rebase -i: rearrange fixup/squash lines using the rebase--helper

This operation has quadratic complexity, which is especially painful
on Windows, where shell scripts are *already* slow (mainly due to the
overhead of the POSIX emulation layer).

Let's reimplement this with linear complexity (using a hash map to
match the commits' subject lines) for the common case; Sadly, the
fixup/squash feature's design neglected performance considerations,
allowing arbitrary prefixes (read: `fixup! hell` will match the
commit subject `hello world`), which means that we are stuck with
quadratic performance in the worst case.

The reimplemented logic also happens to fix a bug where commented-out
lines (representing empty patches) were dropped by the previous code.

While at it, clarify how the fixup/squash feature works in `git rebase
-i`'s man page.

Signed-off-by: Johannes Schindelin <johannes.schindelin@gmx.de>
Signed-off-by: Junio C Hamano <gitster@pobox.com>

1 files changed, 196 insertions, 0 deletions

diff --git a/sequencer.c b/sequencer.c
index 96d43aec76..c54596f969 100644
--- a/sequencer.c
+++ b/sequencer.c
@@ -20,6 +20,7 @@
 #include "trailer.h"
 #include "log-tree.h"
 #include "wt-status.h"
+#include "hashmap.h"
 
 #define GIT_REFLOG_ACTION "GIT_REFLOG_ACTION"
 
@@ -2748,3 +2749,198 @@ int skip_unnecessary_picks(void)
 
