i18n 0.3.3 → 0.3.4

data/vendor/cldr/common/transforms/Han-Spacedhan.xml

@@ -0,0 +1,21 @@
+<?xml version="1.0" encoding="UTF-8" ?>
+<!DOCTYPE supplementalData SYSTEM "../../common/dtd/ldmlSupplemental.dtd">
+<supplementalData>
+	<transforms>
+		<transform source="Han" target="Spacedhan" direction="both" visibility="internal">
+			<comment># Only intended for internal use</comment>
+			<tRule>:: fullwidth-halfwidth;</tRule>
+			<tRule>｡ → '.';</tRule>
+			<tRule>$terminalPunct = [\.\,\:\;\?\!．，：？！｡、；[:Pe:][:Pf:]];</tRule>
+			<tRule>$initialPunct = [:Ps:][:Pi:];</tRule>
+			<comment># add space between any Han or terminal punctuation and letters, and</comment>
+			<comment># between letters and Han or initial punct</comment>
+			<tRule>[[:Ideographic:] $terminalPunct] {} [:Letter:] → ' ' ;</tRule>
+			<tRule>[:Letter:] [:Mark:]* {} [[:Ideographic:] $initialPunct] → ' ' ;</tRule>
+			<comment># remove spacing between ideographs and other letters</comment>
+			<tRule>← [:Ideographic:] { ' ' } [:Letter:] ;</tRule>
+			<tRule>← [:Letter:] [:Mark:]* { ' ' } [:Ideographic:] ;</tRule>
+		</transform>
+	</transforms>
+</supplementalData>
+

data/vendor/cldr/common/transforms/Hangul-Latin.xml

@@ -0,0 +1,13 @@
+<?xml version="1.0" encoding="UTF-8" ?>
+<!DOCTYPE supplementalData SYSTEM "../../common/dtd/ldmlSupplemental.dtd">
+<supplementalData>
+	<transforms>
+		<transform source="Hangul" target="Latin" direction="forward">
+			<tRule>::['ᄀ-하-ᅵᆨ-ᇂㄱ-ㄿㅁ-ㅃㅅ-ㅣ㈀-㈜㉠-㉻가-힣＇ﾡ-ﾯﾱ-ﾳﾵ-ﾾￂ-ￇￊ-ￏￒ-ￗￚ-ￜ];</tRule>
+			<tRule>::NFKD;</tRule>
+			<tRule>::ConjoiningJamo-Latin;</tRule>
+			<tRule>::NFC;</tRule>
+		</transform>
+	</transforms>
+</supplementalData>
+

data/vendor/cldr/common/transforms/Hebrew-Latin-BGN.xml

@@ -0,0 +1,132 @@
+<?xml version="1.0" encoding="UTF-8" ?>
+<!DOCTYPE supplementalData SYSTEM "../../common/dtd/ldmlSupplemental.dtd">
+<supplementalData>
+	<transforms>
+		<transform source="Hebrew" target="Latin" direction="forward" variant="BGN" draft="provisional">
+			<comment>
+			########################################################################
+			# 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 &lt;everson@evertype.com&gt;
+			########################################################################
+			#
+			# MINIMAL FILTER: Hebrew-Latin
+			#
+			</comment>
+			<tRule>:: [ ְֱֲֳִֵֶַָֹֻּׁׂאבגדהוזחטיךכלםמןנסעףפץצקרשת׳] ;</tRule>
+			<tRule>:: NFD (NFC) ;</tRule>
+			<comment>
+			#
+			########################################################################
+			</comment>
+
+			<comment>
