From 973186e4dd63a1b1cdc9acbb72473d2efa822a72 Mon Sep 17 00:00:00 2001 From: Markus Scherer Date: Thu, 15 Aug 2024 10:43:54 -0700 Subject: [PATCH] Unicode 16 regenerated security files --- .../data/security/dev/IdentifierType.txt | 11 +- .../data/security/dev/confusables.txt | 10 +- .../data/security/dev/confusablesSummary.txt | 4 +- .../security/dev/data/draft-restrictions.txt | 7 +- .../data/security/dev/data/idnchars.txt | 8 +- .../data/security/dev/data/review.txt | 593 +++++++++--------- 6 files changed, 311 insertions(+), 322 deletions(-) diff --git a/unicodetools/data/security/dev/IdentifierType.txt b/unicodetools/data/security/dev/IdentifierType.txt index 2640a29fc..145d40c59 100644 --- a/unicodetools/data/security/dev/IdentifierType.txt +++ b/unicodetools/data/security/dev/IdentifierType.txt @@ -1,5 +1,5 @@ # IdentifierType.txt -# Date: 2024-05-04, 21:31:06 GMT +# Date: 2024-08-14, 23:39:57 GMT # © 2024 Unicode®, Inc. # Unicode and the Unicode Logo are registered trademarks of Unicode, Inc. in the U.S. and other countries. # For terms of use and license, see https://www.unicode.org/terms_of_use.html @@ -1406,12 +1406,14 @@ A930..A953 ; Exclusion # 5.1 [36] REJANG LETTER KA..RE 0830..083E ; Exclusion Not_XID # 5.2 [15] SAMARITAN PUNCTUATION NEQUDAA..SAMARITAN PUNCTUATION ANNAAU 1680 ; Exclusion Not_XID # 3.0 OGHAM SPACE MARK 169B..169C ; Exclusion Not_XID # 3.0 [2] OGHAM FEATHER MARK..OGHAM REVERSED FEATHER MARK +16EB..16ED ; Exclusion Not_XID # 3.0 [3] RUNIC SINGLE PUNCTUATION..RUNIC CROSS PUNCTUATION 1735..1736 ; Exclusion Not_XID # 3.2 [2] PHILIPPINE SINGLE PUNCTUATION..PHILIPPINE DOUBLE PUNCTUATION 1800..180A ; Exclusion Not_XID # 3.0 [11] MONGOLIAN BIRGA..MONGOLIAN NIRUGU 1A1E..1A1F ; Exclusion Not_XID # 4.1 [2] BUGINESE PALLAWA..BUGINESE END OF SECTION 2CE5..2CEA ; Exclusion Not_XID # 4.1 [6] COPTIC SYMBOL MI RO..COPTIC SYMBOL SHIMA SIMA 2CF9..2CFF ; Exclusion Not_XID # 4.1 [7] COPTIC OLD NUBIAN FULL STOP..COPTIC MORPHOLOGICAL DIVIDER 2E30 ; Exclusion Not_XID # 5.1 RING POINT +2E3C ; Exclusion Not_XID # 7.0 STENOGRAPHIC FULL STOP A874..A877 ; Exclusion Not_XID # 5.0 [4] PHAGS-PA SINGLE HEAD MARK..PHAGS-PA MARK DOUBLE SHAD A95F ; Exclusion Not_XID # 5.1 REJANG SECTION MARK 10100..10102 ; Exclusion Not_XID # 4.0 [3] AEGEAN WORD SEPARATOR LINE..AEGEAN CHECK MARK @@ -1509,7 +1511,7 @@ A95F ; Exclusion Not_XID # 5.1 REJANG SECTION MARK 1E5FF ; Exclusion Not_XID # 16.0 OL ONAL ABBREVIATION SIGN 1E8C7..1E8CF ; Exclusion Not_XID # 7.0 [9] MENDE KIKAKUI DIGIT ONE..MENDE KIKAKUI DIGIT NINE -# Total code points: 1138 +# Total code points: 1142 # Identifier_Type: Obsolete @@ -1752,7 +1754,6 @@ A8F8..A8FA ; Obsolete Not_XID # 5.2 [3] DEVANAGARI SIGN PUSH 1361..1368 ; Not_XID # 3.0 [8] ETHIOPIC WORDSPACE..ETHIOPIC PARAGRAPH SEPARATOR 1372..137C ; Not_XID # 3.0 [11] ETHIOPIC NUMBER TEN..ETHIOPIC NUMBER TEN THOUSAND 1390..1399 ; Not_XID # 4.1 [10] ETHIOPIC TONAL MARK YIZET..ETHIOPIC TONAL MARK KURT -16EB..16ED ; Not_XID # 3.0 [3] RUNIC SINGLE PUNCTUATION..RUNIC CROSS PUNCTUATION 17D4..17D6 ; Not_XID # 3.0 [3] KHMER SIGN KHAN..KHMER SIGN CAMNUC PII KUUH 17D9..17DB ; Not_XID # 3.0 [3] KHMER SIGN PHNAEK MUAN..KHMER CURRENCY SYMBOL RIEL 17F0..17F9 ; Not_XID # 4.0 [10] KHMER SYMBOL LEK ATTAK SON..KHMER SYMBOL LEK ATTAK PRAM-BUON @@ -1923,7 +1924,7 @@ A8F8..A8FA ; Obsolete Not_XID # 5.2 [3] DEVANAGARI SIGN PUSH 2E33..2E34 ; Not_XID # 6.1 [2] RAISED DOT..RAISED COMMA 2E36..2E38 ; Not_XID # 6.1 [3] DAGGER WITH LEFT GUARD..TURNED DAGGER 2E3A..2E3B ; Not_XID # 6.1 [2] TWO-EM DASH..THREE-EM DASH -2E3C..2E42 ; Not_XID # 7.0 [7] STENOGRAPHIC FULL STOP..DOUBLE LOW-REVERSED-9 QUOTATION MARK +2E3D..2E42 ; Not_XID # 7.0 [6] VERTICAL SIX DOTS..DOUBLE LOW-REVERSED-9 QUOTATION MARK 2E43..2E44 ; Not_XID # 9.0 [2] DASH WITH LEFT UPTURN..DOUBLE SUSPENSION MARK 2E45..2E49 ; Not_XID # 10.0 [5] INVERTED LOW KAVYKA..DOUBLE STACKED COMMA 2E4A..2E4E ; Not_XID # 11.0 [5] DOTTED SOLIDUS..PUNCTUS ELEVATUS MARK @@ -2193,7 +2194,7 @@ FFFD ; Not_XID # 1.1 REPLACEMENT CHARACTE 1FB94..1FBCA ; Not_XID # 13.0 [55] LEFT HALF INVERSE MEDIUM SHADE AND RIGHT HALF BLOCK..WHITE UP-POINTING CHEVRON 1FBCB..1FBEF ; Not_XID # 16.0 [37] WHITE CROSS MARK..TOP LEFT JUSTIFIED LOWER RIGHT QUARTER BLACK CIRCLE -# Total code points: 6415 +# Total code points: 6411 # Identifier_Type: Not_NFKC diff --git a/unicodetools/data/security/dev/confusables.txt b/unicodetools/data/security/dev/confusables.txt index ecbd58c23..f88841b7f 100644 --- a/unicodetools/data/security/dev/confusables.txt +++ b/unicodetools/data/security/dev/confusables.txt @@ -1,5 +1,5 @@ # confusables.txt -# Date: 2024-05-31, 21:12:55 GMT +# Date: 2024-08-14, 23:39:57 GMT # © 2024 Unicode®, Inc. # Unicode and the Unicode Logo are registered trademarks of Unicode, Inc. in the U.S. and other countries. # For terms of use and license, see https://www.unicode.org/terms_of_use.html @@ -593,7 +593,7 @@ FF40 ; 0027 ; MA #* ( ｀ → ' ) FULLWIDTH GRAVE ACCENT → APOSTROPHE # →‘ 02B9 ; 0027 ; MA # ( ʹ → ' ) MODIFIER LETTER PRIME → APOSTROPHE # 0374 ; 0027 ; MA # ( ʹ → ' ) GREEK NUMERAL SIGN → APOSTROPHE # →′→ 02C8 ; 0027 ; MA # ( ˈ → ' ) MODIFIER LETTER VERTICAL LINE → APOSTROPHE # -02CA ; 0027 ; MA # ( ˊ → ' ) MODIFIER LETTER ACUTE ACCENT → APOSTROPHE # →΄→→ʹ→ +02CA ; 0027 ; MA # ( ˊ → ' ) MODIFIER LETTER ACUTE ACCENT → APOSTROPHE # →ʹ→→′→ 02CB ; 0027 ; MA # ( ˋ → ' ) MODIFIER LETTER GRAVE ACCENT → APOSTROPHE # →｀→→‘→ 02F4 ; 0027 ; MA #* ( ˴ → ' ) MODIFIER LETTER MIDDLE GRAVE ACCENT → APOSTROPHE # →ˋ→→｀→→‘→ 02BB ; 0027 ; MA # ( ʻ → ' ) MODIFIER LETTER TURNED COMMA → APOSTROPHE # →‘→ @@ -1904,8 +1904,8 @@ ABAF ; 0063 ; MA # ( ꮯ → c ) CHEROKEE SMALL LETTER TLI → LATIN SMALL LETTE 2DED ; 0368 ; MA # ( ⷭ → ͨ ) COMBINING CYRILLIC LETTER ES → COMBINING LATIN SMALL LETTER C # 1F74C ; 0043 ; MA #* ( 🝌 → C ) ALCHEMICAL SYMBOL FOR CALX → LATIN CAPITAL LETTER C # -118F2 ; 0043 ; MA #* ( 𑣲 → C ) WARANG CITI NUMBER NINETY → LATIN CAPITAL LETTER C # 118E9 ; 0043 ; MA # ( 𑣩 → C ) WARANG CITI DIGIT NINE → LATIN CAPITAL LETTER C # +118F2 ; 0043 ; MA #* ( 𑣲 → C ) WARANG CITI NUMBER NINETY → LATIN CAPITAL LETTER C # FF23 ; 0043 ; MA # ( Ｃ → C ) FULLWIDTH LATIN CAPITAL LETTER C → LATIN CAPITAL LETTER C # →С→ 216D ; 0043 ; MA # ( Ⅽ → C ) ROMAN NUMERAL ONE HUNDRED → LATIN CAPITAL LETTER C # 2102 ; 0043 ; MA # ( ℂ → C ) DOUBLE-STRUCK CAPITAL C → LATIN CAPITAL LETTER C # @@ -3795,8 +3795,8 @@ A7DC ; 0245 0338 ; MA # ( Ƛ → Ʌ̸ ) LATIN CAPITAL LETTER LAMBDA WITH STROKE 1170F ; 0077 ; MA # ( 𑜏 → w ) AHOM LETTER SA → LATIN SMALL LETTER W # AB83 ; 0077 ; MA # ( ꮃ → w ) CHEROKEE SMALL LETTER LA → LATIN SMALL LETTER W # →ᴡ→ -118EF ; 0057 ; MA #* ( 𑣯 → W ) WARANG CITI NUMBER SIXTY → LATIN CAPITAL LETTER W # 118E6 ; 0057 ; MA # ( 𑣦 → W ) WARANG CITI DIGIT SIX → LATIN CAPITAL LETTER W # +118EF ; 0057 ; MA #* ( 𑣯 → W ) WARANG CITI NUMBER SIXTY → LATIN CAPITAL LETTER W # 1CCEC ; 0057 ; MA #* ( 𜳬 → W ) OUTLINED LATIN CAPITAL LETTER W → LATIN CAPITAL LETTER W # 1D416 ; 0057 ; MA # ( 𝐖 → W ) MATHEMATICAL BOLD CAPITAL W → LATIN CAPITAL LETTER W # 1D44A ; 0057 ; MA # ( 𝑊 → W ) MATHEMATICAL ITALIC CAPITAL W → LATIN CAPITAL LETTER W # @@ -4002,8 +4002,8 @@ A76B ; 021D ; MA # ( ꝫ → ȝ ) LATIN SMALL LETTER ET → LATIN SMALL LETTER Y AB93 ; 007A ; MA # ( ꮓ → z ) CHEROKEE SMALL LETTER NO → LATIN SMALL LETTER Z # →ᴢ→ 118C4 ; 007A ; MA # ( 𑣄 → z ) WARANG CITI SMALL LETTER YA → LATIN SMALL LETTER Z # -102F5 ; 005A ; MA #* ( 𐋵 → Z ) COPTIC EPACT NUMBER THREE HUNDRED → LATIN CAPITAL LETTER Z # 118E5 ; 005A ; MA # ( 𑣥 → Z ) WARANG CITI DIGIT FIVE → LATIN CAPITAL LETTER Z # +102F5 ; 005A ; MA #* ( 𐋵 → Z ) COPTIC EPACT NUMBER THREE HUNDRED → LATIN CAPITAL LETTER Z # FF3A ; 005A ; MA # ( Ｚ → Z ) FULLWIDTH LATIN CAPITAL LETTER Z → LATIN CAPITAL LETTER Z # →Ζ→ 2124 ; 005A ; MA # ( ℤ → Z ) DOUBLE-STRUCK CAPITAL Z → LATIN CAPITAL LETTER Z # 2128 ; 005A ; MA # ( ℨ → Z ) BLACK-LETTER CAPITAL Z → LATIN CAPITAL LETTER Z # diff --git a/unicodetools/data/security/dev/confusablesSummary.txt b/unicodetools/data/security/dev/confusablesSummary.txt index 093100c4b..8641b2fcc 100644 --- a/unicodetools/data/security/dev/confusablesSummary.txt +++ b/unicodetools/data/security/dev/confusablesSummary.txt @@ -1,5 +1,5 @@ # confusablesSummary.txt -# Date: 2024-05-31, 21:12:55 GMT +# Date: 2024-08-14, 23:39:56 GMT # © 2024 Unicode®, Inc. # Unicode and the Unicode Logo are registered trademarks of Unicode, Inc. in the U.S. and other countries. # For terms of use and license, see https://www.unicode.org/terms_of_use.html @@ -91,7 +91,7 @@ ← (‎ ʽ ‎) 02BD MODIFIER LETTER REVERSED COMMA # →‘→ ← (‎ ʾ ‎) 02BE MODIFIER LETTER RIGHT HALF RING # →ʼ→→′→ ← (‎ ˈ ‎) 02C8 MODIFIER LETTER VERTICAL LINE -← (‎ ˊ ‎) 02CA MODIFIER LETTER ACUTE ACCENT # →΄→→ʹ→ +← (‎ ˊ ‎) 02CA MODIFIER LETTER ACUTE ACCENT # →ʹ→→′→ ← (‎ ˋ ‎) 02CB MODIFIER LETTER GRAVE ACCENT # →｀→→‘→ ← (‎ ߴ ‎) 07F4 NKO HIGH TONE APOSTROPHE # →’→ ← (‎ ߵ ‎) 07F5 NKO LOW TONE APOSTROPHE # →‘→ diff --git a/unicodetools/data/security/dev/data/draft-restrictions.txt b/unicodetools/data/security/dev/data/draft-restrictions.txt index acb5babdc..a0b42f240 100644 --- a/unicodetools/data/security/dev/data/draft-restrictions.txt +++ b/unicodetools/data/security/dev/data/draft-restrictions.txt @@ -24194,6 +24194,7 @@ AB63 ; ; Uncommon_Use # (ꭣ) LATIN SMALL LETTER UO 0038 ; Allowed ; Recommended # (8) DIGIT EIGHT 0039 ; Allowed ; Recommended # (9) DIGIT NINE 0041..005A ; Allowed ; Recommended # [26] (A..Z) LATIN CAPITAL LETTER A..LATIN CAPITAL LETTER Z +005F ; Allowed ; Recommended # (_) LOW LINE 0061 ; Allowed ; Recommended # (a) LATIN SMALL LETTER A 0062 ; Allowed ; Recommended # (b) LATIN SMALL LETTER B 0063 ; Allowed ; Recommended # (c) LATIN SMALL LETTER C @@ -54817,11 +54818,7 @@ FA29 ; Allowed ; Recommended # (﨩) CJK COMPATIBILITY IDEOGRAPH- 323AF ; Allowed ; Recommended # (𲎯) CJK UNIFIED IDEOGRAPH-323AF E0100..E01EF ; Allowed ; Recommended # [240] (U+E0100..U+E01EF) VARIATION SELECTOR-17..VARIATION SELECTOR-256 -# Total code points: 113001 - -005F ; ~IDNA # (_) LOW LINE - -# Total code points: 1 +# Total code points: 113002 0000..002F ; ~Unicode Identifier # [48] (U+0000../) ..SOLIDUS 003A..0040 ; ~Unicode Identifier # [7] (:..@) COLON..COMMERCIAL AT diff --git a/unicodetools/data/security/dev/data/idnchars.txt b/unicodetools/data/security/dev/data/idnchars.txt index 5375ea8eb..919990f84 100644 --- a/unicodetools/data/security/dev/data/idnchars.txt +++ b/unicodetools/data/security/dev/data/idnchars.txt @@ -1,5 +1,5 @@ # idnchars.txt -# Date: 2024-05-03, 03:51:22 GMT +# Date: 2024-08-14, 23:39:58 GMT # © 2024 Unicode®, Inc. # Unicode and the Unicode Logo are registered trademarks of Unicode, Inc. in the U.S. and other countries. # For terms of use and license, see https://www.unicode.org/terms_of_use.html @@ -11,8 +11,10 @@ # # Allowed as output characters +0027 ; output # (') APOSTROPHE 002D..002E ; output # [2] (-...) HYPHEN-MINUS..FULL STOP -0030..0039 ; output # [10] (0..9) DIGIT ZERO..DIGIT NINE +0030..003A ; output # [11] (0..:) DIGIT ZERO..COLON +005F ; output # (_) LOW LINE 0061..007A ; output # [26] (a..z) LATIN SMALL LETTER A..LATIN SMALL LETTER Z 00B7 ; output # (·) MIDDLE DOT 00DF..00F6 ; output # [24] (ß..ö) LATIN SMALL LETTER SHARP S..LATIN SMALL LETTER O WITH DIAERESIS @@ -663,7 +665,7 @@ FA27..FA29 ; output # [3] (﨧..﨩) CJK COMPATIBILITY IDEOGRAPH-FA27..CJK 30000..3134A ; output # [4939] (𰀀..𱍊) CJK UNIFIED IDEOGRAPH-30000..CJK UNIFIED IDEOGRAPH-3134A 31350..323AF ; output # [4192] (𱍐..𲎯) CJK UNIFIED IDEOGRAPH-31350..CJK UNIFIED IDEOGRAPH-323AF -# Total code points: 112107 +# Total code points: 112110 # Not allowed at start of identifier diff --git a/unicodetools/data/security/dev/data/review.txt b/unicodetools/data/security/dev/data/review.txt index a9722908f..ce6f71b01 100644 --- a/unicodetools/data/security/dev/data/review.txt +++ b/unicodetools/data/security/dev/data/review.txt @@ -1,5 +1,5 @@ # review.txt -# Date: 2024-05-04, 21:31:07 GMT +# Date: 2024-08-14, 23:39:58 GMT # © 2024 Unicode®, Inc. # Unicode and the Unicode Logo are registered trademarks of Unicode, Inc. in the U.S. and other countries. # For terms of use and license, see https://www.unicode.org/terms_of_use.html @@ -12,8 +12,54 @@ # Characters allowed in IDNA +0000 ; Restricted ; Not_XID # (U+0000) +0001 ; Restricted ; Not_XID # (U+0001) +0002 ; Restricted ; Not_XID # (U+0002) +0003 ; Restricted ; Not_XID # (U+0003) +0004 ; Restricted ; Not_XID # (U+0004) +0005 ; Restricted ; Not_XID # (U+0005) +0006 ; Restricted ; Not_XID # (U+0006) +0007 ; Restricted ; Not_XID # (U+0007) +0008 ; Restricted ; Not_XID # (U+0008) +0009 ; Restricted ; Not_XID # (U+0009) +000A ; Restricted ; Not_XID # (U+000A) +000B ; Restricted ; Not_XID # (U+000B) +000C ; Restricted ; Not_XID # (U+000C) +000D ; Restricted ; Not_XID # (U+000D) +000E ; Restricted ; Not_XID # (U+000E) +000F ; Restricted ; Not_XID # (U+000F) +0010 ; Restricted ; Not_XID # (U+0010) +0011 ; Restricted ; Not_XID # (U+0011) +0012 ; Restricted ; Not_XID # (U+0012) +0013 ; Restricted ; Not_XID # (U+0013) +0014 ; Restricted ; Not_XID # (U+0014) +0015 ; Restricted ; Not_XID # (U+0015) +0016 ; Restricted ; Not_XID # (U+0016) +0017 ; Restricted ; Not_XID # (U+0017) +0018 ; Restricted ; Not_XID # (U+0018) +0019 ; Restricted ; Not_XID # (U+0019) +001A ; Restricted ; Not_XID # (U+001A) +001B ; Restricted ; Not_XID # (U+001B) +001C ; Restricted ; Not_XID # (U+001C) +001D ; Restricted ; Not_XID # (U+001D) +001E ; Restricted ; Not_XID # (U+001E) +001F ; Restricted ; Not_XID # (U+001F) +0020 ; Restricted ; Not_XID # (U+0020) SPACE +0021 ; Restricted ; Not_XID # (!) EXCLAMATION MARK +0022 ; Restricted ; Not_XID # (") QUOTATION MARK +0023 ; Restricted ; Not_XID # (#) NUMBER SIGN +0024 ; Restricted ; Not_XID # ($) DOLLAR SIGN +0025 ; Restricted ; Not_XID # (%) PERCENT SIGN +0026 ; Restricted ; Not_XID # (&) AMPERSAND +0027 ; output # (') APOSTROPHE +0028 ; Restricted ; Not_XID # (() LEFT PARENTHESIS +0029 ; Restricted ; Not_XID # ()) RIGHT PARENTHESIS +002A ; Restricted ; Not_XID # (*) ASTERISK +002B ; Restricted ; Not_XID # (+) PLUS SIGN +002C ; Restricted ; Not_XID # (,) COMMA 002D ; output # (-) HYPHEN-MINUS 002E ; output # (.) FULL STOP +002F ; Restricted ; Not_XID # (/) SOLIDUS 0030 ; output # (0) DIGIT ZERO 0031 ; output # (1) DIGIT ONE 0032 ; output # (2) DIGIT TWO @@ -24,6 +70,13 @@ 0037 ; output # (7) DIGIT SEVEN 0038 ; output # (8) DIGIT EIGHT 0039 ; output # (9) DIGIT NINE +003A ; output # (:) COLON +003B ; Restricted ; Not_XID # (;) SEMICOLON +003C ; Restricted ; Not_XID # (<) LESS-THAN SIGN +003D ; Restricted ; Not_XID # (=) EQUALS SIGN +003E ; Restricted ; Not_XID # (>) GREATER-THAN SIGN +003F ; Restricted ; Not_XID # (?) QUESTION MARK +0040 ; Restricted ; Not_XID # (@) COMMERCIAL AT 0041 ; input # (A) LATIN CAPITAL LETTER A 0042 ; input # (B) LATIN CAPITAL LETTER B 0043 ; input # (C) LATIN CAPITAL LETTER C @@ -50,6 +103,12 @@ 0058 ; input # (X) LATIN CAPITAL LETTER X 0059 ; input # (Y) LATIN CAPITAL LETTER Y 005A ; input # (Z) LATIN CAPITAL LETTER Z +005B ; Restricted ; Not_XID # ([) LEFT SQUARE BRACKET +005C ; Restricted ; Not_XID # (\) REVERSE SOLIDUS +005D ; Restricted ; Not_XID # (]) RIGHT SQUARE BRACKET +005E ; Restricted ; Not_XID # (^) CIRCUMFLEX ACCENT +005F ; output # (_) LOW LINE +0060 ; Restricted ; Not_XID # (`) GRAVE ACCENT 0061 ; output # (a) LATIN SMALL LETTER A 0062 ; output # (b) LATIN SMALL LETTER B 0063 ; output # (c) LATIN SMALL LETTER C @@ -76,6 +135,12 @@ 0078 ; output # (x) LATIN SMALL LETTER X 0079 ; output # (y) LATIN SMALL LETTER Y 007A ; output # (z) LATIN SMALL LETTER Z +007B ; Restricted ; Not_XID # ({) LEFT CURLY BRACKET +007C ; Restricted ; Not_XID # (|) VERTICAL LINE +007D ; Restricted ; Not_XID # (}) RIGHT CURLY BRACKET +007E ; Restricted ; Not_XID # (~) TILDE +007F ; Restricted ; Not_XID # (U+007F) +00A0 ; Restricted ; Not_XID # (U+00A0) NO-BREAK SPACE 00A1 ; Restricted ; Not_XID # (¡) INVERTED EXCLAMATION MARK 00A2 ; Restricted ; Not_XID # (¢) CENT SIGN 00A3 ; Restricted ; Not_XID # (£) POUND SIGN @@ -83,19 +148,23 @@ 00A5 ; Restricted ; Not_XID # (¥) YEN SIGN 00A6 ; Restricted ; Not_XID # (¦) BROKEN BAR 00A7 ; Restricted ; Not_XID # (§) SECTION SIGN +00A8 ; Restricted ; Not_XID # (¨) DIAERESIS 00A9 ; Restricted ; Not_XID # (©) COPYRIGHT SIGN 00AA ; input-lenient # (ª) FEMININE ORDINAL INDICATOR 00AB ; Restricted ; Not_XID # («) LEFT-POINTING DOUBLE ANGLE QUOTATION MARK 00AC ; Restricted ; Not_XID # (¬) NOT SIGN 00AD ; Restricted ; Not_XID # (U+00AD) SOFT HYPHEN 00AE ; Restricted ; Not_XID # (®) REGISTERED SIGN +00AF ; Restricted ; Not_XID # (¯) MACRON 00B0 ; Restricted ; Not_XID # (°) DEGREE SIGN 00B1 ; Restricted ; Not_XID # (±) PLUS-MINUS SIGN 00B2 ; Restricted ; Not_XID # (²) SUPERSCRIPT TWO 00B3 ; Restricted ; Not_XID # (³) SUPERSCRIPT THREE +00B4 ; Restricted ; Not_XID # (´) ACUTE ACCENT 00B5 ; input-lenient # (µ) MICRO SIGN 00B6 ; Restricted ; Not_XID # (¶) PILCROW SIGN 00B7 ; output # (·) MIDDLE DOT +00B8 ; Restricted ; Not_XID # (¸) CEDILLA 00B9 ; Restricted ; Not_XID # (¹) SUPERSCRIPT