cldr-transforms 46.0.0-BETA2

package/transforms/ja_Latn-ko.txt

@@ -0,0 +1,141 @@
+
+# Japanese (Rōmaji) to Korean (Hangul) transliteration table for ICU.
+# Can be run in sequence after e.g. Katakana-Latin.
+#
+# Based on 문교부 고시 제85-11호 (1986. 1. 7.) 외래어 표기법
+# For background info, see http://ko.wikisource.org/wiki/문교부_고시_제85-11호
+# and http://ko.wikipedia.org/wiki/외래어_표기법 (外來語表記法)
+::NFD(NFC);
+::[:Latin:] Lower();
+$consonant = [ᄀᄁᄂᄃᄄᄅᄆᄇᄈᄉᄊᄋᄌᄍᄎᄏᄐᄑᄒ];
+$lengthMarker = [̂̄];
+#
+#
+# Drop hyphens and apostrophes.
+[\-\'] → ;
+#
+#
+# Turn long /e:/ into diphthong /ei/.
+e $lengthMarker → | e i ;
+#
+#
+# Ignore vowel length everywhere else.
+$lengthMarker → ;
+#
+#
+# Vowels.
+#
+[^$consonant] { ( [aiueoyw] ) → ᄋ | $1 ;  # Supply a required null initial.
+a → ᅡ ;
+i\~e → | ie ;  # イェ
+i → ᅵ ;
+u\~a → | wa ;  # クァ, グァ
+u\~i → ᅱ ;     # ウィ, クィ, etc.
+u\~e → ᅰ ;     # ウェ
+u\~o → ᅯ ;     # ウォ
+u → ᅮ ;
+e → ᅦ ;
+o → ᅩ ;
+#
+#
+# Geminates.
+#
+kk → ᆺ | k ;
+ss → ᆺ | s ;
+tt → ᆺ | t ;
+tc → ᆺ | c ;
+cc → ᆺ | c ;
+hh → ᆺ | h ;
+ff → ᆺ | f ;
+rr → ᆺ | r ;
+gg → ᆺ | g ;
+zz → ᆺ | z ;
+jj → ᆺ | j ;
+dd → ᆺ | d ;
+bb → ᆺ | b ;
+vv → ᆺ | v ;
+pp → ᆺ | p ;
+#
+#
+# Consonants.
+#
+' ' { k → | g ;   # Beginning of a word (after space).
+^k      → | g ;   # Beginning of the string.
+k → ᄏ ;
+#
+#
+sh → | sy ;
+su → 스 ;
+s → ᄉ ;
+#
+#
+te\~     → | t ;   # テュ
+to\~     → | t ;   # トゥ
+tsu\~    → | ch ;  # ツァ, ツィ, etc.
+tsu → 쓰 ;
+ts       → | ch ;
+' ' { t  → | d ;
+^t       → | d ;
+t → ᄐ ;
+' ' { ch → | j ;
+^ch      → | j ;
+ch → ᄎ ;
+#
+#
+n } [\ \'bcdfghjkmnprstwz] → ᆫ ;
+n$ → ᆫ ;
+n → ᄂ ;
+#
+#
+h → ᄒ ;
+fu\~ → | p ;   # フュ
+fu   → | hu ;
+f    → | p ;
+#
+#
+m } [bmp] → ᆫ ;
+m → ᄆ ;
+#
+#
+ya → ᅣ ;
+yi → ᅵ ;  # Added for convenience, after shi.
+yu → ᅲ ;
+ye → ᅨ ;
+yo → ᅭ ;
+#
+#
+r → ᄅ ;
+#
+#
+wa → ᅪ ;
+w → ;
+#
+#
+g → ᄀ ;
+#
+#
+zu → 즈 ;
+z → | j ;
+j → ᄌ ;
+#
+#
+de\~  → | d ;   # デュ
+dji\~ → | j ;   # ヂァ, ヂゥ, etc.
+dji   → | ji ;  # ヂ
+do\~  → | d ;   # ドゥ
+dzu\~ → | j ;   # ヅァ, ヅィ, etc.
+dzu   → | zu ;  # ヅ
+dz    → | j ;
+d → ᄃ ;
+#
+#
+b → ᄇ ;
+vu\~ → | b ;  # ヴァ, etc.
+v    → | b ;
+#
+#
+p → ᄑ ;
+#
+#
+::NFC(NFD);
+

