twitter_cldr 3.6.0 → 4.0.0

data/resources/shared/transforms/az-Lower.yml

@@ -0,0 +1,12 @@
+--- 
+:transforms: 
+  - 
+    :direction: forward
+    :rules: 
+      - İ>i;
+      - "I([^[:ccc=Not_Reordered:][:ccc=Above:]]*)\\u0307 > i$1 ;"
+      - "I>ı ;"
+      - "::Any-Lower();"
+    :source: az
+    :target: Lower
+    :variant: ~

data/resources/shared/transforms/az-Title.yml

@@ -0,0 +1,13 @@
+--- 
+:transforms: 
+  - 
+    :direction: forward
+    :rules: 
+      - "[:cased:] [:case-ignorable:]* { İ > i;"
+      - "[:cased:] [:case-ignorable:]* { I > ı;"
+      - "[:cased:] [:case-ignorable:]* { (.) > &Any-Lower($1) ;"
+      - "i>İ ;"
+      - "([:Lowercase:]) > &Any-Upper($1) ;"
+    :source: az
+    :target: Title
+    :variant: ~

data/resources/shared/transforms/az-Upper.yml

@@ -0,0 +1,10 @@
+--- 
+:transforms: 
+  - 
+    :direction: forward
+    :rules: 
+      - i>İ;
+      - "::Any-Upper();"
+    :source: az
+    :target: Upper
+    :variant: ~

data/resources/shared/transforms/ch-ch_FONIPA.yml

@@ -0,0 +1,71 @@
+--- 
+:transforms: 
+  - 
+    :direction: forward
+    :rules: 
+      - ""
+      - "::Lower;"
+      - "::NFC;"
+      - ""
+      - "\\' > ʔ;"
+      - "’ > ʔ;"
+      - ""
+      - "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"
+      - ""
+      - "y > d͡z;"
+      - ""
+      - "\\- > \\.; # hyphen is a syllable boundary, eg ‹sena-ta›"
+      - ""
+      - "::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;"
+    :source: ch
+    :target: ch_FONIPA
+    :variant: ~

data/resources/shared/transforms/cs-cs_FONIPA.yml

@@ -0,0 +1,62 @@
+--- 
+:transforms: 
+  - 
+    :direction: forward
+    :rules: 
+      - "::NFC;"
+      - "::Lower;"
+      - "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 ;"
+    :source: cs
+    :target: cs_FONIPA
+    :variant: ~

data/resources/shared/transforms/cs-ja.yml

@@ -0,0 +1,10 @@
+--- 
+:transforms: 
+  - 
+    :direction: forward
+    :rules: 
+      - "::cs-cs_FONIPA;"
+      - "::cs_FONIPA-ja;"
+    :source: cs
+    :target: ja
+    :variant: ~

data/resources/shared/transforms/cs-ko.yml

@@ -0,0 +1,10 @@
+--- 
+:transforms: 
+  - 
+    :direction: forward
+    :rules: 
+      - "::cs-cs_FONIPA;"
+      - "::cs_FONIPA-ko;"
+    :source: cs
+    :target: ko
+    :variant: ~

data/resources/shared/transforms/cs_FONIPA-ja.yml

@@ -0,0 +1,201 @@
+--- 
+:transforms: 
+  - 
+    :direction: forward
+    :rules: 
+      - "$word_boundary = [-\\ $] ;"
+      - "$vowel = [aeiouw] ;       # Vowels and glides"
+      - "$not_vowel = [^$vowel] ;"
+      - "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;"
+      - "'.' > ;"
+      - "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 ;"
+      - "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"
+      - "' ' > ・;"
+    :source: cs_FONIPA
+    :target: ja
+    :variant: ~

