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 +1,72 @@
|
|
1
|
+
---
|
2
|
+
:transforms:
|
3
|
+
-
|
4
|
+
:direction: both
|
5
|
+
:rules:
|
6
|
+
- ":: [[:Hebrew:] [:^ccc=0:] [ְ-ֹֻ-ּׁ-ׂℵ-ℸֿ̄] - [ֽ]] ;"
|
7
|
+
- ":: nfkd (nfc) ;"
|
8
|
+
- "$letterAfter = [:M:]* [:L:] ;"
|
9
|
+
- "ח <> ẖ ;"
|
10
|
+
- "צ <> ẕ } $letterAfter;"
|
11
|
+
- "ץ <> ẕ ;"
|
12
|
+
- "ש <> ş ;"
|
13
|
+
- "ת <> ţ ;"
|
14
|
+
- "א <> ʼ ;"
|
15
|
+
- "ב <> b ;"
|
16
|
+
- "ג <> g ;"
|
17
|
+
- "ד <> d ;"
|
18
|
+
- "ה <> h ;"
|
19
|
+
- "ו <> w ;"
|
20
|
+
- "ז <> z ;"
|
21
|
+
- "ט <> t ;"
|
22
|
+
- "י <> y ;"
|
23
|
+
- "כ <> k } $letterAfter;"
|
24
|
+
- "ך <> k ;"
|
25
|
+
- "ל <> l ;"
|
26
|
+
- "מ <> m } $letterAfter;"
|
27
|
+
- "ם <> m ;"
|
28
|
+
- "נ <> n } $letterAfter;"
|
29
|
+
- "ן <> n ;"
|
30
|
+
- "ס <> s ;"
|
31
|
+
- "ע <> ʻ ;"
|
32
|
+
- "פ <> p } $letterAfter;"
|
33
|
+
- "ף <> p ;"
|
34
|
+
- "ק <> q ;"
|
35
|
+
- "ר <> r ;"
|
36
|
+
- "װ > | וו; # HEBREW LIGATURE YIDDISH DOUBLE VAV"
|
37
|
+
- "ױ > | וי; # HEBREW LIGATURE YIDDISH VAV YOD"
|
38
|
+
- "ײ > | יי ; # HEBREW LIGATURE YIDDISH DOUBLE YOD"
|
39
|
+
- "ּ <> ̇ ; # dagesh just goes to overdot for now"
|
40
|
+
- "ׁ <> ̌ ; # shin dot -> sh"
|
41
|
+
- "ׂ <> ̂ ; # sin dot -> s"
|
42
|
+
- "$above = [^[:ccc=0:][:ccc=230:]]*;"
|
43
|
+
- "ֲ > à ;"
|
44
|
+
- "ֲ $1< a ($above) ̀;"
|
45
|
+
- "ָ > á ;"
|
46
|
+
- "ָ $1 < a ($above) ́;"
|
47
|
+
- "ֱ > è ;"
|
48
|
+
- "ֱ $1 < e ($above) ̀;"
|
49
|
+
- "ֵ > é ;"
|
50
|
+
- "ֵ $1 < e ($above) ́;"
|
51
|
+
- "ְ > e ̆ ;"
|
52
|
+
- "ְ $1 < e ($above) ̆;"
|
53
|
+
- "ֹ > ò ;"
|
54
|
+
- "ֹ $1 < o ($above) ̀;"
|
55
|
+
- "ִ <> i ;"
|
56
|
+
- "ֻ <> u ;"
|
57
|
+
- "ַ <> a ;"
|
58
|
+
- "ֶ <> e ;"
|
59
|
+
- "ֳ <> o ;"
|
60
|
+
- "ֿ <> ̄ ;"
|
61
|
+
- "ק < c ;"
|
62
|
+
- "פ < f } $letterAfter;"
