Skip to content

Commit 0dfc59e

Browse files
committed
CLDR-18041 baseline for sample data for transform variant
includes whitespace fixes previously merged
1 parent e345b60 commit 0dfc59e

File tree

374 files changed

+0
-748
lines changed

Some content is hidden

Large Commits have some content hidden by default. Use the searchbox below for content that may be hidden.

374 files changed

+0
-748
lines changed

cldr-json/cldr-transforms/transforms/Amharic-Latin-BGN.txt

-2
Original file line numberDiff line numberDiff line change
@@ -1,4 +1,3 @@
1-
21
########################################################################
32
# BGN/PCGN 1967 System
43
#
@@ -438,4 +437,3 @@ $wordBoundary{ኧ → e ; # ETHIOPIC SYLLABLE GLOTTAL WA
438437
፹ → 80 ; # ETHIOPIC NUMBER EIGHTY
439438
፺ → 90 ; # ETHIOPIC NUMBER NINETY
440439
፻ → 100 ; # ETHIOPIC NUMBER HUNDRED
441-

cldr-json/cldr-transforms/transforms/Any-Accents.txt

-2
Original file line numberDiff line numberDiff line change
@@ -1,4 +1,3 @@
1-
21
:: NFD (NFC) ;
32
# to do: make reversible
43
# define special conversion characters.
@@ -267,4 +266,3 @@ $pre v $post ↔ ʌ ; # LATIN SMALL LETTER TURNED V
267266
# $pre YYY $post ↔ ẚ ; # LATIN SMALL LETTER A WITH RIGHT HALF RING
268267
# $pre YYY $post ↔ ⁿ ; # SUPERSCRIPT LATIN SMALL LETTER N
269268
:: NFC (NFD) ;
270-

cldr-json/cldr-transforms/transforms/Any-Publishing.txt

-2
Original file line numberDiff line numberDiff line change
@@ -1,4 +1,3 @@
1-
21
# Variables
32
$single = \' ;
43
$space = ' ' ;
@@ -60,4 +59,3 @@ $space {$space} → ;
6059
[^0-9] {3\/8} [^0-9] ↔ ⅜;
6160
[^0-9] {5\/8} [^0-9] ↔ ⅝;
6261
[^0-9] {7\/8} [^0-9] ↔ ⅞;
63-

cldr-json/cldr-transforms/transforms/Arabic-Latin-BGN.txt

-2
Original file line numberDiff line numberDiff line change
@@ -1,4 +1,3 @@
1-
21
#
32
########################################################################
43
# BGN/PCGN 1956 System
@@ -202,4 +201,3 @@ $wordBoundary{آ → ā ; # ARABIC LETTER ALEF WITH MADDA ABOVE
202201
#
203202
#
204203
########################################################################
205-

cldr-json/cldr-transforms/transforms/Arabic-Latin.txt

-2
Original file line numberDiff line numberDiff line change
@@ -1,4 +1,3 @@
1-
21
# Generally follows UNGEGN
32
# http://www.eki.ee/wgrs/rom1_ar.pdf
43
# Occasionally deviates in the direction of ISO 233
@@ -178,4 +177,3 @@ $notAbove = [[:^ccc=0:] & [:^ccc=230:]];
178177
:: (lower) ;
179178
::NFC (NFD);
180179
:: ( [[:Latin:] [%,.0-9;?ʾ-ʿ̂-̄̈-̣̰̊-̱̹;ˌ]] );
181-

cldr-json/cldr-transforms/transforms/Armenian-Latin-BGN.txt

-2
Original file line numberDiff line numberDiff line change
@@ -1,4 +1,3 @@
1-
21
# BGN/PCGN 1981 System
32
#
43
# The BGN/PCGN system for Armenian was designed for use in romanizing
@@ -162,4 +161,3 @@ $wordBoundary{ո → vo ; # ARMENIAN SMALL LETTER VO
162161
Ֆ → F ; # ARMENIAN CAPITAL LETTER FEH
163162
ֆ → f ; # ARMENIAN SMALL LETTER FEH
164163
։ → \. ; # ARMENIAN FULL STOP
165-