package/transforms/ja_Latn-ru.json

@@ -0,0 +1,8 @@
+{
+  "_visibility": "external",
+  "_aliasBcp47": "ru-t-ja-latn",
+  "_source": "ja_Latn",
+  "_direction": "forward",
+  "_target": "ru",
+  "_rulesFile": "ja_Latn-ru.txt"
+}

package/transforms/ja_Latn-ru.txt

@@ -0,0 +1,123 @@
+
+# Japanese (Rōmaji) to Russian (Cyrillic) Polivanov transliteration for ICU.
+# Can be run in sequence after e.g. Katakana-Latin.
+#
+# These rules cannot be used to target Bulgarian, Serbian, Tajik, or Ukrainian.
+#
+# TODO: Cyrillization needs to respect morpheme/Kanji boundaries.
+# 中井 becomes Накаи, but 北海道 becomes Хоккайдо.  We need boundary
+# markup in the input in order to do that properly.
+#
+::NFD(NFC);
+::[:Latin:] Lower();
+#
+#
+$lengthMarker = [̂̄];
+#
+#
+# Delete apostrophes.  Apostrophes after "n" are consumed below.
+\' → ;
+#
+#
+# Turn long /e:/ into diphthong /ei/.
+# Note that /ei/ across a morpheme boundary (e.g. 武井 Takei) becomes эи.
+e $lengthMarker → эй ;
+#
+#
+# Turn long /i:/ into two vowels /ii/.
+i $lengthMarker → | i i ;
+#
+#
+# Ignore vowel length everywhere else.
+$lengthMarker → ;
+#
+#
+# Vowels.
+#
+# TODO(mjansche): Enable diphthongs once we have Kanji boundaries.
+## ai → ай ;
+a  → а ;
+i\~e → | ye ;
+i  → и ;
+u\~ → в ;  # ウィ etc.
+#
+## ui → уй ;
+u  → у ;
+e  → э ;
+o  → о ;
+#
+#
+# Consonants.
+#
+k → к ;
+#
+#
+sh → | sy ;
+s → с ;
+#
+#
+ch     → | ty ;
+c } ch → t ;
+te\~   → | t ;   # テュ
+to\~   → | t ;   # トゥ
+tsu\~  → | ts ;  # ツァ, ツィ, etc.
+ts → ц ;
+t  → т ;
+#
+#
+\~tsu → | tsu ;
+#
+#
+n } [bpm] → м ;  # 群馬 → Гумма
+n\' → нъ ;
+n → н ;
+#
+#
+h → х ;
+fu\~ → | f ;  # フュ
+f → ф ;
+#
+#
+m → м ;
+#
+#
+ya → я ;
+yi → и ;  # Added for convenience, after sh, ch, j.
+yu → ю ;
+ye → е ;  # ?? unobserved
+yo → ё ;
+#
+#
+r → р ;
+#
+#
+wa → ва ;
+w → ;
+#
+#
+g → г ;
+#
+#
+j → | zy ;
+z → дз ;
+#
+#
+de\~  → | d ;  # デュ
+dji\~ → | z ;  # ヂャ, ヂュ, etc.
+dj    → | j ;  # ヂ
+do\~  → | d ;  # ドゥ
+dzu\~ → | z ;  # ヅァ, ヅィ, etc.
+dz    → | z ;  # ヅ
+d → д ;
+#
+#
+b → б ;
+vu\~ → | v ;  # ヴァ, etc.
+v → в ;  # ?? unobserved
+#
+#
+p → п ;
+#
+#
+::NFC(NFD);
+

