Issue 5141 - Convert filter match to C++

compiled/filter/Matcher.cpp

Index: compiled/filter/Matcher.cpp
===================================================================
new file mode 100644
--- /dev/null
+++ b/compiled/filter/Matcher.cpp
@@ -0,0 +1,324 @@
+/*
+ * This file is part of Adblock Plus <https://adblockplus.org/>,
+ * Copyright (C) 2006-present eyeo GmbH
+ *
+ * Adblock Plus is free software: you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 3 as
+ * published by the Free Software Foundation.
+ *
+ * Adblock Plus is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with Adblock Plus.  If not, see <http://www.gnu.org/licenses/>.
+ */
+
+#include "Matcher.h"
+#include "RegExpFilter.h"
+#include "../library.h"
+
+class CombinedMatcher : public MatcherBase
+{
+private:
+  StringMap<Filter*> mResultCache;

[hub, 2017/09/26 21:49:00]

I wanted to use FilterPtr in there, but it didn't want to compile. I'll look at
what it is, it was a mutability issue.

+  static const size_t MAX_CACHE_ENTRIES = 1000;
+  int mMatchReId;
+public:
+  Matcher mBlacklist;
+  Matcher mWhitelist;
+
+  CombinedMatcher()
+    : mMatchReId(GenerateRegExp(u"[a-z0-9%]{3,}"_str, true, true))
+  {
+  }
+
+  ~CombinedMatcher()
+  {
+    DeleteRegExp(mMatchReId);
+  }
+
+  void ResetCache()
+  {
+    for (auto filter : mResultCache)
+      filter.second->ReleaseRef();

[hub, 2017/09/26 21:49:00]

See above: if we could have the FilterPtr as the data type for mResultCache,
this wouldn't be needed :-/

+    mResultCache.clear();
+  }
+
+  void Add(const FilterPtr& filter) override
+  {
+    if (filter->mType == Filter::Type::WHITELIST)
+      mWhitelist.Add(filter);
+    else
+      mBlacklist.Add(filter);
+
+    ResetCache();
+  }
+
+  void Remove(const FilterPtr& filter) override
+  {
+    if (filter->mType == Filter::Type::WHITELIST)
+      mWhitelist.Remove(filter);
+    else
+      mBlacklist.Remove(filter);
+
+    ResetCache();
+  }
+
+  void Clear() override
+  {
+    mBlacklist.Clear();
+    mWhitelist.Clear();
+    ResetCache();
+  }
+
+  OwnedString FindKeyword(const FilterPtr& filter) override
+  {
+    if (filter->mType == Filter::Type::WHITELIST)
+      return mWhitelist.FindKeyword(filter);
+    return mBlacklist.FindKeyword(filter);
+  }
+
+  bool HasFilter(const FilterPtr& filter) const override
+  {
+    if (filter->mType == Filter::Type::WHITELIST)
+      return mWhitelist.HasFilter(filter);
+    return mBlacklist.HasFilter(filter);
+  }
+
+  const String& GetKeywordForFilter(const FilterPtr& filter) override
+  {
+    if (filter->mType == Filter::Type::WHITELIST)
+      return mWhitelist.GetKeywordForFilter(filter);
+    return mBlacklist.GetKeywordForFilter(filter);
+  }
+
+  Filter* MatchesAnyInternal(const String& location,
+    int typeMask, DependentString& docDomain, bool thirdParty,
+    const String& sitekey, bool specificOnly)
+  {
+    ReMatchResults reResult;
+    OwnedString text(location);
+    text.toLower();
+    text.match(mMatchReId, &reResult);
+
+    auto& candidates = reResult.candidates;
+    candidates.push_back(OwnedString());
+
+    Filter* blacklistHit = nullptr;
+    for (size_t i = 0, l = candidates.size(); i < l; i++)
+    {
+      auto substr = candidates[i];
+      if (mWhitelist.mFilterByKeyword.find(substr))
+      {
+        auto result = mWhitelist._CheckEntryMatch(
+          substr, location, typeMask, docDomain, thirdParty, sitekey, specificOnly);
+        if (result)
+          return result;
+      }
+      if (mBlacklist.mFilterByKeyword.find(substr) && !blacklistHit)
+      {
+        blacklistHit = mBlacklist._CheckEntryMatch(
+          substr, location, typeMask, docDomain, thirdParty, sitekey,
+          specificOnly);
+      }
+    }
+    return blacklistHit;
+  }
+
+  Filter* MatchesAny(const String& location,
+    int typeMask, DependentString& docDomain, bool thirdParty,
+    const String& sitekey, bool specificOnly) override
+  {
+    OwnedString key(location);
+    key.append(u" "_str);
+    key.append(typeMask);
+    key.append(u" "_str);
+    key.append(docDomain);
+    key.append(u" "_str);
+    key.append(thirdParty);
+    key.append(u" "_str);
+    key.append(sitekey);
+    key.append(u" "_str);
+    key.append(specificOnly);
+
+    auto cachedResult = mResultCache.find(key);
+    if (cachedResult)
+    {
+      cachedResult->second->AddRef();
+      return cachedResult->second;
+    }
+
+    Filter* result = MatchesAnyInternal(location, typeMask, docDomain,
+                                          thirdParty, sitekey, specificOnly);
+
+    if (mResultCache.size() >= MAX_CACHE_ENTRIES)
+      ResetCache();
+
+    result->AddRef();
+    mResultCache[key] = result;
+
+    result->AddRef();
+    return result;
+  }
+};
+
+MatcherBase* MatcherBase::mInstance = new CombinedMatcher;
+
+Matcher::Matcher()
+  : mFilterReId(GenerateRegExp(DependentString(Filter::regexpRegExp), true, false))
+  , mOptionsReId(GenerateRegExp(DependentString(Filter::optionsRegExp), true, false))
+  , mCandidatesReId(GenerateRegExp(u"[^a-z0-9%*][a-z0-9%]{3,}(?=[^a-z0-9%*])"_str, true, true))
+{
+}
+
+Matcher::~Matcher()
+{
+  DeleteRegExp(mFilterReId);
+  DeleteRegExp(mOptionsReId);
+  DeleteRegExp(mCandidatesReId);
+}
+
+OwnedString Matcher::FindKeyword(const FilterPtr& filter)
+{
+  OwnedString result(u""_str);
+  OwnedString text(filter->GetText());
+  if (TestRegExp(mFilterReId, text))
+    return result;
+
+  // Remove options
+  auto index = ExecRegExp(mOptionsReId, text);
+  if (index != -1)
+    text = text.substr(0, index);
+
+  // Remove whitelist marker
+  if (text[0] == '@' && text[1] == '@')
+    text = text.substr(2);
+
+  text.toLower();
+  ReMatchResults keywords;
+  auto match = text.match(mCandidatesReId, &keywords);
+  if (!match)
+    return result;
+
+  auto& candidates = keywords.candidates;
+
+  auto& hash = mFilterByKeyword;
+  uint32_t resultCount = 0xffffffff;
+  uint32_t resultLength = 0;
+  for (uint32_t i = 0, l = candidates.size(); i < l; i++)
+  {
+    auto candidate = DependentString(candidates[i]).substr(1);
+    auto count = (hash.find(candidate) ? hash[candidate].size() : 0);
+    if (count < resultCount ||
+      (count == resultCount && candidate.length() > resultLength))
+    {
+      result = candidate;
+      resultCount = count;
+      resultLength = candidate.length();
+    }
+  }
+
+  return result;
+}
+
+void Matcher::Add(const FilterPtr& filter)
+{
+  if (mKeywordByFilter.find(filter->GetText()))
+    return;
+
+  auto keyword = FindKeyword(filter);
+  auto oldEntry = mFilterByKeyword.find(keyword);
+  if (!oldEntry)
+    mFilterByKeyword[keyword] = std::vector<FilterPtr>{filter};
+  else
+    mFilterByKeyword[keyword].push_back(filter);
+  mKeywordByFilter[filter->GetText()] = keyword;
+}
+
+void Matcher::Remove(const FilterPtr& filter)
+{
+  if (!mKeywordByFilter.find(filter->GetText()))
+    return;
+
+  auto keyword = mKeywordByFilter[filter->GetText()];
+  auto list = mFilterByKeyword[keyword];
+  if (list.size() == 1)
+    mFilterByKeyword.erase(keyword);
+  else
+  {
+    auto iter = std::find(list.cbegin(), list.cend(), filter);
+    list.erase(iter);
+  }
+  mKeywordByFilter.erase(filter->GetText());
+}
+
+void Matcher::Clear()
+{
+  mFilterByKeyword.clear();
+  mKeywordByFilter.clear();
+}
+
+bool Matcher::HasFilter(const FilterPtr& filter) const
+{
+  return mKeywordByFilter.find(filter->GetText());
+}
+
+static DependentString emptyString = u""_str;
+
+const String& Matcher::GetKeywordForFilter(const FilterPtr& filter)
+{
+  if (mKeywordByFilter.find(filter->GetText()))
+    return mKeywordByFilter[filter->GetText()];
+  return emptyString;
+}
+
+Filter* Matcher::_CheckEntryMatch(const String& keyword,
+  const String& location,
+  int typeMask, DependentString& docDomain, bool thirdParty,
+  const String& sitekey, bool specificOnly)
+{
+  auto list = mFilterByKeyword[keyword];
+  for (auto filter : list) {
+    auto activeFilter = static_cast<ActiveFilter*>(filter.get());

