therubyracer 0.8.1.pre2 → 0.8.1

data/ext/v8/upstream/3.1.8/src/unicode.h

@@ -0,0 +1,280 @@
+// Copyright 2007-2008 the V8 project authors. All rights reserved.
+// Redistribution and use in source and binary forms, with or without
+// modification, are permitted provided that the following conditions are
+// met:
+//
+//     * Redistributions of source code must retain the above copyright
+//       notice, this list of conditions and the following disclaimer.
+//     * Redistributions in binary form must reproduce the above
+//       copyright notice, this list of conditions and the following
+//       disclaimer in the documentation and/or other materials provided
+//       with the distribution.
+//     * Neither the name of Google Inc. nor the names of its
+//       contributors may be used to endorse or promote products derived
+//       from this software without specific prior written permission.
+//
+// THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS
+// "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
+// LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR
+// A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT
+// OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL,
+// SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT
+// LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE,
+// DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY
+// THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
+// (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
+// OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
+
+#ifndef V8_UNICODE_H_
+#define V8_UNICODE_H_
+
+#include <sys/types.h>
+
+/**
+ * \file
+ * Definitions and convenience functions for working with unicode.
+ */
+
+namespace unibrow {
+
+typedef unsigned int uchar;
+typedef unsigned char byte;
+
+/**
+ * The max length of the result of converting the case of a single
+ * character.
+ */
+static const int kMaxMappingSize = 4;
+
+template <class T, int size = 256>
+class Predicate {
+ public:
+  inline Predicate() { }
+  inline bool get(uchar c);
+ private:
+  friend class Test;
+  bool CalculateValue(uchar c);
+  struct CacheEntry {
+    inline CacheEntry() : code_point_(0), value_(0) { }
+    inline CacheEntry(uchar code_point, bool value)
+      : code_point_(code_point),
+        value_(value) { }
+    uchar code_point_ : 21;
+    bool value_ : 1;
+  };
+  static const int kSize = size;
+  static const int kMask = kSize - 1;
+  CacheEntry entries_[kSize];
+};
+
+// A cache used in case conversion.  It caches the value for characters
+// that either have no mapping or map to a single character independent
+// of context.  Characters that map to more than one character or that
+// map differently depending on context are always looked up.
+template <class T, int size = 256>
+class Mapping {
+ public:
+  inline Mapping() { }
+  inline int get(uchar c, uchar n, uchar* result);
+ private:
+  friend class Test;
+  int CalculateValue(uchar c, uchar n, uchar* result);
+  struct CacheEntry {
+    inline CacheEntry() : code_point_(kNoChar), offset_(0) { }
+    inline CacheEntry(uchar code_point, signed offset)
+      : code_point_(code_point),
+        offset_(offset) { }
+    uchar code_point_;
+    signed offset_;
+    static const int kNoChar = (1 << 21) - 1;
+  };
+  static const int kSize = size;
+  static const int kMask = kSize - 1;
+  CacheEntry entries_[kSize];
+};
+
+class UnicodeData {
+ private:
+  friend class Test;
+  static int GetByteCount();
+  static uchar kMaxCodePoint;
+};
+
+// --- U t f   8 ---
+
+template <typename Data>
+class Buffer {
+ public:
+  inline Buffer(Data data, unsigned length) : data_(data), length_(length) { }
+  inline Buffer() : data_(0), length_(0) { }
+  Data data() { return data_; }
+  unsigned length() { return length_; }
+ private:
+  Data data_;
+  unsigned length_;
+};
+
+class Utf8 {
+ public:
+  static inline uchar Length(uchar chr);
+  static inline unsigned Encode(char* out, uchar c);
+  static const byte* ReadBlock(Buffer<const char*> str, byte* buffer,
+      unsigned capacity, unsigned* chars_read, unsigned* offset);
+  static uchar CalculateValue(const byte* str,
+                              unsigned length,
+                              unsigned* cursor);
+  static const uchar kBadChar = 0xFFFD;
+  static const unsigned kMaxEncodedSize   = 4;
+  static const unsigned kMaxOneByteChar   = 0x7f;
+  static const unsigned kMaxTwoByteChar   = 0x7ff;
+  static const unsigned kMaxThreeByteChar = 0xffff;
+  static const unsigned kMaxFourByteChar  = 0x1fffff;
+
+ private:
+  template <unsigned s> friend class Utf8InputBuffer;
+  friend class Test;
+  static inline uchar ValueOf(const byte* str,
+                              unsigned length,
+                              unsigned* cursor);
+};
+
+// --- C h a r a c t e r   S t r e a m ---
+
+class CharacterStream {
+ public:
+  inline uchar GetNext();
+  inline bool has_more() { return remaining_ != 0; }
+  // Note that default implementation is not efficient.
