8000 minix/lib/libfetch/fetch.c at R3.2.0 · aducode/minix · GitHub
[go: up one dir, main page]

Skip to content

Latest commit

 

History

History
626 lines (552 loc) · 13.6 KB

fetch.c

File metadata and controls

626 lines (552 loc) · 13.6 KB
}
*dst = *src;
dst->doc = doc;
return dst;
}
/*
* Split an URL into components. URL syntax is:
* [method:/][/[user[:pwd]@]host[:port]/][document]
* This almost, but not quite, RFC1738 URL syntax.
*/
struct url *
fetchParseURL(const char *URL)
{
const char *p, *q;
struct url *u;
size_t i, count;
int pre_quoted;
/* allocate struct url */
if ((u = calloc(1, sizeof(*u))) == NULL) {
fetch_syserr();
return (NULL);
}
if (*URL == '/') {
pre_quoted = 0;
strcpy(u->scheme, SCHEME_FILE);
p = URL;
goto quote_doc;
}
if (strncmp(URL, "file:", 5) == 0) {
pre_quoted = 1;
strcpy(u->scheme, SCHEME_FILE);
URL += 5;
if (URL[0] != '/' || URL[1] != '/' || URL[2] != '/') {
url_seterr(URL_MALFORMED);
goto ouch;
}
p = URL + 2;
goto quote_doc;
}
if (strncmp(URL, "http:", 5) == 0 ||
strncmp(URL, "https:", 6) == 0) {
pre_quoted = 1;
if (URL[4] == ':') {
strcpy(u->scheme, SCHEME_HTTP);
URL += 5;
} else {
strcpy(u->scheme, SCHEME_HTTPS);
URL += 6;
}
if (URL[0] != '/' || URL[1] != '/') {
url_seterr(URL_MALFORMED);
goto ouch;
}
URL += 2;
p = URL;
goto find_user;
}
if (strncmp(URL, "ftp:", 4) == 0) {
pre_quoted = 1;
strcpy(u->scheme, SCHEME_FTP);
URL += 4;
if (URL[0] != '/' || URL[1] != '/') {
url_seterr(URL_MALFORMED);
goto ouch;
}
URL += 2;
p = URL;
goto find_user;
}
url_seterr(URL_BAD_SCHEME);
goto ouch;
find_user:
p = strpbrk(URL, "/@");
if (p != NULL && *p == '@') {
/* username */
for (q = URL, i = 0; (*q != ':') && (*q != '@'); q++) {
if (i < URL_USERLEN)
u->user[i++] = *q;
}
/* password */
if (*q == ':') {
for (q++, i = 0; (*q != '@'); q++)
if (i < URL_PWDLEN)
u->pwd[i++] = *q;
}
p++;
} else {
p = URL;
}
/* hostname */
#ifdef INET6
if (*p == '[' && (q = strchr(p + 1, ']')) != NULL &&
(*++q == '\0' || *q == '/' || *q == ':')) {
if ((i = q - p - 2) > URL_HOSTLEN)
i = URL_HOSTLEN;
strncpy(u->host, ++p, i);
p = q;
} else
#endif
for (i = 0; *p && (*p != '/') && (*p != ':'); p++)
if (i < URL_HOSTLEN)
u->host[i++] = *p;
/* port */
if (*p == ':') {
for (q = ++p; *q && (*q != '/'); q++)
if (isdigit((unsigned char)*q))
u->port = u->port * 10 + (*q - '0');
else {
/* invalid port */
url_seterr(URL_BAD_PORT);
goto ouch;
}
p = q;
}
/* document */
if (!*p)
p = "/";
quote_doc:
count = 1;
for (i = 0; p[i] != '\0'; ++i) {
if ((!pre_quoted && p[i] == '%') ||
!fetch_urlpath_safe(p[i]))
count += 3;
else
++count;
}
if ((u->doc = malloc(count)) == NULL) {
fetch_syserr();
goto ouch;
}
for (i = 0; *p != '\0'; ++p) {
if ((!pre_quoted && *p == '%') ||
!fetch_urlpath_safe(*p)) {
u->doc[i++] = '%';
if ((unsigned char)*p < 160)
u->doc[i++] = '0' + ((unsigned char)*p) / 16;
else
u->doc[i++] = 'a' - 10 + ((unsigned char)*p) / 16;
if ((unsigned char)*p % 16 < 10)
u->doc[i++] = '0' + ((unsigned char)*p) % 16;
else
u->doc[i++] = 'a' - 10 + ((unsigned char)*p) % 16;
} else
u->doc[i++] = *p;
}
u->doc[i] = '\0';
return (u);
ouch:
free(u);
return (NULL);
}
/*
* Free a URL
*/
void
fetchFreeURL(struct url *u)
{
free(u->doc);
free(u);
}
static char
xdigit2digit(char digit)
{
digit = tolower((unsigned char)digit);
if (digit >= 'a' && digit <= 'f')
digit = digit - 'a' + 10;
else
digit = digit - '0';
return digit;
}
/*
* Unquote whole URL.
* Skips optional parts like query or fragment identifier.
*/
char *
fetchUnquotePath(struct url *url)
{
char *unquoted;
const char *iter;
size_t i;
if ((unquoted = malloc(strlen(url->doc) + 1)) == NULL)
return NULL;
for (i = 0, iter = url->doc; *iter != '\0'; ++iter) {
if (*iter == '#' || *iter == '?')
break;
if (iter[0] != '%' ||
!isxdigit((unsigned char)iter[1]) ||
!isxdigit((unsigned char)iter[2])) {
unquoted[i++] = *iter;
continue;
}
unquoted[i++] = xdigit2digit(iter[1]) * 16 +
xdigit2digit(iter[2]);
iter += 2;
}
unquoted[i] = '\0';
return unquoted;
}
/*
* Extract the file name component of a URL.
*/
char *
fetchUnquoteFilename(struct url *url)
{
char *unquoted, *filename;
const char *last_slash;
if ((unquoted = fetchUnquotePath(url)) == NULL)
return NULL;
if ((last_slash = strrchr(unquoted, '/')) == NULL)
return unquoted;
filename = strdup(last_slash + 1);
free(unquoted);
return filename;
}
char *
fetchStringifyURL(const struct url *url)
{
size_t total;
char *doc;
/* scheme :// user : pwd @ host :port doc */
total = strlen(url->scheme) + 3 + strlen(url->user) + 1 +
strlen(url->pwd) + 1 + strlen(url->host) + 6 + strlen(url->doc) + 1;
if ((doc = malloc(total)) == NULL)
return NULL;
if (url->port != 0)
snprintf(doc, total, "%s%s%s%s%s%s%s:%d%s",
url->scheme,
url->scheme[0] != '\0' ? "://" : "",
url->user,
url->pwd[0] != '\0' ? ":" : "",
url->pwd,
url->user[0] != '\0' || url->pwd[0] != '\0' ? "@" : "",
url->host,
(int)url->port,
url->doc);
else {
snprintf(doc, total, "%s%s%s%s%s%s%s%s",
url->scheme,
url->scheme[0] != '\0' ? "://" : "",
url->user,
url->pwd[0] != '\0' ? ":" : "",
url->pwd,
url->user[0] != '\0' || url->pwd[0] != '\0' ? "@" : "",
url->host,
url->doc);
}
return doc;
}
0