1 // 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 35 #include "pcrecpp_internal.h" 36 #include "pcre_scanner.h" 37 38 using std::vector; 39 40 namespace pcrecpp { 41 42 Scanner::Scanner() 43 : data_(), 44 input_(data_), 45 skip_(NULL), 46 should_skip_(false), 47 skip_repeat_(false), 48 save_comments_(false), 49 comments_(NULL), 50 comments_offset_(0) { 51 } 52 53 Scanner::Scanner(const string& in) 54 : data_(in), 55 input_(data_), 56 skip_(NULL), 57 should_skip_(false), 58 skip_repeat_(false), 59 save_comments_(false), 60 comments_(NULL), 61 comments_offset_(0) { 62 } 63 64 Scanner::~Scanner() { 65 delete skip_; 66 delete comments_; 67 } 68 69 void Scanner::SetSkipExpression(const char* re) { 70 delete skip_; 71 if (re != NULL) { 72 skip_ = new RE(re); 73 should_skip_ = true; 74 skip_repeat_ = true; 75 ConsumeSkip(); 76 } else { 77 skip_ = NULL; 78 should_skip_ = false; 79 skip_repeat_ = false; 80 } 81 } 82 83 void Scanner::Skip(const char* re) { 84 delete skip_; 85 if (re != NULL) { 86 skip_ = new RE(re); 87 should_skip_ = true; 88 skip_repeat_ = false; 89 ConsumeSkip(); 90 } else { 91 skip_ = NULL; 92 should_skip_ = false; 93 skip_repeat_ = false; 94 } 95 } 96 97 void Scanner::DisableSkip() { 98 assert(skip_ != NULL); 99 should_skip_ = false; 100 } 101 102 void Scanner::EnableSkip() { 103 assert(skip_ != NULL); 104 should_skip_ = true; 105 ConsumeSkip(); 106 } 107 108 int Scanner::LineNumber() const { 109 // TODO: Make it more efficient by keeping track of the last point 110 // where we computed line numbers and counting newlines since then. 111 // We could use std:count, but not all systems have it. :-( 112 int count = 1; 113 for (const char* p = data_.data(); p < input_.data(); ++p) 114 if (*p == '\n') 115 ++count; 116 return count; 117 } 118 119 int Scanner::Offset() const { 120 return (int)(input_.data() - data_.c_str()); 121 } 122 123 bool Scanner::LookingAt(const RE& re) const { 124 int consumed; 125 return re.DoMatch(input_, RE::ANCHOR_START, &consumed, 0, 0); 126 } 127 128 129 // helper function to consume *skip_ and honour save_comments_ 130 void Scanner::ConsumeSkip() { 131 const char* start_data = input_.data(); 132 while (skip_->Consume(&input_)) { 133 if (!skip_repeat_) { 134 // Only one skip allowed. 135 break; 136 } 137 } 138 if (save_comments_) { 139 if (comments_ == NULL) { 140 comments_ = new vector<StringPiece>; 141 } 142 // already pointing one past end, so no need to +1 143 int length = (int)(input_.data() - start_data); 144 if (length > 0) { 145 comments_->push_back(StringPiece(start_data, length)); 146 } 147 } 148 } 149 150 151 void Scanner::GetComments(int start, int end, vector<StringPiece> *ranges) { 152 // short circuit out if we've not yet initialized comments_ 153 // (e.g., when save_comments is false) 154 if (!comments_) { 155 return; 156 } 157 // TODO: if we guarantee that comments_ will contain StringPieces 158 // that are ordered by their start, then we can do a binary search 159 // for the first StringPiece at or past start and then scan for the 160 // ones contained in the range, quit early (use equal_range or 161 // lower_bound) 162 for (vector<StringPiece>::const_iterator it = comments_->begin(); 163 it != comments_->end(); ++it) { 164 if ((it->data() >= data_.c_str() + start && 165 it->data() + it->size() <= data_.c_str() + end)) { 166 ranges->push_back(*it); 167 } 168 } 169 } 170 171 172 void Scanner::GetNextComments(vector<StringPiece> *ranges) { 173 // short circuit out if we've not yet initialized comments_ 174 // (e.g., when save_comments is false) 175 if (!comments_) { 176 return; 177 } 178 for (vector<StringPiece>::const_iterator it = 179 comments_->begin() + comments_offset_; 180 it != comments_->end(); ++it) { 181 ranges->push_back(*it); 182 ++comments_offset_; 183 } 184 } 185 186 } // namespace pcrecpp 187