html 转义 c,[C/C++]_[HTML特殊字符转义成正常字符] | 学步园

场景:

1.在没有HTML库时(谁有好的html库介绍下,C/C++的？tinyXML?),以SAX方式解析HTML时,会读入特殊字符,这时候需要转义成正常字符才能使用。

2.耗时，4-6小时(被打扰)。

3.replace虽然挺好,但是会循环整个字符串执行替换,效率应该没有一次过替换高.

#include

void replace( iterator start, iterator end, const TYPE& old_value, const TYPE& new_value );

4.所有转义字符的网址:

文件1：test_htmlescape.cpp

#include

#include

#include

#include

#include

using namespace std;

int IsLittleEndian()

{

int x = 1;

if (*(char*) &x == 1)

{

return 1;

}

else

{

return 0;

}

}

void HtmEscapeEntityCodeToUnicode(const char* entity_code,char* html_char)

{

int decimal_value = atoi(entity_code);

char* uchari = (char*)&decimal_value;

if(IsLittleEndian())

{

html_char[0] = uchari[0] & 0xFF;

html_char[1] = uchari[1] & 0xFF;

}else

{

html_char[0] = uchari[1] & 0xFF;

html_char[1] = uchari[0] & 0xFF;

}

}

void OneUnicode2UTF8(const char* unicode_char,size_t unicode_char_length,

char* utf_char)

{

//unicode: 0x192->110010010 ,utf8:0xC692->1100011010010010

int value = 0;

memcpy(&value,unicode_char,unicode_char_length);

if (value >= 0x0000 && value <= 0x007F)

{

utf_char[0] = unicode_char[0];

}

else if (value >= 0x0080 && value <= 0x07FF)

{

utf_char[0] = ((value >> 6) | 0xC0);

utf_char[1] = ((value & 0x3F) | 0x80);

}

else if (value >= 0x0800 && value <= 0xFFFF)

{

utf_char[0] = ((value >> 12) | 0xE0);

utf_char[1] = ((value >> 6 & 0x3F) | 0x80);

utf_char[2] = ((value & 0x3F) | 0x80);

}

else if (value >= 0x10000 && value <= 0x10FFFF)

{

utf_char[0] = (value >> 18 | 0xF0);

utf_char[1] = ((value >> 12 & 0x3F) | 0x80);

utf_char[2] = ((value >> 6 & 0x3F) | 0x80);

utf_char[3] = ((value & 0x3F) | 0x80);

}

else

{

cerr << "value too big." << endl;

assert(0);

}

}

static const char* kEntityNameToEntityCodeMap[] =

{

"oelig","339","amp","38","rArr","8658","fnof","402"

};

//1.这里可以优化的余地很大.

const char* HtmEscapeEntityNameToEntityCode(const char* entity_name)

{

static size_t length = sizeof(kEntityNameToEntityCodeMap)/sizeof(char*);

for(size_t i = 0; i < length; i+=2)

{

if(!strcmp(entity_name,kEntityNameToEntityCodeMap[i]))

{

return kEntityNameToEntityCodeMap[i+1];

}

}

return NULL;

}

string UnescapeUTFHTMLContent(const char* str)

{

string temp;

char* pos_amp = NULL;

char* pos_semicolon = (char*)str;

const char* start_amp = str;

int entity_length = 0;

char entity_code[5];

const int kMaxEntityLength = 4;

char entity_name[20];

const int kMaxEntityNameLength = 18;

char unicode[3];

char utf8[4];

while(true)

{

if(!start_amp || !(*start_amp))

{

break;

}

pos_amp = strchr(start_amp,'&');

if(!pos_amp)

{

temp.append(start_amp);

break;

}

int pos_no = pos_amp - pos_semicolon;

if(pos_no > 0)

{

temp.append(start_amp,pos_no);

start_amp = pos_amp;

}

char* pos_amp1 = pos_amp+1;

if(!pos_amp1 || !(*pos_amp1))

{

string t2(start_amp);

temp.append(start_amp);

break;

}

if(isalpha(*pos_amp1))

{

pos_semicolon = strchr(pos_amp1,';');

if(pos_semicolon)

{

//调用 HtmEscapeEntityNameToEntityCode

memset(entity_name,0,sizeof(entity_name));

entity_length = ((pos_semicolon - pos_amp1) >

kMaxEntityNameLength)?kMaxEntityNameLength:

(pos_semicolon - pos_amp1);

strncpy(entity_name,pos_amp1,entity_length);

const char* entity_code_c =

HtmEscapeEntityNameToEntityCode(entity_name);

if(entity_code_c)

{

memset(unicode,0,sizeof(unicode));

memset(utf8,0,sizeof(utf8));

HtmEscapeEntityCodeToUnicode(entity_code_c,unicode);

OneUnicode2UTF8(unicode,2,utf8);

temp.append(utf8);

}else

{

temp.append(entity_name);

}

//1.entity_name转换为entity_code之后再转换为utf8字符.

start_amp = pos_semicolon + 1;

pos_semicolon+=1;

}else

{

start_amp = pos_amp1;

}

}else if(*pos_amp1 =='#')

{

char* pos_digit = (pos_amp1+1);

if(!pos_digit)

{

break;

}

if(isdigit(*pos_digit))

{

//1.需要判断数值小于10000.

pos_semicolon = strchr(start_amp,';');

if(pos_semicolon)

{

memset(entity_code,0,sizeof(entity_code));

entity_length = ((pos_semicolon - pos_digit) >

kMaxEntityLength)?kMaxEntityLength:

(pos_semicolon - pos_digit);

strncpy(entity_code,pos_digit,entity_length);

memset(unicode,0,sizeof(unicode));

memset(utf8,0,sizeof(utf8));

HtmEscapeEntityCodeToUnicode(entity_code,unicode);

OneUnicode2UTF8(unicode,2,utf8);

temp.append(utf8);

start_amp = pos_semicolon + 1;

pos_semicolon+=1;

}else

{

start_amp = pos_digit;

}

}

}else

{

string sa(start_amp,pos_amp1 - start_amp);

temp.append(sa);

start_amp = pos_amp1;

}

}

return temp;

}

int main(int argc, char *argv[])

{

printf("Hello, world\n");

string str;

const char *html_str = "ΖabcdΕhello©⇒⇒"

"ƒ…"

    "asfas‡dfeΥΨΩn↓n⋅nωmmm1jh";

str = UnescapeUTFHTMLContent(html_str);

cout << "str: " << str << endl;

html_str = "

&#8736;";

str = UnescapeUTFHTMLContent(html_str);

cout << "str: " << str << endl;

html_str = "

&#8736;;;#8736;";

str = UnescapeUTFHTMLContent(html_str);

cout << "str: " << str << endl;

html_str = "

&#8736;;&";

str = UnescapeUTFHTMLContent(html_str);

cout << "str: " << str << endl;

html_str = "

&#8736;;&amp";

str = UnescapeUTFHTMLContent(html_str);

cout << "str: " << str << endl;

html_str = "

&#8736;;&";

str = UnescapeUTFHTMLContent(html_str);

cout << "str1: " << str << endl;

html_str = "ab";

str = UnescapeUTFHTMLContent(html_str);

cout << "ab: " << str << endl;

return 0;

}

str: ΖabcdΕhello©⇒⇒ƒ…asfas‡dfeΥPsiΩn↓nsdotnωmmm1jh

str:

∠

str:

∠;;#8736;

str:

∠;&

str:

∠;amp

str1:

∠;&

ab: ab