DXR is a code search and navigation tool aimed at making sense of large projects. It supports full-text and regex searches as well as structural queries.

Mercurial (fbecf6c8a86f)

VCS Links

Line Code
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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786
// Copyright (c) 2005, Google Inc.
// All rights reserved.
//
// Redistribution and use in source and binary forms, with or without
// modification, are permitted provided that the following conditions are
// met:
//
//     * Redistributions of source code must retain the above copyright
// notice, this list of conditions and the following disclaimer.
//     * Redistributions in binary form must reproduce the above
// copyright notice, this list of conditions and the following disclaimer
// in the documentation and/or other materials provided with the
// distribution.
//     * Neither the name of Google Inc. nor the names of its
// contributors may be used to endorse or promote products derived from
// this software without specific prior written permission.
//
// THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS
// "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
// LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR
// A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT
// OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL,
// SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT
// LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE,
// DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY
// THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
// (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
// OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
//
// Author: Sanjay Ghemawat
// Support for PCRE_XXX modifiers added by Giuseppe Maxia, July 2005

#ifndef _PCRE_REGEXP_H
#define _PCRE_REGEXP_H

// C++ interface to the pcre regular-expression library.  RE supports
// Perl-style regular expressions (with extensions like \d, \w, \s,
// ...).
//
// -----------------------------------------------------------------------
// REGEXP SYNTAX:
//
// This module is part of the pcre library and hence supports its syntax
// for regular expressions.
//
// The syntax is pretty similar to Perl's.  For those not familiar
// with Perl's regular expressions, here are some examples of the most
// commonly used extensions:
//
//   "hello (\\w+) world"  -- \w matches a "word" character
//   "version (\\d+)"      -- \d matches a digit
//   "hello\\s+world"      -- \s matches any whitespace character
//   "\\b(\\w+)\\b"        -- \b matches empty string at a word boundary
//   "(?i)hello"           -- (?i) turns on case-insensitive matching
//   "/\\*(.*?)\\*/"       -- .*? matches . minimum no. of times possible
//
// -----------------------------------------------------------------------
// MATCHING INTERFACE:
//
// The "FullMatch" operation checks that supplied text matches a
// supplied pattern exactly.
//
// Example: successful match
//    pcrecpp::RE re("h.*o");
//    re.FullMatch("hello");
//
// Example: unsuccessful match (requires full match):
//    pcrecpp::RE re("e");
//    !re.FullMatch("hello");
//
// Example: creating a temporary RE object:
//    pcrecpp::RE("h.*o").FullMatch("hello");
//
// You can pass in a "const char*" or a "string" for "text".  The
// examples below tend to use a const char*.
//
// You can, as in the different examples above, store the RE object
// explicitly in a variable or use a temporary RE object.  The
// examples below use one mode or the other arbitrarily.  Either
// could correctly be used for any of these examples.
//
// -----------------------------------------------------------------------
// MATCHING WITH SUB-STRING EXTRACTION:
//
// You can supply extra pointer arguments to extract matched subpieces.
//
// Example: extracts "ruby" into "s" and 1234 into "i"
//    int i;
//    string s;
//    pcrecpp::RE re("(\\w+):(\\d+)");
//    re.FullMatch("ruby:1234", &s, &i);
//
// Example: does not try to extract any extra sub-patterns
//    re.FullMatch("ruby:1234", &s);
//
// Example: does not try to extract into NULL
//    re.FullMatch("ruby:1234", NULL, &i);
//
// Example: integer overflow causes failure
//    !re.FullMatch("ruby:1234567891234", NULL, &i);
//
// Example: fails because there aren't enough sub-patterns:
//    !pcrecpp::RE("\\w+:\\d+").FullMatch("ruby:1234", &s);
//
// Example: fails because string cannot be stored in integer
//    !pcrecpp::RE("(.*)").FullMatch("ruby", &i);
//
// The provided pointer arguments can be pointers to any scalar numeric
