Event matching by regular expression matching on URLs.

chrome/common/extensions/matcher/regex_set_matcher.cc

Index: chrome/common/extensions/matcher/regex_set_matcher.cc
diff --git a/chrome/common/extensions/matcher/regex_set_matcher.cc b/chrome/common/extensions/matcher/regex_set_matcher.cc
new file mode 100644
index 0000000000000000000000000000000000000000..8ae7aa4e4c34776c4c34aca2e94e065635bc3f48
--- /dev/null
+++ b/chrome/common/extensions/matcher/regex_set_matcher.cc
@@ -0,0 +1,109 @@
+// Copyright (c) 2012 The Chromium Authors. All rights reserved.
+// Use of this source code is governed by a BSD-style license that can be
+// found in the LICENSE file.
+
+#include "chrome/common/extensions/matcher/regex_set_matcher.h"
+
+#include "base/logging.h"
+#include "base/string_util.h"
+#include "base/stl_util.h"
+#include "chrome/common/extensions/matcher/substring_set_matcher.h"
+#include "third_party/re2/re2/filtered_re2.h"
+#include "third_party/re2/re2/re2.h"
+
+namespace extensions {
+
+RegexSetMatcher::RegexSetMatcher() {}
+
+RegexSetMatcher::~RegexSetMatcher() {
+  DeleteSubstringPatterns();
+}
+
+void RegexSetMatcher::AddPatterns(
+    const std::vector<const StringPattern*>& regex_list) {
+  if (regex_list.empty())
+    return;
+  for (size_t i = 0; i < regex_list.size(); ++i) {
+    regexes_[regex_list[i]->id()] = regex_list[i];
+  }
+
+  RebuildMatcher();
+}
+
+void RegexSetMatcher::ClearPatterns() {
+  regexes_.clear();
+  RebuildMatcher();
+}
+
+bool RegexSetMatcher::Match(const std::string& text,
+                            std::set<StringPattern::ID>* matches) const {
+  size_t old_number_of_matches = matches->size();
+  if (regexes_.empty())
+    return false;
+  if (!filtered_re2_.get()) {
+    LOG(ERROR) << "RegexSetMatcher was not initialized";
+    return false;
+  }
+
+  // FilteredRE2 expects lowercase for prefiltering, but we still
+  // match case-sensitively.
+  std::vector<RE2ID> atoms(FindSubstringMatches(
+      StringToLowerASCII(text)));
+
+  std::vector<RE2ID> re2_ids;
+  filtered_re2_->AllMatches(text, atoms, &re2_ids);
+
+  std::set<StringPattern::ID> matched_ids;
+  for (size_t i = 0; i < re2_ids.size(); ++i) {
+    StringPattern::ID id = re2_id_map_[re2_ids[i]];
+    matches->insert(id);
+  }
+  return old_number_of_matches != matches->size();
+}
+
+std::vector<RegexSetMatcher::RE2ID> RegexSetMatcher::FindSubstringMatches(
+    const std::string& text) const {
+  std::set<int> atoms_set;
+  substring_matcher_->Match(text, &atoms_set);
+  return std::vector<RE2ID>(atoms_set.begin(), atoms_set.end());
+}
+
+void RegexSetMatcher::RebuildMatcher() {
+  re2_id_map_.clear();
+  filtered_re2_.reset(new re2::FilteredRE2());
+  if (regexes_.empty())
+    return;
+
+  for (RegexMap::iterator it = regexes_.begin(); it != regexes_.end(); ++it) {
+    RE2ID re2_id;
+    RE2::ErrorCode error = filtered_re2_->Add(
+        it->second->pattern(), RE2::DefaultOptions, &re2_id);
+    if (error == RE2::NoError) {
+      DCHECK_EQ(static_cast<RE2ID>(re2_id_map_.size()), re2_id);
+      re2_id_map_.push_back(it->first);
+    } else {
+      // TODO(yoz): Return an unparseable regex error as soon as possible.
+      LOG(ERROR) << "Could not parse regex (id=" << it->first << ", "
+                 << it->second->pattern() << ")";

[battre, 2012/09/12 18:04:50]

I think it would be great if we could report such errors in some way so that
users are aware that their RegEx were invalid.

[Yoyo Zhou, 2012/09/12 20:25:56]

Yes, I looked into this and it seemed like it would be a somewhat hairier
change, so I left it as a TODO (actually the next thing I'll be doing). I think
it'd be better to test for regex validity earlier, so that by the time the
regexes get here we know they're good.

[battre, 2012/09/12 20:50:39]

SGTM

+    }
+  }
+
+  std::vector<std::string> strings_to_match;
+  filtered_re2_->Compile(&strings_to_match);
+  DeleteSubstringPatterns();

[battre, 2012/09/12 18:04:50]

Here you delete objects, that substring_matcher_ still refers to. I think this
is brittle and would recommend to reset the SubstringSetMatcher before deleting
the old references even though the code in this class will become more
complicated. WDYT?

[Yoyo Zhou, 2012/09/12 20:25:56]

I just moved the substring_matcher_.reset line to above this one.

+
+  // Build SubstringSetMatcher from |strings_to_match|.
+  // SubstringSetMatcher doesn't own its strings.
+  for (size_t i = 0; i < strings_to_match.size(); ++i) {
+    substring_patterns_.push_back(
+        new StringPattern(strings_to_match[i], i));
+  }
+  substring_matcher_.reset(new SubstringSetMatcher);
+  substring_matcher_->RegisterPatterns(substring_patterns_);
+}
+
+void RegexSetMatcher::DeleteSubstringPatterns() {
+  STLDeleteElements(&substring_patterns_);
+}
+
+}  // namespace extensions