+  virtual void Seek(unsigned);
+  unsigned Length();
+  virtual ~CharacterStream() { }
+  static inline bool EncodeCharacter(uchar c, byte* buffer, unsigned capacity,
+      unsigned& offset);
+  static inline bool EncodeAsciiCharacter(uchar c, byte* buffer,
+      unsigned capacity, unsigned& offset);
+  static inline bool EncodeNonAsciiCharacter(uchar c, byte* buffer,
+      unsigned capacity, unsigned& offset);
+  static inline uchar DecodeCharacter(const byte* buffer, unsigned* offset);
+  virtual void Rewind() = 0;
+ protected:
+  virtual void FillBuffer() = 0;
+  // The number of characters left in the current buffer
+  unsigned remaining_;
+  // The current offset within the buffer
+  unsigned cursor_;
+  // The buffer containing the decoded characters.
+  const byte* buffer_;
+};
+
+// --- I n p u t   B u f f e r ---
+
+/**
+ * Provides efficient access to encoded characters in strings.  It
+ * does so by reading characters one block at a time, rather than one
+ * character at a time, which gives string implementations an
+ * opportunity to optimize the decoding.
+ */
+template <class Reader, class Input = Reader*, unsigned kSize = 256>
+class InputBuffer : public CharacterStream {
+ public:
+  virtual void Rewind();
+  inline void Reset(Input input);
+  void Seek(unsigned position);
+  inline void Reset(unsigned position, Input input);
+ protected:
+  InputBuffer() { }
+  explicit InputBuffer(Input input) { Reset(input); }
+  virtual void FillBuffer();
+
+  // A custom offset that can be used by the string implementation to
+  // mark progress within the encoded string.
+  unsigned offset_;
+  // The input string
+  Input input_;
+  // To avoid heap allocation, we keep an internal buffer to which
+  // the encoded string can write its characters.  The string
+  // implementation is free to decide whether it wants to use this
+  // buffer or not.
+  byte util_buffer_[kSize];
+};
+
+// --- U t f 8   I n p u t   B u f f e r ---
+
+template <unsigned s = 256>
+class Utf8InputBuffer : public InputBuffer<Utf8, Buffer<const char*>, s> {
+ public:
+  inline Utf8InputBuffer() { }
+  inline Utf8InputBuffer(const char* data, unsigned length);
+  inline void Reset(const char* data, unsigned length) {
+    InputBuffer<Utf8, Buffer<const char*>, s>::Reset(
+        Buffer<const char*>(data, length));
+  }
+};
+
+
+struct Uppercase {
+  static bool Is(uchar c);
+};
+struct Lowercase {
+  static bool Is(uchar c);
+};
+struct Letter {
+  static bool Is(uchar c);
+};
+struct Space {
+  static bool Is(uchar c);
+};
+struct Number {
+  static bool Is(uchar c);
+};
+struct WhiteSpace {
+  static bool Is(uchar c);
+};
+struct LineTerminator {
+  static bool Is(uchar c);
+};
+struct CombiningMark {
+  static bool Is(uchar c);
+};
+struct ConnectorPunctuation {
+  static bool Is(uchar c);
+};
+struct ToLowercase {
+  static const int kMaxWidth = 3;
+  static int Convert(uchar c,
+                     uchar n,
+                     uchar* result,
+                     bool* allow_caching_ptr);
+};
+struct ToUppercase {
+  static const int kMaxWidth = 3;
+  static int Convert(uchar c,
+                     uchar n,
+                     uchar* result,
+                     bool* allow_caching_ptr);
+};
+struct Ecma262Canonicalize {
+  static const int kMaxWidth = 1;
+  static int Convert(uchar c,
+                     uchar n,
+                     uchar* result,
+                     bool* allow_caching_ptr);
+};
+struct Ecma262UnCanonicalize {
+  static const int kMaxWidth = 4;
+  static int Convert(uchar c,
+                     uchar n,
+                     uchar* result,
+                     bool* allow_caching_ptr);
+};
+struct CanonicalizationRange {
+  static const int kMaxWidth = 1;
+  static int Convert(uchar c,
+                     uchar n,
+                     uchar* result,
+                     bool* allow_caching_ptr);
+};
+
+}  // namespace unibrow
+
+#endif  // V8_UNICODE_H_

data/ext/v8/upstream/3.1.8/src/uri.js

@@ -0,0 +1,402 @@
+// Copyright 2006-2008 the V8 project authors. All rights reserved.
