OLD | NEW |
1 // Copyright (c) 2012 The Chromium Authors. All rights reserved. | 1 // Copyright (c) 2012 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/url_index_private_data.h" | 5 #include "chrome/browser/history/url_index_private_data.h" |
6 | 6 |
7 #include <functional> | 7 #include <functional> |
8 #include <iterator> | 8 #include <iterator> |
9 #include <limits> | 9 #include <limits> |
10 #include <numeric> | 10 #include <numeric> |
11 #include <string> | 11 #include <string> |
12 #include <vector> | 12 #include <vector> |
13 | 13 |
14 #include "base/basictypes.h" | 14 #include "base/basictypes.h" |
15 #include "base/file_util.h" | 15 #include "base/file_util.h" |
16 #include "base/i18n/break_iterator.h" | 16 #include "base/i18n/break_iterator.h" |
17 #include "base/i18n/case_conversion.h" | 17 #include "base/i18n/case_conversion.h" |
18 #include "base/metrics/histogram.h" | 18 #include "base/metrics/histogram.h" |
19 #include "base/strings/string_util.h" | 19 #include "base/strings/string_util.h" |
20 #include "base/strings/utf_string_conversions.h" | 20 #include "base/strings/utf_string_conversions.h" |
21 #include "base/time/time.h" | 21 #include "base/time/time.h" |
22 #include "chrome/browser/history/history_database.h" | 22 #include "chrome/browser/history/history_database.h" |
23 #include "chrome/browser/history/history_db_task.h" | 23 #include "chrome/browser/history/history_db_task.h" |
24 #include "chrome/browser/history/history_service.h" | 24 #include "chrome/browser/history/history_service.h" |
25 #include "chrome/browser/history/in_memory_url_index.h" | 25 #include "chrome/browser/history/in_memory_url_index.h" |
26 #include "components/bookmarks/browser/bookmark_service.h" | |
27 #include "components/bookmarks/browser/bookmark_utils.h" | 26 #include "components/bookmarks/browser/bookmark_utils.h" |
| 27 #include "components/history/core/browser/history_client.h" |
28 #include "net/base/net_util.h" | 28 #include "net/base/net_util.h" |
29 | 29 |
30 #if defined(USE_SYSTEM_PROTOBUF) | 30 #if defined(USE_SYSTEM_PROTOBUF) |
31 #include <google/protobuf/repeated_field.h> | 31 #include <google/protobuf/repeated_field.h> |
32 #else | 32 #else |
33 #include "third_party/protobuf/src/google/protobuf/repeated_field.h" | 33 #include "third_party/protobuf/src/google/protobuf/repeated_field.h" |
34 #endif | 34 #endif |
35 | 35 |
36 using google::protobuf::RepeatedField; | 36 using google::protobuf::RepeatedField; |
37 using google::protobuf::RepeatedPtrField; | 37 using google::protobuf::RepeatedPtrField; |
(...skipping 106 matching lines...) Expand 10 before | Expand all | Expand 10 after Loading... |
144 pre_filter_item_count_(0), | 144 pre_filter_item_count_(0), |
145 post_filter_item_count_(0), | 145 post_filter_item_count_(0), |
146 post_scoring_item_count_(0) { | 146 post_scoring_item_count_(0) { |
147 } | 147 } |
148 | 148 |
149 ScoredHistoryMatches URLIndexPrivateData::HistoryItemsForTerms( | 149 ScoredHistoryMatches URLIndexPrivateData::HistoryItemsForTerms( |
150 base::string16 search_string, | 150 base::string16 search_string, |
151 size_t cursor_position, | 151 size_t cursor_position, |
152 size_t max_matches, | 152 size_t max_matches, |
153 const std::string& languages, | 153 const std::string& languages, |
154 BookmarkService* bookmark_service) { | 154 HistoryClient* history_client) { |
155 // If cursor position is set and useful (not at either end of the | 155 // If cursor position is set and useful (not at either end of the |
156 // string), allow the search string to be broken at cursor position. | 156 // string), allow the search string to be broken at cursor position. |
157 // We do this by pretending there's a space where the cursor is. | 157 // We do this by pretending there's a space where the cursor is. |
158 if ((cursor_position != base::string16::npos) && | 158 if ((cursor_position != base::string16::npos) && |
159 (cursor_position < search_string.length()) && | 159 (cursor_position < search_string.length()) && |
