Issue 4128, 5138 - Add Parser and Serializer implemented in C++

compiled/storage/Serializer.cpp

Index: compiled/storage/Serializer.cpp
diff --git a/compiled/storage/Serializer.cpp b/compiled/storage/Serializer.cpp
new file mode 100644
index 0000000000000000000000000000000000000000..18b50d574ead9b7ce82aab554d7be76dce650988
--- /dev/null
+++ b/compiled/storage/Serializer.cpp
@@ -0,0 +1,72 @@
+/*
+ * 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 <vector>
+#include "Serializer.h"
+#include "../subscription/Subscription.h"
+
+namespace
+{
+  // escape [, if nothing is escaped then `second` is false.
+  std::pair<OwnedString, bool> EscapeOpeningBracket(const String& value)
+  {
+    auto valueLength = value.length();
+    // there are only few filters with [, so it's faster to not copy the value
+    // but quickly scan firstly whether it makes sense to create a new string.
+    int bracketsCounter = 0;
+    for (String::size_type i = 0; i < valueLength; ++i)
+    {
+      if (value[i] == u'[')
+        ++bracketsCounter;
+    }
+    if (bracketsCounter == 0)
+      return std::make_pair(OwnedString(), false);
+
+    OwnedString escapedString(valueLength + bracketsCounter);
+    String::size_type writeOffset = 0;
+    for (String::size_type i = 0; i < valueLength; ++i)
+    {
+      if (value[i] == u'[')
+        escapedString[i + writeOffset++] = u'\\';
+      escapedString[i + writeOffset] = value[i];
+    }
+    return std::make_pair(std::move(escapedString), true);
+  }
+}
+
+Serializer::Serializer()
+{
+  mStream.append(u"# Adblock Plus preferences\nversion=5\n"_str);

[Wladimir Palant, 2017/12/21 10:30:37]

I hope that this is part of your "not complete yet" comment. This approach will
produce a horrible number of reallocations which should render it way too slow
for any realistic data amounts.

+}
+
+void Serializer::Serialize(const Subscription& subscription)
+{
+  mStream.append(u"[Subscription]\n"_str);
+  mStream.append(subscription.SerializeProperties());
+
+  const auto& filters = subscription.GetFilters();
+  if (!filters.empty())
+  {
+    mStream.append(u"[Subscription filters]\n"_str);
+    for (const auto& filter : filters)
+    {
+      auto escapedResult = EscapeOpeningBracket(filter->GetText());

[sergei, 2017/09/19 09:17:35]

BTW, what about escaping of '[' only when it's the first character and there is
']' at the end of the line?

[Wladimir Palant, 2017/12/21 10:30:37]

That should be fine. For now we still have to unescape it everywhere when
parsing however, for backwards compatibility.

+      mStream.append(escapedResult.second ? escapedResult.first : filter->GetText());
+      mStream.append(u'\n');
+    }
+  }
+}