curl/lib/curl_escape.c

234 lines
6.4 KiB
C
Raw Normal View History

2002-09-03 13:52:59 +02:00
/***************************************************************************
2004-06-24 16:35:45 +02:00
* _ _ ____ _
* Project ___| | | | _ \| |
* / __| | | | |_) | |
* | (__| |_| | _ <| |___
1999-12-29 15:20:26 +01:00
* \___|\___/|_| \_\_____|
*
* Copyright (C) 1998 - 2013, Daniel Stenberg, <daniel@haxx.se>, et al.
1999-12-29 15:20:26 +01:00
*
2002-09-03 13:52:59 +02:00
* This software is licensed as described in the file COPYING, which
* you should have received as part of this distribution. The terms
* are also available at http://curl.haxx.se/docs/copyright.html.
2004-06-24 16:35:45 +02:00
*
2001-01-03 10:29:33 +01:00
* You may opt to use, copy, modify, merge, publish, distribute and/or sell
* copies of the Software, and permit persons to whom the Software is
2002-09-03 13:52:59 +02:00
* furnished to do so, under the terms of the COPYING file.
1999-12-29 15:20:26 +01:00
*
2001-01-03 10:29:33 +01:00
* This software is distributed on an "AS IS" basis, WITHOUT WARRANTY OF ANY
* KIND, either express or implied.
1999-12-29 15:20:26 +01:00
*
2002-09-03 13:52:59 +02:00
***************************************************************************/
1999-12-29 15:20:26 +01:00
/* Escape and unescape URL encoding in strings. The functions return a new
* allocated string or NULL if an error occurred. */
#include "curl_setup.h"
#include <curl/curl.h>
#include "curl_memory.h"
#include "curl_urldata.h"
#include "curl_warnless.h"
#include "curl_non_ascii.h"
#include "curl_escape.h"
1999-12-29 15:20:26 +01:00
2004-06-24 16:35:45 +02:00
#define _MPRINTF_REPLACE /* use our functions only */
#include <curl/mprintf.h>
2000-10-09 13:12:34 +02:00
/* The last #include file should be: */
#include "curl_memdebug.h"
2000-10-09 13:12:34 +02:00
2008-09-09 23:15:50 +02:00
/* Portable character check (remember EBCDIC). Do not use isalnum() because
its behavior is altered by the current locale.
See http://tools.ietf.org/html/rfc3986#section-2.3
*/
static bool Curl_isunreserved(unsigned char in)
2008-09-09 23:15:50 +02:00
{
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 '~':
2008-09-09 23:15:50 +02:00
return TRUE;
default:
break;
}
return FALSE;
}
/* for ABI-compatibility with previous versions */
char *curl_escape(const char *string, int inlength)
{
return curl_easy_escape(NULL, string, inlength);
}
/* for ABI-compatibility with previous versions */
char *curl_unescape(const char *string, int length)
{
return curl_easy_unescape(NULL, string, length, NULL);
}
char *curl_easy_escape(CURL *handle, const char *string, int inlength)
1999-12-29 15:20:26 +01:00
{
size_t alloc = (inlength?(size_t)inlength:strlen(string))+1;
2004-05-12 15:04:30 +02:00
char *ns;
char *testing_ptr = NULL;
unsigned char in; /* we need to treat the characters unsigned */
2004-03-08 09:38:29 +01:00
size_t newlen = alloc;
size_t strindex=0;
size_t length;
CURLcode res;
1999-12-29 15:20:26 +01:00
2004-05-12 15:04:30 +02:00
ns = malloc(alloc);
if(!ns)
return NULL;
2001-04-07 20:35:28 +02:00
length = alloc-1;
2001-03-22 12:40:58 +01:00
while(length--) {
in = *string;
if(Curl_isunreserved(in))
/* just copy this */
ns[strindex++]=in;
else {
2001-03-22 12:40:58 +01:00
/* encode it */
newlen += 2; /* the size grows with two, since this'll become a %XX */
if(newlen > alloc) {
alloc *= 2;
testing_ptr = realloc(ns, alloc);
if(!testing_ptr) {
free( ns );
return NULL;
}
else {
ns = testing_ptr;
}
}
res = Curl_convert_to_network(handle, &in, 1);
if(res) {
/* Curl_convert_to_network calls failf if unsuccessful */
free(ns);
return NULL;
}
snprintf(&ns[strindex], 4, "%%%02X", in);
strindex+=3;
2001-03-22 12:40:58 +01:00
}
string++;
}
ns[strindex]=0; /* terminate it */
2001-03-22 12:40:58 +01:00
return ns;
1999-12-29 15:20:26 +01:00
}
2008-10-08 03:17:51 +02:00
/*
* Curl_urldecode() URL decodes the given string.
