organicmaps/icu
13
Fork 0
mirror of https://github.com/unicode-org/icu.git synced 2025-04-18 19:25:49 +00:00
Code Issues 1 Projects Releases Wiki Activity Actions 8

ICU-10706 Spoof Check data update.

Browse source 
X-SVN-Rev: 35164
This commit is contained in:
Andy Heninger 2014-02-19 01:07:32 +00:00
parent a5986fe48d
commit 8525e6bd47
7 changed files with 265 additions and 134 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

54
icu4c/source/data/unidata/confusables.txt
View file

@ -1,8 +1,8 @@
# Recommended confusable mapping for IDN
# File: confusables.txt
# Version: 3.0-draft
# Generated: 2012-07-17, 21:27:33 GMT
# Checkin: $Revision: 1580 $
# Version: 6.3.0
# Generated: 2013-11-13, 00:04:57 GMT
# Checkin: $Revision: 1.32 $
#
# For documentation and usage, see http://www.unicode.org/reports/tr39/
#
@ -131,7 +131,6 @@ FC63 ; FE7C 0670 ; SL #* ( ‎ﱣ‎ → ‎ﹼٰ‎ ) ARABIC LIGATURE SHADDA WI
309C ; FF9F ; SL #* ( ゜ → ﾟ ) KATAKANA-HIRAGANA SEMI-VOICED SOUND MARK → HALFWIDTH KATAKANA SEMI-VOICED SOUND MARK #
180E ; 0020 ; SL #* ( ᠎ → ) MONGOLIAN VOWEL SEPARATOR → SPACE #
2028 ; 0020 ; SL #* ( → ) LINE SEPARATOR → SPACE #
2029 ; 0020 ; SL #* ( → ) PARAGRAPH SEPARATOR → SPACE #
1680 ; 0020 ; SL #* (   → ) OGHAM SPACE MARK → SPACE #
@ -1891,6 +1890,8 @@ FF50 ; 0070 ; SL # ( ｐ → p ) FULLWIDTH LATIN SMALL LETTER P → LATIN SMALL
1D0D ; 0072 006E ; SL # ( ᴍ → rn ) LATIN LETTER SMALL CAPITAL M → LATIN SMALL LETTER R, LATIN SMALL LETTER N # →м→→m→
028D ; 0072 006E ; SL # ( ʍ → rn ) LATIN SMALL LETTER TURNED W → LATIN SMALL LETTER R, LATIN SMALL LETTER N # →m→
20A5 ; 0072 006E 0338 ; SL #* ( ₥ → rn̸ ) MILL SIGN → LATIN SMALL LETTER R, LATIN SMALL LETTER N, COMBINING LONG SOLIDUS OVERLAY # →m̷→
0271 ; 0072 006E 0326 ; SL # ( ɱ → rn̦ ) LATIN SMALL LETTER M WITH HOOK → LATIN SMALL LETTER R, LATIN SMALL LETTER N, COMBINING COMMA BELOW # →m̡→
2129 ; 027F ; SL #* ( ℩ → ɿ ) TURNED GREEK SMALL LETTER IOTA → LATIN SMALL LETTER REVERSED R WITH FISHHOOK #
@ -2230,6 +2231,8 @@ A76B ; 021D ; SL # ( ꝫ → ȝ ) LATIN SMALL LETTER ET → LATIN SMALL LETTER Y
0491 ; 0433 02C8 ; SL # ( ґ → гˈ ) CYRILLIC SMALL LETTER GHE WITH UPTURN → CYRILLIC SMALL LETTER GHE, MODIFIER LETTER VERTICAL LINE #
04BD ; 0435 ; SL # ( ҽ → е ) CYRILLIC SMALL LETTER ABKHASIAN CHE → CYRILLIC SMALL LETTER IE # →e→
0511 ; 0454 ; SL # ( ԑ → є ) CYRILLIC SMALL LETTER REVERSED ZE → CYRILLIC SMALL LETTER UKRAINIAN IE # →ε→
0497 ; 0436 0329 ; SL # ( җ → ж̩ ) CYRILLIC SMALL LETTER ZHE WITH DESCENDER → CYRILLIC SMALL LETTER ZHE, COMBINING VERTICAL LINE BELOW #
@ -2274,7 +2277,7 @@ A76B ; 021D ; SL # ( ꝫ → ȝ ) LATIN SMALL LETTER ET → LATIN SMALL LETTER Y
04CC ; 04B7 ; SL # ( ӌ → ҷ ) CYRILLIC SMALL LETTER KHAKASSIAN CHE → CYRILLIC SMALL LETTER CHE WITH DESCENDER #
04BF ; 04BD 0328 ; SL # ( ҿ → ҽ̨ ) CYRILLIC SMALL LETTER ABKHASIAN CHE WITH DESCENDER → CYRILLIC SMALL LETTER ABKHASIAN CHE, COMBINING OGONEK # →ҽ̢→
04BF ; 04BD 0322 ; SL # ( ҿ → ҽ̢ ) CYRILLIC SMALL LETTER ABKHASIAN CHE WITH DESCENDER → CYRILLIC SMALL LETTER ABKHASIAN CHE, COMBINING RETROFLEX HOOK BELOW #
0463 ; 048D ; SL # ( ѣ → ҍ ) CYRILLIC SMALL LETTER YAT → CYRILLIC SMALL LETTER SEMISOFT SIGN #
@ -4195,7 +4198,7 @@ AA56 ; AA23 ; SL # ( ꩖ → ꨣ ) CHAM DIGIT SIX → CHAM LETTER RA #
14CC ; 14C7 00B7 ; SL # ( ᓌ → ᓇ· ) CANADIAN SYLLABICS WEST-CREE NWA → CANADIAN SYLLABICS NA, MIDDLE DOT # →ᓇᐧ→
14CE ; 14C8 14AB ; SL # ( ᓎ → ᓈᒫ ) CANADIAN SYLLABICS WEST-CREE NWAA → CANADIAN SYLLABICS NAA, CANADIAN SYLLABICS MAA #
14CE ; 14C8 00B7 ; SL # ( ᓎ → ᓈ· ) CANADIAN SYLLABICS WEST-CREE NWAA → CANADIAN SYLLABICS NAA, MIDDLE DOT # →ᓈᐧ→
1604 ; 14D3 ; SL # ( ᘄ → ᓓ ) CANADIAN SYLLABICS CARRIER NE → CANADIAN SYLLABICS LE #
@ -7631,7 +7634,7 @@ FAD7 ; 27ED3 ; SL # ( 𧻓 → 𧻓 ) CJK COMPATIBILITY IDEOGRAPH-FAD7 → CJK UN
2FA1D ; 2A600 ; SL # ( 𪘀 → 𪘀 ) CJK COMPATIBILITY IDEOGRAPH-2FA1D → CJK UNIFIED IDEOGRAPH-2A600 #
# total for (SL): 4918
# total for (SL): 4919
# Single-Script, Anycase Confusables
@ -7759,7 +7762,6 @@ FC63 ; FE7C 0670 ; SA #* ( ‎ﱣ‎ → ‎ﹼٰ‎ ) ARABIC LIGATURE SHADDA WI
309C ; FF9F ; SA #* ( ゜ → ﾟ ) KATAKANA-HIRAGANA SEMI-VOICED SOUND MARK → HALFWIDTH KATAKANA SEMI-VOICED SOUND MARK #
180E ; 0020 ; SA #* ( ᠎ → ) MONGOLIAN VOWEL SEPARATOR → SPACE #
2028 ; 0020 ; SA #* ( → ) LINE SEPARATOR → SPACE #
2029 ; 0020 ; SA #* ( → ) PARAGRAPH SEPARATOR → SPACE #
1680 ; 0020 ; SA #* (   → ) OGHAM SPACE MARK → SPACE #
@ -10039,6 +10041,8 @@ FF30 ; 0050 ; SA # ( Ｐ → P ) FULLWIDTH LATIN CAPITAL LETTER P → LATIN CAPI
1D0D ; 0072 006E ; SA # ( ᴍ → rn ) LATIN LETTER SMALL CAPITAL M → LATIN SMALL LETTER R, LATIN SMALL LETTER N # →м→→m→
028D ; 0072 006E ; SA # ( ʍ → rn ) LATIN SMALL LETTER TURNED W → LATIN SMALL LETTER R, LATIN SMALL LETTER N # →m→
20A5 ; 0072 006E 0338 ; SA #* ( ₥ → rn̸ ) MILL SIGN → LATIN SMALL LETTER R, LATIN SMALL LETTER N, COMBINING LONG SOLIDUS OVERLAY # →m̷→
0271 ; 0072 006E 0326 ; SA # ( ɱ → rn̦ ) LATIN SMALL LETTER M WITH HOOK → LATIN SMALL LETTER R, LATIN SMALL LETTER N, COMBINING COMMA BELOW # →m̡→
20A8 ; 0052 0073 ; SA #* ( ₨ → Rs ) RUPEE SIGN → LATIN CAPITAL LETTER R, LATIN SMALL LETTER S #
@ -10601,6 +10605,8 @@ FF3A ; 005A ; SA # ( Ｚ → Z ) FULLWIDTH LATIN CAPITAL LETTER Z → LATIN CAPI
0490 ; 0413 02C8 ; SA # ( Ґ → Гˈ ) CYRILLIC CAPITAL LETTER GHE WITH UPTURN → CYRILLIC CAPITAL LETTER GHE, MODIFIER LETTER VERTICAL LINE #
04BD ; 0435 ; SA # ( ҽ → е ) CYRILLIC SMALL LETTER ABKHASIAN CHE → CYRILLIC SMALL LETTER IE # →e→
0511 ; 0454 ; SA # ( ԑ → є ) CYRILLIC SMALL LETTER REVERSED ZE → CYRILLIC SMALL LETTER UKRAINIAN IE # →ε→
0497 ; 0436 0329 ; SA # ( җ → ж̩ ) CYRILLIC SMALL LETTER ZHE WITH DESCENDER → CYRILLIC SMALL LETTER ZHE, COMBINING VERTICAL LINE BELOW #
@ -10679,10 +10685,10 @@ FF3A ; 005A ; SA # ( Ｚ → Z ) FULLWIDTH LATIN CAPITAL LETTER Z → LATIN CAPI
04CB ; 04B6 ; SA # ( Ӌ → Ҷ ) CYRILLIC CAPITAL LETTER KHAKASSIAN CHE → CYRILLIC CAPITAL LETTER CHE WITH DESCENDER #
04BF ; 04BD 0328 ; SA # ( ҿ → ҽ̨ ) CYRILLIC SMALL LETTER ABKHASIAN CHE WITH DESCENDER → CYRILLIC SMALL LETTER ABKHASIAN CHE, COMBINING OGONEK # →ҽ̢→
04BE ; 04BC 0328 ; SA # ( Ҿ → Ҽ̨ ) CYRILLIC CAPITAL LETTER ABKHASIAN CHE WITH DESCENDER → CYRILLIC CAPITAL LETTER ABKHASIAN CHE, COMBINING OGONEK #
04BF ; 04BD 0322 ; SA # ( ҿ → ҽ̢ ) CYRILLIC SMALL LETTER ABKHASIAN CHE WITH DESCENDER → CYRILLIC SMALL LETTER ABKHASIAN CHE, COMBINING RETROFLEX HOOK BELOW #
048D ; 042C 0335 ; SA # ( ҍ → Ь̵ ) CYRILLIC SMALL LETTER SEMISOFT SIGN → CYRILLIC CAPITAL LETTER SOFT SIGN, COMBINING SHORT STROKE OVERLAY # →ѣ→
048C ; 042C 0335 ; SA # ( Ҍ → Ь̵ ) CYRILLIC CAPITAL LETTER SEMISOFT SIGN → CYRILLIC CAPITAL LETTER SOFT SIGN, COMBINING SHORT STROKE OVERLAY # →Ѣ→
0463 ; 042C 0335 ; SA # ( ѣ → Ь̵ ) CYRILLIC SMALL LETTER YAT → CYRILLIC CAPITAL LETTER SOFT SIGN, COMBINING SHORT STROKE OVERLAY #
@ -12242,7 +12248,7 @@ AA56 ; AA23 ; SA # ( ꩖ → ꨣ ) CHAM DIGIT SIX → CHAM LETTER RA #
14CC ; 14C7 00B7 ; SA # ( ᓌ → ᓇ· ) CANADIAN SYLLABICS WEST-CREE NWA → CANADIAN SYLLABICS NA, MIDDLE DOT # →ᓇᐧ→
14CE ; 14C8 14AB ; SA # ( ᓎ → ᓈᒫ ) CANADIAN SYLLABICS WEST-CREE NWAA → CANADIAN SYLLABICS NAA, CANADIAN SYLLABICS MAA #
14CE ; 14C8 00B7 ; SA # ( ᓎ → ᓈ· ) CANADIAN SYLLABICS WEST-CREE NWAA → CANADIAN SYLLABICS NAA, MIDDLE DOT # →ᓈᐧ→
1604 ; 14D3 ; SA # ( ᘄ → ᓓ ) CANADIAN SYLLABICS CARRIER NE → CANADIAN SYLLABICS LE #
@ -15636,7 +15642,7 @@ FAD7 ; 27ED3 ; SA # ( 𧻓 → 𧻓 ) CJK COMPATIBILITY IDEOGRAPH-FAD7 → CJK UN
