cldr-transforms 46.0.0-BETA2

package/transforms/ia-ia_FONIPA.txt

@@ -0,0 +1,71 @@
+
+# Transformation from Interlingua (ia) to its IPA transcription (ia_FONIPA).
+# http://en.wikipedia.org/wiki/Interlingua#Interlingua_alphabet
+# http://www.omniglot.com/writing/interlingua.htm
+::NFC;
+::Lower;
+# Interlinua has five falling diphthongs.
+# http://en.wikipedia.org/wiki/Interlingua#Orthography_and_pronunciation
+ai → ai̯;
+au → au̯;
+ei → ei̯;  # rare
+eu → eu̯;
+oi → oi̯;  # rare
+# ‹g› is usually [ɡ], but it is [d͡ʒ] in -age, -agi-, and -egi-.
+# http://www.omniglot.com/writing/interlingua.htm
+$vowel = [aeiouy];
+$end_of_word = [$ ];
+{age} $end_of_word → ad͡ʒe;
+{agi} $vowel → ad͡ʒ;  # viagiar → viad͡ʒar
+agi → ad͡ʒi;
+{egi} $vowel → ed͡ʒ;  # legier → led͡ʒer
+egi → ed͡ʒi;
+gg → ɡ;
+g → ɡ;
+# Omniglot: “The sounds of g and k assimilate a preceding n as in English.”
+{n} [gkqx] → ŋ;
+nn → n;
+n → n;
+a → a;
+bb → b;
+b → b;
+cc → k;
+{c} [ei] → t͡s;
+ch → k;
+c → k;
+dd → d;
+d → d;
+e → e;
+ff → f;
+f → f;
+h → ;  # ‹h› is normally silent.
+i → i;
+j → ʒ;
+kk → k;
+k → k;
+ll → l;
+l → l;
+mm → m;
+m → m;
+o → o;
+ph → f;  # philosophos, physica
+pp → p;
+p → p;
+que → ke;
+qu → kw;
+q → k;
+rr → ɾ;
+r → ɾ;
+sh → ʃ;  # rare
+ss → s;
+s → s;
+[^s] {ti} [aeiouy] → t͡sj;
+tt → t;
+t → t;
+u → u;
+v → v;
+w → v;
+x → ks;
+y → i;
+z → z;
+

