1 /* gnu/regexp/RESyntax.java 2 Copyright (C) 1998-2002, 2004 Free Software Foundation, Inc. 3 4 This file is part of GNU Classpath. 5 6 GNU Classpath is free software; you can redistribute it and/or modify 7 it under the terms of the GNU General Public License as published by 8 the Free Software Foundation; either version 2, or (at your option) 9 any later version. 10 11 GNU Classpath is distributed in the hope that it will be useful, but 12 WITHOUT ANY WARRANTY; without even the implied warranty of 13 MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU 14 General Public License for more details. 15 16 You should have received a copy of the GNU General Public License 17 along with GNU Classpath; see the file COPYING. If not, write to the 18 Free Software Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA 19 02110-1301 USA. 20 21 Linking this library statically or dynamically with other modules is 22 making a combined work based on this library. Thus, the terms and 23 conditions of the GNU General Public License cover the whole 24 combination. 25 26 As a special exception, the copyright holders of this library give you 27 permission to link this library with independent modules to produce an 28 executable, regardless of the license terms of these independent 29 modules, and to copy and distribute the resulting executable under 30 terms of your choice, provided that you also meet, for each linked 31 independent module, the terms and conditions of the license of that 32 module. An independent module is a module which is not derived from 33 or based on this library. If you modify this library, you may extend 34 this exception to your version of the library, but you are not 35 obligated to do so. If you do not wish to do so, delete this 36 exception statement from your version. */ 37 38 39 package gnu.regexp; 40 import java.io.Serializable; 41 import java.util.BitSet; 42 43 /** 44 * An RESyntax specifies the way a regular expression will be compiled. 45 * This class provides a number of predefined useful constants for 46 * emulating popular regular expression syntaxes. Additionally the 47 * user may construct his or her own syntax, using any combination of the 48 * syntax bit constants. The syntax is an optional argument to any of the 49 * matching methods on class RE. 50 * 51 * @author <A HREF="mailto:wes@cacas.org">Wes Biggs</A> 52 */ 53 54 public final class RESyntax implements Serializable { 55 static final String DEFAULT_LINE_SEPARATOR = System.getProperty("line.separator"); 56 57 private static final String SYNTAX_IS_FINAL = RE.getLocalizedMessage("syntax.final"); 58 59 private BitSet bits; 60 61 // true for the constant defined syntaxes 62 private boolean isFinal = false; 63 64 private String lineSeparator = DEFAULT_LINE_SEPARATOR; 65 66 // Values for constants are bit indexes 67 68 /** 69 * Syntax bit. Backslash is an escape character in lists. 70 */ 71 public static final int RE_BACKSLASH_ESCAPE_IN_LISTS = 0; 72 73 /** 74 * Syntax bit. Use \? instead of ? and \+ instead of +. 75 */ 76 public static final int RE_BK_PLUS_QM = 1; 77 78 /** 79 * Syntax bit. POSIX character classes ([:...:]) in lists are allowed. 