2FA1D ; 2A600 ; SA # ( 𪘀 → 𪘀 ) CJK COMPATIBILITY IDEOGRAPH-2FA1D → CJK UNIFIED IDEOGRAPH-2A600 #
# total for (SA): 5145
# total for (SA): 5146
# Mixed-Script, Lowercase Confusables
@ -15779,7 +15785,6 @@ FC63 ; FE7C 0670 ; ML #* ( ‎ﱣ‎ → ‎ﹼٰ‎ ) ARABIC LIGATURE SHADDA WI
309C ; FF9F ; ML #* ( ゜ → ﾟ ) KATAKANA-HIRAGANA SEMI-VOICED SOUND MARK → HALFWIDTH KATAKANA SEMI-VOICED SOUND MARK #
180E ; 0020 ; ML #* ( ᠎ → ) MONGOLIAN VOWEL SEPARATOR → SPACE #
2028 ; 0020 ; ML #* ( → ) LINE SEPARATOR → SPACE #
2029 ; 0020 ; ML #* ( → ) PARAGRAPH SEPARATOR → SPACE #
1680 ; 0020 ; ML #* (   → ) OGHAM SPACE MARK → SPACE #
@ -17070,9 +17075,12 @@ FF45 ; 0065 ; ML # ( ｅ → e ) FULLWIDTH LATIN SMALL LETTER E → LATIN SMALL
1D65A ; 0065 ; ML # ( 𝙚 → e ) MATHEMATICAL SANS-SERIF BOLD ITALIC SMALL E → LATIN SMALL LETTER E #
1D68E ; 0065 ; ML # ( 𝚎 → e ) MATHEMATICAL MONOSPACE SMALL E → LATIN SMALL LETTER E #
0435 ; 0065 ; ML # ( е → e ) CYRILLIC SMALL LETTER IE → LATIN SMALL LETTER E #
04BD ; 0065 ; ML # ( ҽ → e ) CYRILLIC SMALL LETTER ABKHASIAN CHE → LATIN SMALL LETTER E #
011B ; 0115 ; ML # ( ě → ĕ ) LATIN SMALL LETTER E WITH CARON → LATIN SMALL LETTER E WITH BREVE #
04BF ; 0065 0328 ; ML # ( ҿ → ę ) CYRILLIC SMALL LETTER ABKHASIAN CHE WITH DESCENDER → LATIN SMALL LETTER E, COMBINING OGONEK # →ҽ̢→
0259 ; 01DD ; ML # ( ə → ǝ ) LATIN SMALL LETTER SCHWA → LATIN SMALL LETTER TURNED E #
04D9 ; 01DD ; ML # ( ә → ǝ ) CYRILLIC SMALL LETTER SCHWA → LATIN SMALL LETTER TURNED E #
@ -17675,6 +17683,8 @@ FF50 ; 0070 ; ML # ( ｐ → p ) FULLWIDTH LATIN SMALL LETTER P → LATIN SMALL
028D ; 0072 006E ; ML # ( ʍ → rn ) LATIN SMALL LETTER TURNED W → LATIN SMALL LETTER R, LATIN SMALL LETTER N # →m→
043C ; 0072 006E ; ML # ( м → rn ) CYRILLIC SMALL LETTER EM → LATIN SMALL LETTER R, LATIN SMALL LETTER N # →m→
20A5 ; 0072 006E 0338 ; ML #* ( ₥ → rn̸ ) MILL SIGN → LATIN SMALL LETTER R, LATIN SMALL LETTER N, COMBINING LONG SOLIDUS OVERLAY # →m̷→
0271 ; 0072 006E 0326 ; ML # ( ɱ → rn̦ ) LATIN SMALL LETTER M WITH HOOK → LATIN SMALL LETTER R, LATIN SMALL LETTER N, COMBINING COMMA BELOW # →m̡→
04CE ; 0072 006E 0326 ; ML # ( ӎ → rn̦ ) CYRILLIC SMALL LETTER EM WITH TAIL → LATIN SMALL LETTER R, LATIN SMALL LETTER N, COMBINING COMMA BELOW # →м̡→
@ -18065,8 +18075,6 @@ A645 ; 01A8 ; ML # ( ꙅ → ƨ ) CYRILLIC SMALL LETTER REVERSED DZE → LATIN S
04CC ; 04B7 ; ML # ( ӌ → ҷ ) CYRILLIC SMALL LETTER KHAKASSIAN CHE → CYRILLIC SMALL LETTER CHE WITH DESCENDER #
04BF ; 04BD 0328 ; ML # ( ҿ → ҽ̨ ) CYRILLIC SMALL LETTER ABKHASIAN CHE WITH DESCENDER → CYRILLIC SMALL LETTER ABKHASIAN CHE, COMBINING OGONEK # →ҽ̢→
2CBD ; 0448 ; ML # ( ⲽ → ш ) COPTIC SMALL LETTER CRYPTOGRAMMIC NI → CYRILLIC SMALL LETTER SHA #
044B ; 044C 0131 ; ML # ( ы → ьı ) CYRILLIC SMALL LETTER YERU → CYRILLIC SMALL LETTER SOFT SIGN, LATIN SMALL LETTER DOTLESS I #
@ -20086,7 +20094,7 @@ A4F4 ; 144C ; ML # ( ꓴ → ᑌ ) LISU LETTER U → CANADIAN SYLLABICS TE # →
14CC ; 14C7 00B7 ; ML # ( ᓌ → ᓇ· ) CANADIAN SYLLABICS WEST-CREE NWA → CANADIAN SYLLABICS NA, MIDDLE DOT # →ᓇᐧ→
14CE ; 14C8 14AB ; ML # ( ᓎ → ᓈᒫ ) CANADIAN SYLLABICS WEST-CREE NWAA → CANADIAN SYLLABICS NAA, CANADIAN SYLLABICS MAA #
14CE ; 14C8 00B7 ; ML # ( ᓎ → ᓈ· ) CANADIAN SYLLABICS WEST-CREE NWAA → CANADIAN SYLLABICS NAA, MIDDLE DOT # →ᓈᐧ→
1604 ; 14D3 ; ML # ( ᘄ → ᓓ ) CANADIAN SYLLABICS CARRIER NE → CANADIAN SYLLABICS LE #
@ -23527,7 +23535,7 @@ FAD7 ; 27ED3 ; ML # ( 𧻓 → 𧻓 ) CJK COMPATIBILITY IDEOGRAPH-FAD7 → CJK UN
2FA1D ; 2A600 ; ML # ( 𪘀 → 𪘀 ) CJK COMPATIBILITY IDEOGRAPH-2FA1D → CJK UNIFIED IDEOGRAPH-2A600 #
# total for (ML): 5135
# total for (ML): 5136
# Mixed-Script, Anycase Confusables
@ -23671,7 +23679,6 @@ FC63 ; FE7C 0670 ; MA #* ( ‎ﱣ‎ → ‎ﹼٰ‎ ) ARABIC LIGATURE SHADDA WI
309C ; FF9F ; MA #* ( ゜ → ﾟ ) KATAKANA-HIRAGANA SEMI-VOICED SOUND MARK → HALFWIDTH KATAKANA SEMI-VOICED SOUND MARK #
180E ; 0020 ; MA #* ( ᠎ → ) MONGOLIAN VOWEL SEPARATOR → SPACE #
2028 ; 0020 ; MA #* ( → ) LINE SEPARATOR → SPACE #
2029 ; 0020 ; MA #* ( → ) PARAGRAPH SEPARATOR → SPACE #
1680 ; 0020 ; MA #* (   → ) OGHAM SPACE MARK → SPACE #
@ -25156,6 +25163,7 @@ FF45 ; 0065 ; MA # ( ｅ → e ) FULLWIDTH LATIN SMALL LETTER E → LATIN SMALL
1D65A ; 0065 ; MA # ( 𝙚 → e ) MATHEMATICAL SANS-SERIF BOLD ITALIC SMALL E → LATIN SMALL LETTER E #
1D68E ; 0065 ; MA # ( 𝚎 → e ) MATHEMATICAL MONOSPACE SMALL E → LATIN SMALL LETTER E #
0435 ; 0065 ; MA # ( е → e ) CYRILLIC SMALL LETTER IE → LATIN SMALL LETTER E #
04BD ; 0065 ; MA # ( ҽ → e ) CYRILLIC SMALL LETTER ABKHASIAN CHE → LATIN SMALL LETTER E #
22FF ; 0045 ; MA #* ( ⋿ → E ) Z NOTATION BAG MEMBERSHIP → LATIN CAPITAL LETTER E #
FF25 ; 0045 ; MA # ( Ｅ → E ) FULLWIDTH LATIN CAPITAL LETTER E → LATIN CAPITAL LETTER E # →Ε→
@ -25187,6 +25195,8 @@ A4F0 ; 0045 ; MA # ( ꓰ → E ) LISU LETTER E → LATIN CAPITAL LETTER E #
011A ; 0114 ; MA # ( Ě → Ĕ ) LATIN CAPITAL LETTER E WITH CARON → LATIN CAPITAL LETTER E WITH BREVE #
04BF ; 0065 0328 ; MA # ( ҿ → ę ) CYRILLIC SMALL LETTER ABKHASIAN CHE WITH DESCENDER → LATIN SMALL LETTER E, COMBINING OGONEK # →ҽ̢→
0259 ; 01DD ; MA # ( ə → ǝ ) LATIN SMALL LETTER SCHWA → LATIN SMALL LETTER TURNED E #
04D9 ; 01DD ; MA # ( ә → ǝ ) CYRILLIC SMALL LETTER SCHWA → LATIN SMALL LETTER TURNED E #
@ -26221,6 +26231,8 @@ A4E3 ; 0052 ; MA # ( ꓣ → R ) LISU LETTER ZHA → LATIN CAPITAL LETTER R #
028D ; 0072 006E ; MA # ( ʍ → rn ) LATIN SMALL LETTER TURNED W → LATIN SMALL LETTER R, LATIN SMALL LETTER N # →m→
043C ; 0072 006E ; MA # ( м → rn ) CYRILLIC SMALL LETTER EM → LATIN SMALL LETTER R, LATIN SMALL LETTER N # →m→
20A5 ; 0072 006E 0338 ; MA #* ( ₥ → rn̸ ) MILL SIGN → LATIN SMALL LETTER R, LATIN SMALL LETTER N, COMBINING LONG SOLIDUS OVERLAY # →m̷→
0271 ; 0072 006E 0326 ; MA # ( ɱ → rn̦ ) LATIN SMALL LETTER M WITH HOOK → LATIN SMALL LETTER R, LATIN SMALL LETTER N, COMBINING COMMA BELOW # →m̡→
04CE ; 0072 006E 0326 ; MA # ( ӎ → rn̦ ) CYRILLIC SMALL LETTER EM WITH TAIL → LATIN SMALL LETTER R, LATIN SMALL LETTER N, COMBINING COMMA BELOW # →м̡→
@ -26915,8 +26927,6 @@ A645 ; 01A8 ; MA # ( ꙅ → ƨ ) CYRILLIC SMALL LETTER REVERSED DZE → LATIN S
04CB ; 04B6 ; MA # ( Ӌ → Ҷ ) CYRILLIC CAPITAL LETTER KHAKASSIAN CHE → CYRILLIC CAPITAL LETTER CHE WITH DESCENDER #
04BF ; 04BD 0328 ; MA # ( ҿ → ҽ̨ ) CYRILLIC SMALL LETTER ABKHASIAN CHE WITH DESCENDER → CYRILLIC SMALL LETTER ABKHASIAN CHE, COMBINING OGONEK # →ҽ̢→
04BE ; 04BC 0328 ; MA # ( Ҿ → Ҽ̨ ) CYRILLIC CAPITAL LETTER ABKHASIAN CHE WITH DESCENDER → CYRILLIC CAPITAL LETTER ABKHASIAN CHE, COMBINING OGONEK #
2CBD ; 0448 ; MA # ( ⲽ → ш ) COPTIC SMALL LETTER CRYPTOGRAMMIC NI → CYRILLIC SMALL LETTER SHA #
@ -28504,7 +28514,7 @@ AA56 ; AA23 ; MA # ( ꩖ → ꨣ ) CHAM DIGIT SIX → CHAM LETTER RA #
14CC ; 14C7 00B7 ; MA # ( ᓌ → ᓇ· ) CANADIAN SYLLABICS WEST-CREE NWA → CANADIAN SYLLABICS NA, MIDDLE DOT # →ᓇᐧ→
14CE ; 14C8 14AB ; MA # ( ᓎ → ᓈᒫ ) CANADIAN SYLLABICS WEST-CREE NWAA → CANADIAN SYLLABICS NAA, CANADIAN SYLLABICS MAA #
14CE ; 14C8 00B7 ; MA # ( ᓎ → ᓈ· ) CANADIAN SYLLABICS WEST-CREE NWAA → CANADIAN SYLLABICS NAA, MIDDLE DOT # →ᓈᐧ→
1604 ; 14D3 ; MA # ( ᘄ → ᓓ ) CANADIAN SYLLABICS CARRIER NE → CANADIAN SYLLABICS LE #
@ -31898,5 +31908,5 @@ FAD7 ; 27ED3 ; MA # ( 𧻓 → 𧻓 ) CJK COMPATIBILITY IDEOGRAPH-FAD7 → CJK UN
2FA1D ; 2A600 ; MA # ( 𪘀 → 𪘀 ) CJK COMPATIBILITY IDEOGRAPH-2FA1D → CJK UNIFIED IDEOGRAPH-2A600 #
# total for (MA): 5474
# total for (MA): 5475