// type, or one of
//    string        (matched piece is copied to string)
//    StringPiece   (StringPiece is mutated to point to matched piece)
//    T             (where "bool T::ParseFrom(const char*, int)" exists)
//    NULL          (the corresponding matched sub-pattern is not copied)
//
// -----------------------------------------------------------------------
// DO_MATCH
//
// The matching interface supports at most 16 arguments per call.
// If you need more, consider using the more general interface
// pcrecpp::RE::DoMatch().  See pcrecpp.h for the signature for DoMatch.
//
// -----------------------------------------------------------------------
// PARTIAL MATCHES
//
// You can use the "PartialMatch" operation when you want the pattern
// to match any substring of the text.
//
// Example: simple search for a string:
//    pcrecpp::RE("ell").PartialMatch("hello");
//
// Example: find first number in a string:
//    int number;
//    pcrecpp::RE re("(\\d+)");
//    re.PartialMatch("x*100 + 20", &number);
//    assert(number == 100);
//
// -----------------------------------------------------------------------
// UTF-8 AND THE MATCHING INTERFACE:
//
// By default, pattern and text are plain text, one byte per character.
// The UTF8 flag, passed to the constructor, causes both pattern
// and string to be treated as UTF-8 text, still a byte stream but
// potentially multiple bytes per character. In practice, the text
// is likelier to be UTF-8 than the pattern, but the match returned
// may depend on the UTF8 flag, so always use it when matching
// UTF8 text.  E.g., "." will match one byte normally but with UTF8
// set may match up to three bytes of a multi-byte character.
//
// Example:
//    pcrecpp::RE_Options options;
//    options.set_utf8();
//    pcrecpp::RE re(utf8_pattern, options);
//    re.FullMatch(utf8_string);
//
// Example: using the convenience function UTF8():
//    pcrecpp::RE re(utf8_pattern, pcrecpp::UTF8());
//    re.FullMatch(utf8_string);
//
// NOTE: The UTF8 option is ignored if pcre was not configured with the
//       --enable-utf8 flag.
//
// -----------------------------------------------------------------------
// PASSING MODIFIERS TO THE REGULAR EXPRESSION ENGINE
//
// PCRE defines some modifiers to change the behavior of the regular
// expression engine.
// The C++ wrapper defines an auxiliary class, RE_Options, as a vehicle
// to pass such modifiers to a RE class.
//
// Currently, the following modifiers are supported
//
//    modifier              description               Perl corresponding
//
//    PCRE_CASELESS         case insensitive match    /i
//    PCRE_MULTILINE        multiple lines match      /m
//    PCRE_DOTALL           dot matches newlines      /s
//    PCRE_DOLLAR_ENDONLY   $ matches only at end     N/A
//    PCRE_EXTRA            strict escape parsing     N/A
//    PCRE_EXTENDED         ignore whitespaces        /x
//    PCRE_UTF8             handles UTF8 chars        built-in
//    PCRE_UNGREEDY         reverses * and *?         N/A
//    PCRE_NO_AUTO_CAPTURE  disables matching parens  N/A (*)
//
// (For a full account on how each modifier works, please check the
// PCRE API reference manual).
//
// (*) Both Perl and PCRE allow non matching parentheses by means of the
// "?:" modifier within the pattern itself. e.g. (?:ab|cd) does not
// capture, while (ab|cd) does.
//
// For each modifier, there are two member functions whose name is made
// out of the modifier in lowercase, without the "PCRE_" prefix. For
// instance, PCRE_CASELESS is handled by
//    bool caseless(),
// which returns true if the modifier is set, and
//    RE_Options & set_caseless(bool),
// which sets or unsets the modifier.
//
// Moreover, PCRE_CONFIG_MATCH_LIMIT can be accessed through the
// set_match_limit() and match_limit() member functions.
// Setting match_limit to a non-zero value will limit the executation of
// pcre to keep it from doing bad things like blowing the stack or taking
// an eternity to return a result.  A value of 5000 is good enough to stop
// stack blowup in a 2MB thread stack.  Setting match_limit to zero will
// disable match limiting.
//
// Normally, to pass one or more modifiers to a RE class, you declare
// a RE_Options object, set the appropriate options, and pass this
// object to a RE constructor. Example:
//
//    RE_options opt;
//    opt.set_caseless(true);
//
//    if (RE("HELLO", opt).PartialMatch("hello world")) ...
//
// RE_options has two constructors. The default constructor takes no
