cldr-transforms 46.0.0-BETA2
This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
- package/LICENSE +41 -0
- package/README.md +27 -0
- package/bower.json +13 -0
- package/package.json +29 -0
- package/transforms/Amharic-Latin-BGN.json +9 -0
- package/transforms/Amharic-Latin-BGN.txt +441 -0
- package/transforms/Any-Accents.json +9 -0
- package/transforms/Any-Accents.txt +270 -0
- package/transforms/Any-Publishing.json +9 -0
- package/transforms/Any-Publishing.txt +63 -0
- package/transforms/Arabic-Latin-BGN.json +9 -0
- package/transforms/Arabic-Latin-BGN.txt +205 -0
- package/transforms/Arabic-Latin.json +11 -0
- package/transforms/Arabic-Latin.txt +181 -0
- package/transforms/Armenian-Latin-BGN.json +9 -0
- package/transforms/Armenian-Latin-BGN.txt +165 -0
- package/transforms/Azerbaijani-Latin-BGN.json +9 -0
- package/transforms/Azerbaijani-Latin-BGN.txt +183 -0
- package/transforms/Belarusian-Latin-BGN.json +9 -0
- package/transforms/Belarusian-Latin-BGN.txt +194 -0
- package/transforms/Bengali-Arabic.json +9 -0
- package/transforms/Bengali-Arabic.txt +7 -0
- package/transforms/Bengali-Devanagari.json +9 -0
- package/transforms/Bengali-Devanagari.txt +7 -0
- package/transforms/Bengali-Gujarati.json +9 -0
- package/transforms/Bengali-Gujarati.txt +7 -0
- package/transforms/Bengali-Gurmukhi.json +9 -0
- package/transforms/Bengali-Gurmukhi.txt +7 -0
- package/transforms/Bengali-InterIndic.json +7 -0
- package/transforms/Bengali-InterIndic.txt +99 -0
- package/transforms/Bengali-Kannada.json +9 -0
- package/transforms/Bengali-Kannada.txt +7 -0
- package/transforms/Bengali-Latin.json +9 -0
- package/transforms/Bengali-Latin.txt +7 -0
- package/transforms/Bengali-Malayalam.json +9 -0
- package/transforms/Bengali-Malayalam.txt +7 -0
- package/transforms/Bengali-Oriya.json +9 -0
- package/transforms/Bengali-Oriya.txt +7 -0
- package/transforms/Bengali-Tamil.json +9 -0
- package/transforms/Bengali-Tamil.txt +7 -0
- package/transforms/Bengali-Telugu.json +9 -0
- package/transforms/Bengali-Telugu.txt +7 -0
- package/transforms/Bengali-ur.json +8 -0
- package/transforms/Bengali-ur.txt +7 -0
- package/transforms/Bulgarian-Latin-BGN.json +9 -0
- package/transforms/Bulgarian-Latin-BGN.txt +237 -0
- package/transforms/CanadianAboriginal-Latin.json +11 -0
- package/transforms/CanadianAboriginal-Latin.txt +184 -0
- package/transforms/Cyrillic-Latin.json +11 -0
- package/transforms/Cyrillic-Latin.txt +280 -0
- package/transforms/Devanagari-Arabic.json +9 -0
- package/transforms/Devanagari-Arabic.txt +7 -0
- package/transforms/Devanagari-Bengali.json +9 -0
- package/transforms/Devanagari-Bengali.txt +7 -0
- package/transforms/Devanagari-Gujarati.json +9 -0
- package/transforms/Devanagari-Gujarati.txt +7 -0
- package/transforms/Devanagari-Gurmukhi.json +9 -0
- package/transforms/Devanagari-Gurmukhi.txt +7 -0
- package/transforms/Devanagari-InterIndic.json +7 -0
- package/transforms/Devanagari-InterIndic.txt +113 -0
- package/transforms/Devanagari-Kannada.json +9 -0
- package/transforms/Devanagari-Kannada.txt +7 -0
- package/transforms/Devanagari-Latin.json +9 -0
- package/transforms/Devanagari-Latin.txt +7 -0
- package/transforms/Devanagari-Malayalam.json +9 -0
- package/transforms/Devanagari-Malayalam.txt +7 -0
- package/transforms/Devanagari-Oriya.json +9 -0
- package/transforms/Devanagari-Oriya.txt +7 -0
- package/transforms/Devanagari-Tamil.json +9 -0
- package/transforms/Devanagari-Tamil.txt +7 -0
- package/transforms/Devanagari-Telugu.json +9 -0
- package/transforms/Devanagari-Telugu.txt +7 -0
- package/transforms/Devanagari-ur.json +8 -0
- package/transforms/Devanagari-ur.txt +7 -0
- package/transforms/Fullwidth-Halfwidth.json +9 -0
- package/transforms/Fullwidth-Halfwidth.txt +261 -0
- package/transforms/Georgian-Latin-BGN.json +9 -0
- package/transforms/Georgian-Latin-BGN.txt +43 -0
- package/transforms/Georgian-Latin-BGN_1981.json +8 -0
- package/transforms/Georgian-Latin-BGN_1981.txt +54 -0
- package/transforms/Georgian-Latin.json +11 -0
- package/transforms/Georgian-Latin.txt +53 -0
- package/transforms/Greek-Latin-BGN.json +9 -0
- package/transforms/Greek-Latin-BGN.txt +419 -0
- package/transforms/Greek-Latin.json +11 -0
- package/transforms/Greek-Latin.txt +251 -0
- package/transforms/Greek_Latin_UNGEGN.json +11 -0
- package/transforms/Greek_Latin_UNGEGN.txt +179 -0
- package/transforms/Gujarati-Arabic.json +9 -0
- package/transforms/Gujarati-Arabic.txt +7 -0
- package/transforms/Gujarati-Bengali.json +9 -0
- package/transforms/Gujarati-Bengali.txt +7 -0
- package/transforms/Gujarati-Devanagari.json +9 -0
- package/transforms/Gujarati-Devanagari.txt +7 -0
- package/transforms/Gujarati-Gurmukhi.json +9 -0
- package/transforms/Gujarati-Gurmukhi.txt +7 -0
- package/transforms/Gujarati-InterIndic.json +7 -0
- package/transforms/Gujarati-InterIndic.txt +89 -0
- package/transforms/Gujarati-Kannada.json +9 -0
- package/transforms/Gujarati-Kannada.txt +7 -0
- package/transforms/Gujarati-Latin.json +9 -0
- package/transforms/Gujarati-Latin.txt +7 -0
- package/transforms/Gujarati-Malayalam.json +9 -0
- package/transforms/Gujarati-Malayalam.txt +7 -0
- package/transforms/Gujarati-Oriya.json +9 -0
- package/transforms/Gujarati-Oriya.txt +7 -0
- package/transforms/Gujarati-Tamil.json +9 -0
- package/transforms/Gujarati-Tamil.txt +7 -0
- package/transforms/Gujarati-Telugu.json +9 -0
- package/transforms/Gujarati-Telugu.txt +7 -0
- package/transforms/Gujarati-ur.json +8 -0
- package/transforms/Gujarati-ur.txt +7 -0
- package/transforms/Gurmukhi-Arabic.json +9 -0
- package/transforms/Gurmukhi-Arabic.txt +7 -0
- package/transforms/Gurmukhi-Bengali.json +9 -0
- package/transforms/Gurmukhi-Bengali.txt +7 -0
- package/transforms/Gurmukhi-Devanagari.json +9 -0
- package/transforms/Gurmukhi-Devanagari.txt +7 -0
- package/transforms/Gurmukhi-Gujarati.json +9 -0
- package/transforms/Gurmukhi-Gujarati.txt +7 -0
- package/transforms/Gurmukhi-InterIndic.json +7 -0
- package/transforms/Gurmukhi-InterIndic.txt +88 -0
- package/transforms/Gurmukhi-Kannada.json +9 -0
- package/transforms/Gurmukhi-Kannada.txt +7 -0
- package/transforms/Gurmukhi-Latin.json +9 -0
- package/transforms/Gurmukhi-Latin.txt +7 -0
- package/transforms/Gurmukhi-Malayalam.json +9 -0
- package/transforms/Gurmukhi-Malayalam.txt +7 -0
- package/transforms/Gurmukhi-Oriya.json +9 -0
- package/transforms/Gurmukhi-Oriya.txt +7 -0
- package/transforms/Gurmukhi-Tamil.json +9 -0
- package/transforms/Gurmukhi-Tamil.txt +7 -0
- package/transforms/Gurmukhi-Telugu.json +9 -0
- package/transforms/Gurmukhi-Telugu.txt +7 -0
- package/transforms/Gurmukhi-ur.json +8 -0
- package/transforms/Gurmukhi-ur.txt +7 -0
- package/transforms/Han-Latin-Names.json +8 -0
- package/transforms/Han-Latin-Names.txt +65 -0
- package/transforms/Han-Latin.json +9 -0
- package/transforms/Han-Latin.txt +1501 -0
- package/transforms/Han-Spacedhan.json +7 -0
- package/transforms/Han-Spacedhan.txt +35 -0
- package/transforms/Hangul-Latin.json +9 -0
- package/transforms/Hangul-Latin.txt +6 -0
- package/transforms/Hebrew-Latin-BGN.json +9 -0
- package/transforms/Hebrew-Latin-BGN.txt +113 -0
- package/transforms/Hebrew-Latin.json +11 -0
- package/transforms/Hebrew-Latin.txt +91 -0
- package/transforms/Hiragana-Katakana.json +11 -0
- package/transforms/Hiragana-Katakana.txt +179 -0
- package/transforms/Hiragana-Latin.json +11 -0
- package/transforms/Hiragana-Latin.txt +9 -0
- package/transforms/IPA-XSampa.json +11 -0
- package/transforms/IPA-XSampa.txt +228 -0
- package/transforms/InterIndic-Arabic.json +7 -0
- package/transforms/InterIndic-Arabic.txt +128 -0
- package/transforms/InterIndic-Bengali.json +7 -0
- package/transforms/InterIndic-Bengali.txt +135 -0
- package/transforms/InterIndic-Devanagari.json +7 -0
- package/transforms/InterIndic-Devanagari.txt +151 -0
- package/transforms/InterIndic-Gujarati.json +7 -0
- package/transforms/InterIndic-Gujarati.txt +136 -0
- package/transforms/InterIndic-Gurmukhi.json +7 -0
- package/transforms/InterIndic-Gurmukhi.txt +142 -0
- package/transforms/InterIndic-Kannada.json +7 -0
- package/transforms/InterIndic-Kannada.txt +137 -0
- package/transforms/InterIndic-Latin.json +7 -0
- package/transforms/InterIndic-Latin.txt +492 -0
- package/transforms/InterIndic-Malayalam.json +7 -0
- package/transforms/InterIndic-Malayalam.txt +137 -0
- package/transforms/InterIndic-Oriya.json +7 -0
- package/transforms/InterIndic-Oriya.txt +135 -0
- package/transforms/InterIndic-Tamil.json +7 -0
- package/transforms/InterIndic-Tamil.txt +136 -0
- package/transforms/InterIndic-Telugu.json +7 -0
- package/transforms/InterIndic-Telugu.txt +136 -0
- package/transforms/InterIndic-ur.json +7 -0
- package/transforms/InterIndic-ur.txt +119 -0
- package/transforms/Jamo-Latin.json +9 -0
- package/transforms/Jamo-Latin.txt +6 -0
- package/transforms/Kannada-Arabic.json +9 -0
- package/transforms/Kannada-Arabic.txt +7 -0
- package/transforms/Kannada-Bengali.json +9 -0
- package/transforms/Kannada-Bengali.txt +7 -0
- package/transforms/Kannada-Devanagari.json +9 -0
- package/transforms/Kannada-Devanagari.txt +7 -0