+			########################################################################
+			#
+			# Define All Transformation Variables
+			#
+			########################################################################
+			#
+			</comment>
+			<tRule>$alef = ’;</tRule>
+			<tRule>$ayin = ‘;</tRule>
+			<comment>
+			#
+			# Use this $wordBoundary until bug 2034 is fixed in ICU:
+			# http://bugs.icu-project.org/cgi-bin/icu-bugs/transliterate?id=2034;expression=boundary;user=guest
+			#
+			</comment>
+			<tRule>$wordBoundary = [^[:L:][:M:][:N:]] ;</tRule>
+			<comment>
+			#
+			########################################################################
+			</comment>
+
+			<comment>
+			########################################################################
+			#
+			# Rules moved to front to avoid masking
+			#
+			########################################################################
+			#
+			</comment>
+			<tRule>בּ → b ; # HEBREW LETTER BET + DAGESH</tRule>
+			<tRule>פּ → P ; # HEBREW LETTER PE + DAGESH</tRule>
+			<tRule>גּ → g ; # HEBREW LETTER GIMEL + DAGESH</tRule>
+			<tRule>ג׳ → ǧ ; # HEBREW LETTER GIMEL + GERESH</tRule>
+			<tRule>וּ → u ; # HEBREW LETTER VAV + POINT DAGESH</tRule>
+			<tRule>וֹ → o ; # HEBREW LETTER VAV + POINT HOLAM</tRule>
+			<tRule>צ׳ → č ; # HEBREW LETTER TSADI + GERESH</tRule>
+			<tRule>ז׳ → ž ; # HEBREW LETTER ZAYIN + GERESH</tRule>
+			<tRule>דּ → d ; # HEBREW LETTER DALET + DAGESH</tRule>
+			<tRule>הּ → h ; # HEBREW LETTER HE + DAGESH</tRule>
+			<tRule>ךּ → k ; # HEBREW LETTER FINAL KAF + DAGESH</tRule>
+			<tRule>כּ → k ; # HEBREW LETTER KAF + DAGESH</tRule>
+			<tRule>ךְ → kh ; # HEBREW LETTER FINAL KAF + SHEVA</tRule>
+			<tRule>תּ → t ; # HEBREW LETTER TAV + DAGESH</tRule>
+			<comment>
+			#
+			########################################################################
+			</comment>
+
+			<comment>
+			########################################################################
+			#
+			# Start of Alphabetic Transformations
+			#
+			########################################################################
+			#
+			</comment>
+			<tRule>א → $alef ; # HEBREW LETTER ALEF</tRule>
+			<tRule>ב → v ; # HEBREW LETTER BET</tRule>
+			<tRule>ג → g ; # HEBREW LETTER GIMEL</tRule>
+			<tRule>ד → d ; # HEBREW LETTER DALET</tRule>
+			<tRule>ה → h ; # HEBREW LETTER HE</tRule>
+			<tRule>ח → ẖ ; # HEBREW LETTER HET</tRule>
+			<tRule>ו → w ; # HEBREW LETTER VAV</tRule>
+			<tRule>ז → z ; # HEBREW LETTER ZAYIN</tRule>
+			<tRule>[טת] → t ; # HEBREW LETTER TET</tRule>
+			<tRule>י → y ; # HEBREW LETTER YOD</tRule>
