/* TODO: not a proper URI parser */
int uri_parse(const char *uri, struct uri *parsed,
const struct uri *defaults)
{
const char *pnt, *slash, *colon;
parsed->port = -1;
parsed->host = NULL;
parsed->path = NULL;
parsed->scheme = NULL;
pnt = strstr(uri, "://");
if (pnt) {
parsed->scheme = ne_strndup(uri, pnt - uri);
pnt += 3; /* start of hostport segment */
} else {
pnt = uri;
if (defaults && defaults->scheme != NULL) {
parsed->scheme = ne_strdup(defaults->scheme);
}
}
slash = strchr(pnt, '/');
colon = strchr(pnt, ':');
if (slash == NULL) {
parsed->path = ne_strdup("/");
if (colon == NULL) {
if (defaults) parsed->port = defaults->port;
parsed->host = ne_strdup(pnt);
} else {
parsed->port = atoi(colon+1);
parsed->host = ne_strndup(pnt, colon - pnt);
}
} else {
if (colon == NULL || colon > slash) {
/* No port segment */
if (defaults) parsed->port = defaults->port;
parsed->host = ne_strndup(pnt, slash - pnt);
} else {
/* Port segment */
parsed->port = atoi(colon + 1);
parsed->host = ne_strndup(pnt, colon - pnt);
}
parsed->path = ne_strdup(slash);
}
return 0;
}
char *ne_path_parent(const char *uri)
{
size_t len = strlen(uri);
const char *pnt = uri + len - 1;
/* skip trailing slash (parent of "/foo/" is "/") */
if (pnt >= uri && *pnt == '/')
pnt--;
/* find previous slash */
while (pnt > uri && *pnt != '/')
pnt--;
if (pnt < uri || (pnt == uri && *pnt != '/'))
return NULL;
return ne_strndup(uri, pnt - uri + 1);
}
int ne_uri_parse(const char *uri, ne_uri *parsed)
{
const char *s;
#if 1
/*const*/ char *p; //SINA_IMS
#else
const char *p;
#endif
memset(parsed, 0, sizeof *parsed);
p = s = uri;
/* => s = p = URI-reference */
if (uri_lookup(*p) & URI_ALPHA) {
while (uri_lookup(*p) & URI_SCHEME)
p++;
if (*p == ':') {
parsed->scheme = ne_strndup(uri, p - s);
s = p + 1;
}
}
/* => s = heir-part, or s = relative-part */
if (s[0] == '/' && s[1] == '/') {
const char *pa;
/* => s = "//" authority path-abempty (from expansion of
* either heir-part of relative-part) */
/* authority = [ userinfo "@" ] host [ ":" port ] */
s = pa = s + 2; /* => s = authority */
while (*pa != '/' && *pa != '\0')
pa++;
/* => pa = path-abempty */
p = s;
while (p < pa && uri_lookup(*p) & URI_USERINFO)
p++;
if (*p == '@') {
parsed->userinfo = ne_strndup(s, p - s);
s = p + 1;
}
/* => s = host */
if (s[0] == '[') {
p = s + 1;
while (*p != ']' && p < pa)
p++;
if (p == pa || (p + 1 != pa && p[1] != ':')) {
/* Ill-formed IP-literal. */
return -1;
}
p++; /* => p = colon */
} else {
/* Find the colon. */
p = pa;
while (*p != ':' && p > s)
p--;
}
if (p == s) {
p = pa;
/* No colon; => p = path-abempty */
} else if (p + 1 != pa) {
/* => p = colon */
parsed->port = atoi(p + 1);
}
parsed->host = ne_strndup(s, p - s);
s = pa;
if (*s == '\0') {
s = "/"; /* FIXME: scheme-specific. */
}
}
/* => s = path-abempty / path-absolute / path-rootless
* / path-empty / path-noscheme */
p = s;
while (uri_lookup(*p) & URI_SEGCHAR)
p++;
/* => p = [ "?" query ] [ "#" fragment ] */
parsed->path = ne_strndup(s, p - s);
if (*p != '\0') {
s = p++;
while (uri_lookup(*p) & URI_QUERY)
p++;
/* => p = [ "#" fragment ] */
/* => s = [ "?" query ] [ "#" fragment ] */
if (*s == '?') {
/*@FIXME: this is ugly hack. some sina service has not yet supported utf8, we have to convert to gbk
before url parse, therefore, there may exist character < 0. For this case, treat s as query part */
#ifdef SINA_IMS
if( *p < 0 ){
parsed->query = ne_strndup(s + 1,strlen(s) -1 );
*p = '\0';
}else{
parsed->query = ne_strndup(s + 1, p - s - 1);
}
#else
parsed->query = ne_strndup(s + 1, p - s - 1);
#endif
if (*p != '\0') {
s = p++;
while (uri_lookup(*p) & URI_FRAGMENT)
p++;
}
}
/* => p now points to the next character after the
* URI-reference; which should be the NUL byte. */
if (*s == '#') {
parsed->fragment = ne_strndup(s + 1, p - s - 1);
}
else if (*p || *s != '?') {
return -1;
}
}
return 0;
}
/* Returns a malloc-allocate version of IA5 string AS. Really only
* here to prevent char * vs unsigned char * type mismatches without
* losing all hope at type-safety. */
static char *dup_ia5string(const ASN1_IA5STRING *as)
{
unsigned char *data = as->data;
return ne_strndup((char *)data, as->length);
}