git wrapper: DWIM mistyped commands

This patch introduces a modified Damerau-Levenshtein algorithm into
Git's code base, and uses it with the following penalties to show some
similar commands when an unknown command was encountered:

	swap = 0, insertion = 1, substitution = 2, deletion = 4

A typical output would now look like this:

	$ git sm
	git: 'sm' is not a git-command. See 'git --help'.

	Did you mean one of these?
		am
		rm

The cut-off is at similarity rating 6, which was empirically determined
to give sensible results.

As a convenience, if there is only one candidate, Git continues under
the assumption that the user mistyped it.  Example:

	$ git reabse
	WARNING: You called a Git program named 'reabse', which does
	not exist.
	Continuing under the assumption that you meant 'rebase'
	[...]

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

1 files changed, 71 insertions, 1 deletions

diff --git a/help.c b/help.c
index 1afbac0927..b1ebca4091 100644
--- a/help.c
+++ b/help.c
@@ -1,6 +1,7 @@
 #include "cache.h"
 #include "builtin.h"
 #include "exec_cmd.h"
+#include "levenshtein.h"
 #include "help.h"
 
 /* most GUI terminals set COLUMNS (although some don't export it) */
@@ -37,6 +38,16 @@ void add_cmdname(struct cmdnames *cmds, const char *name, int len)
 	cmds->names[cmds->cnt++] = ent;
 }
 
+static void clean_cmdnames(struct cmdnames *cmds)
+{
+	int i;
+	for (i = 0; i < cmds->cnt; ++i)
+		free(cmds->names[i]);
+	free(cmds->names);
+	cmds->cnt = 0;
+	cmds->alloc = 0;
+}
+
 static int cmdname_compare(const void *a_, const void *b_)
 {
 	struct cmdname *a = *(struct cmdname **)a_;
@@ -257,9 +268,68 @@ int is_in_cmdlist(struct cmdnames *c, const char *s)
 	return 0;
 }
 
-void help_unknown_cmd(const char *cmd)
+static int levenshtein_compare(const void *p1, const void *p2)
+{
+	const struct cmdname *const *c1 = p1, *const *c2 = p2;
+	const char *s1 = (*c1)->name, *s2 = (*c2)->name;
+	int l1 = (*c1)->len;
+	int l2 = (*c2)->len;
+	return l1 != l2 ? l1 - l2 : strcmp(s1, s2);
+}
+
+const char *help_unknown_cmd(const char *cmd)
 {
+	int i, n, best_similarity = 0;
+	struct cmdnames main_cmds, other_cmds;
+
+	memset(&main_cmds, 0, sizeof(main_cmds));
+	memset(&other_cmds, 0, sizeof(main_cmds));
+
+	load_command_list("git-", &main_cmds, &other_cmds);
+
+	ALLOC_GROW(main_cmds.names, main_cmds.cnt + other_cmds.cnt,
+		   main_cmds.alloc);
+	memcpy(main_cmds.names + main_cmds.cnt, other_cmds.names,
+	       other_cmds.cnt * sizeof(other_cmds.names[0]));
+	main_cmds.cnt += other_cmds.cnt;
+	free(other_cmds.names);
+
+	/* This reuses cmdname->len for similarity index */
+	for (i = 0; i < main_cmds.cnt; ++i)
+		main_cmds.names[i]->len =
+			levenshtein(cmd, main_cmds.names[i]->name, 0, 2, 1, 4);
+
+	qsort(main_cmds.names, main_cmds.cnt,
+	      sizeof(*main_cmds.names), levenshtein_compare);
+
+	if (!main_cmds.cnt)
+		die ("Uh oh. Your system reports no Git commands at all.");
+
+	best_similarity = main_cmds.names[0]->len;
+	n = 1;
+	while (n < main_cmds.cnt && best_similarity == main_cmds.names[n]->len)
+		++n;
+	if (n == 1) {
+		const char *assumed = main_cmds.names[0]->name;
+		main_cmds.names[0] = NULL;
+		clean_cmdnames(&main_cmds);
+		fprintf(stderr, "WARNING: You called a Git program named '%s', "
+			"which does not exist.\n"
+			"Continuing under the assumption that you meant '%s'\n",
+			cmd, assumed);
+		return assumed;
+	}
+
 	fprintf(stderr, "git: '%s' is not a git-command. See 'git --help'.\n", cmd);
+
+	if (best_similarity < 6) {
+		fprintf(stderr, "\nDid you mean %s?\n",
+			n < 2 ? "this": "one of these");
+
+		for (i = 0; i < n; i++)
+			fprintf(stderr, "\t%s\n", main_cmds.names[i]->name);
+	}
+
 	exit(1);
 }