| 1 |
nigel |
77 |
// Copyright (c) 2005, Google Inc. |
| 2 |
|
|
// All rights reserved. |
| 3 |
|
|
// |
| 4 |
|
|
// Redistribution and use in source and binary forms, with or without |
| 5 |
|
|
// modification, are permitted provided that the following conditions are |
| 6 |
|
|
// met: |
| 7 |
|
|
// |
| 8 |
|
|
// * Redistributions of source code must retain the above copyright |
| 9 |
|
|
// notice, this list of conditions and the following disclaimer. |
| 10 |
|
|
// * Redistributions in binary form must reproduce the above |
| 11 |
|
|
// copyright notice, this list of conditions and the following disclaimer |
| 12 |
|
|
// in the documentation and/or other materials provided with the |
| 13 |
|
|
// distribution. |
| 14 |
|
|
// * Neither the name of Google Inc. nor the names of its |
| 15 |
|
|
// contributors may be used to endorse or promote products derived from |
| 16 |
|
|
// this software without specific prior written permission. |
| 17 |
|
|
// |
| 18 |
|
|
// THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS |
| 19 |
|
|
// "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT |
| 20 |
|
|
// LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR |
| 21 |
|
|
// A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT |
| 22 |
|
|
// OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, |
| 23 |
|
|
// SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT |
| 24 |
|
|
// LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, |
| 25 |
|
|
// DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY |
| 26 |
|
|
// THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT |
| 27 |
|
|
// (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE |
| 28 |
|
|
// OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE. |
| 29 |
|
|
// |
| 30 |
|
|
// Author: Sanjay Ghemawat |
| 31 |
|
|
|
| 32 |
|
|
#include <vector> |
| 33 |
|
|
#include <assert.h> |
| 34 |
|
|
#include "config.h" |
| 35 |
|
|
#include "pcre_scanner.h" |
| 36 |
|
|
|
| 37 |
|
|
using std::vector; |
| 38 |
|
|
|
| 39 |
|
|
namespace pcrecpp { |
| 40 |
|
|
|
| 41 |
|
|
Scanner::Scanner() |
| 42 |
|
|
: data_(), |
| 43 |
|
|
input_(data_), |
| 44 |
|
|
skip_(NULL), |
| 45 |
|
|
should_skip_(false), |
| 46 |
|
|
save_comments_(false), |
| 47 |
|
|
comments_(NULL), |
| 48 |
|
|
comments_offset_(0) { |
| 49 |
|
|
} |
| 50 |
|
|
|
| 51 |
|
|
Scanner::Scanner(const string& in) |
| 52 |
|
|
: data_(in), |
| 53 |
|
|
input_(data_), |
| 54 |
|
|
skip_(NULL), |
| 55 |
|
|
should_skip_(false), |
| 56 |
|
|
save_comments_(false), |
| 57 |
|
|
comments_(NULL), |
| 58 |
|
|
comments_offset_(0) { |
| 59 |
|
|
} |
| 60 |
|
|
|
| 61 |
|
|
Scanner::~Scanner() { |
| 62 |
|
|
delete skip_; |
| 63 |
|
|
delete comments_; |
| 64 |
|
|
} |
| 65 |
|
|
|
| 66 |
|
|
void Scanner::Skip(const char* re) { |
| 67 |
|
|
delete skip_; |
| 68 |
|
|
if (re != NULL) { |
| 69 |
|
|
skip_ = new RE(re); |
| 70 |
|
|
should_skip_ = true; |
| 71 |
|
|
ConsumeSkip(); |
| 72 |
|
|
} else { |
| 73 |
|
|
skip_ = NULL; |
| 74 |
|
|
should_skip_ = false; |
| 75 |
|
|
} |
| 76 |
|
|
} |
| 77 |
|
|
|
| 78 |
|
|
void Scanner::DisableSkip() { |
| 79 |
|
|
assert(skip_ != NULL); |
| 80 |
|
|
should_skip_ = false; |
| 81 |
|
|
} |
| 82 |
|
|
|
| 83 |
|
|
void Scanner::EnableSkip() { |
| 84 |
|
|
assert(skip_ != NULL); |
| 85 |
|
|
should_skip_ = true; |
| 86 |
|
|
ConsumeSkip(); |
| 87 |
|
|
} |
| 88 |
|
|
|
| 89 |
|
|
int Scanner::LineNumber() const { |