// arguments and creates a set of flags that are off by default.
//
// The optional parameter 'option_flags' is to facilitate transfer
// of legacy code from C programs.  This lets you do
//    RE(pattern, RE_Options(PCRE_CASELESS|PCRE_MULTILINE)).PartialMatch(str);
//
// But new code is better off doing
//    RE(pattern,
//      RE_Options().set_caseless(true).set_multiline(true)).PartialMatch(str);
// (See below)
//
// If you are going to pass one of the most used modifiers, there are some
// convenience functions that return a RE_Options class with the
// appropriate modifier already set:
// CASELESS(), UTF8(), MULTILINE(), DOTALL(), EXTENDED()
//
// If you need to set several options at once, and you don't want to go
// through the pains of declaring a RE_Options object and setting several
// options, there is a parallel method that give you such ability on the
// fly. You can concatenate several set_xxxxx member functions, since each
// of them returns a reference to its class object.  e.g.: to pass
// PCRE_CASELESS, PCRE_EXTENDED, and PCRE_MULTILINE to a RE with one
// statement, you may write
//
//    RE(" ^ xyz \\s+ .* blah$", RE_Options()
//                            .set_caseless(true)
//                            .set_extended(true)
//                            .set_multiline(true)).PartialMatch(sometext);
//
// -----------------------------------------------------------------------
// SCANNING TEXT INCREMENTALLY
//
// The "Consume" operation may be useful if you want to repeatedly
// match regular expressions at the front of a string and skip over
// them as they match.  This requires use of the "StringPiece" type,
// which represents a sub-range of a real string.  Like RE, StringPiece
// is defined in the pcrecpp namespace.
//
// Example: read lines of the form "var = value" from a string.
//    string contents = ...;                 // Fill string somehow
//    pcrecpp::StringPiece input(contents);  // Wrap in a StringPiece
//
//    string var;
//    int value;
//    pcrecpp::RE re("(\\w+) = (\\d+)\n");
//    while (re.Consume(&input, &var, &value)) {
//      ...;
//    }
//
// Each successful call to "Consume" will set "var/value", and also
// advance "input" so it points past the matched text.
//
// The "FindAndConsume" operation is similar to "Consume" but does not
// anchor your match at the beginning of the string.  For example, you
// could extract all words from a string by repeatedly calling
//     pcrecpp::RE("(\\w+)").FindAndConsume(&input, &word)
//
// -----------------------------------------------------------------------
// PARSING HEX/OCTAL/C-RADIX NUMBERS
//
// By default, if you pass a pointer to a numeric value, the
// corresponding text is interpreted as a base-10 number.  You can
// instead wrap the pointer with a call to one of the operators Hex(),
// Octal(), or CRadix() to interpret the text in another base.  The
// CRadix operator interprets C-style "0" (base-8) and "0x" (base-16)
// prefixes, but defaults to base-10.
//
// Example:
//   int a, b, c, d;
//   pcrecpp::RE re("(.*) (.*) (.*) (.*)");
//   re.FullMatch("100 40 0100 0x40",
//                pcrecpp::Octal(&a), pcrecpp::Hex(&b),
//                pcrecpp::CRadix(&c), pcrecpp::CRadix(&d));
// will leave 64 in a, b, c, and d.
//
// -----------------------------------------------------------------------
// REPLACING PARTS OF STRINGS
//
// You can replace the first match of "pattern" in "str" with
// "rewrite".  Within "rewrite", backslash-escaped digits (\1 to \9)
// can be used to insert text matching corresponding parenthesized
// group from the pattern.  \0 in "rewrite" refers to the entire
// matching text.  E.g.,
//
//   string s = "yabba dabba doo";
//   pcrecpp::RE("b+").Replace("d", &s);
//
// will leave "s" containing "yada dabba doo".  The result is true if
// the pattern matches and a replacement occurs, or false otherwise.
//
// GlobalReplace() is like Replace(), except that it replaces all
// occurrences of the pattern in the string with the rewrite.
// Replacements are not subject to re-matching.  E.g.,
//
//   string s = "yabba dabba doo";
//   pcrecpp::RE("b+").GlobalReplace("d", &s);
//
// will leave "s" containing "yada dada doo".  It returns the number
// of replacements made.
//
// Extract() is like Replace(), except that if the pattern matches,
// "rewrite" is copied into "out" (an additional argument) with
// substitutions.  The non-matching portions of "text" are ignored.
// Returns true iff a match occurred and the extraction happened
// successfully.  If no match occurs, the string is left unaffected.