138
icu4c/source/data/unidata/confusablesWholeScript.txt
View file

@ -1,8 +1,8 @@
# Summary: Whole-Script Confusables
# File: confusablesWholeScript.txt
# Version: 3.0-draft
# Generated: 2012-07-17, 21:27:33 GMT
# Checkin: $Revision: 1580 $
# Version: 6.3.0
# Generated: 2013-11-13, 00:04:56 GMT
# Checkin: $Revision: 1.32 $
#
# For documentation and usage, see http://www.unicode.org/reports/tr39/
#
@ -161,6 +161,12 @@
# Total code points: 1
# Bengali; Hebrew: [়]
09BC ; Beng; Hebr; L # (়) BENGALI SIGN NUKTA
# Total code points: 1
# Bengali; Kannada: [ঃ]
0983 ; Beng; Knda; L # (ঃ) BENGALI SIGN VISARGA
@ -284,7 +290,7 @@
# Total code points: 2
# Cyrillic; Latin: [агекмо-ухцъє-іјћҍґғқҟҫҭүұһӎӏӕөԁԑԛԝ]
# Cyrillic; Latin: [агекмо-ухцъє-іјћҍґғқҟҫҭүұһҽҿӎӏӕәөԁԑԛԝ]
0430 ; Cyrl; Latn; L # (а) CYRILLIC SMALL LETTER A
0433 ; Cyrl; Latn; L # (г) CYRILLIC SMALL LETTER GHE
@ -307,15 +313,18 @@
04AF ; Cyrl; Latn; L # (ү) CYRILLIC SMALL LETTER STRAIGHT U
04B1 ; Cyrl; Latn; L # (ұ) CYRILLIC SMALL LETTER STRAIGHT U WITH STROKE
04BB ; Cyrl; Latn; L # (һ) CYRILLIC SMALL LETTER SHHA
04BD ; Cyrl; Latn; L # (ҽ) CYRILLIC SMALL LETTER ABKHASIAN CHE
04BF ; Cyrl; Latn; L # (ҿ) CYRILLIC SMALL LETTER ABKHASIAN CHE WITH DESCENDER
04CE..04CF ; Cyrl; Latn; L # [2] (ӎ..ӏ) CYRILLIC SMALL LETTER EM WITH TAIL..CYRILLIC SMALL LETTER PALOCHKA
04D5 ; Cyrl; Latn; L # (ӕ) CYRILLIC SMALL LIGATURE A IE
04D9 ; Cyrl; Latn; L # (ә) CYRILLIC SMALL LETTER SCHWA
04E9 ; Cyrl; Latn; L # (ө) CYRILLIC SMALL LETTER BARRED O
0501 ; Cyrl; Latn; L # (ԁ) CYRILLIC SMALL LETTER KOMI DE
0511 ; Cyrl; Latn; L # (ԑ) CYRILLIC SMALL LETTER REVERSED ZE
051B ; Cyrl; Latn; L # (ԛ) CYRILLIC SMALL LETTER QA
051D ; Cyrl; Latn; L # (ԝ) CYRILLIC SMALL LETTER WE
# Total code points: 37
# Total code points: 40
# Cyrillic; Malayalam: [оө]
@ -406,11 +415,12 @@
# Total code points: 5
# Devanagari; Hebrew: [०]
# Devanagari; Hebrew: [़०]
093C ; Deva; Hebr; L # (़) DEVANAGARI SIGN NUKTA
0966 ; Deva; Hebr; L # (०) DEVANAGARI DIGIT ZERO
# Total code points: 1
# Total code points: 2
# Devanagari; Kannada: [०]
@ -683,11 +693,12 @@
# Total code points: 4
# Gujarati; Hebrew: [૦]
# Gujarati; Hebrew: [઼૦]
0ABC ; Gujr; Hebr; L # (઼) GUJARATI SIGN NUKTA
0AE6 ; Gujr; Hebr; L # (૦) GUJARATI DIGIT ZERO
# Total code points: 1
# Total code points: 2
# Gujarati; Kannada: [૦]
@ -797,11 +808,12 @@
# Total code points: 4
# Gurmukhi; Hebrew: [੦]
# Gurmukhi; Hebrew: [਼੦]
0A3C ; Guru; Hebr; L # (਼) GURMUKHI SIGN NUKTA
0A66 ; Guru; Hebr; L # (੦) GURMUKHI DIGIT ZERO
# Total code points: 1
# Total code points: 2
# Gurmukhi; Kannada: [ਃ੦]
@ -901,17 +913,24 @@
# Total code points: 1
# Hebrew; Bengali: [ִ]
05B4 ; Hebr; Beng; L # (ִ) HEBREW POINT HIRIQ
# Total code points: 1
# Hebrew; Cyrillic: [ס]
05E1 ; Hebr; Cyrl; L # (ס) HEBREW LETTER SAMEKH
# Total code points: 1
# Hebrew; Devanagari: [ס]
# Hebrew; Devanagari: [ִס]
05B4 ; Hebr; Deva; L # (ִ) HEBREW POINT HIRIQ
05E1 ; Hebr; Deva; L # (ס) HEBREW LETTER SAMEKH
# Total code points: 1
# Total code points: 2
# Hebrew; Greek: [טס]
@ -920,17 +939,19 @@
# Total code points: 2
# Hebrew; Gujarati: [ס]
# Hebrew; Gujarati: [ִס]
05B4 ; Hebr; Gujr; L # (ִ) HEBREW POINT HIRIQ
05E1 ; Hebr; Gujr; L # (ס) HEBREW LETTER SAMEKH
# Total code points: 1
# Total code points: 2
# Hebrew; Gurmukhi: [ס]
# Hebrew; Gurmukhi: [ִס]
05B4 ; Hebr; Guru; L # (ִ) HEBREW POINT HIRIQ
05E1 ; Hebr; Guru; L # (ס) HEBREW LETTER SAMEKH
# Total code points: 1
# Total code points: 2
# Hebrew; Kannada: [ס]
@ -966,6 +987,12 @@
# Total code points: 1
# Hebrew; Oriya: [ִ]
05B4 ; Hebr; Orya; L # (ִ) HEBREW POINT HIRIQ
# Total code points: 1
# Hebrew; Sinhala: [ס]
05E1 ; Hebr; Sinh; L # (ס) HEBREW LETTER SAMEKH
@ -1270,7 +1297,7 @@
# Total code points: 12
# Latin; Cyrillic: [a-eh-km-yæçøđħıĸŧơꞓ]
# Latin; Cyrillic: [a-eh-km-yæçøđħıĸŧơəꞓ]
0061..0065 ; Latn; Cyrl; L # [5] (a..e) LATIN SMALL LETTER A..LATIN SMALL LETTER E
0068..006B ; Latn; Cyrl; L # [4] (h..k) LATIN SMALL LETTER H..LATIN SMALL LETTER K
@ -1283,9 +1310,10 @@
0138 ; Latn; Cyrl; L # (ĸ) LATIN SMALL LETTER KRA
0167 ; Latn; Cyrl; L # (ŧ) LATIN SMALL LETTER T WITH STROKE
01A1 ; Latn; Cyrl; L # (ơ) LATIN SMALL LETTER O WITH HORN
0259 ; Latn; Cyrl; L # (ə) LATIN SMALL LETTER SCHWA
A793 ; Latn; Cyrl; L # (ꞓ) LATIN SMALL LETTER C WITH BAR
# Total code points: 32
# Total code points: 33
# Latin; Devanagari: [oøơ]
@ -1717,6 +1745,12 @@ A793 ; Latn; Grek; L # (ꞓ) LATIN SMALL LETTER C WITH BAR
# Total code points: 2
# Oriya; Hebrew: [଼]
0B3C ; Orya; Hebr; L # (଼) ORIYA SIGN NUKTA
# Total code points: 1
# Oriya; Malayalam: [ଠ୦]
0B20 ; Orya; Mlym; L # (ଠ) ORIYA LETTER TTHA
@ -2349,6 +2383,12 @@ A793 ; Latn; Grek; L # (ꞓ) LATIN SMALL LETTER C WITH BAR
# Total code points: 1
# Bengali; Hebrew: [়]
09BC ; Beng; Hebr; A # (়) BENGALI SIGN NUKTA
# Total code points: 1
# Bengali; Kannada: [ঃ]
0983 ; Beng; Knda; A # (ঃ) BENGALI SIGN VISARGA
@ -2508,7 +2548,7 @@ A793 ; Latn; Grek; L # (ꞓ) LATIN SMALL LETTER C WITH BAR
# Total code points: 2
# Cyrillic; Latin: [Є-ІЈА-ВЕКМ-ОР-ТХЫЬЮагекмо-ухцъє-іјћҌҍґғҚқҞҟҢҪ-ҲһӇӉӍ-ӏӔӕӨөԁԌԑԛ-ԝ]
# Cyrillic; Latin: [Є-ІЈА-ВЕКМ-ОР-ТХЫЬЮагекмо-ухцъє-іјћҌҍґғҚқҞҟҢҪ-ҲһҽҿӇӉӍ-ӏӔӕәӨөԁԌԑԛ-ԝ]
0404..0406 ; Cyrl; Latn; A # [3] (Є..І) CYRILLIC CAPITAL LETTER UKRAINIAN IE..CYRILLIC CAPITAL LETTER BYELORUSSIAN-UKRAINIAN I
0408 ; Cyrl; Latn; A # (Ј) CYRILLIC CAPITAL LETTER JE
@ -2539,17 +2579,20 @@ A793 ; Latn; Grek; L # (ꞓ) LATIN SMALL LETTER C WITH BAR
04A2 ; Cyrl; Latn; A # (Ң) CYRILLIC CAPITAL LETTER EN WITH DESCENDER
