i18n 0.3.3 → 0.3.4

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

@@ -0,0 +1,13 @@
+<?xml version="1.0" encoding="UTF-8" ?>
+<!DOCTYPE supplementalData SYSTEM "../../common/dtd/ldmlSupplemental.dtd">
+<supplementalData>
+	<transforms>
+		<transform source="Latin" target="Jamo" direction="forward">
+			<tRule>::[[:script=Latin:][:M:]-];</tRule>
+			<tRule>::NFD;</tRule>
+			<tRule>::Lower;</tRule>
+			<tRule>::Latin-ConjoiningJamo;</tRule>
+			<tRule>::[[:script=Latin:][:M:]] NFC;</tRule>
+		</transform>
+	</transforms>
+</supplementalData>

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

@@ -0,0 +1,15 @@
+<?xml version="1.0" encoding="UTF-8" ?>
+<!DOCTYPE supplementalData SYSTEM "../../common/dtd/ldmlSupplemental.dtd">
+<supplementalData>
+	<transforms>
+		<transform source="Latin" target="Kannada" direction="forward">
+			<tRule>::['.0-9A-Za-z~À-ÅÇ-ÏÑ-ÖÙ-Ýà-åç-ïñ-öù-ýÿ-ďĒ-ĥĨ-İĴ-ķĹ-ľŃ-ňŌ-őŔ-ťŨ-žƠ-ơƯ-ưǍ-ǜǞ-ǣǦ-ǭǰǴ-ǵǸ-țȞ-ȟȦ-ȳʔ́̃-̄̆-̇̐̔-̣̥̱́̈́̕΅-ΆΈ-ΊΌΎ-ΐά-ΰό-ώϓЃЌЎЙйѓќўӁ-ӂӐ-ӑӖ-ӗӢ-ӣӮ-ӯḀ-ẙẠ-ỹἁἃ-ἅἇἉἋ-ἍἏἑἓ-ἕἙἛ-Ἕἡἣ-ἥἧἩἫ-ἭἯἱἳ-ἵἷἹἻ-ἽἿὁὃ-ὅὉὋ-Ὅὑὓ-ὕὗὙὛὝὟὡὣ-ὥὧὩὫ-ὭὯάέήίόύώᾁᾃ-ᾅᾇᾉᾋ-ᾍᾏᾑᾓ-ᾕᾗᾙᾛ-ᾝᾟᾡᾣ-ᾥᾧᾩᾫ-ᾭᾯ-ᾱᾴᾸ-ᾹΆῄΈΉ῎ῐ-ῑΐῘ-ῙΊ῞ῠ-ῡΰῥῨ-ῩΎ-Ῥ΅ῴΌΏK-Å\uE04D\uE064];</tRule>
+			<tRule>::NFD;</tRule>
+			<tRule>::Lower;</tRule>
+			<tRule>::Latin-InterIndic;</tRule>
+			<tRule>::InterIndic-Kannada;</tRule>
+			<tRule>::NFC;</tRule>
+		</transform>
+	</transforms>
+</supplementalData>
+

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

@@ -0,0 +1,389 @@
+<?xml version="1.0" encoding="UTF-8" ?>
+<!DOCTYPE supplementalData SYSTEM "../../common/dtd/ldmlSupplemental.dtd">
+<supplementalData>
+	<transforms>
+		<transform source="Latin" target="Katakana" direction="both">
+			<comment># note: a global filter is more efficient, but MUST include all source chars</comment>
+			<comment>#:: [\u0000-\u007E 、。 ゙-゜ ァ-ー ｡-ﾟ [:Latin:][:Katakana:] [:nonspacing mark:]] ;</comment>
+			<comment># MINIMAL FILTER GENERATED FOR: Latin-Katakana</comment>
+			<comment>### WARNING -- must add width filter, both here and below!!! ###</comment>
+			<tRule>:: [[ᄀ-ᄒᄚᄡ\u1160-ᅵᆪᆬ-ᆭᆰ-ᆵ←-↓│■○\u3000-。「-」゙-゚ァ-ロワヲ-ヴヷヺ-ー！-～￠-￦][',.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]] ;</tRule>
+			<tRule>:: [:Latin:] fullwidth-halfwidth ();</tRule>
+			<tRule>:: NFD (NFC);</tRule>
+			<tRule>:: Lower ();    # whenever transliterating from cased to uncased script, include this</tRule>
+			<comment># :: NFD () ;   # this would catch the odd cases where a lowercase is not in NFD, but none are important for Japanese</comment>
+			<comment># Uses modified Hepburn. Small changes to make  unambiguous.</comment>
