cldr-transforms 46.0.0-BETA2

package/transforms/cs_FONIPA-ko.txt

@@ -0,0 +1,88 @@
+
+# Transliteration of Phonemic Czech (cs_FONIPA) to Korean (ko).
+#
+# First pass: Phonemic Czech (cs_FONIPA) to Latinized Korean (ko_Latn).
+$vowel = [aeɛiɪoux];
+$start = [\u0020$];
+$end = [\u0020$];
+b } $end   → peu ;
+b } $vowel → b ;
+bj } $vowel → b ;  # objɛc → obeti
+b          → beu ;
+c } $end   → ti ;
+c          → t ;
+d͡z         → deuj ;
+d } $end   → teu ;
+d } $vowel → d ;
+d          → deu ;
+ɛ          → e ;
+f } $vowel → p ;
+f          → peu ;
+ɡ } $vowel → g ;
+ɡ          → geu ;
+ɦ } $vowel → h ;
+ɦ          → heu ;
+h } $vowel → h ;
+h          → heu ;
+i          → i ;
+ɪ          → i ;
+j } $end   → i ;  # pokoj → pokoi
+j          → y ;
+kvu        → keub ;  # kvuasɪ → keubasi
+ks } $end  → gseu ;  # ksɛroks → jelogseu
+$start { ks → j ;  # ksɛroks → jelogseu
+ks         → gs ;  # saksofoːn → sagsopon
+k } $vowel → k ;
+k          → keu ;
+$vowel { l } $vowel → ll ;
+lz         → lj ;
+m } $end   → m ;
+m } $vowel → m ;
+m } [l]    → m ;
+m          → meu ;
+ɲ          → n ;
+ŋ          → n ;
+p } $vowel → p ;
+p } t      → b ;  # koroptɛv
+p          → peu ;
+r̝ } $end   → leusi ; # kour̝ → kouleusi
+r̝ } $vowel → leuj ;
+r̝ } k      → leusyu ;  # ɦor̝kiː → holeusyuki
+r̝          → leuju ;
+r } $vowel → l ;
+r          → leu ;
+s } $vowel → s ;
+s          → seu ;
+ʃ } $end   → si ;
+ʃ } $vowel → sy ;
+ʃ          → syu ;
+t͡s} $vowel → ch ;
+t͡s         → cheu ;
+t͡ʃ} $vowel → ch ;
+t͡ʃ         → chi ;
+t } $vowel → t ;
+t          → teu ;
+vj         → b ;    # ʒvjɛr̝ɪna → jubeleujina
+v } $end   → peu ;
+v } $vowel → b ;
+v          → beu ;
+x } $vowel → h ;
+x          → heu ;
+ɣ } $vowel → h ;
+ɣ          → heu ;
+z } $vowel → j ;    # zaːmɛk → jamekeu
+z } $end   → seu ;  # ɦmɪz → heumiseu
+z          → jeu ;  # pozdniː → pojeudeuni
+ʒ } $vowel → j ;    # ʒɪʒka → jisyuka (first ʒ)
+ʒ } v      → ju ;   # ʒvjɛr̝ɪna → jubeleujina
+ʒ } $end   → si ;   # broʒ → beulosi
+ʒ          → syu ;  # ʒɪʒka → jisyuka (second ʒ)
+ɟ } $vowel → dy ;
+ɟ          → ti ;
+ː          → ;
+\u0020     → ;  # space
+#
+#
+# Second pass.
+:: Latin-Hangul ();
+