cldr-json/cldr-transforms/transforms/Azerbaijani-Latin-BGN.txt

-2
Original file line numberDiff line numberDiff line change
@@ -1,4 +1,3 @@
1-
21
#
32
########################################################################
43
# BGN/PCGN 1993 Agreement
@@ -180,4 +179,3 @@ $lower = [$lowerConsonants $lowerVowels] ;
180179
# End BGN Page 14 Note 2.
181180
#
182181
########################################################################
183-

cldr-json/cldr-transforms/transforms/Belarusian-Latin-BGN.txt

-2
Original file line numberDiff line numberDiff line change
@@ -1,4 +1,3 @@
1-
21
# BGN/PCGN 1979 System
32
#
43
# The BGN/PCGN system for Belarusian (formerly Byelorussian) was
@@ -191,4 +190,3 @@ $wordBoundary = [^[:L:][:M:][:N:]] ;
191190
########################################################################
192191
Ґ → G ; # CYRILLIC CAPITAL LETTER GHE WITH UPTURN
193192
ґ → g ; # CYRILLIC SMALL LETTER GHE WITH UPTURN
194-
Original file line numberDiff line numberDiff line change
@@ -1,7 +1,5 @@
1-
21
::[।-॥ঁ-ঃঅ-ঌএ-ঐও-নপ-রলশ-হ়-ৄে-ৈো-্ৗড়-ঢ়য়-ৣ০-৺ৎ];
32
::NFD;
43
::Bengali-InterIndic;
54
::InterIndic-Arabic;
65
::NFC;
7-
Original file line numberDiff line numberDiff line change
@@ -1,7 +1,5 @@
1-
21
::[।-॥ঁ-ঃঅ-ঌএ-ঐও-নপ-রলশ-হ়-ৄে-ৈো-্ৗড়-ঢ়য়-ৣ০-৺ৎ];
32
::NFD;
43
::Bengali-InterIndic;
54
::InterIndic-Devanagari;
65
::NFC;
7-
Original file line numberDiff line numberDiff line change
@@ -1,7 +1,5 @@
1-
21
::[।-॥ঁ-ঃঅ-ঌএ-ঐও-নপ-রলশ-হ়-ৄে-ৈো-্ৗড়-ঢ়য়-ৣ০-৺ৎ];
32
::NFD;
43
::Bengali-InterIndic;
54
::InterIndic-Gujarati;
65
::NFC;
7-
Original file line numberDiff line numberDiff line change
@@ -1,7 +1,5 @@
1-
21
::[।-॥ঁ-ঃঅ-ঌএ-ঐও-নপ-রলশ-হ়-ৄে-ৈো-্ৗড়-ঢ়য়-ৣ০-৺ৎ];
32
::NFD;
43
::Bengali-InterIndic;
54
::InterIndic-Gurmukhi;
65
::NFC;
7-