- package/transforms/Kannada-Gujarati.json +9 -0
- package/transforms/Kannada-Gujarati.txt +7 -0
- package/transforms/Kannada-Gurmukhi.json +9 -0
- package/transforms/Kannada-Gurmukhi.txt +7 -0
- package/transforms/Kannada-InterIndic.json +7 -0
- package/transforms/Kannada-InterIndic.txt +87 -0
- package/transforms/Kannada-Latin.json +9 -0
- package/transforms/Kannada-Latin.txt +7 -0
- package/transforms/Kannada-Malayalam.json +9 -0
- package/transforms/Kannada-Malayalam.txt +7 -0
- package/transforms/Kannada-Oriya.json +9 -0
- package/transforms/Kannada-Oriya.txt +7 -0
- package/transforms/Kannada-Tamil.json +9 -0
- package/transforms/Kannada-Tamil.txt +7 -0
- package/transforms/Kannada-Telugu.json +9 -0
- package/transforms/Kannada-Telugu.txt +7 -0
- package/transforms/Kannada-ur.json +8 -0
- package/transforms/Kannada-ur.txt +7 -0
- package/transforms/Katakana-Latin-BGN.json +9 -0
- package/transforms/Katakana-Latin-BGN.txt +335 -0
- package/transforms/Kazakh-Latin-BGN.json +9 -0
- package/transforms/Kazakh-Latin-BGN.txt +332 -0
- package/transforms/Kirghiz-Latin-BGN.json +9 -0
- package/transforms/Kirghiz-Latin-BGN.txt +211 -0
- package/transforms/Korean-Latin-BGN.json +9 -0
- package/transforms/Korean-Latin-BGN.txt +345 -0
- package/transforms/Latin-ASCII.json +9 -0
- package/transforms/Latin-ASCII.txt +909 -0
- package/transforms/Latin-Armenian.json +11 -0
- package/transforms/Latin-Armenian.txt +88 -0
- package/transforms/Latin-Bengali.json +9 -0
- package/transforms/Latin-Bengali.txt +8 -0
- package/transforms/Latin-Bopomofo.json +11 -0
- package/transforms/Latin-Bopomofo.txt +1445 -0
- package/transforms/Latin-ConjoiningJamo.json +7 -0
- package/transforms/Latin-ConjoiningJamo.txt +477 -0
- package/transforms/Latin-Devanagari.json +9 -0
- package/transforms/Latin-Devanagari.txt +8 -0
- package/transforms/Latin-Ethiopic.json +11 -0
- package/transforms/Latin-Ethiopic.txt +277 -0
- package/transforms/Latin-Gujarati.json +9 -0
- package/transforms/Latin-Gujarati.txt +8 -0
- package/transforms/Latin-Gurmukhi.json +9 -0
- package/transforms/Latin-Gurmukhi.txt +8 -0
- package/transforms/Latin-Hangul.json +9 -0
- package/transforms/Latin-Hangul.txt +7 -0
- package/transforms/Latin-InterIndic.json +7 -0
- package/transforms/Latin-InterIndic.txt +377 -0
- package/transforms/Latin-Jamo.json +9 -0
- package/transforms/Latin-Jamo.txt +7 -0
- package/transforms/Latin-Kannada.json +9 -0
- package/transforms/Latin-Kannada.txt +8 -0
- package/transforms/Latin-Katakana.json +11 -0
- package/transforms/Latin-Katakana.txt +382 -0
- package/transforms/Latin-Malayalam.json +9 -0
- package/transforms/Latin-Malayalam.txt +8 -0
- package/transforms/Latin-NumericPinyin.json +9 -0
- package/transforms/Latin-NumericPinyin.txt +29 -0
- package/transforms/Latin-Oriya.json +9 -0
- package/transforms/Latin-Oriya.txt +8 -0
- package/transforms/Latin-Tamil.json +9 -0
- package/transforms/Latin-Tamil.txt +8 -0
- package/transforms/Latin-Telugu.json +9 -0
- package/transforms/Latin-Telugu.txt +8 -0
- package/transforms/Latin-Thai.json +9 -0
- package/transforms/Latin-Thai.txt +7 -0
- package/transforms/Macedonian-Latin-BGN.json +9 -0
- package/transforms/Macedonian-Latin-BGN.txt +176 -0
- package/transforms/Malayalam-Arabic.json +9 -0
- package/transforms/Malayalam-Arabic.txt +7 -0
- package/transforms/Malayalam-Bengali.json +9 -0
- package/transforms/Malayalam-Bengali.txt +7 -0
- package/transforms/Malayalam-Devanagari.json +9 -0
- package/transforms/Malayalam-Devanagari.txt +7 -0
- package/transforms/Malayalam-Gujarati.json +9 -0
- package/transforms/Malayalam-Gujarati.txt +7 -0
- package/transforms/Malayalam-Gurmukhi.json +9 -0
- package/transforms/Malayalam-Gurmukhi.txt +7 -0
- package/transforms/Malayalam-InterIndic.json +7 -0
- package/transforms/Malayalam-InterIndic.txt +87 -0
- package/transforms/Malayalam-Kannada.json +9 -0
- package/transforms/Malayalam-Kannada.txt +7 -0
- package/transforms/Malayalam-Latin.json +9 -0
- package/transforms/Malayalam-Latin.txt +7 -0
- package/transforms/Malayalam-Oriya.json +9 -0
- package/transforms/Malayalam-Oriya.txt +7 -0
- package/transforms/Malayalam-Tamil.json +9 -0
- package/transforms/Malayalam-Tamil.txt +7 -0
- package/transforms/Malayalam-Telugu.json +9 -0
- package/transforms/Malayalam-Telugu.txt +7 -0
- package/transforms/Malayalam-ur.json +8 -0
- package/transforms/Malayalam-ur.txt +7 -0
- package/transforms/Maldivian-Latin-BGN.json +9 -0
- package/transforms/Maldivian-Latin-BGN.txt +171 -0
- package/transforms/Mongolian-Latin-BGN.json +9 -0
- package/transforms/Mongolian-Latin-BGN.txt +151 -0
- package/transforms/Myanmar-Latin.json +9 -0
- package/transforms/Myanmar-Latin.txt +367 -0
- package/transforms/Oriya-Arabic.json +9 -0
- package/transforms/Oriya-Arabic.txt +7 -0
- package/transforms/Oriya-Bengali.json +9 -0
- package/transforms/Oriya-Bengali.txt +7 -0
- package/transforms/Oriya-Devanagari.json +9 -0
- package/transforms/Oriya-Devanagari.txt +7 -0
- package/transforms/Oriya-Gujarati.json +9 -0
- package/transforms/Oriya-Gujarati.txt +7 -0
- package/transforms/Oriya-Gurmukhi.json +9 -0
- package/transforms/Oriya-Gurmukhi.txt +7 -0
- package/transforms/Oriya-InterIndic.json +7 -0
- package/transforms/Oriya-InterIndic.txt +91 -0
- package/transforms/Oriya-Kannada.json +9 -0
- package/transforms/Oriya-Kannada.txt +7 -0
- package/transforms/Oriya-Latin.json +9 -0
- package/transforms/Oriya-Latin.txt +7 -0
- package/transforms/Oriya-Malayalam.json +9 -0
- package/transforms/Oriya-Malayalam.txt +7 -0
- package/transforms/Oriya-Tamil.json +9 -0
- package/transforms/Oriya-Tamil.txt +7 -0
- package/transforms/Oriya-Telugu.json +9 -0
- package/transforms/Oriya-Telugu.txt +7 -0
- package/transforms/Oriya-ur.json +8 -0
- package/transforms/Oriya-ur.txt +7 -0
- package/transforms/Pashto-Latin-BGN.json +9 -0
- package/transforms/Pashto-Latin-BGN.txt +231 -0
- package/transforms/Persian-Latin-BGN.json +9 -0
- package/transforms/Persian-Latin-BGN.txt +203 -0
- package/transforms/Pinyin-NumericPinyin.json +7 -0
- package/transforms/Pinyin-NumericPinyin.txt +8 -0
- package/transforms/Russian-Latin-BGN.json +9 -0
- package/transforms/Russian-Latin-BGN.txt +235 -0
- package/transforms/Serbian-Latin-BGN.json +9 -0
- package/transforms/Serbian-Latin-BGN.txt +119 -0
- package/transforms/Simplified-Traditional.json +11 -0
- package/transforms/Simplified-Traditional.txt +4393 -0
- package/transforms/Syriac-Latin.json +11 -0
- package/transforms/Syriac-Latin.txt +52 -0
- package/transforms/Tamil-Arabic.json +9 -0
- package/transforms/Tamil-Arabic.txt +7 -0
- package/transforms/Tamil-Bengali.json +9 -0
- package/transforms/Tamil-Bengali.txt +7 -0
- package/transforms/Tamil-Devanagari.json +9 -0
- package/transforms/Tamil-Devanagari.txt +7 -0
- package/transforms/Tamil-Gujarati.json +9 -0
- package/transforms/Tamil-Gujarati.txt +7 -0
- package/transforms/Tamil-Gurmukhi.json +9 -0
- package/transforms/Tamil-Gurmukhi.txt +7 -0
- package/transforms/Tamil-InterIndic.json +7 -0
- package/transforms/Tamil-InterIndic.txt +70 -0
- package/transforms/Tamil-Kannada.json +9 -0
- package/transforms/Tamil-Kannada.txt +7 -0
- package/transforms/Tamil-Latin.json +9 -0
- package/transforms/Tamil-Latin.txt +7 -0
- package/transforms/Tamil-Malayalam.json +9 -0
- package/transforms/Tamil-Malayalam.txt +7 -0
- package/transforms/Tamil-Oriya.json +9 -0
- package/transforms/Tamil-Oriya.txt +7 -0
- package/transforms/Tamil-Telugu.json +9 -0
- package/transforms/Tamil-Telugu.txt +7 -0
- package/transforms/Tamil-ur.json +8 -0
- package/transforms/Tamil-ur.txt +7 -0
- package/transforms/Telugu-Arabic.json +9 -0
- package/transforms/Telugu-Arabic.txt +7 -0
- package/transforms/Telugu-Bengali.json +9 -0
- package/transforms/Telugu-Bengali.txt +7 -0
- package/transforms/Telugu-Devanagari.json +9 -0
- package/transforms/Telugu-Devanagari.txt +7 -0
- package/transforms/Telugu-Gujarati.json +9 -0
- package/transforms/Telugu-Gujarati.txt +7 -0
- package/transforms/Telugu-Gurmukhi.json +9 -0
- package/transforms/Telugu-Gurmukhi.txt +7 -0
- package/transforms/Telugu-InterIndic.json +7 -0
- package/transforms/Telugu-InterIndic.txt +87 -0
- package/transforms/Telugu-Kannada.json +9 -0
- package/transforms/Telugu-Kannada.txt +7 -0
- package/transforms/Telugu-Latin.json +9 -0
- package/transforms/Telugu-Latin.txt +7 -0
- package/transforms/Telugu-Malayalam.json +9 -0
- package/transforms/Telugu-Malayalam.txt +7 -0
- package/transforms/Telugu-Oriya.json +9 -0
- package/transforms/Telugu-Oriya.txt +7 -0
- package/transforms/Telugu-Tamil.json +9 -0
- package/transforms/Telugu-Tamil.txt +7 -0
- package/transforms/Telugu-ur.json +8 -0
- package/transforms/Telugu-ur.txt +7 -0
- package/transforms/Thaana-Latin.json +11 -0
- package/transforms/Thaana-Latin.txt +433 -0
- package/transforms/Thai-Latin.json +9 -0
- package/transforms/Thai-Latin.txt +9 -0
- package/transforms/Thai-ThaiLogical.json +7 -0
- package/transforms/Thai-ThaiLogical.txt +16 -0
- package/transforms/Thai-ThaiSemi.json +7 -0
- package/transforms/Thai-ThaiSemi.txt +6 -0
