common/transforms/blt-fonipa-t-blt.xml

<?xml version="1.0" encoding="UTF-8" ?>
<!DOCTYPE supplementalData SYSTEM "../../common/dtd/ldmlSupplemental.dtd">
<!--
Copyright © 1991-2017 Unicode, Inc.
CLDR data files are interpreted according to the LDML specification (http://unicode.org/reports/tr35/)
For terms of use, see http://www.unicode.org/copyright.html
-->
<supplementalData>
	<version number="$Revision: 13680 $"/>
	<transforms>
		<transform source="blt" target="blt_FONIPA" direction="forward" alias="blt-fonipa-t-blt">
			<tRule><![CDATA[
# 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:       t͡ɕ t͡ɕʷ t͡ɕʰ t͡ɕʰʷ
# Vowels:           i ɨ u ɛ e ə ɔ o a aː
# Diphthongs:       iə̯ ɨə̯ uə̯ ai̯
# 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 = [ ꪰ ꪲ ꪳ ꪴ ꪷ ꪸ ꪾ];  # vowels written above or below consonant
$V3 = [ꪱ ꪮ ꪺ ꪽ];  # vowels written after consonant
$DIGRAPHS = [{ꪹ  ꪸ} {ꪹ  ꪷ} {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 $W? { ꪿ ($V3 $F?)} → $1 ˧˥;  # Tone class 2: High-rising tone
$LO $W? { ꫁ ($V3 $F?)} → $1 ˨˩;  # Tone class 3: Low-falling tone
$HI $W? { ꪿ ($V3 $F?)} → $1 ˦;   # Tone class 5: High-mid tone
$HI $W? { ꫁ ($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? $V12 { ꪿ ($F?)} → $1 ˧˥;  # Tone class 2: High-rising tone
$LO $W? $V12 { ꫁ ($F?)} → $1 ˨˩;  # Tone class 3: Low-falling tone
$HI $W? $V12 { ꪿ ($F?)} → $1 ˦;   # Tone class 5: High-mid tone
$HI $W? $V12 { ꫁ ($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] → t͡ɕ;  # Tai Dón; not used in Tai Dam according to [3]
[ꪌ ꪍ] → t͡ɕʰ;  # 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  ꪸ → e;
ꪹ  ꪷ → ə;
ꪹ ꪱ → aːw;

# Vowels.
 ꪰ → a;
ꪱ → aː;
 ꪲ → i;
 ꪳ → ɨ;
 ꪴ → u;
ꪵ → ɛ;
ꪶ → o;
 ꪷ → ɔ;
ꪮ → ɔ;
ꪺ → uə̯;
ꪽ → an;
ꪹ → ɨə̯;
 ꪸ → iə̯;
ꪻ → əw;
ꪼ → ai̯;
 ꪾ → am;

# Word ligature symbols.
ꫛ → kon˥;
ꫜ → nɨŋ˦;
			]]></tRule>
		</transform>
	</transforms>
</supplementalData>