cldr-transforms 46.0.0-BETA2

package/transforms/Han-Spacedhan.json

@@ -0,0 +1,7 @@
+{
+  "_visibility": "internal",
+  "_source": "Han",
+  "_direction": "both",
+  "_target": "Spacedhan",
+  "_rulesFile": "Han-Spacedhan.txt"
+}

package/transforms/Han-Spacedhan.txt

@@ -0,0 +1,35 @@
+
+# Only intended for internal use
+# Make sure Han are normalized, including characters that contain them.
+# The first set in the filter is computed with http://unicode.org/cldr/utility/list-unicodeset.jsp?a=[:tonfkd:/XXX/:]-[:ideographic:]-[:sc=han:]
+# Where XXX is the resolved [:ideographic:][:sc=han:]. It needs updating with each Unicode release!
+:: [[、。々《-』〜・㆒-㆟㈠-㉇㊀-㊰㋀-㋋ ㍘-㍰㍻-㍿㏠-㏾🈐-🈒🈔-🈺🉀-🉈🉐🉑][:ideographic:][:sc=han:]] nfkc;
+:: fullwidth-halfwidth;
+｡ → '.';
+。→ '.';
+、→ ',';
+､→ ',';
+《→ '«';
+》→ '»';
+〈 → '‹';
+〉→ '›';
+「→ '‘';
+」→ '’';
+｢→ '‘';
+｣→ '’';
+『→ '“';
+』→ '”';
+・→ '‧';
+･ → '‧';
+々→ '⓶';
+〜→ '~';
+$terminalPunct = [\.\,\:\;\?\!．，：？！｡、；[:Pe:][:Pf:]];
+$initialPunct = [:Ps:][:Pi:];
+# add space between any Han or terminal punctuation and letters, and
+# between letters and Han or initial punct
+[[:Ideographic:] $terminalPunct] {} [:Letter:] → ' ' ;
+[:Letter:] [:Mark:]* {} [[:Ideographic:] $initialPunct] → ' ' ;
+# remove spacing between ideographs and other letters
+← [:Ideographic:] { ' ' } [:Letter:] ;
+← [:Letter:] [:Mark:]* { ' ' } [:Ideographic:] ;
+

package/transforms/Hangul-Latin.json

@@ -0,0 +1,9 @@
+{
+  "_visibility": "external",
+  "_alias": "Hangul-Latin",
+  "_aliasBcp47": "und-Latn-t-und-hang",
+  "_source": "Hang",
+  "_direction": "forward",
+  "_target": "Latn",
+  "_rulesFile": "Hangul-Latin.txt"
+}

package/transforms/Hangul-Latin.txt

@@ -0,0 +1,6 @@
+
+::['ᄀ-하-ᅵᆨ-ᇂㄱ-ㄿㅁ-ㅃㅅ-ㅣ㈀-㈜㉠-㉻가-힣＇ﾡ-ﾯﾱ-ﾳﾵ-ﾾￂ-ￇￊ-ￏￒ-ￗￚ-ￜ];
+::NFKD;
+::ConjoiningJamo-Latin;
+::NFC;
+

package/transforms/Hebrew-Latin-BGN.json

@@ -0,0 +1,9 @@
+{
+  "_visibility": "external",
+  "_alias": "Hebrew-Latin/BGN",
+  "_aliasBcp47": "he-Latn-t-he-m0-bgn",
+  "_source": "he",
+  "_direction": "forward",
+  "_target": "he_Latn",
+  "_rulesFile": "Hebrew-Latin-BGN.txt"
+}