package/transforms/kk-am.json

@@ -0,0 +1,8 @@
+{
+  "_visibility": "external",
+  "_aliasBcp47": "am-t-kk",
+  "_source": "kk",
+  "_direction": "forward",
+  "_target": "am",
+  "_rulesFile": "kk-am.txt"
+}

package/transforms/kk-am.txt

@@ -0,0 +1,4 @@
+
+::kk-kk_FONIPA;
+::am_FONIPA-am;
+

package/transforms/kk-ar.json

@@ -0,0 +1,8 @@
+{
+  "_visibility": "external",
+  "_aliasBcp47": "ar-t-kk",
+  "_source": "kk",
+  "_direction": "forward",
+  "_target": "ar",
+  "_rulesFile": "kk-ar.txt"
+}

package/transforms/kk-ar.txt

@@ -0,0 +1,4 @@
+
+::kk-kk_FONIPA;
+::und_FONIPA-ar;
+

package/transforms/kk-chr.json

@@ -0,0 +1,8 @@
+{
+  "_visibility": "external",
+  "_aliasBcp47": "chr-t-kk",
+  "_source": "kk",
+  "_direction": "forward",
+  "_target": "chr",
+  "_rulesFile": "kk-chr.txt"
+}

package/transforms/kk-chr.txt

@@ -0,0 +1,4 @@
+
+::kk-kk_FONIPA;
+::und_FONIPA-chr;
+

package/transforms/kk-fa.json

@@ -0,0 +1,8 @@
+{
+  "_visibility": "external",
+  "_aliasBcp47": "fa-t-kk",
+  "_source": "kk",
+  "_direction": "forward",
+  "_target": "fa",
+  "_rulesFile": "kk-fa.txt"
+}

package/transforms/kk-fa.txt

@@ -0,0 +1,4 @@
+
+::kk-kk_FONIPA;
+::und_FONIPA-fa;
+

package/transforms/kk-kk_FONIPA.json

@@ -0,0 +1,8 @@
+{
+  "_visibility": "external",
+  "_aliasBcp47": "kk-fonipa-t-kk",
+  "_source": "kk",
+  "_direction": "forward",
+  "_target": "kk_FONIPA",
+  "_rulesFile": "kk-kk_FONIPA.txt"
+}

package/transforms/kk-kk_FONIPA.txt

@@ -0,0 +1,59 @@
+
+# http://en.wikipedia.org/wiki/Kazakh_language#Phonology
+#
+# Output:
+#     m n ŋ
+#     p b t d k ɡ q ɢ
+#     f v x h
+#     s z ʃ ʒ ɕ t͡s t͡ɕ
+#     j w l ɾ
+#     ʉ ʊ ɘ ə ɛ æ ɑ
+#     i̯ɘ y̯ʉ u̯ʊ
+::NFC;
+::Lower;
+ә → æ;
+а → ɑ;
+п → p;
+б → b;
+д → d;
+е → i̯ɘ;
+г → ɡ;
+ғ → ɢ;
+һ → h;
+і → ɘ;
+й → j;
+к → k;
+қ → q;
+л → l;
+м → m;
+н → n;
+ң → ŋ;
+р → ɾ;
+с → s;
+т → t;
+у → w;
+з → z;
+ш → ʃ;
+ж → ʒ;
+ы → ə;
+ө → y̯ʉ;
+о → u̯ʊ;
+ү → ʉ;
+ұ → ʊ;
+# Some characters that are not really Kazakh, but appear frequently
+# in Kazakh-language text as part of loanwords.
+в → v;
+и → i;
+ц → t͡s;
+ч → t͡ɕ;
+щ → ɕ;
+х → x;
+ф → f;
+э → ɛ;
+ю → ju;
+я → jɑ;
+ё → jo;
+ъ →;
+ь →;
+\- → ' ';
+