- package/transforms/ThaiLogical-Latin.json +7 -0
- package/transforms/ThaiLogical-Latin.txt +147 -0
- package/transforms/Turkmen-Latin-BGN.json +9 -0
- package/transforms/Turkmen-Latin-BGN.txt +302 -0
- package/transforms/Ukrainian-Latin-BGN.json +9 -0
- package/transforms/Ukrainian-Latin-BGN.txt +283 -0
- package/transforms/Uzbek-Latin-BGN.json +9 -0
- package/transforms/Uzbek-Latin-BGN.txt +261 -0
- package/transforms/am-Ethi-t-am-brai.json +11 -0
- package/transforms/am-Ethi-t-am-brai.txt +652 -0
- package/transforms/am-Ethi-t-am-ethi-m0-geminate.json +9 -0
- package/transforms/am-Ethi-t-am-ethi-m0-geminate.txt +6925 -0
- package/transforms/am-Ethi-t-d0-morse.json +9 -0
- package/transforms/am-Ethi-t-d0-morse.txt +657 -0
- package/transforms/am-am_FONIPA.json +9 -0
- package/transforms/am-am_FONIPA.txt +694 -0
- package/transforms/am-ar.json +8 -0
- package/transforms/am-ar.txt +5 -0
- package/transforms/am-chr.json +8 -0
- package/transforms/am-chr.txt +4 -0
- package/transforms/am-fa.json +8 -0
- package/transforms/am-fa.txt +4 -0
- package/transforms/az-Lower.json +8 -0
- package/transforms/az-Lower.txt +13 -0
- package/transforms/az-Title.json +8 -0
- package/transforms/az-Title.txt +11 -0
- package/transforms/az-Upper.json +8 -0
- package/transforms/az-Upper.txt +5 -0
- package/transforms/blt-fonipa-t-blt.json +8 -0
- package/transforms/blt-fonipa-t-blt.txt +132 -0
- package/transforms/byn-Ethi-t-byn-latn-m0-tekie-alibekit.json +11 -0
- package/transforms/byn-Ethi-t-byn-latn-m0-tekie-alibekit.txt +537 -0
- package/transforms/byn-Ethi-t-byn-latn-m0-xaleget.json +11 -0
- package/transforms/byn-Ethi-t-byn-latn-m0-xaleget.txt +773 -0
- package/transforms/ch-am.json +8 -0
- package/transforms/ch-am.txt +4 -0
- package/transforms/ch-ar.json +8 -0
- package/transforms/ch-ar.txt +4 -0
- package/transforms/ch-ch_FONIPA.json +8 -0
- package/transforms/ch-ch_FONIPA.txt +79 -0
- package/transforms/ch-chr.json +8 -0
- package/transforms/ch-chr.txt +4 -0
- package/transforms/ch-fa.json +8 -0
- package/transforms/ch-fa.txt +4 -0
- package/transforms/chr-chr_FONIPA.json +8 -0
- package/transforms/chr-chr_FONIPA.txt +111 -0
- package/transforms/cs-am.json +8 -0
- package/transforms/cs-am.txt +4 -0
- package/transforms/cs-ar.json +8 -0
- package/transforms/cs-ar.txt +4 -0
- package/transforms/cs-chr.json +8 -0
- package/transforms/cs-chr.txt +4 -0
- package/transforms/cs-cs_FONIPA.json +8 -0
- package/transforms/cs-cs_FONIPA.txt +74 -0
- package/transforms/cs-fa.json +8 -0
- package/transforms/cs-fa.txt +4 -0
- package/transforms/cs-ja.json +8 -0
- package/transforms/cs-ja.txt +4 -0
- package/transforms/cs-ko.json +8 -0
- package/transforms/cs-ko.txt +4 -0
- package/transforms/cs_FONIPA-ja.json +8 -0
- package/transforms/cs_FONIPA-ja.txt +228 -0
- package/transforms/cs_FONIPA-ko.json +8 -0
- package/transforms/cs_FONIPA-ko.txt +88 -0
- package/transforms/cy-fonipa-t-cy.json +8 -0
- package/transforms/cy-fonipa-t-cy.txt +189 -0
- package/transforms/de-ASCII.json +8 -0
- package/transforms/de-ASCII.txt +15 -0
- package/transforms/dsb-dsb_FONIPA.json +8 -0
- package/transforms/dsb-dsb_FONIPA.txt +67 -0
- package/transforms/el-Lower.json +8 -0
- package/transforms/el-Lower.txt +12 -0
- package/transforms/el-Title.json +8 -0
- package/transforms/el-Title.txt +12 -0
- package/transforms/el-Upper.json +8 -0
- package/transforms/el-Upper.txt +11 -0
- package/transforms/eo-am.json +8 -0
- package/transforms/eo-am.txt +4 -0
- package/transforms/eo-ar.json +8 -0
- package/transforms/eo-ar.txt +4 -0
- package/transforms/eo-chr.json +8 -0
- package/transforms/eo-chr.txt +4 -0
- package/transforms/eo-eo_FONIPA.json +8 -0
- package/transforms/eo-eo_FONIPA.txt +47 -0
- package/transforms/eo-fa.json +8 -0
- package/transforms/eo-fa.txt +4 -0
- package/transforms/es-am.json +8 -0
- package/transforms/es-am.txt +4 -0
- package/transforms/es-ar.json +8 -0
- package/transforms/es-ar.txt +13 -0
- package/transforms/es-chr.json +8 -0
- package/transforms/es-chr.txt +4 -0
- package/transforms/es-es_FONIPA.json +8 -0
- package/transforms/es-es_FONIPA.txt +139 -0
- package/transforms/es-fa.json +8 -0
- package/transforms/es-fa.txt +13 -0
- package/transforms/es-ja.json +8 -0
- package/transforms/es-ja.txt +4 -0
- package/transforms/es-zh.json +8 -0
- package/transforms/es-zh.txt +4 -0
- package/transforms/es_419-am.json +8 -0
- package/transforms/es_419-am.txt +5 -0
- package/transforms/es_419-ar.json +8 -0
- package/transforms/es_419-ar.txt +14 -0
- package/transforms/es_419-chr.json +8 -0
- package/transforms/es_419-chr.txt +5 -0
- package/transforms/es_419-fa.json +8 -0
- package/transforms/es_419-fa.txt +14 -0
- package/transforms/es_419-ja.json +8 -0
- package/transforms/es_419-ja.txt +5 -0
- package/transforms/es_419-zh.json +8 -0
- package/transforms/es_419-zh.txt +5 -0
- package/transforms/es_FONIPA-am.json +8 -0
- package/transforms/es_FONIPA-am.txt +230 -0
- package/transforms/es_FONIPA-es_419_FONIPA.json +8 -0
- package/transforms/es_FONIPA-es_419_FONIPA.txt +6 -0
- package/transforms/es_FONIPA-ja.json +8 -0
- package/transforms/es_FONIPA-ja.txt +155 -0
- package/transforms/es_FONIPA-zh.json +8 -0
- package/transforms/es_FONIPA-zh.txt +522 -0
- package/transforms/fa-fa_FONIPA.json +8 -0
- package/transforms/fa-fa_FONIPA.txt +107 -0
- package/transforms/gz-Ethi-t-und-sarb.json +11 -0
- package/transforms/gz-Ethi-t-und-sarb.txt +180 -0
- package/transforms/ha-ha_NE.json +8 -0
- package/transforms/ha-ha_NE.txt +6 -0
- package/transforms/hy-am.json +8 -0
- package/transforms/hy-am.txt +4 -0
- package/transforms/hy-ar.json +8 -0
- package/transforms/hy-ar.txt +4 -0
- package/transforms/hy-chr.json +8 -0
- package/transforms/hy-chr.txt +4 -0
- package/transforms/hy-fa.json +8 -0
- package/transforms/hy-fa.txt +4 -0
- package/transforms/hy-hy_FONIPA.json +8 -0
- package/transforms/hy-hy_FONIPA.txt +52 -0
- package/transforms/hy_AREVMDA-am.json +8 -0
- package/transforms/hy_AREVMDA-am.txt +4 -0
- package/transforms/hy_AREVMDA-ar.json +8 -0
- package/transforms/hy_AREVMDA-ar.txt +4 -0
- package/transforms/hy_AREVMDA-chr.json +8 -0
- package/transforms/hy_AREVMDA-chr.txt +4 -0
- package/transforms/hy_AREVMDA-fa.json +8 -0
- package/transforms/hy_AREVMDA-fa.txt +4 -0
- package/transforms/hy_AREVMDA-hy_AREVMDA_FONIPA.json +8 -0
- package/transforms/hy_AREVMDA-hy_AREVMDA_FONIPA.txt +80 -0
- package/transforms/ia-am.json +8 -0
- package/transforms/ia-am.txt +4 -0
- package/transforms/ia-ar.json +8 -0
- package/transforms/ia-ar.txt +4 -0
- package/transforms/ia-chr.json +8 -0
- package/transforms/ia-chr.txt +4 -0
- package/transforms/ia-fa.json +8 -0
- package/transforms/ia-fa.txt +4 -0
- package/transforms/ia-ia_FONIPA.json +8 -0
- package/transforms/ia-ia_FONIPA.txt +71 -0
- package/transforms/it-am.json +8 -0
- package/transforms/it-am.txt +257 -0
- package/transforms/it-ja.json +8 -0
- package/transforms/it-ja.txt +259 -0
- package/transforms/ja_Latn-ko.json +8 -0
- package/transforms/ja_Latn-ko.txt +141 -0
- package/transforms/ja_Latn-ru.json +8 -0
- package/transforms/ja_Latn-ru.txt +123 -0
- package/transforms/kk-am.json +8 -0
- package/transforms/kk-am.txt +4 -0
- package/transforms/kk-ar.json +8 -0
- package/transforms/kk-ar.txt +4 -0
- package/transforms/kk-chr.json +8 -0
- package/transforms/kk-chr.txt +4 -0
- package/transforms/kk-fa.json +8 -0
- package/transforms/kk-fa.txt +4 -0
- package/transforms/kk-kk_FONIPA.json +8 -0
- package/transforms/kk-kk_FONIPA.txt +59 -0
- package/transforms/ky-am.json +8 -0
- package/transforms/ky-am.txt +4 -0
- package/transforms/ky-ar.json +8 -0
- package/transforms/ky-ar.txt +4 -0
- package/transforms/ky-chr.json +8 -0
- package/transforms/ky-chr.txt +4 -0
- package/transforms/ky-fa.json +8 -0
- package/transforms/ky-fa.txt +4 -0
- package/transforms/ky-ky_FONIPA.json +8 -0
- package/transforms/ky-ky_FONIPA.txt +71 -0
- package/transforms/la-la_FONIPA.json +8 -0
- package/transforms/la-la_FONIPA.txt +79 -0
- package/transforms/lt-Lower.json +8 -0
- package/transforms/lt-Lower.txt +20 -0
- package/transforms/lt-Title.json +8 -0
- package/transforms/lt-Title.txt +15 -0
- package/transforms/lt-Upper.json +8 -0
- package/transforms/lt-Upper.txt +8 -0
- package/transforms/mn-mn_Latn-MNS.json +8 -0
- package/transforms/mn-mn_Latn-MNS.txt +86 -0
- package/transforms/my-am.json +8 -0
- package/transforms/my-am.txt +4 -0
- package/transforms/my-ar.json +8 -0
- package/transforms/my-ar.txt +4 -0
- package/transforms/my-chr.json +8 -0
- package/transforms/my-chr.txt +4 -0
- package/transforms/my-fa.json +8 -0
- package/transforms/my-fa.txt +4 -0
- package/transforms/my-my_FONIPA.json +8 -0
- package/transforms/my-my_FONIPA.txt +325 -0
- package/transforms/my-t-my-d0-zawgyi.json +8 -0
- package/transforms/my-t-my-d0-zawgyi.txt +222 -0
- package/transforms/my-t-my-s0-zawgyi.json +8 -0
- package/transforms/my-t-my-s0-zawgyi.txt +231 -0
- package/transforms/nl-Title.json +8 -0
- package/transforms/nl-Title.txt +7 -0
- package/transforms/nv-nv_FONIPA.json +8 -0
- package/transforms/nv-nv_FONIPA.txt +74 -0
