diff options
author | Vincent Ambo <Vincent Ambo> | 2020-01-11T23·36+0000 |
---|---|---|
committer | Vincent Ambo <Vincent Ambo> | 2020-01-11T23·40+0000 |
commit | 7ef0d62730840ded097b524104cc0a0904591a63 (patch) | |
tree | a670f96103667aeca4789a95d94ca0dff550c4ce /third_party/git/url.c | |
parent | 6a2a3007077818e24a3d56fc492ada9206a10cf0 (diff) | |
parent | 1b593e1ea4d2af0f6444d9a7788d5d99abd6fde5 (diff) |
merge(third_party/git): Merge squashed git subtree at v2.23.0 r/373
Merge commit '1b593e1ea4d2af0f6444d9a7788d5d99abd6fde5' as 'third_party/git'
Diffstat (limited to 'third_party/git/url.c')
-rw-r--r-- | third_party/git/url.c | 113 |
1 files changed, 113 insertions, 0 deletions
diff --git a/third_party/git/url.c b/third_party/git/url.c new file mode 100644 index 000000000000..1b8ef78ceab0 --- /dev/null +++ b/third_party/git/url.c @@ -0,0 +1,113 @@ +#include "cache.h" +#include "url.h" + +int is_urlschemechar(int first_flag, int ch) +{ + /* + * The set of valid URL schemes, as per STD66 (RFC3986) is + * '[A-Za-z][A-Za-z0-9+.-]*'. But use sightly looser check + * of '[A-Za-z0-9][A-Za-z0-9+.-]*' because earlier version + * of check used '[A-Za-z0-9]+' so not to break any remote + * helpers. + */ + int alphanumeric, special; + alphanumeric = ch > 0 && isalnum(ch); + special = ch == '+' || ch == '-' || ch == '.'; + return alphanumeric || (!first_flag && special); +} + +int is_url(const char *url) +{ + /* Is "scheme" part reasonable? */ + if (!url || !is_urlschemechar(1, *url++)) + return 0; + while (*url && *url != ':') { + if (!is_urlschemechar(0, *url++)) + return 0; + } + /* We've seen "scheme"; we want colon-slash-slash */ + return (url[0] == ':' && url[1] == '/' && url[2] == '/'); +} + +static char *url_decode_internal(const char **query, int len, + const char *stop_at, struct strbuf *out, + int decode_plus) +{ + const char *q = *query; + + while (len) { + unsigned char c = *q; + + if (!c) + break; + if (stop_at && strchr(stop_at, c)) { + q++; + len--; + break; + } + + if (c == '%' && (len < 0 || len >= 3)) { + int val = hex2chr(q + 1); + if (0 < val) { + strbuf_addch(out, val); + q += 3; + len -= 3; + continue; + } + } + + if (decode_plus && c == '+') + strbuf_addch(out, ' '); + else + strbuf_addch(out, c); + q++; + len--; + } + *query = q; + return strbuf_detach(out, NULL); +} + +char *url_decode(const char *url) +{ + return url_decode_mem(url, strlen(url)); +} + +char *url_decode_mem(const char *url, int len) +{ + struct strbuf out = STRBUF_INIT; + const char *colon = memchr(url, ':', len); + + /* Skip protocol part if present */ + if (colon && url < colon) { + strbuf_add(&out, url, colon - url); + len -= colon - url; + url = colon; + } + return url_decode_internal(&url, len, NULL, &out, 0); +} + +char *url_decode_parameter_name(const char **query) +{ + struct strbuf out = STRBUF_INIT; + return url_decode_internal(query, -1, "&=", &out, 1); +} + +char *url_decode_parameter_value(const char **query) +{ + struct strbuf out = STRBUF_INIT; + return url_decode_internal(query, -1, "&", &out, 1); +} + +void end_url_with_slash(struct strbuf *buf, const char *url) +{ + strbuf_addstr(buf, url); + strbuf_complete(buf, '/'); +} + +void str_end_url_with_slash(const char *url, char **dest) +{ + struct strbuf buf = STRBUF_INIT; + end_url_with_slash(&buf, url); + free(*dest); + *dest = strbuf_detach(&buf, NULL); +} |