ONE 00BA ; input-lenient # (º) MASCULINE ORDINAL INDICATOR 00BB ; Restricted ; Not_XID # (») RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK @@ -639,6 +708,12 @@ 02D5 ; Restricted ; Not_XID # (˕) MODIFIER LETTER DOWN TACK 02D6 ; Restricted ; Not_XID # (˖) MODIFIER LETTER PLUS SIGN 02D7 ; Restricted ; Not_XID # (˗) MODIFIER LETTER MINUS SIGN +02D8 ; Restricted ; Not_XID # (˘) BREVE +02D9 ; Restricted ; Not_XID # (˙) DOT ABOVE +02DA ; Restricted ; Not_XID # (˚) RING ABOVE +02DB ; Restricted ; Not_XID # (˛) OGONEK +02DC ; Restricted ; Not_XID # (˜) SMALL TILDE +02DD ; Restricted ; Not_XID # (˝) DOUBLE ACUTE ACCENT 02DE ; Restricted ; Not_XID # (˞) MODIFIER LETTER RHOTIC HOOK 02DF ; Restricted ; Not_XID # (˟) MODIFIER LETTER CROSS ACCENT 02E0 ; Restricted ; output-disallowed # (ˠ) MODIFIER LETTER SMALL GAMMA @@ -793,10 +868,14 @@ 0375 ; output # (͵) GREEK LOWER NUMERAL SIGN 0376 ; Restricted ; Obsolete # (Ͷ) GREEK CAPITAL LETTER PAMPHYLIAN DIGAMMA 0377 ; Restricted ; Obsolete # (ͷ) GREEK SMALL LETTER PAMPHYLIAN DIGAMMA +037A ; Restricted ; Not_XID # (ͺ) GREEK YPOGEGRAMMENI 037B ; output # (ͻ) GREEK SMALL REVERSED LUNATE SIGMA SYMBOL 037C ; output # (ͼ) GREEK SMALL DOTTED LUNATE SIGMA SYMBOL 037D ; output # (ͽ) GREEK SMALL REVERSED DOTTED LUNATE SIGMA SYMBOL +037E ; Restricted ; Not_XID # (;) GREEK QUESTION MARK 037F ; Restricted ; Obsolete # (Ϳ) GREEK CAPITAL LETTER YOT +0384 ; Restricted ; Not_XID # (΄) GREEK TONOS +0385 ; Restricted ; Not_XID # (΅) GREEK DIALYTIKA TONOS 0386 ; input # (Ά) GREEK CAPITAL LETTER ALPHA WITH TONOS 0387 ; input-lenient # (·) GREEK ANO TELEIA 0388 ; input # (Έ) GREEK CAPITAL LETTER EPSILON WITH TONOS @@ -5584,7 +5663,11 @@ 1FBA ; input # (Ὰ) GREEK CAPITAL LETTER ALPHA WITH VARIA 1FBB ; input-lenient # (Ά) GREEK CAPITAL LETTER ALPHA WITH OXIA 1FBC ; input # (ᾼ) GREEK CAPITAL LETTER ALPHA WITH PROSGEGRAMMENI +1FBD ; Restricted ; Not_XID # (᾽) GREEK KORONIS 1FBE ; input-lenient # (ι) GREEK PROSGEGRAMMENI +1FBF ; Restricted ; Not_XID # (᾿) GREEK PSILI +1FC0 ; Restricted ; Not_XID # (῀) GREEK PERISPOMENI +1FC1 ; Restricted ; Not_XID # (῁) GREEK DIALYTIKA AND PERISPOMENI 1FC2 ; input # (ῂ) GREEK SMALL LETTER ETA WITH VARIA AND YPOGEGRAMMENI 1FC3 ; input # (ῃ) GREEK SMALL LETTER ETA WITH YPOGEGRAMMENI 1FC4 ; input # (ῄ) GREEK SMALL LETTER ETA WITH OXIA AND YPOGEGRAMMENI @@ -5595,6 +5678,9 @@ 1FCA ; input # (Ὴ) GREEK CAPITAL LETTER ETA WITH VARIA 1FCB ; input-lenient # (Ή) GREEK CAPITAL LETTER ETA WITH OXIA 1FCC ; input # (ῌ) GREEK CAPITAL LETTER ETA WITH PROSGEGRAMMENI +1FCD ; Restricted ; Not_XID # (῍) GREEK PSILI AND VARIA +1FCE ; Restricted ; Not_XID # (῎) GREEK PSILI AND OXIA +1FCF ; Restricted ; Not_XID # (῏) GREEK PSILI AND PERISPOMENI 1FD0 ; output # (ῐ) GREEK SMALL LETTER IOTA WITH VRACHY 1FD1 ; output # (ῑ) GREEK SMALL LETTER IOTA WITH MACRON 1FD2 ; output # (ῒ) GREEK SMALL LETTER IOTA WITH DIALYTIKA AND VARIA @@ -5605,6 +5691,9 @@ 1FD9 ; input # (Ῑ) GREEK CAPITAL LETTER IOTA WITH MACRON 1FDA ; input # (Ὶ) GREEK CAPITAL LETTER IOTA WITH VARIA 1FDB ; input-lenient # (Ί) GREEK CAPITAL LETTER IOTA WITH OXIA +1FDD ; Restricted ; Not_XID # (῝) GREEK DASIA AND VARIA +1FDE ; Restricted ; Not_XID # (῞) GREEK DASIA AND OXIA +1FDF ; Restricted ; Not_XID # (῟) GREEK DASIA AND PERISPOMENI 1FE0 ; output # (ῠ) GREEK SMALL LETTER UPSILON WITH VRACHY 1FE1 ; output # (ῡ) GREEK SMALL LETTER UPSILON WITH MACRON 1FE2 ; output # (ῢ) GREEK SMALL LETTER UPSILON WITH DIALYTIKA AND VARIA @@ -5618,6 +5707,9 @@ 1FEA ; input # (Ὺ) GREEK CAPITAL LETTER UPSILON WITH VARIA 1FEB ; input-lenient # (Ύ) GREEK CAPITAL LETTER UPSILON WITH OXIA 1FEC ; input # (Ῥ) GREEK CAPITAL LETTER RHO WITH DASIA +1FED ; Restricted ; Not_XID # (῭) GREEK DIALYTIKA AND VARIA +1FEE ; Restricted ; Not_XID # (΅) GREEK DIALYTIKA AND OXIA +1FEF ; Restricted ; Not_XID # (`) GREEK VARIA 1FF2 ; input # (ῲ) GREEK SMALL LETTER OMEGA WITH VARIA AND YPOGEGRAMMENI 1FF3 ; input # (ῳ) GREEK SMALL LETTER OMEGA WITH YPOGEGRAMMENI 1FF4 ; input # (ῴ) GREEK SMALL LETTER OMEGA WITH OXIA AND YPOGEGRAMMENI @@ -5628,6 +5720,19 @@ 1FFA ; input # (Ὼ) GREEK CAPITAL LETTER OMEGA WITH VARIA 1FFB ; input-lenient # (Ώ) GREEK CAPITAL LETTER OMEGA WITH OXIA 1FFC ; input # (ῼ) GREEK CAPITAL LETTER OMEGA WITH PROSGEGRAMMENI +1FFD ; Restricted ; Not_XID # (´) GREEK OXIA +1FFE ; Restricted ; Not_XID # (῾) GREEK DASIA +2000 ; Restricted ; Not_XID # (U+2000) EN QUAD +2001 ; Restricted ; Not_XID # (U+2001) EM QUAD +2002 ; Restricted ; Not_XID # (U+2002) EN SPACE +2003 ; Restricted ; Not_XID # (U+2003) EM SPACE +2004 ; Restricted ; Not_XID # (U+2004) THREE-PER-EM SPACE +2005 ; Restricted ; Not_XID # (U+2005) FOUR-PER-EM SPACE +2006 ; Restricted ; Not_XID # (U+2006) SIX-PER-EM SPACE +2007 ; Restricted ; Not_XID # (U+2007) FIGURE SPACE +2008 ; Restricted ; Not_XID # (U+2008) PUNCTUATION SPACE +2009 ; Restricted ; Not_XID # (U+2009) THIN SPACE +200A ; Restricted ; Not_XID # (U+200A) HAIR SPACE 200B ; Restricted ; Not_XID # (U+200B) ZERO WIDTH SPACE 200C..200D ; output # [2] (U+200C..U+200D) ZERO WIDTH NON-JOINER..ZERO WIDTH JOINER 2010 ; output # (‐) HYPHEN @@ -5637,6 +5742,7 @@ 2014 ; Restricted ; Not_XID # (—) EM DASH 2015 ; Restricted ; Not_XID # (―) HORIZONTAL BAR 2016 ; Restricted ; Not_XID # (‖) DOUBLE VERTICAL LINE +2017 ; Restricted ; Not_XID # (‗) DOUBLE LOW LINE 2018 ; Restricted ; Not_XID # (‘) LEFT SINGLE QUOTATION MARK 2019 ; output # (’) RIGHT SINGLE QUOTATION MARK 201A ; Restricted ; Not_XID # (‚) SINGLE LOW-9 QUOTATION MARK @@ -5650,6 +5756,7 @@ 2022 ; Restricted ; Not_XID # (•) BULLET 2023 ; Restricted ; Not_XID # (‣) TRIANGULAR BULLET 2027 ; output # (‧) HYPHENATION POINT +202F ; Restricted ; Not_XID # (U+202F) NARROW NO-BREAK SPACE 2030 ; Restricted ; Not_XID # (‰) PER MILLE SIGN 2031 ; Restricted ; Not_XID # (‱) PER TEN THOUSAND SIGN 2032 ; Restricted ; Not_XID # (′) PRIME @@ -5662,7 +5769,9 @@ 2039 ; Restricted ; Not_XID # (‹) SINGLE LEFT-POINTING ANGLE QUOTATION MARK 203A ; Restricted ; Not_XID # (›) SINGLE RIGHT-POINTING ANGLE QUOTATION MARK 203B ; Restricted ; Not_XID # (※) REFERENCE MARK +203C ; Restricted ; Not_XID # (‼) DOUBLE EXCLAMATION MARK 203D ; Restricted ; Not_XID # (‽) INTERROBANG +203E ; Restricted ; Not_XID # (‾) OVERLINE 203F ; Restricted ; Technical # (‿) UNDERTIE 2040 ; Restricted ; Technical # (⁀) CHARACTER TIE 2041 ; Restricted ; Not_XID # (⁁) CARET INSERTION POINT @@ -5671,6 +5780,9 @@ 2044 ; Restricted ; Not_XID # (⁄) FRACTION SLASH 2045 ; Restricted ; Not_XID # (⁅) LEFT SQUARE BRACKET WITH QUILL 2046 ; Restricted ; Not_XID # (⁆) RIGHT SQUARE BRACKET WITH QUILL +2047 ; Restricted ; Not_XID # (⁇) DOUBLE QUESTION MARK +2048 ; Restricted ; Not_XID # (⁈) QUESTION EXCLAMATION MARK +2049 ; Restricted ; Not_XID # (⁉) EXCLAMATION QUESTION MARK 204A ; Restricted ; Not_XID # (⁊) TIRONIAN SIGN ET 204B ; Restricted ; Not_XID # (⁋) REVERSED PILCROW SIGN 204C ; Restricted ; Not_XID # (⁌) BLACK LEFTWARDS BULLET @@ -5692,6 +5804,7 @@ 205C ; Restricted ; Not_XID # (⁜) DOTTED CROSS 205D ; Restricted ; Not_XID # (⁝) TRICOLON 205E ; Restricted ; Not_XID # (⁞) VERTICAL FOUR DOTS +205F ; Restricted ; Not_XID # (U+205F) MEDIUM MATHEMATICAL SPACE 2060..2064 ; Restricted ; Not_XID # [5] (U+2060..U+2064) WORD JOINER..INVISIBLE PLUS 206A..206F ; Restricted ; Deprecated # [6] (U+206A..U+206F) INHIBIT SYMMETRIC SWAPPING..NOMINAL DIGIT SHAPES 2070 ; Restricted ; Not_XID # (⁰) SUPERSCRIPT ZERO @@ -5702,7 +5815,11 @@ 2077 ; Restricted ; Not_XID # (⁷) SUPERSCRIPT SEVEN 2078 ; Restricted ; Not_XID # (⁸) SUPERSCRIPT EIGHT 2079 ; Restricted ; Not_XID # (⁹) SUPERSCRIPT NINE +207A ; Restricted ; Not_XID # (⁺) SUPERSCRIPT PLUS SIGN 207B ; Restricted ; Not_XID # (⁻) SUPERSCRIPT MINUS +207C ; Restricted ; Not_XID # (⁼) SUPERSCRIPT EQUALS SIGN +207D ; Restricted ; Not_XID # (⁽) SUPERSCRIPT LEFT PARENTHESIS +207E ; Restricted ; Not_XID # (⁾) SUPERSCRIPT RIGHT PARENTHESIS 207F ; input-lenient # (ⁿ) SUPERSCRIPT LATIN SMALL LETTER N 2080 ; Restricted ; Not_XID # (₀) SUBSCRIPT ZERO 2081 ; Restricted ; Not_XID # (₁) SUBSCRIPT ONE @@ -5714,7 +5831,11 @@ 2087 ; Restricted ; Not_XID # (₇) SUBSCRIPT SEVEN 2088 ; Restricted ; Not_XID # (₈) SUBSCRIPT EIGHT 2089 ; Restricted ; Not_XID # (₉) SUBSCRIPT NINE +208A ; Restricted ; Not_XID # (₊) SUBSCRIPT PLUS SIGN 208B ; Restricted ; Not_XID # (₋) SUBSCRIPT MINUS +208C ; Restricted ; Not_XID # (₌) SUBSCRIPT EQUALS SIGN +208D ; Restricted ; Not_XID # (₍) SUBSCRIPT LEFT PARENTHESIS +208E ; Restricted ; Not_XID # (₎) SUBSCRIPT RIGHT PARENTHESIS 2090 ; input-lenient # (ₐ) LATIN SUBSCRIPT SMALL LETTER A 2091 ; input-lenient # (ₑ) LATIN SUBSCRIPT SMALL LETTER E 2092 ; input-lenient # (ₒ) LATIN SUBSCRIPT SMALL LETTER O @@ -5794,9 +5915,13 @@ 20EE ; Restricted ; Technical # (⃮) COMBINING LEFT ARROW BELOW 20EF ; Restricted ; Technical # (⃯) COMBINING RIGHT ARROW BELOW 20F0 ; Restricted ; Technical # (⃰) COMBINING ASTERISK ABOVE +2100 ; Restricted ; Not_XID # (℀) ACCOUNT OF +2101 ; Restricted ; Not_XID # (℁) ADDRESSED TO THE SUBJECT 2102 ; input-lenient # (ℂ) DOUBLE-STRUCK CAPITAL C 2103 ; Restricted ; Not_XID # (℃) DEGREE CELSIUS 2104 ; Restricted ; Not_XID # (℄) CENTRE LINE SYMBOL +2105 ; Restricted ; Not_XID # (℅) CARE OF +2106 ; Restricted ; Not_XID # (℆) CADA UNA 2107 ; Restricted ; output-disallowed # (ℇ) EULER CONSTANT 2108 ; Restricted ; Not_XID # (℈) SCRUPLE 2109 ; Restricted ; Not_XID # (℉) DEGREE FAHRENHEIT @@ -6607,8 +6732,8 @@ 2448 ; Restricted ; Not_XID # (⑈) OCR DASH 2449 ; Restricted ; Not_XID # (⑉) OCR CUSTOMER ACCOUNT NUMBER 244A ; Restricted ; Not_XID # (⑊) OCR DOUBLE BACKSLASH -2460..2473 ; Restricted ; Not_XID # [20] (①..