- package/transforms/pl-am.json +8 -0
- package/transforms/pl-am.txt +4 -0
- package/transforms/pl-ar.json +8 -0
- package/transforms/pl-ar.txt +4 -0
- package/transforms/pl-chr.json +8 -0
- package/transforms/pl-chr.txt +4 -0
- package/transforms/pl-fa.json +8 -0
- package/transforms/pl-fa.txt +4 -0
- package/transforms/pl-ja.json +8 -0
- package/transforms/pl-ja.txt +4 -0
- package/transforms/pl-pl_FONIPA.json +8 -0
- package/transforms/pl-pl_FONIPA.txt +113 -0
- package/transforms/pl_FONIPA-ja.json +8 -0
- package/transforms/pl_FONIPA-ja.txt +301 -0
- package/transforms/rm_SURSILV-am.json +8 -0
- package/transforms/rm_SURSILV-am.txt +4 -0
- package/transforms/rm_SURSILV-ar.json +8 -0
- package/transforms/rm_SURSILV-ar.txt +4 -0
- package/transforms/rm_SURSILV-chr.json +8 -0
- package/transforms/rm_SURSILV-chr.txt +4 -0
- package/transforms/rm_SURSILV-fa.json +8 -0
- package/transforms/rm_SURSILV-fa.txt +4 -0
- package/transforms/rm_SURSILV-rm_FONIPA_SURSILV.json +8 -0
- package/transforms/rm_SURSILV-rm_FONIPA_SURSILV.txt +96 -0
- package/transforms/ro-am.json +8 -0
- package/transforms/ro-am.txt +4 -0
- package/transforms/ro-ar.json +8 -0
- package/transforms/ro-ar.txt +4 -0
- package/transforms/ro-chr.json +8 -0
- package/transforms/ro-chr.txt +4 -0
- package/transforms/ro-fa.json +8 -0
- package/transforms/ro-fa.txt +4 -0
- package/transforms/ro-ja.json +8 -0
- package/transforms/ro-ja.txt +4 -0
- package/transforms/ro-ro_FONIPA.json +8 -0
- package/transforms/ro-ro_FONIPA.txt +121 -0
- package/transforms/ro_FONIPA-ja.json +8 -0
- package/transforms/ro_FONIPA-ja.txt +211 -0
- package/transforms/ru-ja.json +8 -0
- package/transforms/ru-ja.txt +444 -0
- package/transforms/ru-zh.json +8 -0
- package/transforms/ru-zh.txt +996 -0
- package/transforms/ru_Latn-ru-BGN.json +9 -0
- package/transforms/ru_Latn-ru-BGN.txt +97 -0
- package/transforms/sat-am.json +8 -0
- package/transforms/sat-am.txt +6 -0
- package/transforms/sat-ar.json +8 -0
- package/transforms/sat-ar.txt +6 -0
- package/transforms/sat-chr.json +8 -0
- package/transforms/sat-chr.txt +6 -0
- package/transforms/sat-fa.json +8 -0
- package/transforms/sat-fa.txt +6 -0
- package/transforms/sat_Olck-sat_FONIPA.json +8 -0
- package/transforms/sat_Olck-sat_FONIPA.txt +174 -0
- package/transforms/sgw-Ethi-t-und-ethi.json +11 -0
- package/transforms/sgw-Ethi-t-und-ethi.txt +138 -0
- package/transforms/si-am.json +8 -0
- package/transforms/si-am.txt +4 -0
- package/transforms/si-ar.json +8 -0
- package/transforms/si-ar.txt +4 -0
- package/transforms/si-chr.json +8 -0
- package/transforms/si-chr.txt +4 -0
- package/transforms/si-fa.json +8 -0
- package/transforms/si-fa.txt +4 -0
- package/transforms/si-si_FONIPA.json +8 -0
- package/transforms/si-si_FONIPA.txt +157 -0
- package/transforms/si-si_Latn.json +8 -0
- package/transforms/si-si_Latn.txt +94 -0
- package/transforms/sk-am.json +8 -0
- package/transforms/sk-am.txt +4 -0
- package/transforms/sk-ar.json +8 -0
- package/transforms/sk-ar.txt +4 -0
- package/transforms/sk-chr.json +8 -0
- package/transforms/sk-chr.txt +4 -0
- package/transforms/sk-fa.json +8 -0
- package/transforms/sk-fa.txt +4 -0
- package/transforms/sk-ja.json +8 -0
- package/transforms/sk-ja.txt +4 -0
- package/transforms/sk-sk_FONIPA.json +8 -0
- package/transforms/sk-sk_FONIPA.txt +101 -0
- package/transforms/sk_FONIPA-ja.json +8 -0
- package/transforms/sk_FONIPA-ja.txt +252 -0
- package/transforms/ta-ta_FONIPA.json +8 -0
- package/transforms/ta-ta_FONIPA.txt +73 -0
- package/transforms/tlh-am.json +8 -0
- package/transforms/tlh-am.txt +4 -0
- package/transforms/tlh-ar.json +8 -0
- package/transforms/tlh-ar.txt +4 -0
- package/transforms/tlh-chr.json +8 -0
- package/transforms/tlh-chr.txt +4 -0
- package/transforms/tlh-fa.json +8 -0
- package/transforms/tlh-fa.txt +4 -0
- package/transforms/tlh-tlh_FONIPA.json +8 -0
- package/transforms/tlh-tlh_FONIPA.txt +46 -0
- package/transforms/tr-Lower.json +8 -0
- package/transforms/tr-Lower.txt +13 -0
- package/transforms/tr-Title.json +8 -0
- package/transforms/tr-Title.txt +11 -0
- package/transforms/tr-Upper.json +8 -0
- package/transforms/tr-Upper.txt +8 -0
- package/transforms/ug-ug_FONIPA.json +8 -0
- package/transforms/ug-ug_FONIPA.txt +69 -0
- package/transforms/und-Ethi-t-und-cyrl-m0-gutgarts.json +11 -0
- package/transforms/und-Ethi-t-und-cyrl-m0-gutgarts.txt +747 -0
- package/transforms/und-Ethi-t-und-latn-m0-aethiopi-geminate.json +9 -0
- package/transforms/und-Ethi-t-und-latn-m0-aethiopi-geminate.txt +19 -0
- package/transforms/und-Ethi-t-und-latn-m0-aethiopi.json +11 -0
- package/transforms/und-Ethi-t-und-latn-m0-aethiopi.txt +633 -0
- package/transforms/und-Ethi-t-und-latn-m0-alaloc-geminate.json +9 -0
- package/transforms/und-Ethi-t-und-latn-m0-alaloc-geminate.txt +19 -0
- package/transforms/und-Ethi-t-und-latn-m0-alaloc.json +11 -0
- package/transforms/und-Ethi-t-und-latn-m0-alaloc.txt +757 -0
- package/transforms/und-Ethi-t-und-latn-m0-beta_metsehaf-geminate.json +9 -0
- package/transforms/und-Ethi-t-und-latn-m0-beta_metsehaf-geminate.txt +19 -0
- package/transforms/und-Ethi-t-und-latn-m0-beta_metsehaf.json +11 -0
- package/transforms/und-Ethi-t-und-latn-m0-beta_metsehaf.txt +585 -0
- package/transforms/und-Ethi-t-und-latn-m0-es3842.json +9 -0
- package/transforms/und-Ethi-t-und-latn-m0-es3842.txt +640 -0
- package/transforms/und-Ethi-t-und-latn-m0-ies-jes-1964-geminate.json +9 -0
- package/transforms/und-Ethi-t-und-latn-m0-ies-jes-1964-geminate.txt +19 -0
- package/transforms/und-Ethi-t-und-latn-m0-ies-jes-1964.json +11 -0
- package/transforms/und-Ethi-t-und-latn-m0-ies-jes-1964.txt +619 -0
- package/transforms/und-Ethi-t-und-latn-m0-lambdin.json +11 -0
- package/transforms/und-Ethi-t-und-latn-m0-lambdin.txt +627 -0
- package/transforms/und-Ethi-t-und-latn-m0-sera.json +11 -0
- package/transforms/und-Ethi-t-und-latn-m0-sera.txt +695 -0
- package/transforms/und-Ethi-t-und-latn.json +11 -0
- package/transforms/und-Ethi-t-und-latn.txt +16 -0
- package/transforms/und_FONIPA-ar.json +8 -0
- package/transforms/und_FONIPA-ar.txt +114 -0
- package/transforms/und_FONIPA-chr.json +8 -0
- package/transforms/und_FONIPA-chr.txt +172 -0
- package/transforms/und_FONIPA-fa.json +8 -0
- package/transforms/und_FONIPA-fa.txt +109 -0
- package/transforms/uz_Cyrl-uz_Latn.json +9 -0
- package/transforms/uz_Cyrl-uz_Latn.txt +103 -0
- package/transforms/vec-vec_FONIPA.json +8 -0
- package/transforms/vec-vec_FONIPA.txt +85 -0
- package/transforms/xh-am.json +8 -0
- package/transforms/xh-am.txt +4 -0
- package/transforms/xh-ar.json +8 -0
- package/transforms/xh-ar.txt +4 -0
- package/transforms/xh-chr.json +8 -0
- package/transforms/xh-chr.txt +4 -0
- package/transforms/xh-fa.json +8 -0
- package/transforms/xh-fa.txt +4 -0
- package/transforms/xh-xh_FONIPA.json +8 -0
- package/transforms/xh-xh_FONIPA.txt +85 -0
- package/transforms/yo-yo_BJ.json +8 -0
- package/transforms/yo-yo_BJ.txt +36 -0
- package/transforms/zh_Latn_PINYIN-ru.json +8 -0
- package/transforms/zh_Latn_PINYIN-ru.txt +148 -0
- package/transforms/zu-am.json +8 -0
- package/transforms/zu-am.txt +4 -0
- package/transforms/zu-ar.json +8 -0
- package/transforms/zu-ar.txt +4 -0
- package/transforms/zu-chr.json +8 -0
- package/transforms/zu-chr.txt +4 -0
- package/transforms/zu-fa.json +8 -0
- package/transforms/zu-fa.txt +4 -0
- package/transforms/zu-zu_FONIPA.json +8 -0
- package/transforms/zu-zu_FONIPA.txt +72 -0
- package/transforms.json +385 -0
|
@@ -0,0 +1,228 @@
|
|
|
1
|
+
|
|
2
|
+
# Conversion between IPA and X-SAMPA phonetic transcription.
|
|
3
|
+
#
|
|
4
|
+
# See http://www.phon.ucl.ac.uk/home/sampa/x-sampa.htm for a description of
|
|
5
|
+
# X-SAMPA, an ASCII encoding of the International Phonetic Alphabet.
|
|
6
|
+
#
|
|
7
|
+
# The following obsolete or extended IPA symbols have no X-SAMPA equivalents
|
|
8
|
+
# and remain unaffected by this transform:
|
|
9
|
+
#
|
|
10
|
+
# ʞ LATIN SMALL LETTER TURNED K
|
|
11
|
+
# ʩ LATIN SMALL LETTER FENG DIGRAPH
|
|
12
|
+
# ʪ LATIN SMALL LETTER LS DIGRAPH
|
|
13
|
+
# ʫ LATIN SMALL LETTER LZ DIGRAPH
|
|
14
|
+
# ʬ LATIN LETTER BILABIAL PERCUSSIVE
|
|
15
|
+
# ʭ LATIN LETTER BIDENTAL PERCUSSIVE
|
|
16
|
+
#
|
|
17
|
+
# An IPA tie bar is transformed to an X-SAMPA underscore, per the official
|
|
18
|
+
# X-SAMPA guidelines. This can result in certain ambiguities: For example, the
|
|
19
|
+
# labial-velar nasal (http://en.wikipedia.org/wiki/Labial-velar_nasal) can be
|
|
20
|
+
# either written as [ŋ͡m] or [m͡ŋ] in IPA. However, neither version can be
|
|
21
|
+
# represented unambiguously in X-SAMPA: IPA [ŋ͡m] becomes X-SAMPA [N_m], which
|
|
22
|
+
# is also used to represent a hypothetical laminal (_m) velar nasal, IPA [ŋ̻];
|
|
23
|
+
# and IPA [m͡ŋ] becomes X-SAMPA [m_N], which can also represent a linguolabial
|
|
24
|
+
# (_N) nasal, IPA [m̼], which is more appropriately written [n̼]. To avoid
|
|
25
|
+
# unintended ambiguities, it may therefore be advisable to write affricates
|
|
26
|
+
# without tie bars.
|
|
27
|
+
#
|
|
28
|
+
$t = '_'; # X-SAMPA representation of IPA tie bar.
