cldr-transforms 46.0.0-BETA2

package/transforms/ta-ta_FONIPA.txt

@@ -0,0 +1,73 @@
+
+$c = [\u0B95\u0B99\u0B9A\u0B9C\u0B9E\u0B9F\u0BA3\u0BA4\u0BA8-\u0BAA\u0BAE-\u0BB9];
+$v = [\u0BBE-\u0BC2\u0BC6-\u0BC8\u0BCA-\u0BCC];
+$nasal = [ŋɲɳnm];
+# Delete ZWNJ and ZWJ to simplify further processing.
+\u200C → ;
+\u200D → ;
+::NFC;
+# Manifest the implicit vowel after every consonant that is not followed by a
+# dependent vowel or virama.
+($c) } [^$v \u0BCD] → $1 a;
+::Null;
+ஃப → f;
+ஃ → x;
+அ → a;
+ஆ → aː;
+இ → i;
+ஈ → iː;
+உ → u;
+ஊ → uː;
+எ → e;
+ஏ → eː;
+ஐ → aɪ̯;
+ஒ → o;
+ஓ → oː;
+ஔ → aʊ̯;
+$nasal { க → g;
+க → k;
+ங → ŋ;
+$nasal { ச → d͡ʒ;
+ச்ச → t͡ʃ;
+[ʈr] { ச → t͡ʃ;
+ச → s \u02BC;
+ஜ → d͡ʒ;
+ஞ → ɲ;
+$nasal { ட → ɖ;
+ட → ʈ;
+ண → ɳ;
+$nasal { த → d̪;
+த → t̪;
+ந → n;
+ன → n;
+$nasal { ப → b;
+ப → p;
+ம → m;
+ய → j;
+ர → r;
+ற்ற → tʳ;
+ற } \u0BCD → tʳ;
+$nasal { ற → tʳ;
+ற → r;
+ல → l;
+ள → ɭ;
+ழ → ɻ;
+வ → ʋ;
+ஶ → ʃ;
+ஷ → ʂ;
+ஸ் } ர → ʃ;
+ஸ → s;
+ஹ → h;
+\u0BBE → aː;
+\u0BBF → i;
+\u0BC0 → iː;
+\u0BC1 → u;
+\u0BC2 → uː;
+\u0BC6 → e;
+\u0BC7 → eː;
+\u0BC8 → aɪ̯;
+\u0BCA → o;
+\u0BCB → oː;
+\u0BCC → aʊ̯;
+\u0BCD → ;
+

package/transforms/tlh-am.json

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

package/transforms/tlh-am.txt

@@ -0,0 +1,4 @@
+
+::tlh-tlh_FONIPA;
+::am_FONIPA-am;
+

package/transforms/tlh-ar.json

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

package/transforms/tlh-ar.txt

@@ -0,0 +1,4 @@
+
+::tlh-tlh_FONIPA;
+::und_FONIPA-ar;
+

package/transforms/tlh-chr.json

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

package/transforms/tlh-chr.txt

@@ -0,0 +1,4 @@
+
+::tlh-tlh_FONIPA;
+::und_FONIPA-chr;
+

package/transforms/tlh-fa.json

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

package/transforms/tlh-fa.txt

@@ -0,0 +1,4 @@
+
+::tlh-tlh_FONIPA;
+::und_FONIPA-fa;
+

package/transforms/tlh-tlh_FONIPA.json

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

package/transforms/tlh-tlh_FONIPA.txt

@@ -0,0 +1,46 @@
+
+# Transformation from Klingon (tlh) to its IPA transcription (tlh_FONIPA).
+# http://en.wikipedia.org/wiki/Klingon_language#Phonology
+# http://www.kli.org/tlh/sounds.html
+::NFC;
+tlh → t͡ɬ;
+# Dipthongs as per http://www.kli.org/tlh/sounds.html. For those that
+# exist in English, we following the American English pronunciation.
+# http://en.wikipedia.org/wiki/Diphthong#English
+aw → aʊ̯; # similar to English ‹cow›
+ew → ɛʊ̯; # does not exist in English
+Iw → ɪʊ̯; # des not exist English
+ay → aɪ̯; # similar to English ‹why›
+ey → eɪ̯; # similar to English ‹may›
+Iy → ɪː; # KLI says like English ‹key›, which is not a diphthong
+oy → oɪ̯; # KLI says English ‹boy›, which would be [ɔɪ̯], but ‹o› is [o]
+uy → uɪ̯; # similar to English ‹gooey› but in on syllable
+ch → t͡ʃ;
+gh → ɣ;
+ng → ŋ;
+p → pʰ;
+t → tʰ;
+q → qʰ;
+’ → ʔ;
+\' → ʔ;
+b → b;
+D → ɖ;
+Q → q͡χ;
+j → d͡ʒ;
+S → ʂ;
+H → x;
+v → v;
+m → m;
+n → n;
+r → r;
+w → w;
+l → l;
+y → j;
+a → ɑ;
+e → ɛ;
+I → ɪ;
+o → o;
+u → u;
+\- → ;
+::NFC;
+

