• Home
  • Line#
  • Scopes#
  • Navigate#
  • Raw
  • Download
1# © 2016 and later: Unicode, Inc. and others.
2# License & terms of use: http://www.unicode.org/copyright.html
3# Generated using tools/cldr/cldr-to-icu/build-icu-data.xml
4#
5# File: blt_blt_FONIPA.txt
6# Generated from CLDR
7#
8
9# Output phonemes
10# ---------------
11# Nasals:           m mʷ n nʷ ɲ ɲʷ ŋ ŋʷ
12# Plosives:         p pʰ pʰʷ pʷ b t tʷ tʰ d dʷ k kʰ kʰʷ kʷ ɡ ɡʷ ʔ
13# Fricatives:       f fʷ v s sʷ h hʷ x xʷ
14# Other consonants: w j l
15# Affricates:       t\u0361ɕ t\u0361ɕʷ t\u0361ɕʰ t\u0361ɕʰʷ
16# Vowels:           i ɨ u ɛ e ə ɔ o a aː
17# Diphthongs:       iə\u032F ɨə\u032F uə\u032F ai\u032F
18# Tones:            ˨ ˧˥ ˨˩ ˥ ˦ ˧˩
19#
20#
21# Limitations
22# -----------
23# Currently, these rules only support tone marks, but not tone letters.
24#
25#
26# References
27# ----------
28# [1] Jim Brase, SIL International: Proposal to encode the Tai Viet script
29#     in the UCS. ISO/IEC JTC1/SC2/WG2 N3220. March 20, 2007.
30#     http://std.dkuug.dk/jtc1/sc2/wg2/docs/n3220.pdf
31#
32# [2] ScriptSource: Tai Viet Vowels.
33#     http://scriptsource.org/entry/eusd5ehysa
34#
35# [3] ScriptSource: Tai Viet Consonants.
36#     http://scriptsource.org/entry/lbwpkrqk7b
37#
38# [4] http://www.seasite.niu.edu/tai/TaiDam/tones.htm
39$LO = [ꪀ ꪂ ꪄ ꪆ ꪈ ꪊ ꪌ ꪎ ꪐ ꪒ ꪔ ꪖ ꪘ ꪚ ꪜ ꪞ ꪠ ꪢ ꪤ ꪦ ꪨ ꪪ ꪬ ꪮ];
40$HI = [ꪁ ꪃ ꪅ ꪇ ꪉ ꪋ ꪍ ꪏ ꪑ ꪓ ꪕ ꪗ ꪙ ꪛ ꪝ ꪟ ꪡ ꪣ ꪥ ꪧ ꪩ ꪫ ꪭ ꪯ];
41$C = [$LO $HI];
42$V1 = [ꪵ ꪶ ꪹ ꪻ ꪼ];  # vowels written before consonant
43$V2 = [ \uAAB0 \uAAB2 \uAAB3 \uAAB4 \uAAB7 \uAAB8 \uAABE];  # vowels written above or below consonant
44$V3 = [ꪱ ꪮ ꪺ ꪽ];  # vowels written after consonant
45$DIGRAPHS = [{ꪹ  \uAAB8} {ꪹ  \uAAB7} {ꪹ ꪱ}];
46$V12 = [$V1 $V2 $DIGRAPHS];
47$V123 = [$V12 $V3];
48$W = [ꪫ];  # labialization marker
49$F = [$C]; # syllable-final consonant
50$IPA_TONE = [˥ ˦ ˧ ˨ ˩];
51$NOT_IPA_TONE = [^$IPA_TONE];
52$BOUNDARY = [^[:L:][:M:][:N:]];
53# Consonants at the end of “checked” syllables.
54$CHK = [ꪜ ꪝ ꪞ ꪟ ꪔ ꪕ ꪖ ꪗ ꪀ ꪁ ꪂ ꪃ ꪮ ꪯ];
55# The Tai Viet script uses visual ordering. Convert to logical order.
56($V1) ($C $W?) → $2 $1;
57::null;
58# Special handling for stand-alone ꪽ ‘that’.
59$BOUNDARY {ꪽ} $BOUNDARY → nan˧˩;
60# Convert tones for checked syllables (those ending in /p/, /t/, /k/, /ʔ/)
61$LO $W? $V12 {($CHK)} → $1 ˧˥;  # Tone class 2: High-rising tone
62$LO $W? {($V3 $CHK)} → $1 ˧˥;  # Tone class 2: High-rising tone
63$HI $W? $V12 {($CHK)} → $1 ˦;  # Tone class 5: High-mid tone
64$HI $W? {($V3 $CHK)} → $1 ˦;  # Tone class 5: High-mid tone
65# Convert tones for unchecked syllables with vowels that are written
66# after the consonant (V3).
