cldr-transforms 46.0.0-BETA2

package/transforms/und-Ethi-t-und-latn.json

@@ -0,0 +1,11 @@
+{
+  "_backwardAlias": "Latin-Ethiopic",
+  "_visibility": "external",
+  "_backwardAliasBcp47": "und-Ethi-t-und-lant",
+  "_alias": "Ethiopic-Latin",
+  "_aliasBcp47": "und-Latn-t-und-ethi",
+  "_source": "Ethi",
+  "_direction": "both",
+  "_target": "Latn",
+  "_rulesFile": "und-Ethi-t-und-latn.txt"
+}

package/transforms/und-Ethi-t-und-latn.txt

@@ -0,0 +1,16 @@
+
+########################################################################
+#
+# This transformation is introduced to serve as a fallback for a
+# language and variant agnostic conversion between Ethiopic-Latin,
+# and Latin-Ethiopic.  In principle, it should act like an alias
+# to the most widely used transliteration system in the present day,
+# which in turn is believed to be the # "Beta Maṣāḥǝft" system
+# maintained by the Hiob Ludolf Centre for Ethiopian Studies,
+#
+########################################################################
+#
+:: Ethiopic-Latin/Beta_Metsehaf ;
+#
+########################################################################
+

package/transforms/und_FONIPA-ar.json

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

package/transforms/und_FONIPA-ar.txt

@@ -0,0 +1,114 @@
+
+# Vowels
+# ------
+# In these rules, we produce ي و ا both for short and for long vowels.
+# This would be wrong for writing Arabic, but when transliterating
+# foreign words and names, it is strongly preferred to vowel marks.
+# However, we emit short schwa [ə] and a few other, schwa-like vowels.
+$IVowel = [i ɪ e {e̞}];
+$UVowel = [y {ɨ} {ʉ} ɯ u ʏ {ɪ̈} {ʊ̈} {ɯ̽} {ʊ} ø ɤ o {ø̞} {ɤ̞} {o̞} ɞ ɔ w {w̥} ʍ ʷ];
+$AVowel = [ɛ œ ɜ ʌ æ ɐ a ɶ {ä} {ɒ̈} ɑ ɒ];
+$SchwaVowel = [ɘ ɵ ə {ɵ̞}];
+$Vowel = [$IVowel $UVowel $AVowel $SchwaVowel];
+$Click = [ʘ ɋ ǀ ʇ ǃ ʗ ǂ ʄ ǁ ʖ];
+$Boundary =  [^[:L:][:M:][:N:]];
+::NFD;
+[ʰ ʱ ʼ  ̃  ̰  ̋  ́  ̄  ̀  ̏  ̌  ̂ ˥ ˦ ˧ ˨ ˩ ꜜ ꜛ ↗ ↘  ͡  ͜  ̯] → ;
+ʲ → j;
+ᵐ → m;
+ⁿ → n;
+ᵑ → ŋ;
+::NFC;
