diff options
| author | 2024-02-19 09:11:56 -0400 | |
|---|---|---|
| committer | 2024-02-19 09:11:56 -0400 | |
| commit | 6013b2ded106521ee9cae6bd77dacbd5254ff763 (patch) | |
| tree | 990f13cfbe4bfc20a08d2f097c4646984bffb565 /data/unicode/BidiBrackets.txt | |
| parent | Tried SIMD lower/upper string. Slower than linear. (diff) | |
| download | zg-6013b2ded106521ee9cae6bd77dacbd5254ff763.tar.gz zg-6013b2ded106521ee9cae6bd77dacbd5254ff763.tar.xz zg-6013b2ded106521ee9cae6bd77dacbd5254ff763.zip | |
Cleaned up directory structure
Diffstat (limited to 'data/unicode/BidiBrackets.txt')
| -rw-r--r-- | data/unicode/BidiBrackets.txt | 193 |
1 files changed, 193 insertions, 0 deletions
diff --git a/data/unicode/BidiBrackets.txt b/data/unicode/BidiBrackets.txt new file mode 100644 index 0000000..8cebea4 --- /dev/null +++ b/data/unicode/BidiBrackets.txt | |||
| @@ -0,0 +1,193 @@ | |||
| 1 | # BidiBrackets-15.1.0.txt | ||
| 2 | # Date: 2023-01-18 | ||
| 3 | # © 2023 Unicode®, Inc. | ||
| 4 | # Unicode and the Unicode Logo are registered trademarks of Unicode, Inc. in the U.S. and other countries. | ||
| 5 | # For terms of use, see https://www.unicode.org/terms_of_use.html | ||
| 6 | # | ||
| 7 | # Unicode Character Database | ||
| 8 | # For documentation, see https://www.unicode.org/reports/tr44/ | ||
| 9 | # | ||
| 10 | # Bidi_Paired_Bracket and Bidi_Paired_Bracket_Type Properties | ||
| 11 | # | ||
| 12 | # This file is a normative contributory data file in the Unicode | ||
| 13 | # Character Database. | ||
| 14 | # | ||
| 15 | # Bidi_Paired_Bracket is a normative property | ||
| 16 | # which establishes a mapping between characters that are treated as | ||
| 17 | # bracket pairs by the Unicode Bidirectional Algorithm. | ||
| 18 | # | ||
| 19 | # Bidi_Paired_Bracket_Type is a normative property | ||
| 20 | # which classifies characters into opening and closing paired brackets | ||
| 21 | # for the purposes of the Unicode Bidirectional Algorithm. | ||
| 22 | # | ||
| 23 | # This file lists the set of code points with Bidi_Paired_Bracket_Type | ||
| 24 | # property values Open and Close. The set is derived from the character | ||
| 25 | # properties General_Category (gc), Bidi_Class (bc), Bidi_Mirrored (Bidi_M), | ||
| 26 | # and Bidi_Mirroring_Glyph (bmg), as follows: two characters, A and B, | ||
| 27 | # form a bracket pair if A has gc=Ps and B has gc=Pe, both have bc=ON and | ||
| 28 | # Bidi_M=Y, and bmg of A is B. Bidi_Paired_Bracket (bpb) maps A to B and | ||
| 29 | # vice versa, and their Bidi_Paired_Bracket_Type (bpt) property values are | ||
| 30 | # Open (o) and Close (c), respectively. | ||
| 31 | # | ||
| 32 | # The brackets with ticks U+298D LEFT SQUARE BRACKET WITH TICK IN TOP CORNER | ||
| 33 | # through U+2990 RIGHT SQUARE BRACKET WITH TICK IN TOP CORNER are paired the | ||
| 34 | # same way their glyphs form mirror pairs, according to their bmg property | ||
| 35 | # values. They are not paired on the basis of a diagonal or antidiagonal | ||
| 36 | # matching of the corner ticks inferred from code point order. | ||