80 */ 81 public static final int RE_CHAR_CLASSES = 2; 82 83 /** 84 * Syntax bit. ^ and $ are special everywhere. 85 * <B>Not implemented.</B> 86 */ 87 public static final int RE_CONTEXT_INDEP_ANCHORS = 3; 88 89 /** 90 * Syntax bit. Repetition operators are only special in valid positions. 91 * <B>Not implemented.</B> 92 */ 93 public static final int RE_CONTEXT_INDEP_OPS = 4; 94 95 /** 96 * Syntax bit. Repetition and alternation operators are invalid 97 * at start and end of pattern and other places. 98 * <B>Not implemented</B>. 99 */ 100 public static final int RE_CONTEXT_INVALID_OPS = 5; 101 102 /** 103 * Syntax bit. Match-any-character operator (.) matches a newline. 104 */ 105 public static final int RE_DOT_NEWLINE = 6; 106 107 /** 108 * Syntax bit. Match-any-character operator (.) does not match a null. 109 */ 110 public static final int RE_DOT_NOT_NULL = 7; 111 112 /** 113 * Syntax bit. Intervals ({x}, {x,}, {x,y}) are allowed. 114 */ 115 public static final int RE_INTERVALS = 8; 116 117 /** 118 * Syntax bit. No alternation (|), match one-or-more (+), or 119 * match zero-or-one (?) operators. 120 */ 121 public static final int RE_LIMITED_OPS = 9; 122 123 /** 124 * Syntax bit. Newline is an alternation operator. 125 */ 126 public static final int RE_NEWLINE_ALT = 10; // impl. 127 128 /** 129 * Syntax bit. Intervals use { } instead of \{ \} 130 */ 131 public static final int RE_NO_BK_BRACES = 11; 132 133 /** 134 * Syntax bit. Grouping uses ( ) instead of \( \). 135 */ 136 public static final int RE_NO_BK_PARENS = 12; 137 138 /** 139 * Syntax bit. Backreferences not allowed. 140 */ 141 public static final int RE_NO_BK_REFS = 13; 142 143 /** 144 * Syntax bit. Alternation uses | instead of \| 145 */ 146 public static final int RE_NO_BK_VBAR = 14; 147 148 /** 149 * Syntax bit. <B>Not implemented</B>. 150 */ 151 public static final int RE_NO_EMPTY_RANGES = 15; 152 153 /** 154 * Syntax bit. An unmatched right parenthesis (')' or '\)', depending 155 * on RE_NO_BK_PARENS) will throw an exception when compiling. 156 */ 157 public static final int RE_UNMATCHED_RIGHT_PAREN_ORD = 16; 158 159 /** 160 * Syntax bit. <B>Not implemented.</B> 161 */ 162 public static final int RE_HAT_LISTS_NOT_NEWLINE = 17; 163 164 /** 165 * Syntax bit. Stingy matching is allowed (+?, *?, ??, {x,y}?). 166 */ 167 public static final int RE_STINGY_OPS = 18; 168 169 /** 170 * Syntax bit. Allow character class escapes (\d, \D, \s, \S, \w, \W). 171 */ 172 public static final int RE_CHAR_CLASS_ESCAPES = 19; 173 174 /** 175 * Syntax bit. Allow use of (?:xxx) grouping (subexpression is not saved). 176 */ 177 public static final int RE_PURE_GROUPING = 20; 178 179 /** 180 * Syntax bit. Allow use of (?=xxx) and (?!xxx) apply the subexpression 181 * to the text following the current position without consuming that text. 182 */ 183 public static final int RE_LOOKAHEAD = 21; 184 185 /** 186 * Syntax bit. Allow beginning- and end-of-string anchors (\A, \Z). 187 */ 188 public static final int RE_STRING_ANCHORS = 22; 189 190 /** 191 * Syntax bit. Allow embedded comments, (?#comment), as in Perl5. 192 */ 193 public static final int RE_COMMENTS = 23; 194 195 /** 196 * Syntax bit. Allow character class escapes within lists, as in Perl5. 