cldr-transforms 46.0.0-BETA2

package/transforms/si-si_FONIPA.txt

@@ -0,0 +1,157 @@
+
+# Sinhala pronunciation rules
+#
+# Output
+#     k ɡ ŋ ᵑɡ c ɟ ɲ ʈ ɖ ⁿɖ t d n ⁿd p b m ᵐb j r l w ʃ s h f
+#     ə əː a aː æ æː i iː u uː e eː o oː
+#
+# References
+# [1] Asanka Wasala, Ruvan Weerasinghe, and Kumudu Gamage:
+#     Sinhala Grapheme-to-Phoneme Conversion and Rules for Schwa Epenthesis.
+#     Proceedings of the COLING/ACL 2006 Main Conference Poster Sessions,
+#     pages 890–897. http://www.aclweb.org/anthology/P06-2114
+# Simplify ya + yansaya to plain ya after a consonant.
+[\u0D9A-\u0DC6] \u0DCA (\u200D)? { ය්‍ය → ය;
+# Delete ZWNJ and ZWJ to simplify further processing.
+\u200C → ;
+\u200D → ;
+# Insert a schwa after every consonant that is not followed by a dependent vowel
+# or virama.
+::Null;
+([\u0D9A-\u0DC6]) } [^\u0DCA-\u0DDF \u0DF2\u0DF3] → $1 ə;
+# Pronunciation rules proper.
+::Null;
+# fප is an alternative spelling of ෆ.
+# This occurs e.g. in ඩේවිඩ් කොපර්fපීල්ඩ් (David Copperfield)
+# [see http://bradshawofthefuture.blogspot.com/2013/02/f.html].
+[Ff]ප → f;
+# zස is seemingly the only way to unambiguously indicate a voiced /z/ sound.
+# This occurs in e.g. ඇල්zසයිම' රෝගය (Alzheimer's disease)
+# [see https://si.wikipedia.org/wiki/ඇල්zසයිම%27_රෝගය]
+# or in zසීබ්‍රා (zebra) [see https://si.wikipedia.org/wiki/‍zසීබ්‍රා].
+[Zz]ස → z;
+ං → ŋ;
+o → ŋ;  # common substitution for anusvaraya
+ඃ ([\u0D9A-\u0DC6]) → | $1 \u0DCA $1;  # TODO: check which consonants geminate
+ඃ → h;
+අ → a;
+ආ → aː;
+ඇ → æ;
+ඈ → æː;
+ඉ → i;
+ඊ → iː;
+උ → u;
+ඌ → uː;
+ඍ → ri;
+ඎ → ruː;
+ඏ → ilu;
+ඐ → iluː;
+එ → e;
+ඒ → eː;
+ඓ → aj;
+ඔ → o;
+ඕ → oː;
+ඖ → aw;  # TODO: check if this is correct
+ක → k;
+ඛ → k;
+ග → ɡ;
+ඝ → ɡ;
+ඞ → ŋ;
+ඟ → ᵑɡ;
+ච → c;
+ඡ → c;
+ජ → ɟ;
+ඣ → ɟ;
+ඤ → ɲ;
+ඥ → kɲ;  # TODO: double-check
+ඦ → ɟ;
+ට → ʈ;
+ඨ → ʈ;
+ඩ → ɖ;
+ඪ → ɖ;
+ණ → n;
+ඬ → ⁿɖ;
+ත → t;
+ථ → t;
+ද → d;
+ධ → d;
+න → n;
+ඳ → ⁿd;
+ප → p;
+ඵ → p;
+බ → b;
+භ → b;
+ම → m;
+ඹ → ᵐb;
+ය → j;
+ර → r;
+ල → l;
+ව → w;
+ශ → ʃ;
+ෂ → ʃ;
+ස → s;
+හ → h;
+ළ → l;
+ෆ → f;
+\u0DCA → ;  # delete virama
+ා → aː;
+ැ → æ;
+ෑ → æː;
+\u0DD2 → i;
+\u0DD3 → iː;
+\u0DD4 → u;
+\u0DD6 → uː;
+ෘ → ru;
+ෙ → e;
+ේ → eː;
+ෛ → aj;
+ො → o;
+ෝ → oː;
+ෞ → aw;  # TODO: check if this is correct
+ෟ → lu;
+ෲ → ruː;
+ෳ → luː;
+# Heuristics for turning /ə/ into /a/. Based on [1].
+$c=[k ɡ ŋ {ᵑɡ} c ɟ ɲ ʈ ɖ {ⁿɖ} t d n {ⁿd} p b m {ᵐb} j r l w ʃ s z h f];
+$s=[:^L:];
+# Rule #1
+::Null;
+$s sv    { ə      → ə;  # exception (a)
+$s k     { ə } r  → ə;  # exception (b)
+$s $c    { ə } $s → ə;  # exception (c)
+$s $c $c { ə      → a;
+$s $c    { ə      → a;
+# Rule #2
+::Null;
+$c r { ə } $c → a;  # clause (a) and (b)
+$c r { a } h  → a;  # clause (d), exception
+$c r { a } $c → ə;  # clause (c)
+# Rule #3
+# The paper is unclear about what this rule means. The interpretation here
+# assumes that "preceded" in the paper is a typo and should be read "followed".
+::Null;
+[a e æ o ə] h { ə → a;
+# Rules #4 through #7
+::Null;
+ə } $c $c     → a;  # Rule #4
+ə } [rbɖʈ] $s → ə;  # Rule #5 exception
+ə } $c     $s → a;  # Rule #5
+ə } ji     $s → a;  # Rule #6
+k { ə } [rl] u    → a;  # Rule #7
+# Rule #8
+# Note that the paper doesn't say explicitly that this rule should be
+# anchored at the beginning of a word, but the remarks before the rules
+# seem to imply this.
+::Null;
+$s k { a } l[aeo]ːj   → ə;  # Typo in paper: /j/ was /y/.
+$s k { a } le[mh][ui] → ə;
+$s k { alə } h[ui]    → əle;
+$s k { a } lə         → ə;
+# Diphthongs
+::Null;
+www+ → ww;  # යෞව්වන
+[i {iː} e {eː} æ {æː} o {oː} a {aː}] { wu → w;
+əji → aj;
+iji → iː;  # perhaps: ij
+[u {uː} e {eː} æ {æː} o {oː} a {aː}] { ji → j;
+

