cldr-transforms 46.0.0-BETA2

package/transforms/es-es_FONIPA.txt

@@ -0,0 +1,139 @@
+
+# Transformation from Spanish to Spanish in IPA transcription (es_FONIPA).
+# Not fully phonemic, since we mark up allophonic variants of voiced stops,
+# e.g. we break down /b/ into [b] and [β].
+#
+# See e.g. "Ortografía de la lengua española" by Real Academia Española,
+# available in PDF format on the web (non-stable URL).
+#
+# Definitions.
+$bow = [-\ $] ;  # Beginning of word.
+$consonant = [bβdðfgɣʝklʎmnŋɲθprɾstʧx] ;
+$syll = '.' ;    # Syllable boundary.
+#
+#
+#
+#
+::NFC;
+::Lower;
+#
+#
+#
+#
+#
+# Word-initial cluster simplification.
+#
+$bow { ct → | t ;  # ctónico (?)
+$bow { cz → | z ;  # czar
+$bow { gn → | n ;  # gnomo
+$bow { mn → | n ;  # mnemotécnico
+$bow { ps → | s ;  # psicología
+$bow { pt → | t ;  # pterodáctilo
+$bow { x  → | s ;  # xilófono
+#
+#
+#
+# Vowels and glides.
+#
+$bow       { i                 → i ;
+$consonant { i } [ aáeé  oóuú] → j ;
+[aeo]      { i } [^aáeé  oóuú] → i̯ ;
+i } [ aáeé  oóuú] → ʝ ;
+i                 → i ;
+#
+#
+[aeo]      { y } [^aáeéiíoóuú] → i̯ ;
+y } [ aáeéiíoóuú] → ʝ ;
+y                 → i ;
+#
+#
+[aeo]      { u } [^aáeéiíoó  ] → u̯ ;
+u } [ aáeéiíoó  ] → w ;
+ü } [   eéií    ] → w ;
+u                 → u ;
+ü                 → u ;  # Should not be needed, but just in case.
+#
+#
+[aá] → a ;
+[eé] → e ;
+í    → i ;
+[oó] → o ;
+ú    → u ;
+#
+#
+#
+# Consonants.
+#
+b → β ;
+cch → ʧ ;
+ch → ʧ ;
+cc } [^eéií] → k ;
+c } [eéií] → θ ;
+c → k ;
+d → ð ;
+f → f;
+gu } [eéiíy] → ɣ ;
+g } [eéiíy] → x ;
+g → ɣ ;
+hi } [aáeéoóuú] → ʝ ;
+h → $syll ;
+j → x ;
+k → k ;
+ll → ʎ ;
+l → l ;
+m → m ;
+n → n ;
+ñ → ɲ ;
+p → p ;
+qu } [eéiíy] → k ;
+q → k ;
+[-\ lns$] { r → r ;
+rr → r ;
+r → ɾ ;
+ss → s ;
+s → s ;
+tx → ʧ ;  # for loanwords from Basque, Catalan
+t → t ;
+v → β ;
+w → $syll w ;
+x } h?[aáeéiíoóuú$] → ks ;
+x } [^aáeéiíoóuú$] → s ;
+x → ks ;
+z → θ ;
+#
+#
+#
+# Second pass: phoneme-to-phone rules. Differentiation of /β/ into [b] and [β],
+# place assimilation of [n], etc.
+#
+::Null;
+#
+#
+[-\ ] → ;
+#
+#
+[mnɲŋ  $] { β → b ;
+[mnɲŋlʎ$] { ð → d ;
+[mnɲŋ  $] { ɣ → g ;
+#
+#
+n } [gɣk] → ŋ ;
+#
+#
+# Optional: Place assimilation of n before labial consonants.
+#
+# n } [bβpfm] → m ;
+#
+# Optional: Voicing of [s].
+#
+# s } [bβdð] → z ;
+# s } [gɣ][^ei] → z ;
+# s } [mnɲŋlʎrɾ] → z ;
+#
+# Optional: Lenition of [k] before [θ].
+#
+# k } θ → ɣ ;
+#
+#
+::NFC;
+