+# TODO: Diphthongs probably need more work.
+# Romanian [sekujesk] → [sekujask], for emitting سيكوياسك not سيكويسك
+$UVowel [j $IVowel] [e {e̞} $SchwaVowel] → uia;
+# Kazakh Аягөз [ɑjɑɡy̯ʉz] → [ɑjɑɡiuz], to emit TODO
+yʉ → iu;
+::NULL;
+# Vowels
+$Boundary {ʔ? $IVowel ː} → إِي;
+$Boundary {ʔ? $IVowel} → إِ;
+{$IVowel ʔ} $Boundary → ئ;
+{$IVowel ː ʔ} $Boundary → يء;
+{$IVowel ː ʔ} [$Vowel] → ئ;
+$IVowel ː? → ي;
+$Boundary {ʔ? $UVowel ː} → أو;
+$Boundary {ʔ? $UVowel} → أ;
+{$UVowel ʔ} $Boundary → ؤ;
+{$UVowel ː ʔ} $Boundary → وء;
+$UVowel ː? → و;
+$Boundary {ʔ? $AVowel ː} → آ;
+$Boundary {ʔ? $AVowel} → أ;
+{$AVowel ʔ} $Boundary → أ;
+{$AVowel ː ʔ} $Boundary → اء;
+$AVowel ː? ʔ $AVowel ː? → اءا;
+$AVowel ː? → ا;
+$Boundary {ʔ? $SchwaVowel ː} → إِي;
+$Boundary {ʔ? $SchwaVowel} → أ;
+$SchwaVowel ː → ي;
+$SchwaVowel → ;
+# TODO: Handle glottal stop.
+ʔ → ;
+# Shadda for long (geminated) consonants
+ː → ّ;
+# Affricates
+[{t͡ʃ} ʧ] → تْش;
+# Clicks
+[ɡ g ɠ k] $Click → كْش;
+$Click → تْش;
+# Nasal stops
+[{m̥} m ɱ] → م;
+[{n̼̊} {n̼} {n̥} n {ɳ̊} ɳ {ɲ̊} {ɲ̥} ɲ] → ن;
+[{ŋ̊} ŋ {ɴ̥} ɴ] k → نك;
+[{ŋ̊} ŋ {ɴ̥} ɴ] [ɡ g ɠ]? → نْغ;
+# Non-nasal stops
+[p b {p̪} {b̪} ɓ] → ب;
+[{d̼} d ɗ ᶑ] → د;
+[{t̼} t] → ت;
+[ʈ] → ط;
+[ɖ] → ض;
+c → تْش;
+ɟ → دج;
+k → ك;
+[ɡ g ɠ] → غ;
+[q ɢ ʡ ʛ] → ق;
+# Sibilant fricatives
+s → س;
+z → ز;
+[ʃ ʂ ɕ ʄ] → ش;
+[ʒ ʐ ʑ] → ج;
+# Non-sibilant fricatives
+[ɸ f v] → ف;
+β → ب;
+[{θ̼} θ {θ̱}] → ث;
+[{ð̼} ð {ð̠}] → ذ;
+ç → ش;
+ʝ $IVowel? ː? → ي;
+[x χ] → خ;
+[ɣ ʁ] → غ;
+ħ → ح;
+ʕ → ع;
+[h ɦ {ʔ̞}] → ه;
+# Approximants, trills, flaps
+ʋ → و;
+ʙ → بر;
+{r̝} → رش;
+[{ɹ̥} {ɹ} {ɻ̊} {ɻ} {ɾ̥} ɾ {ɽ̊} ɽ {r̼} {r̥} r] → ر;
+[{ʀ̥} ʀ] → غ;
+ʜ → ح;
+ʢ → ع;
+j $IVowel? ː? → ي;
+# Laterals
+ɬ → شْل;
+ɮ → جْل;
+{[{ʎ̥} ʎ]} [^ $IVowel j ʝ] → لي;
+[{l̼} {l̥} l {ɭ̊} ɭ {ʎ̥} ʎ] → ل;
+[ʟ {ʟ̠}] → غ;
+# Independent pass for misc cleanup.
+::NULL;
+# Strip off syllable markers
+\. → ;
+# Sequences of three or more ووو look very confusing; we shorten them.
+# Polish Darłowo [darwɔvɔ] → داروو → داروووو
+ووو+ → وو;
+