|
63
|
+
- "ף < f ;"
|
64
|
+
- "ז < j ;"
|
65
|
+
- "ו < v ;"
|
66
|
+
- "כס < x ;"
|
67
|
+
- ":: (lower);"
|
68
|
+
- ":: nfc (nfd) ;"
|
69
|
+
- ":: ([[:Latin:] [:^ccc=0:] [ʻ-ʼ̀-̧̱̂̇̌̀-́ ̄ ]]);"
|
70
|
+
:source: Hebr
|
71
|
+
:target: Latn
|
72
|
+
:variant: ~
|
@@ -0,0 +1,114 @@
|
|
1
|
+
---
|
2
|
+
:transforms:
|
3
|
+
-
|
4
|
+
:direction: both
|
5
|
+
:rules:
|
6
|
+
- ":: [\\u0000-\\u007E 、。 ゙-゜ ァ-ー 。-゚ー[:Hiragana:] [:Katakana:] [:nonspacing mark:]] ;"
|
7
|
+
- ":: NFKC ();"
|
8
|
+
- "わ゙ <> ヷ;"
|
9
|
+
- "ゐ゙ <> ヸ;"
|
10
|
+
- "ゑ゙ <> ヹ;"
|
11
|
+
- "を゙ <> ヺ;"
|
12
|
+
- "ぁ <> ァ;"
|
13
|
+
- "あ <> ア;"
|
14
|
+
- "ぃ <> ィ;"
|
15
|
+
- "い <> イ;"
|
16
|
+
- "ぅ <> ゥ;"
|
17
|
+
- "う <> ウ;"
|
18
|
+
- "ぇ <> ェ;"
|
19
|
+
- "え <> エ;"
|
20
|
+
- "ぉ <> ォ;"
|
21
|
+
- "お <> オ;"
|
22
|
+
- "か <> カ;"
|
23
|
+
- "が <> ガ;"
|
24
|
+
- "き <> キ;"
|
25
|
+
- "ぎ <> ギ;"
|
26
|
+
- "く <> ク;"
|
27
|
+
- "ぐ <> グ;"
|
28
|
+
- "け <> ケ;"
|
29
|
+
- "げ <> ゲ;"
|
30
|
+
- "こ <> コ;"
|
31
|
+
- "ご <> ゴ;"
|
32
|
+
- "さ <> サ;"
|
33
|
+
- "ざ <> ザ;"
|
34
|
+
- "し <> シ;"
|
35
|
+
- "じ <> ジ;"
|
36
|
+
- "す <> ス;"
|
37
|
+
- "ず <> ズ;"
|
38
|
+
- "せ <> セ;"
|
39
|
+
- "ぜ <> ゼ;"
|
40
|
+
- "そ <> ソ;"
|
41
|
+
- "ぞ <> ゾ;"
|
42
|
+
- "た <> タ;"
|
43
|
+
- "だ <> ダ;"
|
44
|
+
- "ち <> チ;"
|
45
|
+
- "ぢ <> ヂ;"
|
46
|
+
- "っ <> ッ;"
|
47
|
+
- "つ <> ツ;"
|
48
|
+
- "づ <> ヅ;"
|
49
|
+
- "て <> テ;"
|
50
|
+
- "で <> デ;"
|
51
|
+
- "と <> ト;"
|
52
|
+
- "ど <> ド;"
|
53
|
+
- "な <> ナ;"
|
54
|
+
- "に <> ニ;"
|
55
|
+
- "ぬ <> ヌ;"
|
56
|
+
- "ね <> ネ;"
|
57
|
+
- "の <> ノ;"
|
58
|
+
- "は <> ハ;"
|
59
|
+
- "ば <> バ;"
|
60
|
+
- "ぱ <> パ;"
|
61
|
+
- "ひ <> ヒ;"
|
62
|
+
- "び <> ビ;"
|
63
|
+
- "ぴ <> ピ;"
|
64
|
+
- "ふ <> フ;"
|
65
|
+
- "ぶ <> ブ;"
|
66
|
+
- "ぷ <> プ;"
|
67
|
+
- "へ <> ヘ;"
|
68
|
+
- "べ <> ベ;"
|
69
|
+
- "ぺ <> ペ;"
|
70
|
+
- "ほ <> ホ;"
|
71
|
+
