*/
int OSSL_HTTP_parse_url(const char *url, char **phost, char **pport,
- char **ppath, int *pssl)
+ int *pport_num, char **ppath, int *pssl)
{
char *p, *buf;
- char *host;
- const char *port = OSSL_HTTP_PORT;
- size_t https_len = strlen(OSSL_HTTPS_NAME);
-
- if (!ossl_assert(https_len >= strlen(OSSL_HTTP_NAME)))
- return 0;
- if (url == NULL) {
- HTTPerr(0, ERR_R_PASSED_NULL_PARAMETER);
- return 0;
- }
+ char *host, *host_end;
+ const char *path, *port = OSSL_HTTP_PORT;
+ long portnum = 80;
if (phost != NULL)
*phost = NULL;
if (pssl != NULL)
*pssl = 0;
+ if (url == NULL) {
+ HTTPerr(0, ERR_R_PASSED_NULL_PARAMETER);
+ return 0;
+ }
+
/* dup the buffer since we are going to mess with it */
if ((buf = OPENSSL_strdup(url)) == NULL)
goto err;
- /* Check for initial colon */
- p = strchr(buf, ':');
- if (p == NULL || (size_t)(p - buf) > https_len) {
+ /* check for optional prefix "http[s]://" */
+ p = strstr(buf, "://");
+ if (p == NULL) {
p = buf;
} else {
- *(p++) = '\0';
-
+ *p = '\0'; /* p points to end of scheme name */
if (strcmp(buf, OSSL_HTTPS_NAME) == 0) {
if (pssl != NULL)
*pssl = 1;
port = OSSL_HTTPS_PORT;
+ portnum = 443;
} else if (strcmp(buf, OSSL_HTTP_NAME) != 0) {
- goto parse_err;
+ HTTPerr(0, HTTP_R_INVALID_URL_PREFIX);
+ goto err;
}
-
- /* Check for double slash */
- if ((p[0] != '/') || (p[1] != '/'))
- goto parse_err;
- p += 2;
+ p += 3;
}
host = p;
- /* Check for trailing part of path */
- p = strchr(p, '/');
- if (ppath != NULL && (*ppath = OPENSSL_strdup(p == NULL ? "/" : p)) == NULL)
- goto err;
- if (p != NULL)
- *p = '\0'; /* Set start of path to 0 so hostname[:port] is valid */
-
- p = host;
+ /* parse host name/address as far as needed here */
if (host[0] == '[') {
- /* ipv6 literal */
+ /* ipv6 literal, which may include ':' */
host++;
- p = strchr(host, ']');
- if (p == NULL)
+ host_end = strchr(host, ']');
+ if (host_end == NULL)
goto parse_err;
- *p = '\0';
- p++;
+ *host_end++ = '\0';
+ } else {
+ host_end = strchr(host, ':'); /* look for start of optional port */
+ if (host_end == NULL)
+ host_end = strchr(host, '/'); /* look for start of optional path */
+ if (host_end == NULL)
+ /* the remaining string is just the hostname */
+ host_end = host + strlen(host);
}
- /* Look for optional ':' for port number */
- if ((p = strchr(p, ':'))) {
- *p = '\0';
- port = p + 1;
+ /* parse optional port specification starting with ':' */
+ p = host_end;
+ if (*p == ':') {
+ port = ++p;
+ if (pport_num == NULL) {
+ p = strchr(port, '/');
+ if (p == NULL)
+ p = p + strlen(port);
+ } else { /* make sure a numerical port value is given */
+ portnum = strtol(port, &p, 10);
+ if (p == port || (*p != '\0' && *p != '/'))
+ goto parse_err;
+ if (portnum <= 0 || portnum >= 65536) {
+ HTTPerr(0, HTTP_R_INVALID_PORT_NUMBER);
+ goto err;
+ }
+ }
+ }
+ *host_end = '\0';
+ *p = '\0'; /* terminate port string */
+
+ /* check for optional path at end of url starting with '/' */
+ path = url + (p - buf);
+ /* cannot use p + 1 because *p is '\0' and path must start with '/' */
+ if (*path == '\0') {
+ path = "/";
+ } else if (*path != '/') {
+ HTTPerr(0, HTTP_R_INVALID_URL_PATH);
+ goto parse_err;
}
+
if (phost != NULL && (*phost = OPENSSL_strdup(host)) == NULL)
goto err;
if (pport != NULL && (*pport = OPENSSL_strdup(port)) == NULL)
goto err;
+ if (pport_num != NULL)
+ *pport_num = (int)portnum;
+ if (ppath != NULL && (*ppath = OPENSSL_strdup(path)) == NULL)
+ goto err;
OPENSSL_free(buf);
return 1;
const char *proxyuser, const char *proxypass,
int timeout, BIO *bio_err, const char *prog);
int OSSL_HTTP_parse_url(const char *url, char **phost, char **pport,
- char **ppath, int *pssl);
+ int *pport_num, char **ppath, int *pssl);
=head1 DESCRIPTION
-OSSL_HTTP_get() uses HTTP GET to obtain data (of any type) from the given B<url>
+OSSL_HTTP_get() uses HTTP GET to obtain data (of any type) from the given I<url>
and returns it as a memory BIO.