160 (cursor_position > 0)) { | 160 (cursor_position > 0)) { |
161 search_string.insert(cursor_position, base::ASCIIToUTF16(" ")); | 161 search_string.insert(cursor_position, base::ASCIIToUTF16(" ")); |
162 } | 162 } |
163 pre_filter_item_count_ = 0; | 163 pre_filter_item_count_ = 0; |
164 post_filter_item_count_ = 0; | 164 post_filter_item_count_ = 0; |
(...skipping 71 matching lines...) Expand 10 before | Expand all | Expand 10 after Loading... |
236 // Don't score matches when there are no terms to score against. (It's | 236 // Don't score matches when there are no terms to score against. (It's |
237 // possible that the word break iterater that extracts words to search | 237 // possible that the word break iterater that extracts words to search |
238 // for in the database allows some whitespace "words" whereas Tokenize | 238 // for in the database allows some whitespace "words" whereas Tokenize |
239 // excludes a long list of whitespace.) One could write a scoring | 239 // excludes a long list of whitespace.) One could write a scoring |
240 // function that gives a reasonable order to matches when there | 240 // function that gives a reasonable order to matches when there |
241 // are no terms (i.e., all the words are some form of whitespace), | 241 // are no terms (i.e., all the words are some form of whitespace), |
242 // but this is such a rare edge case that it's not worth the time. | 242 // but this is such a rare edge case that it's not worth the time. |
243 return scored_items; | 243 return scored_items; |
244 } | 244 } |
245 scored_items = std::for_each(history_id_set.begin(), history_id_set.end(), | 245 scored_items = std::for_each(history_id_set.begin(), history_id_set.end(), |
246 AddHistoryMatch(*this, languages, bookmark_service, lower_raw_string, | 246 AddHistoryMatch(*this, languages, history_client, lower_raw_string, |
247 lower_raw_terms, base::Time::Now())).ScoredMatches(); | 247 lower_raw_terms, base::Time::Now())).ScoredMatches(); |
248 | 248 |
249 // Select and sort only the top |max_matches| results. | 249 // Select and sort only the top |max_matches| results. |
250 if (scored_items.size() > max_matches) { | 250 if (scored_items.size() > max_matches) { |
251 std::partial_sort(scored_items.begin(), | 251 std::partial_sort(scored_items.begin(), |
252 scored_items.begin() + | 252 scored_items.begin() + |
253 max_matches, | 253 max_matches, |
254 scored_items.end(), | 254 scored_items.end(), |
255 ScoredHistoryMatch::MatchScoreGreater); | 255 ScoredHistoryMatch::MatchScoreGreater); |
256 scored_items.resize(max_matches); | 256 scored_items.resize(max_matches); |
(...skipping 999 matching lines...) Expand 10 before | Expand all | Expand 10 after Loading... |
1256 : used_(true) {} | 1256 : used_(true) {} |
1257 | 1257 |
1258 URLIndexPrivateData::SearchTermCacheItem::~SearchTermCacheItem() {} | 1258 URLIndexPrivateData::SearchTermCacheItem::~SearchTermCacheItem() {} |
1259 | 1259 |
1260 | 1260 |
1261 // URLIndexPrivateData::AddHistoryMatch ---------------------------------------- | 1261 // URLIndexPrivateData::AddHistoryMatch ---------------------------------------- |
1262 | 1262 |
1263 URLIndexPrivateData::AddHistoryMatch::AddHistoryMatch( | 1263 URLIndexPrivateData::AddHistoryMatch::AddHistoryMatch( |
1264 const URLIndexPrivateData& private_data, | 1264 const URLIndexPrivateData& private_data, |
1265 const std::string& languages, | 1265 const std::string& languages, |
1266 BookmarkService* bookmark_service, | 1266 HistoryClient* history_client, |
1267 const base::string16& lower_string, | 1267 const base::string16& lower_string, |
1268 const String16Vector& lower_terms, | 1268 const String16Vector& lower_terms, |
1269 const base::Time now) | 1269 const base::Time now) |
1270 : private_data_(private_data), | 1270 : private_data_(private_data), |
1271 languages_(languages), | 1271 languages_(languages), |
1272 bookmark_service_(bookmark_service), | 1272 history_client_(history_client), |
1273 lower_string_(lower_string), | 1273 lower_string_(lower_string), |
