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

compiled/String.h

Index: compiled/String.h
===================================================================
new file mode 100644
--- /dev/null
+++ b/compiled/String.h
@@ -0,0 +1,331 @@
+#pragma once
+
+#include <cstddef>
+#include <cstring>
+#include <algorithm>
+
+#include "debug.h"
+
+inline void String_assert_readonly(bool readOnly);
+
+class String
+{
+  friend class DependentString;
+  friend class OwnedString;
+
+public:
+  typedef char16_t value_type;
+  typedef size_t size_type;
+
+  // Type flags, stored in the top 2 bits of the mLen member
+  static constexpr size_type INVALID = 0xC0000000;
+  static constexpr size_type DELETED = 0x80000000;
+  static constexpr size_type READ_ONLY = 0x40000000;
+  static constexpr size_type READ_WRITE = 0x00000000;
+
+  static constexpr size_type FLAGS_MASK = 0xC0000000;
+  static constexpr size_type LENGTH_MASK = 0x3FFFFFFF;
+
+  static constexpr size_type npos = -1;
+
+protected:
+  value_type* mBuf;
+  size_type mLen;
+
+  String(value_type* buf, size_type len, size_type flags)
+      : mBuf(buf), mLen((len & LENGTH_MASK) | flags)
+  {
+  }

[sergei, 2016/02/22 12:46:01]

What about assert(mLen > 0 || mBuf == nullptr)?

[Wladimir Palant, 2016/02/23 12:37:32]

Somewhat problematic since asserts take string literals and those haven't been
defined at this point :)

+
+  ~String()
+  {
+  }
+
+  void reset(value_type* buf, size_type len, size_type flags)
+  {
+    mBuf = buf;
+    mLen = (len & LENGTH_MASK) | flags;
+  }
+
+public:
+  size_type length() const
+  {
+    return mLen & LENGTH_MASK;
+  }
+
+  bool empty() const
+  {
+    return !(mLen & LENGTH_MASK);
+  }
+
+  const value_type* data() const
+  {
+    return mBuf;
+  }
+
+  value_type* data()
+  {
+    String_assert_readonly(is_readOnly());
+    return mBuf;
+  }
+
+  const value_type& operator[](size_type pos) const
+  {
+    return mBuf[pos];
+  }
+
+  value_type& operator[](size_type pos)
+  {
+    String_assert_readonly(is_readOnly());
+    return mBuf[pos];
+  }
+
+  bool is_readOnly() const
+  {
+    return (mLen & FLAGS_MASK) != READ_WRITE;
+  }
+
+  bool equals(const String& other) const
+  {
+    if (length() != other.length())
+      return false;
+
+    return std::memcmp(mBuf, other.mBuf, sizeof(value_type) * length()) == 0;
+  }
+
+  size_type find(value_type c, size_type pos = 0) const
+  {
+    for (size_type i = pos; i < length(); ++i)
+      if (mBuf[i] == c)
+        return i;
+    return npos;
+  }
+
+  size_type find(const String& str, size_type pos = 0) const
+  {
+    if (pos + str.length() > length())
+      return npos;
+
+    if (!str.length())
+      return pos;
+
+    for (; pos + str.length() <= length(); ++pos)
+    {
+      if (mBuf[pos] == str[0] &&
+          std::memcmp(mBuf + pos, str.mBuf, sizeof(value_type) * str.length()) == 0)
+      {
+        return pos;
+      }
+    }
+
+    return npos;
+  }
+
+  size_type rfind(value_type c, size_type pos = npos) const
+  {
+    if (length() == 0)
+      return npos;
+
+    if (pos >= length())
+      pos = length() - 1;
+
+    for (int i = pos; i >= 0; --i)
+      if (mBuf[i] == c)
+        return i;
+    return npos;
+  }
+};
+
+class DependentString : public String
+{
+public:
+  DependentString()
+      : String(nullptr, 0, INVALID)
+  {
+  }
+
+  DependentString(value_type* buf, size_type len)
+      : String(buf, len, READ_WRITE)
+  {
+  }
+
+  DependentString(const value_type* buf, size_type len)
+      : String(const_cast<value_type*>(buf), len, READ_ONLY)
+  {
+  }
+
+  DependentString(String& str, size_type pos = 0, size_type len = npos)
+      : String(
+          str.mBuf + std::min(pos, str.length()),
+          std::min(len, str.length() - std::min(pos, str.length())),
+          READ_WRITE

[sergei, 2016/02/22 12:45:58]

