From: Torsten Bögershausen
When a file had been commited with CRLF but now .gitattributes say
"* text=auto" (or core.autocrlf is true),
the following does not roundtrip, `git apply` fails:
printf "Added line\r\n" >>file &&
git diff >patch &&
git checkout -- . &&
git apply patch
Before applying the patch, the file from working tree is converted into the
index format (clean filter, CRLF conversion, ...)
Here, when commited with CRLF, the line endings should not be converted.
Note that `git apply --index` or `git apply --cache` doesn't call
convert_to_git() because the source material is already in index format.
Analyze the patch if there is a) any context line with CRLF,
or b) if any line with CRLF is to be removed.
In this case the patch file `patch` has mixed line endings, for a)
it looks like this (ignore the $ at the begin of the line):
$ diff --git a/one b/one
$ index 533790e..c30dea8 100644
$ --- a/one
$ +++ b/one
$ @@ -1 +1,2 @@
$ a\r
$ +b\r
And for b) it looks like this:
$ diff --git a/one b/one
$ index 533790e..485540d 100644
$ --- a/one
$ +++ b/one
$ @@ -1 +1 @@
$ -a\r
$ +b\r
If `git apply` detects that the patch itself has CRLF, (look at the line
" a\r" or "-a\r" above), the new flag has_crlf is set in "struct patch"
and two things will happen:
- read_old_data() will not convert CRLF into LF by calling
convert_to_git(..., SAFE_CRLF_KEEP_CRLF);
- The WS_CR_AT_EOL bit is set in the "white space rule",
CRLF are no longer treated as white space.
Thanks to Junio C Hamano, his input became the base for the changes in t4124.
One test case is split up into 3:
- Detect the " a\r" line in the patch
- Detect the "-a\r" line in the patch
- Use LF in repo and CLRF in the worktree. (*)
* This one proves that convert_to_git(&the_index,...) still needs to pass
the &index, otherwise Git will crash.
Reported-by: Anthony Sottile
Signed-off-by: Torsten Bögershausen
---
apply.c | 28 +++-
t/t4124-apply-ws-rule.sh | 33 +++--
2 files changed, 50 insertions(+), 11 deletions(-)
diff --git a/apply.c b/apply.c
index f2d599141d..bebb176099 100644
--- a/apply.c
+++ b/apply.c
@@ -220,6 +220,7 @@ struct patch {
unsigned int recount:1;
unsigned int conflicted_threeway:1;
unsigned int direct_to_threeway:1;
+ unsigned int has_crlf:1;
struct fragment *fragments;
char *result;
size_t resultsize;
@@ -1662,6 +1663,17 @@ static void check_whitespace(struct apply_state *state,
record_ws_error(state, result, line + 1, len - 2, state->linenr);
}
+/* Check if the patch has context lines with CRLF or
+ the patch wants to remove lines with CRLF */
+static void check_old_for_crlf(struct patch *patch, const char *line, int len)
+{
+ if (len >= 2 && line[len-1] == '\n' && line[len-2] == '\r') {
+ patch->ws_rule |= WS_CR_AT_EOL;
+ patch->has_crlf = 1;
+ }
+}
+
+
/*
* Parse a unified diff. Note that this really needs to parse each
* fragment separately, since the only way to know the difference
@@ -1712,11 +1724,13 @@ static int parse_fragment(struct apply_state *state,
if (!deleted && !added)
leading++;
trailing++;
+ check_old_for_crlf(patch, line, len);
if (!state->apply_in_reverse &&
state->ws_error_action == correct_ws_error)
check_whitespace(state, line, len,
patch->ws_rule);
break;
case '-':
+ check_old_for_crlf(patch, line, len);
if (state->apply_in_reverse &&
state->ws_error_action != nowarn_ws_error)
check_whitespace(state, line, len,
patch->ws_rule);
@@ -2268,8 +2282,11 @@ static void show_stats(struct apply_state *state, struct
patch *patch)
add, pluses, del, minuses);
}
-static int read_old_data(struct stat *st, const char *path, struct strbuf *buf)
+static int read_old_data(struct stat *st, struct patch *patch,
+const char *path, struct strbuf *buf)
{
+ enum safe_crlf safe_crlf = patch->has_crlf ?
+ SAFE_CRLF_KEEP_CRLF : SAFE_CRLF_FALSE;
switch (st->st_mode & S_IFMT) {
case S_IFLNK:
if (strbuf_readlink(buf, path, st->st_size) < 0)
@@ -2278,7 +2295,7 @@ static int read_old_data(struct stat *st, const char
*path, struct strbuf *buf)
case S_IFREG:
if (strbuf_read_file(buf, path, st->st_size) != st->st_size)
return error(_("unable to open or read %s"), path);
- convert_to_git(&the_index, path, buf->buf, buf->len, buf, 0);
+ convert_to_git(&the_index, path, buf->buf, buf->len, buf,
safe_crlf);
return 0;
default:
