URL编码解码类

URL编码分为ansii和utf8 同时这两种又分为是否编码空格等等，为了方便使用封装此类

头文件：

#ifndef _URLENCODE_H_
#define _URLENCODE_H_ 

#include <string>

// Decode all encoded characters. Also decode + as space.
int UrlDecode(const char *source, char *dest, unsigned max);
int UrlDecodeUTF8(const char *source, char *dest, unsigned max);

// Decode all encoded characters.
int UrlDecodeWithoutEncodingSpaceAsPlus(const char *source, char *dest,
	                                    unsigned max);
int UrlDecodeWithoutEncodingSpaceAsPlusUTF8(const char *source, char *dest,
	                                    unsigned max);

// Encode all characters except alphas, numbers, and -_.!~*'()
// Also encode space as +.
int UrlEncode(const char *source, char *dest, unsigned max);
int UrlEncodeUTF8(const char *source, char *dest, unsigned max);

// Encode all characters except alphas, numbers, and -_.!~*'()
int UrlEncodeWithoutEncodingSpaceAsPlus(const char *source, char *dest,
                                        unsigned max);
int UrlEncodeWithoutEncodingSpaceAsPlusUTF8(const char *source, char *dest,
	                                    unsigned max);

// Encode only unsafe chars, including \ "^&`<>[]{}
// Also encode space as %20, instead of +
int UrlEncodeOnlyUnsafeChars(const char *source, char *dest, unsigned max);
int UrlEncodeOnlyUnsafeCharsUTF8(const char *source, char *dest, unsigned max);

std::string UrlDecodeString(const std::string & encoded);
std::string UrlDecodeStringUTF8(const std::string & encoded);
std::string UrlDecodeStringWithoutEncodingSpaceAsPlus(
    const std::string & encoded);
std::string UrlDecodeStringWithoutEncodingSpaceAsPlusUTF8(
	const std::string & encoded);
std::string UrlEncodeString(const std::string & decoded);
std::string UrlEncodeStringUTF8(const std::string & decoded);
std::string UrlEncodeStringWithoutEncodingSpaceAsPlus(
    const std::string & decoded);
std::string UrlEncodeStringWithoutEncodingSpaceAsPlusUTF8(
	const std::string & decoded);
std::string UrlEncodeStringForOnlyUnsafeChars(const std::string & decoded);
std::string UrlEncodeStringForOnlyUnsafeCharsUTF8(const std::string & decoded);

#endif

　

源文件：

#include "urlencode.h"

#include <assert.h>
#include <Windows.h>

//#define STACK_ARRAY(TYPE, LEN) static_cast<TYPE*>(::alloca((LEN)*sizeof(TYPE)))

// Do not assert in this function since it is used by the asssertion code!
std::wstring SysMultiByteToWide(const std::string& mb, unsigned int code_page) {
	if (mb.empty())
		return std::wstring();

	int mb_length = static_cast<int>(mb.length());
	// Compute the length of the buffer.
	int charcount = MultiByteToWideChar(code_page, 0,
		mb.data(), mb_length, NULL, 0);
	if (charcount == 0)
		return std::wstring();

	std::wstring wide;
	wide.resize(charcount);
	MultiByteToWideChar(code_page, 0, mb.data(), mb_length, &wide[0], charcount);

	return wide;
}

// Do not assert in this function since it is used by the asssertion code!
std::string SysWideToMultiByte(const std::wstring& wide, unsigned int code_page) {
	int wide_length = static_cast<int>(wide.length());
	if (wide_length == 0)
		return std::string();

	// Compute the length of the buffer we'll need.
	int charcount = WideCharToMultiByte(code_page, 0, wide.data(), wide_length,
		NULL, 0, NULL, NULL);
	if (charcount == 0)
		return std::string();

	std::string mb;
	mb.resize(charcount);
	WideCharToMultiByte(code_page, 0, wide.data(), wide_length,
		&mb[0], charcount, NULL, NULL);

	return mb;
}

// Do not assert in this function since it is used by the asssertion code!
std::string SysWideToUTF8(const std::wstring& wide) {
	return SysWideToMultiByte(wide, CP_UTF8);
}

// Do not assert in this function since it is used by the asssertion code!
std::wstring SysUTF8ToWide(const std::string& utf8) {
	return SysMultiByteToWide(utf8, CP_UTF8);
}

std::string SysWideToNativeMB(const std::wstring& wide) {
	return SysWideToMultiByte(wide, CP_ACP);
}

std::wstring SysNativeMBToWide(const std::string& native_mb) {
	return SysMultiByteToWide(native_mb, CP_ACP);
}

static int HexPairValue(const char * code) {
  int value = 0;
  const char * pch = code;
  for (;;) {
    int digit = *pch++;
    if (digit >= '0' && digit <= '9') {
      value += digit - '0';
    }
    else if (digit >= 'A' && digit <= 'F') {
      value += digit - 'A' + 10;
    }
    else if (digit >= 'a' && digit <= 'f') {
      value += digit - 'a' + 10;
    }
    else {
      return -1;
    }
    if (pch == code + 2)
      return value;
    value <<= 4;
  }
}

int InternalUrlDecode(const char *source, char *dest, unsigned max,
                      bool encode_space_as_plus,
					  bool utf8){
 if (max == 0) {
	return 0;
 }

  char * start = dest;

  while (static_cast<unsigned>(dest - start) < max && *source) {
    switch (*source) {
    case '+':
      if (encode_space_as_plus) {
        *(dest++) = ' ';
      } else {
        *dest++ = *source;
      }
      break;
    case '%':
      if (source[1] && source[2]) {
        int value = HexPairValue(source + 1);
        if (value >= 0) {
          *(dest++) = value;
          source += 2;
        }
        else {
          *dest++ = '?';
        }
      }
      else {
        *dest++ = '?';
      }
      break;
    default:
      *dest++ = *source;
    }
    source++;
  }
//  assert(static_cast<unsigned int>(dest - start) < max);
  *dest = 0;
  int size = static_cast<int>(dest - start);
  if (utf8 && size > 0) {
	  std::wstring wide = SysUTF8ToWide(start);
	  std::string native = SysWideToNativeMB(wide);
	  memcpy(start, native.c_str(), strlen(native.c_str()));
	  *(start + strlen(native.c_str())) = 0;
	  size = strlen(start);
  }
  return size;
}

int UrlDecode(const char *source, char *dest, unsigned max) {
  return InternalUrlDecode(source, dest, max, true, false);
}

int UrlDecodeUTF8(const char *source, char *dest, unsigned max) {
	return InternalUrlDecode(source, dest, max, true, true);
}

int UrlDecodeWithoutEncodingSpaceAsPlus(const char *source, char *dest, unsigned max) {
  return InternalUrlDecode(source, dest, max, false, false);
}

int UrlDecodeWithoutEncodingSpaceAsPlusUTF8(const char *source, char *dest, unsigned max) {
	return InternalUrlDecode(source, dest, max, false, true);
}

bool IsValidUrlChar(char ch, bool unsafe_only) {
  if (unsafe_only) {
    return !(ch <= ' ' || strchr("\\\"^&`<>[]{}", ch));
  } else {  
	  return isalnum((unsigned char)ch) || strchr("-_.!~*'()", ch);
  }
}

int InternalUrlEncode(const char *source, char *dest, unsigned int max,
                      bool encode_space_as_plus, bool unsafe_only, bool utf8) {
  static const char *digits = "0123456789ABCDEF";
  if (max == 0) {
    return 0;
  }

  std::string utf8_source;
  if (utf8) {
	  std::wstring wide = SysNativeMBToWide(source);
	  utf8_source = SysWideToUTF8(wide);
	  source = utf8_source.c_str();
  }

  char *start = dest;
  while (static_cast<unsigned>(dest - start) < max && *source) {
    unsigned char ch = static_cast<unsigned char>(*source);
    if (*source == ' ' && encode_space_as_plus && !unsafe_only) {
      *dest++ = '+';
    } else if (IsValidUrlChar(ch, unsafe_only)) {
      *dest++ = *source;
    } else {
      if (static_cast<unsigned>(dest - start) + 4 > max) {
        break;
      }
      *dest++ = '%';
      *dest++ = digits[(ch >> 4) & 0x0F];
      *dest++ = digits[       ch & 0x0F];
    }
    source++;
  }
  assert(static_cast<unsigned int>(dest - start) < max);
  *dest = 0;