197 */ 198 public static final int RE_CHAR_CLASS_ESC_IN_LISTS = 24; 199 200 /** 201 * Syntax bit. Possessive matching is allowed (++, *+, ?+, {x,y}+). 202 */ 203 public static final int RE_POSSESSIVE_OPS = 25; 204 205 private static final int BIT_TOTAL = 26; 206 207 /** 208 * Predefined syntax. 209 * Emulates regular expression support in the awk utility. 210 */ 211 public static final RESyntax RE_SYNTAX_AWK; 212 213 /** 214 * Predefined syntax. 215 * Emulates regular expression support in the ed utility. 216 */ 217 public static final RESyntax RE_SYNTAX_ED; 218 219 /** 220 * Predefined syntax. 221 * Emulates regular expression support in the egrep utility. 222 */ 223 public static final RESyntax RE_SYNTAX_EGREP; 224 225 /** 226 * Predefined syntax. 227 * Emulates regular expression support in the GNU Emacs editor. 228 */ 229 public static final RESyntax RE_SYNTAX_EMACS; 230 231 /** 232 * Predefined syntax. 233 * Emulates regular expression support in the grep utility. 234 */ 235 public static final RESyntax RE_SYNTAX_GREP; 236 237 /** 238 * Predefined syntax. 239 * Emulates regular expression support in the POSIX awk specification. 240 */ 241 public static final RESyntax RE_SYNTAX_POSIX_AWK; 242 243 /** 244 * Predefined syntax. 245 * Emulates POSIX basic regular expression support. 246 */ 247 public static final RESyntax RE_SYNTAX_POSIX_BASIC; 248 249 /** 250 * Predefined syntax. 251 * Emulates regular expression support in the POSIX egrep specification. 252 */ 253 public static final RESyntax RE_SYNTAX_POSIX_EGREP; 254 255 /** 256 * Predefined syntax. 257 * Emulates POSIX extended regular expression support. 258 */ 259 public static final RESyntax RE_SYNTAX_POSIX_EXTENDED; 260 261 /** 262 * Predefined syntax. 263 * Emulates POSIX basic minimal regular expressions. 264 */ 265 public static final RESyntax RE_SYNTAX_POSIX_MINIMAL_BASIC; 266 267 /** 268 * Predefined syntax. 269 * Emulates POSIX extended minimal regular expressions. 270 */ 271 public static final RESyntax RE_SYNTAX_POSIX_MINIMAL_EXTENDED; 272 273 /** 274 * Predefined syntax. 275 * Emulates regular expression support in the sed utility. 276 */ 277 public static final RESyntax RE_SYNTAX_SED; 278 279 /** 280 * Predefined syntax. 281 * Emulates regular expression support in Larry Wall's perl, version 4, 282 */ 283 public static final RESyntax RE_SYNTAX_PERL4; 284 285 /** 286 * Predefined syntax. 287 * Emulates regular expression support in Larry Wall's perl, version 4, 288 * using single line mode (/s modifier). 289 */ 290 public static final RESyntax RE_SYNTAX_PERL4_S; // single line mode (/s) 291 292 /** 293 * Predefined syntax. 294 * Emulates regular expression support in Larry Wall's perl, version 5. 295 */ 296 public static final RESyntax RE_SYNTAX_PERL5; 297 298 /** 299 * Predefined syntax. 300 * Emulates regular expression support in Larry Wall's perl, version 5, 301 * using single line mode (/s modifier). 302 */ 303 public static final RESyntax RE_SYNTAX_PERL5_S; 304 305 /** 306 * Predefined syntax. 307 * Emulates regular expression support in Java 1.4's java.util.regex 308 * package. 