+// Redistribution and use in source and binary forms, with or without
+// modification, are permitted provided that the following conditions are
+// met:
+//
+//     * Redistributions of source code must retain the above copyright
+//       notice, this list of conditions and the following disclaimer.
+//     * Redistributions in binary form must reproduce the above
+//       copyright notice, this list of conditions and the following
+//       disclaimer in the documentation and/or other materials provided
+//       with the distribution.
+//     * Neither the name of Google Inc. nor the names of its
+//       contributors may be used to endorse or promote products derived
+//       from this software without specific prior written permission.
+//
+// THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS
+// "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
+// LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR
+// A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT
+// OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL,
+// SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT
+// LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE,
+// DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY
+// THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
+// (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
+// OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
+
+// This file contains support for URI manipulations written in
+// JavaScript.
+
+// Expect $String = global.String;
+
+// Lazily initialized.
+var hexCharArray = 0;
+var hexCharCodeArray = 0;
+
+
+function URIAddEncodedOctetToBuffer(octet, result, index) {
+  result[index++] = 37; // Char code of '%'.
+  result[index++] = hexCharCodeArray[octet >> 4];
+  result[index++] = hexCharCodeArray[octet & 0x0F];
+  return index;
+}
+
+
+function URIEncodeOctets(octets, result, index) {
+  if (hexCharCodeArray === 0) {
+    hexCharCodeArray = [48, 49, 50, 51, 52, 53, 54, 55, 56, 57,
+                        65, 66, 67, 68, 69, 70];
+  }
+  index = URIAddEncodedOctetToBuffer(octets[0], result, index);
+  if (octets[1]) index = URIAddEncodedOctetToBuffer(octets[1], result, index);
+  if (octets[2]) index = URIAddEncodedOctetToBuffer(octets[2], result, index);
+  if (octets[3]) index = URIAddEncodedOctetToBuffer(octets[3], result, index);
+  return index;
+}
+
+
+function URIEncodeSingle(cc, result, index) {
+  var x = (cc >> 12) & 0xF;
+  var y = (cc >> 6) & 63;
+  var z = cc & 63;
+  var octets = new $Array(3);
+  if (cc <= 0x007F) {
+    octets[0] = cc;
+  } else if (cc <= 0x07FF) {
+    octets[0] = y + 192;
+    octets[1] = z + 128;
+  } else {
+    octets[0] = x + 224;
+    octets[1] = y + 128;
+    octets[2] = z + 128;
+  }
+  return URIEncodeOctets(octets, result, index);
+}
+
+
+function URIEncodePair(cc1 , cc2, result, index) {
+  var u = ((cc1 >> 6) & 0xF) + 1;
+  var w = (cc1 >> 2) & 0xF;
+  var x = cc1 & 3;
+  var y = (cc2 >> 6) & 0xF;
+  var z = cc2 & 63;
+  var octets = new $Array(4);
+  octets[0] = (u >> 2) + 240;
+  octets[1] = (((u & 3) << 4) | w) + 128;
+  octets[2] = ((x << 4) | y) + 128;
+  octets[3] = z + 128;
+  return URIEncodeOctets(octets, result, index);
+}
+
+
+function URIHexCharsToCharCode(highChar, lowChar) {
+  var highCode = HexValueOf(highChar);
+  var lowCode = HexValueOf(lowChar);
+  if (highCode == -1 || lowCode == -1) {
+    throw new $URIError("URI malformed");
+  }
+  return (highCode << 4) | lowCode;
+}
+
+
+function URIDecodeOctets(octets, result, index) {
+  var value;
+  var o0 = octets[0];
+  if (o0 < 0x80) {
+    value = o0;
+  } else if (o0 < 0xc2) {
+    throw new $URIError("URI malformed");
+  } else {
+    var o1 = octets[1];
+    if (o0 < 0xe0) {
+      var a = o0 & 0x1f;
+      if ((o1 < 0x80) || (o1 > 0xbf))