04AA..04B2 ; Cyrl; Latn; A # [9] (Ҫ..Ҳ) CYRILLIC CAPITAL LETTER ES WITH DESCENDER..CYRILLIC CAPITAL LETTER HA WITH DESCENDER
04BB ; Cyrl; Latn; A # (һ) CYRILLIC SMALL LETTER SHHA
04BD ; Cyrl; Latn; A # (ҽ) CYRILLIC SMALL LETTER ABKHASIAN CHE
04BF ; Cyrl; Latn; A # (ҿ) CYRILLIC SMALL LETTER ABKHASIAN CHE WITH DESCENDER
04C7 ; Cyrl; Latn; A # (Ӈ) CYRILLIC CAPITAL LETTER EN WITH HOOK
04C9 ; Cyrl; Latn; A # (Ӊ) CYRILLIC CAPITAL LETTER EN WITH TAIL
04CD..04CF ; Cyrl; Latn; A # [3] (Ӎ..ӏ) CYRILLIC CAPITAL LETTER EM WITH TAIL..CYRILLIC SMALL LETTER PALOCHKA
04D4..04D5 ; Cyrl; Latn; A # [2] (Ӕ..ӕ) CYRILLIC CAPITAL LIGATURE A IE..CYRILLIC SMALL LIGATURE A IE
04D9 ; Cyrl; Latn; A # (ә) CYRILLIC SMALL LETTER SCHWA
04E8..04E9 ; Cyrl; Latn; A # [2] (Ө..ө) CYRILLIC CAPITAL LETTER BARRED O..CYRILLIC SMALL LETTER BARRED O
0501 ; Cyrl; Latn; A # (ԁ) CYRILLIC SMALL LETTER KOMI DE
050C ; Cyrl; Latn; A # (Ԍ) CYRILLIC CAPITAL LETTER KOMI SJE
0511 ; Cyrl; Latn; A # (ԑ) CYRILLIC SMALL LETTER REVERSED ZE
051B..051D ; Cyrl; Latn; A # [3] (ԛ..ԝ) CYRILLIC SMALL LETTER QA..CYRILLIC SMALL LETTER WE
# Total code points: 72
# Total code points: 75
# Cyrillic; Malayalam: [ОоӨө]
@ -2650,11 +2693,12 @@ A793 ; Latn; Grek; L # (ꞓ) LATIN SMALL LETTER C WITH BAR
# Total code points: 5
# Devanagari; Hebrew: [०]
# Devanagari; Hebrew: [़०]
093C ; Deva; Hebr; A # (़) DEVANAGARI SIGN NUKTA
0966 ; Deva; Hebr; A # (०) DEVANAGARI DIGIT ZERO
# Total code points: 1
# Total code points: 2
# Devanagari; Kannada: [०]
@ -2949,11 +2993,12 @@ A793 ; Latn; Grek; L # (ꞓ) LATIN SMALL LETTER C WITH BAR
# Total code points: 4
# Gujarati; Hebrew: [૦]
# Gujarati; Hebrew: [઼૦]
0ABC ; Gujr; Hebr; A # (઼) GUJARATI SIGN NUKTA
0AE6 ; Gujr; Hebr; A # (૦) GUJARATI DIGIT ZERO
# Total code points: 1
# Total code points: 2
# Gujarati; Kannada: [૦]
@ -3063,11 +3108,12 @@ A793 ; Latn; Grek; L # (ꞓ) LATIN SMALL LETTER C WITH BAR
# Total code points: 4
# Gurmukhi; Hebrew: [੦]
# Gurmukhi; Hebrew: [਼੦]
0A3C ; Guru; Hebr; A # (਼) GURMUKHI SIGN NUKTA
0A66 ; Guru; Hebr; A # (੦) GURMUKHI DIGIT ZERO
# Total code points: 1
# Total code points: 2
# Gurmukhi; Kannada: [ਃ੦]
@ -3185,6 +3231,12 @@ A793 ; Latn; Grek; L # (ꞓ) LATIN SMALL LETTER C WITH BAR
# Total code points: 1
# Hebrew; Bengali: [ִ]
05B4 ; Hebr; Beng; A # (ִ) HEBREW POINT HIRIQ
# Total code points: 1
# Hebrew; Cyrillic: [ויןסױ]
05D5 ; Hebr; Cyrl; A # (ו) HEBREW LETTER VAV
@ -3195,11 +3247,12 @@ A793 ; Latn; Grek; L # (ꞓ) LATIN SMALL LETTER C WITH BAR
# Total code points: 5
# Hebrew; Devanagari: [ס]
# Hebrew; Devanagari: [ִס]
05B4 ; Hebr; Deva; A # (ִ) HEBREW POINT HIRIQ
05E1 ; Hebr; Deva; A # (ס) HEBREW LETTER SAMEKH
# Total code points: 1
# Total code points: 2
# Hebrew; Greek: [וטיןסױ]
@ -3211,17 +3264,19 @@ A793 ; Latn; Grek; L # (ꞓ) LATIN SMALL LETTER C WITH BAR
# Total code points: 6
# Hebrew; Gujarati: [ס]
# Hebrew; Gujarati: [ִס]
05B4 ; Hebr; Gujr; A # (ִ) HEBREW POINT HIRIQ
05E1 ; Hebr; Gujr; A # (ס) HEBREW LETTER SAMEKH
# Total code points: 1
# Total code points: 2
# Hebrew; Gurmukhi: [ס]
# Hebrew; Gurmukhi: [ִס]
05B4 ; Hebr; Guru; A # (ִ) HEBREW POINT HIRIQ
05E1 ; Hebr; Guru; A # (ס) HEBREW LETTER SAMEKH
# Total code points: 1
# Total code points: 2
# Hebrew; Kannada: [ס]
@ -3257,6 +3312,12 @@ A793 ; Latn; Grek; L # (ꞓ) LATIN SMALL LETTER C WITH BAR
# Total code points: 1
# Hebrew; Oriya: [ִ]
05B4 ; Hebr; Orya; A # (ִ) HEBREW POINT HIRIQ
# Total code points: 1
# Hebrew; Sinhala: [ס]
05E1 ; Hebr; Sinh; A # (ס) HEBREW LETTER SAMEKH
@ -3575,7 +3636,7 @@ A793 ; Latn; Grek; L # (ꞓ) LATIN SMALL LETTER C WITH BAR
# Total code points: 4
# Latin; Cyrillic: [A-CEG-MOPSTW-Ya-eh-yÆÇØæçøđĦħıĸŁłŦŧƠơǾꞒꞓ]
# Latin; Cyrillic: [A-CEG-MOPSTW-Ya-eh-yÆÇØæçøđĦħıĸŁłŦŧƠơǾəꞒꞓ]
0041..0043 ; Latn; Cyrl; A # [3] (A..C) LATIN CAPITAL LETTER A..LATIN CAPITAL LETTER C
0045 ; Latn; Cyrl; A # (E) LATIN CAPITAL LETTER E
@ -3597,9 +3658,10 @@ A793 ; Latn; Grek; L # (ꞓ) LATIN SMALL LETTER C WITH BAR
0166..0167 ; Latn; Cyrl; A # [2] (Ŧ..ŧ) LATIN CAPITAL LETTER T WITH STROKE..LATIN SMALL LETTER T WITH STROKE
01A0..01A1 ; Latn; Cyrl; A # [2] (Ơ..ơ) LATIN CAPITAL LETTER O WITH HORN..LATIN SMALL LETTER O WITH HORN
01FE ; Latn; Cyrl; A # (Ǿ) LATIN CAPITAL LETTER O WITH STROKE AND ACUTE
0259 ; Latn; Cyrl; A # (ə) LATIN SMALL LETTER SCHWA
A792..A793 ; Latn; Cyrl; A # [2] (Ꞓ..ꞓ) LATIN CAPITAL LETTER C WITH BAR..LATIN SMALL LETTER C WITH BAR
# Total code points: 61
# Total code points: 62
# Latin; Devanagari: [oøơ]
@ -4083,6 +4145,12 @@ A793 ; Latn; Grek; A # (ꞓ) LATIN SMALL LETTER C WITH BAR
# Total code points: 2
# Oriya; Hebrew: [଼]
0B3C ; Orya; Hebr; A # (଼) ORIYA SIGN NUKTA
# Total code points: 1
# Oriya; Latin: [ଠ୦]
0B20 ; Orya; Latn; A # (ଠ) ORIYA LETTER TTHA

4
icu4c/source/i18n/identifier_info.cpp
View file

@ -1,6 +1,6 @@
/*
**********************************************************************
* Copyright (C) 2012-2013, International Business Machines
* Copyright (C) 2012-2014, International Business Machines
* Corporation and others. All Rights Reserved.
**********************************************************************
*/
@ -247,7 +247,7 @@ URestrictionLevel IdentifierInfo::getRestrictionLevel(UErrorCode &status) const
int32_t cardinalityPlus = fRequiredScripts->countMembers() +
(fCommonAmongAlternates->countMembers() == 0 ? uhash_count(fScriptSetSet) : 1);
if (cardinalityPlus < 2) {
return USPOOF_HIGHLY_RESTRICTIVE;
return USPOOF_SINGLE_SCRIPT_RESTRICTIVE;
}
if (containsWithAlternates(*JAPANESE, *fRequiredScripts) || containsWithAlternates(*CHINESE, *fRequiredScripts)
|| containsWithAlternates(*KOREAN, *fRequiredScripts)) {

