Merge branch 'jc/count' into next

* jc/count:
  built-in count-objects.
  pack-objects: update size heuristucs.
  verify-pack: check integrity in a saner order.

5 files changed, 129 insertions, 4 deletions

diff --git a/Makefile b/Makefile
index d2cc01a265..4416af9bb0 100644
--- a/Makefile
+++ b/Makefile
@@ -214,7 +214,7 @@ LIB_OBJS = \
 	$(DIFF_OBJS)
 
 BUILTIN_OBJS = \
-	builtin-log.o builtin-help.o
+	builtin-log.o builtin-help.o builtin-count.o
 
 GITLIBS = $(LIB_FILE) $(XDIFF_LIB)
 LIBS = $(GITLIBS) -lz
diff --git a/builtin-count.c b/builtin-count.c
new file mode 100644
index 0000000000..0256369d5b
--- /dev/null
+++ b/builtin-count.c
@@ -0,0 +1,123 @@
+/*
+ * Builtin "git count-objects".
+ *
+ * Copyright (c) 2006 Junio C Hamano
+ */
+
+#include "cache.h"
+#include "builtin.h"
+
+static const char count_objects_usage[] = "git-count-objects [-v]";
+
+static void count_objects(DIR *d, char *path, int len, int verbose,
+			  unsigned long *loose,
+			  unsigned long *loose_size,
+			  unsigned long *packed_loose,
+			  unsigned long *garbage)
+{
+	struct dirent *ent;
+	while ((ent = readdir(d)) != NULL) {
+		char hex[41];
+		unsigned char sha1[20];
+		const char *cp;
+		int bad = 0;
+
+		if ((ent->d_name[0] == '.') &&
+		    (ent->d_name[1] == 0 ||
+		     ((ent->d_name[1] == '.') && (ent->d_name[2] == 0))))
+			continue;
+		for (cp = ent->d_name; *cp; cp++) {
+			int ch = *cp;
+			if (('0' <= ch && ch <= '9') ||
+			    ('a' <= ch && ch <= 'f'))
+				continue;
+			bad = 1;
+			break;
+		}
+		if (cp - ent->d_name != 38)
+			bad = 1;
+		else {
+			struct stat st;
+			memcpy(path + len + 3, ent->d_name, 38);
+			path[len + 2] = '/';
+			path[len + 41] = 0;
+			if (lstat(path, &st) || !S_ISREG(st.st_mode))
+				bad = 1;
+			else
+				(*loose_size) += st.st_blocks;
+		}
+		if (bad) {
+			if (verbose) {
+				error("garbage found: %.*s/%s",
+				      len + 2, path, ent->d_name);
+				(*garbage)++;
+			}
+			continue;
+		}
+		(*loose)++;
+		if (!verbose)
+			continue;
+		memcpy(hex, path+len, 2);
+		memcpy(hex+2, ent->d_name, 38);
+		hex[40] = 0;
+		if (get_sha1_hex(hex, sha1))
+			die("internal error");
+		if (has_sha1_pack(sha1))
+			(*packed_loose)++;
+	}
+}
+
+int cmd_count_objects(int ac, const char **av, char **ep)
+{
+	int i;
+	int verbose = 0;
+	const char *objdir = get_object_directory();
+	int len = strlen(objdir);
+	char *path = xmalloc(len + 50);
+	unsigned long loose = 0, packed = 0, packed_loose = 0, garbage = 0;
+	unsigned long loose_size = 0;
+
+	for (i = 1; i < ac; i++) {
+		const char *arg = av[i];
+		if (*arg != '-')
+			break;
+		else if (!strcmp(arg, "-v"))
+			verbose = 1;
+		else
+			usage(count_objects_usage);
+	}
+
+	/* we do not take arguments other than flags for now */
+	if (i < ac)
+		usage(count_objects_usage);
+	memcpy(path, objdir, len);
+	if (len && objdir[len-1] != '/')
+		path[len++] = '/';
+	for (i = 0; i < 256; i++) {
+		DIR *d;
+		sprintf(path + len, "%02x", i);
+		d = opendir(path);
+		if (!d)
+			continue;
+		count_objects(d, path, len, verbose,
+			      &loose, &loose_size, &packed_loose, &garbage);
+		closedir(d);
+	}
+	if (verbose) {
+		struct packed_git *p;
+		for (p = packed_git; p; p = p->next) {
+			if (!p->pack_local)
+				continue;
+			packed += num_packed_objects(p);
+		}
+		printf("count: %lu\n", loose);
+		printf("size: %lu\n", loose_size / 2);
+		printf("in-pack: %lu\n", packed);
+		printf("prune-packable: %lu\n", packed_loose);
+		printf("garbage: %lu\n", garbage);
+	}
+	else
+		printf("%lu objects, %lu kilobytes\n",
+		       loose, loose_size / 2);
+	return 0;
+}
diff --git a/builtin.h b/builtin.h
index 94dc0732f9..15bb313ee2 100644
--- a/builtin.h
+++ b/builtin.h
@@ -20,5 +20,6 @@ extern int cmd_whatchanged(int argc, const char **argv, char **envp);
 extern int cmd_show(int argc, const char **argv, char **envp);
 extern int cmd_log(int argc, const char **argv, char **envp);
 extern int cmd_format_patch(int argc, const char **argv, char **envp);
+extern int cmd_count_objects(int argc, const char **argv, char **envp);
 
 #endif
diff --git a/git.c b/git.c
index b761150c29..6d030b01cc 100644
--- a/git.c
+++ b/git.c
@@ -47,6 +47,7 @@ static void handle_internal_command(int argc, const char **argv, char **envp)
 		{ "whatchanged", cmd_whatchanged },
 		{ "show", cmd_show },
 		{ "fmt-patch", cmd_format_patch },
+		{ "count-objects", cmd_count_objects },
 	};
 	int i;
 
diff --git a/pack-check.c b/pack-check.c
index 84ed90d369..e57587909e 100644
--- a/pack-check.c
+++ b/pack-check.c
@@ -29,12 +29,12 @@ static int verify_packfile(struct packed_git *p)
 	pack_base = p->pack_base;
 	SHA1_Update(&ctx, pack_base, pack_size - 20);
 	SHA1_Final(sha1, &ctx);
-	if (memcmp(sha1, index_base + index_size - 40, 20))
-		return error("Packfile %s SHA1 mismatch with idx",
-			     p->pack_name);
 	if (memcmp(sha1, pack_base + pack_size - 20, 20))
 		return error("Packfile %s SHA1 mismatch with itself",
 			     p->pack_name);
+	if (memcmp(sha1, index_base + index_size - 40, 20))
+		return error("Packfile %s SHA1 mismatch with idx",
+			     p->pack_name);
 
 	/* Make sure everything reachable from idx is valid.  Since we
 	 * have verified that nr_objects matches between idx and pack,