summaryrefslogtreecommitdiff
path: root/diff.c
diff options
context:
space:
mode:
authorJunio C Hamano <gitster@pobox.com>2017-03-01 18:04:44 +0100
committerJunio C Hamano <gitster@pobox.com>2017-03-02 10:48:06 -0800
commit12426e114b252d130d83c3f098c4ceae3cf217e3 (patch)
treeb87b7d45487b8c1bea1d33f0336b214d7f3de78c /diff.c
parent0b65a8dbdb38962e700ee16776a3042beb489060 (diff)
downloadgit-12426e114b252d130d83c3f098c4ceae3cf217e3.tar.gz
diff: do not short-cut CHECK_SIZE_ONLY check in diff_populate_filespec()jc/diff-populate-filespec-size-only-fix
Callers of diff_populate_filespec() can choose to ask only for the size of the blob without grabbing the blob data, and the function, after running lstat() when the filespec points at a working tree file, returns by copying the value in size field of the stat structure into the size field of the filespec when this is the case. However, this short-cut cannot be taken if the contents from the path needs to go through convert_to_git(), whose resulting real blob data may be different from what is in the working tree file. As "git diff --quiet" compares the .size fields of filespec structures to skip content comparison, this bug manifests as a false "there are differences" for a file that needs eol conversion, for example. Reported-by: Mike Crowe <mac@mcrowe.com> Helped-by: Torsten Bögershausen <tboegi@web.de> Signed-off-by: Junio C Hamano <gitster@pobox.com>
Diffstat (limited to 'diff.c')
-rw-r--r--diff.c19
1 files changed, 18 insertions, 1 deletions
diff --git a/diff.c b/diff.c
index 059123c5dc..37e60ca601 100644
--- a/diff.c
+++ b/diff.c
@@ -2783,8 +2783,25 @@ int diff_populate_filespec(struct diff_filespec *s, unsigned int flags)
s->should_free = 1;
return 0;
}
- if (size_only)
+
+ /*
+ * Even if the caller would be happy with getting
+ * only the size, we cannot return early at this
+ * point if the path requires us to run the content
+ * conversion.
+ */
+ if (size_only && !would_convert_to_git(s->path))
return 0;
+
+ /*
+ * Note: this check uses xsize_t(st.st_size) that may
+ * not be the true size of the blob after it goes
+ * through convert_to_git(). This may not strictly be
+ * correct, but the whole point of big_file_threshold
+ * and is_binary check being that we want to avoid
+ * opening the file and inspecting the contents, this
+ * is probably fine.
+ */
if ((flags & CHECK_BINARY) &&
s->size > big_file_threshold && s->is_binary == -1) {
s->is_binary = 1;