cldr-transforms 46.0.0-BETA2

package/transforms/xh-fa.json

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

package/transforms/xh-fa.txt

@@ -0,0 +1,4 @@
+
+::xh-xh_FONIPA;
+::und_FONIPA-fa;
+

package/transforms/xh-xh_FONIPA.json

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

package/transforms/xh-xh_FONIPA.txt

@@ -0,0 +1,85 @@
+
+# Pronunciation rules for isiXhosa.
+#
+# Author: mjansche@google.com (Martin Jansche)
+#
+# These rules transcribe isiXhosa into the phoneme inventory used within the
+# NCHLT Speech Corpus (https://sites.google.com/site/nchltspeechcorpus/home).
+#
+# The rules were tested using the NCHLT-inlang isiXhosa pronunciation dictionary
+# (http://rma.nwu.ac.za/index.php/resource-catalogue/nchlt-inlang-dictionaries.html).
+# They correctly account for 14,999 out of 15,000 entries in the dictionary.
+#
+# The NCHLT 2013 phone set does not distinguish short and long vowels and does
+# not indicate tone in any way. Transcription of tone is out of scope without a
+# dictionary, since tone is generally not indicated in the orthography. Nasal
+# clicks are not treated as separated phonemes in the NCHLT 2013 phone set and
+# are transcribed as a sequence of nasal plus click instead.
+#
+# One minor notational deviation from the NCHLT 2013 phone set is that we use a
+# tie bar within the complex (slack voiced) clicks, e.g. ɡ͡ǀ instead of ɡǀ, to
+# avoid ambiguity and make the phoneme inventory uniquely decodable.
+::Lower;
+nyh → ɲʰ;
+n { tsh → t͡ʃʼ;
+tsh → t͡ʃʰ;
+tyh → cʰ;
+bh → bʰ;
+ch → ǀʰ;
+dl → ɮ;
+dy → ɟ;
+gc → ɡ͡ǀ;
+gq → ɡ͡ǃ;
+gr → ɣ;
+gx → ɡ͡ǁ;
+hl → ɬ;
+kh → kʰ;
+kr → k͡x;
+mh } [^l] → mʰ;  # <mhl> denotes /mɬ/ instead
+nh → nʰ;
+ny → ɲ;
+ph → pʰ;
+qh → ǃʰ;
+sh → ʃ;
+th → tʰ;
+tl → t͡ɬʼ;
+ts → t͡sʼ;
+ty → cʼ;
+xh → ǁʰ;
+aa → | a;
+ee → | e;
+ii → | i;
+kc → | c;
+kq → | q;
+mm → | m;
+oo → | o;
+rh → | r;
+uu → | u;
+a → a;
+b → ɓ;
+c → ǀ;
+d → d;
+e → ɛ;
+f → f;
+g → ɡ;
+h → h;
+i → i;
+j → d͡ʒ;
+k → kʼ;
+l → l;
+m → m;
+n } g → ŋ;
+n → n;
+o → ɔ;
+p → pʼ;
+q → ǃ;
+r → r;
+s → s;
+t → tʼ;
+u → u;
+v → v;
+w → w;
+x → ǁ;
+y → j;
+z → z;
+

package/transforms/yo-yo_BJ.json

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

package/transforms/yo-yo_BJ.txt

@@ -0,0 +1,36 @@
+
+#
+########################################################################
+#
+# Latin Characters that must be changed:
+#
+#   ẸỌṢ
+#   ẹọṣ
+#
+# Originally prepared by Jonathan Lai ( jali01@ca.ibm.com )
+########################################################################
+#
+# MINIMAL FILTER: yo-yo-BJ
+#
+:: [ẸỌṢẹọṣ] ;
+:: NFC ;
+#
+#
+########################################################################
+#
+########################################################################
+#
+# Start of Alphabetic Transformations
+#
+########################################################################
+#
+Ẹ→Ɛ;# LATIN CAPITAL LETTER E WITH DOT BELOW
+ẹ→ɛ;# LATIN SMALL LETTER E WITH DOT BELOW
+Ọ→Ɔ ;# LATIN CAPITAL LETTER O WITH DOT BELOW
+ọ→ɔ;# LATIN SMALL LETTER O WITH DOT BELOW
+Ṣ→Sh;# LATIN CAPITAL LETTER S WITH DOT BELOW
+ṣ→sh;# LATIN SMALL LETTER S WITH DOT BELOW
+#
+#
+########################################################################
+