|
|
29
|
+
::NFD(NFC);
|
|
30
|
+
# 5-character X-SAMPA representations
|
|
31
|
+
ʯ ↔ 'z`_w='; # LATIN SMALL LETTER TURNED H WITH FISHHOOK AND TAIL
|
|
32
|
+
# Alternative 5-character X-SAMPA representations
|
|
33
|
+
n\u031F\u030A ← 'n_+_0';
|
|
34
|
+
n\u0320\u030A ← 'n_-_0';
|
|
35
|
+
n\u032A\u030A ← 'n_d_0';
|
|
36
|
+
n\u033A\u030A ← 'n_a_0';
|
|
37
|
+
n\u033B\u030A ← 'n_m_0';
|
|
38
|
+
n\u033C\u030A ← 'n_N_0';
|
|
39
|
+
ɻ\u030A ← 'r\`_0';
|
|
40
|
+
# 4-character X-SAMPA representations
|
|
41
|
+
ǁ ↔ '|\|\'; # LATIN LETTER LATERAL CLICK
|
|
42
|
+
ʄ ↔ 'J\_<'; # LATIN SMALL LETTER DOTLESS J WITH STROKE AND HOOK
|
|
43
|
+
ʛ ↔ 'G\_<'; # LATIN LETTER SMALL CAPITAL G WITH HOOK
|
|
44
|
+
ʮ ↔ 'z_w='; # LATIN SMALL LETTER TURNED H WITH FISHHOOK
|
|
45
|
+
\u1DC4 ↔ '_H_T'; # COMBINING MACRON-ACUTE
|
|
46
|
+
\u1DC5 ↔ '_B_L'; # COMBINING GRAVE-MACRON
|
|
47
|
+
\u1DC8 ↔ '_R_F'; # COMBINING GRAVE-ACUTE-GRAVE
|
|
48
|
+
# Alternative 4-character X-SAMPA representations
|
|
49
|
+
ɭ\u030A ← 'l`_0';
|
|
50
|
+
ɰ\u030A ← 'M\_0';
|
|
51
|
+
ɳ\u030A ← 'n`_0';
|
|
52
|
+
ɽ\u030A ← 'r`_0';
|
|
53
|
+
# 3-character X-SAMPA representations
|
|
54
|
+
ɓ ↔ 'b_<'; # LATIN SMALL LETTER B WITH HOOK
|
|
55
|
+
ɗ ↔ 'd_<'; # LATIN SMALL LETTER D WITH HOOK
|
|
56
|
+
ɠ ↔ 'g_<'; # LATIN SMALL LETTER G WITH HOOK
|
|
57
|
+
ɻ ↔ 'r\`'; # LATIN SMALL LETTER TURNED R WITH HOOK
|
|
58
|
+
↗ ↔ '<R>'; # NORTH EAST ARROW
|
|
59
|
+
↘ ↔ '<F>'; # SOUTH EAST ARROW
|
|
60
|
+
# Alternative 3-character X-SAMPA representations
|
|
61
|
+
j\u030A ← 'j_0';
|
|
62
|
+
ŋ\u030A ← 'N_0';
|
|
63
|
+
ɥ\u030A ← 'H_0';
|
|
64
|
+
ɱ\u030A ← 'F_0';
|
|
65
|
+
ɲ\u030A ← 'J_0';
|
|
66
|
+
# 2-character X-SAMPA representations
|
|
67
|
+
ħ ↔ 'X\'; # LATIN SMALL LETTER H WITH STROKE
|
|
68
|
+
ǀ ↔ '|\'; # LATIN LETTER DENTAL CLICK
|
|
69
|
+
ǂ ↔ '=\'; # LATIN LETTER ALVEOLAR CLICK
|
|
70
|
+
ǃ ↔ '!\'; # LATIN LETTER RETROFLEX CLICK
|
|
71
|
+
ɕ ↔ 's\'; # LATIN SMALL LETTER C WITH CURL
|
|
72
|
+
ɖ ↔ 'd`'; # LATIN SMALL LETTER D WITH TAIL
|
|
73
|
+
ɘ ↔ '@\'; # LATIN SMALL LETTER REVERSED E
|
|
74
|
+
ɚ ↔ '@`'; # LATIN SMALL LETTER SCHWA WITH HOOK
|
|
75
|
+
ɝ ↔ '3`'; # LATIN SMALL LETTER REVERSED OPEN E WITH HOOK
|
|
76
|
+
ɞ ↔ '3\'; # LATIN SMALL LETTER CLOSED REVERSED OPEN E
|
|
77
|
+
ɟ ↔ 'J\'; # LATIN SMALL LETTER DOTLESS J WITH STROKE
|
|
78
|
+
ɢ ↔ 'G\'; # LATIN LETTER SMALL CAPITAL G
|
|
79
|
+
ɦ ↔ 'h\'; # LATIN SMALL LETTER H WITH HOOK
|
|
80
|
+
ɧ ↔ 'x\'; # LATIN SMALL LETTER HENG WITH HOOK
|
|
81
|
+
ɭ ↔ 'l`'; # LATIN SMALL LETTER L WITH RETROFLEX HOOK
|
|
82
|
+
ɮ ↔ 'K\'; # LATIN SMALL LETTER LEZH
|
|
83
|
+
ɰ ↔ 'M\'; # LATIN SMALL LETTER TURNED M WITH LONG LEG
|
|
84
|
+
ɳ ↔ 'n`'; # LATIN SMALL LETTER N WITH RETROFLEX HOOK
|
|
85
|
+
ɴ ↔ 'N\'; # LATIN LETTER SMALL CAPITAL N
|
|
86
|
+
ɸ ↔ 'p\'; # LATIN SMALL LETTER PHI
|
|
87
|
+
ɹ ↔ 'r\'; # LATIN SMALL LETTER TURNED R
|
|
88
|
+
ɺ ↔ 'l\'; # LATIN SMALL LETTER TURNED R WITH LONG LEG
|
|
89
|
+
ɽ ↔ 'r`'; # LATIN SMALL LETTER R WITH TAIL
|
|
90
|
+
ʀ ↔ 'R\'; # LATIN LETTER SMALL CAPITAL R
|
|
91
|
+
ʂ ↔ 's`'; # LATIN SMALL LETTER S WITH HOOK
|
|
92
|
+
ʈ ↔ 't`'; # LATIN SMALL LETTER T WITH RETROFLEX HOOK
|
|
93
|
+
ʐ ↔ 'z`'; # LATIN SMALL LETTER Z WITH RETROFLEX HOOK
|
|
94
|
+
ʑ ↔ 'z\'; # LATIN SMALL LETTER Z WITH CURL
|
|
95
|
+
ʕ ↔ '?\'; # LATIN LETTER PHARYNGEAL VOICED FRICATIVE
|
|
96
|
+
ʘ ↔ 'O\'; # LATIN LETTER BILABIAL CLICK
|
|
97
|
+
ʙ ↔ 'B\'; # LATIN LETTER SMALL CAPITAL B
|
|
98
|
+
ʜ ↔ 'H\'; # LATIN LETTER SMALL CAPITAL H
|
|
99
|
+
ʝ ↔ 'j\'; # LATIN SMALL LETTER J WITH CROSSED-TAIL
|
|
100
|
+
ʟ ↔ 'L\'; # LATIN LETTER SMALL CAPITAL L
|
|
101
|
+
ʡ ↔ '>\'; # LATIN LETTER GLOTTAL STOP WITH STROKE
|
|
102
|
+
ʢ ↔ '<\'; # LATIN LETTER REVERSED GLOTTAL STOP WITH STROKE
|
|
103
|
+
ʰ ↔ '_h'; # MODIFIER LETTER SMALL H
|
|
104
|
+
ʷ ↔ '_w'; # MODIFIER LETTER SMALL W
|
|
105
|
+
ʼ ↔ '_>'; # MODIFIER LETTER APOSTROPHE
|
|
106
|
+
ˆ ↔ '_\'; # MODIFIER LETTER CIRCUMFLEX ACCENT
|
|
107
|
+
ˇ ↔ '_/'; # CARON
|
|
108
|
+
ˑ ↔ ':\'; # MODIFIER LETTER HALF TRIANGULAR COLON
|
|
109
|
+
ˠ ↔ '_G'; # MODIFIER LETTER SMALL GAMMA
|
|
110
|
+
ˡ ↔ '_l'; # MODIFIER LETTER SMALL L
|
|
111
|
+
ˤ ↔ '_?\'; # MODIFIER LETTER SMALL REVERSED GLOTTAL STOP
|
|
112
|
+
\u0300 ↔ '_L'; # COMBINING GRAVE ACCENT
|
|
113
|
+
\u0301 ↔ '_H'; # COMBINING ACUTE ACCENT
|
|
114
|
+
\u0302 ↔ '_F'; # COMBINING CIRCUMFLEX ACCENT
|
|
115
|
+
\u0304 ↔ '_M'; # COMBINING MACRON
|
|
116
|
+
\u0306 ↔ '_X'; # COMBINING BREVE
|
|
117
|
+
\u0308 ↔ '_"'; # COMBINING DIAERESIS
|
|
118
|
+
\u030B ↔ '_T'; # COMBINING DOUBLE ACUTE ACCENT
|
|
119
|
+
\u030C ↔ '_R'; # COMBINING CARON
|
|
120
|
+
\u030F ↔ '_B'; # COMBINING DOUBLE GRAVE ACCENT
|
|
121
|
+
\u0318 ↔ '_A'; # COMBINING LEFT TACK BELOW
|
|
122
|
+
\u0319 ↔ '_q'; # COMBINING RIGHT TACK BELOW
|
|
123
|
+
\u031A ↔ '_}'; # COMBINING LEFT ANGLE ABOVE
|
|
124
|
+
\u031C ↔ '_c'; # COMBINING LEFT HALF RING BELOW
|
|
125
|
+
\u031D ↔ '_r'; # COMBINING UP TACK BELOW
|
|
126
|
+
\u031E ↔ '_o'; # COMBINING DOWN TACK BELOW
|
|
127
|
+
\u031F ↔ '_+'; # COMBINING PLUS SIGN BELOW
|
|
128
|
+
\u0320 ↔ '_-'; # COMBINING MINUS SIGN BELOW
|
|
129
|
+
\u0324 ↔ '_t'; # COMBINING DIAERESIS BELOW
|
|
130
|
+
\u0325 ↔ '_0'; # COMBINING RING BELOW
|
|
131
|
+