package/transforms/Hebrew-Latin-BGN.txt

@@ -0,0 +1,113 @@
+
+#
+########################################################################
+# BGN/PCGN 1981 System
+#
+# The BGN/PCGN system for Hebrew was designed for use in romanizing
+# names written in the Hebrew alphabet. The Roman letters and letter
+# combinations shown as equivalents to the Hebrew characters reflect
+# the eastern variety of Hebrew, i.e., the language spoken in
+# the Republic of Armenia.
+#
+# The Hebrew Alphabet as defined by the BGN (Page 33-35):
+#
+# אבגדהוזחטיכךלמםנןסעפףצץקרששת
+#
+# Originally prepared by Michael Everson <everson@evertype.com>
+########################################################################
+#
+# MINIMAL FILTER: Hebrew-Latin
+#
+:: [ ְֱֲֳִֵֶַָֹֻּׁׂאבגדהוזחטיךכלםמןנסעףפץצקרשת׳] ;
+:: NFD (NFC) ;
+#
+#
+########################################################################
+#
+########################################################################
+#
+# Define All Transformation Variables
+#
+########################################################################
+#
+$alef = ’;
+$ayin = ‘;
+#
+#
+# Use this $wordBoundary until bug 2034 is fixed in ICU:
+# http://bugs.icu-project.org/cgi-bin/icu-bugs/transliterate?id=2034;expression=boundary;user=guest
+#
+$wordBoundary = [^[:L:][:M:][:N:]] ;
+#
+#
+########################################################################
+#
+########################################################################
+#
+# Rules moved to front to avoid masking
+#
+########################################################################
+#
+בּ → b ; # HEBREW LETTER BET + DAGESH
+פּ → P ; # HEBREW LETTER PE + DAGESH
+גּ → g ; # HEBREW LETTER GIMEL + DAGESH
+ג׳ → ǧ ; # HEBREW LETTER GIMEL + GERESH
+וּ → u ; # HEBREW LETTER VAV + POINT DAGESH
+וֹ → o ; # HEBREW LETTER VAV + POINT HOLAM
+צ׳ → č ; # HEBREW LETTER TSADI + GERESH
+ז׳ → ž ; # HEBREW LETTER ZAYIN + GERESH
+דּ → d ; # HEBREW LETTER DALET + DAGESH
+הּ → h ; # HEBREW LETTER HE + DAGESH
+ךּ → k ; # HEBREW LETTER FINAL KAF + DAGESH
+כּ → k ; # HEBREW LETTER KAF + DAGESH
+ךְ → kh ; # HEBREW LETTER FINAL KAF + SHEVA
+תּ → t ; # HEBREW LETTER TAV + DAGESH
+#
+#
+########################################################################
+#
+########################################################################
+#
+# Start of Alphabetic Transformations
+#
+########################################################################
+#
+א → $alef ; # HEBREW LETTER ALEF
+ב → v ; # HEBREW LETTER BET
+ג → g ; # HEBREW LETTER GIMEL
+ד → d ; # HEBREW LETTER DALET
+ה → h ; # HEBREW LETTER HE
+ח → ẖ ; # HEBREW LETTER HET
+ו → w ; # HEBREW LETTER VAV
+ז → z ; # HEBREW LETTER ZAYIN
+[טת] → t ; # HEBREW LETTER TET
+י → y ; # HEBREW LETTER YOD
+[כך] → kh ; # HEBREW LETTER KAF and FINAL KAF
+ל → l ; # HEBREW LETTER LAMED
+[מם] → m ; # HEBREW LETTER MEM and FINAL MEM
+[נן] → n ; # HEBREW LETTER NUN and FINAL NUN
+ס → s ; # HEBREW LETTER SAMEKH
+ע → $ayin ; # HEBREW LETTER AYIN
+[פף] → f ; # HEBREW LETTER PE and FINAL PE
+[צץ] → ẕ ; # HEBREW LETTER TSADI and FINAL TSADI
+ק → q ; # HEBREW LETTER QOF
+ר → r ; # HEBREW LETTER RESH
+שׁ → sh ; # HEBREW LETTER SHIN
+שׂ → s ; # HEBREW LETTER SHIN
+ַ → a ; # HEBREW POINT PATAH
+ֲ → a ; # HEBREW POINT HATAF PATAH
+ָ → o ; # HEBREW POINT QAMATS
+ֶ → e ; # HEBREW POINT SEGOL
+ֱ → e ; # HEBREW POINT HATAF SEGOL
+ֵי → e ; # HEBREW POINT TSERE + LETTER YOD
+ֵ → e ; # HEBREW POINT TSERE
+ְ → e ; # HEBREW POINT SHEVA
+ִי → i ; # HEBREW POINT HIRIQ + LETTER YOD
+ִ → i ; # HEBREW POINT HIRIQ
+ֳ → o ; # HEBREW LETTER HATAF QAMATS
+ֹ → o ; # HEBREW POINT HOLAM
+ֻ → u ; # HEBREW POINT QUBUTS
+#
+#
+########################################################################
+

package/transforms/Hebrew-Latin.json

@@ -0,0 +1,11 @@
+{
+  "_backwardAlias": "Latin-Hebrew",
+  "_visibility": "external",
+  "_backwardAliasBcp47": "und-Hebr-t-und-latn",
+  "_alias": "Hebrew-Latin",
+  "_aliasBcp47": "und-Latn-t-und-hebr",
+  "_source": "Hebr",
+  "_direction": "both",
+  "_target": "Latn",
+  "_rulesFile": "Hebrew-Latin.txt"
+}