22
icu4c/source/i18n/unicode/uspoof.h
View file

@ -1,6 +1,6 @@
/*
***************************************************************************
* Copyright (C) 2008-2013, International Business Machines Corporation
* Copyright (C) 2008-2014, International Business Machines Corporation
* and others. All Rights Reserved.
***************************************************************************
* file name: uspoof.h
@ -275,6 +275,12 @@ typedef enum USpoofChecks {
* @draft ICU 51
*/
USPOOF_ASCII = 0x10000000,
/**
* All characters in each identifier must be from a single script.
*
* @draft ICU 53
*/
USPOOF_SINGLE_SCRIPT_RESTRICTIVE = 0x20000000,
/**
* All characters in each identifier must be from a single script, or from the combinations: Latin + Han +
* Hiragana + Katakana; Latin + Han + Bopomofo; or Latin + Han + Hangul. Note that this level will satisfy the
@ -282,25 +288,31 @@ typedef enum USpoofChecks {
*
* @draft ICU 51
*/
USPOOF_HIGHLY_RESTRICTIVE = 0x20000000,
USPOOF_HIGHLY_RESTRICTIVE = 0x30000000,
/**
* Allow Latin with other scripts except Cyrillic, Greek, Cherokee Otherwise, the same as Highly Restrictive
*
* @draft ICU 51
*/
USPOOF_MODERATELY_RESTRICTIVE = 0x30000000,
USPOOF_MODERATELY_RESTRICTIVE = 0x40000000,
/**
* Allow arbitrary mixtures of scripts. Otherwise, the same as Moderately Restrictive.
*
* @draft ICU 51
*/
USPOOF_MINIMALLY_RESTRICTIVE = 0x40000000,
USPOOF_MINIMALLY_RESTRICTIVE = 0x50000000,
/**
* Any valid identifiers, including characters outside of the Identifier Profile.
*
* @draft ICU 51
*/
USPOOF_UNRESTRICTIVE = 0x50000000
USPOOF_UNRESTRICTIVE = 0x60000000,
/**
* Mask for selecting the Restriction Level bits from the return value of uspoof_check().
*
* @draft ICU 53
*/
USPOOF_RESTRICTION_LEVEL_MASK = 0x7F000000
} URestrictionLevel;
#endif /* U_HIDE_DRAFT_API */

123
icu4c/source/i18n/uspoof.cpp
View file

@ -1,6 +1,6 @@
/*
***************************************************************************
* Copyright (C) 2008-2013, International Business Machines Corporation
* Copyright (C) 2008-2014, International Business Machines Corporation
* and others. All Rights Reserved.
***************************************************************************
* file name: uspoof.cpp
@ -40,7 +40,7 @@ U_NAMESPACE_USE
static UnicodeSet *gInclusionSet = NULL;
static UnicodeSet *gRecommendedSet = NULL;
static const Normalizer2 *gNfdNormalizer = NULL;
static UMutex gInitMutex = U_MUTEX_INITIALIZER;
static UInitOnce gSpoofInitOnce = U_INITONCE_INITIALIZER;
static UBool U_CALLCONV
uspoof_cleanup(void) {
@ -49,44 +49,75 @@ uspoof_cleanup(void) {
delete gRecommendedSet;
gRecommendedSet = NULL;
gNfdNormalizer = NULL;
gSpoofInitOnce.reset();
return TRUE;
}
static void initializeStatics() {
Mutex m(&gInitMutex);
UErrorCode status = U_ZERO_ERROR;
if (gInclusionSet == NULL) {
gInclusionSet = new UnicodeSet(UNICODE_STRING_SIMPLE("[\
\\-.\\u00B7\\u05F3\\u05F4\\u0F0B\\u200C\\u200D\\u2019]"), status);
gRecommendedSet = new UnicodeSet(UNICODE_STRING_SIMPLE("[\
[0-z\\u00C0-\\u017E\\u01A0\\u01A1\\u01AF\\u01B0\\u01CD-\
\\u01DC\\u01DE-\\u01E3\\u01E6-\\u01F5\\u01F8-\\u021B\\u021E\
\\u021F\\u0226-\\u0233\\u02BB\\u02BC\\u02EC\\u0300-\\u0304\
\\u0306-\\u030C\\u030F-\\u0311\\u0313\\u0314\\u031B\\u0323-\
\\u0328\\u032D\\u032E\\u0330\\u0331\\u0335\\u0338\\u0339\
\\u0342-\\u0345\\u037B-\\u03CE\\u03FC-\\u045F\\u048A-\\u0525\
\\u0531-\\u0586\\u05D0-\\u05F2\\u0621-\\u063F\\u0641-\\u0655\
\\u0660-\\u0669\\u0670-\\u068D\\u068F-\\u06D5\\u06E5\\u06E6\
\\u06EE-\\u06FF\\u0750-\\u07B1\\u0901-\\u0939\\u093C-\\u094D\
\\u0950\\u0960-\\u0972\\u0979-\\u0A4D\\u0A5C-\\u0A74\\u0A81-\
\\u0B43\\u0B47-\\u0B61\\u0B66-\\u0C56\\u0C60\\u0C61\\u0C66-\
\\u0CD6\\u0CE0-\\u0CEF\\u0D02-\\u0D28\\u0D2A-\\u0D39\\u0D3D-\
\\u0D43\\u0D46-\\u0D4D\\u0D57-\\u0D61\\u0D66-\\u0D8E\\u0D91-\
\\u0DA5\\u0DA7-\\u0DDE\\u0DF2\\u0E01-\\u0ED9\\u0F00\\u0F20-\
\\u0F8B\\u0F90-\\u109D\\u10D0-\\u10F0\\u10F7-\\u10FA\\u1200-\
\\u135A\\u135F\\u1380-\\u138F\\u1401-\\u167F\\u1780-\\u17A2\
\\u17A5-\\u17A7\\u17A9-\\u17B3\\u17B6-\\u17CA\\u17D2\\u17D7-\
\\u17DC\\u17E0-\\u17E9\\u1810-\\u18A8\\u18AA-\\u18F5\\u1E00-\
\\u1E99\\u1F00-\\u1FFC\\u2D30-\\u2D65\\u2D80-\\u2DDE\\u3005-\
\\u3007\\u3041-\\u31B7\\u3400-\\u9FCB\\uA000-\\uA48C\\uA67F\
\\uA717-\\uA71F\\uA788\\uAA60-\\uAA7B\\uAC00-\\uD7A3\\uFA0E-\
\\uFA29\\U00020000-\
\\U0002B734]-[[:Cn:][:nfkcqc=n:][:XIDC=n:]]]"), status);
gNfdNormalizer = Normalizer2::getNFDInstance(status);
}
static void U_CALLCONV initializeStatics(UErrorCode &status) {
gInclusionSet = new UnicodeSet(UNICODE_STRING_SIMPLE(
"[\\u0027\\u002d-\\u002e\\u003A\\u00B7\\u0375\\u058A\\u05F3-\\u05F4"
"\\u06FD-\\u06FE\\u0F0B\\u200C-\\u200D\\u2010\\u2019\\u2027\\u30A0\\u30FB]"),
status);
// Note: data from http://unicode.org/Public/security/latest/xidmodifications.txt version 6.3.0
gRecommendedSet = new UnicodeSet(UNICODE_STRING_SIMPLE("["
"\\u0030-\\u0039\\u0041-\\u005A\\u005F\\u0061-\\u007A\\u00C0-\\u00D6\\u00D8-\\u00F6"
"\\u00F8-\\u0131\\u0134-\\u013E\\u0141-\\u0148\\u014A-\\u017E\\u01A0-\\u01A1\\u01AF-\\u01B0"
"\\u01CD-\\u01DC\\u01DE-\\u01E3\\u01E6-\\u01F0\\u01F4-\\u01F5\\u01F8-\\u021B\\u021E-\\u021F"
"\\u0226-\\u0233\\u0259\\u02BB-\\u02BC\\u02EC\\u0300-\\u0304\\u0306-\\u030C\\u030F-\\u0311"
"\\u0313-\\u0314\\u031B\\u0323-\\u0328\\u032D-\\u032E\\u0330-\\u0331\\u0335\\u0338-\\u0339"
"\\u0342\\u0345\\u037B-\\u037D\\u0386\\u0388-\\u038A\\u038C\\u038E-\\u03A1\\u03A3-\\u03CE"
"\\u03FC-\\u045F\\u048A-\\u0527\\u0531-\\u0556\\u0559\\u0561-\\u0586\\u05B4\\u05D0-\\u05EA"
"\\u05F0-\\u05F2\\u0620-\\u063F\\u0641-\\u0655\\u0660-\\u0669\\u0670-\\u0672\\u0674"
"\\u0679-\\u068D\\u068F-\\u06D3\\u06D5\\u06E5-\\u06E6\\u06EE-\\u06FC\\u06FF\\u0750-\\u07B1"
"\\u08A0\\u08A2-\\u08AC\\u0901-\\u094D\\u094F-\\u0950\\u0956-\\u0957\\u0960-\\u0963"
