mirror of
https://github.com/moparisthebest/wget
synced 2024-07-03 16:38:41 -04:00
Factor out some initialization code for gethttp
* src/http.c (gethttp): Move some initialization code in... (initialize_request): ... a new function.
This commit is contained in:
Giuseppe Scrivano
parent
799c545722
commit
29850e77d0
257
src/http.c
257
src/http.c
@ -1646,6 +1646,138 @@ read_response_body (struct http_stat *hs, int sock, FILE *fp, wgint contlen,
|
||||
} while (0)
|
||||
#endif /* def __VMS [else] */
|
||||
|
||||
static struct request *
|
||||
initialize_request (struct url *u, struct http_stat *hs, int *dt, struct url *proxy,
|
||||
bool inhibit_keep_alive, bool *basic_auth_finished,
|
||||
wgint *body_data_size, char **user, char **passwd, uerr_t *ret)
|
||||
{
|
||||
bool head_only = !!(*dt & HEAD_ONLY);
|
||||
struct request *req;
|
||||
|
||||
/* Prepare the request to send. */
|
||||
{
|
||||
char *meth_arg;
|
||||
const char *meth = "GET";
|
||||
if (head_only)
|
||||
meth = "HEAD";
|
||||
else if (opt.method)
|
||||
meth = opt.method;
|
||||
/* Use the full path, i.e. one that includes the leading slash and
|
||||
the query string. E.g. if u->path is "foo/bar" and u->query is
|
||||
"param=value", full_path will be "/foo/bar?param=value". */
|
||||
if (proxy
|
||||
#ifdef HAVE_SSL
|
||||
/* When using SSL over proxy, CONNECT establishes a direct
|
||||
connection to the HTTPS server. Therefore use the same
|
||||
argument as when talking to the server directly. */
|
||||
&& u->scheme != SCHEME_HTTPS
|
||||
#endif
|
||||
)
|
||||
meth_arg = xstrdup (u->url);
|
||||
else
|
||||
meth_arg = url_full_path (u);
|
||||
req = request_new (meth, meth_arg);
|
||||
}
|
||||
|
||||
request_set_header (req, "Referer", (char *) hs->referer, rel_none);
|
||||
if (*dt & SEND_NOCACHE)
|
||||
{
|
||||
/* Cache-Control MUST be obeyed by all HTTP/1.1 caching mechanisms... */
|
||||
request_set_header (req, "Cache-Control", "no-cache, must-revalidate", rel_none);
|
||||
|
||||
/* ... but some HTTP/1.0 caches doesn't implement Cache-Control. */
|
||||
request_set_header (req, "Pragma", "no-cache", rel_none);
|
||||
}
|
||||
if (hs->restval)
|
||||
request_set_header (req, "Range",
|
||||
aprintf ("bytes=%s-",
|
||||
number_to_static_string (hs->restval)),
|
||||
rel_value);
|
||||
SET_USER_AGENT (req);
|
||||
request_set_header (req, "Accept", "*/*", rel_none);
|
||||
request_set_header (req, "Accept-Encoding", "identity", rel_none);
|
||||
|
||||
/* Find the username and password for authentication. */
|
||||
*user = u->user;
|
||||
*passwd = u->passwd;
|
||||
search_netrc (u->host, (const char **)&user, (const char **)&passwd, 0);
|
||||
*user = *user ? *user : (opt.http_user ? opt.http_user : opt.user);
|
||||
*passwd = *passwd ? *passwd : (opt.http_passwd ? opt.http_passwd : opt.passwd);
|
||||
|
||||
/* We only do "site-wide" authentication with "global" user/password
|
||||
* values unless --auth-no-challange has been requested; URL user/password
|
||||
* info overrides. */
|
||||
if (user && *passwd && (!u->user || opt.auth_without_challenge))
|
||||
{
|
||||
/* If this is a host for which we've already received a Basic
|
||||
* challenge, we'll go ahead and send Basic authentication creds. */
|
||||
*basic_auth_finished = maybe_send_basic_creds(u->host, *user, *passwd, req);
|
||||
}
|
||||
|
||||
/* Generate the Host header, HOST:PORT. Take into account that:
|
||||
|
||||
- Broken server-side software often doesn't recognize the PORT
|
||||
argument, so we must generate "Host: www.server.com" instead of
|
||||
"Host: www.server.com:80" (and likewise for https port).
