Tim van der Lippe | 706ec96 | 2021-06-04 13:24:42 +0100 | [diff] [blame] | 1 | var EOF = 0; |
| 2 | |
| 3 | // https://drafts.csswg.org/css-syntax-3/ |
| 4 | // § 4.2. Definitions |
| 5 | |
| 6 | // digit |
| 7 | // A code point between U+0030 DIGIT ZERO (0) and U+0039 DIGIT NINE (9). |
| 8 | function isDigit(code) { |
| 9 | return code >= 0x0030 && code <= 0x0039; |
| 10 | } |
| 11 | |
| 12 | // hex digit |
| 13 | // A digit, or a code point between U+0041 LATIN CAPITAL LETTER A (A) and U+0046 LATIN CAPITAL LETTER F (F), |
| 14 | // or a code point between U+0061 LATIN SMALL LETTER A (a) and U+0066 LATIN SMALL LETTER F (f). |
| 15 | function isHexDigit(code) { |
| 16 | return ( |
| 17 | isDigit(code) || // 0 .. 9 |
| 18 | (code >= 0x0041 && code <= 0x0046) || // A .. F |
| 19 | (code >= 0x0061 && code <= 0x0066) // a .. f |
| 20 | ); |
| 21 | } |
| 22 | |
| 23 | // uppercase letter |
| 24 | // A code point between U+0041 LATIN CAPITAL LETTER A (A) and U+005A LATIN CAPITAL LETTER Z (Z). |
| 25 | function isUppercaseLetter(code) { |
| 26 | return code >= 0x0041 && code <= 0x005A; |
| 27 | } |
| 28 | |
| 29 | // lowercase letter |
| 30 | // A code point between U+0061 LATIN SMALL LETTER A (a) and U+007A LATIN SMALL LETTER Z (z). |
| 31 | function isLowercaseLetter(code) { |
| 32 | return code >= 0x0061 && code <= 0x007A; |
| 33 | } |
| 34 | |
| 35 | // letter |
| 36 | // An uppercase letter or a lowercase letter. |
| 37 | function isLetter(code) { |
| 38 | return isUppercaseLetter(code) || isLowercaseLetter(code); |
| 39 | } |
| 40 | |
| 41 | // non-ASCII code point |
| 42 | // A code point with a value equal to or greater than U+0080 <control>. |
| 43 | function isNonAscii(code) { |
| 44 | return code >= 0x0080; |
| 45 | } |
| 46 | |
| 47 | // name-start code point |
| 48 | // A letter, a non-ASCII code point, or U+005F LOW LINE (_). |
| 49 | function isNameStart(code) { |
| 50 | return isLetter(code) || isNonAscii(code) || code === 0x005F; |
| 51 | } |
| 52 | |
| 53 | // name code point |
| 54 | // A name-start code point, a digit, or U+002D HYPHEN-MINUS (-). |
| 55 | function isName(code) { |
| 56 | return isNameStart(code) || isDigit(code) || code === 0x002D; |
| 57 | } |
| 58 | |
| 59 | // non-printable code point |
| 60 | // A code point between U+0000 NULL and U+0008 BACKSPACE, or U+000B LINE TABULATION, |
| 61 | // or a code point between U+000E SHIFT OUT and U+001F INFORMATION SEPARATOR ONE, or U+007F DELETE. |
| 62 | function isNonPrintable(code) { |
| 63 | return ( |
| 64 | (code >= 0x0000 && code <= 0x0008) || |
| 65 | (code === 0x000B) || |
| 66 | (code >= 0x000E && code <= 0x001F) || |
| 67 | (code === 0x007F) |
| 68 | ); |
| 69 | } |
| 70 | |
| 71 | // newline |
| 72 | // U+000A LINE FEED. Note that U+000D CARRIAGE RETURN and U+000C FORM FEED are not included in this definition, |
| 73 | // as they are converted to U+000A LINE FEED during preprocessing. |
| 74 | // TODO: we doesn't do a preprocessing, so check a code point for U+000D CARRIAGE RETURN and U+000C FORM FEED |
| 75 | function isNewline(code) { |
| 76 | return code === 0x000A || code === 0x000D || code === 0x000C; |
| 77 | } |
| 78 | |
| 79 | // whitespace |
| 80 | // A newline, U+0009 CHARACTER TABULATION, or U+0020 SPACE. |
| 81 | function isWhiteSpace(code) { |
| 82 | return isNewline(code) || code === 0x0020 || code === 0x0009; |
| 83 | } |
| 84 | |
| 85 | // § 4.3.8. Check if two code points are a valid escape |
| 86 | function isValidEscape(first, second) { |
| 87 | // If the first code point is not U+005C REVERSE SOLIDUS (\), return false. |
| 88 | if (first !== 0x005C) { |
| 89 | return false; |
| 90 | } |
| 91 | |
| 92 | // Otherwise, if the second code point is a newline or EOF, return false. |
| 93 | if (isNewline(second) || second === EOF) { |
| 94 | return false; |
| 95 | } |
| 96 | |
| 97 | // Otherwise, return true. |
| 98 | return true; |
| 99 | } |
| 100 | |
| 101 | // § 4.3.9. Check if three code points would start an identifier |
| 102 | function isIdentifierStart(first, second, third) { |
| 103 | // Look at the first code point: |
| 104 | |
| 105 | // U+002D HYPHEN-MINUS |
| 106 | if (first === 0x002D) { |
| 107 | // If the second code point is a name-start code point or a U+002D HYPHEN-MINUS, |
| 108 | // or the second and third code points are a valid escape, return true. Otherwise, return false. |
| 109 | return ( |