+			<tRule>[כך] → kh ; # HEBREW LETTER KAF and FINAL KAF</tRule>
+			<tRule>ל → l ; # HEBREW LETTER LAMED</tRule>
+			<tRule>[מם] → m ; # HEBREW LETTER MEM and FINAL MEM</tRule>
+			<tRule>[נן] → n ; # HEBREW LETTER NUN and FINAL NUN</tRule>
+			<tRule>ס → s ; # HEBREW LETTER SAMEKH</tRule>
+			<tRule>ע → $ayin ; # HEBREW LETTER AYIN</tRule>
+			<tRule>[פף] → f ; # HEBREW LETTER PE and FINAL PE</tRule>
+			<tRule>[צץ] → ẕ ; # HEBREW LETTER TSADI and FINAL TSADI</tRule>
+			<tRule>ק → q ; # HEBREW LETTER QOF</tRule>
+			<tRule>ר → r ; # HEBREW LETTER RESH</tRule>
+			<tRule>שׁ → sh ; # HEBREW LETTER SHIN</tRule>
+			<tRule>שׂ → s ; # HEBREW LETTER SHIN</tRule>
+
+			<tRule>ַ → a ; # HEBREW POINT PATAH</tRule>
+			<tRule>ֲ → a ; # HEBREW POINT HATAF PATAH</tRule>
+			<tRule>ָ → o ; # HEBREW POINT QAMATS</tRule>
+			<tRule>ֶ → e ; # HEBREW POINT SEGOL</tRule>
+			<tRule>ֱ → e ; # HEBREW POINT HATAF SEGOL</tRule>
+			<tRule>ֵי → e ; # HEBREW POINT TSERE + LETTER YOD</tRule>
+			<tRule>ֵ → e ; # HEBREW POINT TSERE</tRule>
+			<tRule>ְ → e ; # HEBREW POINT SHEVA</tRule>
+			<tRule>ִי → i ; # HEBREW POINT HIRIQ + LETTER YOD</tRule>
+			<tRule>ִ → i ; # HEBREW POINT HIRIQ</tRule>
+			<tRule>ֳ → o ; # HEBREW LETTER HATAF QAMATS</tRule>
+			<tRule>ֹ → o ; # HEBREW POINT HOLAM</tRule>
+			<tRule>ֻ → u ; # HEBREW POINT QUBUTS</tRule>
+			<comment>
+			#
+			########################################################################
+			</comment>
+		</transform>
+	</transforms>
+</supplementalData>

data/vendor/cldr/common/transforms/Hebrew-Latin.xml

@@ -0,0 +1,95 @@
+<?xml version="1.0" encoding="UTF-8" ?>
+<!DOCTYPE supplementalData SYSTEM "../../common/dtd/ldmlSupplemental.dtd">
+<supplementalData>
+	<transforms>
+		<transform source="Hebrew" target="Latin" direction="both">
+			<comment># Transliteration table for Hebrew</comment>
+			<comment># Based on the UNGEGN table at:</comment>
+			<comment>#   http://www.eki.ee/wgrs/rom1_he.pdf</comment>
+			<comment>#</comment>
+			<comment># Exceptions:</comment>
+			<comment># - Accents are added to disambiguate letters</comment>
+			<comment># - Combinations of dagesh, shin/sin dot that produce different</comment>
+			<comment>#   letters are not yet encoded.</comment>
+			<comment>#</comment>
+			<comment># To test, open:</comment>
+			<comment>#   http://www.ibm.com/software/globalization/icu/demo/transform</comment>
+			<comment># Click Edit, paste in this file, Save As hebrew-latin/XXX</comment>
+			<comment># (where XXX is a username)</comment>