BTW, `READ_WRITE` here should be

str.is_readOnly() ? READ_ONLY : READ_WRITE

+        )
+  {
+  }
+
+  DependentString(const String& str, size_type pos = 0, size_type len = npos)
+      : String(
+          str.mBuf + std::min(pos, str.length()),
+          std::min(len, str.length() - std::min(pos, str.length())),
+          READ_ONLY
+        )
+  {
+  }
+
+  void reset(value_type* buf, size_type len)
+  {
+    *this = DependentString(buf, len);
+  }
+
+  void reset(const value_type* buf, size_type len)
+  {
+    *this = DependentString(buf, len);
+  }
+
+  void reset(String& str, size_type pos = 0, size_type len = npos)
+  {
+    *this = DependentString(str, pos, len);
+  }
+
+  void reset(const String& str, size_type pos = 0, size_type len = npos)
+  {
+    *this = DependentString(str, pos, len);
+  }
+
+  bool is_invalid() const
+  {
+    return (mLen & FLAGS_MASK) == INVALID;
+  }
+
+  bool is_deleted() const
+  {
+    return (mLen & FLAGS_MASK) == DELETED;
+  }
+};
+
+inline DependentString operator "" _str(const String::value_type* str,
+    String::size_type len)
+{
+  return DependentString(str, len);
+}
+
+inline void String_assert_readonly(bool readOnly)
+{
+  assert(!readOnly, u"Writing access to a read-only string"_str);
+}
+
+class OwnedString : public String
+{
+private:
+  value_type* allocate(size_type len)
+  {
+    if (len)
+      return new value_type[len];
+    else
+      return nullptr;
+  }
+
+  void grow(size_type additionalSize)
+  {
+    size_type oldLength = length();
+    size_type newLength = oldLength + additionalSize;
+    value_type* oldBuffer = mBuf;
+
+    reset(nullptr, newLength, READ_WRITE);
+    newLength = length();
+    mBuf = allocate(newLength);
+    annotate_address(mBuf, "String");
+
+    if (oldLength)
+      std::memcpy(mBuf, oldBuffer, sizeof(value_type) * oldLength);
+    if (oldBuffer)
+      delete[] oldBuffer;
+  }
+
+public:
+  OwnedString(size_type len = 0)
+      : String(nullptr, len, READ_WRITE)
+  {
+    mBuf = allocate(length());
+    annotate_address(mBuf, "String");
+  }
+
+  OwnedString(const String& str)
+      : OwnedString(str.length())
+  {
+    std::memcpy(mBuf, str.mBuf, sizeof(value_type) * length());
+  }
+
+  OwnedString(const OwnedString& str)
+      : OwnedString(static_cast<const String&>(str))
+  {
+  }
+
+  OwnedString(const value_type* str, size_type len)
+      : OwnedString(DependentString(str, len))
+  {
+  }
+
+  OwnedString(OwnedString&& str)
+      : OwnedString(str.length())
+  {
+    mBuf = str.mBuf;
+    str.mBuf = nullptr;
+    str.mLen = READ_WRITE | 0;
+  }

[sergei, 2016/02/22 12:45:59]

I think here is a memory leak.
`OwnedString(str.length())` allocates the buffer and then we override the
pointer on it by `mBuf = str.mBuf;`.

[Wladimir Palant, 2016/02/23 12:37:33]

Done.

+
+  OwnedString(const char* source, size_type len)

[sergei, 2016/02/22 12:46:00]

I'm not sure whether we need this method because it does not support UTF-8 and
it's used only once in `to_string(unsigned int)` (in ActiveFilter.cpp).

[Wladimir Palant, 2016/02/23 12:37:30]

Yes, it's somewhat of a hack - removed.

+      : OwnedString(len)
+  {
+    for (size_type i = 0; i < len; i++)
+      mBuf[i] = source[i];
+  }
+
+  ~OwnedString()
+  {
+    if (mBuf)
+      delete[] mBuf;
+  }
+
+  OwnedString& operator=(const String& str)
+  {
+    *this = std::move(OwnedString(str));
+    return *this;
+  }
+
+  OwnedString& operator=(const OwnedString& str)
+  {
+    *this = std::move(OwnedString(str));
+    return *this;
+  }
+
+  OwnedString& operator=(OwnedString&& str)
+  {
+    mBuf = str.mBuf;
+    mLen = str.mLen;
+    str.mBuf = nullptr;
+    str.mLen = READ_WRITE | 0;
+    return *this;
+  }
+
+  void append(const value_type* source, size_type sourceLen)
+  {
+    if (!sourceLen)
+      return;
+
+    assert(source, u"Null buffer passed to OwnedString.append()"_str);
+    size_t oldLength = length();
+    grow(sourceLen);
+    std::memcpy(mBuf + oldLength, source, sizeof(value_type) * sourceLen);
+  }
+
+  void append(const String& str)
+  {
+    append(str.mBuf, str.length());
+  }
+
+  void append(value_type c)
+  {
+    append(&c, 1);
+  }
+};