package/transforms/si-si_Latn.json

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

package/transforms/si-si_Latn.txt

@@ -0,0 +1,94 @@
+
+# Based on http://en.wiktionary.org/wiki/Wiktionary:Sinhalese_transliteration
+::[[:Sinh:][\u200C\u200D]];
+::NFKC;
+# Delete ZWNJ and ZWJ to simplify further processing.
+\u200C → ;
+\u200D → ;
+# Insert "a" after every consonant that is not followed by a dependent vowel
+# or virama.
+::Null;
+([\u0D9A-\u0DC6]) } [^\u0DCA-\u0DDF] → $1 a;
+::Null;
+ක → k;
+ට → ṭ;
+ත → t;
+ප → p;
+ග → g;
+ඩ → ḍ;
+ද → d;
+බ → b;
+[Zz]ස → z;
+ස → s;
+ච → c;
+ම → m;
+ල → l;
+ව → v;
+ණ → ṇ;
+හ → h;
+ජ → j;
+න → n;
+ර → r;
+ය → y;
+ළ → ḷ;
+අ → a;
+එ → e;
+ඉ → i;
+ඔ → o;
+උ → u;
+ඇ → æ;
+ෙ → e;
+ි → i;
+ො → o;
+ු → u;
+ැ → æ;
+ආ → ā;
+ඒ → ē;
+ඊ → ī;
+ඕ → ō;
+ඌ → ū;
+ඈ → ǣ;
+ා → ā;
+ේ → ē;
+ී → ī;
+ෝ → ō;
+ූ → ū;
+ෑ → ǣ;
+ඟ → n̆g;
+ඬ → n̆ḍ;
+ඳ → n̆d;
+ඹ → m̆b;
+ඛ → kh;
+ඨ → ṭh;
+ථ → th;
+ඵ → ph;
+ඝ → gh;
+ඪ → ḍh;
+ධ → dh;
+භ → bh;
+ශ → ś;
+ඡ → ch;
+ඤ → ñ;
+ඞ → ṅ;
+ඦ → n̆j;
+ෂ → ṣ;
+ඣ → jh;
+ඥ → gn;
+ෆ → f;
+[Ff]ප → f;
+ඓ → ai;
+ඍ → ṛ;
+ඏ → ḷ;
+ෛ → ai;
+ෘ → ṛ;
+ෟ → ḷ;
+ඖ → au;
+ඎ → ṝ;
+ඐ → ḹ;
+ෞ → au;
+ෲ → ṝ;
+ෳ → ḹ;
+ඃ  → ḥ;
+ං → ṁ;
+් → ;
+