OSSL_HTTP_get_asn1() uses HTTP GET to obtain an ASN.1-encoded value
-(e.g., an X.509 certificate) with the expected structure specified by B<it>
-(e.g., I<ASN1_ITEM_rptr(X509)>) from the given B<url>
+(e.g., an X.509 certificate) with the expected structure specified by I<it>
+(e.g., I<ASN1_ITEM_rptr(X509)>) from the given I<url>
and returns it on success as a pointer to I<ASN1_VALUE>.
-OSSL_HTTP_post_asn1() uses the HTTP POST method to send a request B<req>
-with the ASN.1 structure defined in B<req_it> and the given B<content_type> to
-the given
B<server> and optional B<port> and B<path>.
-If B<use_ssl> is nonzero a TLS connection is requested and the B<bio_update_fn>
+OSSL_HTTP_post_asn1() uses the HTTP POST method to send a request I<req>
+with the ASN.1 structure defined in I<req_it> and the given I<content_type> to
+the given
I<server> and optional I<port> and I<path>.
+If I<use_ssl> is nonzero a TLS connection is requested and the I<bio_update_fn>
parameter, described below, must be provided.
-The optional list B<headers> may contain additional custom HTTP header lines.
-The expected structure of the response is specified by B<rsp_it>.
+The optional list I<headers> may contain additional custom HTTP header lines.
+The expected structure of the response is specified by I<rsp_it>.
On success it returns the response as a pointer to B<ASN1_VALUE>.
OSSL_HTTP_transfer() exchanges any form of HTTP request and response.
It implements the core of the functions described above.
-If
B<path> parameter is NULL it defaults to "/".
-If B<use_ssl> is nonzero a TLS connection is requested
-and the B<bio_update_fn> parameter, described below, must be provided.
-If B<req_mem> is NULL it uses the HTTP GET method, else it uses HTTP POST to
-send a request with the contents of the memory BIO and optional B<content_type>.
-The optional list B<headers> may contain additional custom HTTP header lines.
-If B<req_mem> is NULL (i.e., the HTTP method is GET) and B<redirection_url>
+If
I<path> parameter is NULL it defaults to "/".
+If I<use_ssl> is nonzero a TLS connection is requested
+and the I<bio_update_fn> parameter, described below, must be provided.
+If I<req_mem> is NULL it uses the HTTP GET method, else it uses HTTP POST to
+send a request with the contents of the memory BIO and optional I<content_type>.
+The optional list I<headers> may contain additional custom HTTP header lines.
+If I<req_mem> is NULL (i.e., the HTTP method is GET) and I<redirection_url>
is not NULL the latter pointer is used to provide any new location that
the server may return with HTTP code 301 (MOVED_PERMANENTLY) or 302 (FOUND).
In this case the caller is responsible for deallocating this URL with
The above functions have the following parameters in common.
Typically the OpenSSL build supports sockets
-and the B<bio> and B<rbio> parameters are both NULL.
+and the I<bio> and I<rbio> parameters are both NULL.