\u032A ↔ '_d'; # COMBINING BRIDGE BELOW
|
|
132
|
+
\u032C ↔ '_v'; # COMBINING CARON BELOW
|
|
133
|
+
\u032F ↔ '_^'; # COMBINING INVERTED BREVE BELOW
|
|
134
|
+
\u0330 ↔ '_k'; # COMBINING TILDE BELOW
|
|
135
|
+
\u0334 ↔ '_e'; # COMBINING TILDE OVERLAY
|
|
136
|
+
\u0339 ↔ '_O'; # COMBINING RIGHT HALF RING BELOW
|
|
137
|
+
\u033A ↔ '_a'; # COMBINING INVERTED BRIDGE BELOW
|
|
138
|
+
\u033B ↔ '_m'; # COMBINING SQUARE BELOW
|
|
139
|
+
\u033C ↔ '_N'; # COMBINING SEAGULL BELOW
|
|
140
|
+
\u033D ↔ '_x'; # COMBINING X ABOVE
|
|
141
|
+
ᵻ ↔ 'I\'; # LATIN SMALL CAPITAL LETTER I WITH STROKE
|
|
142
|
+
ᵿ ↔ 'U\'; # LATIN SMALL CAPITAL LETTER U WITH STROKE
|
|
143
|
+
ⁿ ↔ '_n'; # MODIFIER LETTER LATIN SMALL LETTER N
|
|
144
|
+
# Alternative 2-character X-SAMPA representations
|
|
145
|
+
ʋ ← 'v\'; # LATIN SMALL LETTER V WITH HOOK
|
|
146
|
+
ʲ ← '_j'; # MODIFIER LETTER SMALL J
|
|
147
|
+
\u0303 ← '_~'; # COMBINING TILDE
|
|
148
|
+
\u0329 ← '_='; # COMBINING VERTICAL LINE BELOW
|
|
149
|
+
# 1-character X-SAMPA representations
|
|
150
|
+
c\u0327 ↔ C; # LATIN SMALL LETTER C WITH CEDILLA (decomposed)
|
|
151
|
+
æ ↔ '{'; # LATIN SMALL LETTER AE
|
|
152
|
+
ð ↔ D; # LATIN SMALL LETTER ETH
|
|
153
|
+
ø ↔ 2; # LATIN SMALL LETTER O WITH STROKE
|
|
154
|
+
ŋ ↔ N; # LATIN SMALL LETTER ENG
|
|
155
|
+
œ ↔ 9; # LATIN SMALL LIGATURE OE
|
|
156
|
+
ɐ ↔ 6; # LATIN SMALL LETTER TURNED A
|
|
157
|
+
ɑ ↔ A; # LATIN SMALL LETTER ALPHA
|
|
158
|
+
ɒ ↔ Q; # LATIN SMALL LETTER TURNED ALPHA
|
|
159
|
+
ɔ ↔ O; # LATIN SMALL LETTER OPEN O
|
|
160
|
+
ə ↔ '@'; # LATIN SMALL LETTER SCHWA
|
|
161
|
+
ɛ ↔ E; # LATIN SMALL LETTER OPEN E
|
|
162
|
+
ɜ ↔ 3; # LATIN SMALL LETTER REVERSED OPEN E
|
|
163
|
+
ɡ ↔ g; # LATIN SMALL LETTER SCRIPT G
|
|
164
|
+
ɣ ↔ G; # LATIN SMALL LETTER GAMMA
|
|
165
|
+
ɤ ↔ 7; # LATIN SMALL LETTER RAMS HORN
|
|
166
|
+
ɥ ↔ H; # LATIN SMALL LETTER TURNED H
|
|
167
|
+
ɨ ↔ 1; # LATIN SMALL LETTER I WITH STROKE
|
|
168
|
+
ɪ ↔ I; # LATIN LETTER SMALL CAPITAL I
|
|
169
|
+
ɫ ↔ 5; # LATIN SMALL LETTER L WITH MIDDLE TILDE
|
|
170
|
+
ɬ ↔ K; # LATIN SMALL LETTER L WITH BELT
|
|
171
|
+
ɯ ↔ M; # LATIN SMALL LETTER TURNED M
|
|
172
|
+
ɱ ↔ F; # LATIN SMALL LETTER M WITH HOOK
|
|
173
|
+
ɲ ↔ J; # LATIN SMALL LETTER N WITH LEFT HOOK
|
|
174
|
+
ɵ ↔ 8; # LATIN SMALL LETTER BARRED O
|
|
175
|
+
ɶ ↔ '&'; # LATIN LETTER SMALL CAPITAL OE
|
|
176
|
+
ɾ ↔ 4; # LATIN SMALL LETTER R WITH FISHHOOK
|
|
177
|
+
ʁ ↔ R; # LATIN LETTER SMALL CAPITAL INVERTED R
|
|
178
|
+
ʃ ↔ S; # LATIN SMALL LETTER ESH
|
|
179
|
+
ʉ ↔ '}'; # LATIN SMALL LETTER U BAR
|
|
180
|
+
ʊ ↔ U; # LATIN SMALL LETTER UPSILON
|
|
181
|
+
ʋ ↔ P; # LATIN SMALL LETTER V WITH HOOK
|
|
182
|
+
ʌ ↔ V; # LATIN SMALL LETTER TURNED V
|
|
183
|
+
ʍ ↔ W; # LATIN SMALL LETTER TURNED W
|
|
184
|
+
ʎ ↔ L; # LATIN SMALL LETTER TURNED Y
|
|
185
|
+
ʏ ↔ Y; # LATIN LETTER SMALL CAPITAL Y
|
|
186
|
+
ʒ ↔ Z; # LATIN SMALL LETTER EZH
|
|
187
|
+
ʔ ↔ '?'; # LATIN LETTER GLOTTAL STOP
|
|
188
|
+
ʲ ↔ \'; # MODIFIER LETTER SMALL J
|
|
189
|
+
ˈ ↔ '"'; # MODIFIER LETTER VERTICAL LINE
|
|
190
|
+
ˌ ↔ '%'; # MODIFIER LETTER LOW VERTICAL LINE
|
|
191
|
+
ː ↔ ':'; # MODIFIER LETTER TRIANGULAR COLON
|
|
192
|
+
˞ ↔ '`'; # MODIFIER LETTER RHOTIC HOOK
|
|
193
|
+
\u0303 ↔ '~'; # COMBINING TILDE
|
|
194
|
+
\u0329 ↔ '='; # COMBINING VERTICAL LINE BELOW
|
|
195
|
+
\u0361 ↔ $t; # COMBINING DOUBLE INVERTED BREVE
|
|
196
|
+
β ↔ B; # GREEK SMALL LETTER BETA
|
|
197
|
+
θ ↔ T; # GREEK SMALL LETTER THETA
|
|
198
|
+
χ ↔ X; # GREEK SMALL LETTER CHI
|
|
199
|
+
↑ ↔ '^'; # UPWARDS ARROW
|
|
200
|
+
↓ ↔ '!'; # DOWNWARDS ARROW
|
|
201
|
+
# Compatibility rules for variant or obsolete IPA symbols
|
|
202
|
+
g → g; # LATIN SMALL LETTER G (redundant, for additional clarity)
|
|
203
|
+
ȵ → J; # LATIN SMALL LETTER N WITH CURL
|
|
204
|
+
ɩ → I; # LATIN SMALL LETTER IOTA
|
|
205
|
+
ɷ → U; # LATIN SMALL LETTER CLOSED OMEGA
|
|
206
|
+
ɼ → 'r_r'; # LATIN SMALL LETTER R WITH LONG LEG
|
|
207
|
+
ɿ → 'z='; # LATIN SMALL LETTER REVERSED R WITH FISHHOOK
|
|
208
|
+
ʅ → 'z`='; # LATIN SMALL LETTER SQUAT REVERSED ESH
|
|
209
|
+
ʆ → S\'; # LATIN SMALL LETTER ESH WITH CURL
|
|
210
|
+
ʇ → '|\' ; # LATIN SMALL LETTER TURNED T
|
|
211
|
+
ʓ → Z\'; # LATIN SMALL LETTER EZH WITH CURL
|
|
212
|
+
ʖ → '|\|\'; # LATIN LETTER INVERTED GLOTTAL STOP
|
|
213
|
+
ʗ → '!\'; # LATIN LETTER STRETCHED C
|
|
214
|
+
ʚ → '3\'; # LATIN SMALL LETTER CLOSED OPEN E
|
|
215
|
+
ʠ → 'G\_<_0'; # LATIN SMALL LETTER Q WITH HOOK
|
|
216
|
+
ʣ → d $t z; # LATIN SMALL LETTER DZ DIGRAPH
|
|
217
|
+
ʤ → d $t Z; # LATIN SMALL LETTER DEZH DIGRAPH
|
|
218
|
+
ʥ → d $t 'z\'; # LATIN SMALL LETTER DZ DIGRAPH WITH CURL
|
|
219
|
+
ʦ → t $t s; # LATIN SMALL LETTER TS DIGRAPH
|
|
220
|
+
ʧ → t $t S; # LATIN SMALL LETTER TESH DIGRAPH
|
|
221
|
+
ʨ → t $t 's\'; # LATIN SMALL LETTER TC DIGRAPH WITH CURL
|
|
222
|
+
˔ → '_r'; # MODIFIER LETTER UP TACK
|
|
223
|
+
˕ → '_o'; # MODIFIER LETTER DOWN TACK
|
|
224
|
+
\u030A → '_0'; # COMBINING RING ABOVE
|
|
225
|
+
φ → 'p\'; # GREEK SMALL LETTER PHI
|
|
226
|
+
ꞎ → 'K`'; # LATIN SMALL LETTER L WITH RETROFLEX HOOK AND BELT
|
|
227
|
+
::NFC(NFD);
|
|
228
|
+
|
|
@@ -0,0 +1,128 @@
|
|
|
1
|
+
|
|
2
|
+
$nonword = [^\uE000-\uE0FF];
|
|
3
|
+
$wordBoundary = [^[:L:][:M:][:N:]];