 	return 0;
 }
+
+struct subject2item_entry {
+	struct hashmap_entry entry;
+	int i;
+	char subject[FLEX_ARRAY];
+};
+
+static int subject2item_cmp(const void *fndata,
+			    const struct subject2item_entry *a,
+			    const struct subject2item_entry *b, const void *key)
+{
+	return key ? strcmp(a->subject, key) : strcmp(a->subject, b->subject);
+}
+
+/*
+ * Rearrange the todo list that has both "pick commit-id msg" and "pick
+ * commit-id fixup!/squash! msg" in it so that the latter is put immediately
+ * after the former, and change "pick" to "fixup"/"squash".
+ *
+ * Note that if the config has specified a custom instruction format, each log
+ * message will have to be retrieved from the commit (as the oneline in the
+ * script cannot be trusted) in order to normalize the autosquash arrangement.
+ */
+int rearrange_squash(void)
+{
+	const char *todo_file = rebase_path_todo();
+	struct todo_list todo_list = TODO_LIST_INIT;
+	struct hashmap subject2item;
+	int res = 0, rearranged = 0, *next, *tail, fd, i;
+	char **subjects;
+
+	fd = open(todo_file, O_RDONLY);
+	if (fd < 0)
+		return error_errno(_("could not open '%s'"), todo_file);
+	if (strbuf_read(&todo_list.buf, fd, 0) < 0) {
+		close(fd);
+		return error(_("could not read '%s'."), todo_file);
+	}
+	close(fd);
+	if (parse_insn_buffer(todo_list.buf.buf, &todo_list) < 0) {
+		todo_list_release(&todo_list);
+		return -1;
+	}
+
+	/*
+	 * The hashmap maps onelines to the respective todo list index.
+	 *
+	 * If any items need to be rearranged, the next[i] value will indicate
+	 * which item was moved directly after the i'th.
+	 *
+	 * In that case, last[i] will indicate the index of the latest item to
+	 * be moved to appear after the i'th.
+	 */
+	hashmap_init(&subject2item, (hashmap_cmp_fn) subject2item_cmp,
+		     NULL, todo_list.nr);
+	ALLOC_ARRAY(next, todo_list.nr);
+	ALLOC_ARRAY(tail, todo_list.nr);
+	ALLOC_ARRAY(subjects, todo_list.nr);
+	for (i = 0; i < todo_list.nr; i++) {
+		struct strbuf buf = STRBUF_INIT;
+		struct todo_item *item = todo_list.items + i;
+		const char *commit_buffer, *subject, *p;
+		size_t subject_len;
+		int i2 = -1;
+		struct subject2item_entry *entry;
+
+		next[i] = tail[i] = -1;
+		if (item->command >= TODO_EXEC) {
+			subjects[i] = NULL;
+			continue;
+		}
+
+		if (is_fixup(item->command)) {
+			todo_list_release(&todo_list);
+			return error(_("the script was already rearranged."));
+		}
+
+		item->commit->util = item;
+
+		parse_commit(item->commit);
+		commit_buffer = get_commit_buffer(item->commit, NULL);
+		find_commit_subject(commit_buffer, &subject);
+		format_subject(&buf, subject, " ");
+		subject = subjects[i] = strbuf_detach(&buf, &subject_len);
+		unuse_commit_buffer(item->commit, commit_buffer);
+		if ((skip_prefix(subject, "fixup! ", &p) ||
+		     skip_prefix(subject, "squash! ", &p))) {
+			struct commit *commit2;
+
+			for (;;) {
+				while (isspace(*p))
+					p++;
+				if (!skip_prefix(p, "fixup! ", &p) &&
+				    !skip_prefix(p, "squash! ", &p))
+					break;
+			}
+
+			if ((entry = hashmap_get_from_hash(&subject2item,
+							   strhash(p), p)))
+				/* found by title */
+				i2 = entry->i;
+			else if (!strchr(p, ' ') &&
+				 (commit2 =
+				  lookup_commit_reference_by_name(p)) &&
+				 commit2->util)
+				/* found by commit name */
+				i2 = (struct todo_item *)commit2->util
+					- todo_list.items;
+			else {
+				/* copy can be a prefix of the commit subject */
+				for (i2 = 0; i2 < i; i2++)
+					if (subjects[i2] &&
+					    starts_with(subjects[i2], p))
+						break;
+				if (i2 == i)
+					i2 = -1;
+			}
+		}
+		if (i2 >= 0) {
+			rearranged = 1;
+			todo_list.items[i].command =
+				starts_with(subject, "fixup!") ?
+				TODO_FIXUP : TODO_SQUASH;
+			if (next[i2] < 0)
+				next[i2] = i;
+			else
+				next[tail[i2]] = i;
+			tail[i2] = i;
+		} else if (!hashmap_get_from_hash(&subject2item,
+						strhash(subject), subject)) {
+			FLEX_ALLOC_MEM(entry, subject, subject, subject_len);
+			entry->i = i;
+			hashmap_entry_init(entry, strhash(entry->subject));
+			hashmap_put(&subject2item, entry);
+		}
+	}
+
+	if (rearranged) {
+		struct strbuf buf = STRBUF_INIT;
+
+		for (i = 0; i < todo_list.nr; i++) {
+			enum todo_command command = todo_list.items[i].command;
+			int cur = i;
+
+			/*
+			 * Initially, all commands are 'pick's. If it is a
+			 * fixup or a squash now, we have rearranged it.
+			 */
+			if (is_fixup(command))
+				continue;
+
+			while (cur >= 0) {
+				int offset = todo_list.items[cur].offset_in_buf;
+				int end_offset = cur + 1 < todo_list.nr ?
+					todo_list.items[cur + 1].offset_in_buf :
+					todo_list.buf.len;
+				char *bol = todo_list.buf.buf + offset;
+				char *eol = todo_list.buf.buf + end_offset;
+
+				/* replace 'pick', by 'fixup' or 'squash' */
+				command = todo_list.items[cur].command;
+				if (is_fixup(command)) {
+					strbuf_addstr(&buf,
+						todo_command_info[command].str);
+					bol += strcspn(bol, " \t");
+				}
+
+				strbuf_add(&buf, bol, eol - bol);
+
+				cur = next[cur];
+			}
+		}
+
+		fd = open(todo_file, O_WRONLY);
+		if (fd < 0)
+			res = error_errno(_("could not open '%s'"), todo_file);
+		else if (write(fd, buf.buf, buf.len) < 0)
+			res = error_errno(_("could not read '%s'."), todo_file);
+		else if (ftruncate(fd, buf.len) < 0)
+			res = error_errno(_("could not finish '%s'"),
+					   todo_file);
+		close(fd);
+		strbuf_release(&buf);
+	}
+
+	free(next);
+	free(tail);
+	for (i = 0; i < todo_list.nr; i++)
+		free(subjects[i]);
+	free(subjects);
+	hashmap_free(&subject2item, 1);
+	todo_list_release(&todo_list);
+
+	return res;
+}