+			<comment># Now go back to the main window, and try it out.</comment>
+			<comment># Use hebrew-latin/XXX for Output 1, and (Inverse) for Output 2</comment>
+			<comment># Paste in hebrew text in Input, and hit Transliterate.</comment>
+			<comment>#</comment>
+			<comment># For more information, see&quot;</comment>
+			<comment>#   http://icu.sourceforge.net/userguide/Transform.html</comment>
+			<tRule>:: [[:Hebrew:] [:^ccc=0:] [ְ-ֹֻ-ּׁ-ׂℵ-ℸֿ̄] - [ֽ]] ;</tRule>
+			<tRule>:: nfkd (nfc) ;</tRule>
+			<tRule>$letterAfter = [:M:]* [:L:] ;</tRule>
+			<comment># move longer items here to avoid masking</comment>
+			<tRule>ח ↔ ẖ ;</tRule>
+			<tRule>צ ↔ ẕ } $letterAfter;</tRule>
+			<tRule>ץ ↔ ẕ ;</tRule>
+			<tRule>ש ↔ ş ;</tRule>
+			<tRule>ת ↔ ţ ;</tRule>
+			<tRule>א ↔ ʼ ;</tRule>
+			<tRule>ב ↔ b ;</tRule>
+			<tRule>ג ↔ g ;</tRule>
+			<tRule>ד ↔ d ;</tRule>
+			<tRule>ה ↔ h ;</tRule>
+			<tRule>ו ↔ w ;</tRule>
+			<tRule>ז ↔ z ;</tRule>
+			<tRule>ט ↔ t ;</tRule>
+			<tRule>י ↔ y ;</tRule>
+			<tRule>כ ↔ k } $letterAfter;</tRule>
+			<tRule>ך ↔ k ;</tRule>
+			<tRule>ל ↔ l ;</tRule>
+			<tRule>מ ↔ m } $letterAfter;</tRule>
+			<tRule>ם ↔ m ;</tRule>
+			<tRule>נ ↔ n  } $letterAfter;</tRule>
+			<tRule>ן ↔ n ;</tRule>
+			<tRule>ס ↔ s ;</tRule>
+			<tRule>ע ↔ ʻ ;</tRule>
+			<tRule>פ ↔ p } $letterAfter;</tRule>
+			<tRule>ף ↔ p ;</tRule>
+			<tRule>ק ↔ q ;</tRule>
+			<tRule>ר ↔ r ;</tRule>
+			<tRule>װ → |  וו; # HEBREW LIGATURE YIDDISH DOUBLE VAV</tRule>
+			<tRule>ױ → | וי; # HEBREW LIGATURE YIDDISH VAV YOD</tRule>
+			<tRule>ײ → | יי ; # HEBREW LIGATURE YIDDISH DOUBLE YOD</tRule>
+			<tRule>ּ ↔ ̇ ; # dagesh just goes to overdot for now</tRule>
+			<tRule>ׁ ↔ ̌ ; # shin dot -→ sh</tRule>
+			<tRule>ׂ ↔ ̂ ; # sin dot -→ s</tRule>
+			<comment># points</comment>
+			<tRule>$above = [^[:ccc=0:][:ccc=230:]]*;</tRule>
+			<tRule>‎ֲ‎ → à ;</tRule>
+			<tRule>‎ֲ‎ $1← a ($above)  ̀;</tRule>
+			<tRule>‎ָ‎ → á ;</tRule>
+			<tRule>‎ָ‎  $1 ← a ($above)  ́;</tRule>
+			<tRule>‎ֱ‎ → è ;</tRule>
+			<tRule>‎ֱ‎  $1 ← e ($above)  ̀;</tRule>
+			<tRule>‎ֵ‎ → é ;</tRule>
+			<tRule>‎ֵ‎  $1 ← e ($above)   ́;</tRule>
+			<tRule>‎ְ‎ → e ̆ ;</tRule>
+			<tRule>‎ְ‎  $1 ← e ($above)   ̆;</tRule>
+			<tRule>‎ֹ‎ → ò ;</tRule>
+			<tRule>‎ֹ‎  $1 ← o ($above)   ̀;</tRule>
+			<tRule>ִ ↔ i ;</tRule>
+			<tRule>ֻ ↔ u ;</tRule>
+			<tRule>ַ ↔ a ;</tRule>
+			<tRule>ֶ ↔ e ;</tRule>
+			<tRule>ֳ ↔ o ;</tRule>
+			<tRule>ֿ ↔   ̄ ;</tRule>
+			<comment># fallbacks</comment>
+			<tRule>ק ← c ;</tRule>
+			<tRule>פ ← f } $letterAfter;</tRule>
