Revision 1335d76e4569fa84e52dc24c88c04daeae6e160e authored by Junio C Hamano on 08 July 2016, 17:59:15 UTC, committed by Junio C Hamano on 12 July 2016, 20:06:43 UTC
When merge_recursive() decides what the correct blob object merge result for a path should be, it uses update_file_flags() helper function to write it out to a working tree file and then calls add_cacheinfo(). The add_cacheinfo() function in turn calls make_cache_entry() to create a new cache entry to replace the higher-stage entries for the path that represents the conflict. The make_cache_entry() function calls refresh_cache_entry() to fill in the cached stat information. To mark a cache entry as up-to-date, the data is re-read from the file in the working tree, and goes through convert_to_git() conversion to be compared with the blob object name the new cache entry records. It is important to note that this happens while the higher-stage entries, which are going to be replaced with the new entry, are still in the index. Unfortunately, the convert_to_git() conversion has a misguided "safer crlf" mechanism baked in, and looks at the existing cache entry for the path to decide how to convert the contents in the working tree file. If our side (i.e. stage#2) records a text blob with CRLF in it, even when the system is configured to record LF in blobs and convert them to CRLF upon checkout (and back to LF upon checkin), the "safer crlf" mechanism stops us doing so. This especially poses a problem during a renormalizing merge, where the merge result for the path is computed by first "normalizing" the blobs involved in the merge by using convert_to_working_tree() followed by convert_to_git() with "safer crlf" disabled. The merge result that is computed correctly and fed to add_cacheinfo() via update_file_flags() does _not_ match what refresh_cache_entry() sees by converting the working tree file via convert_to_git(). We can work this around by not refreshing the new cache entry in make_cache_entry() called by add_cacheinfo(). After add_cacheinfo() adds the new entry, we can call refresh_cache_entry() on that, knowing that addition of this new cache entry would have removed the stale cache entries that had CRLF in stage #2 that were carried over before the renormalizing merge started and will not interfere with the correct recording of the result. The test update was taken from a series by Torsten Bögershausen that attempted to fix this with a different approach. Signed-off-by: Torsten Bögershausen <tboegi@web.de> Signed-off-by: Junio C Hamano <gitster@pobox.com> Reviewed-by: Torsten Bögershausen <tboegi@web.de>
1 parent 6523728
url.c
#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 int url_decode_char(const char *q)
{
int i;
unsigned char val = 0;
for (i = 0; i < 2; i++) {
unsigned char c = *q++;
val <<= 4;
if (c >= '0' && c <= '9')
val += c - '0';
else if (c >= 'a' && c <= 'f')
val += c - 'a' + 10;
else if (c >= 'A' && c <= 'F')
val += c - 'A' + 10;
else
return -1;
}
return val;
}
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 == '%') {
int val = url_decode_char(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);
}
![swh spinner](/static/img/swh-spinner.gif)
Computing file changes ...