package/transforms/und_FONIPA-chr.json

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

package/transforms/und_FONIPA-chr.txt

@@ -0,0 +1,172 @@
+
+::NFD;
+̋ → ˥;
+́ → ˦;
+̄ → ˧;
+[ ̀ ̏ ] → ˧˩;
+̌ → ˨˦;
+̂ → ˥˧;
+ə̃ → ə̃;
+[ ̃  ̰ ꜜ ꜛ ↗ ↘ ] → ;
+[{ŋɡ͡} {ŋg͡}] [k q ǃ ʗ ] → nk;
+[{ŋɡ͡} {ŋg͡}] → nɡ;
+{k͡x} → kh;
+{k͡ɬ} → kl;
+[{ɡ͡ǀ} {g͡ǀ}] → t͡ɬ;
+[{l͡ʒ} ɮ] → ls;
+[{n̼} {n̼̊} {m̺} {n̊} {n̥} ⁿ ᵑ {ɳ̊} {ɳ̥} ɳ {ɲ̊} {ɲ̥} ɲ {ɴ̊} {ɴ̥} ɴ {ŋ̊} {ŋ̥} ŋ] → n;
+[ɱ {m̥} {m̪} ᵐ] → m;
+[b {d̼} {b̺} {ɾ̼} ɓ p {t̼} {p̺} pʼ ʘ ɋ] ʰ? → kʷ;  # Bolivia → ᏉᎵᏫᎠ [kʷoliwia], Bahamas → ᏆᎭᎹᏍ [kʷahamas]
+[{t̪} ʈ ǁ ʖ] → t;
+[ɖ ɗ ᶑ ð {ð̠} {ð̼} {β̺}] → d;
+[q ǃ ʗ {q͡χ} {ɡ͡ǃ}] → k;
+[g ɢ ɣ ɠ ʛ] → ɡ;
+[f v β] → w;  # Fiji → ᏫᏥ [wit͡si]
+[θ {θ̱} {θ̞} {θ̼} {ɸ̺} z ʃ ʒ ʂ ʐ ʑ] → s;
+[ɦ {ç} x χ ʕ ʡ ʔ ʰ] → h;
+[r ɾ ɽ ʁ {r̝} ɾ ɽ ʁ {l̥}] → l;
+[ʝ ʲ] → j;
+[ʎ {ʎ̥˔} {ʎ̝} {ʟ̝̊} {ʟ̝}] [y i ɨ ɪ ʉ]? [ʝ ʲ]? → lj;
+[{t͡ʃ} {t͜ʃ} {ʧ} {t͡ɕ} {t͜ɕ} {ʨ} {ʈ͡ʂ} c ɕ {t͡ʃʼ} ǀ ʇ ǂ ʄ] → t͡ɬ;
+[{d͡ʒ} ʤ ʣ {d͡z} {d͜z} {d͡ɕ} ʥ {d͡ʑ} {d͜ʑ} {ɖ͡ʐ} {d͡ʐ} ɟ] → t͡s;
+[y i ɨ ɪ ʉ] → i;
+[ə ɛ æ ɘ] → ə̃;
+[ʊ ɯ] → u;
+[ɔ ø] → o;
+[ɑ] → a;
+[ʼ \. ̯ ] → ;
+::NULL;
+aː → aa;
+eː → ee;
+iː → ii;
+oː → oo;
+uː → uu;
+ə̃ː → ə̃ə̃;
+hh+ → h;
+ː → ;
+::NULL;
+t͡sa → Ꮳ;
+t͡se → Ꮴ;
+t͡si → Ꮵ;