package/transforms/Hebrew-Latin.txt

@@ -0,0 +1,91 @@
+
+# Transliteration table for Hebrew
+# Based on the UNGEGN table at:
+#   http://www.eki.ee/wgrs/rom1_he.pdf
+#
+# Exceptions:
+# - Accents are added to disambiguate letters
+# - Combinations of dagesh, shin/sin dot that produce different
+#   letters are not yet encoded.
+#
+# To test, open:
+#   http://www.ibm.com/software/globalization/icu/demo/transform
+# Click Edit, paste in this file, Save As hebrew-latin/XXX
+# (where XXX is a username)
+# Now go back to the main window, and try it out.
+# Use hebrew-latin/XXX for Output 1, and (Inverse) for Output 2
+# Paste in hebrew text in Input, and hit Transliterate.
+#
+# For more information, see:
+#   http://icu.sourceforge.net/userguide/Transform.html
+:: [[־׳״][:Hebrew:] [:^ccc=0:] [ְ-ֹֻ-ּׁ-ׂℵ-ℸֿ̄] - [ֽ]] ;
+:: nfkd (nfc) ;
+׳ ↔ '′';
+״ ↔ '″';
+־ ↔ '-';
+$letterAfter = [:M:]* [:L:] ;
+# move longer items here to avoid masking
+ח ↔ ẖ ;
+צ ↔ ẕ } $letterAfter;
+ץ ↔ ẕ ;
+ש ↔ ş ;
+ת ↔ ţ ;
+א ↔ ʼ ;
+ב ↔ b ;
+ג ↔ g ;
+ד ↔ d ;
+ה ↔ h ;
+ו ↔ w ;
+ז ↔ z ;
+ט ↔ t ;
+י ↔ y ;
+כ ↔ k } $letterAfter;
+ך ↔ k ;
+ל ↔ l ;
+מ ↔ m } $letterAfter;
+ם ↔ m ;
+נ ↔ n  } $letterAfter;
+ן ↔ n ;
+ס ↔ s ;
+ע ↔ ʻ ;
+פ ↔ p } $letterAfter;
+ף ↔ p ;
+ק ↔ q ;
+ר ↔ r ;
+װ → |  וו; # HEBREW LIGATURE YIDDISH DOUBLE VAV
+ױ → | וי; # HEBREW LIGATURE YIDDISH VAV YOD
+ײ → | יי ; # HEBREW LIGATURE YIDDISH DOUBLE YOD
+ּ ↔ ̇ ; # dagesh just goes to overdot for now
+ׁ ↔ ̌ ; # shin dot -→ sh
+ׂ ↔ ̂ ; # sin dot -→ s
+# points
+$above = [^[:ccc=0:][:ccc=230:]]*;
+‎ֲ‎ → à ;
+‎ֲ‎ $1← a ($above)  ̀;
+‎ָ‎ → á ;
+‎ָ‎  $1 ← a ($above)  ́;
+‎ֱ‎ → è ;
+‎ֱ‎  $1 ← e ($above)  ̀;
+‎ֵ‎ → é ;
+‎ֵ‎  $1 ← e ($above)   ́;
+‎ְ‎ → e ̆ ;
+‎ְ‎  $1 ← e ($above)   ̆;
+‎ֹ‎ → ò ;
+‎ֹ‎  $1 ← o ($above)   ̀;
+ִ ↔ i ;
+ֻ ↔ u ;
+ַ ↔ a ;
+ֶ ↔ e ;
+ֳ ↔ o ;
+ֿ ↔   ̄ ;
+# fallbacks
+ק ← c ;
+פ ← f } $letterAfter;
+ף ← f ;
+ז ← j ;
+ו ← v ;
+כס ← x ;
+:: (lower);
+:: nfc (nfd) ;
+:: ([[-′″][:Latin:] [:^ccc=0:] [ʻ-ʼ̀-̧̱̂̇̌̀-́    ̄ ]]);
+

package/transforms/Hiragana-Katakana.json

@@ -0,0 +1,11 @@
+{
+  "_backwardAlias": "Katakana-Hiragana",
+  "_visibility": "external",
+  "_backwardAliasBcp47": "und-Hira-t-und-kana",
+  "_alias": "Hiragana-Katakana",
+  "_aliasBcp47": "und-Kana-t-und-hira",
+  "_source": "Hira",
+  "_direction": "both",
+  "_target": "Kana",
+  "_rulesFile": "Hiragana-Katakana.txt"
+}

