[PATCH] git wrapper: DWIM mistyped commands

@@ -358,6 +358,7 @@ LIB_H += graph.h
 LIB_H += grep.h
 LIB_H += hash.h
 LIB_H += help.h
+LIB_H += levenshtein.h
 LIB_H += list-objects.h
 LIB_H += ll-merge.h
 LIB_H += log-tree.h

@@ -433,6 +434,7 @@ LIB_OBJS += hash.o
 LIB_OBJS += help.o
 LIB_OBJS += ident.o
 LIB_OBJS += interpolate.o
+LIB_OBJS += levenshtein.o
 LIB_OBJS += list-objects.o
 LIB_OBJS += ll-merge.o
 LIB_OBJS += lockfile.o

@@ -11,7 +11,7 @@ extern const char git_usage_string[];
 extern const char git_more_info_string[];
 
 extern void list_common_cmds_help(void);
-extern void help_unknown_cmd(const char *cmd);
+extern const char *help_unknown_cmd(const char *cmd);
 extern void prune_packed_objects(int);
 extern int read_line_with_nul(char *buf, int size, FILE *file);
 extern int fmt_merge_msg(int merge_summary, struct strbuf *in,

@@ -499,7 +499,9 @@ int main(int argc, const char **argv)
 				cmd, argv[0]);
 			exit(1);
 		}
-		help_unknown_cmd(cmd);
+		argv[0] = help_unknown_cmd(cmd);
+		handle_internal_command(argc, argv);
+		execv_dashed_external(argv);
 	}
 
 	fprintf(stderr, "Failed to run command '%s': %s\n",

@@ -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_;

@@ -250,9 +261,68 @@ 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);
 }
 

@@ -5,7 +5,7 @@ struct cmdnames {
 	int alloc;
 	int cnt;
 	struct cmdname {
-		size_t len;
+		size_t len; /* also used for similarity index in help.c */
 		char name[FLEX_ARRAY];
 	} **names;
 };

@@ -0,0 +1,47 @@
+#include "cache.h"
+#include "levenshtein.h"
+
+int levenshtein(const char *string1, const char *string2,
+		int w, int s, int a, int d)
+{
+	int len1 = strlen(string1), len2 = strlen(string2);
+	int *row0 = xmalloc(sizeof(int) * (len2 + 1));
+	int *row1 = xmalloc(sizeof(int) * (len2 + 1));
+	int *row2 = xmalloc(sizeof(int) * (len2 + 1));
+	int i, j;
+
+	for (j = 0; j <= len2; j++)
+		row1[j] = j * a;
+	for (i = 0; i < len1; i++) {
+		int *dummy;
+
+		row2[0] = (i + 1) * d;
+		for (j = 0; j < len2; j++) {
+			/* substitution */
+			row2[j + 1] = row1[j] + s * (string1[i] != string2[j]);
+			/* swap */
+			if (i > 0 && j > 0 && string1[i - 1] == string2[j] &&
+					string1[i] == string2[j - 1] &&
+					row2[j + 1] > row0[j - 1] + w)
+				row2[j + 1] = row0[j - 1] + w;
+			/* deletion */
+			if (j + 1 < len2 && row2[j + 1] > row1[j + 1] + d)
+				row2[j + 1] = row1[j + 1] + d;
+			/* insertion */
+			if (row2[j + 1] > row2[j] + a)
+				row2[j + 1] = row2[j] + a;
+		}
+
+		dummy = row0;
+		row0 = row1;
+		row1 = row2;
+		row2 = dummy;
+	}
+
+	i = row1[len2];
+	free(row0);
+	free(row1);
+	free(row2);
+
+	return i;
+}

@@ -0,0 +1,8 @@
+#ifndef LEVENSHTEIN_H
+#define LEVENSHTEIN_H
+
+int levenshtein(const char *string1, const char *string2,
+	int swap_penalty, int substition_penalty,
+	int insertion_penalty, int deletion_penalty);
+
+#endif

@@ -790,6 +790,15 @@ help.format::
 	Values 'man', 'info', 'web' and 'html' are supported. 'man' is
 	the default. 'web' and 'html' are the same.
 
+help.autocorrect::
+	Automatically correct and execute mistyped commands after
+	waiting for the given number of deciseconds (0.1 sec). If more
+	than one command can be deduced from the entered text, nothing
+	will be executed.  If the value of this option is negative,
+	the corrected command will be executed immediately. If the
+	value is 0 - the command will be just shown but not executed.
+	This is the default.
+
 http.proxy::
 	Override the HTTP proxy, normally configured using the 'http_proxy'
 	environment variable (see linkgit:curl[1]).  This can be overridden

@@ -261,6 +261,16 @@ int is_in_cmdlist(struct cmdnames *c, const char *s)
 	return 0;
 }
 
+static int autocorrect;
+
+static int git_unknown_cmd_config(const char *var, const char *value, void *cb)
+{
+	if (!strcmp(var, "help.autocorrect"))
+		autocorrect = git_config_int(var,value);
+
+	return git_default_config(var, value, cb);
+}
+
 static int levenshtein_compare(const void *p1, const void *p2)
 {
 	const struct cmdname *const *c1 = p1, *const *c2 = p2;

@@ -278,6 +288,8 @@ const char *help_unknown_cmd(const char *cmd)
 	memset(&main_cmds, 0, sizeof(main_cmds));
 	memset(&other_cmds, 0, sizeof(main_cmds));
 
+	git_config(git_unknown_cmd_config, NULL);
+
 	load_command_list("git-", &main_cmds, &other_cmds);
 
 	ALLOC_GROW(main_cmds.names, main_cmds.cnt + other_cmds.cnt,

@@ -302,7 +314,7 @@ const char *help_unknown_cmd(const char *cmd)
 	n = 1;
 	while (n < main_cmds.cnt && best_similarity == main_cmds.names[n]->len)
 		++n;
-	if (n == 1) {
+	if (autocorrect && n == 1) {
 		const char *assumed = main_cmds.names[0]->name;
 		main_cmds.names[0] = NULL;
 		clean_cmdnames(&main_cmds);

@@ -310,6 +322,11 @@ const char *help_unknown_cmd(const char *cmd)
 			"which does not exist.\n"
 			"Continuing under the assumption that you meant '%s'\n",
 			cmd, assumed);
+		if (autocorrect > 0) {
+			fprintf(stderr, "in %0.1f seconds automatically...\n",
+				(float)autocorrect/10.0);
+			poll(NULL, 0, autocorrect * 100);
+		}
 		return assumed;
 	}