package/transforms/es-fa.json

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

package/transforms/es-fa.txt

@@ -0,0 +1,13 @@
+
+$Boundary =  [^[:L:][:M:][:N:]];
+$Vowel = [i e o u a];
+::es-es_FONIPA;
+# In Farsi transcription of Spanish, un-stressed [e] should be treated
+# like [ə] which gets stripped off.  However, we currently do have not
+# have a good way of finding stress in Spanish words.  In the long term,
+# it would be _much_ better to look at stress markers, but for now
+# we do this trivial heuristics to find unstressed [e] in the first
+# syllable.
+$Boundary [^$Vowel] {e} [^$Vowel]* $Vowel → ə;
+::und_FONIPA-fa;
+

package/transforms/es-ja.json

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

package/transforms/es-ja.txt

@@ -0,0 +1,4 @@
+
+::es-es_FONIPA;
+::es_FONIPA-ja;
+

package/transforms/es-zh.json

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

package/transforms/es-zh.txt

@@ -0,0 +1,4 @@
+
+::es-es_FONIPA;
+::es_FONIPA-zh;
+

package/transforms/es_419-am.json

@@ -0,0 +1,8 @@
+{
+  "_visibility": "external",
+  "_aliasBcp47": "am-t-es-419",
+  "_source": "es_419",
+  "_direction": "forward",
+  "_target": "am",
+  "_rulesFile": "es_419-am.txt"
+}

package/transforms/es_419-am.txt

@@ -0,0 +1,5 @@
+
+::es-es_FONIPA;
+::es_FONIPA-es_419_FONIPA;
+::am_FONIPA-am;
+

package/transforms/es_419-ar.json

@@ -0,0 +1,8 @@
+{
+  "_visibility": "external",
+  "_aliasBcp47": "ar-t-es-419",
+  "_source": "es_419",
+  "_direction": "forward",
+  "_target": "ar",
+  "_rulesFile": "es_419-ar.txt"
+}

package/transforms/es_419-ar.txt

@@ -0,0 +1,14 @@
+
+$Boundary =  [^[:L:][:M:][:N:]];
+$Vowel = [i e o u a];
+::es-es_FONIPA;
+::es_FONIPA-es_419_FONIPA;
+# In Arabic transcription of Spanish, un-stressed [e] should be treated
+# like [ə] which gets stripped off.  However, we currently do have not
+# have a good way of finding stress in Spanish words.  In the long term,
+# it would be _much_ better to look at stress markers, but for now
+# we do this trivial heuristics to find unstressed [e] in the first
+# syllable.
+$Boundary [^Vowel] {e} [^$Vowel]* $Vowel → ə;
+::und_FONIPA-ar;
+

package/transforms/es_419-chr.json

@@ -0,0 +1,8 @@
+{
+  "_visibility": "external",
+  "_aliasBcp47": "chr-t-es-419",
+  "_source": "es_419",
+  "_direction": "forward",
+  "_target": "chr",
+  "_rulesFile": "es_419-chr.txt"
+}

package/transforms/es_419-chr.txt

@@ -0,0 +1,5 @@
+
+::es-es_FONIPA;
+::es_FONIPA-es_419_FONIPA;
+::und_FONIPA-chr;
+

package/transforms/es_419-fa.json

@@ -0,0 +1,8 @@
+{
+  "_visibility": "external",
+  "_aliasBcp47": "fa-t-es-419",
+  "_source": "es_419",
+  "_direction": "forward",
+  "_target": "fa",
+  "_rulesFile": "es_419-fa.txt"
+}