67# TODO: Also support tone letters, not just tone marks.
68$LO $W? { \uAABF ($V3 $F?)} → $1 ˧˥;  # Tone class 2: High-rising tone
69$LO $W? { \uAAC1 ($V3 $F?)} → $1 ˨˩;  # Tone class 3: Low-falling tone
70$HI $W? { \uAABF ($V3 $F?)} → $1 ˦;   # Tone class 5: High-mid tone
71$HI $W? { \uAAC1 ($V3 $F?)} → $1 ˧˩;  # Tone class 6: Mid-falling tone
72# Convert tones for unchecked syllables with vowels that are either written
73# before the consonant (V1) or vowels that are written above or below it (V2).
74# TODO: Also support tone letters, not just tone marks.
75$LO $W? $V12 { \uAABF ($F?)} → $1 ˧˥;  # Tone class 2: High-rising tone
76$LO $W? $V12 { \uAAC1 ($F?)} → $1 ˨˩;  # Tone class 3: Low-falling tone
77$HI $W? $V12 { \uAABF ($F?)} → $1 ˦;   # Tone class 5: High-mid tone
78$HI $W? $V12 { \uAAC1 ($F?)} → $1 ˧˩;  # Tone class 6: Mid-falling tone
79::null;
80{($LO $W? $V123 $F?)} $NOT_IPA_TONE → $1 ˨;  # Tone class 1: Low-mid tone.
81{($HI $W? $V123 $F?)} $NOT_IPA_TONE → $1 ˥;  # Tone class 4: High tone.
82::null;
83# Harden syllable-final consonants.
84$C $W? $V123 {ꪒ} → ꪔ;  # /d/ → /t/
85::null;
86# Convert labialization marker.
87$C {$W} $V123 → ʷ;
88::null;
89[ꪀ ꪁ] → k;
90[ꪂ ꪃ] → kʰ;  # Tai Dón; not used in Tai Dam according to [3]
91[ꪄ ꪅ] → x;
92[ꪆ ꪇ] → ɡ;  # only in loanwords, according to [3]
93[ꪈ ꪉ] → ŋ;
94[ꪊ ꪋ] → t\u0361ɕ;  # Tai Dón; not used in Tai Dam according to [3]
95[ꪌ ꪍ] → t\u0361ɕʰ;  # Tai Dón; not used in Tai Dam according to [3]
96[ꪎ ꪏ] → s;
97[ꪐ ꪑ] → ɲ;
98[ꪒ ꪓ] → d;
99[ꪔ ꪕ] → t;
100[ꪖ ꪗ] → tʰ;
101[ꪘ ꪙ] → n;
102[ꪚ ꪛ] → b;
103[ꪜ ꪝ] → p;
104[ꪞ ꪟ] → pʰ;  # Tai Dón; not used in Tai Dam according to [3]
105[ꪠ ꪡ] → f;
106[ꪢ ꪣ] → m;
107[ꪤ ꪥ] → j;
108[ꪦ ꪧ] → r;  # only in loanwords, according to [3]
109[ꪨ ꪩ] → l;
110{[ꪪ ꪫ]} $IPA_TONE → w;  # at the end of a syllable (before tone letters)
111[ꪪ ꪫ] → v;  # not at the end of a syllable
112[ꪬ ꪭ] → h;
113ʔ {[ꪮ ꪯ]} → ɔ;  # eg. ꪮꪮꪀ
114[ꪮ ꪯ] → ʔ;
115# Digraphs.
116ꪹ  \uAAB8 → e;
117ꪹ  \uAAB7 → ə;
118ꪹ ꪱ → aːw;
119# Vowels.
120\uAAB0 → a;
121ꪱ → aː;
122\uAAB2 → i;
123\uAAB3 → ɨ;
124\uAAB4 → u;
125ꪵ → ɛ;
126ꪶ → o;
127\uAAB7 → ɔ;
128ꪮ → ɔ;
129ꪺ → uə\u032F;
130ꪽ → an;
131ꪹ → ɨə\u032F;
132\uAAB8 → iə\u032F;
133ꪻ → əw;
134ꪼ → ai\u032F;
135\uAABE → am;
136# Word ligature symbols.
137ꫛ → kon˥;
138ꫜ → nɨŋ˦;
139
140