package/transforms/ky-am.json

@@ -0,0 +1,8 @@
+{
+  "_visibility": "external",
+  "_aliasBcp47": "am-t-ky",
+  "_source": "ky",
+  "_direction": "forward",
+  "_target": "am",
+  "_rulesFile": "ky-am.txt"
+}

package/transforms/ky-am.txt

@@ -0,0 +1,4 @@
+
+::ky-ky_FONIPA;
+::am_FONIPA-am;
+

package/transforms/ky-ar.json

@@ -0,0 +1,8 @@
+{
+  "_visibility": "external",
+  "_aliasBcp47": "ar-t-ky",
+  "_source": "ky",
+  "_direction": "forward",
+  "_target": "ar",
+  "_rulesFile": "ky-ar.txt"
+}

package/transforms/ky-ar.txt

@@ -0,0 +1,4 @@
+
+::ky-ky_FONIPA;
+::und_FONIPA-ar;
+

package/transforms/ky-chr.json

@@ -0,0 +1,8 @@
+{
+  "_visibility": "external",
+  "_aliasBcp47": "chr-t-ky",
+  "_source": "ky",
+  "_direction": "forward",
+  "_target": "chr",
+  "_rulesFile": "ky-chr.txt"
+}

package/transforms/ky-chr.txt

@@ -0,0 +1,4 @@
+
+::ky-ky_FONIPA;
+::und_FONIPA-chr;
+

package/transforms/ky-fa.json

@@ -0,0 +1,8 @@
+{
+  "_visibility": "external",
+  "_aliasBcp47": "fa-t-ky",
+  "_source": "ky",
+  "_direction": "forward",
+  "_target": "fa",
+  "_rulesFile": "ky-fa.txt"
+}

package/transforms/ky-fa.txt

@@ -0,0 +1,4 @@
+
+::ky-ky_FONIPA;
+::und_FONIPA-fa;
+

package/transforms/ky-ky_FONIPA.json

@@ -0,0 +1,8 @@
+{
+  "_visibility": "external",
+  "_aliasBcp47": "ky-fonipa-t-ky",
+  "_source": "ky",
+  "_direction": "forward",
+  "_target": "ky_FONIPA",
+  "_rulesFile": "ky-ky_FONIPA.txt"
+}

package/transforms/ky-ky_FONIPA.txt

@@ -0,0 +1,71 @@
+
+# Transformation from Kyrgyz (ky) to its IPA transcription (ky_FONIPA).
+# http://en.wikipedia.org/wiki/Kyrgyz_alphabet#Correspondence_chart
+::Lower;
+::NFC;
+$consonant_sound = [bdfɡklmnŋpqrʁsʃtvzʒχ];
+аа → ɑː;
+а  → ɑ;
+б  → b;
+в  → v;
+{г} [аоуы]  → ʁ;
+г  → ɡ;
+дж → d͡ʒ;  # eg. Джамадан
+дд → dː;
+д  → d;
+[$] {е} → je;  # at the beginning of a word
+е  → e;
+ё  → jo;  # appears only in loanwords
+ж  → d͡ʒ;
+з  → z;
+ии → iː;
+и  → i;
+й  → j;
+кк → kː;
+[$] {к} [еёиɵүю] → ɡ;    # eg. кирет, кишиден, келди
+{к} [аоуы] → q;          # eg. чокусу, факультетин, нукура
+[ɑouɯ] ː? {к} → q;       # eg. Исак, Бирок, Кутлук, Ферганалык
+[y] $consonant_sound+ ː? {к} [$] → k; # eg. мүлк, түрк
+$consonant_sound {к} [$] → q; # eg. даңк, калк, кырк
+[ŋ] {к} → q;
+к → k;
+# TODO(sascha): Verify whether /lʲ/ is really phonemic in Kyrgyz;
+# is there really a minimal pair with /l/ versus /lʲ/?
+[eøy] ː? {л}к → lʲ;  # eg. мүлк, күлкү, өлкө, эзелки
+лл → lː;
+л  → l;
+мм → mː;
+м  → m;
+нн → nː;
+н  → n;
+ң  → ŋ;
+оо → oː;
+о  → o;
+өө → øː;
+ө  → ø;
+п  → p;
+р  → r;
+сс → sː;
+с  → s;
+тт → tː;
+тч → t͡ʃ;    # eg. екетчилерден
+т  → t;
+уу → uː;
+у  → u;
+үү → yː;
+ү  → y;
+ф  → f;     # only in loanwords
+х  → χ;
+ц  → t͡s;    # only in loanwords
+ч  → t͡ʃ;
+ш  → ʃ;
+щ  → ʃ t͡ʃ;  # only in loanwords
+ъ  → ;      # no phonemic value; appears only in loanwords
+ы  → ɯ;
+ь  → ;      # no phonemic value; appears only in loanwords
+ээ → eː;
+э  → e;
+ю  → ju;
+я  → jɑ;
+\-  → ' ';
+