| 37 | # | ||
| 38 | # For legacy reasons, the characters U+FD3E ORNATE LEFT PARENTHESIS and | ||
| 39 | # U+FD3F ORNATE RIGHT PARENTHESIS do not mirror in bidirectional display | ||
| 40 | # and therefore do not form a bracket pair. | ||
| 41 | # | ||
| 42 | # The Unicode property value stability policy guarantees that characters | ||
| 43 | # which have bpt=o or bpt=c also have bc=ON and Bidi_M=Y. As a result, an | ||
| 44 | # implementation can optimize the lookup of the Bidi_Paired_Bracket_Type | ||
| 45 | # property values Open and Close by restricting the processing to characters | ||
| 46 | # with bc=ON. | ||
| 47 | # | ||
| 48 | # The format of the file is three fields separated by a semicolon. | ||
| 49 | # Field 0: Unicode code point value, represented as a hexadecimal value | ||
| 50 | # Field 1: Bidi_Paired_Bracket property value, a code point value or <none> | ||
| 51 | # Field 2: Bidi_Paired_Bracket_Type property value, one of the following: | ||
| 52 | # o Open | ||
| 53 | # c Close | ||
| 54 | # n None | ||
| 55 | # The names of the characters in field 0 are given in comments at the end | ||
| 56 | # of each line. | ||
| 57 | # | ||
| 58 | # For information on bidirectional paired brackets, see UAX #9: Unicode | ||
| 59 | # Bidirectional Algorithm, at https://www.unicode.org/reports/tr9/ | ||
| 60 | # | ||
| 61 | # This file was originally created by Andrew Glass and Laurentiu Iancu | ||
| 62 | # for Unicode 6.3. | ||
| 63 | |||
| 64 | 0028; 0029; o # LEFT PARENTHESIS | ||
| 65 | 0029; 0028; c # RIGHT PARENTHESIS | ||
| 66 | 005B; 005D; o # LEFT SQUARE BRACKET | ||
| 67 | 005D; 005B; c # RIGHT SQUARE BRACKET | ||
| 68 | 007B; 007D; o # LEFT CURLY BRACKET | ||
| 69 | 007D; 007B; c # RIGHT CURLY BRACKET | ||
| 70 | 0F3A; 0F3B; o # TIBETAN MARK GUG RTAGS GYON | ||
| 71 | 0F3B; 0F3A; c # TIBETAN MARK GUG RTAGS GYAS | ||
| 72 | 0F3C; 0F3D; o # TIBETAN MARK ANG KHANG GYON | ||
| 73 | 0F3D; 0F3C; c # TIBETAN MARK ANG KHANG GYAS | ||
| 74 | 169B; 169C; o # OGHAM FEATHER MARK | ||
| 75 | 169C; 169B; c # OGHAM REVERSED FEATHER MARK | ||
| 76 | 2045; 2046; o # LEFT SQUARE BRACKET WITH QUILL | ||
| 77 | 2046; 2045; c # RIGHT SQUARE BRACKET WITH QUILL | ||
| 78 | 207D; 207E; o # SUPERSCRIPT LEFT PARENTHESIS | ||
| 79 | 207E; 207D; c # SUPERSCRIPT RIGHT PARENTHESIS | ||
| 80 | 208D; 208E; o # SUBSCRIPT LEFT PARENTHESIS | ||
| 81 | 208E; 208D; c # SUBSCRIPT RIGHT PARENTHESIS | ||
| 82 | 2308; 2309; o # LEFT CEILING | ||
| 83 | 2309; 2308; c # RIGHT CEILING | ||
| 84 | 230A; 230B; o # LEFT FLOOR | ||
| 85 | 230B; 230A; c # RIGHT FLOOR | ||
| 86 | 2329; 232A; o # LEFT-POINTING ANGLE BRACKET | ||
| 87 | 232A; 2329; c # RIGHT-POINTING ANGLE BRACKET | ||
| 88 | 2768; 2769; o # MEDIUM LEFT PARENTHESIS ORNAMENT | ||
| 89 | 2769; 2768; c # MEDIUM RIGHT PARENTHESIS ORNAMENT | ||
| 90 | 276A; 276B; o # MEDIUM FLATTENED LEFT PARENTHESIS ORNAMENT | ||
| 91 | 276B; 276A; c # MEDIUM FLATTENED RIGHT PARENTHESIS ORNAMENT | ||