- "ぼ <> ボ;"
|
72
|
+
- "ぽ <> ポ;"
|
73
|
+
- "ま <> マ;"
|
74
|
+
- "み <> ミ;"
|
75
|
+
- "む <> ム;"
|
76
|
+
- "め <> メ;"
|
77
|
+
- "も <> モ;"
|
78
|
+
- "ゃ <> ャ;"
|
79
|
+
- "や <> ヤ;"
|
80
|
+
- "ゅ <> ュ;"
|
81
|
+
- "ゆ <> ユ;"
|
82
|
+
- "ょ <> ョ;"
|
83
|
+
- "よ <> ヨ;"
|
84
|
+
- "ら <> ラ;"
|
85
|
+
- "り <> リ;"
|
86
|
+
- "る <> ル;"
|
87
|
+
- "れ <> レ;"
|
88
|
+
- "ろ <> ロ;"
|
89
|
+
- "ゎ <> ヮ;"
|
90
|
+
- "わ <> ワ;"
|
91
|
+
- "ゐ <> ヰ;"
|
92
|
+
- "ゑ <> ヱ;"
|
93
|
+
- "を <> ヲ;"
|
94
|
+
- "ん <> ン;"
|
95
|
+
- "ゔ <> ヴ;"
|
96
|
+
- "ゝ <> ヽ;"
|
97
|
+
- "ゞ <> ヾ;"
|
98
|
+
- "か < ヵ;"
|
99
|
+
- "け < ヶ;"
|
100
|
+
- "$xa = [ ぁ あ か が さ ざ た だ な は ば ぱ ま ゃ や ら ゎ わ ];"
|
101
|
+
- "$xi = [ ぃ い き ぎ し じ ち ぢ に ひ び ぴ み り ゐ ];"
|
102
|
+
- "$xu = [ ぅ う く ぐ す ず っ つ づ ぬ ふ ぶ ぷ む ゅ ゆ る ゔ ];"
|
103
|
+
- "$xe = [ ぇ え け げ せ ぜ て で ね へ べ ぺ め れ ゑ ];"
|
104
|
+
- "$xo = [ ぉ お こ ご そ ぞ と ど の ほ ぼ ぽ も ょ よ ろ を ];"
|
105
|
+
- "あ < $xa {ー};"
|
106
|
+
- "い < $xi {ー};"
|
107
|
+
- "う < $xu {ー};"
|
108
|
+
- "え < $xe {ー};"
|
109
|
+
- "お < $xo {ー};"
|
110
|
+
- ":: (NFKC) ;"
|
111
|
+
- ":: ([\\u0000-\\u007E 、。 ゙-゜ ァ-ー 。-゚ー[:Hiragana:] [:Katakana:] [:nonspacing mark:]]);"
|
112
|
+
:source: Hira
|
113
|
+
:target: Kana
|
114
|
+
:variant: ~
|
@@ -0,0 +1,15 @@
|
|
1
|
+
---
|
2
|
+
:transforms:
|
3
|
+
-
|
4
|
+
:direction: both
|
5
|
+
:rules:
|
6
|
+
- ":: [ぁ-ゔ゙ゝ-ゞガギグゲゴザジズゼゾダヂヅデドバビブベボヴヷ-ヺーヾ] ;"
|
7
|
+
- ":: NFD ;"
|
8
|
+
- ":: Hiragana-Katakana;"
|
9
|
+
- ":: Katakana-Latin;"
|
10
|
+
- ":: NFC ;"
|
11
|
+
- ":: (Lower) ;"
|
12
|
+
- ":: ([',.A-Za-z~À-ÖØ-öø-ďĒ-ĥĨ-İĴ-ķĹ-ľŃ-ňŌ-őŔ-ťŨ-žƠ-ơƯ-ưǍ-ǜǞ-ǣǦ-ǭǰǴ-ǵǸ-țȞ-ȟȦ-ȳ̄Ӣ-ӣӮ-ӯḀ-ẙẠ-ỹᾱᾹῑῙῡῩK-Å]) ;"
|
13
|
+
:source: Hira
|
14
|
+
:target: Latn
|
15
|
+
:variant: ~
|
@@ -68,7 +68,7 @@
|
|
68
68
|
- $u=\uE041;
|
69
69
|
- $uu=\uE042;
|
70
70
|
- $rh=\uE043;
|
71
|
-
- $
|
71
|
+
- $rrh=\uE044;
|
