|
+
- "ෘ > ṛ;"
|
84
|
+
- "ෟ > ḷ;"
|
85
|
+
- "ඖ > au;"
|
86
|
+
- "ඎ > ṝ;"
|
87
|
+
- "ඐ > ḹ;"
|
88
|
+
- "ෞ > au;"
|
89
|
+
- "ෲ > ṝ;"
|
90
|
+
- "ෳ > ḹ;"
|
91
|
+
- "ඃ > ḥ;"
|
92
|
+
- "ං > ṁ;"
|
93
|
+
- "් > ;"
|
94
|
+
:source: si
|
95
|
+
:target: si_Latn
|
96
|
+
:variant: ~
|