1
0
mirror of https://github.com/moparisthebest/curl synced 2024-11-15 22:15:13 -05:00
curl/lib/escape.c

247 lines
6.9 KiB
C
Raw Normal View History

2002-09-03 07:52:59 -04:00
/***************************************************************************
2004-06-24 10:35:45 -04:00
* _ _ ____ _
* Project ___| | | | _ \| |
* / __| | | | |_) | |
* | (__| |_| | _ <| |___
1999-12-29 09:20:26 -05:00
* \___|\___/|_| \_\_____|
*
* Copyright (C) 1998 - 2020, Daniel Stenberg, <daniel@haxx.se>, et al.
1999-12-29 09:20:26 -05:00
*
2002-09-03 07:52:59 -04:00
* This software is licensed as described in the file COPYING, which
* you should have received as part of this distribution. The terms
2020-11-04 08:02:01 -05:00
* are also available at https://curl.se/docs/copyright.html.
2004-06-24 10:35:45 -04:00
*
2001-01-03 04:29:33 -05:00
* 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 07:52:59 -04:00
* furnished to do so, under the terms of the COPYING file.
1999-12-29 09:20:26 -05:00
*
2001-01-03 04:29:33 -05:00
* This software is distributed on an "AS IS" basis, WITHOUT WARRANTY OF ANY
* KIND, either express or implied.
1999-12-29 09:20:26 -05:00
*
2002-09-03 07:52:59 -04:00
***************************************************************************/
1999-12-29 09:20:26 -05:00
/* Escape and unescape URL encoding in strings. The functions return a new
* allocated string or NULL if an error occurred. */
build: fix circular header inclusion with other packages This commit renames lib/setup.h to lib/curl_setup.h and renames lib/setup_once.h to lib/curl_setup_once.h. Removes the need and usage of a header inclusion guard foreign to libcurl. [1] Removes the need and presence of an alarming notice we carried in old setup_once.h [2] ---------------------------------------- 1 - lib/setup_once.h used __SETUP_ONCE_H macro as header inclusion guard up to commit ec691ca3 which changed this to HEADER_CURL_SETUP_ONCE_H, this single inclusion guard is enough to ensure that inclusion of lib/setup_once.h done from lib/setup.h is only done once. Additionally lib/setup.h has always used __SETUP_ONCE_H macro to protect inclusion of setup_once.h even after commit ec691ca3, this was to avoid a circular header inclusion triggered when building a c-ares enabled version with c-ares sources available which also has a setup_once.h header. Commit ec691ca3 exposes the real nature of __SETUP_ONCE_H usage in lib/setup.h, it is a header inclusion guard foreign to libcurl belonging to c-ares's setup_once.h The renaming this commit does, fixes the circular header inclusion, and as such removes the need and usage of a header inclusion guard foreign to libcurl. Macro __SETUP_ONCE_H no longer used in libcurl. 2 - Due to the circular interdependency of old lib/setup_once.h and the c-ares setup_once.h header, old file lib/setup_once.h has carried back from 2006 up to now days an alarming and prominent notice about the need of keeping libcurl's and c-ares's setup_once.h in sync. Given that this commit fixes the circular interdependency, the need and presence of mentioned notice is removed. All mentioned interdependencies come back from now old days when the c-ares project lived inside a curl subdirectory. This commit removes last traces of such fact.
2013-01-06 13:06:49 -05:00
#include "curl_setup.h"
#include <curl/curl.h>
#include "urldata.h"
#include "warnless.h"
#include "non-ascii.h"
#include "escape.h"
#include "strdup.h"
/* The last 3 #include files should be in this order */
#include "curl_printf.h"
#include "curl_memory.h"
#include "memdebug.h"
2000-10-09 07:12:34 -04:00
2008-09-09 17:15:50 -04:00
/* Portable character check (remember EBCDIC). Do not use isalnum() because
its behavior is altered by the current locale.