package/transforms/cy-fonipa-t-cy.json

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

package/transforms/cy-fonipa-t-cy.txt

@@ -0,0 +1,189 @@
+
+# Transformation from Welsh (cy) to its IPA transcription (cy_FONIPA).
+# Based on description of Northern Welsh in:
+#
+# http://en.wikipedia.org/wiki/Welsh_orthography
+# http://en.wikipedia.org/wiki/Welsh_phonology
+#
+# Note that these rules are NOT complete: to be complete we would have to know
+# the morphological analysis of the word. For example, final ‹au› is pronounced
+# /a/ if it is the noun plural marker, otherwise it is /aɨ/. Similarly in
+# “llongyfarch” (‘congratulating’), the morphological decomposition — “llon +
+# cyfarch” — is needed to know that the ‹ng› is pronounced as /ŋg/, not as
+# /ŋ/.
+#
+# Author: Richard Sproat
+::Lower;
+::NFC;
+[’ [:P:]] → ;
+# Class definitions
+$end = [$ ];
+# Both orthographic and phonetic vowels
+$vowel = [aeiouwyâêîôûŵŷɑɨəɛɪɔʊ];
+# W is a placeholder for the glide -- see below
+$cons = [
+m {m̥} n {n̥} ŋ {ŋ̊}
+p b t d k ɡ
+f v θ ð s ʃ h χ
+l ɬ r {r̥}
+{d͡ʒ} g W w j
+];
+# Preprocessing of letters that sometimes occur
+k → c;
+v → f;
+x → s;
+z → s;
+::Null;
+# Consonant transductions:
+# Trigraphs
+ngh → ŋ̊;
+# Digraphs
+ch → χ;
+dd → ð;
+ff → f;
+ll → ɬ;
+mh → m̥;
+nh → n̥;
+ng → ŋ;
+ph → f;
+rh → r̥;
+th → θ;
+# Monographs
+b → b;
+c → k;
+d → d;
+f → v;
+g → ɡ;
+h → h;
+j → d͡ʒ;   # Loan words
+l → l;
+m → m;
+n → n;
+p → p;
+r → r;
+s → s;
+t → t;
+::Null;
+# Transduce ‹si› to /ʃ/ before vowels
+si} $vowel → ʃ;
+::Null;
+# Treatment of glides.
+# First transduce ‹i›, ‹w› to glides prior to vowels. With ‹w› we want to
+# do this also before /r,l/ after /ɡ/ (from Proto-Celtic *w) e.g. “gwlad”,
+# “gwraig”. However the “after g” environment must allow for the following
+# possibilities:
+#
+# ɡ → ŋ via nasal mutation
+# ɡ → 0 via soft mutation
+{i} $vowel → j;
+{w} $vowel → W; # Temporary register
+[ɡŋ] {w} [rl] $vowel → W;   # Plain or nasal mutation environment
+^ {w} [rl] $vowel → W;      # Soft mutation at the beginning of a word
+# Transduce accented ‹ẃ› to ‹w›: this is used to indicate when a ‹w› that would
+# normally be expected to be a glide, is instead a vowel:
+ẃ → w;
+::Null;
+# Stress placement, needed for vowel quality/quantity prediction
+# Basic rule of stress in Welsh is to place it on the penult,
+# except of course in monosyllables.
+{($vowel+ $cons+ $vowel+ $cons*)} $end → ˈ $1;  ## Polysyllabic words
+$end $cons* {($vowel+ $cons*)} $end → ˈ $1;     ## Monosyllabic words
