curl/lib/dict.c
Viktor Szakats 193cb00ce9
build: stop overriding standard memory allocation functions
Before this patch curl used the C preprocessor to override standard
memory allocation symbols: malloc, calloc, strdup, realloc, free.
The goal of these is to replace them with curl's debug wrappers in
`CURLDEBUG` builds, another was to replace them with the wrappers
calling user-defined allocators in libcurl. This solution needed a bunch
of workarounds to avoid breaking external headers: it relied on include
order to do the overriding last. For "unity" builds it needed to reset
overrides before external includes. Also in test apps, which are always
built as single source files. It also needed the `(symbol)` trick
to avoid overrides in some places. This would still not fix cases where
the standard symbols were macros. It was also fragile and difficult
to figure out which was the actual function behind an alloc or free call
in a specific piece of code. This in turn caused bugs where the wrong
allocator was accidentally called.

To avoid these problems, this patch replaces this solution with
`curlx_`-prefixed allocator macros, and mapping them _once_ to either
the libcurl wrappers, the debug wrappers or the standard ones, matching
the rest of the code in libtests.

This concludes the long journey to avoid redefining standard functions
in the curl codebase.

Note: I did not update `packages/OS400/*.c` sources. They did not
`#include` `curl_setup.h`, `curl_memory.h` or `memdebug.h`, meaning
the overrides were never applied to them. This may or may not have been
correct. For now I suppressed the direct use of standard allocators
via a local `.checksrc`. Probably they (except for `curlcl.c`) should be
updated to include `curl_setup.h` and use the `curlx_` macros.

This patch changes mappings in two places:
- `lib/curl_threads.c` in libtests: Before this patch it mapped to
  libcurl allocators. After, it maps to standard allocators, like
  the rest of libtests code.
- `units`: before this patch it mapped to standard allocators. After, it
  maps to libcurl allocators.

Also:
- drop all position-dependent `curl_memory.h` and `memdebug.h` includes,
  and delete the now unnecessary headers.
- rename `Curl_tcsdup` macro to `curlx_tcsdup` and define like the other
  allocators.
- map `curlx_strdup()` to `_strdup()` on Windows (was: `strdup()`).
  To fix warnings silenced via `_CRT_NONSTDC_NO_DEPRECATE`.
- multibyte: map `curlx_convert_*()` to `_strdup()` on Windows
  (was: `strdup()`).
- src: do not reuse the `strdup` name for the local replacement.
- lib509: call `_strdup()` on Windows (was: `strdup()`).
- test1132: delete test obsoleted by this patch.
- CHECKSRC.md: update text for `SNPRINTF`.
- checksrc: ban standard allocator symbols.

Follow-up to b12da22db1 #18866
Follow-up to db98daab05 #18844
Follow-up to 4deea9396b #18814
Follow-up to 9678ff5b1b #18776
Follow-up to 10bac43b87 #18774
Follow-up to 20142f5d06 #18634
Follow-up to bf7375ecc5 #18503
Follow-up to 9863599d69 #18502
Follow-up to 3bb5e58c10 #17827