"\\u0966-\\u096F\\u0971-\\u0977\\u0979-\\u097F\\u0981-\\u0983\\u0985-\\u098C\\u098F-\\u0990"
"\\u0993-\\u09A8\\u09AA-\\u09B0\\u09B2\\u09B6-\\u09B9\\u09BC-\\u09C4\\u09C7-\\u09C8"
"\\u09CB-\\u09CE\\u09D7\\u09E0-\\u09E3\\u09E6-\\u09F1\\u0A01-\\u0A03\\u0A05-\\u0A0A"
"\\u0A0F-\\u0A10\\u0A13-\\u0A28\\u0A2A-\\u0A30\\u0A32\\u0A35\\u0A38-\\u0A39\\u0A3C"
"\\u0A3E-\\u0A42\\u0A47-\\u0A48\\u0A4B-\\u0A4D\\u0A5C\\u0A66-\\u0A74\\u0A81-\\u0A83"
"\\u0A85-\\u0A8D\\u0A8F-\\u0A91\\u0A93-\\u0AA8\\u0AAA-\\u0AB0\\u0AB2-\\u0AB3\\u0AB5-\\u0AB9"
"\\u0ABC-\\u0AC5\\u0AC7-\\u0AC9\\u0ACB-\\u0ACD\\u0AD0\\u0AE0-\\u0AE3\\u0AE6-\\u0AEF"
"\\u0B01-\\u0B03\\u0B05-\\u0B0C\\u0B0F-\\u0B10\\u0B13-\\u0B28\\u0B2A-\\u0B30\\u0B32-\\u0B33"
"\\u0B35-\\u0B39\\u0B3C-\\u0B43\\u0B47-\\u0B48\\u0B4B-\\u0B4D\\u0B56-\\u0B57\\u0B5F-\\u0B61"
"\\u0B66-\\u0B6F\\u0B71\\u0B82-\\u0B83\\u0B85-\\u0B8A\\u0B8E-\\u0B90\\u0B92-\\u0B95"
"\\u0B99-\\u0B9A\\u0B9C\\u0B9E-\\u0B9F\\u0BA3-\\u0BA4\\u0BA8-\\u0BAA\\u0BAE-\\u0BB9"
"\\u0BBE-\\u0BC2\\u0BC6-\\u0BC8\\u0BCA-\\u0BCD\\u0BD0\\u0BD7\\u0BE6-\\u0BEF\\u0C01-\\u0C03"
"\\u0C05-\\u0C0C\\u0C0E-\\u0C10\\u0C12-\\u0C28\\u0C2A-\\u0C33\\u0C35-\\u0C39\\u0C3D-\\u0C44"
"\\u0C46-\\u0C48\\u0C4A-\\u0C4D\\u0C55-\\u0C56\\u0C60-\\u0C61\\u0C66-\\u0C6F\\u0C82-\\u0C83"
"\\u0C85-\\u0C8C\\u0C8E-\\u0C90\\u0C92-\\u0CA8\\u0CAA-\\u0CB3\\u0CB5-\\u0CB9\\u0CBC-\\u0CC4"
"\\u0CC6-\\u0CC8\\u0CCA-\\u0CCD\\u0CD5-\\u0CD6\\u0CE0-\\u0CE3\\u0CE6-\\u0CEF\\u0CF1-\\u0CF2"
"\\u0D02-\\u0D03\\u0D05-\\u0D0C\\u0D0E-\\u0D10\\u0D12-\\u0D3A\\u0D3D-\\u0D43\\u0D46-\\u0D48"
"\\u0D4A-\\u0D4E\\u0D57\\u0D60-\\u0D61\\u0D66-\\u0D6F\\u0D7A-\\u0D7F\\u0D82-\\u0D83"
"\\u0D85-\\u0D8E\\u0D91-\\u0D96\\u0D9A-\\u0DA5\\u0DA7-\\u0DB1\\u0DB3-\\u0DBB\\u0DBD"
"\\u0DC0-\\u0DC6\\u0DCA\\u0DCF-\\u0DD4\\u0DD6\\u0DD8-\\u0DDE\\u0DF2\\u0E01-\\u0E32"
"\\u0E34-\\u0E3A\\u0E40-\\u0E4E\\u0E50-\\u0E59\\u0E81-\\u0E82\\u0E84\\u0E87-\\u0E88"
"\\u0E8A\\u0E8D\\u0E94-\\u0E97\\u0E99-\\u0E9F\\u0EA1-\\u0EA3\\u0EA5\\u0EA7\\u0EAA-\\u0EAB"
"\\u0EAD-\\u0EB2\\u0EB4-\\u0EB9\\u0EBB-\\u0EBD\\u0EC0-\\u0EC4\\u0EC6\\u0EC8-\\u0ECD"
"\\u0ED0-\\u0ED9\\u0EDE-\\u0EDF\\u0F00\\u0F20-\\u0F29\\u0F35\\u0F37\\u0F3E-\\u0F42"
"\\u0F44-\\u0F47\\u0F49-\\u0F4C\\u0F4E-\\u0F51\\u0F53-\\u0F56\\u0F58-\\u0F5B\\u0F5D-\\u0F68"
"\\u0F6A-\\u0F6C\\u0F71-\\u0F72\\u0F74\\u0F7A-\\u0F80\\u0F82-\\u0F84\\u0F86-\\u0F92"
"\\u0F94-\\u0F97\\u0F99-\\u0F9C\\u0F9E-\\u0FA1\\u0FA3-\\u0FA6\\u0FA8-\\u0FAB\\u0FAD-\\u0FB8"
"\\u0FBA-\\u0FBC\\u0FC6\\u1000-\\u1049\\u1050-\\u109D\\u10C7\\u10CD\\u10D0-\\u10F0"
"\\u10F7-\\u10FA\\u10FD-\\u10FF\\u1200-\\u1248\\u124A-\\u124D\\u1250-\\u1256\\u1258"
"\\u125A-\\u125D\\u1260-\\u1288\\u128A-\\u128D\\u1290-\\u12B0\\u12B2-\\u12B5\\u12B8-\\u12BE"
"\\u12C0\\u12C2-\\u12C5\\u12C8-\\u12D6\\u12D8-\\u1310\\u1312-\\u1315\\u1318-\\u135A"
"\\u135D-\\u135F\\u1380-\\u138F\\u1780-\\u17A2\\u17A5-\\u17A7\\u17A9-\\u17B3\\u17B6-\\u17CA"
"\\u17D2\\u17D7\\u17DC\\u17E0-\\u17E9\\u1E00-\\u1E99\\u1EBF\\u1F00-\\u1F15\\u1F18-\\u1F1D"
"\\u1F20-\\u1F45\\u1F48-\\u1F4D\\u1F50-\\u1F57\\u1F59\\u1F5B\\u1F5D\\u1F5F-\\u1F70"
"\\u1F72\\u1F74\\u1F76\\u1F78\\u1F7A\\u1F7C\\u1F80-\\u1FB4\\u1FB6-\\u1FBA\\u1FBC\\u1FC2-\\u1FC4"
"\\u1FC6-\\u1FC8\\u1FCA\\u1FCC\\u1FD0-\\u1FD2\\u1FD6-\\u1FDA\\u1FE0-\\u1FE2\\u1FE4-\\u1FEA"
"\\u1FEC\\u1FF2-\\u1FF4\\u1FF6-\\u1FF8\\u1FFA\\u1FFC\\u2D27\\u2D2D\\u2D80-\\u2D96\\u2DA0-\\u2DA6"
"\\u2DA8-\\u2DAE\\u2DB0-\\u2DB6\\u2DB8-\\u2DBE\\u2DC0-\\u2DC6\\u2DC8-\\u2DCE\\u2DD0-\\u2DD6"
"\\u2DD8-\\u2DDE\\u3005-\\u3007\\u3041-\\u3096\\u3099-\\u309A\\u309D-\\u309E\\u30A1-\\u30FA"
"\\u30FC-\\u30FE\\u3105-\\u312D\\u31A0-\\u31BA\\u3400-\\u4DB5\\u4E00-\\u9FCC\\uA660-\\uA661"
"\\uA674-\\uA67B\\uA67F\\uA69F\\uA717-\\uA71F\\uA788\\uA78D-\\uA78E\\uA790-\\uA793"
"\\uA7A0-\\uA7AA\\uA7FA\\uA9CF\\uAA60-\\uAA76\\uAA7A-\\uAA7B\\uAB01-\\uAB06\\uAB09-\\uAB0E"
"\\uAB11-\\uAB16\\uAB20-\\uAB26\\uAB28-\\uAB2E\\uAC00-\\uD7A3\\uFA0E-\\uFA0F\\uFA11"
"\\uFA13-\\uFA14\\uFA1F\\uFA21\\uFA23-\\uFA24\\uFA27-\\uFA29\\U0001B000-\\U0001B001\\U00020000-\\U0002A6D6"
"\\U0002A700-\\U0002B734\\U0002B740-\\U0002B81D]"), status);
gNfdNormalizer = Normalizer2::getNFDInstance(status);
ucln_i18n_registerCleanup(UCLN_I18N_SPOOF, uspoof_cleanup);
return;
}
@ -95,7 +126,7 @@ uspoof_open(UErrorCode *status) {
if (U_FAILURE(*status)) {
return NULL;
}
initializeStatics();
umtx_initOnce(gSpoofInitOnce, &initializeStatics, *status);
SpoofImpl *si = new SpoofImpl(SpoofData::getDefault(*status), *status);
if (U_FAILURE(*status)) {
delete si;
@ -111,7 +142,7 @@ uspoof_openFromSerialized(const void *data, int32_t length, int32_t *pActualLeng
if (U_FAILURE(*status)) {
return NULL;
}
initializeStatics();
umtx_initOnce(gSpoofInitOnce, &initializeStatics, *status);
SpoofData *sd = new SpoofData(data, length, *status);
SpoofImpl *si = new SpoofImpl(sd, *status);
if (U_FAILURE(*status)) {
@ -708,26 +739,26 @@ uspoof_serialize(USpoofChecker *sc,void *buf, int32_t capacity, UErrorCode *stat
}
U_CAPI const USet * U_EXPORT2
uspoof_getInclusionSet(UErrorCode *) {
initializeStatics();
uspoof_getInclusionSet(UErrorCode *status) {
umtx_initOnce(gSpoofInitOnce, &initializeStatics, *status);
return gInclusionSet->toUSet();
}
U_CAPI const USet * U_EXPORT2
uspoof_getRecommendedSet(UErrorCode *) {
initializeStatics();
uspoof_getRecommendedSet(UErrorCode *status) {
umtx_initOnce(gSpoofInitOnce, &initializeStatics, *status);
return gRecommendedSet->toUSet();
}
U_I18N_API const UnicodeSet * U_EXPORT2
uspoof_getInclusionUnicodeSet(UErrorCode *) {
initializeStatics();
uspoof_getInclusionUnicodeSet(UErrorCode *status) {
umtx_initOnce(gSpoofInitOnce, &initializeStatics, *status);
return gInclusionSet;
}
U_I18N_API const UnicodeSet * U_EXPORT2
uspoof_getRecommendedUnicodeSet(UErrorCode *) {
initializeStatics();
uspoof_getRecommendedUnicodeSet(UErrorCode *status) {
umtx_initOnce(gSpoofInitOnce, &initializeStatics, *status);
return gRecommendedSet;
}