package/transforms/es_419-fa.txt

@@ -0,0 +1,14 @@
+
+$Boundary =  [^[:L:][:M:][:N:]];
+$Vowel = [i e o u a];
+::es-es_FONIPA;
+::es_FONIPA-es_419_FONIPA;
+# In Farsi transcription of Spanish, un-stressed [e] should be treated
+# like [ə] which gets stripped off.  However, we currently do have not
+# have a good way of finding stress in Spanish words.  In the long term,
+# it would be _much_ better to look at stress markers, but for now
+# we do this trivial heuristics to find unstressed [e] in the first
+# syllable.
+$Boundary [^Vowel] {e} [^$Vowel]* $Vowel → ə;
+::und_FONIPA-fa;
+

package/transforms/es_419-ja.json

@@ -0,0 +1,8 @@
+{
+  "_visibility": "external",
+  "_aliasBcp47": "ja-t-es-419",
+  "_source": "es_419",
+  "_direction": "forward",
+  "_target": "ja",
+  "_rulesFile": "es_419-ja.txt"
+}

package/transforms/es_419-ja.txt

@@ -0,0 +1,5 @@
+
+::es-es_FONIPA;
+::es_FONIPA-es_419_FONIPA;
+::es_FONIPA-ja;
+

package/transforms/es_419-zh.json

@@ -0,0 +1,8 @@
+{
+  "_visibility": "external",
+  "_aliasBcp47": "zh-t-es-419",
+  "_source": "es_419",
+  "_direction": "forward",
+  "_target": "zh",
+  "_rulesFile": "es_419-zh.txt"
+}

package/transforms/es_419-zh.txt

@@ -0,0 +1,5 @@
+
+::es-es_FONIPA;
+::es_FONIPA-es_419_FONIPA;
+::es_FONIPA-zh;
+