package/transforms/sk-am.json

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

package/transforms/sk-am.txt

@@ -0,0 +1,4 @@
+
+::sk-sk_FONIPA;
+::am_FONIPA-am;
+

package/transforms/sk-ar.json

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

package/transforms/sk-ar.txt

@@ -0,0 +1,4 @@
+
+::sk-sk_FONIPA;
+::und_FONIPA-ar;
+

package/transforms/sk-chr.json

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

package/transforms/sk-chr.txt

@@ -0,0 +1,4 @@
+
+::sk-sk_FONIPA;
+::und_FONIPA-chr;
+

package/transforms/sk-fa.json

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

package/transforms/sk-fa.txt

@@ -0,0 +1,4 @@
+
+::sk-sk_FONIPA;
+::und_FONIPA-fa;
+

package/transforms/sk-ja.json

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

package/transforms/sk-ja.txt

@@ -0,0 +1,4 @@
+
+::sk-sk_FONIPA;
+::sk_FONIPA-ja;
+

package/transforms/sk-sk_FONIPA.json

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

package/transforms/sk-sk_FONIPA.txt

@@ -0,0 +1,101 @@
+
+# Slovak orthography to phonemic transcription.
+# http://en.wikipedia.org/wiki/Slovak_language
+# http://en.wikipedia.org/wiki/Slovak_alphabet
+#
+# Letters that trigger softening; also triggered at end of word.
+# Softening also occurs before "ch", but that starts in "c" so it
+# is included in the set below.
+$soften = [ptťkcčsš$] ;
+#
+#
+# Transform input to normalized form NFC, and to lowercase.
+:: NFC () ;
+:: Lower () ;
+#
+#
+# digraphs
+ch → x ;
+#
+#
+dž } $soften → t \u0361 ʃ ;  # affricate indicated by ligature tie
+dz } $soften → t \u0361 s ;
+dž → d \u0361 ʒ ;
+dz → d \u0361 z ;
+#
+#
+a → a ;
+á → aː ;
+ä → ɛ ;
+b } $soften → p ;
+b → b ;
+c → t \u0361 s;  # affricate indicated by ligature tie
+č → t \u0361 ʃ;  # affricate indicated by ligature tie
+d } [ie] → ɟ ;
+d } $soften → t ;
+d → d ;
+ď } $soften → c ;
+ď → ɟ ;
+e → e ;
+é → eː ;
+f → f ;
+g } $soften → k ;
+g → ɡ ;
+h } $soften → x ;
+h → ɦ ;
+i → ɪ ;
+í → iː ;
+j → j ;
+k → k ;
+ľ → ʎ ;
+l\' → ʎ ;
+l → l ;
+ĺ → l̩ː ;
+m } [fv] → ɱ ;
+m → m ;
+n } [kg] → ŋ ;
+n } [ie] → ɲ ;
+n → n ;
+ň → ɲ ;
+o → ɔ ;
+ó → ɔː ;
+ô → u̯o ;
+p → p ;
+q → kv ;
+r → r ;
+ŕ → r̩ː ;
+s → s ;
+š → ʃ ;
+t } [ie] → c ;
+t\' → c ;
+ť → c ;
+t → t ;
+u → u ;
+ú → uː ;
+vz } $soften → fs ;
+v } $soften → f ;
+[ $] { v } ' ' $soften → f ;  # v as preposition
+v → v ;
+w → v ;
+x → ks ;
+y → ɪ ;
+ý → iː ;
+z } $soften → s ;
+z → z ;
+ž } $soften → ʃ ;
+ž → ʒ ;
+::null;
+bb → bː;
+cc → cː;
+dd → dː;
+ff → fː;
+nn → nː;
+pp → pː;
+rr → rː;
+ss → sː;
+tt → tː;
+vv → vː;
+zz → zː;
+ʃʃ → ʃː;
+ʒʒ → ʒː;
+

