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