+t͡so → Ꮶ;
+t͡su → Ꮷ;
+t͡sə̃ → Ꮸ;
+t͡s → Ꮵ;
+t͡ɬa → Ꮭ;
+t͡ɬe → Ꮮ;
+t͡ɬi → Ꮯ;
+t͡ɬo → Ꮰ;
+t͡ɬu → Ꮱ;
+t͡ɬə̃ → Ꮲ;
+t͡ɬ → Ꮯ;
+d͡la → Ꮬ;
+d͡le → Ꮮ;
+d͡li → Ꮯ;
+d͡lo → Ꮰ;
+d͡lu → Ꮱ;
+d͡lə̃ → Ꮲ;
+d͡l → Ꮯ;
+ɬa → Ꮭ;
+ɬe → Ꮮ;
+ɬi → Ꮯ;
+ɬo → Ꮰ;
+ɬu → Ꮱ;
+ɬə̃ → Ꮲ;
+ɬ → Ꮯ;
+ma → Ꮉ;
+me → Ꮊ;
+mi → Ꮋ;
+mo → Ꮌ;
+mu → Ꮍ;
+mə̃ → Ᏽ;
+m → Ꮋ;
+nah → Ꮐ;
+na → Ꮎ;
+ne → Ꮑ;
+ni → Ꮒ;
+no → Ꮓ;
+nu → Ꮔ;
+nə̃ → Ꮕ;
+n → Ꮒ;
+ta → Ꮤ;
+te → Ꮦ;
+ti → Ꮨ;
+to → Ꮩ;
+tu → Ꮪ;
+tə̃ → Ꮫ;
+t → Ꮨ;
+da → Ꮣ;
+de → Ꮥ;
+di → Ꮧ;
+do → Ꮩ;
+du → Ꮪ;
+də̃ → Ꮫ;
+d → Ꮧ;
+[kɡ][wʷ]a → Ꮖ;
+[kɡ][wʷ]e → Ꮗ;
+[kɡ][wʷ]i → Ꮘ;
+[kɡ][wʷ]o → Ꮙ;
+[kɡ][wʷ]u → Ꮚ;
+[kɡ][wʷ]ə̃ → Ꮛ;
+[kɡ][wʷ] → Ꮘ;
+ɡa → Ꭶ;
+ka → Ꭷ;
+[kɡ]e → Ꭸ;
+[kɡ]i → Ꭹ;
+[kɡ]o → Ꭺ;
+[kɡ]u → Ꭻ;
+[kɡ]ə̃ → Ꭼ;
+[kɡ] → Ꭹ;
+sa → Ꮜ;
+se → Ꮞ;
+si → Ꮟ;
+so → Ꮠ;
+su → Ꮡ;
+sə̃ → Ꮢ;
+s → Ꮝ;
+ha → Ꭽ;
+he → Ꭾ;
+hi → Ꭿ;
+ho → Ꮀ;
+hu → Ꮁ;
+hə̃ → Ꮂ;
+hna → Ꮏ;
+h → Ꭿ;
+la → Ꮃ;
+le → Ꮄ;
+li → Ꮅ;
+lo → Ꮆ;
+lu → Ꮇ;
+lə̃ → Ꮈ;
+l → Ꮅ;
+wa → Ꮹ;
+we → Ꮺ;
+wi → Ꮻ;
+wo → Ꮼ;
+wu → Ꮽ;
+wə̃ → Ꮾ;
+w → Ꮻ;
+ja → Ꮿ;
+je → Ᏸ;
+ji → Ᏹ;
+jo → Ᏺ;
+ju → Ᏻ;
+jə̃ → Ᏼ;
+j → Ᏹ;
+a → Ꭰ;
+e → Ꭱ;
+i → Ꭲ;
+o → Ꭳ;
+u → Ꭴ;
+ə̃ → Ꭵ;
+˥˧ → ̂;
+˧˩ → ̀;
+˨˦ → ̌;
+˥ → ̋;
+˦ → ́;
+˧ → ̄;
+::NULL;
+[:Zs:]+ → ' ';
+[^[:sc=Cher:][ ̋ ́ ̄ ̀ ̂ ̌ ]] → ;
+::NFC;
+