package/transforms/sk_FONIPA-ja.json

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

package/transforms/sk_FONIPA-ja.txt

@@ -0,0 +1,252 @@
+
+# Phonemic transcription of Slovak into Katakana.
+$vowel = [aeiouw] ;       # Vowels and glides
+$not_vowel = [^$vowel] ;
+#
+#
+# First pass: Collapse phonetic distinctions that are not preserved in Katakana
+#
+t \' → | t ʃ ;
+t \u0361 → | t ;
+d \u0361 ʒ → | ʒ ;
+d \u0361 z → | z ;
+r̩ → | r ;
+u̯ → | u ;
+ŋ → | n ;
+ɔ → | o ;
+ɛ → | a ;
+ɟ → | d ;
+ɡ → | g ;
+ɦ → | h ;
+ɪ → | i ;
+ɱ → | m ;
+ʎ → | l;
+::Null;
+([bcdfghklmnprstvzʃʒ]) ː → $1 $1;
+::Null;
+# Main pass: Phoneme to Katakana conversion.
+a → ア;
+ba → バ;
+be → ベ;
+bi → ビ;
+bo → ボ;
+bu → ブ;
+b → ブ;
+#
+#
+ca → チャ ; # not backed by data
+ce → チェ ;
+ci → チ ;
+cu → チュ ; # not backed by data
+co → チョ ; # not backed by data
+c → チ ;
+#
+#
+da → ダ ;
+de → デ ;
+di → ディ ;
+do → ド ;
+du → ドゥ ;
+d → ド ;
+#
+#
+e → エ ;
+#
+#
+fa → ファ ;
+fe → フェ ;
+fi → フィ ;
+fo → フォ ;
+fu → フ ;
+f → フ ;
+#
+#
+ga → ガ;
+ge → ゲ;
+gi → ギ;
+go → ゴ;
+gu → グ;
+g → グ;
+#
+#
+ha → ハ ;
+hwe → フェ ;
+he → ヘ ;
+hi → ヒ ; # not backed by data
+ho → ホ ;
+hu → フ ;
+h → フ ;
+#
+#
+^ { ia → ヤ ;
+i → イ ;
+#
+#
+ja → ヤ ;
+je → イェ ;
+ji → イ ; # not backed by data
+jo → ヨ ;
+ju → ユ ;
+#
+#
+ka → カ ;
+ke → ケ ;
+ki → キ ;
+ko → コ ;
+ku → ク ;
+k → ク ;
+#
+#
+l \' a → リヤ ;
+l \' e → レ ; # not backed by data
+l \' i → リ ; # not backed by data
+l \' o → リヨ ; # not backed by data
+l \' u → リユ ; # not backed by data
+l \' → リ ;
+#
+#
+la → ラ ;
+le → レ ;
+li → リ ;
+lo → ロ ;
+lu → ル ;
+l →  ル ;
+#
+#
+ma → マ ;
+me → メ ;
+mi → ミ ;
+mo → モ ;
+mu → ム ;
+m } [bp] → ン ;
+m → ム ;
+#
+#
+ɲa → ニャ ;
+ɲe → ネ ;
+ɲi → ニ ;
+ɲo → ニョ ; # not backed by data
+ɲu → ニュ ; # not backed by data
+ɲ → ニ ;
+#
+#
+na → ナ ;
+ne → ネ ;
+ni → ニ ;
+no → ノ ;
+nu → ヌ ;
+n → ン ;
+#
+#
+o → オ ;
+#
+#
+pa → パ ;
+pe → ペ ;
+pi → ピ ;
+po → ポ ;
+pu → プ ;
+p → プ ;
+#
+#
+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 ;
+ʃe → シェ ;
+ʃio → ショ ;
+ʃi → シ ;
+ʃo → ショ ;
+ʃu → シュ ;
+ʃ → シュ ;
+#
+#
+ta → タ ;
+te → テ ;
+ti → ティ ;
+to → ト ;
+tu → トゥ ;
+#
+#
+tʃa → チャ ;
+tʃea → チャ ;
+tʃe → チェ ;
+tʃiu → チュ ;
+tʃi → チ ;
+tʃo → チョ ;
+tʃu → チュ ;
+tʃ → チュ ;
+#
+#
+tsa → チャ ;
+tse → ツェ ;
+tsi → ツィ;
+tso → ツォ ;
+tsu → ツ ;
+ts → ツ ;
+t → ト ;
+#
+#
+u → ウ ;
+#
+#
+va → バ ;
+ve → ベ ;
+vu → ブ ;
+vi → ビ ;
+vo → ボ ;
+v → ヴ ;
+#
+#
+wa → ワ ;
+we → エ ; # not backed by data
+wi → イ ; # not backed by data
+wo → オ ; # not backed by data
+wu → ウ ; # not backed by data
+w → ウ ;
+#
+#
+xa → ハ ;
+xe → ヘ ; # not backed by data
+xi → ヒ ; # not backed by data
+xo → ホ ;
+xu → フ ; # not backed by data
+x → フ ;
+#
+#
+za → ザ ;
+ze → ゼ ;
+zi → ジ ;
+zo → ゾ ;
+zu → ズ ;
+z → ズ ;
+#
+#
+ʒa → ジャ ;
+ʒea → ジャ ;
+ʒe → ジェ ;
+ʒiu → ジュ ;
+ʒi → ジ ;
+ʒo → ジョ ;
+ʒu → ジュ ;
+ʒ → ジュ ;
+#
+#
+ː → ー ;
+' ' → ・;
+#
+#
+

package/transforms/ta-ta_FONIPA.json

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