#include <string>
// These aren't technically needed here, but we include them
// anyway so folks who include pcrecpp.h don't have to include
// all these other header files as well.
#include <pcre.h>
#include <pcre_stringpiece.h>

namespace pcrecpp {

#define PCRE_SET_OR_CLEAR(b, o) \
    if (b) all_options_ |= (o); else all_options_ &= ~(o); \
    return *this

#define PCRE_IS_SET(o)  \
        (all_options_ & o) == o

// We convert user-passed pointers into special Arg objects
class Arg;
extern Arg no_arg;

/***** Compiling regular expressions: the RE class *****/

// RE_Options allow you to set options to be passed along to pcre,
// along with other options we put on top of pcre.
// Only 9 modifiers, plus match_limit are supported now.
class RE_Options {
 public:
  // constructor
  RE_Options() : match_limit_(0), all_options_(0) {}

  // alternative constructor.
  // To facilitate transfer of legacy code from C programs
  //
  // This lets you do
  //    RE(pattern, RE_Options(PCRE_CASELESS|PCRE_MULTILINE)).PartialMatch(str);
  // But new code is better off doing
  //    RE(pattern,
  //      RE_Options().set_caseless(true).set_multiline(true)).PartialMatch(str);
  RE_Options(int option_flags) : match_limit_(0), all_options_ (option_flags) {}
  // we're fine with the default destructor, copy constructor, etc.

  // accessors and mutators
  int match_limit() const { return match_limit_; };
  RE_Options &set_match_limit(int limit) {
    match_limit_ = limit;
    return *this;
  }

  bool caseless() const {
    return PCRE_IS_SET(PCRE_CASELESS);
  }
  RE_Options &set_caseless(bool x) {
    PCRE_SET_OR_CLEAR(x, PCRE_CASELESS);
  }

  bool multiline() const {
    return PCRE_IS_SET(PCRE_MULTILINE);
  }
  RE_Options &set_multiline(bool x) {
    PCRE_SET_OR_CLEAR(x, PCRE_MULTILINE);
  }

  bool dotall() const {
    return PCRE_IS_SET(PCRE_DOTALL);
  }
  RE_Options &set_dotall(bool x) {
    PCRE_SET_OR_CLEAR(x,PCRE_DOTALL);
  }

  bool extended() const {
    return PCRE_IS_SET(PCRE_EXTENDED);
  }
  RE_Options &set_extended(bool x) {
    PCRE_SET_OR_CLEAR(x,PCRE_EXTENDED);
  }

  bool dollar_endonly() const {
    return PCRE_IS_SET(PCRE_DOLLAR_ENDONLY);
  }
  RE_Options &set_dollar_endonly(bool x) {
    PCRE_SET_OR_CLEAR(x,PCRE_DOLLAR_ENDONLY);
  }

  bool extra() const {
    return PCRE_IS_SET( PCRE_EXTRA);
  }
  RE_Options &set_extra(bool x) {
    PCRE_SET_OR_CLEAR(x, PCRE_EXTRA);
  }

  bool ungreedy() const {
    return PCRE_IS_SET(PCRE_UNGREEDY);
  }
  RE_Options &set_ungreedy(bool x) {
    PCRE_SET_OR_CLEAR(x, PCRE_UNGREEDY);
  }

  bool utf8() const {
    return PCRE_IS_SET(PCRE_UTF8);
  }
  RE_Options &set_utf8(bool x) {
    PCRE_SET_OR_CLEAR(x, PCRE_UTF8);
  }

  bool no_auto_capture() const {
    return PCRE_IS_SET(PCRE_NO_AUTO_CAPTURE);
  }
  RE_Options &set_no_auto_capture(bool x) {
    PCRE_SET_OR_CLEAR(x, PCRE_NO_AUTO_CAPTURE);
  }

  RE_Options &set_all_options(int opt) {
    all_options_ = opt;
    return *this;
  }
  int all_options() const {
    return all_options_ ;
  }

  // TODO: add other pcre flags

 private:
  int match_limit_;
  int all_options_;
};

