前些时间做 xauth
认证程序的编写,网上找到RFC3986编码不支持中文的编码,所以便查找了一些资料.自己写了一个,代码如下.
#include <stdlib.h>
#include <string.h>
#include <stdio.h>
#include <android/log.h>
#include "RFC3986Encoder.h"bool isReverseChar(char c);
char* charToHexString(char c);
bool isChinese(char c);//#define snprintf _snprintf
/**
* Escape ‘string‘ according to RFC3986 and
* http://oauth.net/core/1.0/#encoding_parameters.
*
* @param string The data to be encoded
* @return encoded string otherwise NULL
* The caller must free the returned string.
*/static void *xmalloc_fatal(size_t size) {
if (size==0) return NULL;
fprintf(stderr, "Out of memory.");
exit(1);
}void *xrealloc (void *ptr, size_t size) {
void *p = realloc (ptr, size);
if (p == NULL) return xmalloc_fatal(size);
return p;
}void *xmalloc (size_t size) {
void *ptr = malloc (size);
if (ptr == NULL) return xmalloc_fatal(size);
return ptr;
}char *xstrdup (const char *s) {
void *ptr = xmalloc(strlen(s)+1);
strcpy((char *)ptr, s);
return (char*)ptr;
}char *oauth_url_escape(const char *string) {
size_t alloc, newlen;
char *ns = NULL, *testing_ptr = NULL;
unsigned char in;
size_t strindex=0;
size_t length;if (!string) return xstrdup("");
alloc = strlen(string)+1;
newlen = alloc;ns = (char*) xmalloc(alloc);
length = alloc-1;
while(length--) {
in = *string;switch(in){
case ‘0‘: case ‘1‘: case ‘2‘: case ‘3‘: case ‘4‘:
case ‘5‘: case ‘6‘: case ‘7‘: case ‘8‘: case ‘9‘:
case ‘a‘: case ‘b‘: case ‘c‘: case ‘d‘: case ‘e‘:
case ‘f‘: case ‘g‘: case ‘h‘: case ‘i‘: case ‘j‘:
case ‘k‘: case ‘l‘: case ‘m‘: case ‘n‘: case ‘o‘:
case ‘p‘: case ‘q‘: case ‘r‘: case ‘s‘: case ‘t‘:
case ‘u‘: case ‘v‘: case ‘w‘: case ‘x‘: case ‘y‘: case ‘z‘:
case ‘A‘: case ‘B‘: case ‘C‘: case ‘D‘: case ‘E‘:
case ‘F‘: case ‘G‘: case ‘H‘: case ‘I‘: case ‘J‘:
case ‘K‘: case ‘L‘: case ‘M‘: case ‘N‘: case ‘O‘:
case ‘P‘: case ‘Q‘: case ‘R‘: case ‘S‘: case ‘T‘:
case ‘U‘: case ‘V‘: case ‘W‘: case ‘X‘: case ‘Y‘: case ‘Z‘:
case ‘_‘: case ‘~‘: case ‘.‘: case ‘-‘:
ns[strindex++]=in;
break;
default:
newlen += 2; /* this‘ll become a %XX */
if(newlen > alloc) {
alloc *= 2;
testing_ptr = (char*) xrealloc(ns, alloc);
ns = testing_ptr;
}//转换成16进制. 58-->3A
//%3A 这是3个.这里好像是自动 加 ‘/0‘ 如果生成的的字符串,大于4则不会,自动加/0
//在linux 下,这个方法,的count 包括 ‘/0‘所以最后的结果也是正确的.int result = snprintf(&ns[strindex], 4, "%%%02X", in);
/*
printf("%d\n",result);printf("%d\n",in);
printf("strlen(buf) = %d\n",strlen(ns));
printf("%s\n",ns);
*/strindex+=3;
break;
}
string++;
}
ns[strindex]=0;
return ns;
}#ifndef ISXDIGIT
# define ISXDIGIT(x) (isxdigit((int) ((unsigned char)x)))
#endif//自己写的代码 3
char* rfc3986Encoder(const char* input)
{
//__android_log_print(ANDROID_LOG_INFO, "Test_jni","encoder start %s\n", input);if (!input) return xstrdup("");
//char* sb = (char*)malloc(1024);
char* sb = new char[1024];
sb[0]= ‘\0‘;
int length = strlen(input);
for (int i = 0; i<length; i++)
{
char c = input[i];
if(isReverseChar(c)){
const char* temp;
if(isChinese(c))
{
//这里认为汉字 utf-8为三字节,首位为连续三个1,取unicode的后8位
//这里相于 utf-8 到 unicode 的转换,只是转换了后8位.
int high = (input[i+1]&0x03)<<6;
int low = input[i+2]&0x3f;
char chinese = (high+low)&0xff;
temp = charToHexString(chinese);
i+=2;
}else{
temp = charToHexString(c);
}
strcat(sb,temp);
}
else{
int len = strlen(sb);
const char* p = &c; //字符看不到结束符,所以会错.
strcat(sb,p);
sb[len+1] = ‘\0‘;
}
}
//__android_log_print(ANDROID_LOG_INFO, "Test_jni","encoder end %s\n", sb);
return sb;
}bool isReverseChar(char c)
{
return !((c >= ‘a‘ && c <= ‘z‘) || (c >= ‘A‘ && c <= ‘Z‘) || (c >= ‘0‘ && c <= ‘9‘)
|| c == ‘-‘ || c == ‘_‘ || c == ‘.‘ || c == ‘~‘);
}char* charToHexString(char src){
int v = src & 0xFF;
char* hv = new char[4];
snprintf(hv, 4,"%%%02X",v);
return hv ;
}
bool isChinese(char c)
{
int x = c&0xE0;
if(x == 224)
return true;
else
return false;
}
如程序中体现的,oauth_url_escape() 这个方法不支持对中文的编码
,所以我便另外写了个方法 rfc3986Encoder().如程序中所说,我这里认为UTF8 汉字为 3
byte ,所以已经包含了大部分的汉字.具体的参考资料当时没做笔记,大该就是关于 UTF8 汉字编码的问题.程序思想,也比较好懂.研读java
的RFC3986编码实现,发现其获取utf8汉字的编码实际为unicode 编码的后8位.所以我这里把 utf8 向 unicode
编码的转化,只取了后8位,再转换成 hex 的形式.代码我做了部分测试,目前还没有发现什么问题.
RFC3986编码 C 语言实现(支持大部分中文),布布扣,bubuko.com