package/transforms/und_FONIPA-fa.json

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

package/transforms/und_FONIPA-fa.txt

@@ -0,0 +1,109 @@
+
+# Vowels
+# ------
+# In these rules, we produce ی و ا both for short and for long vowels.
+# This would be wrong for writing Farsi or Arabic, but when transliterating
+# foreign words and names, it is strongly preferred to vowel marks.
+# Short schwa [ə] and a few other, schwa-like vowels get omitted entirely
+# unless at the end of the word, in which case we emit ه whose Farsi
+# word-final pronunciation comes close to [ə]. At the beginning of words,
+# Farsi speakers prefer to see آ for [ɑ] and a few other similar-sounding
+# dark vowels; note that this use of آ is quite different from Arabic.
+$IVowel = [i ɪ e {e̞}];
+$UVowel = [y {ɨ} {ʉ} ɯ u ʏ {ɪ̈} {ʊ̈} {ɯ̽} {ʊ} ø ɤ o {ø̞} {ɤ̞} {o̞} ɔ w {w̥} ʍ ʷ];
+$AVowel = [ɛ œ ɜ æ ɶ];
+$DarkAVowel = [ʌ a ɑ ɒ ɐ ɞ {ä} {ɒ̈}];  # آ instead of ا at beginning of words
+$SchwaVowel = [ɘ ɵ ə {ɵ̞}];
+$Click = [ʘ ɋ ǀ ʇ ǃ ʗ ǂ ʄ ǁ ʖ];
+$Boundary =  [^[:L:][:M:][:N:]];
+::NFD;
+[ʰ ʱ ʼ  ̃  ̰  ̋  ́  ̄  ̀  ̏  ̌  ̂ ˥ ˦ ˧ ˨ ˩ ꜜ ꜛ ↗ ↘  ͡  ͜  ̯] → ;
+ʲ → j;
+ᵐ → m;
+ⁿ → n;
+ᵑ → ŋ;
+::NFC;
+# TODO: Diphthongs probably need more work.
+# Romanian [sekujesk] → [sekujask], for emitting سیکویاسک not سیکویسک
+$UVowel [j $IVowel] [e {e̞} $SchwaVowel] → uia;
+# Kazakh Аягөз [ɑjɑɡy̯ʉz] → [ɑjɑɡiuz], to emit آیاگیوز not آیاگووز
+yʉ → iu;
+::NULL;
+# Vowels
+$Boundary {$SchwaVowel ː?} → ای;
+$SchwaVowel ː → ی;
+{[$SchwaVowel e {e̞}]} [^[:L:][:M:][:N:][\.]] → ه;
+$SchwaVowel → ;
+$Boundary {$IVowel ː?} → ای;
+$IVowel ː? j? → ی;
+$Boundary {$UVowel ː?} → او;
+$UVowel ː? → و;
+$Boundary {$AVowel ː?} → ا;
+$AVowel ː? → ا;
+$Boundary {$DarkAVowel ː?} → آ;
+$DarkAVowel ː? → ا;
+# Shadda for long (geminated) consonants
+ː → ّ;
+# Affricates
+[{t͡ʃ} ʧ] → چ;
+# Clicks
+[ɡ g ɠ k] $Click → کچ;
+[n ɲ]? $Click → نچ;
+# Nasal stops
+[{m̥} m ɱ] → م;
+[{n̼̊} {n̼} {n̥} n {ɳ̊} ɳ {ɲ̊} {ɲ̥} ɲ] → ن;
+[{ŋ̊} ŋ {ɴ̥} ɴ] k → نک;
+[{ŋ̊} ŋ {ɴ̥} ɴ] [ɡ g]? → نگ;
+# Non-nasal stops
+[p {p̪}] → پ;
+[b {b̪} ɓ] → ب;
+[{d̼} d ɗ ᶑ] → د;
+[{t̼} t] → ت;
+[ʈ] → ط;
+[ɖ] → ض;
+c → چ;
+ɟ → دج;
+k → ک;
+[ɡ g ɠ] → گ;
+[q ɢ ʡ ʛ] → ق;
+ʔ → ;
+# Sibilant fricatives
+s → س;
+z → ز;
+[ʃ ʂ ɕ ʄ] → ش;
+[ʒ ʐ ʑ] → ژ;
+# Non-sibilant fricatives
+[ɸ f] → ف;
+[β v] → و;
+[{θ̼} θ {θ̱}] → ث;
+[{ð̼} ð {ð̠}] → ذ;
+ç → ش;
+ʝ $IVowel? ː? → ی;
+[x χ] → خ;
+[ɣ ʁ] → غ;
+ħ → ح;
+ʕ → ع;
+[h ɦ {ʔ̞}] → ه;
+# Approximants, trills, flaps
+ʋ → و;
+ʙ → بر;
+{r̝} → رژ;
+[{ɹ̥} {ɹ} {ɻ̊} {ɻ} {ɾ̥} ɾ {ɽ̊} ɽ {r̼} {r̥} r] → ر;
+[{ʀ̥} ʀ] → غ;
+ʜ → ح;
+ʢ → ع;
+j $IVowel? ː? → ی;
+# Laterals
+ɬ → شل;
+ɮ → ژل;
+{[{ʎ̥} ʎ]} [^ $IVowel j ʝ] → لی;
+[{l̼} {l̥} l {ɭ̊} ɭ {ʎ̥} ʎ] → ل;
+[ʟ {ʟ̠}] → غ;
+# Independent pass for misc cleanup.
+::NULL;
+# Strip off syllable markers
+\. → ;
+# Sequences of three or more ووو look very confusing; we shorten them.
+# Polish Darłowo [darwɔvɔ] → داروو → داروووو
+ووو+ → وو;
+

package/transforms/uz_Cyrl-uz_Latn.json

@@ -0,0 +1,9 @@
+{
+  "_visibility": "external",
+  "_backwardAliasBcp47": "uz-Cyrl-t-uz-latn",
+  "_aliasBcp47": "uz-Latn-t-uz-cyrl",
+  "_source": "uz_Cyrl",
+  "_direction": "both",
+  "_target": "uz_Latn",
+  "_rulesFile": "uz_Cyrl-uz_Latn.txt"
+}