+			<tRule>ף ← f ;</tRule>
+			<tRule>ז ← j ;</tRule>
+			<tRule>ו ← v ;</tRule>
+			<tRule>כס ← x ;</tRule>
+			<tRule>:: (lower);</tRule>
+			<tRule>:: nfc (nfd) ;</tRule>
+			<tRule>:: ([[:Latin:] [:^ccc=0:] [ʻ-ʼ̀-̧̱̂̇̌̀-́    ̄ ]]);</tRule>
+		</transform>
+	</transforms>
+</supplementalData>
+

data/vendor/cldr/common/transforms/Hiragana-Katakana.xml

@@ -0,0 +1,186 @@
+<?xml version="1.0" encoding="UTF-8" ?>
+<!DOCTYPE supplementalData SYSTEM "../../common/dtd/ldmlSupplemental.dtd">
+<supplementalData>
+	<transforms>
+		<transform source="Hiragana" target="Katakana" direction="both">
+			<comment># note: a global filter is more efficient, but MUST include all source chars</comment>
+			<tRule>:: [\u0000-\u007E 、。 ゙-゜ ァ-ー ｡-ﾟー[:Hiragana:] [:Katakana:] [:nonspacing mark:]] ;</tRule>
+			<tRule>:: NFKC ();</tRule>
+			<comment># Hiragana-Katakana</comment>
+			<comment># This is largely a one-to-one mapping, but it has a</comment>
+			<comment># few kinks:</comment>
+			<comment># 1. The Katakana va/vi/ve/vo (30F7-30FA) have no</comment>
+			<comment># Hiragana equivalents.  We use Hiragana wa/wi/we/wo</comment>
+			<comment># (308F-3092) with a voicing mark (3099), which is</comment>
+			<comment># semantically equivalent.  However, this is a non-</comment>
+			<comment># roundtripping transformation.</comment>
+			<comment># 2. The Katakana small ka/ke (30F5,30F6) have no</comment>
+			<comment># Hiragana equiavlents.  We convert them to normal</comment>
+			<comment># Hiragana ka/ke (304B,3051).  This is a one-way</comment>
+			<comment># information-losing transformation and precludes</comment>
+			<comment># round-tripping of 30F5 and 30F6.</comment>
+			<comment># 3. The combining marks 3099-309C are in the Hiragana</comment>
+			<comment># block, but they apply to Katakana as well, so we</comment>
+			<comment># leave them untouched.</comment>
+			<comment># 4. The Katakana prolonged sound mark 30FC doubles the</comment>
+			<comment># preceding vowel.  This is a one-way information-</comment>
+			<comment># losing transformation from Katakana to Hiragana.</comment>
+			<comment># 5. The Katakana middle dot separates words in foreign</comment>
+			<comment># expressions; we leave this unmodified.</comment>
+			<comment># The above points preclude successful round-trip</comment>
+			<comment># transformations of arbitrary input text.  However,</comment>
+			<comment># they provide naturalistic results that should conform</comment>
+			<comment># to user expectations.</comment>