309 */ 310 public static final RESyntax RE_SYNTAX_JAVA_1_4; 311 312 static { 313 // Define syntaxes 314 315 RE_SYNTAX_EMACS = new RESyntax().makeFinal(); 316 317 RESyntax RE_SYNTAX_POSIX_COMMON = new RESyntax() 318 .set(RE_CHAR_CLASSES) 319 .set(RE_DOT_NEWLINE) 320 .set(RE_DOT_NOT_NULL) 321 .set(RE_INTERVALS) 322 .set(RE_NO_EMPTY_RANGES) 323 .makeFinal(); 324 325 RE_SYNTAX_POSIX_BASIC = new RESyntax(RE_SYNTAX_POSIX_COMMON) 326 .set(RE_BK_PLUS_QM) 327 .makeFinal(); 328 329 RE_SYNTAX_POSIX_EXTENDED = new RESyntax(RE_SYNTAX_POSIX_COMMON) 330 .set(RE_CONTEXT_INDEP_ANCHORS) 331 .set(RE_CONTEXT_INDEP_OPS) 332 .set(RE_NO_BK_BRACES) 333 .set(RE_NO_BK_PARENS) 334 .set(RE_NO_BK_VBAR) 335 .set(RE_UNMATCHED_RIGHT_PAREN_ORD) 336 .makeFinal(); 337 338 RE_SYNTAX_AWK = new RESyntax() 339 .set(RE_BACKSLASH_ESCAPE_IN_LISTS) 340 .set(RE_DOT_NOT_NULL) 341 .set(RE_NO_BK_PARENS) 342 .set(RE_NO_BK_REFS) 343 .set(RE_NO_BK_VBAR) 344 .set(RE_NO_EMPTY_RANGES) 345 .set(RE_UNMATCHED_RIGHT_PAREN_ORD) 346 .makeFinal(); 347 348 RE_SYNTAX_POSIX_AWK = new RESyntax(RE_SYNTAX_POSIX_EXTENDED) 349 .set(RE_BACKSLASH_ESCAPE_IN_LISTS) 350 .makeFinal(); 351 352 RE_SYNTAX_GREP = new RESyntax() 353 .set(RE_BK_PLUS_QM) 354 .set(RE_CHAR_CLASSES) 355 .set(RE_HAT_LISTS_NOT_NEWLINE) 356 .set(RE_INTERVALS) 357 .set(RE_NEWLINE_ALT) 358 .makeFinal(); 359 360 RE_SYNTAX_EGREP = new RESyntax() 361 .set(RE_CHAR_CLASSES) 362 .set(RE_CONTEXT_INDEP_ANCHORS) 363 .set(RE_CONTEXT_INDEP_OPS) 364 .set(RE_HAT_LISTS_NOT_NEWLINE) 365 .set(RE_NEWLINE_ALT) 366 .set(RE_NO_BK_PARENS) 367 .set(RE_NO_BK_VBAR) 368 .makeFinal(); 369 370 RE_SYNTAX_POSIX_EGREP = new RESyntax(RE_SYNTAX_EGREP) 371 .set(RE_INTERVALS) 372 .set(RE_NO_BK_BRACES) 373 .makeFinal(); 374 375 /* P1003.2/D11.2, section 4.20.7.1, lines 5078ff. */ 376 377 RE_SYNTAX_ED = new RESyntax(RE_SYNTAX_POSIX_BASIC) 378 .makeFinal(); 379 380 RE_SYNTAX_SED = new RESyntax(RE_SYNTAX_POSIX_BASIC) 381 .makeFinal(); 382 383 RE_SYNTAX_POSIX_MINIMAL_BASIC = new RESyntax(RE_SYNTAX_POSIX_COMMON) 384 .set(RE_LIMITED_OPS) 385 .makeFinal(); 386 387 /* Differs from RE_SYNTAX_POSIX_EXTENDED in that RE_CONTEXT_INVALID_OPS 388 replaces RE_CONTEXT_INDEP_OPS and RE_NO_BK_REFS is added. */ 389 390 RE_SYNTAX_POSIX_MINIMAL_EXTENDED = new RESyntax(RE_SYNTAX_POSIX_COMMON) 391 .set(RE_CONTEXT_INDEP_ANCHORS) 392 .set(RE_CONTEXT_INVALID_OPS) 393 .set(RE_NO_BK_BRACES) 394 .set(RE_NO_BK_PARENS) 395 .set(RE_NO_BK_REFS) 396 .set(RE_NO_BK_VBAR) 397 .set(RE_UNMATCHED_RIGHT_PAREN_ORD) 398 .makeFinal(); 399 400 /* There is no official Perl spec, but here's a "best guess" */ 401 402 RE_SYNTAX_PERL4 = new RESyntax() 403 .set(RE_BACKSLASH_ESCAPE_IN_LISTS) 404 .set(RE_CONTEXT_INDEP_ANCHORS) 405 .set(RE_CONTEXT_INDEP_OPS) // except for '{', apparently 406 .set(RE_INTERVALS) 407 .set(RE_NO_BK_BRACES) 408 .set(RE_NO_BK_PARENS) 409 .set(RE_NO_BK_VBAR) 410 .set(RE_NO_EMPTY_RANGES) 411 .set(RE_CHAR_CLASS_ESCAPES) // \d,\D,\w,\W,\s,\S 412 .makeFinal(); 413 414 RE_SYNTAX_PERL4_S = new RESyntax(RE_SYNTAX_PERL4) 415 .set(RE_DOT_NEWLINE) 416 .makeFinal(); 417 418 RE_SYNTAX_PERL5 = new RESyntax(RE_SYNTAX_PERL4) 419 .set(RE_PURE_GROUPING) // (?:) 420 .set(RE_STINGY_OPS) // *?,??,+?,{}? 421 .set(RE_LOOKAHEAD) // (?=)(?!) 422 .set(RE_STRING_ANCHORS) // \A,\Z 423 .set(RE_CHAR_CLASS_ESC_IN_LISTS)// \d,\D,\w,\W,\s,\S within [] 424 .set(RE_COMMENTS) // (?