|
|
4
|
+
\uE015\uE03F\uE02F\uE03E } $nonword→كيا; # किया
|
|
5
|
+
\uE026\uE03F\uE02F\uE03E } $nonword→ديا; # दिया
|
|
6
|
+
\uE015\uE03F } $nonword→كي; # कि at word end
|
|
7
|
+
\uE039\uE048→هي; # है
|
|
8
|
+
\uE001 } $nonword→ن; # chandrabindu at end to noon
|
|
9
|
+
\uE001→ن; # chandrabindu not at end to noon
|
|
10
|
+
\uE002 } $nonword→ن; # anusvara to noon at end
|
|
11
|
+
\uE002→ن; # anusvara to noon ं
|
|
12
|
+
\uE003→ه ا; # viarga to ha + alif ः
|
|
13
|
+
\uE004→ا; # short a to alif ऄ
|
|
14
|
+
\uE005→ا; # अ
|
|
15
|
+
\uE006→ا ٓ; # alif with mad आ
|
|
16
|
+
[[:L:][:M:]] {\uE007}→ي; # इ after another letter or mark
|
|
17
|
+
\uE007→إ; # इ at beginning of word
|
|
18
|
+
[[:L:][:M:]] {\uE008}→ي; # ई after another letter or mark
|
|
19
|
+
\uE008→إ; # ई at beginning of word
|
|
20
|
+
\uE009→و; # उ
|
|
21
|
+
\uE00A→و; # ऊ
|
|
22
|
+
\uE00B→ر; # ऋ
|
|
23
|
+
\uE00C→ل; # ऌ
|
|
24
|
+
\uE00D→ا ي; # ऍ
|
|
25
|
+
\uE00E→ي; # ऎ
|
|
26
|
+
$wordBoundary {\uE00F} → إي; # word-initial ए
|
|
27
|
+
\uE00F } $nonword→ي; # ए use ي when at end
|
|
28
|
+
\uE00F→ي; # ए use ي when not at end
|
|
29
|
+
\uE010 } $nonword→ا ي; # ऐ use ي when at end
|
|
30
|
+
\uE010→ا ي; # ऐ use ي when not at end
|
|
31
|
+
\uE011→ا و; # ऑ
|
|
32
|
+
\uE012→ا و; # ऒ
|
|
33
|
+
\uE013→ا و; # ओ
|
|
34
|
+
\uE014→ا و; # औ
|
|
35
|
+
\uE015→ك; # क
|
|
36
|
+
\uE016→كه; # ख
|
|
37
|
+
\uE017→ج; # ग
|
|
38
|
+
\uE018→جه; # घ
|
|
39
|
+
\uE019→نج; # ङ
|
|
40
|
+
\uE01A→تش; # च
|
|
41
|
+
\uE01B→تشه; # छ
|
|
42
|
+
\uE01C→ج; # ज
|
|
43
|
+
\uE01D→جه; # झ
|
|
44
|
+
\uE01E→ن; # ञ
|
|
45
|
+
\uE01F→ط; # ट
|
|
46
|
+
\uE020→طه; # ठ
|
|
47
|
+
\uE021→د; # ड
|
|
48
|
+
\uE022→ده; # ढ
|
|
49
|
+
\uE023→ن; # ण
|
|
50
|
+
\uE024→ت; # त
|
|
51
|
+
\uE025→ته; # थ
|
|
52
|
+
\uE026→د; # द
|
|
53
|
+
\uE027→ده; # ध
|
|
54
|
+
\uE028→ن; # न
|
|
55
|
+
\uE029→ن; # ऩ
|
|
56
|
+
\uE02A→ب; # प
|
|
57
|
+
\uE02B→به; # फ
|
|
58
|
+
\uE02C→ب; # ब
|
|
59
|
+
\uE02D→به; # भ
|
|
60
|
+
\uE02E→م; # म
|
|
61
|
+
\uE02F→ي; # य
|
|
62
|
+
\uE030→ر; # र
|
|
63
|
+
\uE031→ر; # ऱ
|
|
64
|
+
\uE032→ل; # ल
|
|
65
|
+
\uE033→ر; # ळ
|
|
66
|
+
\uE034→ر; # ऴ
|
|
67
|
+
\uE035→و; # व
|
|
68
|
+
\uE036→ش; # श
|
|
69
|
+
\uE037→ش; # ष
|
|
70
|
+
\uE038→س; # स
|
|
71
|
+
\uE039→ه; # ह
|
|
72
|
+
\uE03C→; # ़
|
|
73
|
+
\uE03D→; # ऽ
|
|
74
|
+
\uE03E→ا; # ा
|
|
75
|
+
\uE03F→ي; # ि
|
|
76
|
+
\uE040→ي; # ी
|
|
77
|
+
\uE041→و; # ु
|
|
78
|
+
\uE042→و; # ू
|
|
79
|
+
\uE043→ر; # ृ
|
|
80
|
+
\uE044→ر; # ॄ
|
|
81
|
+
\uE045→ن; # ॅ
|
|
82
|
+
\uE046→ي; # ॆ
|
|
83
|
+
\uE047 } $nonword→ي; # े use ي when at end
|
|
84
|
+
\uE047→ي; # े use ي when not at end
|
|
85
|
+
\uE048 } $nonword→ا ي; # ै use ي when at end
|
|
86
|
+
\uE048→ا ي; # ै use ي when not at end
|
|
87
|
+
\uE049→و; # ॉ
|
|
88
|
+
\uE04A→ا و; # ॊ
|
|
89
|
+
\uE04B→و; # ो
|
|
90
|
+
\uE04C→ا و; # ौ
|
|
91
|
+
\uE04D→; # ्
|
|
92
|
+
\uE050→ا و; # ॐ
|
|
93
|
+
\uE051→; # ॑
|
|
94
|
+
\uE052→; # ॒
|
|
95
|
+
\uE053→; # ॓
|
|
96
|
+
\uE054→; # ॔
|
|
97
|
+
\uE058→ق; # क़
|
|
98
|
+
\uE059→خ; # ख़
|
|
99
|
+
\uE05A→غ; # ग़
|
|
100
|
+
\uE05B→ز; # ज़
|
|
101
|
+
\uE05C→ر; # ड़
|
|
102
|
+
\uE05D→ره; # ढ़
|
|
103
|
+
\uE05E→ف; # फ़
|
|
104
|
+
\uE05F→ي; # य़
|
|
105
|
+
\uE060→ر; # ॠ
|
|
106
|
+
\uE061→ل; # ॡ
|
|
107
|
+
\uE062→ل; # ॢ
|
|
108
|
+
\uE063→ل; # ॣ
|
|
109
|
+
\uE064→۔; # ।
|
|
110
|
+
\uE065→۔; # ॥
|
|
111
|
+
\uE066→\.; # ०
|
|
112
|
+
\uE067→١; # १
|
|
113
|
+
\uE068→٢; # २
|
|
114
|
+
\uE069→٣; # ३
|
|
115
|
+
\uE06A→٤; # ४
|
|
116
|
+
\uE06B→٥; # ५
|
|
117
|
+
\uE06C→٦; # ६
|
|
118
|
+
\uE06D→٧; # ७
|
|
119
|
+
\uE06E→٨; # ८
|
|
120
|
+
\uE06F→٩; # ९
|
|
121
|
+
\uE070→\.; # ॰
|
|
122
|
+
\uE082→; # ॽ
|
|
123
|
+
# Remove sequences of alif characters.
|
|
124
|
+
# For example, transform पाओला → بااولا → باولا.
|
|
125
|
+
::null;
|
|
126
|
+
$alif = [أإآا] [:M:]*;
|
|
127
|
+
($alif) $alif+ → $1;
|
|
128
|
+
|
|
@@ -0,0 +1,135 @@
|
|
|
1
|
+
|
|
2
|
+
# InterIndic-Bengali
|
|
3
|
+
#:: NFD (NFC) ;
|
|
4
|
+
\uE001→ঁ; # SIGN CANDRABINDU
|
|
5
|
+
\uE002→ং; # SIGN ANUSVARA
|
|
6
|
+
\uE003→ঃ; # SIGN VISARGA
|
|
7
|
+
\uE004→অ; # FALLBACK TO LETTER A
|
|
8
|
+
\uE005→অ; # LETTER A
|
|
9
|
+
\uE006→আ; # LETTER AA
|
|
10
|
+
\uE007→ই; # LETTER I
|
|
11
|
+
\uE008→ঈ; # LETTER II
|
|
12
|
+
\uE009→উ; # LETTER U
|
|
13
|
+
\uE00A→ঊ; # LETTER UU
|
|
14
|
+
\uE00B→ঋ; # LETTER VOCALIC R
|
|
15
|
+
\uE00C→ঌ; # LETTER VOCALIC L
|
|
16
|
+
\uE00D→এ; # FALLBACK
|
|
17
|
+
\uE00E→এ; # FALLBACK
|
|
18
|
+
\uE00F→এ; # LETTER E
|
|
19
|
+
\uE010→ঐ; # LETTER AI
|
|
20
|
+
\uE011→ও; # FALLBACK
|
|
21
|
+
\uE012→ও; # FALLBACK
|
|
22
|
+
\uE013→ও; # LETTER O
|
|
23
|
+
\uE014→ঔ; # LETTER AU
|
|
24
|
+
\uE015→ক; # LETTER KA
|
|
25
|
+
\uE016→খ; # LETTER KHA
|
|
26
|
+
\uE017→গ; # LETTER GA
|
|
27
|
+
\uE018→ঘ; # LETTER GHA
|
|
28
|
+
\uE019→ঙ; # LETTER NGA
|
|
29
|
+
\uE01A→চ; # LETTER CA
|
|
30
|
+
\uE01B→ছ; # LETTER CHA
|
|
31
|
+
\uE01C→জ; # LETTER JA
|
|
32
|
+
\uE01D→ঝ; # LETTER JHA
|
|
33
|
+
\uE01E→ঞ; # LETTER NYA
|
|
34
|
+
\uE01F→ট; # LETTER TTA
|
|
35
|
+
\uE020→ঠ; # LETTER TTHA
|
|
36
|
+
\uE021→ড; # LETTER DDA
|
|
37
|
+
\uE022→ঢ; # LETTER DDHA
|
|
38
|
+
\uE023→ণ; # LETTER NNA
|
|
39
|
+
\uE024→ত; # LETTER TA
|
|
40
|
+
\uE025→থ; # LETTER THA
|
|
41
|
+
\uE026→দ; # LETTER DA
|
|
42
|
+
\uE027→ধ; # LETTER DHA
|
|
43
|
+
\uE028→ন; # LETTER NA
|
|
44
|
+
\uE029→ন়; # REMAP (indicExceptions.txt): \u09A9→ন = LETTER NNNA→LETTER NA
|
|
45
|
+
\uE02A→প; # LETTER PA
|
|
46
|
+
\uE02B→ফ; # LETTER PHA
|
|
47
|
+
\uE02C→ব; # LETTER BA
|
|
48
|
+
\uE02D→ভ; # LETTER BHA
|
|
49
|
+
\uE02E→ম; # LETTER MA
|
|
50
|
+
\uE02F→য; # LETTER YA
|
|
51
|
+
\uE030→র; # LETTER RA
|
|
52
|
+
\uE031→র়; # FALLBACK to RA
|
|
53
|
+
\uE032→ল; # LETTER LA
|
|
54
|
+
\uE033→ল; # REMAP (indicExceptions.txt): \u09B3→ল = LETTER LLA→LETTER LA
|
|
55
|
+
\uE034→ল; # REMAP (indicExceptions.txt): \u09B4→ল = LETTER LLLA→LETTER LA
|
|
56
|
+
\uE035→ব; # REMAP (indicExceptions.txt): \u09B5→ব = LETTER VA→LETTER BA
|
|
57
|
+
\uE036→শ; # LETTER SHA
|
|
58
|
+
\uE037→ষ; # LETTER SSA
|
|
59
|
+
\uE038→স; # LETTER SA
|
|
60
|
+
\uE039→হ; # LETTER HA
|
|
61
|
+
\uE03C→়; # SIGN NUKTA
|
|
62
|
+
\uE03D→ঽ; # SIGN AVAGRAHA
|
|
63
|
+
\uE03E→া; # VOWEL SIGN AA
|
|
64
|
+
\uE03F→ি; # VOWEL SIGN I
|
|
65
|
+
\uE040→ী; # VOWEL SIGN II
|
|
66
|
+
\uE041→ু; # VOWEL SIGN U
|
|
67
|
+
\uE042→ূ; # VOWEL SIGN UU
|
|
68
|
+
\uE043→ৃ; # VOWEL SIGN VOCALIC R
|
|
69
|
+
\uE044→ৄ; # VOWEL SIGN VOCALIC RR
|
|
70
|
+
\uE045→ে; # REMAP (indicExceptions.txt): \u09C5→ে = VOWEL SIGN CANDRA E→VOWEL SIGN E
|
|
71
|
+
\uE046→ে; # FALLBACK
|
|
72
|
+
\uE047→ে; # VOWEL SIGN E
|
|
73
|
+
\uE048→ৈ; # VOWEL SIGN AI
|
|
74
|
+
\uE049→ো; # REMAP (indicExceptions.txt): \u09C9→ো = VOWEL SIGN CANDRA O→VOWEL SIGN O
|
|
75
|
+
\uE04A→ো; # FALLBACK
|
|
76
|
+
\uE04B→ো; # VOWEL SIGN O
|
|
77
|
+
\uE04C→ৌ; # VOWEL SIGN AU
|
|
78
|
+
\uE04D→্; # SIGN VIRAMA
|
|
79
|
+
\uE050→ওং; # InterIndic-Bengali: OM
|
|
80
|
+
\uE051→;
|
|
81
|
+
\uE052→;
|
|
82
|
+
\uE053→;
|
|
83
|
+
\uE054→;
|
|
84
|
+
\uE055→; # LENGTH MARK
|
|
85
|
+
\uE056→ৈ; # REMAP (indicExceptions.txt): \u09D6→ৈ = AI LENGTH MARK→VOWEL SIGN AI
|
|
86
|
+
\uE057→ৗ; # AU LENGTH MARK
|
|
87
|
+
\uE058→ক়; # FALLBACK
|
|
88
|
+
\uE059→খ়; # REMAP (indicExceptions.txt): \u09D9→খ = LETTER KHHA→LETTER KHA
|
|
89
|
+
\uE05A→গ়; # REMAP (indicExceptions.txt): \u09DA→গ = LETTER GHHA→LETTER GA
|
|
90
|
+
\uE05B→জ়; # REMAP (indicExceptions.txt): \u09DB→জ = LETTER ZA→LETTER JA
|
|
91
|
+
\uE05C→ড়; # FALLBACK
|
|
92
|
+
\uE05D→ঢ়; # LETTER RHA
|
|
93
|
+
\uE05E→ফ়; # REMAP (indicExceptions.txt): \u09DE→ফ = LETTER FA→LETTER PHA
|
|
94
|
+
\uE05F→য়; # LETTER YYA
|
|
95
|
+
\uE060→ৠ; # LETTER VOCALIC RR
|
|
96
|
+