In this case the client creates a network BIO internally
-for connecting to the given B<server>
-at the specified
B<port> (if any, defaulting to 80 for HTTP or 443 for HTTPS),
-optionally via a B<proxy> (respecting B<no_proxy>) as described below.
+for connecting to the given I<server>
+at the specified
I<port> (if any, defaulting to 80 for HTTP or 443 for HTTPS),
+optionally via a I<proxy> (respecting I<no_proxy>) as described below.
Then the client uses this internal BIO for exchanging the request and response.
-If B<bio> is given and B<rbio> is NULL then the client uses this B<bio> instead.
-If both B<bio> and B<rbio> are given (which may be memory BIOs for instance)
+If I<bio> is given and I<rbio> is NULL then the client uses this I<bio> instead.
+If both I<bio> and I<rbio> are given (which may be memory BIOs for instance)
then no explicit connection is attempted,
-B<bio> is used for writing the request, and B<rbio> for reading the response.
-As soon as the client has flushed B<bio> the server must be ready to provide
-a response or indicate a waiting condition via B<rbio>.
+I<bio> is used for writing the request, and I<rbio> for reading the response.
+As soon as the client has flushed I<bio> the server must be ready to provide
+a response or indicate a waiting condition via I<rbio>.
-The optional
B<proxy> parameter can be used to set the address of the an
+The optional
I<proxy> parameter can be used to set the address of the an
HTTP(S) proxy to use (unless overridden by "no_proxy" settings).
-If TLS is not used this defaults to the environment variable B<http_proxy>
-if set, else B<HTTP_PROXY>.
-If B<use_ssl> != 0 it defaults to B<https_proxy> if set, else B<HTTPS_PROXY>.
+If TLS is not used this defaults to the environment variable C<http_proxy>
+if set, else C<HTTP_PROXY>.
+If I<use_ssl> != 0 it defaults to C<https_proxy> if set, else C<HTTPS_PROXY>.
An empty proxy string specifies not to use a proxy.
-Else the format is I<[http[s]://]address[:port][/path]>,
+Else the format is C<[http[s]://]address[:port][/path]>,
where any path given is ignored.
The default proxy port number is 80, or 443 in case "https:" is given.
-The HTTP client functions connect via the given proxy unless the B<server>
-is found in the optional list B<no_proxy> of proxy hostnames (if not NULL;
-default is the environment variable B<no_proxy> if set, else B<NO_PROXY>).
+The HTTP client functions connect via the given proxy unless the I<server>
+is found in the optional list I<no_proxy> of proxy hostnames (if not NULL;
+default is the environment variable C<no_proxy> if set, else C<NO_PROXY>).
Proxying plain HTTP is supported directly,
while using a proxy for HTTPS connections requires a suitable callback function
-such as B<OSSL_HTTP_proxy_connect()>, described below.
+such as OSSL_HTTP_proxy_connect(), described below.
-The B<maxline> parameter specifies the response header maximum line length,
+The I<maxline> parameter specifies the response header maximum line length,
where 0 indicates the default value, which currently is 4k.
-The B<max_resp_len> parameter specifies the maximum response length,
+The I<max_resp_len> parameter specifies the maximum response length,
where 0 indicates the default value, which currently is 100k.
An ASN.1-encoded response is expected by OSSL_HTTP_get_asn1() and
OSSL_HTTP_post_asn1(), while for OSSL_HTTP_get() or OSSL_HTTP_transfer()
-this is only the case if the B<expect_asn1> parameter is nonzero.
+this is only the case if the I<expect_asn1> parameter is nonzero.
If the response header contains one or more "Content-Length" header lines and/or
an ASN.1-encoded response is expected, which should include a total length,
the length indications received are checked for consistency
and for not exceeding the maximum response length.
-If the parameter B<expected_content_type> (or B<expected_ct>, respectively)
+If the parameter I<expected_content_type> (or I<expected_ct>, respectively)
is not NULL then the HTTP client checks that the given content type string
is included in the HTTP header of the response and returns an error if not.