|
||||
|
||||
- IPv6 addresses contain ":", so "Host: 3ffe:8100:200:2::2:1234"
|
||||
becomes ambiguous and needs to be rewritten as "Host:
|
||||
[3ffe:8100:200:2::2]:1234". */
|
||||
{
|
||||
/* Formats arranged for hfmt[add_port][add_squares]. */
|
||||
static const char *hfmt[][2] = {
|
||||
{ "%s", "[%s]" }, { "%s:%d", "[%s]:%d" }
|
||||
};
|
||||
int add_port = u->port != scheme_default_port (u->scheme);
|
||||
int add_squares = strchr (u->host, ':') != NULL;
|
||||
request_set_header (req, "Host",
|
||||
aprintf (hfmt[add_port][add_squares], u->host, u->port),
|
||||
rel_value);
|
||||
}
|
||||
|
||||
if (inhibit_keep_alive)
|
||||
request_set_header (req, "Connection", "Close", rel_none);
|
||||
else
|
||||
{
|
||||
request_set_header (req, "Connection", "Keep-Alive", rel_none);
|
||||
if (proxy)
|
||||
request_set_header (req, "Proxy-Connection", "Keep-Alive", rel_none);
|
||||
}
|
||||
|
||||
if (opt.method)
|
||||
{
|
||||
|
||||
if (opt.body_data || opt.body_file)
|
||||
{
|
||||
request_set_header (req, "Content-Type",
|
||||
"application/x-www-form-urlencoded", rel_none);
|
||||
|
||||
if (opt.body_data)
|
||||
*body_data_size = strlen (opt.body_data);
|
||||
else
|
||||
{
|
||||
*body_data_size = file_size (opt.body_file);
|
||||
if (*body_data_size == -1)
|
||||
{
|
||||
logprintf (LOG_NOTQUIET, _("BODY data file %s missing: %s\n"),
|
||||
quote (opt.body_file), strerror (errno));
|
||||
request_free (req);
|
||||
*ret = FILEBADFILE;
|
||||
return NULL;
|
||||
}
|
||||
}
|
||||
request_set_header (req, "Content-Length",
|
||||
xstrdup (number_to_static_string (*body_data_size)),
|
||||
rel_value);
|
||||
}
|
||||
else if (c_strcasecmp (opt.method, "post") == 0
|
||||
|| c_strcasecmp (opt.method, "put") == 0
|
||||
|| c_strcasecmp (opt.method, "patch") == 0)
|
||||
request_set_header (req, "Content-Length", "0", rel_none);
|
||||
}
|
||||
return req;
|
||||
}
|
||||
|
||||
/* Retrieve a document through HTTP protocol. It recognizes status
|
||||
code, and correctly handles redirections. It closes the network
|
||||
socket. If it receives an error from the functions below it, it
|
||||
@ -1749,127 +1881,14 @@ gethttp (struct url *u, struct http_stat *hs, int *dt, struct url *proxy,
|
||||
|
||||
conn = u;
|
||||
|
||||
/* Prepare the request to send. */
|
||||
{
|
||||
char *meth_arg;
|
||||
const char *meth = "GET";
|
||||
if (head_only)
|
||||
meth = "HEAD";
|
||||
else if (opt.method)
|
||||
meth = opt.method;
|
||||
/* Use the full path, i.e. one that includes the leading slash and
|
||||
the query string. E.g. if u->path is "foo/bar" and u->query is
|
||||
"param=value", full_path will be "/foo/bar?param=value". */
|
||||
if (proxy
|
||||
#ifdef HAVE_SSL
|
||||
/* When using SSL over proxy, CONNECT establishes a direct
|
||||
connection to the HTTPS server. Therefore use the same
|
||||
argument as when talking to the server directly. */
|
||||
&& u->scheme != SCHEME_HTTPS
|
||||
#endif
|
||||
)
|
||||
meth_arg = xstrdup (u->url);
|
||||
else
|
||||
meth_arg = url_full_path (u);
|
||||
req = request_new (meth, meth_arg);
|
||||
uerr_t ret;
|
||||
req = initialize_request (u, hs, dt, proxy, inhibit_keep_alive,
|
||||
&basic_auth_finished, &body_data_size,
|
||||
&user, &passwd, &ret);
|
||||
if (req == NULL)
|
||||
return ret;
|
||||
}
|
||||
|
||||
request_set_header (req, "Referer", (char *) hs->referer, rel_none);
|
||||
if (*dt & SEND_NOCACHE)
|
||||
{
|
||||
/* Cache-Control MUST be obeyed by all HTTP/1.1 caching mechanisms... */
|
||||
request_set_header (req, "Cache-Control", "no-cache, must-revalidate", rel_none);
|
||||
|
||||
/* ... but some HTTP/1.0 caches doesn't implement Cache-Control. */