cldr-json/cldr-transforms/transforms/Bengali-InterIndic.txt

-2
Original file line numberDiff line numberDiff line change
@@ -1,4 +1,3 @@
1-
21
# Bengali-InterIndic
32
ো→\uE04B; # VOWEL SIGN O
43
ৌ→\uE04C; # VOWEL SIGN AU
@@ -96,4 +95,3 @@
9695
॥→\uE065; # DOUBLE DANDA
9796
# :: NFC (NFD) ;
9897
# eof
99-
Original file line numberDiff line numberDiff line change
@@ -1,7 +1,5 @@
1-
21
::[।-॥ঁ-ঃঅ-ঌএ-ঐও-নপ-রলশ-হ়-ৄে-ৈো-্ৗড়-ঢ়য়-ৣ০-৺ৎ];
32
::NFD;
43
::Bengali-InterIndic;
54
::InterIndic-Kannada;
65
::NFC;
7-
Original file line numberDiff line numberDiff line change
@@ -1,7 +1,5 @@
1-
21
::[[:script=bengali:][।-॥ঁ-ঃঅ-ঌএ-ঐও-নপ-রলশ-হ়-ৄে-ৈো-্ৗড়-ঢ়য়-ৣ০-৺ৎ]];
32
::NFD;
43
::Bengali-InterIndic;
54
::InterIndic-Latin;
65
::NFC;
7-
Original file line numberDiff line numberDiff line change
@@ -1,7 +1,5 @@
1-
21
::[।-॥ঁ-ঃঅ-ঌএ-ঐও-নপ-রলশ-হ়-ৄে-ৈো-্ৗড়-ঢ়য়-ৣ০-৺ৎ];
32
::NFD;
43
::Bengali-InterIndic;
54
::InterIndic-Malayalam;
65
::NFC;
7-
Original file line numberDiff line numberDiff line change
@@ -1,7 +1,5 @@
1-
21
::[।-॥ঁ-ঃঅ-ঌএ-ঐও-নপ-রলশ-হ়-ৄে-ৈো-্ৗড়-ঢ়য়-ৣ০-৺ৎ];
32
::NFD;
43
::Bengali-InterIndic;
54
::InterIndic-Oriya;
65
::NFC;
7-
Original file line numberDiff line numberDiff line change
@@ -1,7 +1,5 @@
1-
21
::[।-॥ঁ-ঃঅ-ঌএ-ঐও-নপ-রলশ-হ়-ৄে-ৈো-্ৗড়-ঢ়য়-ৣ০-৺ৎ];
32
::NFD;
43
::Bengali-InterIndic;
54
::InterIndic-Tamil;
65
::NFC;
7-
Original file line numberDiff line numberDiff line change
@@ -1,7 +1,5 @@
1-
21
::[।-॥ঁ-ঃঅ-ঌএ-ঐও-নপ-রলশ-হ়-ৄে-ৈো-্ৗড়-ঢ়য়-ৣ০-৺ৎ];
32
::NFD;
43
::Bengali-InterIndic;
54
::InterIndic-Telugu;
65
::NFC;
7-
Original file line numberDiff line numberDiff line change
@@ -1,7 +1,5 @@
1-
21
::[।-॥ঁ-ঃঅ-ঌএ-ঐও-নপ-রলশ-হ়-ৄে-ৈো-্ৗড়-ঢ়য়-ৣ০-৺ৎ];
32
::NFD;
43
::Bengali-InterIndic;
54
::InterIndic-ur;
65
::NFC;
7-

cldr-json/cldr-transforms/transforms/Bulgarian-Latin-BGN.txt

-2
Original file line numberDiff line numberDiff line change
@@ -1,4 +1,3 @@
1-
21
#
32
########################################################################
43
# BGN/PCGN 1952 System
@@ -234,4 +233,3 @@ $bulgarian { [Ъъ] } $wordBoundary > ;
234233
# End BGN Page 16 Note 3
235234
#
236235
########################################################################
237-

cldr-json/cldr-transforms/transforms/CanadianAboriginal-Latin.txt

-2
Original file line numberDiff line numberDiff line change
@@ -1,4 +1,3 @@
1-
21
šwê ↔ ᔗ ;
32
šwî ↔ ᔛ ;
43
šwi ↔ ᔙ ;
@@ -181,4 +180,3 @@ hâ ↔ ᐋ ;
181180
ha ↔ ᐊ ;
182181
h ↔ ᐦ ;
183182
'.' ↔ ᙮ ;
184-

