count-objects: report garbage files in pack directory too

prepare_packed_git_one() is modified to allow count-objects to hook a
report function to so we don't need to duplicate the pack searching
logic in count-objects.c. When report_pack_garbage is NULL, the
overhead is insignificant.

The garbage is reported with warning() instead of error() in packed
garbage case because it's not an error to have garbage. Loose garbage
is still reported as errors and will be converted to warnings later.

Signed-off-by: Nguyễn Thái Ngọc Duy <pclouds@gmail.com>
Signed-off-by: Junio C Hamano <gitster@pobox.com>

1 files changed, 82 insertions, 1 deletions

diff --git a/sha1_file.c b/sha1_file.c
index 239bee7..16967d3 100644
--- a/sha1_file.c
+++ b/sha1_file.c
@@ -21,6 +21,7 @@
 #include "sha1-lookup.h"
 #include "bulk-checkin.h"
 #include "streaming.h"
+#include "dir.h"
 
 #ifndef O_NOATIME
 #if defined(__linux__) && (defined(__i386__) || defined(__PPC__))
@@ -1000,6 +1001,63 @@ void install_packed_git(struct packed_git *pack)
 	packed_git = pack;
 }
 
+void (*report_garbage)(const char *desc, const char *path);
+
+static void report_helper(const struct string_list *list,
+			  int seen_bits, int first, int last)
+{
+	const char *msg;
+	switch (seen_bits) {
+	case 0:
+		msg = "no corresponding .idx nor .pack";
+		break;
+	case 1:
+		msg = "no corresponding .idx";
+		break;
+	case 2:
+		msg = "no corresponding .pack";
+		break;
+	default:
+		return;
+	}
+	for (; first < last; first++)
+		report_garbage(msg, list->items[first].string);
+}
+
+static void report_pack_garbage(struct string_list *list)
+{
+	int i, baselen = -1, first = 0, seen_bits = 0;
+
+	if (!report_garbage)
+		return;
+
+	sort_string_list(list);
+
+	for (i = 0; i < list->nr; i++) {
+		const char *path = list->items[i].string;
+		if (baselen != -1 &&
+		    strncmp(path, list->items[first].string, baselen)) {
+			report_helper(list, seen_bits, first, i);
+			baselen = -1;
+			seen_bits = 0;
+		}
+		if (baselen == -1) {
+			const char *dot = strrchr(path, '.');
+			if (!dot) {
+				report_garbage("garbage found", path);
+				continue;
+			}
+			baselen = dot - path + 1;
+			first = i;
+		}
+		if (!strcmp(path + baselen, "pack"))
+			seen_bits |= 1;
+		else if (!strcmp(path + baselen, "idx"))
+			seen_bits |= 2;
+	}
+	report_helper(list, seen_bits, first, list->nr);
+}
+
 static void prepare_packed_git_one(char *objdir, int local)
 {
 	/* Ensure that this buffer is large enough so that we can
@@ -1009,6 +1067,7 @@ static void prepare_packed_git_one(char *objdir, int local)
 	int len;
 	DIR *dir;
 	struct dirent *de;
+	struct string_list garbage = STRING_LIST_INIT_DUP;
 
 	sprintf(path, "%s/pack", objdir);
 	len = strlen(path);
@@ -1024,7 +1083,17 @@ static void prepare_packed_git_one(char *objdir, int local)
 		int namelen = strlen(de->d_name);
 		struct packed_git *p;
 
-		if (len + namelen + 1 > sizeof(path))
+		if (len + namelen + 1 > sizeof(path)) {
+			if (report_garbage) {
+				struct strbuf sb = STRBUF_INIT;
+				strbuf_addf(&sb, "%.*s/%s", len - 1, path, de->d_name);
+				report_garbage("path too long", sb.buf);
+				strbuf_release(&sb);
+			}
+			continue;
+		}
+
+		if (is_dot_or_dotdot(de->d_name))
 			continue;
 
 		strcpy(path + len, de->d_name);
@@ -1043,8 +1112,20 @@ static void prepare_packed_git_one(char *objdir, int local)
 			    (p = add_packed_git(path, len + namelen, local)) != NULL)
 				install_packed_git(p);
 		}
+
+		if (!report_garbage)
+			continue;
+
+		if (has_extension(de->d_name, ".idx") ||
+		    has_extension(de->d_name, ".pack") ||
+		    has_extension(de->d_name, ".keep"))
+			string_list_append(&garbage, path);
+		else
+			report_garbage("garbage found", path);
 	}
 	closedir(dir);
+	report_pack_garbage(&garbage);
+	string_list_clear(&garbage, 0);
 }
 
 static int sort_pack(const void *a_, const void *b_)