+        throw new $URIError("URI malformed");
+      var b = o1 & 0x3f;
+      value = (a << 6) + b;
+      if (value < 0x80 || value > 0x7ff)
+        throw new $URIError("URI malformed");
+    } else {
+      var o2 = octets[2];
+      if (o0 < 0xf0) {
+        var a = o0 & 0x0f;
+        if ((o1 < 0x80) || (o1 > 0xbf))
+          throw new $URIError("URI malformed");
+        var b = o1 & 0x3f;
+        if ((o2 < 0x80) || (o2 > 0xbf))
+          throw new $URIError("URI malformed");
+        var c = o2 & 0x3f;
+        value = (a << 12) + (b << 6) + c;
+        if ((value < 0x800) || (value > 0xffff))
+          throw new $URIError("URI malformed");
+      } else {
+        var o3 = octets[3];
+        if (o0 < 0xf8) {
+          var a = (o0 & 0x07);
+          if ((o1 < 0x80) || (o1 > 0xbf))
+            throw new $URIError("URI malformed");
+          var b = (o1 & 0x3f);
+          if ((o2 < 0x80) || (o2 > 0xbf))
+            throw new $URIError("URI malformed");
+          var c = (o2 & 0x3f);
+          if ((o3 < 0x80) || (o3 > 0xbf))
+            throw new $URIError("URI malformed");
+          var d = (o3 & 0x3f);
+          value = (a << 18) + (b << 12) + (c << 6) + d;
+          if ((value < 0x10000) || (value > 0x10ffff))
+            throw new $URIError("URI malformed");
+        } else {
+          throw new $URIError("URI malformed");
+        }
+      }
+    }
+  }
+  if (value < 0x10000) {
+    result[index++] = value;
+    return index;
+  } else {
+    result[index++] = (value >> 10) + 0xd7c0;
+    result[index++] = (value & 0x3ff) + 0xdc00;
+    return index;
+  }
+}
+
+
+// ECMA-262, section 15.1.3
+function Encode(uri, unescape) {
+  var uriLength = uri.length;
+  var result = new $Array(uriLength);
+  var index = 0;
+  for (var k = 0; k < uriLength; k++) {
+    var cc1 = uri.charCodeAt(k);
+    if (unescape(cc1)) {
+      result[index++] = cc1;
+    } else {
+      if (cc1 >= 0xDC00 && cc1 <= 0xDFFF) throw new $URIError("URI malformed");
+      if (cc1 < 0xD800 || cc1 > 0xDBFF) {
+        index = URIEncodeSingle(cc1, result, index);
+      } else {
+        k++;
+        if (k == uriLength) throw new $URIError("URI malformed");
+        var cc2 = uri.charCodeAt(k);
+        if (cc2 < 0xDC00 || cc2 > 0xDFFF) throw new $URIError("URI malformed");
+        index = URIEncodePair(cc1, cc2, result, index);
+      }
+    }
+  }
+  return %StringFromCharCodeArray(result);
+}
+
+
+// ECMA-262, section 15.1.3
+function Decode(uri, reserved) {
+  var uriLength = uri.length;
+  var result = new $Array(uriLength);
+  var index = 0;
+  for (var k = 0; k < uriLength; k++) {
+    var ch = uri.charAt(k);
+    if (ch == '%') {
+      if (k + 2 >= uriLength) throw new $URIError("URI malformed");
+      var cc = URIHexCharsToCharCode(uri.charCodeAt(++k), uri.charCodeAt(++k));
+      if (cc >> 7) {
+        var n = 0;
+        while (((cc << ++n) & 0x80) != 0) ;
+        if (n == 1 || n > 4) throw new $URIError("URI malformed");
+        var octets = new $Array(n);
+        octets[0] = cc;
+        if (k + 3 * (n - 1) >= uriLength) throw new $URIError("URI malformed");
+        for (var i = 1; i < n; i++) {
+          if (uri.charAt(++k) != '%') throw new $URIError("URI malformed");
+          octets[i] = URIHexCharsToCharCode(uri.charCodeAt(++k), uri.charCodeAt(++k));
+        }
+        index = URIDecodeOctets(octets, result, index);
+      } else {
+        if (reserved(cc)) {
+          result[index++] = 37; // Char code of '%'.
+          result[index++] = uri.charCodeAt(k - 1);
+          result[index++] = uri.charCodeAt(k);
+        } else {
+          result[index++] = cc;
+        }
+      }
+    } else {
+      result[index++] = ch.charCodeAt(0);
+    }
+  }
+  result.length = index;
+  return %StringFromCharCodeArray(result);
+}
+
+
+// ECMA-262 - 15.1.3.1.