+			<comment># | Kunrei-shiki: Hepburn/MHepburn</comment>
+			<comment># | ------------------------------</comment>
+			<comment># | si: shi</comment>
+			<comment># | si ~ya: sha</comment>
+			<comment># | si ~yu: shu</comment>
+			<comment># | si ~yo: sho</comment>
+			<comment># | zi: ji</comment>
+			<comment># | zi ~ya: ja</comment>
+			<comment># | zi ~yu: ju</comment>
+			<comment># | zi ~yo: jo</comment>
+			<comment># | ti: chi</comment>
+			<comment># | ti ~ya: cha</comment>
+			<comment># | ti ~yu: chu</comment>
+			<comment># | ti ~yu: cho</comment>
+			<comment># | tu: tsu</comment>
+			<comment># | di: ji/dji</comment>
+			<comment># | du: zu/dzu</comment>
+			<comment># | hu: fu</comment>
+			<comment># | For foreign words:</comment>
+			<comment># | -----------------</comment>
+			<comment># | se ~i si</comment>
+			<comment># | si ~e she</comment>
+			<comment># |</comment>
+			<comment># | ze ~i zi</comment>
+			<comment># | zi ~e je</comment>
+			<comment># |</comment>
+			<comment># | te ~i ti</comment>
+			<comment># | ti ~e che</comment>
+			<comment># | te ~u tu</comment>
+			<comment># |</comment>
+			<comment># | de ~i di</comment>
+			<comment># | de ~u du</comment>
+			<comment># | de ~i di</comment>
+			<comment># |</comment>
+			<comment># | he ~u: hu</comment>
+			<comment># | hu ~a fa</comment>
+			<comment># | hu ~i fi</comment>
+			<comment># | hu ~e he</comment>
+			<comment># | hu ~o ho</comment>
+			<comment># Most small forms are generated, but if necessary</comment>
+			<comment># explicit small forms are given with ~a, ~ya, etc.</comment>
+			<comment>#------------------------------------------------------</comment>
+			<comment># Variables</comment>
+			<tRule>$vowel = [aeiou] ;</tRule>
+			<tRule>$consonant = [bcdfghjklmnpqrstvwxyz] ;</tRule>
+			<tRule>$macron = ̄ ;</tRule>
+			<comment># Variables used for doubled-consonants with tsu</comment>
+			<tRule>$kana = [ぁ-ゔ] ;</tRule>
+			<tRule>$voice = [゙゛];</tRule>
+			<tRule>$semivoice = [゚゜];</tRule>
+			<tRule>$k_start = [カキクケコかきくけこ] ;</tRule>
+			<tRule>$s_start = [サシスセソさしすせそ] ;</tRule>
+			<tRule>$j_start = [シし] $voice ;</tRule>
+			<tRule>$t_start = [タチツテトたちつてと] ;</tRule>
+			<tRule>$n_start = [ナニヌネノンなにぬねの] ;</tRule>
+			<tRule>$h_start = [ハヒヘホはひへほ] ;</tRule>
+			<tRule>$f_start = [フふ] ;</tRule>
+			<tRule>$m_start = [マミムメモまみむめも] ;</tRule>
+			<tRule>$y_start = [ヤユヨやゆよ] ;</tRule>
+			<tRule>$r_start = [ラリルレロらりるれろ] ;</tRule>
+			<tRule>$w_start = [ワヰヱヲわゐゑを] ;</tRule>
+			<tRule>$v_start = [ワヰヱヲ]゙ ;</tRule>