72
72
|
- "$ce=\\uE045; #VOWEL SIGN CANDRA E"
|
73
73
|
- "$se=\\uE046; #VOWEL SIGN SHORT E"
|
74
74
|
- $e=\uE047;
|
@@ -96,7 +96,7 @@
|
|
96
96
|
- $uya=\uE05F;
|
97
97
|
- $wrr=\uE060;
|
98
98
|
- $wll=\uE061;
|
99
|
-
- $
|
99
|
+
- $lh=\uE062;
|
100
100
|
- $llh=\uE063;
|
101
101
|
- $danda=\uE064;
|
102
102
|
- $doubleDanda=\uE065;
|
@@ -19,7 +19,7 @@
|
|
19
19
|
- "Đ > D ; # 0110;LATIN CAPITAL LETTER D WITH STROKE"
|
20
20
|
- "đ > d ; # 0111;LATIN SMALL LETTER D WITH STROKE"
|
21
21
|
- "Ħ > H ; # 0126;LATIN CAPITAL LETTER H WITH STROKE"
|
22
|
-
- "ħ > h ; # 0126;LATIN
|
22
|
+
- "ħ > h ; # 0126;LATIN SMALL LETTER H WITH STROKE"
|
23
23
|
- "ı > i ; # 0131;LATIN SMALL LETTER DOTLESS I"
|
24
24
|
- "IJ > IJ ; # 0132;LATIN CAPITAL LIGATURE IJ (compat)"
|
25
25
|
- "ij > ij ; # 0133;LATIN SMALL LIGATURE IJ (compat)"
|
@@ -543,6 +543,13 @@
|
|
543
543
|
- "\\u200A > ' ' ; # 200A;HAIR SPACE (compat)"
|
544
544
|
- "\\u205F > ' ' ; # 205F;MEDIUM MATHEMATICAL SPACE (compat)"
|
545
545
|
- "\\u3000 > ' ' ; # 3000;IDEOGRAPHIC SPACE (from ‹character-fallback›)"
|
546
|
+
- "ʹ > \\' ; # 02B9;MODIFIER LETTER PRIME"
|
547
|
+
- "ʺ > \\\" ; # 02BA;MODIFIER LETTER DOUBLE PRIME"
|
548
|
+
- "ʻ > \\' ; # 02BB;MODIFIER LETTER TURNED COMMA"
|
549
|
+
- "ʼ > \\' ; # 02BC;MODIFIER LETTER APOSTROPHE"
|
550
|
+
- "ʽ > \\' ; # 02BD;MODIFIER LETTER REVERSED COMMA"
|
551
|
+
- "ˈ > \\' ; # 02C8;MODIFIER LETTER VERTICAL LINE"
|
552
|
+
- "ˋ > '`' ; # 02CB;MODIFIER LETTER GRAVE ACCENT"
|
546
553
|
- "‘ > \\' ; # 2018;LEFT SINGLE QUOTATION MARK (from ‹character-fallback›)"
|
547
554
|
- "’ > \\' ; # 2019;RIGHT SINGLE QUOTATION MARK (from ‹character-fallback›)"
|
548
555
|
- "‚ > ',' ; # 201A;SINGLE LOW-9 QUOTATION MARK (from ‹character-fallback›)"
|
@@ -573,6 +580,12 @@
|
|
573
580
|
- "﹘ > '-' ; # FE58;SMALL EM DASH (compat)"