package/transforms/la-la_FONIPA.json

@@ -0,0 +1,8 @@
+{
+  "_visibility": "external",
+  "_aliasBcp47": "la-fonipa-t-la",
+  "_source": "la",
+  "_direction": "forward",
+  "_target": "la_FONIPA",
+  "_rulesFile": "la-la_FONIPA.txt"
+}

package/transforms/la-la_FONIPA.txt

@@ -0,0 +1,79 @@
+
+# Transformation from Latin (la) to its IPA transcription (la_FONIPA).
+# http://en.wikipedia.org/wiki/Latin_spelling_and_pronunciation
+# http://en.wikipedia.org/wiki/Wikipedia:IPA_for_Latin
+#
+# These rules follow the Wikipedia description of the presumed pronunciation
+# of Classical Latin. This is different from Medieval Latin, and it is also
+# different from the ecclesiastical pronunciation used by the Roman Catholic
+# church.
+::Lower;
+::NFC;
+$vowel = [aáàăāeéèĕēiíìĭīoóòŏōuúùŭūæœ];
+$end_of_word = [$ ];
+ae → aj;
+av → aw;
+æ → aj; # 19th century English orthography
+ā → aː;
+[aáàă] → a;
+b → b;
+ch → kʰ; # Greek loanwoards
+c → k;
+d → d;
+ev → ew;
+ē → eː;
+[eéèĕ] → ɛ;
+f → f;
+{g} n → ŋ; # eg. agnus
+g → ɡ;
+h → h;
+ī → iː;
+{[iíìĭ]} $vowel → j; # eg. cuius
+[iíìĭ] → ɪ;
+k → k;
+l → l;
+m → m;
+{n} [bpfm] → m; # eg. infirmus
+{n} [gckq] → ŋ; # eg. quinque
+n → n;
+œ → oj; # 19th century English orthography
+oe → oj;
+ō → oː;
+[oóòŏ] → ɔ;
+ph → pʰ; # Greek loanwords
+p → p;
+qu → kʷ;
+qv → kʷ;
+rh → rʰ; # Greek loanwords
+r → r;
+s → s;
+th → tʰ; # Greek loanwords
+t → t;
+ū → uː;
+[uúùŭ] → ʊ;
+{v} $vowel → w;
+v → u;
+xs → ks; # Old Latin spelling
+x → ks;
+y → y; # Greek loanwords
+z → d͡z; # eg. zerum
+::Null;
+# Gemination of double consonants.
+# http://en.wikipedia.org/wiki/Latin_spelling_and_pronunciation#Double_consonants
+bb → bː;
+dd → dː;
+ɡɡ → ɡː;
+hh → hː;
+kk → kː;
+ll → lː;
+mm → mː;
+nn → nː;
+pp → pː;
+rr → rː;
+ss → sː;
+tt → tː;
+# Velarization of [l].
+# http://en.wikipedia.org/wiki/Latin_spelling_and_pronunciation#cite_note-20
+{l} [^aeɛiouː] → ɫ;
+::NFC;
+