+::Null;
+# Transduction of vowels
+# The first rule above overgenerates streams of stress marks. The rule below
+# cleans that up.
+ˈ+ → ˈ;
+# Diphthongs
+# Deal with ‹y› first since we also need to lengthen the /ɨ/ if that is in the
+# correct environment for lengthening.
+# ‹y› is /ɨ/ in final syllable, otherwise /ə/
+yw } $cons* $end → ɨu;
+yw → əu;
+y} $cons* $end → ɨ;
+y → ə;
+::Null;
+# Diphthongs in long environment
+# Final, or before word-final s
+ˈ { ɨu } s? $end → ɨːu;
+ˈ { aw } s? $end → ɑːu;
+ˈ { ew } s? $end → eːu;
+ˈ { oe } s? $end → ɔːɨ;
+ˈ { ou } s? $end → ɔːɨ;
+ˈ { wy } s? $end → uːɨ;
+# before b, ch, d, dd, g, f, ff, th followed by the end of a word
+# or a vowel
+ˈ { ɨu } [bχdðɡvfθ] $end → ɨːu;
+ˈ { aw } [bχdðɡvfθ] $end → ɑːu;
+ˈ { ew } [bχdðɡvfθ] $end → eːu;
+ˈ { oe } [bχdðɡvfθ] $end → ɔːɨ;
+ˈ { ou } [bχdðɡvfθ] $end → ɔːɨ;
+ˈ { wy } [bχdðɡvfθ] $end → uːɨ;
+ˈ { ɨu } [bχdðɡvfθ] $vowel → ɨːu;
+ˈ { aw } [bχdðɡvfθ] $vowel → ɑːu;
+ˈ { ew } [bχdðɡvfθ] $vowel → eːu;
+ˈ { oe } [bχdðɡvfθ] $vowel → ɔːɨ;
+ˈ { ou } [bχdðɡvfθ] $vowel → ɔːɨ;
+ˈ { wy } [bχdðɡvfθ] $vowel → uːɨ;
+# Diphthongs in other environments
+ae → ɑːɨ;
+ai → ai;
+au → aɨ; ## As plural ending /a/, but we can't predict this
+aw → au;
+ei → əi;
+eu → əɨ;
+ew → ɛu;
+ey → əɨ;
+iw → ɪu;
+oe → ɔɨ;
+oi → ɔi;
+ou → ɔɨ;
+uw → ɨu;
+wy → ʊɨ;
+# Long environments
+# Final, or before word-final s
+ˈ { ɨ } s? $end → ɨː;
+ˈ { a } s? $end → ɑː;
+ˈ { e } s? $end → eː;
+ˈ { i } s? $end → iː;
+ˈ { o } s? $end → oː;
+ˈ { u } s? $end → ɨː;
+ˈ { w } s? $end → uː;
+# before b, ch, d, dd, g, f, ff, th followed by the end of a word
+# or a vowel
+ˈ { ɨ } [bχdðɡvfθ] $end → ɨː;
+ˈ { a } [bχdðɡvfθ] $end → ɑː;
+ˈ { e } [bχdðɡvfθ] $end → eː;
+ˈ { i } [bχdðɡvfθ] $end → iː;
+ˈ { o } [bχdðɡvfθ] $end → oː;
+ˈ { u } [bχdðɡvfθ] $end → ɨː;
+ˈ { w } [bχdðɡvfθ] $end → uː;
+ˈ { ɨ } [bχdðɡvfθ] $vowel → ɨː;
+ˈ { a } [bχdðɡvfθ] $vowel → ɑː;
+ˈ { e } [bχdðɡvfθ] $vowel → eː;
+ˈ { i } [bχdðɡvfθ] $vowel → iː;
+ˈ { o } [bχdðɡvfθ] $vowel → oː;
+ˈ { u } [bχdðɡvfθ] $vowel → ɨː;
+ˈ { w } [bχdðɡvfθ] $vowel → uː;
+# Short environments
+a → a;
+e → ɛ;
+i → ɪ;
+o → ɔ;
+u → ɨ̞;
+w → ʊ;
+::Null;
+W → w;
+# Finally, deal with vowels that are marked as long with a circumflex
+# (“to bach”). Do this last because we don't want the other vowel
+# changes messing this up.
+â → ɑː;
+ê → eː;
+î → iː;
+ô → oː;
+û → ɨː;
+ŵ → uː;
+ŷ → ɨː;
+::Null;
+# Move IPA stress marker to start of syllable.
+([$cons w] [l ɬ r {r̥}]? j? w?) ˈ → ˈ $1;
+