package/transforms/zh_Latn_PINYIN-ru.json

@@ -0,0 +1,8 @@
+{
+  "_visibility": "external",
+  "_aliasBcp47": "ru-t-zh-latn-pinyin",
+  "_source": "zh_Latn_PINYIN",
+  "_direction": "forward",
+  "_target": "ru",
+  "_rulesFile": "zh_Latn_PINYIN-ru.txt"
+}

package/transforms/zh_Latn_PINYIN-ru.txt

@@ -0,0 +1,148 @@
+
+# Cyrillization of Mandarin Chinese from Pinyin into Russian (Palladius system).
+#
+# References:
+#   http://ru.wikipedia.org/wiki/Транскрипционная_система_Палладия
+#   http://www.omniglot.com/writing/mandarin_pts.htm
+#   http://www.pinyin.info/romanization/russian/index.html
+# These differ in the treatment of some syllables (e.g. <jue>) from the rules
+# below.
+#
+# Further commentary:
+#   http://languagelog.ldc.upenn.edu/nll/?p=604
+#
+# Remove tone marks.
+:: NFD (NFC);
+[\u0304\u0301\u030C\u0300\u0306] → ;
+:: NFC (NFD);
+#
+#
+# Syllabify. Add apostrophes to disambiguate whether <n> and <g> belong to the
+# coda or onset of a syllable.
+:: Null ();
+ng } [aeou] → n\'g;
+ng → ng\';
+n } [aeiouü] → \'n;
+n → n\';
+#
+#
+# Main pass.
+:: Null ();
+#
+#
+Ai → Ай;
+A  → А;
+B  → Б;
+Ch → Ч;
+Ci → Цы;
+C  → Ц;
+D  → Д;
+E  → Э;
+F  → Ф;
+G  → Г;
+H  → Х;
+Ju → Цз | ü;
+J  → Цз;
+K  → К;
+L  → Л;
+M  → М;
+N  → Н;
+O  → О;
+P  → П;
+Qu → Ц | ü;
+Q  → Ц;
+R  → Ж;
+Sh → Ш;
+Si → Сы;
+S  → С;
+T  → Т;
+Wu → У;
+W  → В;
+Xu → С | ü;
+X  → С;
+Yai → Яй;
+Ya → Я;
+Ye → Е;
+Yi → И;
+You → Ю;
+Yo } ng → Ю;
+Yo → Ё;
+Yu → Ю | v;
+Zh → Чж;
+Zi → Цзы;
+Z  → Цз;
+#
+#
+[$] { n → н;
+\'n → н;
+\'  → ;
+#
+#
+ai → ай;
+a  → а;
+b  → б;
+ch → ч;
+ci → цы;
+c  → ц;
+d  → д;
+ei → эй;
+e  → э;
+f  → ф;
+g  → г;
+h  → х;
+ia → я;
+ie → е;
+io } ng → ю;
+iu → ю;
+i  → и;
+ju → цз | ü;
+j  → цз;
+k  → к;
+l  → л;
+m  → м;
+ng → н;
+n  → нь;
+o } ng → у;
+o  → о;
+p  → п;
+qu → ц | ü;
+q  → ц;
+r } [^aeiou] → р;
+r  → ж;
+sh → ш;
+si → сы;
+s  → с;
+t  → т;
+[Хх] { ui → уэй;  # special exception
+ui → уй;
+uo → о;
+u  → у;
+ü  → ю | v;
+#
+# We use the dummy symbol <v> to signal that an <ü> or equivalent character has
+# just been processed.
+ve → э;
+#
+#alternative: ve → е;
+v } [an] → ;
+v  → й;
+wu → у;
+w  → в;
+xu → с | ü;
+x  → с;
+yai → яй;
+ya → я;
+ye → е;
+yi → и;
+you → ю;
+yo } ng → ю;
+yo → ё;
+yu → ю | v;
+zh → чж;
+zi → цзы;
+z  → цз;
+#
+#
+# Final pass: Make sure that the output consists entirely of Cyrillic letters.
+:: NFC ();
+