#) 425 .makeFinal(); 426 427 RE_SYNTAX_PERL5_S = new RESyntax(RE_SYNTAX_PERL5) 428 .set(RE_DOT_NEWLINE) 429 .makeFinal(); 430 431 RE_SYNTAX_JAVA_1_4 = new RESyntax(RE_SYNTAX_PERL5) 432 // XXX 433 .set(RE_POSSESSIVE_OPS) // *+,?+,++,{}+ 434 .makeFinal(); 435 } 436 437 /** 438 * Construct a new syntax object with all bits turned off. 439 * This is equivalent to RE_SYNTAX_EMACS. 440 */ RESyntax()441 public RESyntax() { 442 bits = new BitSet(BIT_TOTAL); 443 } 444 445 /** 446 * Called internally when constructing predefined syntaxes 447 * so their interpretation cannot vary. Conceivably useful 448 * for your syntaxes as well. Causes IllegalAccessError to 449 * be thrown if any attempt to modify the syntax is made. 450 * 451 * @return this object for convenient chaining 452 */ makeFinal()453 public RESyntax makeFinal() { 454 isFinal = true; 455 return this; 456 } 457 458 /** 459 * Construct a new syntax object with all bits set the same 460 * as the other syntax. 461 */ RESyntax(RESyntax other)462 public RESyntax(RESyntax other) { 463 bits = (BitSet) other.bits.clone(); 464 } 465 466 /** 467 * Check if a given bit is set in this syntax. 468 */ get(int index)469 public boolean get(int index) { 470 return bits.get(index); 471 } 472 473 /** 474 * Set a given bit in this syntax. 475 * 476 * @param index the constant (RESyntax.RE_xxx) bit to set. 477 * @return a reference to this object for easy chaining. 478 */ set(int index)479 public RESyntax set(int index) { 480 if (isFinal) throw new IllegalAccessError(SYNTAX_IS_FINAL); 481 bits.set(index); 482 return this; 483 } 484 485 /** 486 * Clear a given bit in this syntax. 487 * 488 * @param index the constant (RESyntax.RE_xxx) bit to clear. 489 * @return a reference to this object for easy chaining. 490 */ clear(int index)491 public RESyntax clear(int index) { 492 if (isFinal) throw new IllegalAccessError(SYNTAX_IS_FINAL); 493 bits.clear(index); 494 return this; 495 } 496 497 /** 498 * Changes the line separator string for regular expressions 499 * created using this RESyntax. The default separator is the 500 * value returned by the system property "line.separator", which 501 * should be correct when reading platform-specific files from a 502 * filesystem. However, many programs may collect input from 503 * sources where the line separator is differently specified (for 504 * example, in the applet environment, the text box widget 505 * interprets line breaks as single-character newlines, 506 * regardless of the host platform. 507 * 508 * Note that setting the line separator to a character or 509 * characters that have specific meaning within the current syntax 510 * can cause unexpected chronosynclastic infundibula. 511 * 512 * @return this object for convenient chaining 513 */ setLineSeparator(String aSeparator)514 public RESyntax setLineSeparator(String aSeparator) { 515 if (isFinal) throw new IllegalAccessError(SYNTAX_IS_FINAL); 516 lineSeparator = aSeparator; 517 return this; 518 } 519 520 /** 521 * Returns the currently active line separator string. The default 522 * is the platform-dependent system property "line.separator". 523 */ getLineSeparator()524 public String getLineSeparator() { 525 return lineSeparator; 526 } 527 } 528