package/transforms/de-ASCII.json

@@ -0,0 +1,8 @@
+{
+  "_visibility": "external",
+  "_aliasBcp47": "de-t-de-d0-ascii",
+  "_source": "de",
+  "_direction": "forward",
+  "_target": "ASCII",
+  "_rulesFile": "de-ASCII.txt"
+}

package/transforms/de-ASCII.txt

@@ -0,0 +1,15 @@
+
+$AE = [Ä {A \u0308}];
+$OE = [Ö {O \u0308}];
+$UE = [Ü {U \u0308}];
+[ä {a \u0308}] → ae;
+[ö {o \u0308}] → oe;
+[ü {u \u0308}] → ue;
+{$AE} [:Lowercase:] → Ae;
+{$OE} [:Lowercase:] → Oe;
+{$UE} [:Lowercase:] → Ue;
+$AE → AE;
+$OE → OE;
+$UE → UE;
+::Any-ASCII;
+

package/transforms/dsb-dsb_FONIPA.json

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

package/transforms/dsb-dsb_FONIPA.txt

@@ -0,0 +1,67 @@
+
+# Transforms Lower Sorbian (dsb) to its IPA transcription (dsb_FONIPA).
+# http://en.wikipedia.org/wiki/Sorbian_alphabet
+# Transform input to normalized form NFC, and to lowercase.
+::NFC;
+::Lower;
+a → a ;
+b́ → bʲ ; # old spelling
+bj → bʲ ; # modern spelling
+b → b ;
+ch → x ;
+č → t \u0361 ʃ ; # affricate indicated by ligature tie
+ć → t \u0361 ɕ ; # affricate indicated by ligature tie
+c → t \u0361 s ; # affricate indicated by ligature tie
+dź → d \u0361 ʑ ; # affricate indicated by ligature tie
+d → d ;
+ě → iɪ̯;
+e → ɛ ;
+f → f ;
+g → ɡ ;
+h → h ;
+i → i ;
+j → j ;
+k → k ;
+ł → v ;
+l → l ;
+ḿ → mʲ ; # old spelling
+mj → mʲ ; # modern spelling
+m → m ;
+ń → ɲ ;
+n → n ;
+ó → ɛ ;
+o → ɔ ;
+ṕ → pʲ ; # old spelling
+pj → pʲ ; # modern spelling
+p → p ;
+ř → ʃ ;
+ŕ → rʲ ;
+r → r ;
+š → ʃ ;
+ś → ɕ ;
+s → s ;
+t → t ;
+u → u ;
+ẃ → wʲ ; # old spelling
+wj → wʲ ; # modern spelling
+w → w ;
+y → ɨ ;
+ž → ʒ ;
+ź → ʑ ;
+z → z ;
+::NFC;
+# Assimilation.
+b } [k] → p ;
+d } [k] → t ;
+ʃt͡ɕ → ɕt͡ɕ ;
+# Final de-voicing.
+b } [$] → p ;
+d \u0361 z } [$] → t \u0361 s ;
+d } [$] → t ;
+ɡ } [$] → k ;
+v } [$] → f ;
+w } [$] → f ;
+ʑ } [$] → ɕ ;
+z } [$] → s ;
+ʒ } [$] → ʃ ;
+

package/transforms/el-Lower.json

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

package/transforms/el-Lower.txt

@@ -0,0 +1,12 @@
+
+# Special case for final form of sigma.
+::NFD();
+# C is preceded by a sequence consisting of a cased letter and then zero or more case-ignorable characters,
+# and C is not followed by a sequence consisting of zero or more case-ignorable characters and then a cased letter.
+# 03A3; 03C2; 03A3; 03A3; Final_Sigma; # GREEK CAPITAL LETTER SIGMA
+# With translit rules, easiest is to handle the negative condition first, mapping in that case to the regular sigma.
+Σ } [:case-ignorable:]* [:cased:] → σ;
+[:cased:] [:case-ignorable:]* { Σ → ς;
+::Any-Lower;
+::NFC();
+