package/transforms/it-am.json

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

package/transforms/it-am.txt

@@ -0,0 +1,257 @@
+
+# Italian to Amharic Transliteration
+::NFD(NFC);
+::Lower();
+::[:Latin:] fullwidth-halfwidth();
+#
+#
+# Variables.
+$vowel = [aeiou];
+$consonant = [bcdfghjklmnpqrstvwxyz];
+#
+#
+# Ignore apostrophe.
+($consonant) \' → | $1;
+\' → ;
+#
+#
+cqu → ኩ ;
+cc → | c;
+ca → ካ;
+cia → ቻ;
+cio → ቺዮ;
+ciu → ቺዩ;
+ci → ቺ;
+cu → ኩ;
+ce → ቼ;
+co → ኮ;
+cha → ካ;
+chi → ኪ;
+chu → ኩ;
+che → ኬ;
+cho → ኮ;
+c } $consonant → ክ;
+#
+#
+gg → | g;
+ghi → ጊ;
+ghe → ጌ;
+ghu → ጉ;
+gli → | li;
+gna → ኛ;
+gni → ኚ;
+gnu → ኙ;
+gne → ኜ;
+gno → ኞ;
+gn } $consonant → ኝ;
+#
+#
+ga → ጋ;
+gia → ጂያ;
+giu → ጂዩ;
+gio → ጂዮ;
+gi → ጂ;
+gu → ጉ;
+ge → ጄ;
+go → ጎ;
+g } $consonant → ግ;
+#
+#
+rr → | r;
+ra → ራ;
+ri → ሪ;
+ru → ሩ;
+re → ሬ;
+ro → ሮ;
+r } $consonant → ር;
+#
+#
+ll → | l;
+la → ላ;
+li → ሊ;
+lu → ሉ;
+le → ሌ;
+lo → ሎ;
+l } $consonant → ል;
+#
+#
+tt → | t;
+ta → ታ;
+ti → ቲ;
+thi → ቲ;
+tu → ቱ;
+thu → ቱ;
+te → ቴ;
+the → ቴ;
+to → ቶ;
+tho → ቶ;
+tzu → ፁ;
+tz → | zz;
+t } $consonant → ት;
+#
+#
+dd → | d;
+da → ዳ;
+di → ዲ;
+du → ዱ;
+de → ዴ;
+do → ዶ;
+d } $consonant → ድ;
+#
+#
+mm → | m;
+ma → ማ;
+mi → ሚ;
+mu → ሙ;
+me → ሜ;
+mo → ሞ;
+m } $consonant → ም;
+#
+#
+nn → | n;
+na → ና;
+ni → ኒ;
+nu → ኑ;
+ne → ኔ;
+no → ኖ;
+n } $consonant → ን;
+#
+#
+ff → | f;
+fa → ፋ;
+fi → ፊ;
+fu → ፉ;
+fe → ፌ;
+fo → ፎ;
+f } $consonant → ፍ;
+#
+#
+bb → | b;
+ba → ባ;
+bi → ቢ;
+bu → ቡ;
+be → ቤ;
+bo → ቦ;
+b } $consonant → ብ;
+#
+#
+pp → | p;
+pa → ፓ;
+pi → ፒ;
+pu → ፑ;
+pe → ፔ;
+po → ፖ;
+p } $consonant → ፕ;
+#
+#
+vv → | v;
+va → ቫ;
+vi → ቪ;
+vu → ቩ;
+ve → ቬ;
+vo → ቮ;
+v } $consonant → ቩ;
+#
+#
+sa } nt[ao] → ሣ;
+ss → | \~s;
+#
+#
+# 's' is voiced before [bdglmnrv].
+sb → ዝ | b;
+sd → ዝ | d;
+sg → ዝ | g;
+sl → ዝ | l;
+sm → ዝ | m;
+sn → ዝ | n;
+sr → ዝ | r;
+sv → ዝ | v;
+#
+#
+# Force 's' after a consonat to be unvoiced.
+($consonant) s } $vowel → | $1 \~ s;
+\~sa → ሣ;
+\~si → ሢ;
+\~su → ሡ;
+\~se → ሤ;
+\~so → ሦ;
+#
+#
+# 's' at the beginning is usually unvoiced.
+[:^Letter:] { sa → ሣ;
+[:^Letter:] { si → ሢ;
+[:^Letter:] { su → ሡ;
+[:^Letter:] { se → ሤ;
+[:^Letter:] { so → ሦ;
+#
+#
+# Otherwise voiced 's' are common.
+sa → ዛ;
+si → ዚ;
+su → ዙ;
+se → ዜ;
+so → ዞ;
+#
+#
+scia → ሺያ;
+sci → ሺ;
+sce → ሼ;
+#
+#
+zz → | \~z;
+#
+# Force 'z' after a consonat to be unvoiced.
+($consonant) z → | $1 \~z;
+\~za → ጻ;
+\~zi → ጺ;
+\~zu → ጹ;
+\~ze → ጼ;
+\~zo → ጾ;
+#
+#
+# Otherwise voiced 'z' are common except for 'zi'.
+za → ዛ;
+[:^Letter:] { zi → ዚ;
+zi → ዚ;
+zu → ዙ;
+ze → ዜ;
+zo → ዞ;
+#
+#
+ja → ያ;
+je → ዬ;
+j → | i;
+#
+#
+# Standalone vowels and consonants.
+a → አ;
+i → ዒ;
+u → ዑ;
+e → ዔ;
+o → ዖ;
+#
+#
+b → ብ;
+c → ክ;
+d → ድ;
+f → ፍ;
+g → ግ;
+h → ህ;
+k → ክ;
+l → ል;
+m → ም;
+n → ን;
+p → ፕ;
+q → ክ;
+r → ር;
+s → ስ;
+t → ት;
+v → ው;
+x → | cs;
+y → | i;
+z → ዝ;
+#
+#
+[:nonspacing mark:] → ;
+::NFC(NFD);
+

