cldr-transforms 46.0.0-BETA2

package/transforms/ch-am.json

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

package/transforms/ch-am.txt

@@ -0,0 +1,4 @@
+
+::ch-ch_FONIPA;
+::am_FONIPA-am;
+

package/transforms/ch-ar.json

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

package/transforms/ch-ar.txt

@@ -0,0 +1,4 @@
+
+::ch-ch_FONIPA;
+::und_FONIPA-ar;
+

package/transforms/ch-ch_FONIPA.json

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

package/transforms/ch-ch_FONIPA.txt

@@ -0,0 +1,79 @@
+
+# Transformation from Chamorro (ch) to its IPA transcription (ch_FONIPA).
+#
+# http://en.wikipedia.org/wiki/Chamorro_language#Orthography
+# http://www.omniglot.com/writing/chamorro.htm
+# http://guampedia.com/chamorro-orthography-rules/
+# http://finochamoru.blogspot.com/2009/04/leksion-chamoru-pronunsiasion.html
+#
+# Recorded sound samples: http://www.chamorro.com/fino/fino.html
+#
+# http://guampedia.com/chamorro-orthography-rules/ lists in section 3.b)
+# graphemes that would be used for loanwords/proper names. Most examples
+# are Spanish. Our rules thus generate the Spanish sounds [θ], [x], [β]
+# and [w] even though these sounds are not used by the Chamorro language.
+::Lower;
+::NFC;
+\' → ʔ;
+’ → ʔ;
+# The IPA chart from Omniglot appears to be mixing up [æ] and [ɑ] when
+# explaining how to pronounce ‹a› and ‹å›. The language course on
+# finochamoru.blogspot.com copies the pronunciation chart from Omniglot,
+# but then explains that ‹å› gets prounounced like in English ‹father›,
+# which would be [ɑ]. Also, the sound samples on www.chamorro.com pronounce
+# ‹a› as [æ] and ‹å› as [ɑ].
+a → æ;
+å → ɑ;
+b → b;
+ch → t͡s;
+{c} [eéií] → θ; # loanwords
+c → k; # loanwords
+d → d;
+e → e;
+f → f;
+gu → ɡʷ;
+g → ɡ;
+h → h;
+i → i;
+j → x ; # loanwords
+k → k;
+l → l;
+m → m;
+ng → ŋ;
+ñ → ɲ;
+n → n;
+o → o;
+p → p;
+{qu} [eéiíy] → k; # loanwords
+q → k; # loanwords
+rr → r;
+r → ɾ;
+s → s;
+t → t;
+u → u;
+v → β; # loanwords
+w → w; # loanwords
+{x} h?[aáåeéiíoóuú$] → ks; # loanwords
+{x} [^aáåeéiíoóuú$] → s; # loanwords
+x → ks ; # loanwords
+# Wikipedia [http://en.wikipedia.org/wiki/Chamorro_language#Orthography]
+# writes that ‹y› gets pronounced as [d͡z], while Omniglot says [d͡ʒ].
+y → d͡z;
+\- → \.; # hyphen is a syllable boundary, eg ‹sena-ta›
+# Handle geminated consonants.
+::Null;
+bb → bː;
+dd → dː;
+ff → fː;
+ɡɡ → ɡː;
+hh → hː;
+kk → kː;
+ll → lː;
+mm → mː;
+nn → nː;
+pp → pː;
+rr → rː;
+ss → sː;
+tt → tː;
+::NFC;
+

