| OLD | NEW |
| 1 // Copyright (c) 2010 The Chromium Authors. All rights reserved. | 1 // Copyright (c) 2010 The Chromium Authors. All rights reserved. |
| 2 // Use of this source code is governed by a BSD-style license that can be | 2 // Use of this source code is governed by a BSD-style license that can be |
| 3 // found in the LICENSE file. | 3 // found in the LICENSE file. |
| 4 | 4 |
| 5 #include "chrome/browser/history/query_parser.h" | 5 #include "chrome/browser/history/query_parser.h" |
| 6 | 6 |
| 7 #include <algorithm> | 7 #include <algorithm> |
| 8 | 8 |
| 9 #include "app/l10n_util.h" | 9 #include "app/l10n_util.h" |
| 10 #include "base/i18n/word_iterator.h" | 10 #include "base/i18n/break_iterator.h" |
| 11 #include "base/logging.h" | 11 #include "base/logging.h" |
| 12 #include "base/scoped_vector.h" | 12 #include "base/scoped_vector.h" |
| 13 #include "base/string_util.h" | 13 #include "base/string_util.h" |
| 14 #include "base/utf_string_conversions.h" | 14 #include "base/utf_string_conversions.h" |
| 15 #include "unicode/uscript.h" | 15 #include "unicode/uscript.h" |
| 16 | 16 |
| 17 namespace { | 17 namespace { |
| 18 | 18 |
| 19 // Returns true if |mp1.first| is less than |mp2.first|. This is used to | 19 // Returns true if |mp1.first| is less than |mp2.first|. This is used to |
| 20 // sort match positions. | 20 // sort match positions. |
| (...skipping 294 matching lines...) Expand 10 before | Expand all | Expand 10 after Loading... |
| 315 match_positions->clear(); | 315 match_positions->clear(); |
| 316 } else { | 316 } else { |
| 317 CoalseAndSortMatchPositions(&matches); | 317 CoalseAndSortMatchPositions(&matches); |
| 318 match_positions->swap(matches); | 318 match_positions->swap(matches); |
| 319 } | 319 } |
| 320 return true; | 320 return true; |
| 321 } | 321 } |
| 322 | 322 |
| 323 bool QueryParser::ParseQueryImpl(const string16& query, | 323 bool QueryParser::ParseQueryImpl(const string16& query, |
| 324 QueryNodeList* root) { | 324 QueryNodeList* root) { |
| 325 WordIterator iter(&query, WordIterator::BREAK_WORD); | 325 base::BreakIterator iter(&query, base::BreakIterator::BREAK_WORD); |
| 326 // TODO(evanm): support a locale here | 326 // TODO(evanm): support a locale here |
| 327 if (!iter.Init()) | 327 if (!iter.Init()) |
| 328 return false; | 328 return false; |
| 329 | 329 |
| 330 // To handle nesting, we maintain a stack of QueryNodeLists. | 330 // To handle nesting, we maintain a stack of QueryNodeLists. |
| 331 // The last element (back) of the stack contains the current, deepest node. | 331 // The last element (back) of the stack contains the current, deepest node. |
| 332 std::vector<QueryNodeList*> query_stack; | 332 std::vector<QueryNodeList*> query_stack; |
| 333 query_stack.push_back(root); | 333 query_stack.push_back(root); |
| 334 | 334 |
| 335 bool in_quotes = false; // whether we're currently in a quoted phrase | 335 bool in_quotes = false; // whether we're currently in a quoted phrase |
| (...skipping 22 matching lines...) Expand all Loading... |
| 358 } | 358 } |
| 359 } | 359 } |
| 360 } | 360 } |
| 361 | 361 |
| 362 root->RemoveEmptySubnodes(); | 362 root->RemoveEmptySubnodes(); |
| 363 return true; | 363 return true; |
| 364 } | 364 } |
| 365 | 365 |
| 366 void QueryParser::ExtractQueryWords(const string16& text, | 366 void QueryParser::ExtractQueryWords(const string16& text, |
| 367 std::vector<QueryWord>* words) { | 367 std::vector<QueryWord>* words) { |
| 368 WordIterator iter(&text, WordIterator::BREAK_WORD); | 368 base::BreakIterator iter(&text, base::BreakIterator::BREAK_WORD); |
| 369 // TODO(evanm): support a locale here | 369 // TODO(evanm): support a locale here |
| 370 if (!iter.Init()) | 370 if (!iter.Init()) |
| 371 return; | 371 return; |
| 372 | 372 |
| 373 while (iter.Advance()) { | 373 while (iter.Advance()) { |
| 374 // Just found a span between 'prev' (inclusive) and 'pos' (exclusive). It | 374 // Just found a span between 'prev' (inclusive) and 'pos' (exclusive). It |
| 375 // is not necessarily a word, but could also be a sequence of punctuation | 375 // is not necessarily a word, but could also be a sequence of punctuation |
| 376 // or whitespace. | 376 // or whitespace. |
| 377 if (iter.IsWord()) { | 377 if (iter.IsWord()) { |
| 378 string16 word = iter.GetWord(); | 378 string16 word = iter.GetWord(); |
| 379 if (!word.empty()) { | 379 if (!word.empty()) { |
| 380 words->push_back(QueryWord()); | 380 words->push_back(QueryWord()); |
| 381 words->back().word = word; | 381 words->back().word = word; |
| 382 words->back().position = iter.prev(); | 382 words->back().position = iter.prev(); |
| 383 } | 383 } |
| 384 } | 384 } |
| 385 } | 385 } |
| 386 } | 386 } |
| OLD | NEW |