| 110 | isNameStart(second) || |
| 111 | second === 0x002D || |
| 112 | isValidEscape(second, third) |
| 113 | ); |
| 114 | } |
| 115 | |
| 116 | // name-start code point |
| 117 | if (isNameStart(first)) { |
| 118 | // Return true. |
| 119 | return true; |
| 120 | } |
| 121 | |
| 122 | // U+005C REVERSE SOLIDUS (\) |
| 123 | if (first === 0x005C) { |
| 124 | // If the first and second code points are a valid escape, return true. Otherwise, return false. |
| 125 | return isValidEscape(first, second); |
| 126 | } |
| 127 | |
| 128 | // anything else |
| 129 | // Return false. |
| 130 | return false; |
| 131 | } |
| 132 | |
| 133 | // § 4.3.10. Check if three code points would start a number |
| 134 | function isNumberStart(first, second, third) { |
| 135 | // Look at the first code point: |
| 136 | |
| 137 | // U+002B PLUS SIGN (+) |
| 138 | // U+002D HYPHEN-MINUS (-) |
| 139 | if (first === 0x002B || first === 0x002D) { |
| 140 | // If the second code point is a digit, return true. |
| 141 | if (isDigit(second)) { |
| 142 | return 2; |
| 143 | } |
| 144 | |
| 145 | // Otherwise, if the second code point is a U+002E FULL STOP (.) |
| 146 | // and the third code point is a digit, return true. |
| 147 | // Otherwise, return false. |
| 148 | return second === 0x002E && isDigit(third) ? 3 : 0; |
| 149 | } |
| 150 | |
| 151 | // U+002E FULL STOP (.) |
| 152 | if (first === 0x002E) { |
| 153 | // If the second code point is a digit, return true. Otherwise, return false. |
| 154 | return isDigit(second) ? 2 : 0; |
| 155 | } |
| 156 | |
| 157 | // digit |
| 158 | if (isDigit(first)) { |
| 159 | // Return true. |
| 160 | return 1; |
| 161 | } |
| 162 | |
| 163 | // anything else |
| 164 | // Return false. |
| 165 | return 0; |
| 166 | } |
| 167 | |
| 168 | // |
| 169 | // Misc |
| 170 | // |
| 171 | |
| 172 | // detect BOM (https://en.wikipedia.org/wiki/Byte_order_mark) |
| 173 | function isBOM(code) { |
| 174 | // UTF-16BE |
| 175 | if (code === 0xFEFF) { |
| 176 | return 1; |
| 177 | } |
| 178 | |
| 179 | // UTF-16LE |
| 180 | if (code === 0xFFFE) { |
| 181 | return 1; |
| 182 | } |
| 183 | |
| 184 | return 0; |
| 185 | } |
| 186 | |
| 187 | // Fast code category |
| 188 | // |
| 189 | // https://drafts.csswg.org/css-syntax/#tokenizer-definitions |
| 190 | // > non-ASCII code point |
| 191 | // > A code point with a value equal to or greater than U+0080 <control> |
| 192 | // > name-start code point |
| 193 | // > A letter, a non-ASCII code point, or U+005F LOW LINE (_). |
| 194 | // > name code point |
| 195 | // > A name-start code point, a digit, or U+002D HYPHEN-MINUS (-) |
| 196 | // That means only ASCII code points has a special meaning and we define a maps for 0..127 codes only |
| 197 | var CATEGORY = new Array(0x80); |
| 198 | charCodeCategory.Eof = 0x80; |
| 199 | charCodeCategory.WhiteSpace = 0x82; |
| 200 | charCodeCategory.Digit = 0x83; |
| 201 | charCodeCategory.NameStart = 0x84; |
| 202 | charCodeCategory.NonPrintable = 0x85; |
| 203 | |
| 204 | for (var i = 0; i < CATEGORY.length; i++) { |
| 205 | switch (true) { |
| 206 | case isWhiteSpace(i): |
| 207 | CATEGORY[i] = charCodeCategory.WhiteSpace; |
| 208 | break; |
| 209 | |
| 210 | case isDigit(i): |
| 211 | CATEGORY[i] = charCodeCategory.Digit; |
| 212 | break; |
| 213 | |
| 214 | case isNameStart(i): |
| 215 | CATEGORY[i] = charCodeCategory.NameStart; |
| 216 | break; |
| 217 | |
| 218 | case isNonPrintable(i): |
| 219 | CATEGORY[i] = charCodeCategory.NonPrintable; |
| 220 | break; |
| 221 | |
| 222 | default: |
| 223 | CATEGORY[i] = i || charCodeCategory.Eof; |
| 224 | } |
| 225 | } |
| 226 | |
| 227 | function charCodeCategory(code) { |
| 228 | return code < 0x80 ? CATEGORY[code] : charCodeCategory.NameStart; |
| 229 | }; |
| 230 | |
| 231 | module.exports = { |
| 232 | isDigit: isDigit, |
| 233 | isHexDigit: isHexDigit, |
| 234 | isUppercaseLetter: isUppercaseLetter, |
| 235 | isLowercaseLetter: isLowercaseLetter, |
| 236 | isLetter: isLetter, |
| 237 | isNonAscii: isNonAscii, |
| 238 | isNameStart: isNameStart, |
| 239 | isName: isName, |
| 240 | isNonPrintable: isNonPrintable, |
| 241 | isNewline: isNewline, |
| 242 | isWhiteSpace: isWhiteSpace, |
| 243 | isValidEscape: isValidEscape, |
| 244 | isIdentifierStart: isIdentifierStart, |
| 245 | isNumberStart: isNumberStart, |
| 246 | |
| 247 | isBOM: isBOM, |
| 248 | charCodeCategory: charCodeCategory |
| 249 | }; |