| 90 |
|
|
// TODO: Make it more efficient by keeping track of the last point |
| 91 |
|
|
// where we computed line numbers and counting newlines since then. |
| 92 |
nigel |
87 |
// We could use std:count, but not all systems have it. :-( |
| 93 |
|
|
int count = 1; |
| 94 |
|
|
for (const char* p = data_.data(); p < input_.data(); ++p) |
| 95 |
|
|
if (*p == '\n') |
| 96 |
|
|
++count; |
| 97 |
|
|
return count; |
| 98 |
nigel |
77 |
} |
| 99 |
|
|
|
| 100 |
|
|
int Scanner::Offset() const { |
| 101 |
|
|
return input_.data() - data_.c_str(); |
| 102 |
|
|
} |
| 103 |
|
|
|
| 104 |
|
|
bool Scanner::LookingAt(const RE& re) const { |
| 105 |
|
|
int consumed; |
| 106 |
|
|
return re.DoMatch(input_, RE::ANCHOR_START, &consumed, 0, 0); |
| 107 |
|
|
} |
| 108 |
|
|
|
| 109 |
|
|
|
| 110 |
|
|
bool Scanner::Consume(const RE& re, |
| 111 |
|
|
const Arg& arg0, |
| 112 |
|
|
const Arg& arg1, |
| 113 |
|
|
const Arg& arg2) { |
| 114 |
|
|
const bool result = re.Consume(&input_, arg0, arg1, arg2); |
| 115 |
|
|
if (result && should_skip_) ConsumeSkip(); |
| 116 |
|
|
return result; |
| 117 |
|
|
} |
| 118 |
|
|
|
| 119 |
|
|
// helper function to consume *skip_ and honour save_comments_ |
| 120 |
|
|
void Scanner::ConsumeSkip() { |
| 121 |
|
|
if (save_comments_) { |
| 122 |
|
|
if (NULL == comments_) { |
| 123 |
|
|
comments_ = new vector<StringPiece>; |
| 124 |
|
|
} |
| 125 |
|
|
const char *start_data = input_.data(); |
| 126 |
|
|
skip_->Consume(&input_); |
| 127 |
|
|
// already pointing one past end, so no need to +1 |
| 128 |
|
|
int length = input_.data() - start_data; |
| 129 |
|
|
if (length > 0) { |
| 130 |
|
|
comments_->push_back(StringPiece(start_data, length)); |
| 131 |
|
|
} |
| 132 |
|
|
} else { |
| 133 |
|
|
skip_->Consume(&input_); |
| 134 |
|
|
} |
| 135 |
|
|
} |
| 136 |
|
|
|
| 137 |
|
|
|
| 138 |
|
|
void Scanner::GetComments(int start, int end, vector<StringPiece> *ranges) { |
| 139 |
|
|
// short circuit out if we've not yet initialized comments_ |
| 140 |
|
|
// (e.g., when save_comments is false) |
| 141 |
|
|
if (!comments_) { |
| 142 |
|
|
return; |
| 143 |
|
|
} |
| 144 |
|
|
// TODO: if we guarantee that comments_ will contain StringPieces |
| 145 |
|
|
// that are ordered by their start, then we can do a binary search |
| 146 |
|
|
// for the first StringPiece at or past start and then scan for the |
| 147 |
|
|
// ones contained in the range, quit early (use equal_range or |
| 148 |
|
|
// lower_bound) |
| 149 |
|
|
for (vector<StringPiece>::const_iterator it = comments_->begin(); |
| 150 |
|
|
it != comments_->end(); ++it) { |
| 151 |
|
|
if ((it->data() >= data_.c_str() + start && |
| 152 |
|
|
it->data() + it->size() <= data_.c_str() + end)) { |
| 153 |
|
|
ranges->push_back(*it); |
| 154 |
|
|
} |
| 155 |
|
|
} |
| 156 |
|
|
} |
| 157 |
|
|
|
| 158 |
|
|
|
| 159 |
|
|
void Scanner::GetNextComments(vector<StringPiece> *ranges) { |
| 160 |
|
|
// short circuit out if we've not yet initialized comments_ |
| 161 |
|
|
// (e.g., when save_comments is false) |
| 162 |
|
|
if (!comments_) { |
| 163 |
|
|
return; |
| 164 |
|
|
} |
| 165 |
|
|
for (vector<StringPiece>::const_iterator it = |
| 166 |
|
|
comments_->begin() + comments_offset_; |
| 167 |
|
|
it != comments_->end(); ++it) { |
| 168 |
|
|
ranges->push_back(*it); |
| 169 |
|
|
++comments_offset_; |
| 170 |
|
|
} |
| 171 |
|
|
} |
| 172 |
|
|
|
| 173 |
|
|
} // namespace pcrecpp |