+			<comment># Combining equivalents va/vi/ve/vo</comment>
+			<tRule>わ゙ ↔ ヷ;</tRule>
+			<tRule>ゐ゙ ↔ ヸ;</tRule>
+			<tRule>ゑ゙ ↔ ヹ;</tRule>
+			<tRule>を゙ ↔ ヺ;</tRule>
+			<comment># One-to-one mappings, main block</comment>
+			<comment># 3041:3094 ↔ 30A1:30F4</comment>
+			<comment># 309D,E ↔ 30FD,E</comment>
+			<tRule>ぁ ↔ ァ;</tRule>
+			<tRule>あ ↔ ア;</tRule>
+			<tRule>ぃ ↔ ィ;</tRule>
+			<tRule>い ↔ イ;</tRule>
+			<tRule>ぅ ↔ ゥ;</tRule>
+			<tRule>う ↔ ウ;</tRule>
+			<tRule>ぇ ↔ ェ;</tRule>
+			<tRule>え ↔ エ;</tRule>
+			<tRule>ぉ ↔ ォ;</tRule>
+			<tRule>お ↔ オ;</tRule>
+			<tRule>か ↔ カ;</tRule>
+			<tRule>が ↔ ガ;</tRule>
+			<tRule>き ↔ キ;</tRule>
+			<tRule>ぎ ↔ ギ;</tRule>
+			<tRule>く ↔ ク;</tRule>
+			<tRule>ぐ ↔ グ;</tRule>
+			<tRule>け ↔ ケ;</tRule>
+			<tRule>げ ↔ ゲ;</tRule>
+			<tRule>こ ↔ コ;</tRule>
+			<tRule>ご ↔ ゴ;</tRule>
+			<tRule>さ ↔ サ;</tRule>
+			<tRule>ざ ↔ ザ;</tRule>
+			<tRule>し ↔ シ;</tRule>
+			<tRule>じ ↔ ジ;</tRule>
+			<tRule>す ↔ ス;</tRule>
+			<tRule>ず ↔ ズ;</tRule>
+			<tRule>せ ↔ セ;</tRule>
+			<tRule>ぜ ↔ ゼ;</tRule>
+			<tRule>そ ↔ ソ;</tRule>
+			<tRule>ぞ ↔ ゾ;</tRule>
+			<tRule>た ↔ タ;</tRule>
+			<tRule>だ ↔ ダ;</tRule>
+			<tRule>ち ↔ チ;</tRule>
+			<tRule>ぢ ↔ ヂ;</tRule>
+			<tRule>っ ↔ ッ;</tRule>
+			<tRule>つ ↔ ツ;</tRule>
+			<tRule>づ ↔ ヅ;</tRule>
+			<tRule>て ↔ テ;</tRule>
+			<tRule>で ↔ デ;</tRule>
+			<tRule>と ↔ ト;</tRule>
+			<tRule>ど ↔ ド;</tRule>
+			<tRule>な ↔ ナ;</tRule>
+			<tRule>に ↔ ニ;</tRule>
+			<tRule>ぬ ↔ ヌ;</tRule>
+			<tRule>ね ↔ ネ;</tRule>
+			<tRule>の ↔ ノ;</tRule>
+			<tRule>は ↔ ハ;</tRule>
+			<tRule>ば ↔ バ;</tRule>
+			<tRule>ぱ ↔ パ;</tRule>
+			<tRule>ひ ↔ ヒ;</tRule>
+			<tRule>び ↔ ビ;</tRule>
+			<tRule>ぴ ↔ ピ;</tRule>
+			<tRule>ふ ↔ フ;</tRule>
+			<tRule>ぶ ↔ ブ;</tRule>
+			<tRule>ぷ ↔ プ;</tRule>
+			<tRule>へ ↔ ヘ;</tRule>
+			<tRule>べ ↔ ベ;</tRule>
+			<tRule>ぺ ↔ ペ;</tRule>
+			<tRule>ほ ↔ ホ;</tRule>
+			<tRule>ぼ ↔ ボ;</tRule>
+			<tRule>ぽ ↔ ポ;</tRule>
+			<tRule>ま ↔ マ;</tRule>
+			<tRule>み ↔ ミ;</tRule>
+			<tRule>む ↔ ム;</tRule>
+			<tRule>め ↔ メ;</tRule>
+			<tRule>も ↔ モ;</tRule>
+			<tRule>ゃ ↔ ャ;</tRule>
+			<tRule>や ↔ ヤ;</tRule>
+			<tRule>ゅ ↔ ュ;</tRule>
+			<tRule>ゆ ↔ ユ;</tRule>
+			<tRule>ょ ↔ ョ;</tRule>
+			<tRule>よ ↔ ヨ;</tRule>
+			<tRule>ら ↔ ラ;</tRule>
+			<tRule>り ↔ リ;</tRule>
+			<tRule>る ↔ ル;</tRule>
+			<tRule>れ ↔ レ;</tRule>
+			<tRule>ろ ↔ ロ;</tRule>
+			<tRule>ゎ ↔ ヮ;</tRule>
+			<tRule>わ ↔ ワ;</tRule>
+			<tRule>ゐ ↔ ヰ;</tRule>
+			<tRule>ゑ ↔ ヱ;</tRule>
+			<tRule>を ↔ ヲ;</tRule>
+			<tRule>ん ↔ ン;</tRule>
+			<tRule>ゔ ↔ ヴ;</tRule>
+			<tRule>ゝ ↔ ヽ;</tRule>
+			<tRule>ゞ ↔ ヾ;</tRule>