  return static_cast<int>(dest - start);
}

int UrlEncode(const char *source, char *dest, unsigned max) {
  return InternalUrlEncode(source, dest, max, true, false, false);
}

int UrlEncodeUTF8(const char *source, char *dest, unsigned max) {
	return InternalUrlEncode(source, dest, max, true, false, true);
}

int UrlEncodeWithoutEncodingSpaceAsPlus(const char *source, char *dest,
                                        unsigned max) {
  return InternalUrlEncode(source, dest, max, false, false, false);
}

int UrlEncodeWithoutEncodingSpaceAsPlusUTF8(const char *source, char *dest,
	unsigned max) {
	return InternalUrlEncode(source, dest, max, false, false, true);
}

int UrlEncodeOnlyUnsafeChars(const char *source, char *dest, unsigned max) {
  return InternalUrlEncode(source, dest, max, false, true, false);
}

int UrlEncodeOnlyUnsafeCharsUTF8(const char *source, char *dest, unsigned max) {
	return InternalUrlEncode(source, dest, max, false, true, true);
}

std::string
InternalUrlDecodeString(const std::string & encoded,
                        bool encode_space_as_plus,
						bool utf8) {
  size_t needed_length = encoded.length() + 1;
  //char* buf = STACK_ARRAY(char, needed_length);
  std::string buf;
  buf.resize(needed_length);
  InternalUrlDecode(encoded.c_str(), (char*)buf.c_str(), needed_length, encode_space_as_plus, utf8);
  return buf;
}

std::string
UrlDecodeString(const std::string & encoded) {
  return InternalUrlDecodeString(encoded, true, false);
}

std::string
UrlDecodeStringUTF8(const std::string & encoded) {
  return InternalUrlDecodeString(encoded, true, true);
}

std::string
UrlDecodeStringWithoutEncodingSpaceAsPlus(const std::string & encoded) {
  return InternalUrlDecodeString(encoded, false, false);
}

std::string
UrlDecodeStringWithoutEncodingSpaceAsPlusUTF8(const std::string & encoded) {
  return InternalUrlDecodeString(encoded, false, true);
}

std::string
InternalUrlEncodeString(const std::string & decoded,
                        bool encode_space_as_plus,
                        bool unsafe_only,
						bool utf8) {
  int needed_length = static_cast<int>(decoded.length()) * 3 + 1;
  //char* buf = STACK_ARRAY(char, needed_length);
  std::string buf;
  buf.resize(needed_length);
  InternalUrlEncode(decoded.c_str(), (char*)buf.c_str(), needed_length,
                    encode_space_as_plus, unsafe_only, utf8);
  return buf;
}

std::string
UrlEncodeString(const std::string & decoded) {
  return InternalUrlEncodeString(decoded, true, false, false);
}

std::string
UrlEncodeStringUTF8(const std::string & decoded) {
  return InternalUrlEncodeString(decoded, true, false, true);
}

std::string
UrlEncodeStringWithoutEncodingSpaceAsPlus(const std::string & decoded) {
  return InternalUrlEncodeString(decoded, false, false, false);
}

std::string
UrlEncodeStringWithoutEncodingSpaceAsPlusUTF8(const std::string & decoded) {
  return InternalUrlEncodeString(decoded, false, false, true);
}

std::string
UrlEncodeStringForOnlyUnsafeChars(const std::string & decoded) {
  return InternalUrlEncodeString(decoded, false, true, false);
}

std::string
UrlEncodeStringForOnlyUnsafeCharsUTF8(const std::string & decoded) {
return InternalUrlEncodeString(decoded, false, true, true);
}

　　测试源码：

#include "urlencode.h"