-If the B<timeout> parameter is > 0 this indicates the maximum number of seconds
+If the I<timeout> parameter is > 0 this indicates the maximum number of seconds
to wait until the transfer is complete.
A value of 0 enables waiting indefinitely,
while a value < 0 immediately leads to a timeout condition.
-The optional parameter
B<bio_update_fn> with its optional argument B<arg> may
+The optional parameter
I<bio_update_fn> with its optional argument I<arg> may
be used to modify the connection BIO used by the HTTP client (and cannot be
-used when both B<bio> and B<rbio> are given).
-B<bio_update_fn> is a BIO connect/disconnect callback function with prototype
+used when both I<bio> and I<rbio> are given).
+I<bio_update_fn> is a BIO connect/disconnect callback function with prototype
BIO *(*OSSL_HTTP_bio_cb_t)(BIO *bio, void *arg, int connect, int detail)
-The callback may modify the HTTP BIO provided in the B<bio> argument,
-whereby it may make use of a custom defined argument
B<arg>,
+The callback may modify the HTTP BIO provided in the I<bio> argument,
+whereby it may make use of a custom defined argument
I<arg>,
which may for instance refer to an I<SSL_CTX> structure.
During connection establishment, just after calling BIO_do_connect_retry(),
-the function is invoked with the B<connect> argument being 1 and the B<detail>
+the function is invoked with the I<connect> argument being 1 and the I<detail>
argument being 1 if HTTPS is requested, i.e., SSL/TLS should be enabled.
-On disconnect B<connect> is 0 and B<detail> is 1 if no error occurred, else 0.
+On disconnect I<connect> is 0 and I<detail> is 1 if no error occurred, else 0.
For instance, on connect the function may prepend a TLS BIO to implement HTTPS;
after disconnect it may do some diagnostic output and/or specific cleanup.
The function should return NULL to indicate failure.
OSSL_HTTP_proxy_connect() may be used by an above BIO connect callback function
to set up an SSL/TLS connection via an HTTPS proxy.
-It promotes the given BIO B<bio> representing a connection
+It promotes the given BIO I<bio> representing a connection
pre-established with a TLS proxy using the HTTP CONNECT method,
-optionally using proxy client credentials
B<proxyuser> and B<proxypass>,
-to connect with TLS protection ultimately to
B<server> and B<port>.
-If the
B<port> argument is NULL or the empty string it defaults to "443".
-The B<timeout> parameter is used as described above.
+optionally using proxy client credentials
I<proxyuser> and I<proxypass>,
+to connect with TLS protection ultimately to
I<server> and I<port>.
+If the
I<port> argument is NULL or the empty string it defaults to "443".
+The I<timeout> parameter is used as described above.
Since this function is typically called by applications such as
-L<openssl-s_client(1)> it uses the
B<bio_err> and B<prog> parameters (unless
+L<openssl-s_client(1)> it uses the
I<bio_err> and I<prog> parameters (unless
NULL) to print additional diagnostic information in a user-oriented way.
-OSSL_HTTP_parse_url() parses its input string B<url> as a URL and splits it up
-into host, port and path components and a flag whether it begins with 'https'.
-The host component may be a DNS name or an IPv4 or an IPv6 address.
+OSSL_HTTP_parse_url() parses its input string I<url> as a URL
+of the form C<[http[s]://]address[:port][/path]> and splits it up into host,
+port, and path components and a flag indicating whether it begins with 'https'.
+The host component may be a DNS name or an IP address
+where IPv6 addresses should be enclosed in square brackets C<[> and C<]>.
The port component is optional and defaults to "443" for HTTPS, else "80".
+If the I<pport_num> argument is NULL the port specification
+can be in mnemonic form such as "http" like with L<BIO_set_conn_port(3)>, else
+it must be in numerical form and its integer value is assigned to B<*pport_num>.
The path component is also optional and defaults to "/".
-As far as the result pointer arguments are not NULL it assigns via
-them copies of the respective string components.
-The strings returned this way must be deallocated by the caller using
-L<OPENSSL_free(3)> unless they are NULL, which is their default value on error.
+On success the function assigns via each non-NULL result pointer argument
+I<phost>, I<pport>, I<pport_num>, I<ppath>, and I<pssl>
+the respective url component.
