cldr-transforms 46.0.0-BETA2

package/transforms/am-chr.txt

@@ -0,0 +1,4 @@
+
+::am-am_FONIPA;
+::und_FONIPA-chr;
+

package/transforms/am-fa.json

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

package/transforms/am-fa.txt

@@ -0,0 +1,4 @@
+
+::am-am_FONIPA;
+::und_FONIPA-fa;
+

package/transforms/az-Lower.json

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

package/transforms/az-Lower.txt

@@ -0,0 +1,13 @@
+
+# I and i-dotless; I-dot and i are case pairs in Turkish and Azeri
+# 0130; 0069; 0130; 0130; tr; # LATIN CAPITAL LETTER I WITH DOT ABOVE
+İ→i;
+# When lowercasing, remove dot_above in the sequence I + dot_above, which will turn into i.
+# This matches the behavior of the canonically equivalent I-dot_above
+# 0307; ; 0307; 0307; tr After_I; # COMBINING DOT ABOVE
+# When lowercasing, unless an I is before a dot_above, it turns into a dotless i.
+# 0049; 0131; 0049; 0049; tr Not_Before_Dot; # LATIN CAPITAL LETTER I
+I([^[:ccc=Not_Reordered:][:ccc=Above:]]*)\u0307 → i$1 ;
+I→ı ;
+::Any-Lower();
+

package/transforms/az-Title.json

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

package/transforms/az-Title.txt

@@ -0,0 +1,11 @@
+
+# I and i-dotless; I-dot and i are case pairs in Turkish and Azeri
+# Make any string of letters after a cased letter be lower, with rules for i
+[:cased:] [:case-ignorable:]* { İ → i;
+[:cased:] [:case-ignorable:]* { I → ı;
+[:cased:] [:case-ignorable:]* { (.) → &Any-Lower($1) ;
+# Otherwise all lowercase go to upper (titlecase stay as is)
+i→İ ;
+([:Lowercase:]) → &Any-Upper($1) ;
+# do later I([^[:ccc=Not_Reordered:][:ccc=Above:]]*)\u0307 → i$1 ;
+

package/transforms/az-Upper.json

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

package/transforms/az-Upper.txt

@@ -0,0 +1,5 @@
+
+# Copyright (C) 2011-2013, Apple Inc.; Unicode, Inc.; and others. All Rights Reserved.
+i→İ;
+::Any-Upper();
+

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

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

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

@@ -0,0 +1,132 @@
+
+# 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˦;
+

package/transforms/byn-Ethi-t-byn-latn-m0-tekie-alibekit.json

@@ -0,0 +1,11 @@
+{
+  "_backwardAlias": "Latin-Ethiopic/Tekie_Alibekit",
+  "_visibility": "external",
+  "_backwardAliasBcp47": "byn-Ethi-t-byn-latn-m0-tekieali",
+  "_alias": "Ethiopic-Latin/Tekie_Alibekit",
+  "_aliasBcp47": "byn-Latn-t-byn-ethi-m0-tekieali",
+  "_source": "byn_Ethi",
+  "_direction": "both",
+  "_target": "byn_Latn",
+  "_rulesFile": "byn-Ethi-t-byn-latn-m0-tekie-alibekit.txt"
+}