package/transforms/el-Title.json

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

package/transforms/el-Title.txt

@@ -0,0 +1,12 @@
+
+::NFD();
+# Remove \0301 following Greek, with possible intervening 0308 marks.
+# [[:Greek:] & [:Ll:]] [\u0308]? { \u0301 → ;
+# Make any string of letters after a cased letter be lower, with rules for sigma
+[:cased:] [:case-ignorable:]* { Σ } [:case-ignorable:]* [:cased:] → σ;
+[:cased:] [:case-ignorable:]* { Σ → ς;
+[:cased:] [:case-ignorable:]* { (.) → &Any-Lower($1) ;
+# Otherwise all lowercase go to upper (titlecase stay as is)
+([:Lowercase:]) → &Any-Title($1) ;
+::NFC();
+

package/transforms/el-Upper.json

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

package/transforms/el-Upper.txt

@@ -0,0 +1,11 @@
+
+# Copyright (C) 2011-2013, Apple Inc. and others. All Rights Reserved.
+# Remove \0301 following Greek, with possible intervening 0308 marks.
+::NFD();
+# For uppercasing (not titlecasing!) remove all greek accents from greek letters.
+# This is done in two groups, to account for canonical ordering.
+[:Greek:] [^[:ccc=Not_Reordered:][:ccc=Above:]]*? { [\u0313\u0314\u0301\u0300\u0306\u0342\u0308\u0304] → ;
+[:Greek:] [^[:ccc=Not_Reordered:][:ccc=Iota_Subscript:]]*? { \u0345 → ;
+::NFC();
+::Any-Upper();
+

package/transforms/eo-am.json

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

package/transforms/eo-am.txt

@@ -0,0 +1,4 @@
+
+::eo-eo_FONIPA;
+::am_FONIPA-am;
+

package/transforms/eo-ar.json

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

package/transforms/eo-ar.txt

@@ -0,0 +1,4 @@
+
+::eo-eo_FONIPA;
+::und_FONIPA-ar;
+

package/transforms/eo-chr.json

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

package/transforms/eo-chr.txt

@@ -0,0 +1,4 @@
+
+::eo-eo_FONIPA;
+::und_FONIPA-chr;
+

package/transforms/eo-eo_FONIPA.json

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

package/transforms/eo-eo_FONIPA.txt

@@ -0,0 +1,47 @@
+
+# https://en.wikipedia.org/wiki/Esperanto_phonology
+::NFC;
+::Lower;
+[\-\'’] → ;  # eg. vorto-provizo, famili’
+aj → ai̯;
+aŭ → au̯;
+á → a;
+a → a;
+b → b;
+ĉ → t͡ʃ;
+c → t͡s;
+dz → d͡z;
+d → d;
+ej → ei̯;
+eŭ → eu̯;
+é → e;
+e → e;
+f → f;
+ĝ → d͡ʒ;
+g → ɡ;
+ĥ → x;
+h → h;
+í → i;
+i → i;
+ĵ → ʒ;
+j → j;
+k → k;
+l → l;
+m → m;
+n → n;
+oj → oi̯;
+ó → o;
+o → o;
+p → p;
+r → r;
+ŝ → ʃ;
+s → s;
+t → t;
+uj → ui̯;
+ŭ → w;  # eg. ŭa!
+ú → u;
+u → u;
+v → v;
+z → z;
+::NFC;
+

package/transforms/eo-fa.json

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

package/transforms/eo-fa.txt

@@ -0,0 +1,4 @@
+
+::eo-eo_FONIPA;
+::und_FONIPA-fa;
+

package/transforms/es-am.json

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

package/transforms/es-am.txt

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

package/transforms/es-ar.json

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

package/transforms/es-ar.txt

@@ -0,0 +1,13 @@
+
+$Boundary =  [^[:L:][:M:][:N:]];
+$Vowel = [i e o u a];
+::es-es_FONIPA;
+# In Ararbic 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-chr.json

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

package/transforms/es-chr.txt

@@ -0,0 +1,4 @@
+
+::es-es_FONIPA;
+::und_FONIPA-chr;
+

package/transforms/es-es_FONIPA.json

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