⑳) CIRCLED DIGIT ONE..CIRCLED NUMBER TWENTY -24B6..24FF ; Restricted ; Not_XID # [74] (Ⓐ..⓿) CIRCLED LATIN CAPITAL LETTER A..NEGATIVE CIRCLED DIGIT ZERO +2460..2487 ; Restricted ; Not_XID # [40] (①..⒇) CIRCLED DIGIT ONE..PARENTHESIZED NUMBER TWENTY +249C..24FF ; Restricted ; Not_XID # [100] (⒜..⓿) PARENTHESIZED LATIN SMALL LETTER A..NEGATIVE CIRCLED DIGIT ZERO 2500 ; Restricted ; Not_XID # (─) BOX DRAWINGS LIGHT HORIZONTAL 2501 ; Restricted ; Not_XID # (━) BOX DRAWINGS HEAVY HORIZONTAL 2502 ; Restricted ; Not_XID # (│) BOX DRAWINGS LIGHT VERTICAL @@ -8005,6 +8130,9 @@ 2A71 ; Restricted ; Not_XID # (⩱) EQUALS SIGN ABOVE PLUS SIGN 2A72 ; Restricted ; Not_XID # (⩲) PLUS SIGN ABOVE EQUALS SIGN 2A73 ; Restricted ; Not_XID # (⩳) EQUALS SIGN ABOVE TILDE OPERATOR +2A74 ; Restricted ; Not_XID # (⩴) DOUBLE COLON EQUAL +2A75 ; Restricted ; Not_XID # (⩵) TWO CONSECUTIVE EQUALS SIGNS +2A76 ; Restricted ; Not_XID # (⩶) THREE CONSECUTIVE EQUALS SIGNS 2A77 ; Restricted ; Not_XID # (⩷) EQUALS SIGN WITH TWO DOTS ABOVE AND TWO DOTS BELOW 2A78 ; Restricted ; Not_XID # (⩸) EQUIVALENT WITH FOUR DOTS ABOVE 2A79 ; Restricted ; Not_XID # (⩹) LESS-THAN WITH CIRCLE INSIDE @@ -8997,6 +9125,7 @@ 2FD3 ; Restricted ; Not_XID # (⿓) KANGXI RADICAL DRAGON 2FD4 ; Restricted ; Not_XID # (⿔) KANGXI RADICAL TURTLE 2FD5 ; Restricted ; Not_XID # (⿕) KANGXI RADICAL FLUTE +3000 ; Restricted ; Not_XID # (U+3000) IDEOGRAPHIC SPACE 3001 ; Restricted ; Not_XID # (、) IDEOGRAPHIC COMMA 3002 ; Restricted ; Not_XID # (。) IDEOGRAPHIC FULL STOP 3003 ; Restricted ; Not_XID # (〃) DITTO MARK @@ -9148,6 +9277,8 @@ 3096 ; output # (ゖ) HIRAGANA LETTER SMALL KE 3099 ; output-nonstarting # (゙) COMBINING KATAKANA-HIRAGANA VOICED SOUND MARK 309A ; output-nonstarting # (゚) COMBINING KATAKANA-HIRAGANA SEMI-VOICED SOUND MARK +309B ; Restricted ; Not_XID # (゛) KATAKANA-HIRAGANA VOICED SOUND MARK +309C ; Restricted ; Not_XID # (゜) KATAKANA-HIRAGANA SEMI-VOICED SOUND MARK 309D ; output # (ゝ) HIRAGANA ITERATION MARK 309E ; output # (ゞ) HIRAGANA VOICED ITERATION MARK 309F ; input-lenient # (ゟ) HIRAGANA DIGRAPH YORI @@ -9444,6 +9575,73 @@ 31FD ; Restricted ; Obsolete # (ㇽ) KATAKANA LETTER SMALL RU 31FE ; Restricted ; Obsolete # (ㇾ) KATAKANA LETTER SMALL RE 31FF ; Restricted ; Obsolete # (ㇿ) KATAKANA LETTER SMALL RO +3200 ; Restricted ; Not_XID # (㈀) PARENTHESIZED HANGUL KIYEOK +3201 ; Restricted ; Not_XID # (㈁) PARENTHESIZED HANGUL NIEUN +3202 ; Restricted ; Not_XID # (㈂) PARENTHESIZED HANGUL TIKEUT +3203 ; Restricted ; Not_XID # (㈃) PARENTHESIZED HANGUL RIEUL +3204 ; Restricted ; Not_XID # (㈄) PARENTHESIZED HANGUL MIEUM +3205 ; Restricted ; Not_XID # (㈅) PARENTHESIZED HANGUL PIEUP +3206 ; Restricted ; Not_XID # (㈆) PARENTHESIZED HANGUL SIOS +3207 ; Restricted ; Not_XID # (㈇) PARENTHESIZED HANGUL IEUNG +3208 ; Restricted ; Not_XID # (㈈) PARENTHESIZED HANGUL CIEUC +3209 ; Restricted ; Not_XID # (㈉) PARENTHESIZED HANGUL CHIEUCH +320A ; Restricted ; Not_XID # (㈊) PARENTHESIZED HANGUL KHIEUKH +320B ; Restricted ; Not_XID # (㈋) PARENTHESIZED HANGUL THIEUTH +320C ; Restricted ; Not_XID # (㈌) PARENTHESIZED HANGUL PHIEUPH +320D ; Restricted ; Not_XID # (㈍) PARENTHESIZED HANGUL HIEUH +320E ; Restricted ; Not_XID # (㈎) PARENTHESIZED HANGUL KIYEOK A +320F ; Restricted ; Not_XID # (㈏) PARENTHESIZED HANGUL NIEUN A +3210 ; Restricted ; Not_XID # (㈐) PARENTHESIZED HANGUL TIKEUT A +3211 ; Restricted ; Not_XID # (㈑) PARENTHESIZED HANGUL RIEUL A +3212 ; Restricted ; Not_XID # (㈒) PARENTHESIZED HANGUL MIEUM A +3213 ; Restricted ; Not_XID # (㈓) PARENTHESIZED HANGUL PIEUP A +3214 ; Restricted ; Not_XID # (㈔) PARENTHESIZED HANGUL SIOS A +3215 ; Restricted ; Not_XID # (㈕) PARENTHESIZED HANGUL IEUNG A +3216 ; Restricted ; Not_XID # (㈖) PARENTHESIZED HANGUL CIEUC A +3217 ; Restricted ; Not_XID # (㈗) PARENTHESIZED HANGUL CHIEUCH A +3218 ; Restricted ; Not_XID # (㈘) PARENTHESIZED HANGUL KHIEUKH A +3219 ; Restricted ; Not_XID # (㈙) PARENTHESIZED HANGUL THIEUTH A +321A ; Restricted ; Not_XID # (㈚) PARENTHESIZED HANGUL PHIEUPH A +321B ; Restricted ; Not_XID # (㈛) PARENTHESIZED HANGUL HIEUH A +321C ; Restricted ; Not_XID # (㈜) PARENTHESIZED HANGUL CIEUC U +321D ; Restricted ; Not_XID # (㈝) PARENTHESIZED KOREAN CHARACTER OJEON +321E ; Restricted ; Not_XID # (㈞) PARENTHESIZED KOREAN CHARACTER O HU +3220 ; Restricted ; Not_XID # (㈠) PARENTHESIZED IDEOGRAPH ONE +3221 ; Restricted ; Not_XID # (㈡) PARENTHESIZED IDEOGRAPH TWO +3222 ; Restricted ; Not_XID # (㈢) PARENTHESIZED IDEOGRAPH THREE +3223 ; Restricted ; Not_XID # (㈣) PARENTHESIZED IDEOGRAPH FOUR +3224 ; Restricted ; Not_XID # (㈤) PARENTHESIZED IDEOGRAPH FIVE +3225 ; Restricted ; Not_XID # (㈥) PARENTHESIZED IDEOGRAPH SIX +3226 ; Restricted ; Not_XID # (㈦) PARENTHESIZED IDEOGRAPH SEVEN +3227 ; Restricted ; Not_XID # (㈧) PARENTHESIZED IDEOGRAPH EIGHT +3228 ; Restricted ; Not_XID # (㈨) PARENTHESIZED IDEOGRAPH NINE +3229 ; Restricted ; Not_XID # (㈩) PARENTHESIZED IDEOGRAPH TEN +322A ; Restricted ; Not_XID # (㈪) PARENTHESIZED IDEOGRAPH MOON +322B ; Restricted ; Not_XID # (㈫) PARENTHESIZED IDEOGRAPH FIRE +322C ; Restricted ; Not_XID # (㈬) PARENTHESIZED IDEOGRAPH WATER +322D ; Restricted ; Not_XID # (㈭) PARENTHESIZED IDEOGRAPH WOOD +322E ; Restricted ; Not_XID # (㈮) PARENTHESIZED IDEOGRAPH METAL +322F ; Restricted ; Not_XID # (㈯) PARENTHESIZED IDEOGRAPH EARTH +3230 ; Restricted ; Not_XID # (㈰) PARENTHESIZED IDEOGRAPH SUN +3231 ; Restricted ; Not_XID # (㈱) PARENTHESIZED IDEOGRAPH STOCK +3232 ; Restricted ; Not_XID # (㈲) PARENTHESIZED IDEOGRAPH HAVE +3233 ; Restricted ; Not_XID # (㈳) PARENTHESIZED IDEOGRAPH SOCIETY +3234 ; Restricted ; Not_XID # (㈴) PARENTHESIZED IDEOGRAPH NAME +3235 ; Restricted ; Not_XID # (㈵) PARENTHESIZED IDEOGRAPH SPECIAL +3236 ; Restricted ; Not_XID # (㈶) PARENTHESIZED IDEOGRAPH FINANCIAL +3237 ; Restricted ; Not_XID # (㈷) PARENTHESIZED IDEOGRAPH CONGRATULATION +3238 ; Restricted ; Not_XID # (㈸) PARENTHESIZED IDEOGRAPH LABOR +3239 ; Restricted ; Not_XID # (㈹) PARENTHESIZED IDEOGRAPH REPRESENT +323A ; Restricted ; Not_XID # (㈺) PARENTHESIZED IDEOGRAPH CALL +323B ; Restricted ; Not_XID # (㈻) PARENTHESIZED IDEOGRAPH STUDY +323C ; Restricted ; Not_XID # (㈼) PARENTHESIZED IDEOGRAPH SUPERVISE +323D ; Restricted ; Not_XID # (㈽) PARENTHESIZED IDEOGRAPH ENTERPRISE +323E ; Restricted ; Not_XID # (㈾) PARENTHESIZED IDEOGRAPH RESOURCE +323F ; Restricted ; Not_XID # (㈿) PARENTHESIZED IDEOGRAPH ALLIANCE +3240 ; Restricted ; Not_XID # (㉀) PARENTHESIZED IDEOGRAPH FESTIVAL +3241 ; Restricted ; Not_XID # (㉁) PARENTHESIZED IDEOGRAPH REST +3242 ; Restricted ; Not_XID # (㉂) PARENTHESIZED IDEOGRAPH SELF +3243 ; Restricted ; Not_XID # (㉃) PARENTHESIZED IDEOGRAPH REACH 3244 ; Restricted ; Not_XID # (㉄) CIRCLED IDEOGRAPH QUESTION 3245 ; Restricted ; Not_XID # (㉅) CIRCLED IDEOGRAPH KINDERGARTEN 3246 ; Restricted ; Not_XID # (㉆) CIRCLED IDEOGRAPH SCHOOL @@ -11749,6 +11947,7 @@ FAD9 ; input-lenient # (龎) CJK COMPATIBILITY I FB00..FB06 ; Restricted ; Technical # [7] (ff..st) LATIN SMALL LIGATURE FF..LATIN SMALL LIGATURE ST FB13..FB17 ; Restricted ; Technical # [5] (ﬓ..ﬗ) ARMENIAN SMALL LIGATURE MEN NOW..ARMENIAN SMALL LIGATURE MEN XEH FB1D..FB28 ; Restricted ; Technical # [12] (יִ..ﬨ) HEBREW LETTER YOD WITH HIRIQ..HEBREW LETTER WIDE TAV +FB29 ; Restricted ; Not_XID # (﬩) HEBREW LETTER ALTERNATIVE PLUS SIGN FB2A..FB36 ; Restricted ; Technical # [13] (שׁ..זּ) HEBREW LETTER SHIN WITH SHIN DOT..HEBREW LETTER ZAYIN WITH DAGESH FB38..FB3C ; Restricted ; Technical # [5] (טּ..