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

compiled/Filter.cpp

 #include "Filter.h"
 #include "CommentFilter.h"
+#include "InvalidFilter.h"
 #include "RegExpFilter.h"
+#include "BlockingFilter.h"
+#include "WhitelistFilter.h"
+#include "ElemHideBase.h"
 #include "ElemHideFilter.h"
 #include "ElemHideException.h"
+#include "CSSPropertyFilter.h"
 #include "StringMap.h"
 
 namespace
 {
-  /* TODO: This is a memory leak. Store raw/weak pointers as soon as we are
-     actually using the filters somewhere. */
-  StringMap<FilterPtr> knownFilters(8192);
+  StringMap<Filter*> knownFilters(8192);
 
-  void trim_spaces(String& str)
+  void NormalizeWhitespace(DependentString& 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;
 
-    // Remove leading whitespace
-    for (pos = 0; pos < str.length(); ++pos)
-      if (str[pos] != u' ')
+    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;
-    str.reset(str, pos);
 
-    // Remove trailing whitespace
-    for (pos = str.length(); pos > 0; --pos)
-      if (str[pos - 1] != u' ')
-        break;
-    str.reset(str, 0, pos);
-  }
-
-  void remove_spaces(String& str)
-  {
-    String::size_type pos;
-
-    for (String::size_type i = 0; i < str.length(); ++i)
-      if (str[i] != u' ')
-        str[pos++] = str[i];
-
-    str.reset(str, 0, pos);
+    // Set new string boundaries
+    text.reset(text, start, end - start);
   }
 }
 
-Filter::Filter(const String& text)
-    : mText(text)
+Filter::Filter(Type type, const String& text)
+    : mType(type), mText(text)
 {
   annotate_address(this, "Filter");
-  mText.ensure_own_buffer();
 }
 
-String Filter::Serialize()
+Filter::~Filter()
 {
-  String result(u"[Filter]\ntext="_str);
+  knownFilters.erase(mText);
+}
+
+OwnedString Filter::Serialize() const
+{
+  OwnedString result(u"[Filter]\ntext="_str);
   result.append(mText);
   result.append(u'\n');
-  return std::move(result);
+  return result;
 }
 
-FilterPtr Filter::FromText(const String& text)
+Filter* Filter::FromText(DependentString& text)
 {
-  auto it = knownFilters.find(text);
-  if (it != knownFilters.end())
-    return it->second;
+  NormalizeWhitespace(text);
+  if (text.empty())
+    return nullptr;
 
-  FilterPtr filter = FilterPtr(CommentFilter::Create(text));
-  if (!filter)
-    filter.reset(ElemHideBase::Create(text));
-  if (!filter)
-    filter.reset(RegExpFilter::Create(text));
+  // Parsing also normalizes the filter text, so it has to be done before the
+  // lookup in knownFilters.
+  union
+  {
+    RegExpFilterData regexp;
+    ElemHideData elemhide;
+  } data;
+  DependentString error;
 
-  enter_context("Adding to known filters");
-  knownFilters[filter->mText] = filter;
-  exit_context();
-  return filter;
-}
+  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);
 
-String Filter::Normalize(String& text)
-{
-  // Removing special characters like line breaks
-  String::size_type delta = 0;
-  for (String::size_type i = 0; i < text.length(); ++i)
+  auto knownFilter = knownFilters.find(text);
+  if (knownFilter)
   {
-    if (text[i] >= u' ')
-      text[i - delta] = text[i];
-    else
-      ++delta;
-  }
-  text.reset(text, 0, text.length() - delta);
-
-  trim_spaces(text);
-
-  {
-    String::size_type domainsEnd;
-    String::size_type selectorStart;
-    Filter::Type type = ElemHideBase::Parse(text, &domainsEnd, &selectorStart);
-    if (type != Filter::Type::UNKNOWN)
-    {
-      String domains(text, 0, domainsEnd);
-      String selector(text, selectorStart);
-      remove_spaces(domains);
-      trim_spaces(selector);
-
-      String::size_type domainsDelta = domainsEnd - domains.length();
-      String::size_type selectorDelta = text.length() - selectorStart -
-          selector.length();
-
-      if (domainsDelta)
-        for (String::size_type i = domainsEnd; i < selectorStart; ++i)
-          text[i - domainsDelta] = text[i];
-
-      if (domainsDelta + selectorDelta)
-        for (String::size_type i = 0; i < selector.length(); ++i)
-          text[selectorStart - domainsDelta + i] = selector[i];
-
-      text.reset(text, 0, text.length() - domainsDelta - selectorDelta);
-      return text;
-    }
+    knownFilter->second->AddRef();
+    return knownFilter->second;
   }
 
-  if (CommentFilter::Parse(text) == Filter::Type::UNKNOWN)
-    remove_spaces(text);
-  return text;
+  FilterPtr 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 BlockingFilter(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 (static_cast<CSSPropertyFilter*>(filter.get())->IsGeneric())
+        filter = new InvalidFilter(text, u"filter_cssproperty_nodomain"_str);
+      break;
+    default:
+      // This should never happen but just in case
+      return nullptr;
+  }
+
+  // This is a hack: we looked up the entry using text but create it using
+  // filter->mText. This works because both are equal at this point. However,
+  // text refers to a temporary buffer which will go away.
+  enter_context("Adding to known filters");
+  knownFilter.assign(filter->mText, filter.get());
+  exit_context();
+
+  return filter.release();
 }