package/transforms/uz_Cyrl-uz_Latn.txt

@@ -0,0 +1,103 @@
+
+# Rules are predicated on running NFD first, and NFC afterwards
+:: NFD (NFC) ;
+$letters = [[:sc=Latn:][:sc=Cyrl:] & [:L:]] ;
+$latinVowel = [AEIOUaeiouĬĭʼËë{oʻ}{Oʻ}] ;
+$lower = [$letters & [:Ll:]] ;
+у \u0306 ↔ oʻ ;
+У \u0306 ↔ Oʻ ;
+ғ ↔ gʻ ;
+Ғ ↔ Gʻ ;
+# For many cases, use a following character to determine the difference between XY and Xy
+ш ↔ sh ;
+{ Ш } $lower ↔ Sh ;
+Ш ↔ SH ;
+ч ↔ ch ;
+{ Ч } $lower ↔ Ch ;
+Ч ↔ CH ;
+# нг ↔ ng ; as separate letters works
+# Нг ↔ Ng ; as separate letters works
+# If we have a lowercase letter on either side, use the lowercase hard sign
+ъ ↔ { ʼ } $lower ;
+ъ ← $lower { ʼ } ;
+Ъ ↔ ʼ ;
+е\u0308 ↔ yo ;
+Е\u0308 } $lower ↔ Yo ;
+Е\u0308 ↔ YO ;
+# е → 'ye' at the beginning of a syllable, after a vowel, ъ or ь, otherwise 'e'
+[:^L:] { е ↔ ye ;
+[:^L:] { Е } $lower ↔ Ye ;
+[:^L:] {Е ↔ YE ;
+$latinVowel { е → ye ;
+$latinVowel { Е } $lower → Ye ;
+$latinVowel { Е → YE ;
+# handle these specially, since ьЬ otherwise disappear.
+ье → ye ;
+{ ьЕ } $lower → Ye ;
+ьЕ → YE ;
+Ье → ye ;
+{ ЬЕ } $lower → Ye ;
+ЬЕ → YE ;
+е → e ;
+Е → E ;
+ю ↔ yu ;
+{ Ю } $lower ↔ Yu ;
+Ю ↔ YU ;
+я ↔ ya ;
+{ Я } $lower ↔ Ya ;
+Я ↔ YA ;
+ц ↔ ts ;
+{ Ц } $lower ↔ Ts ;
+Ц ↔ TS ;
+а ↔ a ;
+А ↔ A ;
+б ↔ b ;
+Б ↔ B ;
+д ↔ d ;
+Д ↔ D ;
+э ↔ e ;
+Э ↔ E ;
+ф ↔ f ;
+Ф ↔ F ;
+г ↔ g ;
+Г ↔ G ;
+ҳ ↔ h ;
+Ҳ ↔ H ;
+и\u0306 ↔ y ;
+И\u0306 ↔ Y ;
+и ↔ i ;
+И ↔ I ;
+ж ↔ j ;
+Ж ↔ J ;
+к ↔ k ;
+К ↔ K ;
+л ↔ l ;
+Л ↔ L ;
+м ↔ m ;
+М ↔ M ;
+н ↔ n ;
+Н ↔ N ;
+о ↔ o ;
+О ↔ O ;
+п ↔ p ;
+П ↔ P ;
+қ ↔ q ;
+Қ ↔ Q ;
+р ↔ r ;
+Р ↔ R ;
+с ↔ s ;
+С ↔ S ;
+т ↔ t ;
+Т ↔ T ;
+у ↔ u ;
+У ↔ U ;
+в ↔ v ;
+В ↔ V ;
+х ↔ x ;
+Х ↔ X ;
+з ↔ z ;
+З ↔ Z ;
+ь → ;
+Ь → ;
+::NFC (NFD) ;
+