Closes #19626
2025-11-28 10:44:26 +01:00

312 lines
8.5 KiB
C

/***************************************************************************
* _ _ ____ _
* Project ___| | | | _ \| |
* / __| | | | |_) | |
* | (__| |_| | _ <| |___
* \___|\___/|_| \_\_____|
*
* Copyright (C) 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 https://curl.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
* furnished to do so, under the terms of the COPYING file.
*
* This software is distributed on an "AS IS" basis, WITHOUT WARRANTY OF ANY
* KIND, either express or implied.
*
* SPDX-License-Identifier: curl
*
***************************************************************************/
#include "curl_setup.h"
#ifndef CURL_DISABLE_DICT
#ifdef HAVE_NETINET_IN_H
#include <netinet/in.h>
#endif
#ifdef HAVE_NETDB_H
#include <netdb.h>
#endif
#ifdef HAVE_ARPA_INET_H
#include <arpa/inet.h>
#endif
#ifdef HAVE_NET_IF_H
#include <net/if.h>
#endif
#ifdef HAVE_SYS_IOCTL_H
#include <sys/ioctl.h>
#endif
#ifdef HAVE_SYS_PARAM_H
#include <sys/param.h>
#endif
#ifdef HAVE_SYS_SELECT_H
#include <sys/select.h>
#elif defined(HAVE_UNISTD_H)
#include <unistd.h>
#endif
#include "urldata.h"
#include <curl/curl.h>
#include "transfer.h"
#include "sendf.h"
#include "escape.h"
#include "progress.h"
#include "dict.h"
#define DICT_MATCH "/MATCH:"
#define DICT_MATCH2 "/M:"
#define DICT_MATCH3 "/FIND:"
#define DICT_DEFINE "/DEFINE:"
#define DICT_DEFINE2 "/D:"
#define DICT_DEFINE3 "/LOOKUP:"
/*
* Forward declarations.
*/
static CURLcode dict_do(struct Curl_easy *data, bool *done);
/*
* DICT protocol handler.
*/
const struct Curl_handler Curl_handler_dict = {
"dict", /* scheme */
ZERO_NULL, /* setup_connection */
dict_do, /* do_it */
ZERO_NULL, /* done */
ZERO_NULL, /* do_more */
ZERO_NULL, /* connect_it */
ZERO_NULL, /* connecting */
ZERO_NULL, /* doing */
ZERO_NULL, /* proto_pollset */
ZERO_NULL, /* doing_pollset */
ZERO_NULL, /* domore_pollset */
ZERO_NULL, /* perform_pollset */
ZERO_NULL, /* disconnect */
ZERO_NULL, /* write_resp */
ZERO_NULL, /* write_resp_hd */
ZERO_NULL, /* connection_check */
ZERO_NULL, /* attach connection */
ZERO_NULL, /* follow */
PORT_DICT, /* defport */
CURLPROTO_DICT, /* protocol */
CURLPROTO_DICT, /* family */
PROTOPT_NONE | PROTOPT_NOURLQUERY /* flags */
};
#define DYN_DICT_WORD 10000
static char *unescape_word(const char *input)
{
struct dynbuf out;
const char *ptr;
CURLcode result = CURLE_OK;
curlx_dyn_init(&out, DYN_DICT_WORD);
/* According to RFC2229 section 2.2, these letters need to be escaped with
\[letter] */
for(ptr = input; *ptr; ptr++) {
char ch = *ptr;
if((ch <= 32) || (ch == 127) ||
(ch == '\'') || (ch == '\"') || (ch == '\\'))
result = curlx_dyn_addn(&out, "\\", 1);
if(!result)
result = curlx_dyn_addn(&out, ptr, 1);
if(result)
return NULL;
}
return curlx_dyn_ptr(&out);
}
/* sendf() sends formatted data to the server */
static CURLcode sendf(struct Curl_easy *data,
const char *fmt, ...) CURL_PRINTF(2, 3);
static CURLcode sendf(struct Curl_easy *data, const char *fmt, ...)
{
size_t bytes_written;
size_t write_len;
CURLcode result = CURLE_OK;
char *s;
char *sptr;
va_list ap;
va_start(ap, fmt);
s = curl_mvaprintf(fmt, ap); /* returns an allocated string */
va_end(ap);
if(!s)
return CURLE_OUT_OF_MEMORY; /* failure */
bytes_written = 0;
write_len = strlen(s);