|
||||
request_set_header (req, "Pragma", "no-cache", rel_none);
|
||||
}
|
||||
if (hs->restval)
|
||||
request_set_header (req, "Range",
|
||||
aprintf ("bytes=%s-",
|
||||
number_to_static_string (hs->restval)),
|
||||
rel_value);
|
||||
SET_USER_AGENT (req);
|
||||
request_set_header (req, "Accept", "*/*", rel_none);
|
||||
request_set_header (req, "Accept-Encoding", "identity", rel_none);
|
||||
|
||||
/* Find the username and password for authentication. */
|
||||
user = u->user;
|
||||
passwd = u->passwd;
|
||||
search_netrc (u->host, (const char **)&user, (const char **)&passwd, 0);
|
||||
user = user ? user : (opt.http_user ? opt.http_user : opt.user);
|
||||
passwd = passwd ? passwd : (opt.http_passwd ? opt.http_passwd : opt.passwd);
|
||||
|
||||
/* We only do "site-wide" authentication with "global" user/password
|
||||
* values unless --auth-no-challange has been requested; URL user/password
|
||||
* info overrides. */
|
||||
if (user && passwd && (!u->user || opt.auth_without_challenge))
|
||||
{
|
||||
/* If this is a host for which we've already received a Basic
|
||||
* challenge, we'll go ahead and send Basic authentication creds. */
|
||||
basic_auth_finished = maybe_send_basic_creds(u->host, user, passwd, req);
|
||||
}
|
||||
|
||||
/* Generate the Host header, HOST:PORT. Take into account that:
|
||||
|
||||
- Broken server-side software often doesn't recognize the PORT
|
||||
argument, so we must generate "Host: www.server.com" instead of
|
||||
"Host: www.server.com:80" (and likewise for https port).
|
||||
|
||||
- IPv6 addresses contain ":", so "Host: 3ffe:8100:200:2::2:1234"
|
||||
becomes ambiguous and needs to be rewritten as "Host:
|
||||
[3ffe:8100:200:2::2]:1234". */
|
||||
{
|
||||
/* Formats arranged for hfmt[add_port][add_squares]. */
|
||||
static const char *hfmt[][2] = {
|
||||
{ "%s", "[%s]" }, { "%s:%d", "[%s]:%d" }
|
||||
};
|
||||
int add_port = u->port != scheme_default_port (u->scheme);
|
||||
int add_squares = strchr (u->host, ':') != NULL;
|
||||
request_set_header (req, "Host",
|
||||
aprintf (hfmt[add_port][add_squares], u->host, u->port),
|
||||
rel_value);
|
||||
}
|
||||
|
||||
if (inhibit_keep_alive)
|
||||
request_set_header (req, "Connection", "Close", rel_none);
|
||||
else
|
||||
{
|
||||
request_set_header (req, "Connection", "Keep-Alive", rel_none);
|
||||
if (proxy)
|
||||
request_set_header (req, "Proxy-Connection", "Keep-Alive", rel_none);
|
||||
}
|
||||
|
||||
if (opt.method)
|
||||
{
|
||||
|
||||
if (opt.body_data || opt.body_file)
|
||||
{
|
||||
request_set_header (req, "Content-Type",
|
||||
"application/x-www-form-urlencoded", rel_none);
|
||||
|
||||
if (opt.body_data)
|
||||
body_data_size = strlen (opt.body_data);
|
||||
else
|
||||
{
|
||||
body_data_size = file_size (opt.body_file);
|
||||
if (body_data_size == -1)
|
||||
{
|
||||
logprintf (LOG_NOTQUIET, _("BODY data file %s missing: %s\n"),
|
||||
quote (opt.body_file), strerror (errno));
|
||||
request_free (req);
|
||||
return FILEBADFILE;
|
||||
}
|
||||
}
|
||||
request_set_header (req, "Content-Length",
|
||||
xstrdup (number_to_static_string (body_data_size)),
|
||||
rel_value);
|
||||
}
|
||||
else if (c_strcasecmp (opt.method, "post") == 0
|
||||
|| c_strcasecmp (opt.method, "put") == 0
|
||||
|| c_strcasecmp (opt.method, "patch") == 0)
|
||||
request_set_header (req, "Content-Length", "0", rel_none);
|
||||
}
|
||||
|
||||
retry_with_auth:
|
||||
/* We need to come back here when the initial attempt to retrieve
|
||||
without authorization header fails. (Expected to happen at least
|
||||
|
||||
Loading…
Reference in New Issue
Block a user