curl/lib/dict.c
Stefan Eissing d7b6ce64ce
lib: replace readwrite with write_resp
This clarifies the handling of server responses by folding the code for
the complicated protocols into their protocol handlers. This concerns
mainly HTTP and its bastard sibling RTSP.

The terms "read" and "write" are often used without clear context if
they refer to the connect or the client/application side of a
transfer. This PR uses "read/write" for operations on the client side
and "send/receive" for the connection, e.g. server side. If this is
considered useful, we can revisit renaming of further methods in another
PR.

Curl's protocol handler `readwrite()` method been changed:

```diff
-  CURLcode (*readwrite)(struct Curl_easy *data, struct connectdata *conn,
-                        const char *buf, size_t blen,
-                        size_t *pconsumed, bool *readmore);
+  CURLcode (*write_resp)(struct Curl_easy *data, const char *buf, size_t blen,
+                         bool is_eos, bool *done);
```

The name was changed to clarify that this writes reponse data to the
client side. The parameter changes are:

* `conn` removed as it always operates on `data->conn`
* `pconsumed` removed as the method needs to handle all data on success
* `readmore` removed as no longer necessary
* `is_eos` as indicator that this is the last call for the transfer
  response (end-of-stream).
* `done` TRUE on return iff the transfer response is to be treated as
  finished

This change affects many files only because of updated comments in
handlers that provide no implementation. The real change is that the
HTTP protocol handlers now provide an implementation.

The HTTP protocol handlers `write_resp()` implementation will get passed
**all** raw data of a server response for the transfer. The HTTP/1.x
formatted status and headers, as well as the undecoded response
body. `Curl_http_write_resp_hds()` is used internally to parse the
response headers and pass them on. This method is public as the RTSP
protocol handler also uses it.

HTTP/1.1 "chunked" transport encoding is now part of the general
*content encoding* writer stack, just like other encodings. A new flag
`CLIENTWRITE_EOS` was added for the last client write. This allows
writers to verify that they are in a valid end state. The chunked
decoder will check if it indeed has seen the last chunk.

The general response handling in `transfer.c:466` happens in function
`readwrite_data()`. This mainly operates now like:

```
static CURLcode readwrite_data(data, ...)
{
  do {
    Curl_xfer_recv_resp(data, buf)
    ...
    Curl_xfer_write_resp(data, buf)
    ...
  } while(interested);
  ...
}
```

All the response data handling is implemented in
`Curl_xfer_write_resp()`. It calls the protocol handler's `write_resp()`
implementation if available, or does the default behaviour.

All raw response data needs to pass through this function. Which also
means that anyone in possession of such data may call
`Curl_xfer_write_resp()`.

Closes #12480
2024-01-13 17:23:42 +01:00

331 lines
8.8 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"
#include "curl_printf.h"
#include "strcase.h"
#include "curl_memory.h"
/* The last #include file should be: */
#include "memdebug.h"
/*
* 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_getsock */
ZERO_NULL, /* doing_getsock */
ZERO_NULL, /* domore_getsock */
ZERO_NULL, /* perform_getsock */
ZERO_NULL, /* disconnect */
ZERO_NULL, /* write_resp */
ZERO_NULL, /* connection_check */
ZERO_NULL, /* attach connection */
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;
Curl_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 = Curl_dyn_addn(&out, "\\", 1);
if(!result)
result = Curl_dyn_addn(&out, ptr, 1);
if(result)
return NULL;
}
return Curl_dyn_ptr(&out);
}
/* sendf() sends formatted data to the server */
static CURLcode sendf(curl_socket_t sockfd, struct Curl_easy *data,
const char *fmt, ...) CURL_PRINTF(3, 4);
static CURLcode sendf(curl_socket_t sockfd, struct Curl_easy *data,
const char *fmt, ...)
{
ssize_t bytes_written;
size_t write_len;
CURLcode result = CURLE_OK;
char *s;
char *sptr;
va_list ap;
va_start(ap, fmt);
#ifdef __clang__
#pragma clang diagnostic push
#pragma clang diagnostic ignored "-Wformat-nonliteral"
#endif
s = vaprintf(fmt, ap); /* returns an allocated string */
#ifdef __clang__
#pragma clang diagnostic pop
#endif
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_write(data, sockfd, sptr, write_len, &bytes_written);
if(result)
break;
Curl_debug(data, CURLINFO_DATA_OUT, sptr, (size_t)bytes_written);
if((size_t)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;
}
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;
struct connectdata *conn = data->conn;
curl_socket_t sockfd = conn->sock[FIRSTSOCKET];
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(strncasecompare(path, DICT_MATCH, sizeof(DICT_MATCH)-1) ||
strncasecompare(path, DICT_MATCH2, sizeof(DICT_MATCH2)-1) ||
strncasecompare(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");
word = (char *)"default";
}
if(!database || (*database == (char)0)) {
database = (char *)"!";
}
if(!strategy || (*strategy == (char)0)) {
strategy = (char *)".";
}
eword = unescape_word(word);
if(!eword) {
result = CURLE_OUT_OF_MEMORY;
goto error;
}
result = sendf(sockfd, data,
"CLIENT " LIBCURL_NAME " " LIBCURL_VERSION "\r\n"
"MATCH "
"%s " /* database */
"%s " /* strategy */
"%s\r\n" /* word */
"QUIT\r\n",
database,
strategy,
eword);
if(result) {
failf(data, "Failed sending DICT request");
goto error;
}
Curl_setup_transfer(data, FIRSTSOCKET, -1, FALSE, -1); /* no upload */
}
else if(strncasecompare(path, DICT_DEFINE, sizeof(DICT_DEFINE)-1) ||
strncasecompare(path, DICT_DEFINE2, sizeof(DICT_DEFINE2)-1) ||
strncasecompare(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");
word = (char *)"default";
}
if(!database || (*database == (char)0)) {
database = (char *)"!";
}
eword = unescape_word(word);
if(!eword) {
result = CURLE_OUT_OF_MEMORY;
goto error;
}
result = sendf(sockfd, data,
"CLIENT " LIBCURL_NAME " " LIBCURL_VERSION "\r\n"
"DEFINE "
"%s " /* database */
"%s\r\n" /* word */
"QUIT\r\n",
database,
eword);
if(result) {
failf(data, "Failed sending DICT request");
goto error;
}
Curl_setup_transfer(data, FIRSTSOCKET, -1, FALSE, -1);
}
else {
ppath = strchr(path, '/');
if(ppath) {
int i;
ppath++;
for(i = 0; ppath[i]; i++) {
if(ppath[i] == ':')
ppath[i] = ' ';
}
result = sendf(sockfd, 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_setup_transfer(data, FIRSTSOCKET, -1, FALSE, -1);
}
}
error:
free(eword);
free(path);
return result;
}
#endif /* CURL_DISABLE_DICT */