Issue 4125 - [emscripten] Convert filter classes to C++

compiled/Filter.cpp

+#include "Filter.h"
+#include "CommentFilter.h"
+#include "InvalidFilter.h"
+#include "RegExpFilter.h"
+#include "WhitelistFilter.h"
+#include "ElemHideBase.h"
+#include "ElemHideFilter.h"
+#include "ElemHideException.h"
+#include "CSSPropertyFilter.h"
+#include "StringMap.h"
+
+namespace
+{
+  StringMap<Filter*> knownFilters(8192);
+
+  void NormalizeWhitespace(String& text)
+  {
+    String::size_type start = 0;
+    String::size_type end = text.length();
+
+    // Remove leading spaces and special characters like line breaks
+    for (; start < end; start++)
+      if (text[start] > ' ')
+        break;
+
+    // Now look for invalid characters inside the string
+    String::size_type pos;
+    for (pos = start; pos < end; pos++)
+      if (text[pos] < ' ')
+        break;
+
+    if (pos < end)
+    {
+      // Found invalid characters, copy all the valid characters while skipping
+      // the invalid ones.
+      String::size_type delta = 1;
+      for (pos = pos + 1; pos < end; pos++)
+      {
+        if (text[pos] < ' ')
+          delta++;
+        else
+          text[pos - delta] = text[pos];
+      }
+      end -= delta;
+    }
+
+    // Remove trailing spaces
+    for (; end > 0; end--)
+      if (text[end - 1] != ' ')
+        break;
+
+    // Set new string boundaries
+    text.reset(text, start, end - start);
+  }
+}
+
+Filter::Filter(const String& text)
+    : ref_counted(), mText(text)
+{
+  annotate_address(this, "Filter");
+  mText.ensure_own_buffer();
+}
+
+Filter::~Filter()
+{
+  // TODO: This should be removing from knownFilters
+}
+
+String Filter::Serialize() const
+{
+  String result(u"[Filter]\ntext="_str);
+  result.append(mText);
+  result.append(u'\n');
+  return std::move(result.ensure_own_buffer());
+}
+
+Filter* Filter::FromText(String& text)
+{
+  NormalizeWhitespace(text);
+  if (text.empty())
+    return nullptr;
+
+  // Parsing also normalizes the filter text, so it has to be done before the
+  // lookup in knownFilters.
+  union
+  {
+    RegExpFilterData regexp;
+    ElemHideData elemhide;
+  } data;
+  String error;
+
+  Filter::Type type = CommentFilter::Parse(text);
+  if (type == Filter::Type::UNKNOWN)
+    type = ElemHideBase::Parse(text, data.elemhide);
+  if (type == Filter::Type::UNKNOWN)
+    type = RegExpFilter::Parse(text, error, data.regexp);
+
+  FilterPtr filter(GetKnownFilter(text));
+  if (filter)
+    return filter;
+
+  switch (type)
+  {
+    case Filter::Type::COMMENT:
+      filter = new CommentFilter(text);
+      break;
+    case Filter::Type::INVALID:
+      filter = new InvalidFilter(text, error);
+      break;
+    case Filter::Type::BLOCKING:
+      filter = new RegExpFilter(text, data.regexp);
+      break;
+    case Filter::Type::WHITELIST:
+      filter = new WhitelistFilter(text, data.regexp);
+      break;
+    case Filter::Type::ELEMHIDE:
+      filter = new ElemHideFilter(text, data.elemhide);
+      break;
+    case Filter::Type::ELEMHIDEEXCEPTION:
+      filter = new ElemHideException(text, data.elemhide);
+      break;
+    case Filter::Type::CSSPROPERTY:
+      filter = new CSSPropertyFilter(text, data.elemhide);
+      if (reinterpret_cast<CSSPropertyFilter*>(filter.get())->IsGeneric())
+        filter = new InvalidFilter(text,
+            u"No active domain specified for CSS property filter"_str);
+      break;
+    default:
+      // This should never happen but just in case
+      return nullptr;
+  }
+
+  enter_context("Adding to known filters");
+  knownFilters[filter->mText] = filter.get();
+  exit_context();
+
+  // TODO: We intentionally leak the filter here - currently it won't be used
+  // for anything and would be deleted immediately.
+  filter->AddRef();
+
+  return filter;
+}
+
+Filter* Filter::GetKnownFilter(const String& text)
+{
+  auto it = knownFilters.find(text);
+  if (it != knownFilters.end())
+    return it->second;
+  else
+    return nullptr;
+}