1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 | package Torello.CSS; import Torello.Java.Additional.ByRef; import java.util.Vector; import java.util.function.Consumer; /** Represents a range of characters in Unicode. */ @Torello.JavaDoc.JDHeaderBackgroundImg(EmbedTagFileID="CSS_TOK") public class UnicodeRange extends CSSToken implements CharSequence, java.io.Serializable, Comparable<CharSequence> { /** <EMBED CLASS='external-html' DATA-FILE-ID=SVUID> */ protected static final long serialVersionUID = 1; // Don't worry about me right now. The Pseudo-Code said this should be "configurable". I have // not implemented this idea at the moment. In order to properly implement this, I would need // to build an entire "ParserBuilder" (a build that allows a user to configure-and-then-build) // his own parser, JUST FOR THIS ONE STUPID CONFIGURATION-FIELD. // // Since this is the only configuration in the entire Parer's Suite of CONSUME methods, I think // I'll one day make this a public & static Configuration-Field, and provide a javadoc warnign // (Similar to this one you are reading right now). There is just simply no reason to over // complicate this pacakge with a "Parser Builder" static final boolean UNICODE_RANGES = true; /** The starting value of the range that has been specified, as a Java Integer. */ public final int sRange; /** The ending value of the range that has been specified, as a Java Integer */ public final int eRange; // ******************************************************************************************** // ******************************************************************************************** // Private Constructor, API "is" and "if" Methods // ******************************************************************************************** // ******************************************************************************************** private UnicodeRange(final int[] css, final int sPos, final int ePos, int sRange, int eRange) { super(css, sPos, ePos); this.sRange = sRange; this.eRange = eRange; } @Override public final boolean isUnicodeRange() { return true; } @Override public final UnicodeRange ifUnicodeRange() { return this; } // ******************************************************************************************** // ******************************************************************************************** // User's Constructor: a static "build" method // ******************************************************************************************** // ******************************************************************************************** /** * <EMBED CLASS=defs DATA-TOK=Str DATA-P=rangeStr> * <EMBED CLASS='external-html' DATA-FILE-ID=BUILD_DESC> * @param rangeStr <EMBED CLASS='external-html' DATA-FILE-ID=BUILD_PARAM> * @return <EMBED CLASS='external-html' DATA-FILE-ID=BUILD_RET> * @throws TokenizeException <EMBED CLASS='external-html' DATA-FILE-ID=BUILD_TOK_EX> */ @SuppressWarnings("unchecked") public static UnicodeRange build(final String rangeStr) { return (UnicodeRange) CSSToken.build(rangeStr, INPUT_CHECKER, UnicodeRange::consume); } private static final CSSToken.InputChecker INPUT_CHECKER = (int[] css) -> { if (css.length < 3) throw new TokenizeException(UnicodeRange.class); if (! UnicodeRange.is(css, 0)) throw new TokenizeException ("String-text beginning does not constitute a valid CSS UnicodeRange-Token"); }; // ******************************************************************************************** // ******************************************************************************************** // Tokenizer's "is" Method(s) // ******************************************************************************************** // ******************************************************************************************** // *** *** *** *** *** *** *** *** *** *** *** *** *** *** *** *** *** *** *** *** *** *** *** // Copied from: // https://drafts.csswg.org/css-syntax-3/#check-if-three-code-points-would-start-a-unicode-range // April 27th, 2024 // *** *** *** *** *** *** *** *** *** *** *** *** *** *** *** *** *** *** *** *** *** *** *** // // 4.3.11. Check if three code points would start a unicode-range // // This section describes