cldr-json/cldr-transforms/transforms/Cyrillic-Latin.txt

-2
Original file line numberDiff line numberDiff line change
@@ -1,4 +1,3 @@
1-
21
# TODO: add remaining characters
32
# Should add variants for Russian-English, Russian-German
43
# Those can use this as a base, and then remap cases
@@ -277,4 +276,3 @@ $ignore = [[:Mark:]''] * ;
277276
# :: ([\u0000-\u007E ʹ ʺ [:Cyrillic:] [:Latin:] [:nonspacing mark:] ‧]);
278277
# MINIMAL FILTER: Latin-Cyrillic
279278
:: ( [ḫḪhH‧ˌ̈A-Za-zÀ-ÏÑ-ÖÙ-Ýà-ïñ-öù-ýÿ-ĥĨ-İĴ-ķĹ-ľŃ-ňŌ-őŔ-ťŨ-žƏƠ-ơƯ-ưǍ-ǜǞ-ǣǦ-ǰǴ-ǵǸ-țȞ-ȟȦ-ȳəʹ-ʺ̀-̂̆-̦̱̇̌̀-́̈́ʹ΅-ΆΈ-ΊΌΎ-ΐά-ΰό-ώϓЀЃЌ-ЎЙйѐѓќ-ўӁ-ӂӐ-ӑӖ-ӗḀ-ẙẛẠ-ỹἂ-ἅἊ-Ἅἒ-ἕἚ-Ἕἢ-ἥἪ-Ἥἲ-ἵἺ-Ἵὂ-ὅὊ-Ὅὒ-ὕὛὝὢ-ὥὪ-Ὥὰ-ώᾂ-ᾅᾊ-ᾍᾒ-ᾕᾚ-ᾝᾢ-ᾥᾪ-ᾭᾰᾲᾴᾸᾺ-ΆῂῄῈ-Ή῍-῎ῐῒ-ΐῘῚ-Ί῝-῞ῠῢ-ΰῨῪ-Ύ῭-΅ῲῴῸ-ΏK-Å] ) ;
280-
Original file line numberDiff line numberDiff line change
@@ -1,7 +1,5 @@
1-
21
::[ँ-ःऄअ-ह़-्ॐ-॔क़-९ॽ];
32
::NFD;
43
::Devanagari-InterIndic;
54
::InterIndic-Arabic;
65
::NFC;
7-
Original file line numberDiff line numberDiff line change
@@ -1,7 +1,5 @@
1-
21
::[ँ-ःऄअ-ह़-्ॐ-॔क़-९ॽ];
32
::NFD;
43
::Devanagari-InterIndic;
54
::InterIndic-Bengali;
65
::NFC;
7-
Original file line numberDiff line numberDiff line change
@@ -1,7 +1,5 @@
1-
21
::[ँ-ःऄअ-ह़-्ॐ-॔क़-९ॽ];
32
::NFD;
43
::Devanagari-InterIndic;
54
::InterIndic-Gujarati;
65
::NFC;
7-
Original file line numberDiff line numberDiff line change
@@ -1,7 +1,5 @@
1-
21
::[ँ-ःऄअ-ह़-्ॐ-॔क़-९ॽ];
32
::NFD;
43
::Devanagari-InterIndic;
54
::InterIndic-Gurmukhi;
65
::NFC;
7-