\uE061→ৡ; # LETTER VOCALIC LL
|
|
97
|
+
\uE062→ৢ; # VOWEL SIGN VOCALIC L
|
|
98
|
+
\uE063→ৣ; # VOWEL SIGN VOCALIC LL
|
|
99
|
+
\uE064→।; # DANDA
|
|
100
|
+
\uE065→॥; # DOUBLE DANDA
|
|
101
|
+
\uE066→০; # DIGIT ZERO
|
|
102
|
+
\uE067→১; # DIGIT ONE
|
|
103
|
+
\uE068→২; # DIGIT TWO
|
|
104
|
+
\uE069→৩; # DIGIT THREE
|
|
105
|
+
\uE06A→৪; # DIGIT FOUR
|
|
106
|
+
\uE06B→৫; # DIGIT FIVE
|
|
107
|
+
\uE06C→৬; # DIGIT SIX
|
|
108
|
+
\uE06D→৭; # DIGIT SEVEN
|
|
109
|
+
\uE06E→৮; # DIGIT EIGHT
|
|
110
|
+
\uE06F→৯; # DIGIT NINE
|
|
111
|
+
\uE070→; # ABBREVIATION SIGN
|
|
112
|
+
\uE071→ৰ; # LETTER RA WITH MIDDLE DIAGONAL
|
|
113
|
+
\uE072→ৱ; # LETTER RA WITH LOWER DIAGONAL
|
|
114
|
+
\uE073→৲; # RUPEE MARK
|
|
115
|
+
\uE074→৳; # RUPEE SIGN
|
|
116
|
+
\uE075→৴; # CURRENCY NUMERATOR ONE
|
|
117
|
+
\uE076→৵; # CURRENCY NUMERATOR TWO
|
|
118
|
+
\uE077→৶; # CURRENCY NUMERATOR THREE
|
|
119
|
+
\uE078→৷; # CURRENCY NUMERATOR FOUR
|
|
120
|
+
\uE079→৸; # CURRENCY NUMERATOR ONE LESS THAN THE DENOMINATOR
|
|
121
|
+
\uE07A→৹; # CURRENCY DENOMINATOR SIXTEEN
|
|
122
|
+
\uE07B→৺; # ISSHAR
|
|
123
|
+
\uE07C→; # TIPPI
|
|
124
|
+
\uE07D→; # ADDAK
|
|
125
|
+
\uE07E→; # IRI
|
|
126
|
+
\uE07F→; # URA
|
|
127
|
+
\uE080→; # EK ONKAR
|
|
128
|
+
\uE081→ব; # FALLBACK FOR ORIYA LETTER WA
|
|
129
|
+
\uE082→; # Devanagari Glottal Stop
|
|
130
|
+
\uE083→ৎ; # Khanda-ta
|
|
131
|
+
0 → ০; # FALLBACK FOR TAMIL
|
|
132
|
+
1 → ১;
|
|
133
|
+
# :: NFC (NFD) ;
|
|
134
|
+
# eof
|
|
135
|
+
|
|
@@ -0,0 +1,151 @@
|
|
|
1
|
+
|
|
2
|
+
# InterIndic-Devanagari
|
|
3
|
+
#:: NFD (NFC) ;
|
|
4
|
+
#Rules for Decomposed characters
|
|
5
|
+
\uE028\uE03C → ऩ; #\uE029
|
|
6
|
+
\uE030\uE03C → ऱ; #\uE031
|
|
7
|
+
\uE033\uE03C → ऴ; #\uE034
|
|
8
|
+
\uE015\uE03C → क़; #\uE058 LETTER QA (For Urdu)
|
|
9
|
+
\uE016\uE03C → ख़; #\uE059 LETTER KHHA (For Urdu)
|
|
10
|
+
\uE017\uE03C → ग़; #\uE05A LETTER GHHA (For Urdu)
|
|
11
|
+
\uE01C\uE03C → ज़; #\uE05B LETTER ZA (For Urdu)
|
|
12
|
+
\uE021\uE03C → ड़; #\uE05C LETTER DDDHA (pronounced RRA)
|
|
13
|
+
\uE022\uE03C → ढ़; #\uE05D LETTER RHA (pronounced RRHA)
|
|
14
|
+
\uE02B\uE03C → फ़; #\uE05E LETTER FA
|
|
15
|
+
\uE02F\uE03C → य़; #\uE05F LETTER YYA
|
|
16
|
+
#Decomposed compatibility transliterations
|
|
17
|
+
\uE012\uE057→औ; # FALLBACK FOR TAMIL AU
|
|
18
|
+
0 → ०; # FALLBACK FOR TAMIL
|
|
19
|
+
1 → १;
|
|
20
|
+
\uE055→; # FALLBACK BLOW AWAY KANNADA AND TELUGU LENGTH MARK
|
|
21
|
+
\uE056→; # FALLBACK BLOW AWAY KANNADA AND TELUGU AI LENGTH MARK
|
|
22
|
+
\uE057→; # FALLBACK BLOW AWAY TAMIL AU LENGTH MARK
|
|
23
|
+
\uE001 → ँ; # SIGN CANDRABINDU
|
|
24
|
+
\uE002 → ं; # SIGN ANUSVARA
|
|
25
|
+
\uE003 → ः; # SIGN VISARGA
|
|
26
|
+
\uE004 → ऄ; # SIGN SHORT A
|
|
27
|
+
\uE005 → अ; # LETTER A
|
|
28
|
+
\uE006 → आ; # LETTER AA
|
|
29
|
+
\uE007 → इ; # LETTER I
|
|
30
|
+
\uE008 → ई; # LETTER II
|
|
31
|
+
\uE009 → उ; # LETTER U
|
|
32
|
+
\uE00A → ऊ; # LETTER UU
|
|
33
|
+
\uE00B → ऋ; # LETTER VOCALIC R
|
|
34
|
+
\uE00C → ऌ; # LETTER VOCALIC L
|
|
35
|
+
\uE00D → ऍ; # LETTER CANDRA E (For representing English sounds)
|
|
36
|
+
\uE00E → ऎ; # LETTER SHORT E(For Southern Scripts)
|
|
37
|
+
\uE00F → ए; # LETTER E
|
|
38
|
+
\uE010 → ऐ; # LETTER AI
|
|
39
|
+
\uE011 → ऑ; # LETTER CANDRA O (For representing English sounds)
|
|
40
|
+
\uE012 → ऒ; # LETTER SHORT O (For Southern Scripts)
|
|
41
|
+
\uE013 → ओ; # LETTER O
|
|
42
|
+
\uE014 → औ; # LETTER AU
|
|
43
|
+
\uE015 → क; # LETTER KA
|
|
44
|
+
\uE016 → ख; # LETTER KHA
|
|
45
|
+
\uE017 → ग; # LETTER GA
|
|
46
|
+
\uE018 → घ; # LETTER GHA
|
|
47
|
+
\uE019 → ङ; # LETTER NGA
|
|
48
|
+
\uE01A → च; # LETTER CA
|
|
49
|
+
\uE01B → छ; # LETTER CHA
|
|
50
|
+
\uE01C → ज; # LETTER JA
|
|
51
|
+
\uE01D → झ; # LETTER JHA
|
|
52
|
+
\uE01E → ञ; # LETTER NYA
|
|
53
|
+
\uE01F → ट; # LETTER TTA
|
|
54
|
+
\uE020 → ठ; # LETTER TTHA
|
|
55
|
+
\uE021 → ड; # LETTER DDA
|
|
56
|
+
\uE022 → ढ; # LETTER DDHA
|
|
57
|
+
\uE023 → ण; # LETTER NNA
|
|
58
|
+
\uE024 → त; # LETTER TA
|
|
59
|
+
\uE025 → थ; # LETTER THA
|
|
60
|
+
\uE026 → द; # LETTER DA
|
|
61
|
+
\uE027 → ध; # LETTER DHA
|
|
62
|
+
\uE028 → न; # LETTER NA
|
|
63
|
+
\uE029 → ऩ; # LETTER NNNA
|
|
64
|
+
\uE02A → प; # LETTER PA
|
|
65
|
+
\uE02B → फ; # LETTER PHA
|
|
66
|
+
\uE02C → ब; # LETTER BA
|
|
67
|
+
\uE02D → भ; # LETTER BHA
|
|
68
|
+
\uE02E → म; # LETTER MA
|
|
69
|
+
\uE02F → य; # LETTER YA
|
|
70
|
+
\uE030 → र; # LETTER RA
|
|
71
|
+
\uE031 → ऱ; # LETTER RRA (Eyelash RA for Southern scripts)
|
|
72
|
+
#\uE031 → र;
|
|
73
|
+
\uE032 → ल; # LETTER LA
|
|
74
|
+
\uE033 → ळ; # LETTER LLA
|
|
75
|
+
\uE034 → ऴ; # LETTER LLLA (LLLA for Southern scripts)
|
|
76
|
+
#\uE034 → ळ;
|
|
77
|
+
\uE035 → व; # LETTER VA
|
|
78
|
+
\uE036 → श; # LETTER SHA
|
|
79
|
+
\uE037 → ष; # LETTER SSA
|
|
80
|
+
\uE038 → स; # LETTER SA
|
|
81
|
+
\uE039 → ह; # LETTER HA
|
|
82
|
+
\uE03C → ़; # SIGN NUKTA
|
|
83
|
+
\uE03D → ऽ; # SIGN AVAGRAHA
|
|
84
|
+
\uE03E → ा; # VOWEL SIGN AA
|
|
85
|
+
\uE03F → ि; # VOWEL SIGN I
|
|
86
|
+
\uE040 → ी; # VOWEL SIGN II
|
|
87
|
+
\uE041 → ु; # VOWEL SIGN U
|
|
88
|
+
\uE042 → ू; # VOWEL SIGN UU
|
|
89
|
+
\uE043 → ृ; # VOWEL SIGN VOCALIC R
|
|
90
|
+
\uE044 → ॄ; # VOWEL SIGN VOCALIC RR
|
|
91
|
+
\uE045 → ॅ; # VOWEL SIGN CANDRA E
|
|
92
|
+
\uE046 → ॆ; # VOWEL SIGN SHORT E
|
|
93
|
+
\uE047 → े; # VOWEL SIGN E
|
|
94
|
+
\uE048 → ै; # VOWEL SIGN AI
|
|
95
|
+
\uE049 → ॉ; # VOWEL SIGN CANDRA O
|
|
96
|
+
\uE04A → ॊ; # VOWEL SIGN SHORT O
|
|
97
|
+
\uE04B → ो; # VOWEL SIGN O
|
|
98
|
+
\uE04C → ौ; # VOWEL SIGN AU
|
|
99
|
+
\uE04D → ्; # SIGN VIRAMA
|
|
100
|
+
\uE050 → ॐ; # OM
|
|
101
|
+
\uE051 → ॑; # STRESS SIGN UDATTA
|
|
102
|
+
\uE052 → ॒; # STRESS SIGN ANUDATTA
|
|
103
|
+
\uE053 → ॓; # GRAVE ACCENT
|
|
104
|
+
\uE054 → ॔; # ACUTE ACCENT
|
|
105
|
+
\uE058 → क़; # LETTER QA (For Urdu)
|
|
106
|
+
\uE059 → ख़; # LETTER KHHA (For Urdu)
|
|
107
|
+
\uE05A → ग़; # LETTER GHHA (For Urdu)
|
|
108
|
+
\uE05B → ज़; # LETTER ZA (For Urdu)
|
|
109
|
+
\uE05C → ड़; # LETTER DDDHA (pronounced RRA)
|
|
110
|
+
\uE05D → ढ़; # LETTER RHA (pronounced RRHA)
|
|
111
|
+
\uE05E → फ़; # LETTER FA
|
|
112
|
+
\uE05F → य़; # LETTER YYA
|
|
113
|
+
\uE060 → ॠ; # LETTER VOCALIC RR
|
|
114
|
+
\uE061 → ॡ; # LETTER VOCALIC LL
|
|
115
|
+
\uE062 → ॢ; # VOWEL SIGN VOCALIC L
|
|
116
|
+
\uE063 → ॣ; # VOWEL SIGN VOCALIC LL
|
|
117
|
+
\uE064 → ।; # DANDA
|
|
118
|
+
\uE065 → ॥; # DOUBLE DANDA
|
|
119
|
+
\uE066 → ०; # DIGIT ZERO
|
|
120
|
+
\uE067 → १; # DIGIT ONE
|
|
121
|
+
\uE068 → २; # DIGIT TWO
|
|
122
|
+
\uE069 → ३; # DIGIT THREE
|
|
123
|
+
\uE06A → ४; # DIGIT FOUR
|
|
124
|
+
\uE06B → ५; # DIGIT FIVE
|
|
125
|
+
\uE06C → ६; # DIGIT SIX
|
|
126
|
+
\uE06D → ७; # DIGIT SEVEN
|
|
127
|
+
\uE06E → ८; # DIGIT EIGHT
|
|
128
|
+
\uE06F → ९; # DIGIT NINE
|
|
129
|
+
\uE070→॰; # ABBREVIATION SIGN
|
|
130
|
+
\uE071→र; # LETTER RA WITH MIDDLE DIAGONAL
|
|
131
|
+
\uE072→र; # LETTER RA WITH LOWER DIAGONAL
|
|
132
|
+
\uE073→; # RUPEE MARK
|
|
133
|
+
\uE074→रू; # RUPEE SIGN
|
|
134
|
+
\uE075→; # CURRENCY NUMERATOR ONE
|
|
135
|
+
\uE076→; # CURRENCY NUMERATOR TWO
|
|
136
|
+
\uE077→; # CURRENCY NUMERATOR THREE
|
|
137
|
+
\uE078→; # CURRENCY NUMERATOR FOUR
|
|
138
|
+
\uE079→; # CURRENCY NUMERATOR ONE LESS THAN THE DENOMINATOR
|
|
139
|
+
\uE07A→; # CURRENCY DENOMINATOR SIXTEEN
|
|
140
|
+
\uE07B→; # ISSHAR
|
|
141
|
+
\uE07C→; # TIPPI
|
|
142
|
+
\uE07D→; # ADDAK
|
|
143
|
+
\uE07E→; # IRI
|
|
144
|
+
\uE07F→; # URA
|
|
145
|
+
\uE080→; # EK ONKAR
|
|
146
|
+
\uE081→व; # FALLBACK FOR ORIYA LETTER WA
|
|
147
|
+
\uE082→ॽ; # Devanagari Glottal Sign
|
|
148
|
+
\uE083→त्; # Bengali Khanda-ta
|
|
149
|
+
# :: NFC;
|
|
150
|
+
# eof
|
|
151
|
+
|