|
574
581
|
- "﹣ > '-' ; # FE63;SMALL HYPHEN-MINUS (compat)"
|
575
582
|
- "- > '-' ; # FF0D;FULLWIDTH HYPHEN-MINUS (compat)"
|
583
|
+
- "˂ > '<' ; # 02C2;MODIFIER LETTER LEFT ARROWHEAD"
|
584
|
+
- "˃ > '>' ; # 02C3;MODIFIER LETTER RIGHT ARROWHEAD"
|
585
|
+
- "˄ > '^' ; # 02C4;MODIFIER LETTER UP ARROWHEAD"
|
586
|
+
- "ˆ > '^' ; # 02C6;MODIFIER LETTER CIRCUMFLEX ACCENT"
|
587
|
+
- "ː > ':' ; # 02D0;MODIFIER LETTER TRIANGULAR COLON"
|
588
|
+
- "˜ > '~' ; # 02DC;SMALL TILDE"
|
576
589
|
- "‖ > '||' ; # 2016;DOUBLE VERTICAL LINE"
|
577
590
|
- "․ > '.' ; # 2024;ONE DOT LEADER (compat)"
|
578
591
|
- "‥ > '..' ; # 2025;TWO DOT LEADER (compat)"
|
@@ -677,6 +690,8 @@
|
|
677
690
|
- "、 > ',' ; # FF64;HALFWIDTH IDEOGRAPHIC COMMA (compat)"
|
678
691
|
- "× > '*' ; # 00D7;MULTIPLICATION SIGN"
|
679
692
|
- "÷ > '/' ; # 00F7;DIVISION SIGN"
|
693
|
+
- "˖ > '+' ; # 02D6;MODIFIER LETTER PLUS SIGN"
|
694
|
+
- "˗ > '-' ; # 02D7;MODIFIER LETTER MINUS SIGN"
|
680
695
|
- "− > '-' ; # 2212;MINUS SIGN (from ‹character-fallback›)"
|
681
696
|
- "∕ > '/' ; # 2215;DIVISION SLASH (from ‹character-fallback›)"
|
682
697
|
- "∖ > '\\' ; # 2216;SET MINUS (from ‹character-fallback›)"
|
@@ -68,7 +68,7 @@
|
|
68
68
|
- $u=\uE041;
|
69
69
|
- $uu=\uE042;
|
70
70
|
- $rh=\uE043;
|
71
|
-
- $
|
71
|
+
- $rrh=\uE044;
|
72
72
|
- "$ce=\\uE045; #VOWEL SIGN CANDRA E"
|
73
73
|
- "$se=\\uE046; #VOWEL SIGN SHORT E"
|
74
74
|
- $e=\uE047;
|
@@ -92,7 +92,7 @@
|
|
92
92
|
- $uya=\uE05F;
|
93
93
|
- $wrr=\uE060;
|
94
94
|
- $wll=\uE061;
|
95
|
-
- $
|
95
|
+
- $lh=\uE062;
|
96
96
|
- $llh=\uE063;
|
97
97
|
- $danda=\uE064;
|
98
98
|
- $doubleDanda=\uE065;
|
@@ -0,0 +1,90 @@
|
|
1
|
+
---
|
2
|
+
:transforms:
|
3
|
+
-
|
4
|
+
:direction: both
|
5
|
+
:rules:
|
6
|
+
- "::NFD(NFC);"
|
7
|
+
- "ev <> և ;"
|
8
|
+
- "tʻ <> թ ;"
