Merge branch 'mp/rebase-label-length-limit'

Overly long label names used in the sequencer machinery are now
chopped to fit under filesystem limitation.

* mp/rebase-label-length-limit:
  rebase: allow overriding the maximal length of the generated labels
  sequencer: truncate labels to accommodate loose refs

1 files changed, 41 insertions, 6 deletions

diff --git a/sequencer.c b/sequencer.c
index fcf5a7eba0..48475d1cc6 100644
--- a/sequencer.c
+++ b/sequencer.c
@@ -51,6 +51,15 @@
 
 #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 ";
 
@@ -5352,6 +5361,7 @@ struct label_state {
 	struct oidmap commit2label;
 	struct hashmap labels;
 	struct strbuf buf;
+	int max_label_length;
 };
 
 static const char *label_oid(struct object_id *oid, const char *label,
@@ -5408,6 +5418,8 @@ 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 + state->max_label_length;
 
 		/*
 		 * Sanitize labels by replacing non-alpha-numeric characters
@@ -5416,14 +5428,34 @@ 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-");
@@ -5485,7 +5517,8 @@ static int make_script_with_merges(struct pretty_print_context *pp,
 	struct string_entry *entry;
 	struct oidset interesting = OIDSET_INIT, child_seen = OIDSET_INIT,
 		shown = OIDSET_INIT;
-	struct label_state state = { OIDMAP_INIT, { NULL }, STRBUF_INIT };
+	struct label_state state =
+		{ OIDMAP_INIT, { NULL }, STRBUF_INIT, GIT_MAX_LABEL_LENGTH };
 
 	int abbr = flags & TODO_LIST_ABBREVIATE_CMDS;
 	const char *cmd_pick = abbr ? "p" : "pick",
@@ -5493,6 +5526,8 @@ static int make_script_with_merges(struct pretty_print_context *pp,
 		*cmd_reset = abbr ? "t" : "reset",
 		*cmd_merge = abbr ? "m" : "merge";
 
+	git_config_get_int("rebase.maxlabellength", &state.max_label_length);
+
 	oidmap_init(&commit2todo, 0);
 	oidmap_init(&state.commit2label, 0);
 	hashmap_init(&state.labels, labels_cmp, NULL, 0);