+			<tRule>$voweled_basekana = [ァ-オカキクケコサシスセソタチッツテトナ-ノハヒフヘホマ-ヲヵヶ] ;</tRule>
+			<comment># if ン is followed by $n_quoter, then it needs an</comment>
+			<comment># apostrophe after its romaji form to disambiguate it.</comment>
+			<comment># e.g., ン ア ! =  ナ, so represent as &quot;n'a&quot;, not &quot;na&quot;.</comment>
+			<tRule>$n_quoter  =  [ア イ ウ エ オ ナ ニ ヌ ネ ノ ヤ ユ ヨ ン] ;</tRule>
+			<tRule>$small_y = [ャィュェョ] ;</tRule>
+			<tRule>$iteration = ゝ ;</tRule>
+			<comment>#------------------------------------------------------</comment>
+			<comment># katakana rules</comment>
+			<comment># Punctuation</comment>
+			<tRule>'.' ↔ 。;</tRule>
+			<tRule>',' ↔ 、;</tRule>
+			<comment># ' ' } [a-z] → ; # delete spaces before latin</comment>
+			<comment># ' ' ← [^' '゠-ヿ] {} ['゠-ヿ] ; #insert spaces before hiragana</comment>
+			<comment># Iteration Mark</comment>
+			<comment># Copy previous letter § marks</comment>
+			<comment># TODO</comment>
+			<comment># | $1 $1 ← ($kana [[:M:]$voice$semivoice]?) $iteration</comment>
+			<comment># Specials for katakana -- not shared with hiragana</comment>
+			<tRule>va ↔ ヷ ;</tRule>
+			<tRule>vi ↔ ヸ ;</tRule>
+			<tRule>ve ↔ ヹ ;</tRule>
+			<tRule>vo ↔ ヺ ;</tRule>
+			<tRule>'~ka' ↔ ヵ ;</tRule>
+			<tRule>'~ke' ↔ ヶ ;</tRule>
+			<comment># ~~~ begin shared rules ~~~</comment>
+			<comment>#special</comment>
+			<tRule>ya ← '~'ャ;</tRule>
+			<tRule>yi ← '~'ィ ;</tRule>
+			<tRule>yu ← '~'ュ;</tRule>
+			<tRule>ye ← '~'ェ;</tRule>
+			<tRule>yo ← '~'ョ;</tRule>
+			<comment>#normal</comment>
+			<tRule>a ↔ ア ;</tRule>
+			<tRule>b | '~' ← ヒ ゙} $small_y ;</tRule>
+			<tRule>by } $vowel → ビ | '~y' ;</tRule>
+			<tRule>ba ↔ バ ;</tRule>
+			<tRule>bi ↔ ビ ;</tRule>
+			<tRule>bu ↔ ブ ;</tRule>
+			<tRule>be ↔ ベ ;</tRule>
+			<tRule>bo ↔ ボ ;</tRule>
+			<tRule>c } i → | s ;</tRule>
+			<tRule>c } e → | s ;</tRule>
+			<tRule>da ↔ ダ ;</tRule>
+			<tRule>di ↔ ディ ;</tRule>
+			<tRule>du ↔ デゥ ;</tRule>
+			<tRule>de ↔ デ ;</tRule>
+			<tRule>do ↔ ド ;</tRule>
+			<tRule>dzu ↔ ヅ ;</tRule>
+			<tRule>dja ← ヂャ ;</tRule>
+			<tRule>dji'~i' ← ヂィ ; # liu</tRule>
+			<tRule>dju ← ヂュ ;</tRule>
+			<tRule>dje ← ヂェ ;</tRule>
+			<tRule>djo ← ヂョ ;</tRule>
+			<tRule>dji ↔ ヂ ;</tRule>
+			<tRule>dj  } $vowel → ヂ | '~y' ;</tRule>
+			<comment># TODO: QUESTION: use ĵĴżŻ instead of dj, dz</comment>
+			<tRule>cha ← チャ ;</tRule>
+			<tRule>chi'~i' ← チィ ; # liu</tRule>
+			<tRule>chu ← チュ ;</tRule>
+			<tRule>che ← チェ ;</tRule>
+			<tRule>cho ← チョ ;</tRule>
+			<tRule>chi ↔ チ ;</tRule>
+			<tRule>ch } $vowel → チ | '~y' ;</tRule>
+			<tRule>e ↔ エ ;</tRule>