4
icu4c/source/test/intltest/itspoof.cpp
View file

@ -1,6 +1,6 @@
/*
**********************************************************************
* Copyright (C) 2011-2013, International Business Machines Corporation
* Copyright (C) 2011-2014, International Business Machines Corporation
* and others. All Rights Reserved.
**********************************************************************
*/
@ -675,7 +675,7 @@ void IntlTestSpoof::testRestrictionLevel() {
} tests[] = {
{"\\u0061\\u03B3\\u2665", USPOOF_UNRESTRICTIVE},
{"a", USPOOF_ASCII},
{"\\u03B3", USPOOF_HIGHLY_RESTRICTIVE},
{"\\u03B3", USPOOF_SINGLE_SCRIPT_RESTRICTIVE},
{"\\u0061\\u30A2\\u30FC", USPOOF_HIGHLY_RESTRICTIVE},
{"\\u0061\\u0904", USPOOF_MODERATELY_RESTRICTIVE},
{"\\u0061\\u03B3", USPOOF_MINIMALLY_RESTRICTIVE}

54
icu4c/source/test/testdata/confusables.txt vendored
View file

@ -1,8 +1,8 @@
# Recommended confusable mapping for IDN
# File: confusables.txt
# Version: 3.0-draft
# Generated: 2012-07-17, 21:27:33 GMT
# Checkin: $Revision: 1580 $
# Version: 6.3.0
# Generated: 2013-11-13, 00:04:57 GMT
# Checkin: $Revision: 1.32 $
#
# For documentation and usage, see http://www.unicode.org/reports/tr39/
#
@ -131,7 +131,6 @@ FC63 ; FE7C 0670 ; SL #* ( ‎ﱣ‎ → ‎ﹼٰ‎ ) ARABIC LIGATURE SHADDA WI
309C ; FF9F ; SL #* ( ゜ → ﾟ ) KATAKANA-HIRAGANA SEMI-VOICED SOUND MARK → HALFWIDTH KATAKANA SEMI-VOICED SOUND MARK #
180E ; 0020 ; SL #* ( ᠎ → ) MONGOLIAN VOWEL SEPARATOR → SPACE #
2028 ; 0020 ; SL #* ( → ) LINE SEPARATOR → SPACE #
2029 ; 0020 ; SL #* ( → ) PARAGRAPH SEPARATOR → SPACE #
1680 ; 0020 ; SL #* (   → ) OGHAM SPACE MARK → SPACE #
@ -1891,6 +1890,8 @@ FF50 ; 0070 ; SL # ( ｐ → p ) FULLWIDTH LATIN SMALL LETTER P → LATIN SMALL
1D0D ; 0072 006E ; SL # ( ᴍ → rn ) LATIN LETTER SMALL CAPITAL M → LATIN SMALL LETTER R, LATIN SMALL LETTER N # →м→→m→
028D ; 0072 006E ; SL # ( ʍ → rn ) LATIN SMALL LETTER TURNED W → LATIN SMALL LETTER R, LATIN SMALL LETTER N # →m→
20A5 ; 0072 006E 0338 ; SL #* ( ₥ → rn̸ ) MILL SIGN → LATIN SMALL LETTER R, LATIN SMALL LETTER N, COMBINING LONG SOLIDUS OVERLAY # →m̷→
0271 ; 0072 006E 0326 ; SL # ( ɱ → rn̦ ) LATIN SMALL LETTER M WITH HOOK → LATIN SMALL LETTER R, LATIN SMALL LETTER N, COMBINING COMMA BELOW # →m̡→
2129 ; 027F ; SL #* ( ℩ → ɿ ) TURNED GREEK SMALL LETTER IOTA → LATIN SMALL LETTER REVERSED R WITH FISHHOOK #
@ -2230,6 +2231,8 @@ A76B ; 021D ; SL # ( ꝫ → ȝ ) LATIN SMALL LETTER ET → LATIN SMALL LETTER Y
0491 ; 0433 02C8 ; SL # ( ґ → гˈ ) CYRILLIC SMALL LETTER GHE WITH UPTURN → CYRILLIC SMALL LETTER GHE, MODIFIER LETTER VERTICAL LINE #
04BD ; 0435 ; SL # ( ҽ → е ) CYRILLIC SMALL LETTER ABKHASIAN CHE → CYRILLIC SMALL LETTER IE # →e→
0511 ; 0454 ; SL # ( ԑ → є ) CYRILLIC SMALL LETTER REVERSED ZE → CYRILLIC SMALL LETTER UKRAINIAN IE # →ε→
0497 ; 0436 0329 ; SL # ( җ → ж̩ ) CYRILLIC SMALL LETTER ZHE WITH DESCENDER → CYRILLIC SMALL LETTER ZHE, COMBINING VERTICAL LINE BELOW #
@ -2274,7 +2277,7 @@ A76B ; 021D ; SL # ( ꝫ → ȝ ) LATIN SMALL LETTER ET → LATIN SMALL LETTER Y
04CC ; 04B7 ; SL # ( ӌ → ҷ ) CYRILLIC SMALL LETTER KHAKASSIAN CHE → CYRILLIC SMALL LETTER CHE WITH DESCENDER #
04BF ; 04BD 0328 ; SL # ( ҿ → ҽ̨ ) CYRILLIC SMALL LETTER ABKHASIAN CHE WITH DESCENDER → CYRILLIC SMALL LETTER ABKHASIAN CHE, COMBINING OGONEK # →ҽ̢→
04BF ; 04BD 0322 ; SL # ( ҿ → ҽ̢ ) CYRILLIC SMALL LETTER ABKHASIAN CHE WITH DESCENDER → CYRILLIC SMALL LETTER ABKHASIAN CHE, COMBINING RETROFLEX HOOK BELOW #
0463 ; 048D ; SL # ( ѣ → ҍ ) CYRILLIC SMALL LETTER YAT → CYRILLIC SMALL LETTER SEMISOFT SIGN #
@ -4195,7 +4198,7 @@ AA56 ; AA23 ; SL # ( ꩖ → ꨣ ) CHAM DIGIT SIX → CHAM LETTER RA #
14CC ; 14C7 00B7 ; SL # ( ᓌ → ᓇ· ) CANADIAN SYLLABICS WEST-CREE NWA → CANADIAN SYLLABICS NA, MIDDLE DOT # →ᓇᐧ→
14CE ; 14C8 14AB ; SL # ( ᓎ → ᓈᒫ ) CANADIAN SYLLABICS WEST-CREE NWAA → CANADIAN SYLLABICS NAA, CANADIAN SYLLABICS MAA #
14CE ; 14C8 00B7 ; SL # ( ᓎ → ᓈ· ) CANADIAN SYLLABICS WEST-CREE NWAA → CANADIAN SYLLABICS NAA, MIDDLE DOT # →ᓈᐧ→
1604 ; 14D3 ; SL # ( ᘄ → ᓓ ) CANADIAN SYLLABICS CARRIER NE → CANADIAN SYLLABICS LE #
@ -7631,7 +7634,7 @@ FAD7 ; 27ED3 ; SL # ( 𧻓 → 𧻓 ) CJK COMPATIBILITY IDEOGRAPH-FAD7 → CJK UN
2FA1D ; 2A600 ; SL # ( 𪘀 → 𪘀 ) CJK COMPATIBILITY IDEOGRAPH-2FA1D → CJK UNIFIED IDEOGRAPH-2A600 #
# total for (SL): 4918
# total for (SL): 4919
# Single-Script, Anycase Confusables
@ -7759,7 +7762,6 @@ FC63 ; FE7C 0670 ; SA #* ( ‎ﱣ‎ → ‎ﹼٰ‎ ) ARABIC LIGATURE SHADDA WI
309C ; FF9F ; SA #* ( ゜ → ﾟ ) KATAKANA-HIRAGANA SEMI-VOICED SOUND MARK → HALFWIDTH KATAKANA SEMI-VOICED SOUND MARK #
180E ; 0020 ; SA #* ( ᠎ → ) MONGOLIAN VOWEL SEPARATOR → SPACE #
2028 ; 0020 ; SA #* ( → ) LINE SEPARATOR → SPACE #
2029 ; 0020 ; SA #* ( → ) PARAGRAPH SEPARATOR → SPACE #
1680 ; 0020 ; SA #* (   → ) OGHAM SPACE MARK → SPACE #
@ -10039,6 +10041,8 @@ FF30 ; 0050 ; SA # ( Ｐ → P ) FULLWIDTH LATIN CAPITAL LETTER P → LATIN CAPI
1D0D ; 0072 006E ; SA # ( ᴍ → rn ) LATIN LETTER SMALL CAPITAL M → LATIN SMALL LETTER R, LATIN SMALL LETTER N # →м→→m→
028D ; 0072 006E ; SA # ( ʍ → rn ) LATIN SMALL LETTER TURNED W → LATIN SMALL LETTER R, LATIN SMALL LETTER N # →m→
20A5 ; 0072 006E 0338 ; SA #* ( ₥ → rn̸ ) MILL SIGN → LATIN SMALL LETTER R, LATIN SMALL LETTER N, COMBINING LONG SOLIDUS OVERLAY # →m̷→
0271 ; 0072 006E 0326 ; SA # ( ɱ → rn̦ ) LATIN SMALL LETTER M WITH HOOK → LATIN SMALL LETTER R, LATIN SMALL LETTER N, COMBINING COMMA BELOW # →m̡→
20A8 ; 0052 0073 ; SA #* ( ₨ → Rs ) RUPEE SIGN → LATIN CAPITAL LETTER R, LATIN SMALL LETTER S #
@ -10601,6 +10605,8 @@ FF3A ; 005A ; SA # ( Ｚ → Z ) FULLWIDTH LATIN CAPITAL LETTER Z → LATIN CAPI
0490 ; 0413 02C8 ; SA # ( Ґ → Гˈ ) CYRILLIC CAPITAL LETTER GHE WITH UPTURN → CYRILLIC CAPITAL LETTER GHE, MODIFIER LETTER VERTICAL LINE #
04BD ; 0435 ; SA # ( ҽ → е ) CYRILLIC SMALL LETTER ABKHASIAN CHE → CYRILLIC SMALL LETTER IE # →e→
0511 ; 0454 ; SA # ( ԑ → є ) CYRILLIC SMALL LETTER REVERSED ZE → CYRILLIC SMALL LETTER UKRAINIAN IE # →ε→
0497 ; 0436 0329 ; SA # ( җ → ж̩ ) CYRILLIC SMALL LETTER ZHE WITH DESCENDER → CYRILLIC SMALL LETTER ZHE, COMBINING VERTICAL LINE BELOW #
@ -10679,10 +10685,10 @@ FF3A ; 005A ; SA # ( Ｚ → Z ) FULLWIDTH LATIN CAPITAL LETTER Z → LATIN CAPI
04CB ; 04B6 ; SA # ( Ӌ → Ҷ ) CYRILLIC CAPITAL LETTER KHAKASSIAN CHE → CYRILLIC CAPITAL LETTER CHE WITH DESCENDER #
04BF ; 04BD 0328 ; SA # ( ҿ → ҽ̨ ) CYRILLIC SMALL LETTER ABKHASIAN CHE WITH DESCENDER → CYRILLIC SMALL LETTER ABKHASIAN CHE, COMBINING OGONEK # →ҽ̢→
04BE ; 04BC 0328 ; SA # ( Ҿ → Ҽ̨ ) CYRILLIC CAPITAL LETTER ABKHASIAN CHE WITH DESCENDER → CYRILLIC CAPITAL LETTER ABKHASIAN CHE, COMBINING OGONEK #
04BF ; 04BD 0322 ; SA # ( ҿ → ҽ̢ ) CYRILLIC SMALL LETTER ABKHASIAN CHE WITH DESCENDER → CYRILLIC SMALL LETTER ABKHASIAN CHE, COMBINING RETROFLEX HOOK BELOW #
048D ; 042C 0335 ; SA # ( ҍ → Ь̵ ) CYRILLIC SMALL LETTER SEMISOFT SIGN → CYRILLIC CAPITAL LETTER SOFT SIGN, COMBINING SHORT STROKE OVERLAY # →ѣ→
048C ; 042C 0335 ; SA # ( Ҍ → Ь̵ ) CYRILLIC CAPITAL LETTER SEMISOFT SIGN → CYRILLIC CAPITAL LETTER SOFT SIGN, COMBINING SHORT STROKE OVERLAY # →Ѣ→
0463 ; 042C 0335 ; SA # ( ѣ → Ь̵ ) CYRILLIC SMALL LETTER YAT → CYRILLIC CAPITAL LETTER SOFT SIGN, COMBINING SHORT STROKE OVERLAY #
@ -12242,7 +12248,7 @@ AA56 ; AA23 ; SA # ( ꩖ → ꨣ ) CHAM DIGIT SIX → CHAM LETTER RA #
14CC ; 14C7 00B7 ; SA # ( ᓌ → ᓇ· ) CANADIAN SYLLABICS WEST-CREE NWA → CANADIAN SYLLABICS NA, MIDDLE DOT # →ᓇᐧ→
14CE ; 14C8 14AB ; SA # ( ᓎ → ᓈᒫ ) CANADIAN SYLLABICS WEST-CREE NWAA → CANADIAN SYLLABICS NAA, CANADIAN SYLLABICS MAA #
14CE ; 14C8 00B7 ; SA # ( ᓎ → ᓈ· ) CANADIAN SYLLABICS WEST-CREE NWAA → CANADIAN SYLLABICS NAA, MIDDLE DOT # →ᓈᐧ→