package/transforms/tr-Lower.json

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

package/transforms/tr-Lower.txt

@@ -0,0 +1,13 @@
+
+# I and i-dotless; I-dot and i are case pairs in Turkish and Azeri
+# 0130; 0069; 0130; 0130; tr; # LATIN CAPITAL LETTER I WITH DOT ABOVE
+İ→i;
+# When lowercasing, remove dot_above in the sequence I + dot_above, which will turn into i.
+# This matches the behavior of the canonically equivalent I-dot_above
+# 0307; ; 0307; 0307; tr After_I; # COMBINING DOT ABOVE
+# When lowercasing, unless an I is before a dot_above, it turns into a dotless i.
+# 0049; 0131; 0049; 0049; tr Not_Before_Dot; # LATIN CAPITAL LETTER I
+I([^[:ccc=Not_Reordered:][:ccc=Above:]]*)\u0307 → i$1 ;
+I→ı ;
+::Any-Lower();
+

package/transforms/tr-Title.json

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

package/transforms/tr-Title.txt

@@ -0,0 +1,11 @@
+
+# I and i-dotless; I-dot and i are case pairs in Turkish and Azeri
+# Make any string of letters after a cased letter be lower, with rules for i
+[:cased:] [:case-ignorable:]* { İ → i;
+[:cased:] [:case-ignorable:]* { I → ı;
+[:cased:] [:case-ignorable:]* { (.) → &Any-Lower($1) ;
+# Otherwise all lowercase go to upper (titlecase stay as is)
+i→İ ;
+([:Lowercase:]) → &Any-Upper($1) ;
+# do later I([^[:ccc=Not_Reordered:][:ccc=Above:]]*)\u0307 → i$1 ;
+

package/transforms/tr-Upper.json

@@ -0,0 +1,8 @@
+{
+  "_visibility": "external",
+  "_aliasBcp47": "tr-t-d0-upper",
+  "_source": "tr",
+  "_direction": "forward",
+  "_target": "Upper",
+  "_rulesFile": "tr-Upper.txt"
+}

package/transforms/tr-Upper.txt

@@ -0,0 +1,8 @@
+
+# Copyright (C) 2011-2013, Apple Inc.; Unicode, Inc.; and others. All Rights Reserved.
+# I and i-dotless; I-dot and i are case pairs in Turkish and Azeri
+# When uppercasing, i turns into a dotted capital I
+# 0069; 0069; 0130; 0130; tr; # LATIN SMALL LETTER I
+i→İ;
+::Any-Upper();
+

package/transforms/ug-ug_FONIPA.json

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

package/transforms/ug-ug_FONIPA.txt

@@ -0,0 +1,69 @@
+
+# Uyghur to phonemic transcription
+# Alphabet http://learn101.org/uyghur_alphabet.php + youtube video https://youtu.be/dw1DVFgC8x0
+# Vowel-consonant harmony in Uyghur. Laura Becker http://home.uni-leipzig.de/lbecker/papers/VowelConsHarmonyUyghur.pdf
+# Shadike, Muhetaer & Wasili, Buheliqiguli. (2014). Acoustic Articulatory of Uyghur Phonetics. Applied Mechanics and Materials. 519→520. 762→766. 10.4028/www.scientific.net/AMM.519→520.762.
+# https://kuscholarworks.ku.edu/bitstream/handle/1808/5624/EngYakDwy2009_Uyg1full_10.pdf?seque
+#
+# Originally prepared by Alina Korshunova <alinakor2202@gmail.com>
+# as part of her internship at PanLex (panlex.org)
+ئ → ʔ;
+ا → a;
+ە → ‎ɛ;
+ب‎ → b;
+پ → p;
+ت → t;
+ج → d͡ʒ;
+چ → t͡ʃ;
+خ → x;
+د → d;
+ر → r;
+ز → z;
+ژ → ʒ;
+س → s;
+ش → ʃ;
+غ → ʁ;
+ف → f;
+ق → q;
+ك → k;
+گ → ɡ;
+ڭ → ŋ;
+ل → l;
+م → m;
+ن → n;
+ھ → h;
+و → o;
+ۇ → u;
+ۆ → ø;
+ۈ → y;
+ۋ → w;
+ې → e;
+ى → i;
+ي → j;
+# Handle geminated consonants
+::Null;
+bb → bː;
+pp → pː;
+tt } [^\u0361] → tː; # make sure not to consume tt͡ʃ
+d͡ʒd͡ʒ → d͡ʒː;
+t͡ʃt͡ʃ → t͡ʃː;
+xx → xː;
+dd } [^\u0361] → dː; # make sure not to consume dd͡ʒ
+rr → rː;
+zz → zː;
+ʒʒ → ʒː;
+ss → sː;
+ʃʃ → ʃː;
+ʁʁ → ʁː;
+ff → fː;
+qq → qː;
+kk → kː;
+ɡɡ → ɡː;
+ŋŋ → ŋː;
+ll → lː;
+mm → mː;
+nn → nː;
+hh → hː;
+ww → wː;
+jj → jː;
+

package/transforms/und-Ethi-t-und-cyrl-m0-gutgarts.json

@@ -0,0 +1,11 @@
+{
+  "_backwardAlias": "Cyrillic-Ethiopic/Gutgarts",
+  "_visibility": "external",
+  "_backwardAliasBcp47": "und-Ethi-t-und-cyrl-m0-gutgarts",
+  "_alias": "Ethiopic-Cyrillic/Gutgarts",
+  "_aliasBcp47": "und-Cyrl-t-und-ethi-m0-gutgarts",
+  "_source": "Ethi",
+  "_direction": "both",
+  "_target": "Cyrl",
+  "_rulesFile": "und-Ethi-t-und-cyrl-m0-gutgarts.txt"
+}