package/transforms/Hiragana-Katakana.txt

@@ -0,0 +1,179 @@
+
+# note: a global filter is more efficient, but MUST include all source chars
+:: [[\u0000-\u007E 、。 ゙-゜ ァ-ー ｡-ﾟー[:Hiragana:] [:Katakana:] [:nonspacing mark:]]-[\u309B \u309C]];
+:: NFKC (NFC);
+# Hiragana-Katakana
+# This is largely a one-to-one mapping, but it has a
+# few kinks:
+# 1. The Katakana va/vi/ve/vo (30F7-30FA) have no
+# Hiragana equivalents.  We use Hiragana wa/wi/we/wo
+# (308F-3092) with a voicing mark (3099), which is
+# semantically equivalent.  However, this is a non-
+# roundtripping transformation.
+# 2. The Katakana small ka/ke (30F5,30F6) have no
+# Hiragana equiavlents.  We convert them to normal
+# Hiragana ka/ke (304B,3051).  This is a one-way
+# information-losing transformation and precludes
+# round-tripping of 30F5 and 30F6.
+# 3. The combining marks 3099-309C are in the Hiragana
+# block, but they apply to Katakana as well, so we
+# leave them untouched.
+# 4. The Katakana prolonged sound mark 30FC doubles the
+# preceding vowel.  This is a one-way information-
+# losing transformation from Katakana to Hiragana.
+# 5. The Katakana middle dot separates words in foreign
+# expressions; we leave this unmodified.
+# The above points preclude successful round-trip
+# transformations of arbitrary input text.  However,
+# they provide naturalistic results that should conform
+# to user expectations.
+# Combining equivalents va/vi/ve/vo
+わ゙ ↔ ヷ;
+ゐ゙ ↔ ヸ;
+ゑ゙ ↔ ヹ;
+を゙ ↔ ヺ;
+# One-to-one mappings, main block
+# 3041:3094 ↔ 30A1:30F4
+# 309D,E ↔ 30FD,E
+ぁ ↔ ァ;
+あ ↔ ア;
+ぃ ↔ ィ;
+い ↔ イ;
+ぅ ↔ ゥ;
+う ↔ ウ;
+ぇ ↔ ェ;
+え ↔ エ;
+ぉ ↔ ォ;
+お ↔ オ;
+か ↔ カ;
+が ↔ ガ;
+き ↔ キ;
+ぎ ↔ ギ;
+く ↔ ク;
+ぐ ↔ グ;
+け ↔ ケ;
+げ ↔ ゲ;
+こ ↔ コ;
+ご ↔ ゴ;
+さ ↔ サ;
+ざ ↔ ザ;
+し ↔ シ;
+じ ↔ ジ;
+す ↔ ス;
+ず ↔ ズ;
+せ ↔ セ;
+ぜ ↔ ゼ;
+そ ↔ ソ;
+ぞ ↔ ゾ;
+た ↔ タ;
+だ ↔ ダ;
+ち ↔ チ;
+ぢ ↔ ヂ;
+っ ↔ ッ;
+つ ↔ ツ;
+づ ↔ ヅ;
+て ↔ テ;
+で ↔ デ;
+と ↔ ト;
+ど ↔ ド;
+な ↔ ナ;
+に ↔ ニ;
+ぬ ↔ ヌ;
+ね ↔ ネ;
+の ↔ ノ;
+は ↔ ハ;
+ば ↔ バ;
+ぱ ↔ パ;
+ひ ↔ ヒ;
+び ↔ ビ;
+ぴ ↔ ピ;
+ふ ↔ フ;
+ぶ ↔ ブ;
+ぷ ↔ プ;
+へ ↔ ヘ;
+べ ↔ ベ;
+ぺ ↔ ペ;
+ほ ↔ ホ;
+ぼ ↔ ボ;
+ぽ ↔ ポ;
+ま ↔ マ;
+み ↔ ミ;
+む ↔ ム;
+め ↔ メ;
+も ↔ モ;
+ゃ ↔ ャ;
+や ↔ ヤ;
+ゅ ↔ ュ;
+ゆ ↔ ユ;
+ょ ↔ ョ;
+よ ↔ ヨ;
+ら ↔ ラ;
+り ↔ リ;
+る ↔ ル;
+れ ↔ レ;
+ろ ↔ ロ;
+ゎ ↔ ヮ;
+わ ↔ ワ;
+ゐ ↔ ヰ;
+ゑ ↔ ヱ;
+を ↔ ヲ;
+ん ↔ ン;
+ゔ ↔ ヴ;
+ゝ ↔ ヽ;
+ゞ ↔ ヾ;
+# One-way Katakana-Hiragana xform of small K ka/ke to
+# normal H ka/ke.
+か ← ヵ;
+け ← ヶ;
+# Katakana followed by a prolonged sound mark 30FC has
+# its final vowel doubled.  This is a Katakana-Hiragana
+# one-way information-losing transformation.  We
+# include the small Katakana (e.g., small A 3041) and
+# do not distinguish them from their large
+# counterparts.  It doesn't make sense to double a
+# small counterpart vowel as a small Hiragana vowel, so
+# we don't do so.  In natural text this should never
+# occur anyway.  If a 30FC is seen without a preceding
+# vowel sound (e.g., after n 30F3) we do not change it.
+### $long = ー;
+# The following categories are Hiragana, not Katakana
+# as might be expected, since by the time we get to the
+# 30FC, the preceding character will have already been
+# transformed to Hiragana.
+# {The following mechanically generated from the
+# Unicode 3.0 data:}
+$xa = [
+ぁ あ か が さ ざ
+た だ な は ば ぱ
+ま ゃ や ら ゎ わ
+];
+$xi = [
+ぃ い き ぎ し じ
+ち ぢ に ひ び ぴ
+み り ゐ
+];
+$xu = [
+ぅ う く ぐ す ず
+っ つ づ ぬ ふ ぶ
+ぷ む ゅ ゆ る ゔ
+];
+$xe = [
+ぇ え け げ せ ぜ
+て で ね へ べ ぺ
+め れ ゑ
+];
+$xo = [
+ぉ お こ ご そ ぞ
+と ど の ほ ぼ ぽ
+も ょ よ ろ を
+];
+あ ← $xa {ー};
+い ← $xi {ー};
+う ← $xu {ー};
+え ← $xe {ー};
+お ← $xo {ー};
+:: NFC (NFKC) ;
+# note: a global filter is more efficient, but MUST include all source chars!!
+:: ([[\u0000-\u007E 、。 ゙-゜ ァ-ー ｡-ﾟー[:Hiragana:] [:Katakana:] [:nonspacing mark:]]-[\u309B \u309C]]);
+# eof
+