cldr-json/cldr-transforms/transforms/Devanagari-InterIndic.txt

-2
Original file line numberDiff line numberDiff line change
@@ -1,4 +1,3 @@
1-
21
# Devanagari-InterIndic
32
# :: NFD;
43
#Rules for Decomposed characters
@@ -110,4 +109,3 @@
110109
ॽ→\uE082; # Devanagari Glottal Stop
111110
ॲ→\uE084; # https://en.wiktionary.org/wiki/%E0%A5%B2
112111
# :: NFC (NFD) ;
113-
Original file line numberDiff line numberDiff line change
@@ -1,7 +1,5 @@
1-
21
::[ँ-ःऄअ-ह़-्ॐ-॔क़-९ॽ];
32
::NFD;
43
::Devanagari-InterIndic;
54
::InterIndic-Kannada;
65
::NFC;
7-
Original file line numberDiff line numberDiff line change
@@ -1,7 +1,5 @@
1-
21
::[॑ ॒ ॔ ॓ ़ ँ-ः । ॥ ॰ ०-९ ॐ ॲ ऄ-ऋ ॠ ऌ ॡ ऍ-कक़ खख़ गग़ घ-जज़ झ-डड़ ढढ़ ण-फफ़ ब-यय़ र-ह ऽ ॽ ा-ॄ ॢ ॣ ॅ-्];
32
::NFD;
43
::Devanagari-InterIndic;
54
::InterIndic-Latin;
65
::NFC;
7-
Original file line numberDiff line numberDiff line change
@@ -1,7 +1,5 @@
1-
21
::[ँ-ःऄअ-ह़-्ॐ-॔क़-९ॽ];
32
::NFD;
43
::Devanagari-InterIndic;
54
::InterIndic-Malayalam;
65
::NFC;
7-
Original file line numberDiff line numberDiff line change
@@ -1,7 +1,5 @@
1-
21
::[ँ-ःऄअ-ह़-्ॐ-॔क़-९ॽ];
32
::NFD;
43
::Devanagari-InterIndic;
54
::InterIndic-Oriya;
65
::NFC;
7-
Original file line numberDiff line numberDiff line change
@@ -1,7 +1,5 @@
1-
21
::[ँ-ःऄअ-ह़-्ॐ-॔क़-९ॽ];
32
::NFD;
43
::Devanagari-InterIndic;
54
::InterIndic-Tamil;
65
::NFC;
7-
Original file line numberDiff line numberDiff line change
@@ -1,7 +1,5 @@
1-
21
::[ँ-ःऄअ-ह़-्ॐ-॔क़-९ॽ];
32
::NFD;
43
::Devanagari-InterIndic;
54
::InterIndic-Telugu;
65
::NFC;
7-
Original file line numberDiff line numberDiff line change
@@ -1,7 +1,5 @@
1-
21
::[ँ-ःऄअ-ह़-्ॐ-॔क़-९ॽ];
32
::NFD;
43
::Devanagari-InterIndic;
54
::InterIndic-ur;
65
::NFC;
7-

cldr-json/cldr-transforms/transforms/Fullwidth-Halfwidth.txt

-2
Original file line numberDiff line numberDiff line change
@@ -1,4 +1,3 @@
1-
21
# Fullwidth-Halfwidth
32
# Mechanically generated from Unicode Character Database
43
# IDEOGRAPHIC SPACE then added, and
@@ -258,4 +257,3 @@
258257
■↔■; # to HALFWIDTH BLACK SQUARE
259258
○↔○; # to HALFWIDTH WHITE CIRCLE
260259
# eof
261-

cldr-json/cldr-transforms/transforms/Georgian-Latin-BGN.txt

-2
Original file line numberDiff line numberDiff line change
@@ -1,4 +1,3 @@
1-
21
# BGN/PCGN 2009 System
32
#
43
# The BGN/PCGN system for Georgian was designed for use in romanizing
@@ -40,4 +39,3 @@
4039
ხ → kh;
4140
ჯ → j;
4241
ჰ → h;
43-

cldr-json/cldr-transforms/transforms/Georgian-Latin-BGN_1981.txt

-2
Original file line numberDiff line numberDiff line change
@@ -1,4 +1,3 @@
1-
21
########################################################################
32
# BGN/PCGN 1981 System
43
#
@@ -51,4 +50,3 @@ $wordBoundary = [^[:L:][:M:][:N:]] ;
5150
ხ → kh ; # GEORGIAN LETTER XAN
5251
ჯ → j ; # GEORGIAN LETTER JHAN
5352
ჰ → h ; # GEORGIAN LETTER HAE
54-

cldr-json/cldr-transforms/transforms/Georgian-Latin.txt

-2
Original file line numberDiff line numberDiff line change
@@ -1,4 +1,3 @@
1-
21
# long items moved up
32
წ ↔ tsʼ ;
43
კ ↔ kʼ ;
@@ -50,4 +49,3 @@
5049
ჰ ↔ h ;
5150
#ჳ ↔ ŭi ;
5251
ჴ ↔ q ;
53-

cldr-json/cldr-transforms/transforms/Greek-Latin-BGN.txt

-2
Original file line numberDiff line numberDiff line change
@@ -1,4 +1,3 @@
1-
21
#
32
########################################################################
43
# BGN/PCGN 1962 System
@@ -416,4 +415,3 @@ $wordBoundary{ντ → d ; # GREEK SMALL LETTER NU + SMALL TAU
416415
#
417416
#
418417
########################################################################
419-