// These functions return some common RE_Options
static inline RE_Options UTF8() {
  return RE_Options().set_utf8(true);
}

static inline RE_Options CASELESS() {
  return RE_Options().set_caseless(true);
}
static inline RE_Options MULTILINE() {
  return RE_Options().set_multiline(true);
}

static inline RE_Options DOTALL() {
  return RE_Options().set_dotall(true);
}

static inline RE_Options EXTENDED() {
  return RE_Options().set_extended(true);
}

// Interface for regular expression matching.  Also corresponds to a
// pre-compiled regular expression.  An "RE" object is safe for
// concurrent use by multiple threads.
class RE {
 public:
  // We provide implicit conversions from strings so that users can
  // pass in a string or a "const char*" wherever an "RE" is expected.
  RE(const char* pat) { Init(pat, NULL); }
  RE(const char *pat, const RE_Options& option) { Init(pat, &option); }
  RE(const string& pat) { Init(pat.c_str(), NULL); }
  RE(const string& pat, const RE_Options& option) { Init(pat.c_str(), &option); }

  ~RE();

  // The string specification for this RE.  E.g.
  //   RE re("ab*c?d+");
  //   re.pattern();    // "ab*c?d+"
  const string& pattern() const { return pattern_; }

  // If RE could not be created properly, returns an error string.
  // Else returns the empty string.
  const string& error() const { return *error_; }

  /***** The useful part: the matching interface *****/

  // This is provided so one can do pattern.ReplaceAll() just as
  // easily as ReplaceAll(pattern-text, ....)

  bool FullMatch(const StringPiece& text,
                 const Arg& ptr1 = no_arg,
                 const Arg& ptr2 = no_arg,
                 const Arg& ptr3 = no_arg,
                 const Arg& ptr4 = no_arg,
                 const Arg& ptr5 = no_arg,
                 const Arg& ptr6 = no_arg,
                 const Arg& ptr7 = no_arg,
                 const Arg& ptr8 = no_arg,
                 const Arg& ptr9 = no_arg,
                 const Arg& ptr10 = no_arg,
                 const Arg& ptr11 = no_arg,
                 const Arg& ptr12 = no_arg,
                 const Arg& ptr13 = no_arg,
                 const Arg& ptr14 = no_arg,
                 const Arg& ptr15 = no_arg,
                 const Arg& ptr16 = no_arg) const;

  bool PartialMatch(const StringPiece& text,
                    const Arg& ptr1 = no_arg,
                    const Arg& ptr2 = no_arg,
                    const Arg& ptr3 = no_arg,
                    const Arg& ptr4 = no_arg,
                    const Arg& ptr5 = no_arg,
                    const Arg& ptr6 = no_arg,
                    const Arg& ptr7 = no_arg,
                    const Arg& ptr8 = no_arg,
                    const Arg& ptr9 = no_arg,
                    const Arg& ptr10 = no_arg,
                    const Arg& ptr11 = no_arg,
                    const Arg& ptr12 = no_arg,
                    const Arg& ptr13 = no_arg,
                    const Arg& ptr14 = no_arg,
                    const Arg& ptr15 = no_arg,
                    const Arg& ptr16 = no_arg) const;

  bool Consume(StringPiece* input,
               const Arg& ptr1 = no_arg,
               const Arg& ptr2 = no_arg,
               const Arg& ptr3 = no_arg,
               const Arg& ptr4 = no_arg,
               const Arg& ptr5 = no_arg,
               const Arg& ptr6 = no_arg,
               const Arg& ptr7 = no_arg,
               const Arg& ptr8 = no_arg,
               const Arg& ptr9 = no_arg,
               const Arg& ptr10 = no_arg,
               const Arg& ptr11 = no_arg,
               const Arg& ptr12 = no_arg,
               const Arg& ptr13 = no_arg,
               const Arg& ptr14 = no_arg,
               const Arg& ptr15 = no_arg,
               const Arg& ptr16 = no_arg) const;

  bool FindAndConsume(StringPiece* input,
                      const Arg& ptr1 = no_arg,
                      const Arg& ptr2 = no_arg,
                      const Arg& ptr3 = no_arg,
                      const Arg& ptr4 = no_arg,
                      const Arg& ptr5 = no_arg,
                      const Arg& ptr6 = no_arg,
                      const Arg& ptr7 = no_arg,
                      const Arg& ptr8 = no_arg,
                      const Arg& ptr9 = no_arg,
                      const Arg& ptr10 = no_arg,
                      const Arg& ptr11 = no_arg,
                      const Arg& ptr12 = no_arg,
                      const Arg& ptr13 = no_arg,
                      const Arg& ptr14 = no_arg,
                      const Arg& ptr15 = no_arg,
                      const Arg& ptr16 = no_arg) const;

  bool Replace(const StringPiece& rewrite,
               string *str) const;

  int GlobalReplace(const StringPiece& rewrite,
                    string *str) const;

  bool Extract(const StringPiece &rewrite,
               const StringPiece &text,
               string *out) const;