+			<tRule>g | '~' ← ギ} $small_y ;</tRule>
+			<tRule>gy  } $vowel → ギ | '~y' ;</tRule>
+			<tRule>ga ↔ ガ ;</tRule>
+			<tRule>gi ↔ ギ ;</tRule>
+			<tRule>gu ↔ グ ;</tRule>
+			<tRule>ge ↔ ゲ ;</tRule>
+			<tRule>go ↔ ゴ ;</tRule>
+			<tRule>i ↔ イ ;</tRule>
+			<comment># j  } $vowel → ジ | '~y' ;</comment>
+			<tRule>ja ↔ ジャ ;</tRule>
+			<tRule>ji'~i' ← ジィ ; # liu</tRule>
+			<tRule>ju ↔ ジュ ;</tRule>
+			<tRule>je ↔ ジェ ;</tRule>
+			<tRule>jo ↔ ジョ ;</tRule>
+			<tRule>ji ↔ ジ ;</tRule>
+			<tRule>k | '~' ← キ} $small_y ;</tRule>
+			<tRule>ky  } $vowel → キ | '~y' ;</tRule>
+			<tRule>ka ↔ カ ;</tRule>
+			<tRule>ki ↔ キ ;</tRule>
+			<tRule>ku ↔ ク ;</tRule>
+			<tRule>ke ↔ ケ ;</tRule>
+			<tRule>ko ↔ コ ;</tRule>
+			<tRule>m | '~' ← ミ} $small_y ;</tRule>
+			<tRule>my  } $vowel → ミ | '~y' ;</tRule>
+			<tRule>ma ↔ マ ;</tRule>
+			<tRule>mi ↔ ミ ;</tRule>
+			<tRule>mu ↔ ム ;</tRule>
+			<tRule>me ↔ メ ;</tRule>
+			<tRule>mo ↔ モ ;</tRule>
+			<tRule>m } [pbfv] → ン ;</tRule>
+			<tRule>n | '~' ← ニ } $small_y ;</tRule>
+			<tRule>ny  } $vowel → ニ | '~y' ;</tRule>
+			<tRule>na ↔ ナ ;</tRule>
+			<tRule>ni ↔ ニ ;</tRule>
+			<tRule>nu ↔ ヌ ;</tRule>
+			<tRule>ne ↔ ネ ;</tRule>
+			<tRule>no ↔ ノ ;</tRule>
+			<tRule>o ↔ オ ;</tRule>
+			<tRule>p | '~' ← ピ } $small_y ;</tRule>
+			<tRule>py  } $vowel → ピ | '~y' ;</tRule>
+			<tRule>pa ↔ パ ;</tRule>
+			<tRule>pi ↔ ピ ;</tRule>
+			<tRule>pu ↔ プ ;</tRule>
+			<tRule>pe ↔ ペ ;</tRule>
+			<tRule>po ↔ ポ ;</tRule>
+			<tRule>h | '~' ← ヒ } $small_y ;</tRule>
+			<tRule>hy  } $vowel → ヒ | '~y' ;</tRule>
+			<tRule>ha ↔ ハ ;</tRule>
+			<tRule>hi ↔ ヒ ;</tRule>
+			<tRule>hu ↔ ヘゥ ;</tRule>
+			<tRule>he ↔ ヘ ;</tRule>
+			<tRule>ho ↔ ホ ;</tRule>
+			<comment># f | '~' ← フ } $small_y ;</comment>
+			<comment># f } $vowel → フ | '~' ;</comment>
+			<tRule>fa ↔ ファ ;</tRule>
+			<tRule>fi ↔ フィ ;</tRule>
+			<tRule>fe ↔ フェ ;</tRule>
+			<tRule>fo ↔ フォ ;</tRule>
+			<tRule>fu ↔ フ ;</tRule>
+			<tRule>r | '~' ← リ } $small_y ;</tRule>
+			<tRule>ry  } $vowel → リ | '~y' ;</tRule>
+			<tRule>ra ↔ ラ ;</tRule>
+			<tRule>ri ↔ リ ;</tRule>
+			<tRule>ru ↔ ル ;</tRule>
+			<tRule>re ↔ レ ;</tRule>
+			<tRule>ro ↔ ロ ;</tRule>
+			<tRule>za ↔ ザ ;</tRule>
+			<tRule>zi ↔ ゼィ ;</tRule>
+			<tRule>zu ↔ ズ ;</tRule>
+			<tRule>ze ↔ ゼ ;</tRule>
+			<tRule>zo ↔ ゾ ;</tRule>
+			<tRule>sa ↔ サ ;</tRule>
+			<tRule>si ↔ セィ ;</tRule>
+			<tRule>su ↔ ス ;</tRule>
+			<tRule>se ↔ セ ;</tRule>
+			<tRule>so ↔ ソ ;</tRule>
+			<tRule>sha ← シャ ;</tRule>
+			<tRule>shi'~i' ← シィ ; # liu</tRule>
+			<tRule>shu ← シュ ;</tRule>
+			<tRule>she ← シェ ;</tRule>
+			<tRule>sho ← ショ ;</tRule>