package/transforms/ch-chr.json

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

package/transforms/ch-chr.txt

@@ -0,0 +1,4 @@
+
+::ch-ch_FONIPA;
+::und_FONIPA-chr;
+

package/transforms/ch-fa.json

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

package/transforms/ch-fa.txt

@@ -0,0 +1,4 @@
+
+::ch-ch_FONIPA;
+::und_FONIPA-fa;
+

package/transforms/chr-chr_FONIPA.json

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

package/transforms/chr-chr_FONIPA.txt

@@ -0,0 +1,111 @@
+
+# References
+# ----------
+# [1] http://www.omniglot.com/writing/cherokee.htm
+# [2] https://en.wikipedia.org/wiki/Cherokee_language#Phonology
+# [3] Edward Finegan. Language: Its structure and use. ISBN 978-1-4130-3055-6.
+#     Figure 12-4: The Cherokee Writing System, page 401.
+::[[:sc=Cher:][:P:][:M:]];
+::upper;
+[:P:]+ → ' ';
+Ꭰ → a;
+Ꭱ → e;
+Ꭲ → i;
+Ꭳ → o;
+Ꭴ → u;
+Ꭵ → ə̃;
+Ꭶ → ɡa;
+Ꭷ → ka;
+Ꭸ → ɡe;
+Ꭹ → ɡi;
+Ꭺ → ɡo;
+Ꭻ → ɡu;
+Ꭼ → ɡə̃;
+Ꭽ → ha;
+Ꭾ → he;
+Ꭿ → hi;
+Ꮀ → ho;
+Ꮁ → hu;
+Ꮂ → hə̃;
+Ꮃ → la;
+Ꮄ → le;
+Ꮅ → li;
+Ꮆ → lo;
+Ꮇ → lu;
+Ꮈ → lə̃;
+Ꮉ → ma;
+Ꮊ → me;
+Ꮋ → mi;
+Ꮌ → mo;
+Ꮍ → mu;
+Ᏽ → mə̃;
+Ꮎ → na;
+Ꮏ → hna;
+Ꮐ → nah;
+Ꮑ → ne;
+Ꮒ → ni;
+Ꮓ → no;
+Ꮔ → nu;
+Ꮕ → nə̃;
+Ꮖ → kʷa;
+Ꮗ → kʷe;
+Ꮘ → kʷi;
+Ꮙ → kʷo;
+Ꮚ → kʷu;
+Ꮛ → kʷə̃;
+Ꮝ → s;
+Ꮜ → sa;
+Ꮞ → se;
+Ꮟ → si;
+Ꮠ → so;
+Ꮡ → su;
+Ꮢ → sə̃;
+Ꮣ → da;
+Ꮤ → ta;
+Ꮥ → de;
+Ꮦ → te;
+Ꮧ → di;
+Ꮨ → ti;
+Ꮩ → do;
+Ꮪ → du;
+Ꮫ → də̃;
+Ꮬ → d͡la;
+Ꮭ → t͡ɬa;
+Ꮮ → t͡ɬe;
+Ꮯ → t͡ɬi;
+Ꮰ → t͡ɬo;
+Ꮱ → t͡ɬu;
+Ꮲ → t͡ɬə̃;
+Ꮳ → t͡sa;
+Ꮴ → t͡se;
+Ꮵ → t͡si;
+Ꮶ → t͡so;
+Ꮷ → t͡su;
+Ꮸ → t͡sə̃;
+Ꮹ → wa;
+Ꮺ → we;
+Ꮻ → wi;
+Ꮼ → wo;
+Ꮽ → wu;
+Ꮾ → wə̃;
+Ꮿ → ja;
+Ᏸ → je;
+Ᏹ → ji;
+Ᏺ → jo;
+Ᏻ → ju;
+Ᏼ → jə̃;
+̋ → ˥;
+́ → ˦;
+̄ → ˧;
+̀ → ˧˩;
+[ ̌ ̆ ] → ˨˦;
+̂ → ˥˧;
+[:M:] → ;
+::null;
+a a+ → aː;
+e e+ → eː;
+i i+ → iː;
+o o+ → oː;
+u u+ → uː;
+ə̃ {ə̃}+ → ə̃;
+