לּ) HEBREW LETTER TET WITH DAGESH..HEBREW LETTER LAMED WITH DAGESH FB3E ; Restricted ; Technical # (מּ) HEBREW LETTER MEM WITH DAGESH @@ -11757,33 +11956,56 @@ FB43..FB44 ; Restricted ; Technical # [2] (ףּ..פּ) HEBREW LETTER FB46..FBB1 ; Restricted ; Technical # [108] (צּ..ﮱ) HEBREW LETTER TSADI WITH DAGESH..ARABIC LETTER YEH BARREE WITH HAMZA ABOVE FINAL FORM FBB2..FBC2 ; Restricted ; Not_XID # [17] (﮲..﯂) ARABIC SYMBOL DOT ABOVE..ARABIC SYMBOL WASLA ABOVE FBD3..FC5D ; Restricted ; Technical # [139] (ﯓ..ﱝ) ARABIC LETTER NG ISOLATED FORM..ARABIC LIGATURE ALEF MAKSURA WITH SUPERSCRIPT ALEF ISOLATED FORM +FC5E..FC63 ; Restricted ; Not_XID # [6] (ﱞ..ﱣ) ARABIC LIGATURE SHADDA WITH DAMMATAN ISOLATED FORM..ARABIC LIGATURE SHADDA WITH SUPERSCRIPT ALEF ISOLATED FORM FC64..FD3D ; Restricted ; Technical # [218] (ﱤ..ﴽ) ARABIC LIGATURE YEH WITH HAMZA ABOVE WITH REH FINAL FORM..ARABIC LIGATURE ALEF WITH FATHATAN ISOLATED FORM FD3E..FD4F ; Restricted ; Not_XID # [18] (﴾..﵏) ORNATE LEFT PARENTHESIS..ARABIC LIGATURE RAHIMAHUM ALLAAH FD50..FD8F ; Restricted ; Technical # [64] (ﵐ..ﶏ) ARABIC LIGATURE TEH WITH JEEM WITH MEEM INITIAL FORM..ARABIC LIGATURE MEEM WITH KHAH WITH MEEM INITIAL FORM FD92..FDC7 ; Restricted ; Technical # [54] (ﶒ..ﷇ) ARABIC LIGATURE MEEM WITH JEEM WITH KHAH INITIAL FORM..ARABIC LIGATURE NOON WITH JEEM WITH YEH FINAL FORM FDCF ; Restricted ; Not_XID # (﷏) ARABIC LIGATURE SALAAMUHU ALAYNAA FDF0..FDF9 ; Restricted ; Technical # [10] (ﷰ..ﷹ) ARABIC LIGATURE SALLA USED AS KORANIC STOP SIGN ISOLATED FORM..ARABIC LIGATURE SALLA ISOLATED FORM -FDFC..FDFF ; Restricted ; Not_XID # [4] (﷼..﷿) RIAL SIGN..ARABIC LIGATURE AZZA WA JALL +FDFA..FDFF ; Restricted ; Not_XID # [6] (ﷺ..﷿) ARABIC LIGATURE SALLALLAHOU ALAYHE WASALLAM..ARABIC LIGATURE AZZA WA JALL FE00..FE0F ; Restricted ; Technical # [16] (U+FE00..U+FE0F) VARIATION SELECTOR-1..VARIATION SELECTOR-16 -FE11 ; Restricted ; Not_XID # (︑) PRESENTATION FORM FOR VERTICAL IDEOGRAPHIC COMMA -FE17..FE18 ; Restricted ; Not_XID # [2] (︗..︘) PRESENTATION FORM FOR VERTICAL LEFT WHITE LENTICULAR BRACKET..PRESENTATION FORM FOR VERTICAL RIGHT WHITE LENTICULAR BRAKCET +FE10..FE11 ; Restricted ; Not_XID # [2] (︐..︑) PRESENTATION FORM FOR VERTICAL COMMA..PRESENTATION FORM FOR VERTICAL IDEOGRAPHIC COMMA +FE13..FE18 ; Restricted ; Not_XID # [6] (︓..︘) PRESENTATION FORM FOR VERTICAL COLON..PRESENTATION FORM FOR VERTICAL RIGHT WHITE LENTICULAR BRAKCET FE20..FE2F ; Restricted ; Technical # [16] (︠..︯) COMBINING LIGATURE LEFT HALF..COMBINING CYRILLIC TITLO RIGHT HALF FE31..FE32 ; Restricted ; Not_XID # [2] (︱..︲) PRESENTATION FORM FOR VERTICAL EM DASH..PRESENTATION FORM FOR VERTICAL EN DASH -FE39..FE46 ; Restricted ; Not_XID # [14] (︹..﹆) PRESENTATION FORM FOR VERTICAL LEFT TORTOISE SHELL BRACKET..WHITE SESAME DOT -FE51 ; Restricted ; Not_XID # (﹑) SMALL IDEOGRAPHIC COMMA -FE58 ; Restricted ; Not_XID # (﹘) SMALL EM DASH -FE5D..FE5E ; Restricted ; Not_XID # [2] (﹝..﹞) SMALL LEFT TORTOISE SHELL BRACKET..SMALL RIGHT TORTOISE SHELL BRACKET -FE63 ; Restricted ; Not_XID # (﹣) SMALL HYPHEN-MINUS +FE33..FE34 ; Restricted ; Technical # [2] (︳..︴) PRESENTATION FORM FOR VERTICAL LOW LINE..PRESENTATION FORM FOR VERTICAL WAVY LOW LINE +FE35..FE4C ; Restricted ; Not_XID # [24] (︵..﹌) PRESENTATION FORM FOR VERTICAL LEFT PARENTHESIS..DOUBLE WAVY OVERLINE +FE4D..FE4F ; Restricted ; Technical # [3] (﹍..﹏) DASHED LOW LINE..WAVY LOW LINE +FE50..FE51 ; Restricted ; Not_XID # [2] (﹐..﹑) SMALL COMMA..SMALL IDEOGRAPHIC COMMA +FE54..FE66 ; Restricted ; Not_XID # [19] (﹔..﹦) SMALL SEMICOLON..SMALL EQUALS SIGN +FE68..FE6B ; Restricted ; Not_XID # [4] (﹨..﹫) SMALL REVERSE SOLIDUS..SMALL COMMERCIAL AT +FE70 ; Restricted ; Not_XID # (ﹰ) ARABIC FATHATAN ISOLATED FORM FE71 ; Restricted ; Technical # (ﹱ) ARABIC TATWEEL WITH FATHATAN ABOVE +FE72 ; Restricted ; Not_XID # (ﹲ) ARABIC DAMMATAN ISOLATED FORM FE73 ; Restricted ; Technical # (ﹳ) ARABIC TAIL FRAGMENT +FE74 ; Restricted ; Not_XID # (ﹴ) ARABIC KASRATAN ISOLATED FORM +FE76 ; Restricted ; Not_XID # (ﹶ) ARABIC FATHA ISOLATED FORM FE77 ; Restricted ; Technical # (ﹷ) ARABIC FATHA MEDIAL FORM +FE78 ; Restricted ; Not_XID # (ﹸ) ARABIC DAMMA ISOLATED FORM FE79 ; Restricted ; Technical # (ﹹ) ARABIC DAMMA MEDIAL FORM +FE7A ; Restricted ; Not_XID # (ﹺ) ARABIC KASRA ISOLATED FORM FE7B ; Restricted ; Technical # (ﹻ) ARABIC KASRA MEDIAL FORM +FE7C ; Restricted ; Not_XID # (ﹼ) ARABIC SHADDA ISOLATED FORM FE7D ; Restricted ; Technical # (ﹽ) ARABIC SHADDA MEDIAL FORM +FE7E ; Restricted ; Not_XID # (ﹾ) ARABIC SUKUN ISOLATED FORM FE7F..FEFC ; Restricted ; Technical # [126] (ﹿ..ﻼ) ARABIC SUKUN MEDIAL FORM..ARABIC LIGATURE LAM WITH ALEF FINAL FORM FEFF ; Restricted ; Not_XID # (U+FEFF) ZERO WIDTH NO-BREAK SPACE +FF01 ; Restricted ; Not_XID # (！) FULLWIDTH EXCLAMATION MARK +FF02 ; Restricted ; Not_XID # (＂) FULLWIDTH QUOTATION MARK +FF03 ; Restricted ; Not_XID # (＃) FULLWIDTH NUMBER SIGN +FF04 ; Restricted ; Not_XID # (＄) FULLWIDTH DOLLAR SIGN +FF05 ; Restricted ; Not_XID # (％) FULLWIDTH PERCENT SIGN +FF06 ; Restricted ; Not_XID # (＆) FULLWIDTH AMPERSAND +FF07 ; Restricted ; Not_XID # (＇) FULLWIDTH APOSTROPHE +FF08 ; Restricted ; Not_XID # (（) FULLWIDTH LEFT PARENTHESIS +FF09 ; Restricted ; Not_XID # (）) FULLWIDTH RIGHT PARENTHESIS +FF0A ; Restricted ; Not_XID # (＊) FULLWIDTH ASTERISK +FF0B ; Restricted ; Not_XID # (＋) FULLWIDTH PLUS SIGN +FF0C ; Restricted ; Not_XID # (，) FULLWIDTH COMMA FF0D ; Restricted ; Not_XID # (－) FULLWIDTH HYPHEN-MINUS FF0E ; Restricted ; Not_XID # (．) FULLWIDTH FULL STOP +FF0F ; Restricted ; Not_XID # (／) FULLWIDTH SOLIDUS FF10 ; input-lenient # (０) FULLWIDTH DIGIT ZERO FF11 ; input-lenient # (１) FULLWIDTH DIGIT ONE FF12 ; input-lenient # (２) FULLWIDTH DIGIT TWO @@ -11794,6 +12016,13 @@ FF16 ; input-lenient # (６) FULLWIDTH DIGIT SIX FF17 ; input-lenient # (７) FULLWIDTH DIGIT SEVEN FF18 ; input-lenient # (８) FULLWIDTH DIGIT EIGHT FF19 ; input-lenient # (９) FULLWIDTH DIGIT NINE +FF1A ; Restricted ; Not_XID # (：) FULLWIDTH COLON +FF1B ; Restricted ; Not_XID # (；) FULLWIDTH SEMICOLON +FF1C ; Restricted ; Not_XID # (＜) FULLWIDTH LESS-THAN SIGN +FF1D ; Restricted ; Not_XID # (＝) FULLWIDTH EQUALS SIGN +FF1E ; Restricted ; Not_XID # (＞) FULLWIDTH GREATER-THAN SIGN +FF1F ; Restricted ; Not_XID # (？) FULLWIDTH QUESTION MARK +FF20 ; Restricted ; Not_XID # (＠) FULLWIDTH COMMERCIAL AT FF21 ; input-lenient # (Ａ) FULLWIDTH LATIN CAPITAL LETTER A FF22 ; input-lenient # (Ｂ) FULLWIDTH LATIN CAPITAL LETTER B FF23 ; input-lenient # (Ｃ) FULLWIDTH LATIN CAPITAL LETTER C @@ -11820,6 +12049,12 @@ FF37 ; input-lenient # (Ｗ) FULLWIDTH LATIN CAP FF38 ; input-lenient # (Ｘ) FULLWIDTH LATIN CAPITAL LETTER X FF39 ; input-lenient # (Ｙ) FULLWIDTH LATIN CAPITAL LETTER Y FF3A ; input-lenient # (Ｚ) FULLWIDTH LATIN CAPITAL LETTER Z +FF3B ; Restricted ; Not_XID # (［) FULLWIDTH LEFT SQUARE BRACKET +FF3C ; Restricted ; Not_XID # (＼) FULLWIDTH REVERSE SOLIDUS +FF3D ; Restricted ; Not_XID # (］) FULLWIDTH RIGHT SQUARE BRACKET +FF3E ; Restricted ; Not_XID # (＾) FULLWIDTH CIRCUMFLEX ACCENT +FF3F ; input-lenient # (＿) FULLWIDTH LOW LINE +FF40 ; Restricted ; Not_XID # (｀) FULLWIDTH GRAVE ACCENT FF41 ; input-lenient # (ａ) FULLWIDTH LATIN SMALL LETTER A FF42 ; input-lenient # (ｂ) FULLWIDTH LATIN SMALL LETTER B FF43 ; input-lenient # (ｃ) FULLWIDTH LATIN SMALL LETTER C @@ -11846,6 +12081,10 @@ FF57 ; input-lenient # (ｗ) FULLWIDTH LATIN SMA FF58 ; input-lenient # (ｘ) FULLWIDTH LATIN SMALL LETTER X FF59 ; input-lenient # (ｙ) FULLWIDTH LATIN SMALL LETTER Y FF5A ; input-lenient # (ｚ) FULLWIDTH LATIN SMALL LETTER Z +FF5B ; Restricted ; Not_XID # (｛) FULLWIDTH LEFT CURLY BRACKET +FF5C ; Restricted ; Not_XID # (｜) FULLWIDTH VERTICAL LINE +FF5D ; Restricted ; Not_XID # (｝) FULLWIDTH RIGHT CURLY BRACKET +FF5E ; Restricted ; Not_XID # (～) FULLWIDTH TILDE FF5F ; Restricted ; Not_XID # (｟) FULLWIDTH LEFT WHITE PARENTHESIS FF60 ; Restricted ; Not_XID # (｠) FULLWIDTH RIGHT WHITE PARENTHESIS FF61 ; Restricted ; Not_XID # (｡) HALFWIDTH IDEOGRAPHIC FULL STOP @@ -11966,6 +12205,7 @@ FFDC ; Restricted ; Obsolete # (ￜ) HALFWIDTH HANGUL LE FFE0 ; Restricted ; Not_XID # (￠) FULLWIDTH CENT SIGN FFE1 ; Restricted ; Not_XID # (￡) FULLWIDTH POUND SIGN FFE2 ; Restricted ; Not_XID # (￢) FULLWIDTH NOT SIGN +FFE3 ; Restricted ; Not_XID # (￣) FULLWIDTH MACRON FFE4 ; Restricted ; Not_XID # (￤) FULLWIDTH BROKEN BAR FFE5 ; Restricted ; Not_XID # (￥) FULLWIDTH YEN SIGN FFE6 ; Restricted ; Not_XID # (￦) FULLWIDTH WON SIGN @@ -35786,11 +36026,47 @@ FFEE ; Restricted ; Not_XID # (￮) HALFWIDTH