package/transforms/zu-am.json

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

package/transforms/zu-am.txt

@@ -0,0 +1,4 @@
+
+::zu-zu_FONIPA;
+::am_FONIPA-am;
+

package/transforms/zu-ar.json

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

package/transforms/zu-ar.txt

@@ -0,0 +1,4 @@
+
+::zu-zu_FONIPA;
+::und_FONIPA-ar;
+

package/transforms/zu-chr.json

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

package/transforms/zu-chr.txt

@@ -0,0 +1,4 @@
+
+::zu-zu_FONIPA;
+::und_FONIPA-chr;
+

package/transforms/zu-fa.json

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

package/transforms/zu-fa.txt

@@ -0,0 +1,4 @@
+
+::zu-zu_FONIPA;
+::und_FONIPA-fa;
+

package/transforms/zu-zu_FONIPA.json

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

package/transforms/zu-zu_FONIPA.txt

@@ -0,0 +1,72 @@
+
+# Pronunciation rules for isiZulu.
+#
+# Author: mjansche@google.com (Martin Jansche)
+#
+# These rules transcribe isiZulu into the phoneme inventory used within the
+# NCHLT Speech Corpus (https://sites.google.com/site/nchltspeechcorpus/home).
+#
+# The rules were tested using the NCHLT-inlang isiZulu pronunciation dictionary
+# (http://rma.nwu.ac.za/index.php/resource-catalogue/nchlt-inlang-dictionaries.html).
+# They correctly account for all 15,000 entries in the dictionary.
+#
+# The NCHLT 2013 phone set does not indicate tone in any way. Transcription of
+# tone is out of scope without a dictionary, since tone is generally not
+# indicated in the orthography. Nasal clicks are not treated as separated
+# phonemes in the NCHLT 2013 phone set and are transcribed as a sequence of
+# nasal plus click instead.
+#
+# One minor notational deviation from the NCHLT 2013 phone set is that we use a
+# tie bar within the complex (depressor) clicks, e.g. ɡ͡ǀ instead of ɡǀ, to
+# avoid ambiguity and make the phoneme inventory uniquely decodable.
+::Lower;
+tsh → t͡ʃʼ;
+bh → b;
+ch → ǀʰ;
+dl → ɮ;
+gc → ɡ͡ǀ;
+gq → ɡ͡ǃ;
+gx → ɡ͡ǁ;
+hh → ɦ;  # To investigate: /ɦ/ and /h/ may be switched in the NCHLT dictionary.
+hl → ɬ;
+kh → kʰ;
+kl → k͡ɬ;
+ny → ɲ;
+ph → pʰ;
+qh → ǃʰ;
+n { sh → t͡sʼ;
+sh → ʃ;
+th → tʰ;
+xh → ǁʰ;
+a → a;
+m { b → b;
+b → ɓ;
+c → ǀ;
+d → d;
+e → ɛ;
+f → f;
+g → ɡ;
+h → h;
+i → i;
+j → d͡ʒ;
+k → k;
+l → l;
+m → m;
+[$] { n } gc → n;
+n } [gk] → ŋ;
+n } j → ɲ;
+n → n;
+o → ɔ;
+p → pʼ;
+q → ǃ;
+n { s → t͡sʼ;
+s → s;
+t → tʼ;
+u → u;
+v → v;
+w → w;
+x → ǁ;
+y → j;
+n { z → d͡z;
+z → z;
+