#define ARRAY_SIZE(x) (static_cast<int>(sizeof(x) / sizeof(x[0])))

void SourceTooLong() {
	char source[] = "^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^"
		"^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^";
	char dest[1];
	int i =UrlEncode(source, dest, ARRAY_SIZE(dest));
	// ASSERT_EQ('\0', dest[0]);

	dest[0] = 'a';
	i = UrlEncode(source, dest, 0);
	//ASSERT_EQ('a', dest[0]);
}

void OneCharacterConversion() {
	char source[] = "^";
	char dest[4];
	int i = UrlEncode(source, dest, ARRAY_SIZE(dest));//3
	//ASSERT_STREQ("%5E", dest);
}

void ShortDestinationNoEncoding() {
	// In this case we have a destination that would not be
	// big enough to hold an encoding but is big enough to
	// hold the text given.
	char source[] = "aa";
	char dest[3];
	int i = UrlEncode(source, dest, ARRAY_SIZE(dest)); //2
	//ASSERT_STREQ("aa", dest);
}

void ShortDestinationEncoding() {
	// In this case we have a destination that is not
	// big enough to hold the encoding.
	char source[] = "&";
	char dest[3];
	int i = UrlEncode(source, dest, ARRAY_SIZE(dest)); //0
	//ASSERT_EQ('\0', dest[0]);
}

void Encoding1() {
	char* source = "[session=]#中国#china sad_sad@163.com";
	char dest[180];
	int i = UrlEncodeUTF8(source, dest, ARRAY_SIZE(dest)); //5
	std::string dests = UrlEncodeStringWithoutEncodingSpaceAsPlusUTF8(source);
	//ASSERT_STREQ("A%5E+", dest);
}

void Encoding2() {
	char source[] = "A^ ";
	char dest[8];
	int i = UrlEncodeWithoutEncodingSpaceAsPlus(source, dest,
		ARRAY_SIZE(dest)); //i
	//ASSERT_STREQ("A%5E%20", dest);
}

void Decoding1() {
	char source[] = "ed2k://|file|%E5%B0%8F%E5%8E%9F%E5%88%AB%E5%93%AD.Nakuna.Hara-chan.Ep06.Chi_Jap.HDTVrip.1024X576-YYeTs%E4%BA%BA%E4%BA%BA%E5%BD%B1%E8%A7%86.mkv|575452738|a9be9c1cf178805985002437b5782548|h=iqipca7ddjb2osas7s26u5in5ejooaae|/";
	char dest[800];
	int i = UrlDecodeUTF8(source, dest, ARRAY_SIZE(dest)); //3

	std::string dests = UrlDecodeStringUTF8(source);
	//ASSERT_STREQ("A^ ", dest);
}

void Decoding2() {
	char source[] = "A%5E+";
	char dest[8];
	int i = UrlDecodeWithoutEncodingSpaceAsPlus(source, dest, ARRAY_SIZE(dest));//3
	// ASSERT_STREQ("A^+", dest);
}

char s1[] = "女孩";
char s2[] = "BBC.单口喜剧的艺术.第二集.BBC.Imagine.2011.The.Art.of.Stand-up.Chi_Eng.HR-HDTV.AAC.1024X576.x264-YYeTs人人影视.mkv";
char s3[] = "%5B%C9%ED%D4%DA%C6%E4%D6%D0%5D.Inside.2007.x264.720P.DTS.BDRiP-CHD.mkv";
char s4[] = "璀︾晫閲戠.Golden.Boy.S01E01.HDTVrip.x264.鍙岃瀛楀箷-娣卞奖瀛楀箷缁mp4";
char s5[] = "閭伓宕囨嫓.Cult.S01E01.Chi_Eng.HDTVrip.1024X576-YYeTs浜轰汉褰辫.mkv";


int main() {

	std::string st1 = UrlEncodeStringWithoutEncodingSpaceAsPlusUTF8(s1);
	//bool f = IsStringASCII(st1);
	std::string st2 = UrlDecodeString(s1);
	//f = IsStringASCII(st2);
	std::string st3 = UrlDecodeString(s3);
	//f = IsStringASCII(st3);


	//SourceTooLong();
	//OneCharacterConversion();
	//ShortDestinationNoEncoding();
	//ShortDestinationEncoding();
	//Encoding1();
	//Encoding2();
	//Decoding1();
	//Decoding2();
}