+			<comment># One-way Katakana-Hiragana xform of small K ka/ke to</comment>
+			<comment># normal H ka/ke.</comment>
+			<tRule>か ← ヵ;</tRule>
+			<tRule>け ← ヶ;</tRule>
+			<comment># Katakana followed by a prolonged sound mark 30FC has</comment>
+			<comment># its final vowel doubled.  This is a Katakana-Hiragana</comment>
+			<comment># one-way information-losing transformation.  We</comment>
+			<comment># include the small Katakana (e.g., small A 3041) and</comment>
+			<comment># do not distinguish them from their large</comment>
+			<comment># counterparts.  It doesn't make sense to double a</comment>
+			<comment># small counterpart vowel as a small Hiragana vowel, so</comment>
+			<comment># we don't do so.  In natural text this should never</comment>
+			<comment># occur anyway.  If a 30FC is seen without a preceding</comment>
+			<comment># vowel sound (e.g., after n 30F3) we do not change it.</comment>
+			<comment>### $long = ー;</comment>
+			<comment># The following categories are Hiragana, not Katakana</comment>
+			<comment># as might be expected, since by the time we get to the</comment>
+			<comment># 30FC, the preceding character will have already been</comment>
+			<comment># transformed to Hiragana.</comment>
+			<comment># {The following mechanically generated from the</comment>
+			<comment># Unicode 3.0 data:}</comment>
+			<tRule>$xa = [ \</tRule>
+			<tRule>ぁ あ か が さ ざ \</tRule>
+			<tRule>た だ な は ば ぱ \</tRule>
+			<tRule>ま ゃ や ら ゎ わ \</tRule>
+			<tRule>];</tRule>
+			<tRule>$xi = [ \</tRule>
+			<tRule>ぃ い き ぎ し じ \</tRule>
+			<tRule>ち ぢ に ひ び ぴ \</tRule>
+			<tRule>み り ゐ \</tRule>
+			<tRule>];</tRule>
+			<tRule>$xu = [ \</tRule>
+			<tRule>ぅ う く ぐ す ず \</tRule>
+			<tRule>っ つ づ ぬ ふ ぶ \</tRule>
+			<tRule>ぷ む ゅ ゆ る ゔ \</tRule>
+			<tRule>];</tRule>
+			<tRule>$xe = [ \</tRule>
+			<tRule>ぇ え け げ せ ぜ \</tRule>
+			<tRule>て で ね へ べ ぺ \</tRule>
+			<tRule>め れ ゑ \</tRule>
+			<tRule>];</tRule>
+			<tRule>$xo = [ \</tRule>
+			<tRule>ぉ お こ ご そ ぞ \</tRule>
+			<tRule>と ど の ほ ぼ ぽ \</tRule>
+			<tRule>も ょ よ ろ を \</tRule>
+			<tRule>];</tRule>
+			<tRule>あ ← $xa {ー};</tRule>
+			<tRule>い ← $xi {ー};</tRule>
+			<tRule>う ← $xu {ー};</tRule>
+			<tRule>え ← $xe {ー};</tRule>
+			<tRule>お ← $xo {ー};</tRule>
+			<tRule>:: (NFKC) ;</tRule>
+			<comment># note: a global filter is more efficient, but MUST include all source chars!!</comment>
+			<tRule>:: ([\u0000-\u007E 、。 ゙-゜ ァ-ー ｡-ﾟー[:Hiragana:] [:Katakana:] [:nonspacing mark:]]);</tRule>
+			<comment># eof</comment>
+		</transform>
+	</transforms>
+</supplementalData>
+