package/transforms/it-ja.json

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

package/transforms/it-ja.txt

@@ -0,0 +1,259 @@
+
+# Italian to Katakana Transliteration Table for ICU
+# Based on:
+#   "現代イタリア語入門" (大学書林, 1974. ISBN:978-4475017176)
+#   http://ja.wikipedia.org/wiki/%E3%82%A4%E3%82%BF%E3%83%AA%E3%82%A2%E8%AA%9E
+::NFD(NFC);
+::Lower();
+::[:Latin:] fullwidth-halfwidth();
+#
+#
+# Variables.
+$vowel = [aeiou];
+$consonant = [bcdfghjklmnpqrstvwxyz];
+#
+#
+# Ignore apostrophe.
+($consonant) \' → | $1;
+\' → ;
+#
+#
+cqu → ック;
+cc → ッ | c;
+ca → カ;
+ッ { cia → チャ;
+cio → チョ;
+ci → チ;
+cu → ク;
+ce → チェ;
+co → コ;
+#
+#
+cha → シャ;
+chi → キ;
+chu → チュ;
+che → ケ;
+cho → チョ;
+#
+#
+gg → ッ | g;
+ghi → ギ;
+ghe → ゲ;
+ghu → グ;
+gli → | li;
+gna → ニャ;
+gni → ニ;
+gnu → ヌ;
+gne → ニェ;
+gno → ニョ;
+#
+#
+ga → ガ;
+gia → ジャ;
+giu → ジュ;
+gio → ジョ;
+gi → ジ;
+gu → グ;
+ge → ジェ;
+go → ゴ;
+#
+#
+rr → ッ | r;
+ra → ラ;
+ri → リ;
+ru → ル;
+re → レ;
+ro → ロ;
+#
+#
+ll → ッ | l;
+la → ラ;
+li → リ;
+lu → ル;
+le → レ;
+lo → ロ;
+#
+#
+tt → ッ | t;
+ta → タ;
+ti → ティ;
+thi → ティ;
+tu → トゥ;
+thu → トゥ;
+te → テ;
+the → テ;
+to → ト;
+tho → ト;
+tzu → | ッツ;
+tz → | zz;
+#
+#
+dd → ッ | d;
+da → ダ;
+di → ディ;
+du → ドゥ;
+de → デ;
+do → ド;
+#
+#
+ma → マ;
+mi → ミ;
+mu → ム;
+me → メ;
+mo → モ;
+m } $consonant → ン;
+#
+#
+na → ナ;
+ni → ニ;
+nu → ヌ;
+ne → ネ;
+no → ノ;
+#
+#
+ff → ッ | f;
+fa → ファ;
+fi → フィ;
+fu → フ;
+fe → フェ;
+fo → フォ;
+#
+#
+bb → ッ | b;
+ba → バ;
+bi → ビ;
+bu → ブ;
+be → ベ;
+bo → ボ;
+#
+#
+pp → ッ | p;
+pa → パ;
+pi → ピ;
+pu → プ;
+pe → ペ;
+po → ポ;
+#
+#
+vv → ッ | v;
+va → ヴァ;
+vi → ヴィ;
+vu → ヴ;
+ve → ヴェ;
+vo → ヴォ;
+#
+#
+sa } nt[ao] → サ;
+ss → ッ | \~s;
+#
+#
+# 's' is voiced before [bdglmnrv].
+sb → ズ | b;
+sd → ズ | d;
+sg → ズ | g;
+sl → ズ | l;
+sm → ズ | m;
+sn → ズ | n;
+sr → ズ | r;
+sv → ズ | v;
+#
+#
+# Force 's' after a consonat to be unvoiced.
+($consonant) s } $vowel → | $1 \~ s;
+\~sa → サ;
+\~si → シ;
+\~su → ス;
+\~se → セ;
+\~so → ソ;
+#
+#
+# 's' at the beginning is usually unvoiced.
+[:^Letter:] { sa → サ;
+[:^Letter:] { si → シ;
+[:^Letter:] { su → ス;
+[:^Letter:] { se → セ;
+[:^Letter:] { so → ソ;
+#
+#
+# Otherwise voiced 's' are common.
+sa → ザ;
+si → ジ;
+su → ズ;
+se → ゼ;
+so → ゾ;
+#
+#
+scia → シャ;
+sci → シ;
+sce → シェ;
+#
+#
+zz → ッ | \~z;
+#
+# Force 'z' after a consonat to be unvoiced.
+($consonant) z → | $1 \~z;
+\~za → ツァ;
+\~zi → ツィ;
+\~zu → ツ;
+\~ze → ツェ;
+\~zo → ツォ;
+#
+#
+# Otherwise voiced 'z' are common except for 'zi'.
+za → ザ;
+[:^Letter:] { zi → ジ;
+zi → ツィ;
+zu → ズ;
+ze → ゼ;
+zo → ゾ;
+#
+#
+ja → ヤ;
+je → イェ;
+j → | i;
+#
+#
+# Standalone vowels and consonants.
+a → ア;
+i → イ;
+u → ウ;
+e → エ;
+o → オ;
+#
+#
+b → ブ;
+c → ク;
+d → ド;
+f → フ;
+g → グ;
+h → ;
+k → | c;
+l → ル;
+m → ム;
+n → ン;
+p → プ;
+q → | c;
+r → ル;
+s → ス;
+t → ト;
+v → ヴ;
+x → | cs;
+y → | i;
+z → ツ;
+#
+#
+# word delimiter of transliterated foreign phrase is '・'.
+' ' → ・;
+#
+#
+# Latin hyphen should be transliterated to U+30A0 (KATAKANA-HIRAGANA
+# DOUBLE HYPHEN), ideally. But since the character isn't supported by
+# many fonts or software, we use U+FF1D (FULLWIDTH EQUALS SIGN),
+# which is widely used as "double hyphen".
+#
+\- → ＝;
+#
+#
+[:nonspacing mark:] → ;
+::NFC(NFD);
+

package/transforms/ja_Latn-ko.json

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