[hub, 2017/09/26 21:49:00]

This is done without checking. And it is ugly. And given that we have RTTI
disabled, we can't even dynamic_cast<>.

[sergei, 2017/10/02 12:02:33]

Although we don't pass other filters here, what do you think about having some
`Filter::As` (see Subscriptions) method down-casting with the checking of its
type and returning nullptr if the type is incorrect. Here we could have an
assert that it should never be a nullptr.

+    if (specificOnly && activeFilter->IsGeneric() &&
+        !(activeFilter->mType != Filter::Type::WHITELIST))
+      continue;
+    auto reFilter = static_cast<RegExpFilter*>(activeFilter);

[hub, 2017/09/26 21:49:00]

SImilarly as above: this is unchecked.

+    if (reFilter->Matches(location, typeMask, docDomain, thirdParty, sitekey))
+    {
+      return filter.get();
+    }
+  }
+  return nullptr;
+}
+
+Filter* Matcher::MatchesAny(const String& location,
+  int typeMask, DependentString& docDomain, bool thirdParty,
+  const String& sitekey, bool specificOnly)
+{
+  ReMatchResults reResult;
+  auto re_id = GenerateRegExp(u"[a-z0-9%]{3,}"_str, true, true);
+  OwnedString text(location);
+  text.toLower();
+  MatchRegExp(re_id, text, &reResult);
+  auto& candidates = reResult.candidates;
+  candidates.push_back(OwnedString());
+  for (size_t i = 0, l = candidates.size(); i < l; i++)
+  {
+    auto substr = candidates[i];
+    if (mFilterByKeyword.find(substr))
+    {
+      auto result = _CheckEntryMatch(substr, location, typeMask, docDomain, 
+                                     thirdParty, sitekey, specificOnly);
+      if (result)
+      {
+        result->AddRef();
+        return result;
+      }
+    }
+  }
+
+  return nullptr;
+}