+			<tRule>shi ↔ シ ;</tRule>
+			<tRule>sh } $vowel → シ | '~y' ;</tRule>
+			<tRule>ta ↔ タ ;</tRule>
+			<tRule>ti ↔ ティ ;</tRule>
+			<tRule>tu ↔ テゥ ;</tRule>
+			<tRule>te ↔ テ ;</tRule>
+			<tRule>to ↔ ト ;</tRule>
+			<tRule>tsu ↔ ツ ;</tRule>
+			<comment># v  } $vowel → ヴ | '~' ;</comment>
+			<comment>#'v~a' ← ヴァ ; # liu</comment>
+			<comment>#'v~i' ← ヴィ ; # liu</comment>
+			<comment>#'v~e' ← ヴェ ; # liu</comment>
+			<comment>#'v~o' ← ヴォ ; # liu</comment>
+			<tRule>vu ↔ ヴ ;</tRule>
+			<tRule>u ↔ ウ ;</tRule>
+			<comment># w  } $vowel → ウ | '~' ;</comment>
+			<tRule>wa ↔ ワ ;</tRule>
+			<tRule>wi ↔ ヰ ;</tRule>
+			<tRule>wu → ウ ;</tRule>
+			<tRule>we ↔ ヱ ;</tRule>
+			<tRule>wo ↔ ヲ ;</tRule>
+			<tRule>ya ↔ ヤ ;</tRule>
+			<tRule>yi → イ ;</tRule>
+			<tRule>yu ↔ ユ ;</tRule>
+			<tRule>ye → エ ;</tRule>
+			<tRule>yo ↔ ヨ ;</tRule>
+			<comment># double consonants</comment>
+			<comment>#specials</comment>
+			<tRule>s } sh → ッ ;</tRule>
+			<tRule>t } ch → ッ ;</tRule>
+			<comment>#voiced</comment>
+			<tRule>j } j ↔ ッ } $j_start ;</tRule>
+			<tRule>b } b ↔ ッ } [$h_start$f_start] $voice;</tRule>
+			<tRule>d } d ↔ ッ } $t_start $voice;</tRule>
+			<tRule>g } g ↔ ッ } $k_start $voice;</tRule>
+			<tRule>p } p ↔ ッ } [$h_start$f_start] $semivoice;</tRule>
+			<comment># v } v ↔ ッ } [ワヰウヱヲう]  $voice ;</comment>
+			<tRule>z } z ↔ ッ } $s_start $voice;</tRule>
+			<tRule>v } v ↔ ッ } $v_start;</tRule>
+			<comment># normal</comment>
+			<tRule>k } k ↔ ッ } $k_start ;</tRule>
+			<tRule>m } m ↔ ッ } $m_start ;</tRule>
+			<tRule>n } n ↔ ッ } $n_start ;</tRule>
+			<tRule>h } h ↔ ッ } $h_start ;</tRule>
+			<tRule>f } f ↔ ッ } $f_start ;</tRule>
+			<tRule>r } r ↔ ッ } $r_start ;</tRule>
+			<tRule>t } t ↔ ッ } $t_start ;</tRule>
+			<tRule>s } s ↔ ッ } $s_start ;</tRule>
+			<tRule>w } w  ↔ ッ } $w_start;</tRule>
+			<tRule>y } y ↔ ッ } $y_start;</tRule>
+			<comment># completeness</comment>
+			<tRule>x } x → ッ ;</tRule>
+			<tRule>c } k → ッ ;</tRule>
+			<tRule>c } c → ッ ;</tRule>
+			<tRule>c } q → ッ ;</tRule>
+			<tRule>l } l → ッ ;</tRule>
+			<tRule>q } q → ッ ;</tRule>
+			<comment># y } y → ッ ;</comment>
+			<comment># w } w → ッ ;</comment>
+			<comment># prolonged vowel mark. this indicates a doubling of</comment>
+			<comment># the preceding vowel sound</comment>
+			<comment>#a ← a { ー ; # liu</comment>
+			<comment>#e ← e { ー ; # liu</comment>
+			<comment>#i ← i { ー ; # liu</comment>
+			<comment>#o ← o { ー ; # liu</comment>
+			<comment>#u ← u { ー ; # liu</comment>
+			<tRule>$macron ↔ ー ;</tRule>
+			<comment># small forms</comment>
