Merge branch 'jc/count'

* jc/count:
  builtin-count-objects: open packs when running -v
  builtin-count-objects: make it official.
  built-in count-objects.

6 files changed, 141 insertions, 35 deletions

diff --git a/Documentation/git-count-objects.txt b/Documentation/git-count-objects.txt
index 47216f4..198ce77 100644
--- a/Documentation/git-count-objects.txt
+++ b/Documentation/git-count-objects.txt
@@ -7,13 +7,23 @@ git-count-objects - Reports on unpacked objects
 
 SYNOPSIS
 --------
-'git-count-objects'
+'git-count-objects' [-v]
 
 DESCRIPTION
 -----------
 This counts the number of unpacked object files and disk space consumed by
 them, to help you decide when it is a good time to repack.
 
+
+OPTIONS
+-------
+-v::
+	In addition to the number of loose objects and disk
+	space consumed, it reports the number of in-pack
+	objects, and number of objects that can be removed by
+	running `git-prune-packed`.
+
+
 Author
 ------
 Written by Junio C Hamano <junkio@cox.net>
diff --git a/Makefile b/Makefile
index 9cb40a8..67559c9 100644
--- a/Makefile
+++ b/Makefile
@@ -115,7 +115,7 @@ SPARSE_FLAGS = -D__BIG_ENDIAN__ -D__powerpc__
 SCRIPT_SH = \
 	git-add.sh git-bisect.sh git-branch.sh git-checkout.sh \
 	git-cherry.sh git-clean.sh git-clone.sh git-commit.sh \
-	git-count-objects.sh git-diff.sh git-fetch.sh \
+	git-diff.sh git-fetch.sh \
 	git-format-patch.sh git-ls-remote.sh \
 	git-merge-one-file.sh git-parse-remote.sh \
 	git-prune.sh git-pull.sh git-rebase.sh \
@@ -168,7 +168,7 @@ PROGRAMS = \
 	git-describe$X git-merge-tree$X git-blame$X git-imap-send$X
 
 BUILT_INS = git-log$X \
-	git-push$X
+	git-count-objects$X git-push$X
 
 # what 'all' will build and 'install' will install, in gitexecdir
 ALL_PROGRAMS = $(PROGRAMS) $(SIMPLE_PROGRAMS) $(SCRIPTS)
@@ -215,7 +215,7 @@ LIB_OBJS = \
 	$(DIFF_OBJS)
 
 BUILTIN_OBJS = \
-	builtin-log.o builtin-help.o builtin-push.o
+	builtin-log.o builtin-help.o builtin-count.o builtin-push.o
 
 GITLIBS = $(LIB_FILE) $(XDIFF_LIB)
 LIBS = $(GITLIBS) -lz
diff --git a/builtin-count.c b/builtin-count.c
new file mode 100644
index 0000000..5ee72df
--- /dev/null
+++ b/builtin-count.c
@@ -0,0 +1,125 @@
+/*
+ * 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;
+		if (!packed_git)
+			prepare_packed_git();
+		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 94fa9b5..dca6963 100644
--- a/builtin.h
+++ b/builtin.h
@@ -19,6 +19,7 @@ extern int cmd_version(int argc, const char **argv, char **envp);
 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_count_objects(int argc, const char **argv, char **envp);
 
 extern int cmd_push(int argc, const char **argv, char **envp);
 
diff --git a/git-count-objects.sh b/git-count-objects.sh
deleted file mode 100755
index 40c58ef..0000000
--- a/git-count-objects.sh
+++ /dev/null
@@ -1,31 +0,0 @@
-#!/bin/sh
-#
-# Copyright (c) 2005 Junio C Hamano
-#
-
-GIT_DIR=`git-rev-parse --git-dir` || exit $?
-
-dc </dev/null 2>/dev/null || {
-	# This is not a real DC at all -- it just knows how
-	# this script feeds DC and does the computation itself.
-	dc () {
-		while read a b
-		do
-			case $a,$b in
-			0,)	acc=0 ;;
-			*,+)	acc=$(($acc + $a)) ;;
-			p,)	echo "$acc" ;;
-			esac
-		done
-	}
-}
-
-echo $(find "$GIT_DIR/objects"/?? -type f -print 2>/dev/null | wc -l) objects, \
-$({
-    echo 0
-    # "no-such" is to help Darwin folks by not using xargs -r.
-    find "$GIT_DIR/objects"/?? -type f -print 2>/dev/null |
-    xargs du -k "$GIT_DIR/objects/no-such" 2>/dev/null |
-    sed -e 's/[ 	].*/ +/'
-    echo p
-} | dc) kilobytes
diff --git a/git.c b/git.c
index fd479e9..4d3a5a3 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 },
 		{ "push", cmd_push },
+		{ "count-objects", cmd_count_objects },
 	};
 	int i;