data/resources/shared/transforms/cs_FONIPA-ko.yml

@@ -0,0 +1,88 @@
+--- 
+:transforms: 
+  - 
+    :direction: forward
+    :rules: 
+      - "$vowel = [aeɛiɪoux];"
+      - "$start = [\\u0020$];"
+      - "$end = [\\u0020$];"
+      - "b } $end   > peu ;"
+      - "b } $vowel > b ;"
+      - "bj } $vowel > b ;  # objɛc > obeti"
+      - "b          > beu ;"
+      - "c } $end   > ti ;"
+      - "c          > t ;"
+      - "d͡z         > deuj ;"
+      - "d } $end   > teu ;"
+      - "d } $vowel > d ;"
+      - "d          > deu ;"
+      - "ɛ          > e ;"
+      - "f } $vowel > p ;"
+      - "f          > peu ;"
+      - "ɡ } $vowel > g ;"
+      - "ɡ          > geu ;"
+      - "ɦ } $vowel > h ;"
+      - "ɦ          > heu ;"
+      - "h } $vowel > h ;"
+      - "h          > heu ;"
+      - "i          > i ;"
+      - "ɪ          > i ;"
+      - "j } $end   > i ;  # pokoj > pokoi"
+      - "j          > y ;"
+      - "kvu        > keub ;  # kvuasɪ > keubasi"
+      - "ks } $end  > gseu ;  # ksɛroks > jelogseu"
+      - "$start { ks > j ;  # ksɛroks > jelogseu"
+      - "ks         > gs ;  # saksofoːn > sagsopon"
+      - "k } $vowel > k ;"
+      - "k          > keu ;"
+      - "$vowel { l } $vowel > ll ;"
+      - "lz         > lj ;"
+      - "m } $end   > m ;"
+      - "m } $vowel > m ;"
+      - "m } [l]    > m ;"
+      - "m          > meu ;"
+      - "ɲ          > n ;"
+      - "ŋ          > n ;"
+      - "p } $vowel > p ;"
+      - "p } t      > b ;  # koroptɛv"
+      - "p          > peu ;"
+      - "r̝ } $end   > leusi ; # kour̝ > kouleusi"
+      - "r̝ } $vowel > leuj ;"
+      - "r̝ } k      > leusyu ;  # ɦor̝kiː > holeusyuki"
+      - "r̝          > leuju ;"
+      - "r } $vowel > l ;"
+      - "r          > leu ;"
+      - "s } $vowel > s ;"
+      - "s          > seu ;"
+      - "ʃ } $end   > si ;"
+      - "ʃ } $vowel > sy ;"
+      - "ʃ          > syu ;"
+      - "t͡s} $vowel > ch ;"
+      - "t͡s         > cheu ;"
+      - "t͡ʃ} $vowel > ch ;"
+      - "t͡ʃ         > chi ;"
+      - "t } $vowel > t ;"
+      - "t          > teu ;"
+      - "vj         > b ;    # ʒvjɛr̝ɪna > jubeleujina"
+      - "v } $end   > peu ;"
+      - "v } $vowel > b ;"
+      - "v          > beu ;"
+      - "x } $vowel > h ;"
+      - "x          > heu ;"
+      - "ɣ } $vowel > h ;"
+      - "ɣ          > heu ;"
+      - "z } $vowel > j ;    # zaːmɛk > jamekeu"
+      - "z } $end   > seu ;  # ɦmɪz > heumiseu"
+      - "z          > jeu ;  # pozdniː > pojeudeuni"
+      - "ʒ } $vowel > j ;    # ʒɪʒka > jisyuka (first ʒ)"
+      - "ʒ } v      > ju ;   # ʒvjɛr̝ɪna > jubeleujina"
+      - "ʒ } $end   > si ;   # broʒ > beulosi"
+      - "ʒ          > syu ;  # ʒɪʒka > jisyuka (second ʒ)"
+      - "ɟ } $vowel > dy ;"
+      - "ɟ          > ti ;"
+      - "ː          > ;"
+      - "\\u0020     > ;  # space"
+      - ":: Latin-Hangul ();"
+    :source: cs_FONIPA
+    :target: ko
+    :variant: ~