+			<tRule>'~a' ↔ ァ ;</tRule>
+			<tRule>'~i' ↔ ィ ;</tRule>
+			<tRule>'~u' ↔ ゥ ;</tRule>
+			<tRule>'~e' ↔ ェ ;</tRule>
+			<tRule>'~o' ↔ ォ ;</tRule>
+			<tRule>'~tsu' ↔ ッ ;</tRule>
+			<tRule>'~wa' ↔ ヮ ;</tRule>
+			<tRule>'~ya' ↔ ャ ;</tRule>
+			<tRule>'~yi' → ィ ;</tRule>
+			<tRule>'~yu' ↔ ュ ;</tRule>
+			<tRule>'~ye' → ェ ;</tRule>
+			<tRule>'~yo' ↔ ョ ;</tRule>
+			<comment># iteration marks</comment>
+			<comment># TODO: make more accurate</comment>
+			<tRule>j $1 ← sh (y* $vowel) {ヽ$voice ;</tRule>
+			<tRule>dj $1 ← ch (y* $vowel) {ヽ$voice ;</tRule>
+			<tRule>dz $1 ← ts (y* $vowel) {ヽ$voice ;</tRule>
+			<tRule>g $1 ← k (y* $vowel) {ヽ$voice ;</tRule>
+			<tRule>z $1 ← s (y* $vowel) {ヽ$voice ;</tRule>
+			<tRule>d $1 ← t (y* $vowel) {ヽ$voice ;</tRule>
+			<tRule>h $1 ← b (y* $vowel) {ヽ$voice ;</tRule>
+			<tRule>v $1 ← w (y* $vowel) {ヽ$voice ;</tRule>
+			<tRule>sh $1 ← sh (y* $vowel) {ヽ$voice ;</tRule>
+			<tRule>j $1 ← j (y* $vowel) {ヽ$voice ;</tRule>
+			<tRule>ch $1 ← ch (y* $vowel) {ヽ$voice ;</tRule>
+			<tRule>dj $1 ← dj(y* $vowel) {ヽ$voice ;</tRule>
+			<tRule>ts $1 ← ts (y* $vowel) {ヽ$voice ;</tRule>
+			<tRule>dz $1 ← dz (y* $vowel) {ヽ$voice ;</tRule>
+			<tRule>$1 ← ($consonant y* $vowel) {ヽ$voice? ;</tRule>
+			<tRule>$1 ← (.) {ヽ $voice? ; # otherwise repeat last character</tRule>
+			<tRule>← ヽ $voice? ; # delete if no characters found</tRule>
+			<comment># h- rule: lengthens vowel if not followed by a vowel.</comment>
+			<comment># At the point this is applied, latin [cons]?vowel sequences</comment>
+			<comment># have been converted to katakana in NFD form.</comment>
+			<tRule>$voweled_basekana [\u3099 \u309A]? { h → ー ;</tRule>
+			<comment># one-way latin- → kana rules. these do not occur in</comment>
+			<comment># well-formed romaji representing actual japanese text.</comment>
+			<comment># their purpose is to make all romaji map to kana of</comment>
+			<comment># some sort.</comment>
+			<comment># the following are not really necessary, but produce</comment>
+			<comment># slightly more natural results.</comment>
+			<tRule>cy → セィ ;</tRule>
+			<tRule>dy → ディ ;</tRule>
+			<tRule>hy → ヒ ;</tRule>
+			<tRule>sy → セィ ;</tRule>
+			<tRule>ty → ティ ;</tRule>
+			<tRule>zy → ゼィ ;</tRule>
+			<tRule>h → ヘ ;</tRule>
+			<comment># isolated consonants listed here so as not to mask</comment>
+			<comment># longer rules above.</comment>
+			<tRule>ch → チ;</tRule>
+			<tRule>sh → シ ;</tRule>
+			<tRule>dz → ヅ ;</tRule>
+			<tRule>dj → ヂ;</tRule>
+			<tRule>b → ブ ;</tRule>
+			<tRule>d → デ ;</tRule>
+			<tRule>g → グ ;</tRule>