1604 ; 14D3 ; SA # ( ᘄ → ᓓ ) CANADIAN SYLLABICS CARRIER NE → CANADIAN SYLLABICS LE #
@ -15636,7 +15642,7 @@ FAD7 ; 27ED3 ; SA # ( 𧻓 → 𧻓 ) CJK COMPATIBILITY IDEOGRAPH-FAD7 → CJK UN
2FA1D ; 2A600 ; SA # ( 𪘀 → 𪘀 ) CJK COMPATIBILITY IDEOGRAPH-2FA1D → CJK UNIFIED IDEOGRAPH-2A600 #
# total for (SA): 5145
# total for (SA): 5146
# Mixed-Script, Lowercase Confusables
@ -15779,7 +15785,6 @@ FC63 ; FE7C 0670 ; ML #* ( ‎ﱣ‎ → ‎ﹼٰ‎ ) ARABIC LIGATURE SHADDA WI
309C ; FF9F ; ML #* ( ゜ → ﾟ ) KATAKANA-HIRAGANA SEMI-VOICED SOUND MARK → HALFWIDTH KATAKANA SEMI-VOICED SOUND MARK #
180E ; 0020 ; ML #* ( ᠎ → ) MONGOLIAN VOWEL SEPARATOR → SPACE #
2028 ; 0020 ; ML #* ( → ) LINE SEPARATOR → SPACE #
2029 ; 0020 ; ML #* ( → ) PARAGRAPH SEPARATOR → SPACE #
1680 ; 0020 ; ML #* (   → ) OGHAM SPACE MARK → SPACE #
@ -17070,9 +17075,12 @@ FF45 ; 0065 ; ML # ( ｅ → e ) FULLWIDTH LATIN SMALL LETTER E → LATIN SMALL
1D65A ; 0065 ; ML # ( 𝙚 → e ) MATHEMATICAL SANS-SERIF BOLD ITALIC SMALL E → LATIN SMALL LETTER E #
1D68E ; 0065 ; ML # ( 𝚎 → e ) MATHEMATICAL MONOSPACE SMALL E → LATIN SMALL LETTER E #
0435 ; 0065 ; ML # ( е → e ) CYRILLIC SMALL LETTER IE → LATIN SMALL LETTER E #
04BD ; 0065 ; ML # ( ҽ → e ) CYRILLIC SMALL LETTER ABKHASIAN CHE → LATIN SMALL LETTER E #
011B ; 0115 ; ML # ( ě → ĕ ) LATIN SMALL LETTER E WITH CARON → LATIN SMALL LETTER E WITH BREVE #
04BF ; 0065 0328 ; ML # ( ҿ → ę ) CYRILLIC SMALL LETTER ABKHASIAN CHE WITH DESCENDER → LATIN SMALL LETTER E, COMBINING OGONEK # →ҽ̢→
0259 ; 01DD ; ML # ( ə → ǝ ) LATIN SMALL LETTER SCHWA → LATIN SMALL LETTER TURNED E #
04D9 ; 01DD ; ML # ( ә → ǝ ) CYRILLIC SMALL LETTER SCHWA → LATIN SMALL LETTER TURNED E #
@ -17675,6 +17683,8 @@ FF50 ; 0070 ; ML # ( ｐ → p ) FULLWIDTH LATIN SMALL LETTER P → LATIN SMALL
028D ; 0072 006E ; ML # ( ʍ → rn ) LATIN SMALL LETTER TURNED W → LATIN SMALL LETTER R, LATIN SMALL LETTER N # →m→
043C ; 0072 006E ; ML # ( м → rn ) CYRILLIC SMALL LETTER EM → LATIN SMALL LETTER R, LATIN SMALL LETTER N # →m→
20A5 ; 0072 006E 0338 ; ML #* ( ₥ → rn̸ ) MILL SIGN → LATIN SMALL LETTER R, LATIN SMALL LETTER N, COMBINING LONG SOLIDUS OVERLAY # →m̷→
0271 ; 0072 006E 0326 ; ML # ( ɱ → rn̦ ) LATIN SMALL LETTER M WITH HOOK → LATIN SMALL LETTER R, LATIN SMALL LETTER N, COMBINING COMMA BELOW # →m̡→
04CE ; 0072 006E 0326 ; ML # ( ӎ → rn̦ ) CYRILLIC SMALL LETTER EM WITH TAIL → LATIN SMALL LETTER R, LATIN SMALL LETTER N, COMBINING COMMA BELOW # →м̡→
@ -18065,8 +18075,6 @@ A645 ; 01A8 ; ML # ( ꙅ → ƨ ) CYRILLIC SMALL LETTER REVERSED DZE → LATIN S
04CC ; 04B7 ; ML # ( ӌ → ҷ ) CYRILLIC SMALL LETTER KHAKASSIAN CHE → CYRILLIC SMALL LETTER CHE WITH DESCENDER #
04BF ; 04BD 0328 ; ML # ( ҿ → ҽ̨ ) CYRILLIC SMALL LETTER ABKHASIAN CHE WITH DESCENDER → CYRILLIC SMALL LETTER ABKHASIAN CHE, COMBINING OGONEK # →ҽ̢→
2CBD ; 0448 ; ML # ( ⲽ → ш ) COPTIC SMALL LETTER CRYPTOGRAMMIC NI → CYRILLIC SMALL LETTER SHA #
044B ; 044C 0131 ; ML # ( ы → ьı ) CYRILLIC SMALL LETTER YERU → CYRILLIC SMALL LETTER SOFT SIGN, LATIN SMALL LETTER DOTLESS I #
@ -20086,7 +20094,7 @@ A4F4 ; 144C ; ML # ( ꓴ → ᑌ ) LISU LETTER U → CANADIAN SYLLABICS TE # →
14CC ; 14C7 00B7 ; ML # ( ᓌ → ᓇ· ) CANADIAN SYLLABICS WEST-CREE NWA → CANADIAN SYLLABICS NA, MIDDLE DOT # →ᓇᐧ→
14CE ; 14C8 14AB ; ML # ( ᓎ → ᓈᒫ ) CANADIAN SYLLABICS WEST-CREE NWAA → CANADIAN SYLLABICS NAA, CANADIAN SYLLABICS MAA #
14CE ; 14C8 00B7 ; ML # ( ᓎ → ᓈ· ) CANADIAN SYLLABICS WEST-CREE NWAA → CANADIAN SYLLABICS NAA, MIDDLE DOT # →ᓈᐧ→
1604 ; 14D3 ; ML # ( ᘄ → ᓓ ) CANADIAN SYLLABICS CARRIER NE → CANADIAN SYLLABICS LE #
@ -23527,7 +23535,7 @@ FAD7 ; 27ED3 ; ML # ( 𧻓 → 𧻓 ) CJK COMPATIBILITY IDEOGRAPH-FAD7 → CJK UN
2FA1D ; 2A600 ; ML # ( 𪘀 → 𪘀 ) CJK COMPATIBILITY IDEOGRAPH-2FA1D → CJK UNIFIED IDEOGRAPH-2A600 #
# total for (ML): 5135
# total for (ML): 5136
# Mixed-Script, Anycase Confusables
@ -23671,7 +23679,6 @@ FC63 ; FE7C 0670 ; MA #* ( ‎ﱣ‎ → ‎ﹼٰ‎ ) ARABIC LIGATURE SHADDA WI
309C ; FF9F ; MA #* ( ゜ → ﾟ ) KATAKANA-HIRAGANA SEMI-VOICED SOUND MARK → HALFWIDTH KATAKANA SEMI-VOICED SOUND MARK #
180E ; 0020 ; MA #* ( ᠎ → ) MONGOLIAN VOWEL SEPARATOR → SPACE #
2028 ; 0020 ; MA #* ( → ) LINE SEPARATOR → SPACE #
2029 ; 0020 ; MA #* ( → ) PARAGRAPH SEPARATOR → SPACE #
1680 ; 0020 ; MA #* (   → ) OGHAM SPACE MARK → SPACE #
@ -25156,6 +25163,7 @@ FF45 ; 0065 ; MA # ( ｅ → e ) FULLWIDTH LATIN SMALL LETTER E → LATIN SMALL
1D65A ; 0065 ; MA # ( 𝙚 → e ) MATHEMATICAL SANS-SERIF BOLD ITALIC SMALL E → LATIN SMALL LETTER E #
1D68E ; 0065 ; MA # ( 𝚎 → e ) MATHEMATICAL MONOSPACE SMALL E → LATIN SMALL LETTER E #
0435 ; 0065 ; MA # ( е → e ) CYRILLIC SMALL LETTER IE → LATIN SMALL LETTER E #
04BD ; 0065 ; MA # ( ҽ → e ) CYRILLIC SMALL LETTER ABKHASIAN CHE → LATIN SMALL LETTER E #
22FF ; 0045 ; MA #* ( ⋿ → E ) Z NOTATION BAG MEMBERSHIP → LATIN CAPITAL LETTER E #
FF25 ; 0045 ; MA # ( Ｅ → E ) FULLWIDTH LATIN CAPITAL LETTER E → LATIN CAPITAL LETTER E # →Ε→
@ -25187,6 +25195,8 @@ A4F0 ; 0045 ; MA # ( ꓰ → E ) LISU LETTER E → LATIN CAPITAL LETTER E #
011A ; 0114 ; MA # ( Ě → Ĕ ) LATIN CAPITAL LETTER E WITH CARON → LATIN CAPITAL LETTER E WITH BREVE #
04BF ; 0065 0328 ; MA # ( ҿ → ę ) CYRILLIC SMALL LETTER ABKHASIAN CHE WITH DESCENDER → LATIN SMALL LETTER E, COMBINING OGONEK # →ҽ̢→
0259 ; 01DD ; MA # ( ə → ǝ ) LATIN SMALL LETTER SCHWA → LATIN SMALL LETTER TURNED E #
04D9 ; 01DD ; MA # ( ә → ǝ ) CYRILLIC SMALL LETTER SCHWA → LATIN SMALL LETTER TURNED E #
@ -26221,6 +26231,8 @@ A4E3 ; 0052 ; MA # ( ꓣ → R ) LISU LETTER ZHA → LATIN CAPITAL LETTER R #
028D ; 0072 006E ; MA # ( ʍ → rn ) LATIN SMALL LETTER TURNED W → LATIN SMALL LETTER R, LATIN SMALL LETTER N # →m→
043C ; 0072 006E ; MA # ( м → rn ) CYRILLIC SMALL LETTER EM → LATIN SMALL LETTER R, LATIN SMALL LETTER N # →m→
20A5 ; 0072 006E 0338 ; MA #* ( ₥ → rn̸ ) MILL SIGN → LATIN SMALL LETTER R, LATIN SMALL LETTER N, COMBINING LONG SOLIDUS OVERLAY # →m̷→
0271 ; 0072 006E 0326 ; MA # ( ɱ → rn̦ ) LATIN SMALL LETTER M WITH HOOK → LATIN SMALL LETTER R, LATIN SMALL LETTER N, COMBINING COMMA BELOW # →m̡→
04CE ; 0072 006E 0326 ; MA # ( ӎ → rn̦ ) CYRILLIC SMALL LETTER EM WITH TAIL → LATIN SMALL LETTER R, LATIN SMALL LETTER N, COMBINING COMMA BELOW # →м̡→
@ -26915,8 +26927,6 @@ A645 ; 01A8 ; MA # ( ꙅ → ƨ ) CYRILLIC SMALL LETTER REVERSED DZE → LATIN S
04CB ; 04B6 ; MA # ( Ӌ → Ҷ ) CYRILLIC CAPITAL LETTER KHAKASSIAN CHE → CYRILLIC CAPITAL LETTER CHE WITH DESCENDER #
04BF ; 04BD 0328 ; MA # ( ҿ → ҽ̨ ) CYRILLIC SMALL LETTER ABKHASIAN CHE WITH DESCENDER → CYRILLIC SMALL LETTER ABKHASIAN CHE, COMBINING OGONEK # →ҽ̢→
04BE ; 04BC 0328 ; MA # ( Ҿ → Ҽ̨ ) CYRILLIC CAPITAL LETTER ABKHASIAN CHE WITH DESCENDER → CYRILLIC CAPITAL LETTER ABKHASIAN CHE, COMBINING OGONEK #
2CBD ; 0448 ; MA # ( ⲽ → ш ) COPTIC SMALL LETTER CRYPTOGRAMMIC NI → CYRILLIC SMALL LETTER SHA #
@ -28504,7 +28514,7 @@ AA56 ; AA23 ; MA # ( ꩖ → ꨣ ) CHAM DIGIT SIX → CHAM LETTER RA #
14CC ; 14C7 00B7 ; MA # ( ᓌ → ᓇ· ) CANADIAN SYLLABICS WEST-CREE NWA → CANADIAN SYLLABICS NA, MIDDLE DOT # →ᓇᐧ→
14CE ; 14C8 14AB ; MA # ( ᓎ → ᓈᒫ ) CANADIAN SYLLABICS WEST-CREE NWAA → CANADIAN SYLLABICS NAA, CANADIAN SYLLABICS MAA #
14CE ; 14C8 00B7 ; MA # ( ᓎ → ᓈ· ) CANADIAN SYLLABICS WEST-CREE NWAA → CANADIAN SYLLABICS NAA, MIDDLE DOT # →ᓈᐧ→
1604 ; 14D3 ; MA # ( ᘄ → ᓓ ) CANADIAN SYLLABICS CARRIER NE → CANADIAN SYLLABICS LE #
@ -31898,5 +31908,5 @@ FAD7 ; 27ED3 ; MA # ( 𧻓 → 𧻓 ) CJK COMPATIBILITY IDEOGRAPH-FAD7 → CJK UN
2FA1D ; 2A600 ; MA # ( 𪘀 → 𪘀 ) CJK COMPATIBILITY IDEOGRAPH-2FA1D → CJK UNIFIED IDEOGRAPH-2A600 #
# total for (MA): 5474
# total for (MA): 5475