WHITE CIR 1F0F3 ; Restricted ; Not_XID # (🃳) PLAYING CARD TRUMP-19 1F0F4 ; Restricted ; Not_XID # (🃴) PLAYING CARD TRUMP-20 1F0F5 ; Restricted ; Not_XID # (🃵) PLAYING CARD TRUMP-21 +1F101 ; Restricted ; Not_XID # (🄁) DIGIT ZERO COMMA +1F102 ; Restricted ; Not_XID # (🄂) DIGIT ONE COMMA +1F103 ; Restricted ; Not_XID # (🄃) DIGIT TWO COMMA +1F104 ; Restricted ; Not_XID # (🄄) DIGIT THREE COMMA +1F105 ; Restricted ; Not_XID # (🄅) DIGIT FOUR COMMA +1F106 ; Restricted ; Not_XID # (🄆) DIGIT FIVE COMMA +1F107 ; Restricted ; Not_XID # (🄇) DIGIT SIX COMMA +1F108 ; Restricted ; Not_XID # (🄈) DIGIT SEVEN COMMA +1F109 ; Restricted ; Not_XID # (🄉) DIGIT EIGHT COMMA +1F10A ; Restricted ; Not_XID # (🄊) DIGIT NINE COMMA 1F10B ; Restricted ; Not_XID # (🄋) DINGBAT CIRCLED SANS-SERIF DIGIT ZERO 1F10C ; Restricted ; Not_XID # (🄌) DINGBAT NEGATIVE CIRCLED SANS-SERIF DIGIT ZERO 1F10D ; Restricted ; Not_XID # (🄍) CIRCLED ZERO WITH SLASH 1F10E ; Restricted ; Not_XID # (🄎) CIRCLED ANTICLOCKWISE ARROW 1F10F ; Restricted ; Not_XID # (🄏) CIRCLED DOLLAR SIGN WITH OVERLAID BACKSLASH +1F110 ; Restricted ; Not_XID # (🄐) PARENTHESIZED LATIN CAPITAL LETTER A +1F111 ; Restricted ; Not_XID # (🄑) PARENTHESIZED LATIN CAPITAL LETTER B +1F112 ; Restricted ; Not_XID # (🄒) PARENTHESIZED LATIN CAPITAL LETTER C +1F113 ; Restricted ; Not_XID # (🄓) PARENTHESIZED LATIN CAPITAL LETTER D +1F114 ; Restricted ; Not_XID # (🄔) PARENTHESIZED LATIN CAPITAL LETTER E +1F115 ; Restricted ; Not_XID # (🄕) PARENTHESIZED LATIN CAPITAL LETTER F +1F116 ; Restricted ; Not_XID # (🄖) PARENTHESIZED LATIN CAPITAL LETTER G +1F117 ; Restricted ; Not_XID # (🄗) PARENTHESIZED LATIN CAPITAL LETTER H +1F118 ; Restricted ; Not_XID # (🄘) PARENTHESIZED LATIN CAPITAL LETTER I +1F119 ; Restricted ; Not_XID # (🄙) PARENTHESIZED LATIN CAPITAL LETTER J +1F11A ; Restricted ; Not_XID # (🄚) PARENTHESIZED LATIN CAPITAL LETTER K +1F11B ; Restricted ; Not_XID # (🄛) PARENTHESIZED LATIN CAPITAL LETTER L +1F11C ; Restricted ; Not_XID # (🄜) PARENTHESIZED LATIN CAPITAL LETTER M +1F11D ; Restricted ; Not_XID # (🄝) PARENTHESIZED LATIN CAPITAL LETTER N +1F11E ; Restricted ; Not_XID # (🄞) PARENTHESIZED LATIN CAPITAL LETTER O +1F11F ; Restricted ; Not_XID # (🄟) PARENTHESIZED LATIN CAPITAL LETTER P +1F120 ; Restricted ; Not_XID # (🄠) PARENTHESIZED LATIN CAPITAL LETTER Q +1F121 ; Restricted ; Not_XID # (🄡) PARENTHESIZED LATIN CAPITAL LETTER R +1F122 ; Restricted ; Not_XID # (🄢) PARENTHESIZED LATIN CAPITAL LETTER S +1F123 ; Restricted ; Not_XID # (🄣) PARENTHESIZED LATIN CAPITAL LETTER T +1F124 ; Restricted ; Not_XID # (🄤) PARENTHESIZED LATIN CAPITAL LETTER U +1F125 ; Restricted ; Not_XID # (🄥) PARENTHESIZED LATIN CAPITAL LETTER V +1F126 ; Restricted ; Not_XID # (🄦) PARENTHESIZED LATIN CAPITAL LETTER W +1F127 ; Restricted ; Not_XID # (🄧) PARENTHESIZED LATIN CAPITAL LETTER X +1F128 ; Restricted ; Not_XID # (🄨) PARENTHESIZED LATIN CAPITAL LETTER Y +1F129 ; Restricted ; Not_XID # (🄩) PARENTHESIZED LATIN CAPITAL LETTER Z 1F12A ; Restricted ; Not_XID # (🄪) TORTOISE SHELL BRACKETED LATIN CAPITAL LETTER S 1F12B ; Restricted ; Not_XID # (🄫) CIRCLED ITALIC LATIN CAPITAL LETTER C 1F12C ; Restricted ; Not_XID # (🄬) CIRCLED ITALIC LATIN CAPITAL LETTER R @@ -66051,77 +66327,13 @@ FFEE ; Restricted ; Not_XID # (￮) HALFWIDTH WHITE CIR 323AF ; output # (𲎯) CJK UNIFIED IDEOGRAPH-323AF E0100..E01EF ; Restricted ; output-disallowed # [240] (U+E0100..U+E01EF) VARIATION SELECTOR-17..VARIATION SELECTOR-256 -# Total code points: 154469 +# Total code points: 154837 # Characters disallowed in IDNA # The IDNA spec doesn't allow any of these characters, # so don't report any of them as being missing from the above list. # Some possible future additions, once IDNA updates to Unicode 4.1, are given. -0000 ; Restricted ; not in XID+ # (U+0000) -0001 ; Restricted ; not in XID+ # (U+0001) -0002 ; Restricted ; not in XID+ # (U+0002) -0003 ; Restricted ; not in XID+ # (U+0003) -0004 ; Restricted ; not in XID+ # (U+0004) -0005 ; Restricted ; not in XID+ # (U+0005) -0006 ; Restricted ; not in XID+ # (U+0006) -0007 ; Restricted ; not in XID+ # (U+0007) -0008 ; Restricted ; not in XID+ # (U+0008) -0009 ; Restricted ; not in XID+ # (U+0009) -000A ; Restricted ; not in XID+ # (U+000A) -000B ; Restricted ; not in XID+ # (U+000B) -000C ; Restricted ; not in XID+ # (U+000C) -000D ; Restricted ; not in XID+ # (U+000D) -000E ; Restricted ; not in XID+ # (U+000E) -000F ; Restricted ; not in XID+ # (U+000F) -0010 ; Restricted ; not in XID+ # (U+0010) -0011 ; Restricted ; not in XID+ # (U+0011) -0012 ; Restricted ; not in XID+ # (U+0012) -0013 ; Restricted ; not in XID+ # (U+0013) -0014 ; Restricted ; not in XID+ # (U+0014) -0015 ; Restricted ; not in XID+ # (U+0015) -0016 ; Restricted ; not in XID+ # (U+0016) -0017 ; Restricted ; not in XID+ # (U+0017) -0018 ; Restricted ; not in XID+ # (U+0018) -0019 ; Restricted ; not in XID+ # (U+0019) -001A ; Restricted ; not in XID+ # (U+001A) -001B ; Restricted ; not in XID+ # (U+001B) -001C ; Restricted ; not in XID+ # (U+001C) -001D ; Restricted ; not in XID+ # (U+001D) -001E ; Restricted ; not in XID+ # (U+001E) -001F ; Restricted ; not in XID+ # (U+001F) -0020 ; Restricted ; not in XID+ # (U+0020) SPACE -0021 ; Restricted ; not in XID+ # (!) EXCLAMATION MARK -0022 ; Restricted ; not in XID+ # (") QUOTATION MARK -0023 ; Restricted ; not in XID+ # (#) NUMBER SIGN -0024 ; Restricted ; not in XID+ # ($) DOLLAR SIGN -0025 ; Restricted ; not in XID+ # (%) PERCENT SIGN -0026 ; Restricted ; not in XID+ # (&) AMPERSAND -0027 ; Restricted ; not in XID+ # (') APOSTROPHE -0028 ; Restricted ; not in XID+ # (() LEFT PARENTHESIS -0029 ; Restricted ; not in XID+ # ()) RIGHT PARENTHESIS -002A ; Restricted ; not in XID+ # (*) ASTERISK -002B ; Restricted ; not in XID+ # (+) PLUS SIGN -002C ; Restricted ; not in XID+ # (,) COMMA -002F ; Restricted ; not in XID+ # (/) SOLIDUS -003A ; Restricted ; not in XID+ # (:) COLON -003B ; Restricted ; not in XID+ # (;) SEMICOLON -003C ; Restricted ; not in XID+ # (<) LESS-THAN SIGN -003D ; Restricted ; not in XID+ # (=) EQUALS SIGN -003E ; Restricted ; not in XID+ # (>) GREATER-THAN SIGN -003F ; Restricted ; not in XID+ # (?) QUESTION MARK -0040 ; Restricted ; not in XID+ # (@) COMMERCIAL AT -005B ; Restricted ; not in XID+ # ([) LEFT SQUARE BRACKET -005C ; Restricted ; not in XID+ # (\) REVERSE SOLIDUS -005D ; Restricted ; not in XID+ # (]) RIGHT SQUARE BRACKET -005E ; Restricted ; not in XID+ # (^) CIRCUMFLEX ACCENT -005F ; future? # (_) LOW LINE -0060 ; Restricted ; not in XID+ # (`) GRAVE ACCENT -007B ; Restricted ; not in XID+ # ({) LEFT CURLY BRACKET -007C ; Restricted ; not in XID+ # (|) VERTICAL LINE -007D ; Restricted ; not in XID+ # (}) RIGHT CURLY BRACKET -007E ; Restricted ; not in XID+ # (~) TILDE -007F ; Restricted ; not in XID+ # (U+007F) 0080 ; Restricted ; not in XID+ # (U+0080) 0081 ; Restricted ; not in XID+ # (U+0081) 0082 ; Restricted ; not in XID+ # (U+0082) @@ -66154,21 +66366,6 @@ E0100..E01EF ; Restricted ; output-disallowed # [240] (U+E0100..U+E01EF) VARIA 009D ; Restricted ; not in XID+ # (U+009D) 009E ; Restricted ; not in XID+ # (U+009E) 009F ; Restricted ; not in XID+ # (U+009F) -00A0 ; Restricted ; not in XID+ # (U+00A0) NO-BREAK SPACE -00A8 ; Restricted ; not in XID+ # (¨) DIAERESIS -00AF ; Restricted ; not in XID+ # (¯) MACRON -00B4 ; Restricted ; not in XID+ # (´) ACUTE ACCENT -00B8 ; Restricted ; not in XID+ # (¸) CEDILLA -02D8 ; Restricted ; not in XID+ # (˘) BREVE -02D9 ; Restricted ; not in XID+ # (˙) DOT ABOVE -02DA ; Restricted ; not in XID+ # (˚) RING ABOVE -02DB ; Restricted ; not in XID+ # (˛) OGONEK -02DC ; Restricted ; not in XID+ # (˜) SMALL TILDE -02DD ; Restricted ; not in XID+ # (˝) DOUBLE ACUTE ACCENT -037A ; Restricted ; not in XID+ # (ͺ) GREEK YPOGEGRAMMENI -037E ; Restricted ; not in XID+ # (;) GREEK QUESTION MARK -0384 ; Restricted ; not in XID+ # (΄) GREEK TONOS -0385 ; Restricted ; not in XID+ # (΅) GREEK DIALYTIKA TONOS 0600 ; Restricted ; not in XID+ # (U+0600) ARABIC NUMBER SIGN 0601 ; Restricted ; not in XID+ # (U+0601) ARABIC SIGN SANAH 0602 ; Restricted ; not in XID+ # (U+0602) ARABIC FOOTNOTE MARKER @@ -66182,64 +66379,15 @@ E0100..E01EF ; Restricted ; output-disallowed # [240] (U+E0100..U+E01EF) VARIA 0891 ; Restricted ; not in XID+ # (U+0891) ARABIC PIASTRE MARK ABOVE 08E2 ; Restricted ; not in XID+ # (U+08E2) ARABIC DISPUTED END OF AYAH 1680 ; Restricted ; not in XID+ # (U+1680) OGHAM SPACE MARK -1FBD ; Restricted ; not in XID+ # (᾽) GREEK KORONIS -1FBF ; Restricted ; not