+			<tRule>k → ク ;</tRule>
+			<tRule>m → ム ;</tRule>
+			<tRule>n'' ← ン } $n_quoter ;</tRule>
+			<tRule>n ↔ ン ;</tRule>
+			<tRule>p → プ ;</tRule>
+			<tRule>r → ル ;</tRule>
+			<tRule>s → ス ;</tRule>
+			<tRule>t → テ ;</tRule>
+			<tRule>y → イ ;</tRule>
+			<tRule>z → ズ ;</tRule>
+			<tRule>v → ヴ ;</tRule>
+			<tRule>f → フ;</tRule>
+			<tRule>j  → ジ;</tRule>
+			<tRule>w → ウ;</tRule>
+			<tRule>ß → | ss ;</tRule>
+			<tRule>æ → | e ;</tRule>
+			<tRule>ð → | d ;</tRule>
+			<tRule>ø → | u ;</tRule>
+			<tRule>þ → | th ;</tRule>
+			<comment># simple substitutions using backup</comment>
+			<tRule>c → | k ;</tRule>
+			<tRule>l → | r ;</tRule>
+			<tRule>q → | k ;</tRule>
+			<tRule>x → | ks ;</tRule>
+			<comment># ~~~ END shared rules ~~~</comment>
+			<comment>#------------------------------------------------------</comment>
+			<comment># Final cleanup</comment>
+			<tRule>'~' → ; # delete stray tildes between letters</tRule>
+			<tRule>[:Katakana:] { '' } [:Latin:] → ; # delete stray quotes between letters</tRule>
+			<comment># [ʾ[:Nonspacing Mark:]-[゙-゜]] → ; # delete any non-spacing marks that we didn't use</comment>
+			<tRule>:: NFC (NFD) ;</tRule>
+			<tRule>:: ([[:Katakana:][\u309B\u309C\u30A0\u30FC\uFF70\uFF9E\uFF9F]] halfwidth-fullwidth);</tRule>
+			<comment># note: a global filter is more efficient, but MUST include all source chars!!</comment>
+			<comment>#:: ([\u0000-\u007E 、。 ゙-゜ ァ-ー ｡-ﾟ [:Latin:][:Katakana:] [:nonspacing mark:]]);</comment>
+			<comment># MINIMAL FILTER GENERATED FOR: Latin-Katakana BACKWARD</comment>
+			<tRule>:: ( [[\ -~¢-£¥-¦¬̄₩｡-ﾾￂ-ￇￊ-ￏￒ-ￗￚ-ￜ￨-￮][~、-。がぎぐげござじずぜぞだぢづでどば-ぱび-ぴぶ-ぷべ-ぺぼ-ぽゔ゙-゛ゞァ-ヺー-ヾ][\u309B\u309C\u30A0\u30FC\uFF70\uFF9E\uFF9F]] ) ;</tRule>
+			<comment># eof</comment>
+		</transform>
+	</transforms>
+</supplementalData>
+

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

@@ -0,0 +1,15 @@
+<?xml version="1.0" encoding="UTF-8" ?>
+<!DOCTYPE supplementalData SYSTEM "../../common/dtd/ldmlSupplemental.dtd">
+<supplementalData>
+	<transforms>
+		<transform source="Latin" target="Malayalam" direction="forward">
+			<tRule>::['.0-9A-Za-z~À-ÅÇ-ÏÑ-ÖÙ-Ýà-åç-ïñ-öù-ýÿ-ďĒ-ĥĨ-İĴ-ķĹ-ľŃ-ňŌ-őŔ-ťŨ-žƠ-ơƯ-ưǍ-ǜǞ-ǣǦ-ǭǰǴ-ǵǸ-țȞ-ȟȦ-ȳʔ́̃-̄̆-̇̐̔-̣̥̱́̈́̕΅-ΆΈ-ΊΌΎ-ΐά-ΰό-ώϓЃЌЎЙйѓќўӁ-ӂӐ-ӑӖ-ӗӢ-ӣӮ-ӯḀ-ẙẠ-ỹἁἃ-ἅἇἉἋ-ἍἏἑἓ-ἕἙἛ-Ἕἡἣ-ἥἧἩἫ-ἭἯἱἳ-ἵἷἹἻ-ἽἿὁὃ-ὅὉὋ-Ὅὑὓ-ὕὗὙὛὝὟὡὣ-ὥὧὩὫ-ὭὯάέήίόύώᾁᾃ-ᾅᾇᾉᾋ-ᾍᾏᾑᾓ-ᾕᾗᾙᾛ-ᾝᾟᾡᾣ-ᾥᾧᾩᾫ-ᾭᾯ-ᾱᾴᾸ-ᾹΆῄΈΉ῎ῐ-ῑΐῘ-ῙΊ῞ῠ-ῡΰῥῨ-ῩΎ-Ῥ΅ῴΌΏK-Å\uE04D\uE064];</tRule>
+			<tRule>::NFD;</tRule>
+			<tRule>::Lower;</tRule>
+			<tRule>::Latin-InterIndic;</tRule>
+			<tRule>::InterIndic-Malayalam;</tRule>
