sequencer: truncate labels to accommodate loose refs
Some commits may have unusually long subject lines. When those subject
lines are used as labels in the `--rebase-merges` mode of `git rebase`,
they can cause errors when writing the corresponding loose refs because
most file systems have a maximal file name length of 255 (`NAME_MAX`).
The symptom looks like this:
$ git rebase --continue
error: cannot lock ref 'refs/rewritten/SANITIZED-SUBJECT': Unable to create '.git/refs/rewritten/SANITIZED-SUBJECT.lock': File name too long - where SANITIZED-SUBJECT is very long
Let's accommodate this situation by truncating the labels.
Care must be taken in case the subject line contains multi-byte
characters so as not to truncate in the middle of a character.
Signed-off-by: Mark Ruvald Pedersen <mped@demant.com>
Signed-off-by: Johannes Schindelin <Johannes.Schindelin@gmx.de>
Signed-off-by: Junio C Hamano <gitster@pobox.com>
diff --git a/sequencer.c b/sequencer.c
index bceb6ab..c3e23a9 100644
--- a/sequencer.c
+++ b/sequencer.c
@@ -50,6 +50,15 @@
#define GIT_REFLOG_ACTION "GIT_REFLOG_ACTION"
+/*
+ * To accommodate common filesystem limitations, where the loose refs' file
+ * names must not exceed `NAME_MAX`, the labels generated by `git rebase
+ * --rebase-merges` need to be truncated if the corresponding commit subjects
+ * are too long.
+ * Add some margin to stay clear from reaching `NAME_MAX`.
+ */
+#define GIT_MAX_LABEL_LENGTH ((NAME_MAX) - (LOCK_SUFFIX_LEN) - 16)
+
static const char sign_off_header[] = "Signed-off-by: ";
static const char cherry_picked_prefix[] = "(cherry picked from commit ";
@@ -5386,6 +5395,8 @@ static const char *label_oid(struct object_id *oid, const char *label,
}
} else {
struct strbuf *buf = &state->buf;
+ int label_is_utf8 = 1; /* start with this assumption */
+ size_t max_len = buf->len + GIT_MAX_LABEL_LENGTH;
/*
* Sanitize labels by replacing non-alpha-numeric characters
@@ -5394,14 +5405,34 @@ static const char *label_oid(struct object_id *oid, const char *label,
*
* Note that we retain non-ASCII UTF-8 characters (identified
* via the most significant bit). They should be all acceptable
- * in file names. We do not validate the UTF-8 here, that's not
- * the job of this function.
+ * in file names.
+ *
+ * As we will use the labels as names of (loose) refs, it is
+ * vital that the name not be longer than the maximum component
+ * size of the file system (`NAME_MAX`). We are careful to
+ * truncate the label accordingly, allowing for the `.lock`
+ * suffix and for the label to be UTF-8 encoded (i.e. we avoid
+ * truncating in the middle of a character).
*/
- for (; *label; label++)
- if ((*label & 0x80) || isalnum(*label))
+ for (; *label && buf->len + 1 < max_len; label++)
+ if (isalnum(*label) ||
+ (!label_is_utf8 && (*label & 0x80)))
strbuf_addch(buf, *label);
+ else if (*label & 0x80) {
+ const char *p = label;
+
+ utf8_width(&p, NULL);
+ if (p) {
+ if (buf->len + (p - label) > max_len)
+ break;
+ strbuf_add(buf, label, p - label);
+ label = p - 1;
+ } else {
+ label_is_utf8 = 0;
+ strbuf_addch(buf, *label);
+ }
/* avoid leading dash and double-dashes */
- else if (buf->len && buf->buf[buf->len - 1] != '-')
+ } else if (buf->len && buf->buf[buf->len - 1] != '-')
strbuf_addch(buf, '-');
if (!buf->len) {
strbuf_addstr(buf, "rev-");