in XID+ # (᾿) GREEK PSILI -1FC0 ; Restricted ; not in XID+ # (῀) GREEK PERISPOMENI -1FC1 ; Restricted ; not in XID+ # (῁) GREEK DIALYTIKA AND PERISPOMENI -1FCD ; Restricted ; not in XID+ # (῍) GREEK PSILI AND VARIA -1FCE ; Restricted ; not in XID+ # (῎) GREEK PSILI AND OXIA -1FCF ; Restricted ; not in XID+ # (῏) GREEK PSILI AND PERISPOMENI -1FDD ; Restricted ; not in XID+ # (῝) GREEK DASIA AND VARIA -1FDE ; Restricted ; not in XID+ # (῞) GREEK DASIA AND OXIA -1FDF ; Restricted ; not in XID+ # (῟) GREEK DASIA AND PERISPOMENI -1FED ; Restricted ; not in XID+ # (῭) GREEK DIALYTIKA AND VARIA -1FEE ; Restricted ; not in XID+ # (΅) GREEK DIALYTIKA AND OXIA -1FEF ; Restricted ; not in XID+ # (`) GREEK VARIA -1FFD ; Restricted ; not in XID+ # (´) GREEK OXIA -1FFE ; Restricted ; not in XID+ # (῾) GREEK DASIA -2000 ; Restricted ; not in XID+ # (U+2000) EN QUAD -2001 ; Restricted ; not in XID+ # (U+2001) EM QUAD -2002 ; Restricted ; not in XID+ # (U+2002) EN SPACE -2003 ; Restricted ; not in XID+ # (U+2003) EM SPACE -2004 ; Restricted ; not in XID+ # (U+2004) THREE-PER-EM SPACE -2005 ; Restricted ; not in XID+ # (U+2005) FOUR-PER-EM SPACE -2006 ; Restricted ; not in XID+ # (U+2006) SIX-PER-EM SPACE -2007 ; Restricted ; not in XID+ # (U+2007) FIGURE SPACE -2008 ; Restricted ; not in XID+ # (U+2008) PUNCTUATION SPACE -2009 ; Restricted ; not in XID+ # (U+2009) THIN SPACE -200A ; Restricted ; not in XID+ # (U+200A) HAIR SPACE 200E..200F ; Restricted ; not in XID+ # [2] (U+200E..U+200F) LEFT-TO-RIGHT MARK..RIGHT-TO-LEFT MARK -2017 ; Restricted ; not in XID+ # (‗) DOUBLE LOW LINE 2024 ; Restricted ; not in XID+ # (․) ONE DOT LEADER 2025 ; Restricted ; not in XID+ # (‥) TWO DOT LEADER 2026 ; Restricted ; not in XID+ # (…) HORIZONTAL ELLIPSIS 2028 ; Restricted ; not in XID+ # (U+2028) LINE SEPARATOR 2029 ; Restricted ; not in XID+ # (U+2029) PARAGRAPH SEPARATOR 202A..202E ; Restricted ; not in XID+ # [5] (U+202A..U+202E) LEFT-TO-RIGHT EMBEDDING..RIGHT-TO-LEFT OVERRIDE -202F ; Restricted ; not in XID+ # (U+202F) NARROW NO-BREAK SPACE -203C ; Restricted ; not in XID+ # (‼) DOUBLE EXCLAMATION MARK -203E ; Restricted ; not in XID+ # (‾) OVERLINE -2047 ; Restricted ; not in XID+ # (⁇) DOUBLE QUESTION MARK -2048 ; Restricted ; not in XID+ # (⁈) QUESTION EXCLAMATION MARK -2049 ; Restricted ; not in XID+ # (⁉) EXCLAMATION QUESTION MARK -205F ; Restricted ; not in XID+ # (U+205F) MEDIUM MATHEMATICAL SPACE 2066..2069 ; Restricted ; not in XID+ # [4] (U+2066..U+2069) LEFT-TO-RIGHT ISOLATE..POP DIRECTIONAL ISOLATE -207A ; Restricted ; not in XID+ # (⁺) SUPERSCRIPT PLUS SIGN -207C ; Restricted ; not in XID+ # (⁼) SUPERSCRIPT EQUALS SIGN -207D ; Restricted ; not in XID+ # (⁽) SUPERSCRIPT LEFT PARENTHESIS -207E ; Restricted ; not in XID+ # (⁾) SUPERSCRIPT RIGHT PARENTHESIS -208A ; Restricted ; not in XID+ # (₊) SUBSCRIPT PLUS SIGN -208C ; Restricted ; not in XID+ # (₌) SUBSCRIPT EQUALS SIGN -208D ; Restricted ; not in XID+ # (₍) SUBSCRIPT LEFT PARENTHESIS -208E ; Restricted ; not in XID+ # (₎) SUBSCRIPT RIGHT PARENTHESIS -2100 ; Restricted ; not in XID+ # (℀) ACCOUNT OF -2101 ; Restricted ; not in XID+ # (℁) ADDRESSED TO THE SUBJECT -2105 ; Restricted ; not in XID+ # (℅) CARE OF -2106 ; Restricted ; not in XID+ # (℆) CADA UNA -2474..24B5 ; Restricted ; not in XID+ # [66] (⑴..⒵) PARENTHESIZED DIGIT ONE..PARENTHESIZED LATIN SMALL LETTER Z -2A74 ; Restricted ; not in XID+ # (⩴) DOUBLE COLON EQUAL -2A75 ; Restricted ; not in XID+ # (⩵) TWO CONSECUTIVE EQUALS SIGNS -2A76 ; Restricted ; not in XID+ # (⩶) THREE CONSECUTIVE EQUALS SIGNS +2488..249B ; Restricted ; not in XID+ # [20] (⒈..⒛) DIGIT ONE FULL STOP..NUMBER TWENTY FULL STOP 2FF0 ; Restricted ; not in XID+ # (⿰) IDEOGRAPHIC DESCRIPTION CHARACTER LEFT TO RIGHT 2FF1 ; Restricted ; not in XID+ # (⿱) IDEOGRAPHIC DESCRIPTION CHARACTER ABOVE TO BELOW 2FF2 ; Restricted ; not in XID+ # (⿲) IDEOGRAPHIC DESCRIPTION CHARACTER LEFT TO MIDDLE AND RIGHT @@ -66256,137 +66404,14 @@ E0100..E01EF ; Restricted ; output-disallowed # [240] (U+E0100..U+E01EF) VARIA 2FFD ; Restricted ; not in XID+ # (⿽) IDEOGRAPHIC DESCRIPTION CHARACTER SURROUND FROM LOWER RIGHT 2FFE ; Restricted ; not in XID+ # (⿾) IDEOGRAPHIC DESCRIPTION CHARACTER HORIZONTAL REFLECTION 2FFF ; Restricted ; not in XID+ # (⿿) IDEOGRAPHIC DESCRIPTION CHARACTER ROTATION -3000 ; Restricted ; not in XID+ # (U+3000) IDEOGRAPHIC SPACE -309B ; Restricted ; not in XID+ # (゛) KATAKANA-HIRAGANA VOICED SOUND MARK -309C ; Restricted ; not in XID+ # (゜) KATAKANA-HIRAGANA SEMI-VOICED SOUND MARK 31EF ; Restricted ; not in XID+ # (㇯) IDEOGRAPHIC DESCRIPTION CHARACTER SUBTRACTION -3200 ; Restricted ; not in XID+ # (㈀) PARENTHESIZED HANGUL KIYEOK -3201 ; Restricted ; not in XID+ # (㈁) PARENTHESIZED HANGUL NIEUN -3202 ; Restricted ; not in XID+ # (㈂) PARENTHESIZED HANGUL TIKEUT -3203 ; Restricted ; not in XID+ # (㈃) PARENTHESIZED HANGUL RIEUL -3204 ; Restricted ; not in XID+ # (㈄) PARENTHESIZED HANGUL MIEUM -3205 ; Restricted ; not in XID+ # (㈅) PARENTHESIZED HANGUL PIEUP -3206 ; Restricted ; not in XID+ # (㈆) PARENTHESIZED HANGUL SIOS -3207 ; Restricted ; not in XID+ # (㈇) PARENTHESIZED HANGUL IEUNG -3208 ; Restricted ; not in XID+ # (㈈) PARENTHESIZED HANGUL CIEUC -3209 ; Restricted ; not in XID+ # (㈉) PARENTHESIZED HANGUL CHIEUCH -320A ; Restricted ; not in XID+ # (㈊) PARENTHESIZED HANGUL KHIEUKH -320B ; Restricted ; not in XID+ # (㈋) PARENTHESIZED HANGUL THIEUTH -320C ; Restricted ; not in XID+ # (㈌) PARENTHESIZED HANGUL PHIEUPH -320D ; Restricted ; not in XID+ # (㈍) PARENTHESIZED HANGUL HIEUH -320E ; Restricted ; not in XID+ # (㈎) PARENTHESIZED HANGUL KIYEOK A -320F ; Restricted ; not in XID+ # (㈏) PARENTHESIZED HANGUL NIEUN A -3210 ; Restricted ; not in XID+ # (㈐) PARENTHESIZED HANGUL TIKEUT A -3211 ; Restricted ; not in XID+ # (㈑) PARENTHESIZED HANGUL RIEUL A -3212 ; Restricted ; not in XID+ # (㈒) PARENTHESIZED HANGUL MIEUM A -3213 ; Restricted ; not in XID+ # (㈓) PARENTHESIZED HANGUL PIEUP A -3214 ; Restricted ; not in XID+ # (㈔) PARENTHESIZED HANGUL SIOS A -3215 ; Restricted ; not in XID+ # (㈕) PARENTHESIZED HANGUL IEUNG A -3216 ; Restricted ; not in XID+ # (㈖) PARENTHESIZED HANGUL CIEUC A -3217 ; Restricted ; not in XID+ # (㈗) PARENTHESIZED HANGUL CHIEUCH A -3218 ; Restricted ; not in XID+ # (㈘) PARENTHESIZED HANGUL KHIEUKH A -3219 ; Restricted ; not in XID+ # (㈙) PARENTHESIZED HANGUL THIEUTH A -321A ; Restricted ; not in XID+ # (㈚) PARENTHESIZED HANGUL PHIEUPH A -321B ; Restricted ; not in XID+ # (㈛) PARENTHESIZED HANGUL HIEUH A -321C ; Restricted ; not in XID+ # (㈜) PARENTHESIZED HANGUL CIEUC U -321D ; Restricted ; not in XID+ # (㈝) PARENTHESIZED KOREAN CHARACTER OJEON -321E ; Restricted ; not in XID+ # (㈞) PARENTHESIZED KOREAN CHARACTER O HU -3220 ; Restricted ; not in XID+ # (㈠) PARENTHESIZED IDEOGRAPH ONE -3221 ; Restricted ; not in XID+ # (㈡) PARENTHESIZED IDEOGRAPH TWO -3222 ; Restricted ; not in XID+ # (㈢) PARENTHESIZED IDEOGRAPH THREE -3223 ; Restricted ; not in XID+ # (㈣) PARENTHESIZED IDEOGRAPH FOUR -3224 ; Restricted ; not in XID+ # (㈤) PARENTHESIZED IDEOGRAPH FIVE -3225 ; Restricted ; not in XID+ # (㈥) PARENTHESIZED IDEOGRAPH SIX -3226 ; Restricted ; not in XID+ # (㈦) PARENTHESIZED IDEOGRAPH SEVEN -3227 ; Restricted ; not in XID+ # (㈧) PARENTHESIZED IDEOGRAPH EIGHT -3228 ; Restricted ; not in XID+ # (㈨) PARENTHESIZED IDEOGRAPH NINE -3229 ; Restricted ; not in XID+ # (㈩) PARENTHESIZED IDEOGRAPH TEN -322A ; Restricted ; not in XID+ # (㈪) PARENTHESIZED IDEOGRAPH MOON -322B ; Restricted ; not in XID+ # (㈫) PARENTHESIZED IDEOGRAPH FIRE -322C ; Restricted ; not in XID+ # (㈬) PARENTHESIZED IDEOGRAPH WATER -322D ; Restricted ; not in XID+ # (㈭) PARENTHESIZED IDEOGRAPH WOOD -322E ; Restricted ; not in XID+ # (㈮) PARENTHESIZED IDEOGRAPH METAL -322F ; Restricted ; not in XID+ # (㈯) PARENTHESIZED IDEOGRAPH EARTH -3230 ; Restricted ; not in XID+ # (㈰) PARENTHESIZED IDEOGRAPH SUN -3231 ; Restricted ; not in XID+ # (㈱) PARENTHESIZED IDEOGRAPH STOCK -3232 ; Restricted ; not in XID+ # (㈲) PARENTHESIZED IDEOGRAPH HAVE -3233 ; Restricted ; not in XID+ # (㈳) PARENTHESIZED IDEOGRAPH SOCIETY -3234 ; Restricted ; not in XID+ # (㈴) PARENTHESIZED IDEOGRAPH NAME -3235 ; Restricted ; not in XID+ # (㈵) PARENTHESIZED IDEOGRAPH SPECIAL -3236 ; Restricted ; not in XID+ # (㈶) PARENTHESIZED IDEOGRAPH FINANCIAL -3237 ; Restricted ; not in XID+ # (㈷) PARENTHESIZED IDEOGRAPH CONGRATULATION -3238 ; Restricted ; not in XID+ # (㈸) PARENTHESIZED IDEOGRAPH LABOR -3239 ; Restricted ; not in XID+ # (㈹) PARENTHESIZED IDEOGRAPH REPRESENT -323A ; Restricted ; not in XID+ # (㈺) PARENTHESIZED IDEOGRAPH CALL -323B ; Restricted ; not in XID+ # (㈻) PARENTHESIZED IDEOGRAPH STUDY -323C ; Restricted ; not in XID+ # (㈼) PARENTHESIZED IDEOGRAPH SUPERVISE -323D ; Restricted ; not in XID+ # (㈽) PARENTHESIZED IDEOGRAPH ENTERPRISE -323E ; Restricted ; not in XID+ # (㈾) PARENTHESIZED IDEOGRAPH RESOURCE -323F ; Restricted ; not in XID+ # (㈿) PARENTHESIZED IDEOGRAPH ALLIANCE -3240 ; Restricted ; not in XID+ # (㉀) PARENTHESIZED IDEOGRAPH FESTIVAL -3241 ; Restricted ; not in XID+ # (㉁) PARENTHESIZED IDEOGRAPH REST -3242 ; Restricted ; not in XID+ # (㉂) PARENTHESIZED IDEOGRAPH SELF -3243 ; Restricted ; not in XID+ # (㉃) PARENTHESIZED IDEOGRAPH REACH 33C2 ; Restricted ; not in XID+ # (㏂) SQUARE AM 33C7 ; Restricted ; not in XID+ # (㏇) SQUARE CO 33D8 ; Restricted ; not in XID+ # (㏘) SQUARE PM -FB29 ; Restricted ; not in XID+ # (﬩) HEBREW LETTER ALTERNATIVE PLUS SIGN -FC5E..FC63 ; Restricted ; not in XID+ # [6] (ﱞ..