+			<tRule>::NFC;</tRule>
+		</transform>
+	</transforms>
+</supplementalData>
+

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

@@ -0,0 +1,36 @@
+<?xml version="1.0" encoding="UTF-8" ?>
+<!DOCTYPE supplementalData SYSTEM "../../common/dtd/ldmlSupplemental.dtd">
+<supplementalData>
+	<transforms>
+		<transform source="Latin" target="NumericPinyin" direction="both">
+			<comment># According to the pinyin definitions I've been able to find:</comment>
+			<comment># 'a', 'e' are the preferred bases</comment>
+			<comment># otherwise 'o'</comment>
+			<comment># otherwise last vowel</comment>
+			<comment># The trailing form of syllables are the following:</comment>
+			<comment>#         &quot;a&quot;, &quot;ai&quot;, &quot;ao&quot;, &quot;an&quot;, &quot;ang&quot;,</comment>
+			<comment>#         &quot;o&quot;, &quot;ou&quot;, &quot;ong&quot;,</comment>
+			<comment>#         &quot;e&quot;, &quot;ei&quot;, &quot;er&quot;, &quot;en&quot;, &quot;eng&quot;,</comment>
+			<comment>#         &quot;i&quot;, &quot;ia&quot;, &quot;iao&quot;, &quot;ie&quot;, &quot;iu&quot;, &quot;ian&quot;, &quot;in&quot;, &quot;iang&quot;, &quot;ing&quot;, &quot;iong&quot;,</comment>
+			<comment>#         &quot;u&quot;, &quot;ua&quot;, &quot;uo&quot;, &quot;uai&quot;, &quot;ui&quot;, &quot;uan&quot;, &quot;un&quot;, &quot;uang&quot;, &quot;ueng&quot;,</comment>
+			<comment>#         &quot;ü&quot;, &quot;üe&quot;, &quot;üan&quot;, &quot;ün&quot;</comment>
+			<comment># so the letters the tone will 'hop' are:</comment>
+			<tRule>::NFD (NFC);</tRule>
+			<tRule>$tone = [̄́̌̀̆] ;</tRule>
+			<comment># Move the tone to the end of a syllable, and convert to number</comment>
+			<tRule>e {($tone) r} → r &amp;Pinyin-NumericPinyin($1);</tRule>
+			<tRule>($tone) ( [i o n u {o n} {n g}]) → $2 &amp;Pinyin-NumericPinyin($1);</tRule>
+			<tRule>($tone) → &amp;Pinyin-NumericPinyin($1);</tRule>
+			<comment># The following backs up until it finds the right vowel, then deposits the tone</comment>
+			<tRule>$vowel = [aAeEiIoOuUüÜ {ü} {Ü} ];</tRule>
+			<tRule>$consonant = [[a-z A-Z] - [$vowel]];</tRule>
+			<tRule>$digit = [1-5];</tRule>
+			<tRule>$1 &amp;NumericPinyin-Pinyin($3) $2 ← ([aAeE]) ($vowel* $consonant*) ($digit);</tRule>
+			<tRule>$1 &amp;NumericPinyin-Pinyin($3) $2 ← ([oO]) ([$vowel-[aeAE]]* $consonant*) ($digit);</tRule>
+			<tRule>$1 &amp;NumericPinyin-Pinyin($3) $2 ← ($vowel) ($consonant*) ($digit);</tRule>
+			<tRule>&amp;NumericPinyin-Pinyin($1) ← [:letter:] {($digit)};</tRule>
+			<tRule>::NFC (NFD);</tRule>
+		</transform>
+	</transforms>
+</supplementalData>
+