+On error, B<*phost>, B<*pport>, and B<*ppath> are assigned to NULL,
+else they are guaranteed to contain non-NULL string pointers.
+It is the reponsibility of the caller to free them using L<OPENSSL_free(3)>.
+A string returned via B<*ppath> is guaranteed to begin with a C</> character.
=head1 NOTES
The names of the environment variables used by this implementation:
-B<http_proxy>, B<HTTP_PROXY>, B<https_proxy>, B<HTTPS_PROXY>, B<no_proxy>, and
-B<NO_PROXY>, have been chosen for maximal compatibility with
+C<http_proxy>, C<HTTP_PROXY>, C<https_proxy>, C<HTTPS_PROXY>, C<no_proxy>, and
+C<NO_PROXY>, have been chosen for maximal compatibility with
other HTTP client implementations such as wget, curl, and git.
=head1 RETURN VALUES
OSSL_HTTP_proxy_connect() and OSSL_HTTP_parse_url()
return 1 on success, 0 on error.
+=head1 SEE ALSO
+
+L<BIO_set_conn_port(3)>
+
=head1 HISTORY
OSSL_HTTP_get(), OSSL_HTTP_get_asn1(), OSSL_HTTP_post_asn1(),
return res;
}
+static int test_http_url_ok(const char *url, const char *exp_host, int exp_ssl)
+{
+ char *host, *port, *path;
+ int num, ssl;
+ int res;
+
+ res = TEST_true(OSSL_HTTP_parse_url(url, &host, &port, &num, &path, &ssl))
+ && TEST_str_eq(host, exp_host)
+ && TEST_str_eq(port, "65535")
+ && TEST_int_eq(num, 65535)
+ && TEST_str_eq(path, "/pkix")
+ && TEST_int_eq(ssl, exp_ssl);
+ OPENSSL_free(host);
+ OPENSSL_free(port);
+ OPENSSL_free(path);
+ return res;
+}
+
+static int test_http_url_dns(void)
+{
+ return test_http_url_ok("server:65535/pkix", "server", 0);
+}
+
+static int test_http_url_ipv4(void)
+{
+ return test_http_url_ok("https://1.2.3.4:65535/pkix", "1.2.3.4", 1);
+}
+
+static int test_http_url_ipv6(void)
+{
+ return test_http_url_ok("http://[FF01::101]:65535/pkix", "FF01::101", 0);
+}
+
+static int test_http_url_invalid(const char *url)
+{
+ char *host = "1", *port = "1", *path = "1";
+ int num = 1, ssl = 1;
+ int res;
+
+ res = TEST_false(OSSL_HTTP_parse_url(url, &host, &port, &num, &path, &ssl))
+ && TEST_ptr_null(host)
+ && TEST_ptr_null(port)
+ && TEST_ptr_null(path);
+ if (!res) {
+ OPENSSL_free(host);
+ OPENSSL_free(port);
+ OPENSSL_free(path);
+ }
+ return res;
+}
+
+static int test_http_url_invalid_prefix(void)
+{
+ return test_http_url_invalid("htttps://1.2.3.4:65535/pkix");
+}
+
+static int test_http_url_invalid_port(void)
+{
+ return test_http_url_invalid("https://1.2.3.4:65536/pkix");
+}
+
+static int test_http_url_invalid_path(void)
+{
+ return test_http_url_invalid("https://[FF01::101]pkix");
+}
+
static int test_http_get_x509(void)
{
return test_http_x509(1);
if (!TEST_ptr((x509 = load_pem_cert(test_get_argument(0)))))
return 1;
+ ADD_TEST(test_http_url_dns);
+ ADD_TEST(test_http_url_ipv4);
+ ADD_TEST(test_http_url_ipv6);
+ ADD_TEST(test_http_url_invalid_prefix);
+ ADD_TEST(test_http_url_invalid_port);
+ ADD_TEST(test_http_url_invalid_path);
ADD_TEST(test_http_get_x509);
ADD_TEST(test_http_post_x509);
return 1;
projects / openssl.git / commitdiff