how to check if three code points would start a unicode-range. The // algorithm described here can be called explicitly with three code points, or can be called // with the input stream itself. In the latter case, the three code points in question are the // current input code point and the next two input code points, in that order. // // NOTE: This algorithm will not consume any additional code points. // // If all of the following are true: // // 1) The first code point is either U+0055 LATIN CAPITAL LETTER U (U) or // U+0075 LATIN SMALL LETTER U (u) // // 2) The second code point is U+002B PLUS SIGN (+). // // 3) The third code point is either U+003F QUESTION MARK (?) or a hex digit // // then return true. // // Otherwise return false. /** * Checks whether or not the next token to consume is a Unicode Range. * <EMBED CLASS=defs DATA-TOK=Escape-Sequence * DATA-URL=check-if-three-code-points-would-start-a-unicode-range DATA-OP=Check> * <EMBED CLASS=external-html DATA-FILE-ID=COPIED_CSS_WG> * <EMBED CLASS=external-html DATA-FILE-ID=CHECK_UNIRANGE_3CP> * @param css CSS-{@code String} as an array of code-points. * @param sPos The array-index where the tokenizer is to consume its next token * @return {@code TRUE} if and only if the next token in the array is a Unicode-Range */ public static boolean is(final int[] css, final int sPos) { if (! UNICODE_RANGES) return false; final int c1 = ((sPos + 0) < css.length) ? css[sPos+0] : 0; final int c2 = ((sPos + 1) < css.length) ? css[sPos+1] : 0; final int c3 = ((sPos + 2) < css.length) ? css[sPos+2] : 0; if ((c1 != 'u') && (c1 != 'U')) return false; if (c2 != '+') return false; if (c3 == '?') return true; if ((c3 >= '0') && (c3 <= '9')) return true; if ((c3 >= 'A') && (c3 <= 'F')) return true; if ((c3 >= 'a') && (c3 <= 'f')) return true; return false; } // ******************************************************************************************** // ******************************************************************************************** // CONSUME // ******************************************************************************************** // ******************************************************************************************** // *** *** *** *** *** *** *** *** *** *** *** *** *** *** *** *** *** *** *** *** *** *** *** // Copied From: // https://drafts.csswg.org/css-syntax-3/#consume-unicode-range-token // April 2024 // *** *** *** *** *** *** *** *** *** *** *** *** *** *** *** *** *** *** *** *** *** *** *** // // 4.3.14. Consume a unicode-range token // // This section describes how to consume a unicode-range token from a stream of code points. It // returns a <unicode-range-token>. // // NOTE: This algorithm does not do the verification of the first few code points that are // necessary to ensure the returned code points would constitute an // <unicode-range-token>. Ensure that the stream would start a unicode-range before // calling this algorithm. // // NOTE: This token is not produced by the tokenizer under normal circumstances. This algorithm // is only called during consume the value of a unicode-range descriptor, which itself is // only called as a special case for parsing the unicode-range descriptor; this single // invocation in the entire language is due to a bad syntax design in early CSS. // // 1) Consume the next two input code points and discard them. // // 2) Consume as many hex digits as possible, but no more than 6. If less than 6 hex digits // were consumed, consume as many U+003F QUESTION MARK (?) code points as possible, but no // more than enough to make the total of hex digits and U+003F QUESTION MARK (?) code // points equal to 6. // // Let first segment be the consumed code points. // // 3) If first segment contains any question mark code points, then: // // 1) Replace the question marks in first segment with U+0030 DIGIT ZERO (0) code points, // and interpret the result as a hexadecimal number. Let this be start of range. // // 2) Replace the question marks in first segment with U+0046 LATIN CAPITAL LETTER F (F) // code points, and interpret the result as a hexadecimal number. Let this be end of // range. // // 3) Return a new <unicode-range-token> starting at start of range and ending at end