package/transforms/es_FONIPA-am.json

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

package/transforms/es_FONIPA-am.txt

@@ -0,0 +1,230 @@
+
+# Phonemic transcription of Spanish into Amharic.
+# First pass: Collapse phonetic distinctions not preserved in Amharic.
+β → b;
+ð → d;
+ɣ → g;
+ʎ → ʝ;
+#
+#
+ŋ → n;
+θ → s;
+ɾ → r;
+#
+#
+i̯ → i;
+u̯ → u;
+#
+#
+j → i;
+[^gk] { w → u;
+#
+#
+# Main pass: Phoneme to Katakana conversion.
+::Null;
+#
+#
+'.' → ;
+#
+#
+# Degemination.
+bb → | b;
+dd → | d;
+ff → | f;
+gg → | g;
+ʝʝ → | ʝ;
+kk → | k;
+ll → | l;
+mm → | m;
+nn → | n;
+ɲɲ → | ɲ;
+pp → | p;
+rr → | r;
+ss → | s;
+ʃʃ → | ʃ;
+tt → | t;
+ʧʧ → | ʧ;
+xx → | x;
+ʒʒ → | ʒ;
+#
+#
+a → አ ;
+#
+#
+ba → ባ ;
+be → ቤ ;
+bi → ቢ ;
+bo → ቦ ;
+bu → ቡ ;
+b → ብ ;
+#
+#
+da → ዳ ;
+de → ዴ ;
+di → ዲ ;
+do → ዶ ;
+du → ዱ ;
+d → ድ ;
+#
+#
+e → ኤ ;
+#
+#
+fa → ፋ ;
+fe → ፌ ;
+fi → ፊ ;
+fo → ፎ ;
+fu → ፉ ;
+f → ፍ ;
+#
+#
+ga → ጋ ;
+ge → ጌ ;
+gi → ጊ ;
+go → ጎ ;
+gu → ጉ ;
+gwa → ጓ ;
+gwe → ጔ ;
+gwi → ጒ ;
+gwo → ጉዎ ;
+g → ግ ;
+#
+#
+i → ኢ ;
+#
+#
+ʝa → ያ ;
+ʝe → ዬ ;
+ʝi → ዪ ;
+ʝo → ዮ ;
+ʝu → ዩ ;
+ʝ → ይ ;
+#
+#
+ka → ካ ;
+ke → ኬ ;
+ki → ኪ ;
+ko → ኮ ;
+ku → ኩ ;
+kwa → ኳ ;
+kwe → ኴ ;
+kwi → ኲ ;
+kwo → ኩዎ ;
+k → ክ ;
+#
+#
+la → ላ ;
+le → ሌ ;
+li → ሊ ;
+lo → ሎ ;
+lu → ሉ ;
+l → ል ;
+#
+#
+ma → ማ ;
+me → ሜ ;
+mi → ሚ ;
+mo → ሞ ;
+mu → ሙ ;
+m → ም ;
+#
+#
+na → ና ;
+ne → ኔ ;
+ni → ኒ ;
+no → ኖ ;
+nu → ኑ ;
+n → ን ;
+#
+#
+ɲa → ኛ ;
+ɲe → ኜ ;
+ɲi → ኚ ;
+ɲo → ኞ ;
+ɲu → ኙ ;
+ɲ → ኝ ;
+#
+#
+o → ኦ ;
+#
+#
+pa → ፓ ;
+pe → ፔ ;
+pi → ፒ ;
+po → ፖ ;
+pu → ፑ ;
+p → ፕ ;
+#
+#
+ra → ራ ;
+re → ሬ ;
+ri → ሪ ;
+ro → ሮ ;
+ru → ሩ ;
+r → ር ;
+#
+#
+sa → ሳ ;
+se → ሴ ;
+si → ሲ ;
+so → ሶ ;
+su → ሱ ;
+s → ስ ;
+#
+#
+# Not used in Iberian Spanish, but occurs e.g. in Galician.
+ʃa → ሻ ;
+ʃe → ሼ ;
+ʃi → ሺ ;
+ʃo → ሾ ;
+ʃu → ሹ ;
+ʃ → ሽ ;
+#
+#
+ta → ታ ;
+te → ቴ ;
+ti → ቲ ;
+to → ቶ ;
+tu → ቱ ;
+t → ት ;
+#
+#
+ʧa → ቻ ;
+ʧe → ቼ ;
+ʧi → ቺ ;
+ʧo → ቾ ;
+ʧu → ቹ ;
+ʧ → ች ;
+#
+#
+u → ኡ ;
+#
+#
+# Not strictly used in Spanish, but needed for Amharic.
+va → ቫ ;
+ve → ቬ ;
+vi → ቪ ;
+vo → ቮ ;
+vu → ቩ ;
+v → ቭ ;
+#
+#
+xa → ኻ ;
+xe → ኼ ;
+xi → ኺ ;
+xo → ኾ ;
+xu → ኹ ;
+x → ኽ ;
+#
+#
+# Not used in Iberian Spanish, but occurs in e.g. Catalan.
+ʒa → ዣ ;
+ʒe → ዤ ;
+ʒi → ዢ ;
+ʒo → ዦ ;
+ʒu → ዡ ;
+ʒ → ዥ ;
+#
+#
+::NFC;
+

package/transforms/es_FONIPA-es_419_FONIPA.json

@@ -0,0 +1,8 @@
+{
+  "_visibility": "external",
+  "_aliasBcp47": "es-419-fonipa-t-es-fonipa",
+  "_source": "es_FONIPA",
+  "_direction": "forward",
+  "_target": "es_419_FONIPA",
+  "_rulesFile": "es_FONIPA-es_419_FONIPA.txt"
+}

package/transforms/es_FONIPA-es_419_FONIPA.txt

@@ -0,0 +1,6 @@
+
+# Conflate sounds of Castilian Spanish to produce Latin American Spanish.
+# This operates on a phonemic IPA transcription of Spanish (es_FONIPA).
+ʎ → ʝ;
+[sθ]+ → s;
+

package/transforms/es_FONIPA-ja.json

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