summaryrefslogtreecommitdiff
path: root/convert.c
diff options
context:
space:
mode:
authorFinn Arne Gangstad <finnag@pvv.org>2010-05-12 00:37:57 +0200
committerJunio C Hamano <gitster@pobox.com>2010-05-11 23:02:49 -0700
commitc4805393d73425a5f467f10fa434fb99bfba17ac (patch)
tree5a7eacb540709dbf854e134d1deac346b294707a /convert.c
parente923eaeb901ff056421b9007adcbbce271caa7b6 (diff)
downloadgit-c4805393d73425a5f467f10fa434fb99bfba17ac.tar.gz
autocrlf: Make it work also for un-normalized repositories
Previously, autocrlf would only work well for normalized repositories. Any text files that contained CRLF in the repository would cause problems, and would be modified when handled with core.autocrlf set. Change autocrlf to not do any conversions to files that in the repository already contain a CR. git with autocrlf set will never create such a file, or change a LF only file to contain CRs, so the (new) assumption is that if a file contains a CR, it is intentional, and autocrlf should not change that. The following sequence should now always be a NOP even with autocrlf set (assuming a clean working directory): git checkout <something> touch * git add -A . (will add nothing) git commit (nothing to commit) Previously this would break for any text file containing a CR. Some of you may have been folowing Eyvind's excellent thread about trying to make end-of-line translation in git a bit smoother. I decided to attack the problem from a different angle: Is it possible to make autocrlf behave non-destructively for all the previous problem cases? Stealing the problem from Eyvind's initial mail (paraphrased and summarized a bit): 1. Setting autocrlf globally is a pain since autocrlf does not work well with CRLF in the repo 2. Setting it in individual repos is hard since you do it "too late" (the clone will get it wrong) 3. If someone checks in a file with CRLF later, you get into problems again 4. If a repository once has contained CRLF, you can't tell autocrlf at which commit everything is sane again 5. autocrlf does needless work if you know that all your users want the same EOL style. I belive that this patch makes autocrlf a safe (and good) default setting for Windows, and this solves problems 1-4 (it solves 2 by being set by default, which is early enough for clone). I implemented it by looking for CR charactes in the index, and aborting any conversion attempt if this is found. Signed-off-by: Finn Arne Gangstad <finag@pvv.org> Signed-off-by: Junio C Hamano <gitster@pobox.com>
Diffstat (limited to 'convert.c')
-rw-r--r--convert.c49
1 files changed, 49 insertions, 0 deletions
diff --git a/convert.c b/convert.c
index 27acce58bc..a54c5fc4a2 100644
--- a/convert.c
+++ b/convert.c
@@ -120,6 +120,43 @@ static void check_safe_crlf(const char *path, int action,
}
}
+static int has_cr_in_index(const char *path)
+{
+ int pos, len;
+ unsigned long sz;
+ enum object_type type;
+ void *data;
+ int has_cr;
+ struct index_state *istate = &the_index;
+
+ len = strlen(path);
+ pos = index_name_pos(istate, path, len);
+ if (pos < 0) {
+ /*
+ * We might be in the middle of a merge, in which
+ * case we would read stage #2 (ours).
+ */
+ int i;
+ for (i = -pos - 1;
+ (pos < 0 && i < istate->cache_nr &&
+ !strcmp(istate->cache[i]->name, path));
+ i++)
+ if (ce_stage(istate->cache[i]) == 2)
+ pos = i;
+ }
+ if (pos < 0)
+ return 0;
+ data = read_sha1_file(istate->cache[pos]->sha1, &type, &sz);
+ if (!data || type != OBJ_BLOB) {
+ free(data);
+ return 0;
+ }
+
+ has_cr = memchr(data, '\r', sz) != NULL;
+ free(data);
+ return has_cr;
+}
+
static int crlf_to_git(const char *path, const char *src, size_t len,
struct strbuf *buf, int action, enum safe_crlf checksafe)
{
@@ -145,6 +182,13 @@ static int crlf_to_git(const char *path, const char *src, size_t len,
*/
if (is_binary(len, &stats))
return 0;
+
+ /*
+ * If the file in the index has any CR in it, do not convert.
+ * This is the new safer autocrlf handling.
+ */
+ if (has_cr_in_index(path))
+ return 0;
}
check_safe_crlf(path, action, &stats, checksafe);
@@ -203,6 +247,11 @@ static int crlf_to_worktree(const char *path, const char *src, size_t len,
return 0;
if (action == CRLF_GUESS) {
+ /* If we have any CR or CRLF line endings, we do not touch it */
+ /* This is the new safer autocrlf-handling */
+ if (stats.cr > 0 || stats.crlf > 0)
+ return 0;
+
/* If we have any bare CR characters, we're not going to touch it */
if (stats.cr != stats.crlf)
return 0;