package/transforms/cs-am.json

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

package/transforms/cs-am.txt

@@ -0,0 +1,4 @@
+
+::cs-cs_FONIPA;
+::am_FONIPA-am;
+

package/transforms/cs-ar.json

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

package/transforms/cs-ar.txt

@@ -0,0 +1,4 @@
+
+::cs-cs_FONIPA;
+::und_FONIPA-ar;
+

package/transforms/cs-chr.json

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

package/transforms/cs-chr.txt

@@ -0,0 +1,4 @@
+
+::cs-cs_FONIPA;
+::und_FONIPA-chr;
+

package/transforms/cs-cs_FONIPA.json

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

package/transforms/cs-cs_FONIPA.txt

@@ -0,0 +1,74 @@
+
+# Transformation from Czech to Czech in IPA transcription (cs_FONIPA).
+# The transcription is not fully phonemic since we mark allophonic variations
+# of /m/, /n/, /x/ and /ɦ/.
+#
+# http://en.wikipedia.org/wiki/Czech_alphabet
+# http://en.wikipedia.org/wiki/Czech_language#Phonology
+# http://en.wikipedia.org/wiki/Czech_orthography
+#
+# Transform input to normalized form NFC, and to lowercase.
+::NFC;
+::Lower;
+#
+#
+#
+#
+# Digraphs.
+#
+ch } [ bdďjlmnňrřvwzž ] → ɣ ;
+ch → x ;
+dě → ɟɛ ;
+mě → mɲɛ ;
+tě → cɛ ;
+ně → ɲɛ ;
+dž → d \u0361 ʒ;  # affricate indicated by ligature tie
+dz → d \u0361 z;  # affricate indicated by ligature tie
+#
+#
+#
+a → a ;
+á → aː ;
+b → b ;
+c → t \u0361 s;  # affricate indicated by ligature tie
+č → t \u0361 ʃ;  # affricate indicated by ligature tie
+d → d ;
+ď → ɟ ;
+e → ɛ ;
+é → ɛː ;
+ě → jɛ ;
+f → f ;
+g → ɡ ;
+h } [cčfkpqsštťx] → h ;
+h → ɦ ;
+i → ɪ ;
+í → iː ;
+j → j ;
+k → k ;
+l → l ;
+m } [fvw] → ɱ ;
+m → m ;
+n } [gkqx] → ŋ ;
+n → n ;
+ň → ɲ ;
+o → o ;
+ó → oː ;
+p → p ;
+q → kv ;
+r → r ;
+ř → r̝ ;
+s → s ;
+š → ʃ ;
+t → t ;
+ť → c ;
+u → u ;
+ú → uː ;
+ů → uː ;
+v → v ;
+w → v ;
+x → ks ;
+y → ɪ ;
+ý → iː ;
+z → z ;
+ž → ʒ ;
+

