icu4c/source/data/translit/fa_fa_FONIPA.txt

# © 2016 and later: Unicode, Inc. and others.
# License & terms of use: http://www.unicode.org/copyright.html
# Generated using tools/cldr/cldr-to-icu/build-icu-data.xml
#
# File: fa_fa_FONIPA.txt
# Generated from CLDR
#

[\u200c \u200d] → ;  # Strip off ZWJ and ZWNJ.
::NFD;
# Rewrite similarly-looking Arabic letters to Persian.
ي → ی;
ى → ی;
ك → ک;
ە → ه;
::NULL;
$VOWEL = [ \u064E \u0650  \u064F  \u0653 ا و ی];
$BOUNDARY = [^[:L:][:M:][:N:]];
$IPA_CONSONANT = [ m n p b t d k ɡ ʔ f v s z ʃ ʒ ʁ ɢ h χ {t\u0361ʃ} {d\u0361ʒ} l ɾ ];
# Vowels
ی\u0651 → jj;
و\u0651 → vv;
([ \u064E \u0650  \u064F])\u0651 → \u0651 | $1;
\u064Eی\u0652 → æj;
\u0650ی → ej;
یو\u0652 → iːv;
{یو} ه $BOUNDARY → iːv;
{یو} ه\u0654 $BOUNDARY → iːv;
یو → juː;
\u064Eو\u0652 → av;
# Hamza forms
ء → ʔ;
ا \u064E \u0654 → ʔæ; # Needed because NFD reorders fatha before hamza
ا \u0654 → ʔ;
و \u0654 → ʔ;
ی \u0652 \u0654 → ʔ; # Needed because NFD reorders sukun before hamza
ی \u0650 \u0654 → ʔe; # Needed because NFD reorders kasra before hamza
ی \u0654 → ʔ;
{ \u064E ه} $BOUNDARY → æ;
[^ːeoæ] {ه\u0654} $BOUNDARY → eje;
[e] {ه\u0654} $BOUNDARY → je;
[^ːeoæ] {ه} $BOUNDARY → e;
[e] {ه} $BOUNDARY → ;
ا\u064E → æ;
ا\u064B $BOUNDARY → æn;
\u064E → æ;
یه → je;
ی\u0670 → ɒː;
$IPA_CONSONANT {وی} $VOWEL → uːj;
# If yeh is preceded by a consonant and followed by a vowel,
# it's pronounced /iːj/, but a sukun breaks that and makes it
# be pronounced just as /j/.
$IPA_CONSONANT {\u0652 یو} → juː;
$IPA_CONSONANT {\u0652 ی} $VOWEL → j;
$IPA_CONSONANT {ی} $VOWEL → iːj;
{ی} $VOWEL → j;
ی \u0652 → j;
ی → iː;
$BOUNDARY {ای} → iː;
ا\u0653 → ɒː;
آ → ɒː;
ا\u0650 → e;
$BOUNDARY {ا\u064Fو} → o;
ا\u064F → o;
$BOUNDARY {او} → uː;
او → ɒːv;
ا → ɒː; # Probably [^$BOUNDARY]
\u0650 → e;
ه \u0650 \u0651 → hhe; # Needed because NFD moves kasra before shadda
ه\u0650 → he;
خوا → χɒː;
خوی → χiː;
{و} $VOWEL → v;
{و} ه $BOUNDARY → v;
{و} ه\u0654 $BOUNDARY → v;
$IPA_CONSONANT {و} → uː;
$IPA_CONSONANT \u0651 {و} → uː; # shadda after a consonant
\u064F{و} $IPA_CONSONANT → uː;
$BOUNDARY {و} $BOUNDARY → va;
{ \u064Fو} $VOWEL → ov;
\u064F و \u0654 → oʔ;
\u064Fو → o;
\u064F → o;
# Consonants
پ → p;
ب → b;
[ت ط] → t;
د → d;
ک → k;
گ → ɡ;
ع → ʔ;
چ → t\u0361ʃ;
ج → d\u0361ʒ;
ف → f;
[س ص ث] → s;
[ز ذ ض ظ] → z;
ش → ʃ;
ژ → ʒ;
خ → χ;
غ → ʁ;
ق → ɢ;
ح → h;
م → m;
ن → n;
ه → h;
ل → l;
ر → ɾ;
\u0652 → ;
::NULL;
# TODO: How to handle these?
([$IPA_CONSONANT|$VOWEL]){\u0651} → $1;
[ \u0651 \u0654 \u064B \u0670 ] → ;
::NFC;