  /***** Generic matching interface *****/

  // Type of match (TODO: Should be restructured as part of RE_Options)
  enum Anchor {
    UNANCHORED,         // No anchoring
    ANCHOR_START,       // Anchor at start only
    ANCHOR_BOTH         // Anchor at start and end
  };

  // General matching routine.  Stores the length of the match in
  // "*consumed" if successful.
  bool DoMatch(const StringPiece& text,
               Anchor anchor,
               int* consumed,
               const Arg* const* args, int n) const;

  // Return the number of capturing subpatterns, or -1 if the
  // regexp wasn't valid on construction.
  int NumberOfCapturingGroups();

 private:

  void Init(const char* pattern, const RE_Options* options);

  // Match against "text", filling in "vec" (up to "vecsize" * 2/3) with
  // pairs of integers for the beginning and end positions of matched
  // text.  The first pair corresponds to the entire matched text;
  // subsequent pairs correspond, in order, to parentheses-captured
  // matches.  Returns the number of pairs (one more than the number of
  // the last subpattern with a match) if matching was successful
  // and zero if the match failed.
  // I.e. for RE("(foo)|(bar)|(baz)") it will return 2, 3, and 4 when matching
  // against "foo", "bar", and "baz" respectively.
  // When matching RE("(foo)|hello") against "hello", it will return 1.
  // But the values for all subpattern are filled in into "vec".
  int TryMatch(const StringPiece& text,
               int startpos,
               Anchor anchor,
               int *vec,
               int vecsize) const;

  // Append the "rewrite" string, with backslash subsitutions from "text"
  // and "vec", to string "out".
  bool Rewrite(string *out,
               const StringPiece& rewrite,
               const StringPiece& text,
               int *vec,
               int veclen) const;

  // internal implementation for DoMatch
  bool DoMatchImpl(const StringPiece& text,
                   Anchor anchor,
                   int* consumed,
                   const Arg* const args[],
                   int n,
                   int* vec,
                   int vecsize) const;

  // Compile the regexp for the specified anchoring mode
  pcre* Compile(Anchor anchor);

  string        pattern_;
  RE_Options    options_;
  pcre*         re_full_;       // For full matches
  pcre*         re_partial_;    // For partial matches
  const string* error_;         // Error indicator (or points to empty string)
  int           match_limit_;   // limit on execution resources

  // Don't allow the default copy or assignment constructors --
  // they're expensive and too easy to do by accident.
  RE(const RE&);
  void operator=(const RE&);
};


/***** Implementation details *****/

// Hex/Octal/Binary?

// Special class for parsing into objects that define a ParseFrom() method
template <class T>
class _RE_MatchObject {
 public:
  static inline bool Parse(const char* str, int n, void* dest) {
    T* object = reinterpret_cast<T*>(dest);
    return object->ParseFrom(str, n);
  }
};

class Arg {
 public:
  // Empty constructor so we can declare arrays of Arg
  Arg();

  // Constructor specially designed for NULL arguments
  Arg(void*);

  typedef bool (*Parser)(const char* str, int n, void* dest);

// Type-specific parsers
#define PCRE_MAKE_PARSER(type,name)                             \
  Arg(type* p) : arg_(p), parser_(name) { }                     \
  Arg(type* p, Parser parser) : arg_(p), parser_(parser) { }