1274 lower_terms_(lower_terms), | 1274 lower_terms_(lower_terms), |
1275 now_(now) { | 1275 now_(now) { |
1276 // Calculate offsets for each term. For instance, the offset for | 1276 // Calculate offsets for each term. For instance, the offset for |
1277 // ".net" should be 1, indicating that the actual word-part of the term | 1277 // ".net" should be 1, indicating that the actual word-part of the term |
1278 // starts at offset 1. | 1278 // starts at offset 1. |
1279 lower_terms_to_word_starts_offsets_.resize(lower_terms_.size(), 0u); | 1279 lower_terms_to_word_starts_offsets_.resize(lower_terms_.size(), 0u); |
1280 for (size_t i = 0; i < lower_terms_.size(); ++i) { | 1280 for (size_t i = 0; i < lower_terms_.size(); ++i) { |
1281 base::i18n::BreakIterator iter(lower_terms_[i], | 1281 base::i18n::BreakIterator iter(lower_terms_[i], |
1282 base::i18n::BreakIterator::BREAK_WORD); | 1282 base::i18n::BreakIterator::BREAK_WORD); |
1283 // If the iterator doesn't work, assume an offset of 0. | 1283 // If the iterator doesn't work, assume an offset of 0. |
1284 if (!iter.Init()) | 1284 if (!iter.Init()) |
1285 continue; | 1285 continue; |
(...skipping 12 matching lines...) Expand all Loading... |
1298 HistoryInfoMap::const_iterator hist_pos = | 1298 HistoryInfoMap::const_iterator hist_pos = |
1299 private_data_.history_info_map_.find(history_id); | 1299 private_data_.history_info_map_.find(history_id); |
1300 if (hist_pos != private_data_.history_info_map_.end()) { | 1300 if (hist_pos != private_data_.history_info_map_.end()) { |
1301 const URLRow& hist_item = hist_pos->second.url_row; | 1301 const URLRow& hist_item = hist_pos->second.url_row; |
1302 const VisitInfoVector& visits = hist_pos->second.visits; | 1302 const VisitInfoVector& visits = hist_pos->second.visits; |
1303 WordStartsMap::const_iterator starts_pos = | 1303 WordStartsMap::const_iterator starts_pos = |
1304 private_data_.word_starts_map_.find(history_id); | 1304 private_data_.word_starts_map_.find(history_id); |
1305 DCHECK(starts_pos != private_data_.word_starts_map_.end()); | 1305 DCHECK(starts_pos != private_data_.word_starts_map_.end()); |
1306 ScoredHistoryMatch match(hist_item, visits, languages_, lower_string_, | 1306 ScoredHistoryMatch match(hist_item, visits, languages_, lower_string_, |
1307 lower_terms_, lower_terms_to_word_starts_offsets_, | 1307 lower_terms_, lower_terms_to_word_starts_offsets_, |
1308 starts_pos->second, now_, bookmark_service_); | 1308 starts_pos->second, now_, history_client_); |
1309 if (match.raw_score() > 0) | 1309 if (match.raw_score() > 0) |
1310 scored_matches_.push_back(match); | 1310 scored_matches_.push_back(match); |
1311 } | 1311 } |
1312 } | 1312 } |
1313 | 1313 |
1314 | 1314 |
1315 // URLIndexPrivateData::HistoryItemFactorGreater ------------------------------- | 1315 // URLIndexPrivateData::HistoryItemFactorGreater ------------------------------- |
1316 | 1316 |
1317 URLIndexPrivateData::HistoryItemFactorGreater::HistoryItemFactorGreater( | 1317 URLIndexPrivateData::HistoryItemFactorGreater::HistoryItemFactorGreater( |
1318 const HistoryInfoMap& history_info_map) | 1318 const HistoryInfoMap& history_info_map) |
(...skipping 18 matching lines...) Expand all Loading... |
1337 // recently visited (within the last 12/24 hours) as highly important. Get | 1337 // recently visited (within the last 12/24 hours) as highly important. Get |
1338 // input from mpearson. | 1338 // input from mpearson. |
1339 if (r1.typed_count() != r2.typed_count()) | 1339 if (r1.typed_count() != r2.typed_count()) |
1340 return (r1.typed_count() > r2.typed_count()); | 1340 return (r1.typed_count() > r2.typed_count()); |
1341 if (r1.visit_count() != r2.visit_count()) | 1341 if (r1.visit_count() != r2.visit_count()) |
1342 return (r1.visit_count() > r2.visit_count()); | 1342 return (r1.visit_count() > r2.visit_count()); |
1343 return (r1.last_visit() > r2.last_visit()); | 1343 return (r1.last_visit() > r2.last_visit()); |
1344 } | 1344 } |
1345 | 1345 |
1346 } // namespace history | 1346 } // namespace history |
OLD | NEW |