*
* Optionally detects control characters (byte codes lower than 32) in the
* data and rejects such data.
*
* Returns a pointer to a malloced string in *ostring with length given in
* *olen. If length == 0, the length is assumed to be strlen(string).
*
2008-10-08 03:17:51 +02:00
*/
CURLcode Curl_urldecode(struct SessionHandle *data,
const char *string, size_t length,
char **ostring, size_t *olen,
bool reject_ctrl)
1999-12-29 15:20:26 +01:00
{
size_t alloc = (length?length:strlen(string))+1;
2001-03-22 12:40:58 +01:00
char *ns = malloc(alloc);
unsigned char in;
size_t strindex=0;
2010-02-24 01:03:06 +01:00
unsigned long hex;
CURLcode res;
2004-06-24 16:35:45 +02:00
if(!ns)
return CURLE_OUT_OF_MEMORY;
2004-06-24 16:35:45 +02:00
2001-03-22 12:40:58 +01:00
while(--alloc > 0) {
in = *string;
if(('%' == in) && ISXDIGIT(string[1]) && ISXDIGIT(string[2])) {
/* this is two hexadecimal digits following a '%' */
char hexstr[3];
char *ptr;
hexstr[0] = string[1];
hexstr[1] = string[2];
hexstr[2] = 0;
2010-02-24 01:03:06 +01:00
hex = strtoul(hexstr, &ptr, 16);
2010-02-24 01:03:06 +01:00
in = curlx_ultouc(hex); /* this long is never bigger than 255 anyway */
res = Curl_convert_from_network(data, &in, 1);
if(res) {
/* Curl_convert_from_network calls failf if unsuccessful */
free(ns);
return res;
}
string+=2;
alloc-=2;
2001-03-22 12:40:58 +01:00
}
if(reject_ctrl && (in < 0x20)) {
free(ns);
return CURLE_URL_MALFORMAT;
}
2004-06-24 16:35:45 +02:00
ns[strindex++] = in;
2001-03-22 12:40:58 +01:00
string++;
}
ns[strindex]=0; /* terminate it */
if(olen)
/* store output size */
*olen = strindex;
if(ostring)
/* store output string */
*ostring = ns;
return CURLE_OK;
}
/*
* Unescapes the given URL escaped string of given length. Returns a
* pointer to a malloced string with length given in *olen.
* If length == 0, the length is assumed to be strlen(string).
* If olen == NULL, no output length is stored.
*/
char *curl_easy_unescape(CURL *handle, const char *string, int length,
int *olen)
{
char *str = NULL;
size_t inputlen = length;
size_t outputlen;
CURLcode res = Curl_urldecode(handle, string, inputlen, &str, &outputlen,
FALSE);
if(res)
return NULL;
if(olen)
*olen = curlx_uztosi(outputlen);
return str;
1999-12-29 15:20:26 +01:00
}
/* For operating systems/environments that use different malloc/free
2008-09-09 23:15:50 +02:00
systems for the app and for this library, we provide a free that uses
the library's memory system */
2002-09-25 14:26:07 +02:00
void curl_free(void *p)
{
if(p)
free(p);
2002-09-25 14:26:07 +02:00
}