| 92 | 276C; 276D; o # MEDIUM LEFT-POINTING ANGLE BRACKET ORNAMENT | ||
| 93 | 276D; 276C; c # MEDIUM RIGHT-POINTING ANGLE BRACKET ORNAMENT | ||
| 94 | 276E; 276F; o # HEAVY LEFT-POINTING ANGLE QUOTATION MARK ORNAMENT | ||
| 95 | 276F; 276E; c # HEAVY RIGHT-POINTING ANGLE QUOTATION MARK ORNAMENT | ||
| 96 | 2770; 2771; o # HEAVY LEFT-POINTING ANGLE BRACKET ORNAMENT | ||
| 97 | 2771; 2770; c # HEAVY RIGHT-POINTING ANGLE BRACKET ORNAMENT | ||
| 98 | 2772; 2773; o # LIGHT LEFT TORTOISE SHELL BRACKET ORNAMENT | ||
| 99 | 2773; 2772; c # LIGHT RIGHT TORTOISE SHELL BRACKET ORNAMENT | ||
| 100 | 2774; 2775; o # MEDIUM LEFT CURLY BRACKET ORNAMENT | ||
| 101 | 2775; 2774; c # MEDIUM RIGHT CURLY BRACKET ORNAMENT | ||
| 102 | 27C5; 27C6; o # LEFT S-SHAPED BAG DELIMITER | ||
| 103 | 27C6; 27C5; c # RIGHT S-SHAPED BAG DELIMITER | ||
| 104 | 27E6; 27E7; o # MATHEMATICAL LEFT WHITE SQUARE BRACKET | ||
| 105 | 27E7; 27E6; c # MATHEMATICAL RIGHT WHITE SQUARE BRACKET | ||
| 106 | 27E8; 27E9; o # MATHEMATICAL LEFT ANGLE BRACKET | ||
| 107 | 27E9; 27E8; c # MATHEMATICAL RIGHT ANGLE BRACKET | ||
| 108 | 27EA; 27EB; o # MATHEMATICAL LEFT DOUBLE ANGLE BRACKET | ||
| 109 | 27EB; 27EA; c # MATHEMATICAL RIGHT DOUBLE ANGLE BRACKET | ||
| 110 | 27EC; 27ED; o # MATHEMATICAL LEFT WHITE TORTOISE SHELL BRACKET | ||
| 111 | 27ED; 27EC; c # MATHEMATICAL RIGHT WHITE TORTOISE SHELL BRACKET | ||
| 112 | 27EE; 27EF; o # MATHEMATICAL LEFT FLATTENED PARENTHESIS | ||
| 113 | 27EF; 27EE; c # MATHEMATICAL RIGHT FLATTENED PARENTHESIS | ||
| 114 | 2983; 2984; o # LEFT WHITE CURLY BRACKET | ||
| 115 | 2984; 2983; c # RIGHT WHITE CURLY BRACKET | ||
| 116 | 2985; 2986; o # LEFT WHITE PARENTHESIS | ||
| 117 | 2986; 2985; c # RIGHT WHITE PARENTHESIS | ||
| 118 | 2987; 2988; o # Z NOTATION LEFT IMAGE BRACKET | ||
| 119 | 2988; 2987; c # Z NOTATION RIGHT IMAGE BRACKET | ||
| 120 | 2989; 298A; o # Z NOTATION LEFT BINDING BRACKET | ||
| 121 | 298A; 2989; c # Z NOTATION RIGHT BINDING BRACKET | ||
| 122 | 298B; 298C; o # LEFT SQUARE BRACKET WITH UNDERBAR | ||
| 123 | 298C; 298B; c # RIGHT SQUARE BRACKET WITH UNDERBAR | ||
| 124 | 298D; 2990; o # LEFT SQUARE BRACKET WITH TICK IN TOP CORNER | ||
| 125 | 298E; 298F; c # RIGHT SQUARE BRACKET WITH TICK IN BOTTOM CORNER | ||
| 126 | 298F; 298E; o # LEFT SQUARE BRACKET WITH TICK IN BOTTOM CORNER | ||
| 127 | 2990; 298D; c # RIGHT SQUARE BRACKET WITH TICK IN TOP CORNER | ||
| 128 | 2991; 2992; o # LEFT ANGLE BRACKET WITH DOT | ||
| 129 | 2992; 2991; c # RIGHT ANGLE BRACKET WITH DOT | ||
| 130 | 2993; 2994; o # LEFT ARC LESS-THAN BRACKET | ||
| 131 | 2994; 2993; c # RIGHT ARC GREATER-THAN BRACKET | ||
| 132 | 2995; 2996; o # DOUBLE LEFT ARC GREATER-THAN BRACKET | ||
| 133 | 2996; 2995; c # DOUBLE RIGHT ARC LESS-THAN BRACKET | ||
| 134 | 2997; 2998; o # LEFT BLACK TORTOISE SHELL BRACKET | ||
| 135 | 2998; 2997; c # RIGHT BLACK TORTOISE SHELL BRACKET | ||
| 136 | 29D8; 29D9; o # LEFT WIGGLY FENCE | ||
| 137 | 29D9; 29D8; c # RIGHT WIGGLY FENCE | ||
| 138 | 29DA; 29DB; o # LEFT DOUBLE WIGGLY FENCE | ||
| 139 | 29DB; 29DA; c # RIGHT DOUBLE WIGGLY FENCE | ||
