help: always suggest common-cmds if prefix of cmd

If someone runs "git st", the command "git status" is not suggested
because it's not one of the closest levenshtein-neighbour.

Reserve the distance of 0 for common commands where the entered command
is a prefixe, as these are often more likely to be what the user meant.

This way, "git status" is the first suggestion, while a list of possible
typos are still suggested as well.

Signed-off-by: Erik Faye-Lund <kusmabite@gmail.com>
Signed-off-by: Junio C Hamano <gitster@pobox.com>

2 files changed, 41 insertions, 8 deletions

diff --git a/Makefile b/Makefile
index 919ed2b7ec..7baa621c19 100644
--- a/Makefile
+++ b/Makefile
@@ -1620,6 +1620,8 @@ git$X: git.o $(BUILTIN_OBJS) $(GITLIBS)
 	$(QUIET_LINK)$(CC) $(ALL_CFLAGS) -o $@ git.o \
 		$(BUILTIN_OBJS) $(ALL_LDFLAGS) $(LIBS)
 
+help.o: common-cmds.h
+
 builtin/help.o: common-cmds.h
 builtin/help.s builtin/help.o: EXTRA_CPPFLAGS = \
 	'-DGIT_HTML_PATH="$(htmldir_SQ)"' \
diff --git a/help.c b/help.c
index 7f4928e459..7654f1bfd6 100644
--- a/help.c
+++ b/help.c
@@ -3,6 +3,7 @@
 #include "exec_cmd.h"
 #include "levenshtein.h"
 #include "help.h"
+#include "common-cmds.h"
 
 /* most GUI terminals set COLUMNS (although some don't export it) */
 static int term_columns(void)
@@ -298,7 +299,8 @@ static void add_cmd_list(struct cmdnames *cmds, struct cmdnames *old)
 }
 
 /* An empirically derived magic number */
-#define SIMILAR_ENOUGH(x) ((x) < 6)
+#define SIMILARITY_FLOOR 7
+#define SIMILAR_ENOUGH(x) ((x) < SIMILARITY_FLOOR)
 
 const char *help_unknown_cmd(const char *cmd)
 {
@@ -319,10 +321,28 @@ const char *help_unknown_cmd(const char *cmd)
 	      sizeof(main_cmds.names), cmdname_compare);
 	uniq(&main_cmds);
 
-	/* This reuses cmdname->len for similarity index */
-	for (i = 0; i < main_cmds.cnt; ++i)
+	/* This abuses cmdname->len for levenshtein distance */
+	for (i = 0, n = 0; i < main_cmds.cnt; i++) {
+		int cmp = 0; /* avoid compiler stupidity */
+		const char *candidate = main_cmds.names[i]->name;
+
+		/* Does the candidate appear in common_cmds list? */
+		while (n < ARRAY_SIZE(common_cmds) &&
+		       (cmp = strcmp(common_cmds[n].name, candidate)) < 0)
+			n++;
+		if ((n < ARRAY_SIZE(common_cmds)) && !cmp) {
+			/* Yes, this is one of the common commands */
+			n++; /* use the entry from common_cmds[] */
+			if (!prefixcmp(candidate, cmd)) {
+				/* Give prefix match a very good score */
+				main_cmds.names[i]->len = 0;
+				continue;
+			}
+		}
+
 		main_cmds.names[i]->len =
-			levenshtein(cmd, main_cmds.names[i]->name, 0, 2, 1, 4);
+			levenshtein(cmd, candidate, 0, 2, 1, 4) + 1;
+	}
 
 	qsort(main_cmds.names, main_cmds.cnt,
 	      sizeof(*main_cmds.names), levenshtein_compare);
@@ -330,10 +350,21 @@ const char *help_unknown_cmd(const char *cmd)
 	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;
+	/* skip and count prefix matches */
+	for (n = 0; n < main_cmds.cnt && !main_cmds.names[n]->len; n++)
+		; /* still counting */
+
+	if (main_cmds.cnt <= n) {
+		/* prefix matches with everything? that is too ambiguous */
+		best_similarity = SIMILARITY_FLOOR + 1;
+	} else {
+		/* count all the most similar ones */
+		for (best_similarity = main_cmds.names[n++]->len;
+		     (n < main_cmds.cnt &&
+		      best_similarity == main_cmds.names[n]->len);
+		     n++)
+			; /* still counting */
+	}
 	if (autocorrect && n == 1 && SIMILAR_ENOUGH(best_similarity)) {
 		const char *assumed = main_cmds.names[0]->name;
 		main_cmds.names[0] = NULL;