of // range. // // 4) Otherwise, interpret first segment as a hexadecimal number, and let the result be start // of range. // // 5) If the next 2 input code points are U+002D HYPHEN-MINUS (-) followed by a hex digit, // then: // // 1) Consume the next input code point. // // 2) Consume as many hex digits as possible, but no more than 6. Interpret the consumed // code points as a hexadecimal number. Let this be end of range. // // 3) Return a new <unicode-range-token> starting at start of range and ending at end of // range. // // 6) Otherwise, return a new <unicode-range-token> both starting and ending at start of range. /** * This is a tokenizer method which <B>"consumes"</B> the next {@code UnicodeRange}-Token * from the input Code-Point Array. * * <EMBED CLASS=defs DATA-TOK=UnicodeRange DATA-URL=consume-unicode-range-token * DATA-OP=Consume> * <EMBED CLASS=external-html DATA-FILE-ID=COPIED_CSS_WG> * <EMBED CLASS=external-html DATA-FILE-ID=UNICODE_RANGE_TOKEN> * <EMBED CLASS=external-html DATA-FILE-ID=UNICODE_RG_TOK_SVG> */ protected static void consume( // When invoked from 'CSSTokenizer' final int[] css, // C, int[] css final ByRef<Integer> POS, // P, array-pos loop-variable final Consumer<CSSToken> returnParsedToken ) { // 1) Consume the next two input code points and discard them. int pos = POS.f + 2; // 2) Consume as many hex digits as possible, but no more than 6. If less than 6 hex // digits were consumed, consume as many U+003F QUESTION MARK (?) code points as // possible, but no more than enough to make the total of hex digits and // U+003F QUESTION MARK (?) code points equal to 6. // // Let first segment be the consumed code points. int count = 0; boolean hadQuestionMarks = false; while ( (count < 6) && (pos < css.length) && isHexDigit(css[pos]) ) { count++; pos++; } while ( (count < 6) && (pos < css.length) && (css[pos] == '?') ) { count++; pos++; hadQuestionMarks=true;} // *** 3) If first segment contains any question mark code points, then: // [The next 3 bullet points were UN-INDENTED, for readability] // // 1) Replace the question marks in first segment with U+0030 DIGIT ZERO (0) code points, // and interpret the result as a hexadecimal number. Let this be start of range. // // 2) Replace the question marks in first segment with U+0046 LATIN CAPITAL LETTER F (F) // code points, and interpret the result as a hexadecimal number. Let this be end of // range. // // 3) Return a new <unicode-range-token> starting at start of range and ending at end of // range. final String s1 = new String(css, POS.f + 2, pos - (POS.f + 2)); final int sRange, eRange; if (hadQuestionMarks) { sRange = Integer.parseInt(s1.replace('?', '0'), 16); eRange = Integer.parseInt(s1.replace('?', 'F'), 16); returnParsedToken.accept(new UnicodeRange(css, POS.f, pos, sRange, eRange)); POS.f = pos; return; } // 4) Otherwise, interpret first segment as a hexadecimal number, and let the result be // start of range. else sRange = Integer.parseInt(s1, 16); // *** 5) If the next 2 input code points are U+002D HYPHEN-MINUS (-) followed by a hex // digit, then: // [The next 3 bullet points were UN-INDENTED, for readability] // // 1) Consume the next input code point. // // 2) Consume as many hex digits as possible, but no more than 6. Interpret the consumed // code points as a hexadecimal number. Let this be end of range. // // 3) Return a new <unicode-range-token> starting at start of range and ending at end of // range. if (((pos+1) < css.length) && (css[pos] == '-') && isHexDigit(css[pos+1])) { pos++; count = 0; int c; final StringBuilder sb = new StringBuilder(); while ( (count < 6) && (pos < css.length) && isHexDigit(c = css[pos]) ) { sb.append((char) c); count++; pos++; } eRange = Integer.parseInt(sb.toString(), 16); returnParsedToken.accept(new UnicodeRange(css, POS.f, pos, sRange, eRange)); POS.f = pos; return; } // 6) Otherwise, return a new <unicode-range-token> both starting and ending at start of // range. returnParsedToken.accept(new UnicodeRange(css, POS.f, pos, sRange, sRange)); POS.f = pos; } private static boolean isHexDigit(int codePoint) { return ((codePoint >= '0') && (codePoint <= '9')) || ((codePoint >= 'a') && (codePoint <= 'f')) || ((codePoint >= 'A') && (codePoint <= 'F')); } } |