package/transforms/lt-Lower.json

@@ -0,0 +1,8 @@
+{
+  "_visibility": "external",
+  "_aliasBcp47": "lt-t-d0-lower",
+  "_source": "lt",
+  "_direction": "forward",
+  "_target": "Lower",
+  "_rulesFile": "lt-Lower.txt"
+}

package/transforms/lt-Lower.txt

@@ -0,0 +1,20 @@
+
+# Introduce an explicit dot above when lowercasing capital Is and Js
+# whenever there are more accents above.
+# (of the accents used in Lithuanian: grave, acute, tilde above, and ogonek)
+# 0049; 0069 0307; 0049; 0049; lt More_Above; # LATIN CAPITAL LETTER I
+# 004A; 006A 0307; 004A; 004A; lt More_Above; # LATIN CAPITAL LETTER J
+# 012E; 012F 0307; 012E; 012E; lt More_Above; # LATIN CAPITAL LETTER I WITH OGONEK
+# 00CC; 0069 0307 0300; 00CC; 00CC; lt; # LATIN CAPITAL LETTER I WITH GRAVE
+# 00CD; 0069 0307 0301; 00CD; 00CD; lt; # LATIN CAPITAL LETTER I WITH ACUTE
+# 0128; 0069 0307 0303; 0128; 0128; lt; # LATIN CAPITAL LETTER I WITH TILDE
+::NFD();
+I } [^[:ccc=Not_Reordered:][:ccc=Above:]]* [:ccc=Above:] → i \u0307;
+J } [^[:ccc=Not_Reordered:][:ccc=Above:]]* [:ccc=Above:] → j \u0307;
+I \u0328 } [^[:ccc=Not_Reordered:][:ccc=Above:]]* [:ccc=Above:] → i \u0328 \u0307;
+I \u0300 → i \u0307 \u0300;
+I \u0301 → i \u0307 \u0301;
+I \u0303 → i \u0307 \u0303;
+::Any-Lower();
+::NFC();
+

package/transforms/lt-Title.json

@@ -0,0 +1,8 @@
+{
+  "_visibility": "external",
+  "_aliasBcp47": "lt-t-d0-title",
+  "_source": "lt",
+  "_direction": "forward",
+  "_target": "Title",
+  "_rulesFile": "lt-Title.txt"
+}

package/transforms/lt-Title.txt

@@ -0,0 +1,15 @@
+
+# Make any string of letters after a cased letter be lower
+::NFD();
+[:cased:] [:case-ignorable:]* {I } [^[:ccc=Not_Reordered:][:ccc=Above:]]* [:ccc=Above:] → i \u0307;
+[:cased:] [:case-ignorable:]* {J } [^[:ccc=Not_Reordered:][:ccc=Above:]]* [:ccc=Above:] → j \u0307;
+[:cased:] [:case-ignorable:]* {I \u0328 } [^[:ccc=Not_Reordered:][:ccc=Above:]]* [:ccc=Above:] → i \u0328 \u0307;
+[:cased:] [:case-ignorable:]* {I \u0300 → i \u0307 \u0300;
+[:cased:] [:case-ignorable:]* {I \u0301 → i \u0307 \u0301;
+[:cased:] [:case-ignorable:]* {I \u0303 → i \u0307 \u0303;
+[:cased:] [:case-ignorable:]* { (.) → &Any-Lower($1) ;
+# Otherwise all lowercase go to upper (titlecase stay as is)
+[:Soft_Dotted:] [^[:ccc=Not_Reordered:][:ccc=Above:]]* { \u0307 → ;
+([:Lowercase:]) → &Any-Upper($1) ;
+::NFC();
+