|
9
|
+
- "čʻ <> չ ;"
|
10
|
+
- "cʻ <> ց ;"
|
11
|
+
- "pʻ <> փ ;"
|
12
|
+
- "kʻ <> ք ;"
|
13
|
+
- "u <> ու ;"
|
14
|
+
- "a <> ա ;"
|
15
|
+
- "b <> բ ;"
|
16
|
+
- "g <> գ ;"
|
17
|
+
- "d <> դ ;"
|
18
|
+
- "e <> ե ;"
|
19
|
+
- "z <> զ ;"
|
20
|
+
- "ē <> է ;"
|
21
|
+
- "ə <> ը ;"
|
22
|
+
- "ž <> ժ ;"
|
23
|
+
- "i <> ի ;"
|
24
|
+
- "l <> լ ;"
|
25
|
+
- "x <> խ ;"
|
26
|
+
- "c <> ծ ;"
|
27
|
+
- "k <> կ ;"
|
28
|
+
- "h <> հ ;"
|
29
|
+
- "j <> ձ ;"
|
30
|
+
- "ġ <> ղ ;"
|
31
|
+
- "č <> ճ ;"
|
32
|
+
- "m <> մ ;"
|
33
|
+
- "y <> յ ;"
|
34
|
+
- "n <> ն ;"
|
35
|
+
- "š <> շ ;"
|
36
|
+
- "o <> ո ;"
|
37
|
+
- "p <> պ ;"
|
38
|
+
- "ǰ <> ջ ;"
|
39
|
+
- "ṙ <> ռ ;"
|
40
|
+
- "s <> ս ;"
|
41
|
+
- "v <> վ ;"
|
42
|
+
- "t <> տ ;"
|
43
|
+
- "r <> ր ;"
|
44
|
+
- "w <> ւ ;"
|
45
|
+
- "ō <> օ ;"
|
46
|
+
- "f <> ֆ ;"
|
47
|
+
- "U <> ՈՒ ;"
|
48
|
+
- "EV <> ԵՒ ;"
|
49
|
+
- "J̌ <> Ջ ;"
|
50
|
+
- "Pʻ <> Փ ;"
|
51
|
+
- "Kʻ <> Ք ;"
|
52
|
+
- "Tʻ <> Թ ;"
|
53
|
+
- "Čʻ <> Չ ;"
|
54
|
+
- "Cʻ <> Ց ;"
|
55
|
+
- "A <> Ա ;"
|
56
|
+
- "B <> Բ ;"
|
57
|
+
- "G <> Գ ;"
|
58
|
+
- "D <> Դ ;"
|
59
|
+
- "E <> Ե ;"
|
60
|
+
- "Z <> Զ ;"
|
61
|
+
- "Ē <> Է ;"
|
62
|
+
- "Ə <> Ը ;"
|
63
|
+
- "Ž <> Ժ ;"
|
64
|
+
- "I <> Ի ;"
|
65
|
+
- "L <> Լ ;"
|
66
|
+
- "X <> Խ ;"
|
67
|
+
- "C <> Ծ ;"
|
68
|
+
- "K <> Կ ;"
|
69
|
+
- "H <> Հ ;"
|
70
|
+
- "J <> Ձ ;"
|
71
|
+
- "Ġ <> Ղ ;"
|
72
|
+
- "Č <> Ճ ;"
|
73
|
+
- "M <> Մ ;"
|
74
|
+
- "Y <> Յ ;"
|
75
|
+
- "N <> Ն ;"
|
76
|
+
- "Š <> Շ ;"
|
77
|
+
- "O <> Ո ;"
|
78
|
+
- "P <> Պ ;"
|
79
|
+
- "Ṙ <> Ռ ;"
|
80
|
+
- "S <> Ս ;"
|
81
|
+
- "V <> Վ ;"
|
82
|
+
- "T <> Տ ;"
|
83
|
+
- "R <> Ր ;"
|
84
|
+
- "W <> Ւ ;"
|
85
|
+
- "Ō <> Օ ;"
|
86
|
+
- "F <> Ֆ ;"
|
87
|
+
- "::NFC(NFD);"
|
88
|
+
:source: Latn
|
89
|
+
:target: Armn
|
90
|
+
:variant: ~
|