cldr-json/cldr-transforms/transforms/Greek-Latin.txt

-2
Original file line numberDiff line numberDiff line change
@@ -1,4 +1,3 @@
1-
21
# Rules are predicated on running NFD first, and NFC afterwards
32
# :: [\u0000-\u007F \u0370-Ͽ [:Greek:] [:nonspacing mark:]] ;
43
# MINIMAL FILTER GENERATED FOR: Greek-Latin
@@ -248,4 +247,3 @@ $rough ↔ h ;
248247
# ([\u0000-\u007F · [:Latin:] [:nonspacing mark:]]) ;
249248
# MINIMAL FILTER GENERATED FOR: Latin-Greek BACKWARD
250249
:: ( [':?A-Za-zÀ-ÅÇ-ÏÑ-ÖÙ-Ýà-åç-ïñ-öù-ýÿ-ďĒ-ĥĨ-İĴ-ķĹ-ľŃ-ňŌ-őŔ-ťŨ-žƠ-ơƯ-ưǍ-ǜǞ-ǣǦ-ǰǴ-ǵǸ-țȞ-ȟȦ-ȳ̀-̷̹-ͅ΅-ΆΈ-ΊΌΎ-ΐΪ-ΰϊ-ώϓ-ϔЀ-ЁЃЇЌ-ЎЙйѐ-ёѓїќ-ўѶ-ѷӁ-ӂӐ-ӓӖ-ӗӚ-ӟӢ-ӧӪ-ӵӸ-ӹḀ-ẙẛẠ-ỹἀ-ἕἘ-Ἕἠ-ὅὈ-Ὅὐ-ὗὙὛὝὟ-ώᾀ-ᾴᾶ-ᾼ῁-ῄῆ-ΐῖ-Ί῝-΅ῲ-ῴῶ-ῼK-Å] ) ;
251-

cldr-json/cldr-transforms/transforms/Greek_Latin_UNGEGN.txt

-2
Original file line numberDiff line numberDiff line change
@@ -1,4 +1,3 @@
1-
21
# For modern Greek, based on UNGEGN rules.
32
# Rules are predicated on running NFD first, and NFC afterwards
43
# MINIMAL FILTER GENERATED FOR: Greek-Latin/UNGEGN
@@ -176,4 +175,3 @@ $afterLetter { ς ↔ $afterLetter { s ;
176175
::NFC (NFD) ;
177176
# MINIMAL FILTER GENERATED FOR: Latin-Greek/UNGEGN BACKWARD
178177
:: ([[[:Latin:][:Mn:][:Me:]] ['\:?]]) ;
179-
Original file line numberDiff line numberDiff line change
@@ -1,7 +1,5 @@
1-
21
::[।-॥ઁ-ઃઅ-ઍએ-ઑઓ-નપ-રલ-ળવ-હ઼-ૅે-ૉો-્ૐૠૡ૦-૯];
32
::NFD;
43
::Gujarati-InterIndic;
54
::InterIndic-Arabic;
65
::NFC;
7-
Original file line numberDiff line numberDiff line change
@@ -1,7 +1,5 @@
1-
21
::[।-॥ઁ-ઃઅ-ઍએ-ઑઓ-નપ-રલ-ળવ-હ઼-ૅે-ૉો-્ૐૠૡ૦-૯];
32
::NFD;
43
::Gujarati-InterIndic;
54
::InterIndic-Bengali;
65
::NFC;
7-
Original file line numberDiff line numberDiff line change
@@ -1,7 +1,5 @@
1-
21
::[।-॥ઁ-ઃઅ-ઍએ-ઑઓ-નપ-રલ-ળવ-હ઼-ૅે-ૉો-્ૐૠૡ૦-૯];
32
::NFD;
43
::Gujarati-InterIndic;
54
::InterIndic-Devanagari;
65
::NFC;
7-

0 commit comments

Comments
 (0)