2016-02-02 23:09:25 -05:00
See https://tools.ietf.org/html/rfc3986#section-2.3
*/
bool Curl_isunreserved(unsigned char in)
2008-09-09 17:15:50 -04:00
{
switch(in) {
2008-09-09 17:15:50 -04:00
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 17:15:50 -04:00
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(struct Curl_easy *data, const char *string,
int inlength)
1999-12-29 09:20:26 -05:00
{
size_t length;
CURLcode result;
struct dynbuf d;
1999-12-29 09:20:26 -05:00
if(inlength < 0)
return NULL;
Curl_dyn_init(&d, CURL_MAX_INPUT_LENGTH * 3);
2004-05-12 09:04:30 -04:00
length = (inlength?(size_t)inlength:strlen(string));
if(!length)
return strdup("");
2001-03-22 06:40:58 -05:00
while(length--) {
unsigned char in = *string; /* we need to treat the characters unsigned */
if(Curl_isunreserved(in)) {
/* append this */
if(Curl_dyn_addn(&d, &in, 1))
return NULL;
}
else {
2001-03-22 06:40:58 -05:00
/* encode it */
char encoded[4];
result = Curl_convert_to_network(data, (char *)&in, 1);
if(result) {
/* Curl_convert_to_network calls failf if unsuccessful */
Curl_dyn_free(&d);
return NULL;
}
msnprintf(encoded, sizeof(encoded), "%%%02X", in);
if(Curl_dyn_add(&d, encoded))
return NULL;
2001-03-22 06:40:58 -05:00
}
string++;
}
return Curl_dyn_ptr(&d);
1999-12-29 09:20:26 -05:00
}
2008-10-07 21:17:51 -04:00
/*
* Curl_urldecode() URL decodes the given string.
*
* 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).
*
* 'data' can be set to NULL but then this function can't convert network
* data to host for non-ascii.
*
* ctrl options:
* - REJECT_NADA: accept everything
* - REJECT_CTRL: rejects control characters (byte codes lower than 32) in
* the data
* - REJECT_ZERO: rejects decoded zero bytes
*
* The values for the enum starts at 2, to make the assert detect legacy
* invokes that used TRUE/FALSE (0 and 1).
2008-10-07 21:17:51 -04:00
*/
CURLcode Curl_urldecode(struct Curl_easy *data,
const char *string, size_t length,
char **ostring, size_t *olen,
enum urlreject ctrl)
1999-12-29 09:20:26 -05:00
{
size_t alloc;
char *ns;
size_t strindex = 0;
2010-02-23 19:03:06 -05:00
unsigned long hex;
CURLcode result = CURLE_OK;
2004-06-24 10:35:45 -04:00
DEBUGASSERT(string);
DEBUGASSERT(ctrl >= REJECT_NADA); /* crash on TRUE/FALSE */
alloc = (length?length:strlen(string)) + 1;
ns = malloc(alloc);
if(!ns)
return CURLE_OUT_OF_MEMORY;
2004-06-24 10:35:45 -04:00
2001-03-22 06:40:58 -05:00
while(--alloc > 0) {
unsigned char in = *string;
if(('%' == in) && (alloc > 2) &&
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;
2010-02-23 19:03:06 -05:00
hex = strtoul(hexstr, &ptr, 16);
2010-02-23 19:03:06 -05:00
in = curlx_ultouc(hex); /* this long is never bigger than 255 anyway */
if(data) {
result = Curl_convert_from_network(data, (char *)&in, 1);
if(result) {
/* Curl_convert_from_network calls failf if unsuccessful */
free(ns);
return result;
}
}
string += 2;
alloc -= 2;
2001-03-22 06:40:58 -05:00
}
if(((ctrl == REJECT_CTRL) && (in < 0x20)) ||
((ctrl == REJECT_ZERO) && (in == 0))) {
free(ns);
return CURLE_URL_MALFORMAT;
}
2004-06-24 10:35:45 -04:00
ns[strindex++] = in;
2001-03-22 06:40:58 -05:00
string++;
}
ns[strindex] = 0; /* terminate it */
if(olen)
/* store output size */
*olen = strindex;
/* 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(struct Curl_easy *data, const char *string,
int length, int *olen)
{
char *str = NULL;
if(length >= 0) {
size_t inputlen = length;
size_t outputlen;
CURLcode res = Curl_urldecode(data, string, inputlen, &str, &outputlen,
REJECT_NADA);
if(res)
return NULL;
if(olen) {
if(outputlen <= (size_t) INT_MAX)
*olen = curlx_uztosi(outputlen);
else
/* too large to return in an int, fail! */
Curl_safefree(str);
}
}
return str;
1999-12-29 09:20:26 -05:00
}
/* For operating systems/environments that use different malloc/free
2008-09-09 17:15:50 -04:00
systems for the app and for this library, we provide a free that uses
the library's memory system */
2002-09-25 08:26:07 -04:00
void curl_free(void *p)
{
free(p);
2002-09-25 08:26:07 -04:00
}