ﱣ) ARABIC LIGATURE SHADDA WITH DAMMATAN ISOLATED FORM..ARABIC LIGATURE SHADDA WITH SUPERSCRIPT ALEF ISOLATED FORM -FDFA..FDFB ; Restricted ; not in XID+ # [2] (ﷺ..ﷻ) ARABIC LIGATURE SALLALLAHOU ALAYHE WASALLAM..ARABIC LIGATURE JALLAJALALOUHOU -FE10 ; Restricted ; not in XID+ # (︐) PRESENTATION FORM FOR VERTICAL COMMA -FE12..FE16 ; Restricted ; not in XID+ # [5] (︒..︖) PRESENTATION FORM FOR VERTICAL IDEOGRAPHIC FULL STOP..PRESENTATION FORM FOR VERTICAL QUESTION MARK +FE12 ; Restricted ; not in XID+ # (︒) PRESENTATION FORM FOR VERTICAL IDEOGRAPHIC FULL STOP FE19 ; Restricted ; not in XID+ # (︙) PRESENTATION FORM FOR VERTICAL HORIZONTAL ELLIPSIS FE30 ; Restricted ; not in XID+ # (︰) PRESENTATION FORM FOR VERTICAL TWO DOT LEADER -FE33..FE34 ; future? # [2] (︳..︴) PRESENTATION FORM FOR VERTICAL LOW LINE..PRESENTATION FORM FOR VERTICAL WAVY LOW LINE -FE35..FE38 ; Restricted ; not in XID+ # [4] (︵..︸) PRESENTATION FORM FOR VERTICAL LEFT PARENTHESIS..PRESENTATION FORM FOR VERTICAL RIGHT CURLY BRACKET -FE47..FE4C ; Restricted ; not in XID+ # [6] (﹇..﹌) PRESENTATION FORM FOR VERTICAL LEFT SQUARE BRACKET..DOUBLE WAVY OVERLINE -FE4D..FE4F ; future? # [3] (﹍..﹏) DASHED LOW LINE..WAVY LOW LINE -FE50 ; Restricted ; not in XID+ # (﹐) SMALL COMMA FE52 ; Restricted ; not in XID+ # (﹒) SMALL FULL STOP -FE54..FE57 ; Restricted ; not in XID+ # [4] (﹔..﹗) SMALL SEMICOLON..SMALL EXCLAMATION MARK -FE59..FE5C ; Restricted ; not in XID+ # [4] (﹙..﹜) SMALL LEFT PARENTHESIS..SMALL RIGHT CURLY BRACKET -FE5F..FE62 ; Restricted ; not in XID+ # [4] (﹟..﹢) SMALL NUMBER SIGN..SMALL PLUS SIGN -FE64..FE66 ; Restricted ; not in XID+ # [3] (﹤..﹦) SMALL LESS-THAN SIGN..SMALL EQUALS SIGN -FE68..FE6B ; Restricted ; not in XID+ # [4] (﹨..﹫) SMALL REVERSE SOLIDUS..SMALL COMMERCIAL AT -FE70 ; Restricted ; not in XID+ # (ﹰ) ARABIC FATHATAN ISOLATED FORM -FE72 ; Restricted ; not in XID+ # (ﹲ) ARABIC DAMMATAN ISOLATED FORM -FE74 ; Restricted ; not in XID+ # (ﹴ) ARABIC KASRATAN ISOLATED FORM -FE76 ; Restricted ; not in XID+ # (ﹶ) ARABIC FATHA ISOLATED FORM -FE78 ; Restricted ; not in XID+ # (ﹸ) ARABIC DAMMA ISOLATED FORM -FE7A ; Restricted ; not in XID+ # (ﹺ) ARABIC KASRA ISOLATED FORM -FE7C ; Restricted ; not in XID+ # (ﹼ) ARABIC SHADDA ISOLATED FORM -FE7E ; Restricted ; not in XID+ # (ﹾ) ARABIC SUKUN ISOLATED FORM -FF01 ; Restricted ; not in XID+ # (！) FULLWIDTH EXCLAMATION MARK -FF02 ; Restricted ; not in XID+ # (＂) FULLWIDTH QUOTATION MARK -FF03 ; Restricted ; not in XID+ # (＃) FULLWIDTH NUMBER SIGN -FF04 ; Restricted ; not in XID+ # (＄) FULLWIDTH DOLLAR SIGN -FF05 ; Restricted ; not in XID+ # (％) FULLWIDTH PERCENT SIGN -FF06 ; Restricted ; not in XID+ # (＆) FULLWIDTH AMPERSAND -FF07 ; Restricted ; not in XID+ # (＇) FULLWIDTH APOSTROPHE -FF08 ; Restricted ; not in XID+ # (（) FULLWIDTH LEFT PARENTHESIS -FF09 ; Restricted ; not in XID+ # (）) FULLWIDTH RIGHT PARENTHESIS -FF0A ; Restricted ; not in XID+ # (＊) FULLWIDTH ASTERISK -FF0B ; Restricted ; not in XID+ # (＋) FULLWIDTH PLUS SIGN -FF0C ; Restricted ; not in XID+ # (，) FULLWIDTH COMMA -FF0F ; Restricted ; not in XID+ # (／) FULLWIDTH SOLIDUS -FF1A ; Restricted ; not in XID+ # (：) FULLWIDTH COLON -FF1B ; Restricted ; not in XID+ # (；) FULLWIDTH SEMICOLON -FF1C ; Restricted ; not in XID+ # (＜) FULLWIDTH LESS-THAN SIGN -FF1D ; Restricted ; not in XID+ # (＝) FULLWIDTH EQUALS SIGN -FF1E ; Restricted ; not in XID+ # (＞) FULLWIDTH GREATER-THAN SIGN -FF1F ; Restricted ; not in XID+ # (？) FULLWIDTH QUESTION MARK -FF20 ; Restricted ; not in XID+ # (＠) FULLWIDTH COMMERCIAL AT -FF3B ; Restricted ; not in XID+ # (［) FULLWIDTH LEFT SQUARE BRACKET -FF3C ; Restricted ; not in XID+ # (＼) FULLWIDTH REVERSE SOLIDUS -FF3D ; Restricted ; not in XID+ # (］) FULLWIDTH RIGHT SQUARE BRACKET -FF3E ; Restricted ; not in XID+ # (＾) FULLWIDTH CIRCUMFLEX ACCENT -FF3F ; future? # (＿) FULLWIDTH LOW LINE -FF40 ; Restricted ; not in XID+ # (｀) FULLWIDTH GRAVE ACCENT -FF5B ; Restricted ; not in XID+ # (｛) FULLWIDTH LEFT CURLY BRACKET -FF5C ; Restricted ; not in XID+ # (｜) FULLWIDTH VERTICAL LINE -FF5D ; Restricted ; not in XID+ # (｝) FULLWIDTH RIGHT CURLY BRACKET -FF5E ; Restricted ; not in XID+ # (～) FULLWIDTH TILDE -FFE3 ; Restricted ; not in XID+ # (￣) FULLWIDTH MACRON FFF9 ; Restricted ; not in XID+ # (U+FFF9) INTERLINEAR ANNOTATION ANCHOR FFFA ; Restricted ; not in XID+ # (U+FFFA) INTERLINEAR ANNOTATION SEPARATOR FFFB ; Restricted ; not in XID+ # (U+FFFB) INTERLINEAR ANNOTATION TERMINATOR @@ -66411,43 +66436,7 @@ FFFD ; Restricted ; not in XID+ # (�) REPLACEMENT CHARACTER 1343E ; Restricted ; not in XID+ # (U+1343E) EGYPTIAN HIEROGLYPH BEGIN WALLED ENCLOSURE 1343F ; Restricted ; not in XID+ # (U+1343F) EGYPTIAN HIEROGLYPH END WALLED ENCLOSURE 1F100 ; Restricted ; not in XID+ # (🄀) DIGIT ZERO FULL STOP -1F101 ; Restricted ; not in XID+ # (🄁) DIGIT ZERO COMMA -1F102 ; Restricted ; not in XID+ # (🄂) DIGIT ONE COMMA -1F103 ; Restricted ; not in XID+ # (🄃) DIGIT TWO COMMA -1F104 ; Restricted ; not in XID+ # (🄄) DIGIT THREE COMMA -1F105 ; Restricted ; not in XID+ # (🄅) DIGIT FOUR COMMA -1F106 ; Restricted ; not in XID+ # (🄆) DIGIT FIVE COMMA -1F107 ; Restricted ; not in XID+ # (🄇) DIGIT SIX COMMA -1F108 ; Restricted ; not in XID+ # (🄈) DIGIT SEVEN COMMA -1F109 ; Restricted ; not in XID+ # (🄉) DIGIT EIGHT COMMA -1F10A ; Restricted ; not in XID+ # (🄊) DIGIT NINE COMMA -1F110 ; Restricted ; not in XID+ # (🄐) PARENTHESIZED LATIN CAPITAL LETTER A -1F111 ; Restricted ; not in XID+ # (🄑) PARENTHESIZED LATIN CAPITAL LETTER B -1F112 ; Restricted ; not in XID+ # (🄒) PARENTHESIZED LATIN CAPITAL LETTER C -1F113 ; Restricted ; not in XID+ # (🄓) PARENTHESIZED LATIN CAPITAL LETTER D -1F114 ; Restricted ; not in XID+ # (🄔) PARENTHESIZED LATIN CAPITAL LETTER E -1F115 ; Restricted ; not in XID+ # (🄕) PARENTHESIZED LATIN CAPITAL LETTER F -1F116 ; Restricted ; not in XID+ # (🄖) PARENTHESIZED LATIN CAPITAL LETTER G -1F117 ; Restricted ; not in XID+ # (🄗) PARENTHESIZED LATIN CAPITAL LETTER H -1F118 ; Restricted ; not in XID+ # (🄘) PARENTHESIZED LATIN CAPITAL LETTER I -1F119 ; Restricted ; not in XID+ # (🄙) PARENTHESIZED LATIN CAPITAL LETTER J -1F11A ; Restricted ; not in XID+ # (🄚) PARENTHESIZED LATIN CAPITAL LETTER K -1F11B ; Restricted ; not in XID+ # (🄛) PARENTHESIZED LATIN CAPITAL LETTER L -1F11C ; Restricted ; not in XID+ # (🄜) PARENTHESIZED LATIN CAPITAL LETTER M -1F11D ; Restricted ; not in XID+ # (🄝) PARENTHESIZED LATIN CAPITAL LETTER N -1F11E ; Restricted ; not in XID+ # (🄞) PARENTHESIZED LATIN CAPITAL LETTER O -1F11F ; Restricted ; not in XID+ # (🄟) PARENTHESIZED LATIN CAPITAL LETTER P -1F120 ; Restricted ; not in XID+ # (🄠) PARENTHESIZED LATIN CAPITAL LETTER Q -1F121 ; Restricted ; not in XID+ # (🄡) PARENTHESIZED LATIN CAPITAL LETTER R -1F122 ; Restricted ; not in XID+ # (🄢) PARENTHESIZED LATIN CAPITAL LETTER S -1F123 ; Restricted ; not in XID+ # (🄣) PARENTHESIZED LATIN CAPITAL LETTER T -1F124 ; Restricted ; not in XID+ # (🄤) PARENTHESIZED LATIN CAPITAL LETTER U -1F125 ; Restricted ; not in XID+ # (🄥) PARENTHESIZED LATIN CAPITAL LETTER V -1F126 ; Restricted ; not in XID+ # (🄦) PARENTHESIZED LATIN CAPITAL LETTER W -1F127 ; Restricted ; not in XID+ # (🄧) PARENTHESIZED LATIN CAPITAL LETTER X -1F128 ; Restricted ; not in XID+ # (🄨) PARENTHESIZED LATIN CAPITAL LETTER Y -1F129 ; Restricted ; not in XID+ # (🄩) PARENTHESIZED LATIN CAPITAL LETTER Z E0001 ; Restricted ; not in XID+ # (U+E0001) LANGUAGE TAG E0020..E007F ; Restricted ; not in XID+ # [96] (U+E0020..U+E007F) TAG SPACE..CANCEL TAG -# Total code points: 594 +# Total code points: 226