package/transforms/vec-vec_FONIPA.json

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

package/transforms/vec-vec_FONIPA.txt

@@ -0,0 +1,85 @@
+
+# References
+# ----------
+# [1] Personal communication with Academia de ła Bona Creansa, Venice
+# [2] https://en.wikipedia.org/wiki/Venetian_language#Phonology
+# [3] https://en.wikipedia.org/wiki/Help:IPA/Venetian (mixed with Ladin)
+#
+# Output phonemes
+# ---------------
+#   m n ɲ ŋ
+#   p b t d k ɡ
+#   f v ɾ s z
+#   l ʎ j w
+#   t͡ʃ d͡ʒ d͡z
+#   i u e e̯ o ɛ ɔ a
+$boundary = [^[:L:][:M:][:N:]];
+$e = [e é è];
+$i = [i í ì];
+$ei = [$e $i];
+$vowel = [a á à $ei o ó ò u ú ù];
+$onset = [
+j w m n ɲ ŋ p b t d k ɡ f v ɾ s z h l ʎ {e̯}
+{t͡ʃ} {d͡ʒ} {d͡z} {mj} {mw} {nj} {nw}
+{ps} {pɾ} {pɾw} {pl} {pj} {pw} {bɾ} {bɾw} {bw} {bj} {bl}
+{ts} {tɾ} {tɾw} {tl} {tj} {tw} {dɾ} {dɾw} {dw} {dj} {dl}
+{kɾ} {kw} {kɾw} {kl} {kj} {kw} {ɡɾ} {ɡɾw} {ɡw} {ɡj} {ɡl}
+{fɾ} {fj} {fl} {fw} {fɾw} {vɾ} {vj} {vw} {ɾw} {ɾj}
+{zm} {zn} {zɲ} {zj} {zl} {zb} {zbɾ} {zbj} {zbw} {zd} {zdɾ} {zdj} {zdw}
+{zɡ} {zɡɾ} {zɡj} {zɡw} {zv} {zvɾ} {zɾ} {zvj} {zd͡ʒ} {zw}
+{sp} {spɾ} {spw} {st} {stɾ} {stw} {sk} {skɾ} {skw}
+{sf} {sfɾ} {sɾ} {st͡ʃ} {sj} {sw} {lj} {lw}
+];
+::Lower;
+::NFC;
+([abefjklmoptvw]) → $1;
+[á à] → ˈa;
+{c [$ei \' ’]} $vowel → t͡ʃ;
+cé [\' ’]? → t͡ʃˈe;
+cè [\' ’]? → t͡ʃˈɛ;
+c e [\' ’]? → t͡ʃe;
+c [íì] [\' ’]? → t͡ʃˈi;
+c i [\' ’]? → t͡ʃi;
+[c {ch} k q {qu}] → k;
+é → ˈe;
+è → ˈɛ;
+{g l $ei} $vowel → ʎ;
+g l → ʎ;
+ġ → d͡ʒ;
+gé [\' ’]? → d͡ʒˈe;
+gè [\' ’]? → d͡ʒˈɛ;
+g [íì] [\' ’]? → d͡ʒˈi;
+{g [$ei \' ’]} $vowel → d͡ʒ;
+{g} $ei → d͡ʒ;
+gn → ɲ;
+[g {gh}] → ɡ;
+[í ì] → ˈi;
+{i} $vowel → j;
+ł → ɰ;
+ṅ → ŋ;
+ñ → ɲ;
+nj → ɲ;
+ó → ˈo;
+ò → ˈɔ;
+r → ɾ;
+[ṡ x z] → z;
+{s}[bdg] → z;
+s → s;
+{u} $vowel → w;
+[ú ù] → ˈu;
+u → u;
+y → j;
+[ż đ {dh}] → d͡z;
+d → d;
+[[:P:][:Z:]]+ → ' ';
+::NULL;
+{n} [p b t d k ɡ f v ɾ s z $boundary] → ŋ;
+{ɰ} ˈ? [ei] → ;
+eɰ → e;
+iɰ → i;
+ɰ → e̯;
+::NULL;
+# Move stress marker before syllable onset: [zɡɾaŋfiɲˈae] → [zɡɾaŋfiˈɲae]
+($onset) ˈ → ˈ $1;
+::NULL;
+

package/transforms/xh-am.json

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

package/transforms/xh-am.txt

@@ -0,0 +1,4 @@
+
+::xh-xh_FONIPA;
+::am_FONIPA-am;
+

package/transforms/xh-ar.json

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

package/transforms/xh-ar.txt

@@ -0,0 +1,4 @@
+
+::xh-xh_FONIPA;
+::und_FONIPA-ar;
+

package/transforms/xh-chr.json

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

package/transforms/xh-chr.txt

@@ -0,0 +1,4 @@
+
+::xh-xh_FONIPA;
+::und_FONIPA-chr;
+