return url_escape_1 (s, urlchr_unsafe, false);
}
+/* URL-escape the unsafe and reserved characters (see urlchr_table) in
+ a given string, returning a freshly allocated string. */
+
+char *
+url_escape_unsafe_and_reserved (const char *s)
+{
+ return url_escape_1 (s, urlchr_unsafe|urlchr_reserved, false);
+}
+
/* URL-escape the unsafe characters (see urlchr_table) in a given
string. If no characters are unsafe, S is returned. */
#define PE_NO_ERROR 0
N_("No error"),
#define PE_UNSUPPORTED_SCHEME 1
- N_("Unsupported scheme"),
+ N_("Unsupported scheme %s"),
#define PE_INVALID_HOST_NAME 2
N_("Invalid host name"),
#define PE_BAD_PORT_NUMBER 3
error, and if ERROR is not NULL, also set *ERROR to the appropriate
error code. */
struct url *
-url_parse (const char *url, int *error)
+url_parse (const char *url, int *error, struct iri *iri, bool percent_encode)
{
struct url *u;
const char *p;
int port;
char *user = NULL, *passwd = NULL;
- char *url_encoded = NULL;
+ const char *url_encoded = NULL;
+ char *new_url = NULL;
int error_code;
goto error;
}
- url_encoded = reencode_escapes (url);
+ if (iri && iri->utf8_encode)
+ {
+ iri->utf8_encode = remote_to_utf8 (iri, iri->orig_url ? iri->orig_url : url, (const char **) &new_url);
+ if (!iri->utf8_encode)
+ new_url = NULL;
+ else
+ iri->orig_url = xstrdup (url);
+ }
+
+ /* XXX XXX Could that change introduce (security) bugs ??? XXX XXX*/
+ if (percent_encode)
+ url_encoded = reencode_escapes (new_url ? new_url : url);
+ else
+ url_encoded = new_url ? new_url : url;
+
p = url_encoded;
+ if (new_url && url_encoded != new_url)
+ xfree (new_url);
+
p += strlen (supported_schemes[scheme].leading_string);
uname_b = p;
p = url_skip_credentials (p);
{
url_unescape (u->host);
host_modified = true;
+
+ /* Apply IDNA regardless of iri->utf8_encode status */
+ if (opt.enable_iri && iri)
+ {
+ char *new = idn_encode (iri, u->host);
+ if (new)
+ {
+ xfree (u->host);
+ u->host = new;
+ host_modified = true;
+ }
+ }
}
if (params_b)
if (fragment_b)
u->fragment = strdupdelim (fragment_b, fragment_e);
- if (path_modified || u->fragment || host_modified || path_b == path_e)
+ if (opt.enable_iri || path_modified || u->fragment || host_modified || path_b == path_e)
{
/* If we suspect that a transformation has rendered what
url_string might return different from URL_ENCODED, rebuild
if (url_encoded == url)
u->url = xstrdup (url);
else
- u->url = url_encoded;
+ u->url = (char *) url_encoded;
}
return u;
error:
/* Cleanup in case of error: */
if (url_encoded && url_encoded != url)
- xfree (url_encoded);
+ xfree ((char *) url_encoded);
/* Transmit the error code to the caller, if the caller wants to
know. */
/* Return the error message string from ERROR_CODE, which should have
been retrieved from url_parse. The error message is translated. */
-const char *
-url_error (int error_code)
+char *
+url_error (const char *url, int error_code)
{
assert (error_code >= 0 && ((size_t) error_code) < countof (parse_errors));
- return _(parse_errors[error_code]);
+
+ if (error_code == PE_UNSUPPORTED_SCHEME)
+ {
+ char *error, *p;
+ char *scheme = xstrdup (url);
+ assert (url_has_scheme (url));
+
+ if ((p = strchr (scheme, ':')))
+ *p = '\0';
+ if (!strcasecmp (scheme, "https"))
+ error = aprintf (_("HTTPS support not compiled in"));
+ else
+ error = aprintf (_(parse_errors[error_code]), quote (scheme));
+ xfree (scheme);
+
+ return error;
+ }
+ else
+ return xstrdup (_(parse_errors[error_code]));
}
/* Split PATH into DIR and FILE. PATH comes from the URL and is
const char *u_file, *u_query;
char *fname, *unique;
+ char *index_filename = "index.html"; /* The default index file is index.html */
fnres.base = NULL;
fnres.size = 0;
fnres.tail = 0;
+ /* If an alternative index file was defined, change index_filename */
+ if (opt.default_page)
+ index_filename = opt.default_page;
+
+
/* Start with the directory prefix, if specified. */
if (opt.dir_prefix)
append_string (opt.dir_prefix, &fnres);
/* Add the file name. */
if (fnres.tail)
append_char ('/', &fnres);
- u_file = *u->file ? u->file : "index.html";
+ u_file = *u->file ? u->file : index_filename;
append_uri_pathel (u_file, u_file + strlen (u_file), false, &fnres);
/* Append "?query" to the file name. */
\f
static int
getchar_from_escaped_string (const char *str, char *c)
-{
+{
const char *p = str;
assert (str && *str);
assert (c);
-
+
if (p[0] == '%')
{
if (!c_isxdigit(p[1]) || !c_isxdigit(p[2]))
p += pp;
q += qq;
}
-
+
return (*p == 0 && *q == 0 ? true : false);
}
\f
} test_array[] = {
{ "http://www.yoyodyne.com/path/", "somepage.html", false, "http://www.yoyodyne.com/path/somepage.html" },
};
-
+
for (i = 0; i < sizeof(test_array)/sizeof(test_array[0]); ++i)
{
struct growable dest;