sptr = s;
for(;;) {
/* Write the buffer to the socket */
result = Curl_xfer_send(data, sptr, write_len, FALSE, &bytes_written);
if(result)
break;
Curl_debug(data, CURLINFO_DATA_OUT, sptr, bytes_written);
if(bytes_written != write_len) {
/* if not all was written at once, we must advance the pointer, decrease
the size left and try again! */
write_len -= bytes_written;
sptr += bytes_written;
}
else
break;
}
curlx_free(s); /* free the output string */
return result;
}
static CURLcode dict_do(struct Curl_easy *data, bool *done)
{
char *word;
char *eword = NULL;
char *ppath;
char *database = NULL;
char *strategy = NULL;
char *nthdef = NULL; /* This is not part of the protocol, but required
by RFC 2229 */
CURLcode result;
char *path;
*done = TRUE; /* unconditionally */
/* url-decode path before further evaluation */
result = Curl_urldecode(data->state.up.path, 0, &path, NULL, REJECT_CTRL);
if(result)
return result;
if(curl_strnequal(path, DICT_MATCH, sizeof(DICT_MATCH)-1) ||
curl_strnequal(path, DICT_MATCH2, sizeof(DICT_MATCH2)-1) ||
curl_strnequal(path, DICT_MATCH3, sizeof(DICT_MATCH3)-1)) {
word = strchr(path, ':');
if(word) {
word++;
database = strchr(word, ':');
if(database) {
*database++ = (char)0;
strategy = strchr(database, ':');
if(strategy) {
*strategy++ = (char)0;
nthdef = strchr(strategy, ':');
if(nthdef) {
*nthdef = (char)0;
}
}
}
}
if(!word || (*word == (char)0)) {
infof(data, "lookup word is missing");
}
eword = unescape_word((!word || (*word == (char)0)) ? "default" : word);
if(!eword) {
result = CURLE_OUT_OF_MEMORY;
goto error;
}
result = sendf(data,
"CLIENT " LIBCURL_NAME " " LIBCURL_VERSION "\r\n"
"MATCH "
"%s " /* database */
"%s " /* strategy */
"%s\r\n" /* word */
"QUIT\r\n",
(!database || (*database == (char)0)) ? "!" : database,
(!strategy || (*strategy == (char)0)) ? "." : strategy,
eword);
if(result) {
failf(data, "Failed sending DICT request");
goto error;
}
Curl_xfer_setup_recv(data, FIRSTSOCKET, -1);
}
else if(curl_strnequal(path, DICT_DEFINE, sizeof(DICT_DEFINE)-1) ||
curl_strnequal(path, DICT_DEFINE2, sizeof(DICT_DEFINE2)-1) ||
curl_strnequal(path, DICT_DEFINE3, sizeof(DICT_DEFINE3)-1)) {
word = strchr(path, ':');
if(word) {
word++;
database = strchr(word, ':');
if(database) {
*database++ = (char)0;
nthdef = strchr(database, ':');
if(nthdef) {
*nthdef = (char)0;
}
}
}
if(!word || (*word == (char)0)) {
infof(data, "lookup word is missing");
}
eword = unescape_word((!word || (*word == (char)0)) ? "default" : word);
if(!eword) {
result = CURLE_OUT_OF_MEMORY;
goto error;
}
result = sendf(data,
"CLIENT " LIBCURL_NAME " " LIBCURL_VERSION "\r\n"
"DEFINE "
"%s " /* database */
"%s\r\n" /* word */
"QUIT\r\n",
(!database || (*database == (char)0)) ? "!" : database,
eword);
if(result) {
failf(data, "Failed sending DICT request");
goto error;
}
Curl_xfer_setup_recv(data, FIRSTSOCKET, -1);
}
else {
ppath = strchr(path, '/');
if(ppath) {
int i;
ppath++;
for(i = 0; ppath[i]; i++) {
if(ppath[i] == ':')
ppath[i] = ' ';
}
result = sendf(data,
"CLIENT " LIBCURL_NAME " " LIBCURL_VERSION "\r\n"
"%s\r\n"
"QUIT\r\n", ppath);
if(result) {
failf(data, "Failed sending DICT request");
goto error;
}
Curl_xfer_setup_recv(data, FIRSTSOCKET, -1);
}
}
error:
curlx_free(eword);
curlx_free(path);
return result;
}
#endif /* CURL_DISABLE_DICT */