package/transforms/cs-fa.json

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

package/transforms/cs-fa.txt

@@ -0,0 +1,4 @@
+
+::cs-cs_FONIPA;
+::und_FONIPA-fa;
+

package/transforms/cs-ja.json

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

package/transforms/cs-ja.txt

@@ -0,0 +1,4 @@
+
+::cs-cs_FONIPA;
+::cs_FONIPA-ja;
+

package/transforms/cs-ko.json

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

package/transforms/cs-ko.txt

@@ -0,0 +1,4 @@
+
+::cs-cs_FONIPA;
+::cs_FONIPA-ko;
+

package/transforms/cs_FONIPA-ja.json

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

package/transforms/cs_FONIPA-ja.txt

@@ -0,0 +1,228 @@
+
+# Transforms a Phonemic IPA transcription of Czech (cs_FONIPA) to Katakana.
+$word_boundary = [-\ $] ;
+$vowel = [aeiouw] ;       # Vowels and glides
+$not_vowel = [^$vowel] ;
+#
+#
+# First pass: Collapse phonetic distinctions not preserved in Katakana.
+d͡ʒ → | ʒ ;
+d͡z → | z ;
+ɛ → | e;
+ll → | l;
+ɣ → | x;
+ɦ → | h;
+ŋ → | n;
+ɾ → | r;
+t \u0361 ʃ → | ʧ;
+t \u0361 → t;
+[i{i̯}ɪ]+ → i;
+[uw{u̯}]+ → u;
+#
+#
+nn → n ;
+#
+#
+::Null;
+#
+#
+# Main pass: Phoneme to Katakana conversion.
+'.' → ;
+a → ア;
+ba → バ;
+bb → ッ | b;
+be → ベ;
+bi → ビ;
+bje → ビェ ;
+bo → ボ;
+bu → ブ;
+b } $word_boundary → プ;
+b → ブ;
+ca → チャ ;
+ce → チェ ;
+ci → チ ;
+cu → チュ ;
+co → チョ ;
+c → チ ;
+da → ダ;
+dd → ッ | d;
+de → デ;
+di → ディ;
+do → ド;
+du → ドゥ;
+d } $word_boundary → ト;
+d → ド;
+e → エ;
+fa → ファ;
+fe → フェ;
+ff → ッ | f;
+fi → フィ;
+fo → フォ;
+fu → フ;
+f → フ;
+ha → ハ;
+hi → ヒ;
+hu → フ;
+he → ヘ;
+ho → ホ;
+h } $word_boundary → ;
+h → フ;
+ga → ガ; # not backed by data
+ge → グエ; # not backed by data
+gi → グイ; # not backed by data
+gg → ッ | g; # not backed by data
+go → ゴ; # not backed by data
+gu → グ; # not backed by data
+g } $word_boundary → ク; # not backed by data
+g → グ; # not backed by data
+i → イ ;
+ɟa → ジャ;
+ɟi → ジ; # not backed by data
+ɟo → ジョ; # not backed by data
+ɟe → ジェ;
+ɟu → ジュ; # not backed by data
+#
+#
+ja → ヤ;
+ji → イ;
+jo → ヨ;
+je → イェ;
+ju → ユ; # not backed by data
+j → イ;
+#
+#
+ka → カ;
+ke → ケ;
+ki → キ;
+kk → ッ | k;
+ko → コ;
+ku → ク;
+k → ク;
+la → ラ ;
+le → レ ;
+li → リ ;
+lho → ロ ;
+lo → ロ ;
+lu → ル ;
+l → ル ;
+ma → マ ;
+me → メ ;
+#
+#mɲe → ミェ;
+mi → ミ ;
+mo → モ ;
+mu → ム ;
+m } [bp] → ン ;
+m → ム ;
+na → ナ ;
+ne → ネ ;
+ni → ニ ;
+no → ノ ;
+nu → ヌ ;
+n → ン ;
+ɲa → ニャ ;
+ɲe → ニェ ;
+ɲi → ニ ;
+ɲo → ニョ ;
+ɲu → ニュ ;
+ɲ → ニ ;
+o → オ ;
+pa → パ ;
+pe → ペ ;
+pi → ピ ;
+po → ポ ;
+pp → ッ | p;
+pu → プ ;
+p → プ ;
+#
+#
+r̝a → ジャ;
+r̝e → ジェ;
+r̝i → ジ;
+r̝o → ジョ; # not backed by data
+r̝u → ジュ; # not backed by data
+r̝ → ルシ;
+#
+#
+ra → ラ ;
+re → レ ;
+ri → リ ;
+ro → ロ ;
+ru → ル ;
+r → ル;
+sa → サ ;
+se → セ ;
+si → シ ;
+so → ソ ;
+su → ス ;
+s → ス ;
+ʃa → シャ;
+ʃo → ショ;
+ʃi → シ;
+ʃu → シュ;
+ʃe → シェ;
+ʃ → シュ;
+ta → タ;
+te → テ ;
+ti → ティ ;
+to → ト ;
+tu → トゥ ;
+tsa → ツァ ;
+tse → ツェ ;
+tsi → ツィ ;
+tso → ツォ ;
+tsu → ツ ;
+ts → ツ ;
+tt → ッ | t;
+t → ト ;
+#
+#
+ʧa → チャ ;
+ʧe → チェ ;
+ʧi → チ ;
+ʧo → チョ ;
+ʧu → チュ ;
+ʧ } k → チ ;
+ʧ → チュ ;
+u → ウ ;
+#
+#
+va → ヴァ;
+ve → ヴェ;
+vi → ヴィ;
+vo → ヴォ;
+vu → ヴ;
+vje → ヴィエ ;
+v } $word_boundary → フ;
+v → ヴ;
+#
+#
+xa → ハ ;
+xe → ヘ ;
+xi → ヒ ;
+xo → ホ ;
+xu → フ ;
+x → フ ;
+#
+#
+za → ザ;
+ze → ゼ;
+zi → ジ;
+zo → ゾ;
+zu → ズ;
+z } $word_boundary → ス;
+z → ズ;
+ʒa → ジャ;
+ʒe → ジェ; # not backed by data
+ʒi → ジ; # not backed by data
+ʒo → ジョ; # not backed by data
+ʒu → ジュ; # not backed by data
+ʒ } k → シュ;
+ʒ → ジュ;
+#
+#
+ː → ー; # Long vowel
+' ' → ・;
+#
+#
+

package/transforms/cs_FONIPA-ko.json

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