| 140 | 29FC; 29FD; o # LEFT-POINTING CURVED ANGLE BRACKET | ||
| 141 | 29FD; 29FC; c # RIGHT-POINTING CURVED ANGLE BRACKET | ||
| 142 | 2E22; 2E23; o # TOP LEFT HALF BRACKET | ||
| 143 | 2E23; 2E22; c # TOP RIGHT HALF BRACKET | ||
| 144 | 2E24; 2E25; o # BOTTOM LEFT HALF BRACKET | ||
| 145 | 2E25; 2E24; c # BOTTOM RIGHT HALF BRACKET | ||
| 146 | 2E26; 2E27; o # LEFT SIDEWAYS U BRACKET | ||
| 147 | 2E27; 2E26; c # RIGHT SIDEWAYS U BRACKET | ||
| 148 | 2E28; 2E29; o # LEFT DOUBLE PARENTHESIS | ||
| 149 | 2E29; 2E28; c # RIGHT DOUBLE PARENTHESIS | ||
| 150 | 2E55; 2E56; o # LEFT SQUARE BRACKET WITH STROKE | ||
| 151 | 2E56; 2E55; c # RIGHT SQUARE BRACKET WITH STROKE | ||
| 152 | 2E57; 2E58; o # LEFT SQUARE BRACKET WITH DOUBLE STROKE | ||
| 153 | 2E58; 2E57; c # RIGHT SQUARE BRACKET WITH DOUBLE STROKE | ||
| 154 | 2E59; 2E5A; o # TOP HALF LEFT PARENTHESIS | ||
| 155 | 2E5A; 2E59; c # TOP HALF RIGHT PARENTHESIS | ||
| 156 | 2E5B; 2E5C; o # BOTTOM HALF LEFT PARENTHESIS | ||
| 157 | 2E5C; 2E5B; c # BOTTOM HALF RIGHT PARENTHESIS | ||
| 158 | 3008; 3009; o # LEFT ANGLE BRACKET | ||
| 159 | 3009; 3008; c # RIGHT ANGLE BRACKET | ||
| 160 | 300A; 300B; o # LEFT DOUBLE ANGLE BRACKET | ||
| 161 | 300B; 300A; c # RIGHT DOUBLE ANGLE BRACKET | ||
| 162 | 300C; 300D; o # LEFT CORNER BRACKET | ||
| 163 | 300D; 300C; c # RIGHT CORNER BRACKET | ||
| 164 | 300E; 300F; o # LEFT WHITE CORNER BRACKET | ||
| 165 | 300F; 300E; c # RIGHT WHITE CORNER BRACKET | ||
| 166 | 3010; 3011; o # LEFT BLACK LENTICULAR BRACKET | ||
| 167 | 3011; 3010; c # RIGHT BLACK LENTICULAR BRACKET | ||
| 168 | 3014; 3015; o # LEFT TORTOISE SHELL BRACKET | ||
| 169 | 3015; 3014; c # RIGHT TORTOISE SHELL BRACKET | ||
| 170 | 3016; 3017; o # LEFT WHITE LENTICULAR BRACKET | ||
| 171 | 3017; 3016; c # RIGHT WHITE LENTICULAR BRACKET | ||
| 172 | 3018; 3019; o # LEFT WHITE TORTOISE SHELL BRACKET | ||
| 173 | 3019; 3018; c # RIGHT WHITE TORTOISE SHELL BRACKET | ||
| 174 | 301A; 301B; o # LEFT WHITE SQUARE BRACKET | ||
| 175 | 301B; 301A; c # RIGHT WHITE SQUARE BRACKET | ||
| 176 | FE59; FE5A; o # SMALL LEFT PARENTHESIS | ||
| 177 | FE5A; FE59; c # SMALL RIGHT PARENTHESIS | ||
| 178 | FE5B; FE5C; o # SMALL LEFT CURLY BRACKET | ||
| 179 | FE5C; FE5B; c # SMALL RIGHT CURLY BRACKET | ||
| 180 | FE5D; FE5E; o # SMALL LEFT TORTOISE SHELL BRACKET | ||
| 181 | FE5E; FE5D; c # SMALL RIGHT TORTOISE SHELL BRACKET | ||
| 182 | FF08; FF09; o # FULLWIDTH LEFT PARENTHESIS | ||
| 183 | FF09; FF08; c # FULLWIDTH RIGHT PARENTHESIS | ||
| 184 | FF3B; FF3D; o # FULLWIDTH LEFT SQUARE BRACKET | ||
| 185 | FF3D; FF3B; c # FULLWIDTH RIGHT SQUARE BRACKET | ||
| 186 | FF5B; FF5D; o # FULLWIDTH LEFT CURLY BRACKET | ||
| 187 | FF5D; FF5B; c # FULLWIDTH RIGHT CURLY BRACKET | ||
| 188 | FF5F; FF60; o # FULLWIDTH LEFT WHITE PARENTHESIS | ||
| 189 | FF60; FF5F; c # FULLWIDTH RIGHT WHITE PARENTHESIS | ||
| 190 | FF62; FF63; o # HALFWIDTH LEFT CORNER BRACKET | ||
| 191 | FF63; FF62; c # HALFWIDTH RIGHT CORNER BRACKET | ||
| 192 | |||
| 193 | # EOF | ||