  PCRE_MAKE_PARSER(char,               parse_char);
  PCRE_MAKE_PARSER(unsigned char,      parse_uchar);
  PCRE_MAKE_PARSER(short,              parse_short);
  PCRE_MAKE_PARSER(unsigned short,     parse_ushort);
  PCRE_MAKE_PARSER(int,                parse_int);
  PCRE_MAKE_PARSER(unsigned int,       parse_uint);
  PCRE_MAKE_PARSER(long,               parse_long);
  PCRE_MAKE_PARSER(unsigned long,      parse_ulong);
#if @pcre_have_long_long@
  PCRE_MAKE_PARSER(long long,          parse_longlong);
#endif
#if @pcre_have_ulong_long@
  PCRE_MAKE_PARSER(unsigned long long, parse_ulonglong);
#endif
  PCRE_MAKE_PARSER(float,              parse_float);
  PCRE_MAKE_PARSER(double,             parse_double);
  PCRE_MAKE_PARSER(string,             parse_string);
  PCRE_MAKE_PARSER(StringPiece,        parse_stringpiece);

#undef PCRE_MAKE_PARSER

  // Generic constructor
  template <class T> Arg(T*, Parser parser);
  // Generic constructor template
  template <class T> Arg(T* p)
    : arg_(p), parser_(_RE_MatchObject<T>::Parse) {
  }

  // Parse the data
  bool Parse(const char* str, int n) const;

 private:
  void*         arg_;
  Parser        parser_;

  static bool parse_null          (const char* str, int n, void* dest);
  static bool parse_char          (const char* str, int n, void* dest);
  static bool parse_uchar         (const char* str, int n, void* dest);
  static bool parse_float         (const char* str, int n, void* dest);
  static bool parse_double        (const char* str, int n, void* dest);
  static bool parse_string        (const char* str, int n, void* dest);
  static bool parse_stringpiece   (const char* str, int n, void* dest);

#define PCRE_DECLARE_INTEGER_PARSER(name)                                   \
 private:                                                                   \
  static bool parse_ ## name(const char* str, int n, void* dest);           \
  static bool parse_ ## name ## _radix(                                     \
    const char* str, int n, void* dest, int radix);                         \
 public:                                                                    \
  static bool parse_ ## name ## _hex(const char* str, int n, void* dest);   \
  static bool parse_ ## name ## _octal(const char* str, int n, void* dest); \
  static bool parse_ ## name ## _cradix(const char* str, int n, void* dest)

  PCRE_DECLARE_INTEGER_PARSER(short);
  PCRE_DECLARE_INTEGER_PARSER(ushort);
  PCRE_DECLARE_INTEGER_PARSER(int);
  PCRE_DECLARE_INTEGER_PARSER(uint);
  PCRE_DECLARE_INTEGER_PARSER(long);
  PCRE_DECLARE_INTEGER_PARSER(ulong);
  PCRE_DECLARE_INTEGER_PARSER(longlong);
  PCRE_DECLARE_INTEGER_PARSER(ulonglong);

#undef PCRE_DECLARE_INTEGER_PARSER
};

inline Arg::Arg() : arg_(NULL), parser_(parse_null) { }
inline Arg::Arg(void* p) : arg_(p), parser_(parse_null) { }

inline bool Arg::Parse(const char* str, int n) const {
  return (*parser_)(str, n, arg_);
}

// This part of the parser, appropriate only for ints, deals with bases
#define MAKE_INTEGER_PARSER(type, name) \
  inline Arg Hex(type* ptr) { \
    return Arg(ptr, Arg::parse_ ## name ## _hex); } \
  inline Arg Octal(type* ptr) { \
    return Arg(ptr, Arg::parse_ ## name ## _octal); } \
  inline Arg CRadix(type* ptr) { \
    return Arg(ptr, Arg::parse_ ## name ## _cradix); }

MAKE_INTEGER_PARSER(short,              short);
MAKE_INTEGER_PARSER(unsigned short,     ushort);
MAKE_INTEGER_PARSER(int,                int);
MAKE_INTEGER_PARSER(unsigned int,       uint);
MAKE_INTEGER_PARSER(long,               long);
MAKE_INTEGER_PARSER(unsigned long,      ulong);
#if @pcre_have_long_long@
MAKE_INTEGER_PARSER(long long,          longlong);
#endif
#if @pcre_have_ulong_long@
MAKE_INTEGER_PARSER(unsigned long long, ulonglong);
#endif

#undef PCRE_IS_SET
#undef PCRE_SET_OR_CLEAR
#undef MAKE_INTEGER_PARSER

}   // namespace pcrecpp


#endif /* _PCRE_REGEXP_H */