* | (__| |_| | _ <| |___
* \___|\___/|_| \_\_____|
*
- * Copyright (C) 1998 - 2006, Daniel Stenberg, <daniel@haxx.se>, et al.
+ * Copyright (C) 1998 - 2017, Daniel Stenberg, <daniel@haxx.se>, et al.
*
* 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.
+ * are also available at https://curl.haxx.se/docs/copyright.html.
*
* 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
* This software is distributed on an "AS IS" basis, WITHOUT WARRANTY OF ANY
* KIND, either express or implied.
*
- * $Id$
***************************************************************************/
/* Escape and unescape URL encoding in strings. The functions return a new
* allocated string or NULL if an error occurred. */
-#include "setup.h"
-#include <ctype.h>
+#include "curl_setup.h"
+
#include <curl/curl.h>
-#include <stdio.h>
-#include <stdlib.h>
-#include <string.h>
-#include "memory.h"
-/* urldata.h and easyif.h are included for Curl_convert_... prototypes */
#include "urldata.h"
-#include "easyif.h"
-
-#define _MPRINTF_REPLACE /* use our functions only */
-#include <curl/mprintf.h>
-
-/* The last #include file should be: */
+#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"
+/* Portable character check (remember EBCDIC). Do not use isalnum() because
+ its behavior is altered by the current locale.
+ See https://tools.ietf.org/html/rfc3986#section-2.3
+*/
+static bool Curl_isunreserved(unsigned char in)
+{
+ 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 '~':
+ return TRUE;
+ default:
+ break;
+ }
+ return FALSE;
+}
+
/* for ABI-compatibility with previous versions */
char *curl_escape(const char *string, int inlength)
{
return curl_easy_unescape(NULL, string, length, NULL);
}
-char *curl_easy_escape(CURL *handle, const char *string, int inlength)
+char *curl_easy_escape(struct Curl_easy *data, const char *string,
+ int inlength)
{
- size_t alloc = (inlength?(size_t)inlength:strlen(string))+1;
+ size_t alloc;
char *ns;
char *testing_ptr = NULL;
- unsigned char in;
- size_t newlen = alloc;
- int strindex=0;
+ unsigned char in; /* we need to treat the characters unsigned */
+ size_t newlen;
+ size_t strindex = 0;
size_t length;
+ CURLcode result;
+
+ if(inlength < 0)
+ return NULL;
+
+ alloc = (inlength?(size_t)inlength:strlen(string)) + 1;
+ newlen = alloc;
-#ifndef CURL_DOES_CONVERSIONS
- /* avoid compiler warnings */
- (void)handle;
-#endif
ns = malloc(alloc);
if(!ns)
return NULL;
length = alloc-1;
while(length--) {
in = *string;
- if(!(in >= 'a' && in <= 'z') &&
- !(in >= 'A' && in <= 'Z') &&
- !(in >= '0' && in <= '9')) {
+
+ if(Curl_isunreserved(in))
+ /* just copy this */
+ ns[strindex++] = in;
+ else {
/* 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 );
+ testing_ptr = Curl_saferealloc(ns, alloc);
+ if(!testing_ptr)
return NULL;
- }
- else {
- ns = testing_ptr;
- }
+ ns = testing_ptr;
}
-#ifdef CURL_DOES_CONVERSIONS
-/* escape sequences are always in ASCII so convert them on non-ASCII hosts */
- if (!handle ||
- (Curl_convert_to_network(handle, &in, 1) != CURLE_OK)) {
+ result = Curl_convert_to_network(data, (char *)&in, 1);
+ if(result) {
/* Curl_convert_to_network calls failf if unsuccessful */
free(ns);
return NULL;
}
-#endif /* CURL_DOES_CONVERSIONS */
snprintf(&ns[strindex], 4, "%%%02X", in);
- strindex+=3;
- }
- else {
- /* just copy this */
- ns[strindex++]=in;
+ strindex += 3;
}
string++;
}
- ns[strindex]=0; /* terminate it */
+ ns[strindex] = 0; /* terminate it */
return ns;
}
-#define ishex(in) ((in >= 'a' && in <= 'f') || \
- (in >= 'A' && in <= 'F') || \
- (in >= '0' && in <= '9'))
-
-char *curl_easy_unescape(CURL *handle, const char *string, int length,
- int *olen)
+/*
+ * 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).
+ *
+ */
+CURLcode Curl_urldecode(struct Curl_easy *data,
+ const char *string, size_t length,
+ char **ostring, size_t *olen,
+ bool reject_ctrl)
{
- int alloc = (length?length:(int)strlen(string))+1;
+ size_t alloc = (length?length:strlen(string)) + 1;
char *ns = malloc(alloc);
unsigned char in;
- int strindex=0;
- long hex;
-
-#ifndef CURL_DOES_CONVERSIONS
- /* avoid compiler warnings */
- (void)handle;
-#endif
- if( !ns )
- return NULL;
+ size_t strindex = 0;
+ unsigned long hex;
+ CURLcode result;
+
+ if(!ns)
+ return CURLE_OUT_OF_MEMORY;
while(--alloc > 0) {
in = *string;
- if(('%' == in) && ishex(string[1]) && ishex(string[2])) {
+ if(('%' == in) && (alloc > 2) &&
+ ISXDIGIT(string[1]) && ISXDIGIT(string[2])) {
/* this is two hexadecimal digits following a '%' */
char hexstr[3];
char *ptr;
hexstr[1] = string[2];
hexstr[2] = 0;
- hex = strtol(hexstr, &ptr, 16);
+ hex = strtoul(hexstr, &ptr, 16);
- in = (unsigned char)hex; /* this long is never bigger than 255 anyway */
+ in = curlx_ultouc(hex); /* this long is never bigger than 255 anyway */
-#ifdef CURL_DOES_CONVERSIONS
-/* escape sequences are always in ASCII so convert them on non-ASCII hosts */
- if (!handle ||
- (Curl_convert_from_network(handle, &in, 1) != CURLE_OK)) {
+ result = Curl_convert_from_network(data, (char *)&in, 1);
+ if(result) {
/* Curl_convert_from_network calls failf if unsuccessful */
free(ns);
- return NULL;
+ return result;
}
-#endif /* CURL_DOES_CONVERSIONS */
- string+=2;
- alloc-=2;
+ string += 2;
+ alloc -= 2;
+ }
+
+ if(reject_ctrl && (in < 0x20)) {
+ free(ns);
+ return CURLE_URL_MALFORMAT;
}
ns[strindex++] = in;
string++;
}
- ns[strindex]=0; /* terminate it */
+ ns[strindex] = 0; /* terminate it */
if(olen)
/* store output size */
*olen = strindex;
- return ns;
+
+ /* 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,
+ FALSE);
+ 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;
}
/* For operating systems/environments that use different malloc/free
- ssystems for the app and for this library, we provide a free that uses
+ systems for the app and for this library, we provide a free that uses
the library's memory system */
void curl_free(void *p)
{
- if(p)
- free(p);
+ free(p);
}
projects / platform / upstream / curl.git / blobdiff