mimics_pcre.cc | Explore in Territory

// Copyright 2008 The RE2 Authors.  All Rights Reserved.
// Use of this source code is governed by a BSD-style
// license that can be found in the LICENSE file.

// Determine whether this library should match PCRE exactly
// for a particular Regexp.  (If so, the testing framework can
// check that it does.)
//
// This library matches PCRE except in these cases:
//   * the regexp contains a repetition of an empty string,
//     like (a*)* or (a*)+.  In this case, PCRE will treat
//     the repetition sequence as ending with an empty string,
//     while this library does not.
//   * Perl and PCRE differ on whether \v matches \n.
//     For historical reasons, this library implements the Perl behavior.
//   * Perl and PCRE allow $ in one-line mode to match either the very
//     end of the text or just before a \n at the end of the text.
//     This library requires it to match only the end of the text.
//   * Similarly, Perl and PCRE do not allow ^ in multi-line mode to
//     match the end of the text if the last character is a \n.
//     This library does allow it.
//
// Regexp::MimicsPCRE checks for any of these conditions.

#include "absl/log/absl_log.h"
#include "re2/regexp.h"
#include "re2/walker-inl.h"

namespace re2 {

// Returns whether re might match an empty string.
static bool CanBeEmptyString(Regexp *re);

// Walker class to compute whether library handles a regexp
// exactly as PCRE would.  See comment at top for conditions.

class PCREWalker : public Regexp::Walker<bool> { … };

// Called after visiting each of re's children and accumulating
// the return values in child_args.  So child_args contains whether
// this library mimics PCRE for those subexpressions.
bool PCREWalker::PostVisit(Regexp* re, bool parent_arg, bool pre_arg,
                           bool* child_args, int nchild_args) { … }

// Returns whether this regexp's behavior will mimic PCRE's exactly.
bool Regexp::MimicsPCRE() { … }


// Walker class to compute whether a Regexp can match an empty string.
// It is okay to overestimate.  For example, \b\B cannot match an empty
// string, because \b and \B are mutually exclusive, but this isn't
// that smart and will say it can.  Spurious empty strings
// will reduce the number of regexps we sanity check against PCRE,
// but they won't break anything.

class EmptyStringWalker : public Regexp::Walker<bool> { … };

// Called after visiting re's children.  child_args contains the return
// value from each of the children's PostVisits (i.e., whether each child
// can match an empty string).  Returns whether this clause can match an
// empty string.
bool EmptyStringWalker::PostVisit(Regexp* re, bool parent_arg, bool pre_arg,
                                  bool* child_args, int nchild_args) { … }

// Returns whether re can match an empty string.
static bool CanBeEmptyString(Regexp* re) { … }

}  // namespace re2
chromium/third_party/re2/src/re2/mimics_pcre.cc
