[PATCH] C version of git-count-objects

[Peter Hagervall <hager@cs.umu.se>]

Answering the call Linus made[1], sort of, but for a completely
different program.

Anyway, it ought to be at least as portable as the shell script, and a
whole lot faster, however much that matters.

Signed-off-by: Peter Hagervall <hager@cs.umu.se>

[1] http://article.gmane.org/gmane.comp.version-control.git/19073

---

 Makefile             |    5 +--
 count-objects.c      |   56 +++++++++++++++++++++++++++++++++++++
 git-count-objects.sh |   31 --------------------
 3 files changed, 59 insertions(+), 33 deletions(-)


diff --git a/Makefile b/Makefile
index 8ce27a6..53e7591 100644
--- a/Makefile
+++ b/Makefile
@@ -115,7 +115,7 @@ ### --- END CONFIGURATION SECTION ---
 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-push.sh git-rebase.sh \
@@ -165,7 +165,8 @@ PROGRAMS = \
 	git-upload-pack$X git-verify-pack$X git-write-tree$X \
 	git-update-ref$X git-symbolic-ref$X git-check-ref-format$X \
 	git-name-rev$X git-pack-redundant$X git-repo-config$X git-var$X \
-	git-describe$X git-merge-tree$X git-blame$X git-imap-send$X
+	git-describe$X git-merge-tree$X git-blame$X git-imap-send$X \
+	git-count-objects$X
 
 BUILT_INS = git-log$X
 
diff --git a/count-objects.c b/count-objects.c
new file mode 100644
index 0000000..67ab6f0
--- /dev/null
+++ b/count-objects.c
@@ -0,0 +1,56 @@
+#include "cache.h"
+#include "git-compat-util.h"
+
+static char pathname[PATH_MAX + 1];
+static int numobjects, numblocks;
+static const char hex_digits[] = "0123456789abcdef";
+
+void count_objects(void)
+{
+	char subdir[3];
+	int i, j;
+	struct stat statbuf;
+	struct dirent *dirp;
+	DIR *dp;
+	subdir[2] = '\0';
+	for (i = 0; i < 16; i++) {
+		subdir[0] = hex_digits[i];
+		for (j = 0; j < 16; j++) {
+			subdir[1] = hex_digits[j];
+			if (access(subdir, R_OK | X_OK))
+				continue;
+			chdir(subdir);
+			if (!(dp = opendir("."))) {
+				error("can't open subdir %s", subdir);
+				continue;
+			}
+			while ((dirp = readdir(dp))) {
+				if (!strcmp(dirp->d_name, ".") ||
+					!strcmp(dirp->d_name, ".."))
+					continue;
+				if (lstat(dirp->d_name, &statbuf)) {
+					error("can't stat file %s", dirp->d_name);
+					continue;
+				}
+				numblocks += statbuf.st_blocks;
+				numobjects++;
+			}
+			closedir(dp);
+			chdir("..");
+		}
+	}
+}
+
+int main(int argc, char **argv)
+{
+	setup_git_directory();
+
+	if (chdir(".git/objects"))
+		die("%s", strerror(errno));
+
+	count_objects();
+
+	printf("%d objects, %d kilobytes\n", numobjects, numblocks / 2);
+
+	return 0;
+}
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