package/transforms/Hiragana-Latin.json

@@ -0,0 +1,11 @@
+{
+  "_backwardAlias": "Latin-Hiragana",
+  "_visibility": "external",
+  "_backwardAliasBcp47": "und-Hira-t-und-latn",
+  "_alias": "Hiragana-Latin",
+  "_aliasBcp47": "und-Latn-t-und-hira",
+  "_source": "Hira",
+  "_direction": "both",
+  "_target": "Latn",
+  "_rulesFile": "Hiragana-Latin.txt"
+}

package/transforms/Hiragana-Latin.txt

@@ -0,0 +1,9 @@
+
+:: [ぁ-ゔ゙ゝ-ゞガギグゲゴザジズゼゾダヂヅデドバビブベボヴヷ-ヺーヾ] ;
+:: NFD ;
+:: Hiragana-Katakana;
+:: Katakana-Latin;
+:: NFC ;
+:: (Lower) ;
+:: ([',.A-Za-z~À-ÖØ-öø-ďĒ-ĥĨ-İĴ-ķĹ-ľŃ-ňŌ-őŔ-ťŨ-žƠ-ơƯ-ưǍ-ǜǞ-ǣǦ-ǭǰǴ-ǵǸ-țȞ-ȟȦ-ȳ̄Ӣ-ӣӮ-ӯḀ-ẙẠ-ỹᾱᾹῑῙῡῩK-Å]) ;
+

package/transforms/IPA-XSampa.json

@@ -0,0 +1,11 @@
+{
+  "_backwardAlias": "XSampa-IPA",
+  "_visibility": "external",
+  "_backwardAliasBcp47": "und-fonipa-t-und-fonxsamp",
+  "_alias": "IPA-XSampa",
+  "_aliasBcp47": "und-fonxsamp-t-und-fonipa",
+  "_source": "und_FONIPA",
+  "_direction": "both",
+  "_target": "und_FONXSAMP",
+  "_rulesFile": "IPA-XSampa.txt"
+}