+function URIDecode(uri) {
+  function reservedPredicate(cc) {
+    // #$
+    if (35 <= cc && cc <= 36) return true;
+    // &
+    if (cc == 38) return true;
+    // +,
+    if (43 <= cc && cc <= 44) return true;
+    // /
+    if (cc == 47) return true;
+    // :;
+    if (58 <= cc && cc <= 59) return true;
+    // =
+    if (cc == 61) return true;
+    // ?@
+    if (63 <= cc && cc <= 64) return true;
+
+    return false;
+  };
+  var string = ToString(uri);
+  return Decode(string, reservedPredicate);
+}
+
+
+// ECMA-262 - 15.1.3.2.
+function URIDecodeComponent(component) {
+  function reservedPredicate(cc) { return false; };
+  var string = ToString(component);
+  return Decode(string, reservedPredicate);
+}
+
+
+// Does the char code correspond to an alpha-numeric char.
+function isAlphaNumeric(cc) {
+  // a - z
+  if (97 <= cc && cc <= 122) return true;
+  // A - Z
+  if (65 <= cc && cc <= 90) return true;
+  // 0 - 9
+  if (48 <= cc && cc <= 57) return true;
+
+  return false;
+}
+
+
+// ECMA-262 - 15.1.3.3.
+function URIEncode(uri) {
+  function unescapePredicate(cc) {
+    if (isAlphaNumeric(cc)) return true;
+    // !
+    if (cc == 33) return true;
+    // #$
+    if (35 <= cc && cc <= 36) return true;
+    // &'()*+,-./
+    if (38 <= cc && cc <= 47) return true;
+    // :;
+    if (58 <= cc && cc <= 59) return true;
+    // =
+    if (cc == 61) return true;
+    // ?@
+    if (63 <= cc && cc <= 64) return true;
+    // _
+    if (cc == 95) return true;
+    // ~
+    if (cc == 126) return true;
+
+    return false;
+  };
+
+  var string = ToString(uri);
+  return Encode(string, unescapePredicate);
+}
+
+
+// ECMA-262 - 15.1.3.4
+function URIEncodeComponent(component) {
+  function unescapePredicate(cc) {
+    if (isAlphaNumeric(cc)) return true;
+    // !
+    if (cc == 33) return true;
+    // '()*
+    if (39 <= cc && cc <= 42) return true;
+    // -.
+    if (45 <= cc && cc <= 46) return true;
+    // _
+    if (cc == 95) return true;
+    // ~
+    if (cc == 126) return true;
+
+    return false;
+  };
+
+  var string = ToString(component);
+  return Encode(string, unescapePredicate);
+}
+
+
+function HexValueOf(code) {
+  // 0-9
+  if (code >= 48 && code <= 57) return code - 48;
+  // A-F
+  if (code >= 65 && code <= 70) return code - 55;
+  // a-f
+  if (code >= 97 && code <= 102) return code - 87;
+
+  return -1;
+}
+
+
+// Convert a character code to 4-digit hex string representation
+// 64 -> 0040, 62234 -> F31A.
+function CharCodeToHex4Str(cc) {
+  var r = "";
+  if (hexCharArray === 0) {
+    hexCharArray = ["0", "1", "2", "3", "4", "5", "6", "7", "8", "9",
+                    "A", "B", "C", "D", "E", "F"];
+  }
+  for (var i = 0; i < 4; ++i) {
+    var c = hexCharArray[cc & 0x0F];
+    r = c + r;
+    cc = cc >>> 4;
+  }
+  return r;
+}
+
+
+// Returns true if all digits in string s are valid hex numbers
+function IsValidHex(s) {
+  for (var i = 0; i < s.length; ++i) {
+    var cc = s.charCodeAt(i);
+    if ((48 <= cc && cc <= 57) || (65 <= cc && cc <= 70) || (97 <= cc && cc <= 102)) {
+      // '0'..'9', 'A'..'F' and 'a' .. 'f'.
+    } else {
+      return false;
+    }
+  }
+  return true;
+}
+
+
+// ECMA-262 - B.2.1.
+function URIEscape(str) {
+  var s = ToString(str);
+  return %URIEscape(s);
+}
+
+
+// ECMA-262 - B.2.2.
+function URIUnescape(str) {
+  var s = ToString(str);
+  return %URIUnescape(s);
+}
+
+
+// -------------------------------------------------------------------
+
+function SetupURI() {
+  // Setup non-enumerable URI functions on the global object and set
+  // their names.
+  InstallFunctions(global, DONT_ENUM, $Array(
+    "escape", URIEscape,
+    "unescape", URIUnescape,
+    "decodeURI", URIDecode,
+    "decodeURIComponent", URIDecodeComponent,
+    "encodeURI", URIEncode,
+    "encodeURIComponent", URIEncodeComponent
+  ));
+}
+
+SetupURI();