Git-prune-script loses blobs referenced from an uncommitted cache.

(updated from the version posted to GIT mailing list).

When a new blob is registered with update-cache, and before the cache
is written as a tree and committed, git-fsck-cache will find the blob
unreachable.  This patch adds a new flag, "--cache" to git-fsck-cache,
with which it keeps such blobs from considered "unreachable".

The git-prune-script is updated to use this new flag.  At the same time
it adds .git/refs/*/* to the set of default locations to look for heads,
which should be consistent with expectations from Cogito users.

Without this fix, "diff-cache -p --cached" after git-prune-script has
pruned the blob object will fail mysteriously and git-write-tree would
also fail.

Signed-off-by: Junio C Hamano <junkio@cox.net>

2 files changed, 60 insertions, 5 deletions

diff --git a/fsck-cache.c b/fsck-cache.c
index fb0d82f..5db07e0 100644
--- a/fsck-cache.c
+++ b/fsck-cache.c
@@ -12,6 +12,7 @@
 static int show_root = 0;
 static int show_tags = 0;
 static int show_unreachable = 0;
+static int keep_cache_objects = 0; 
 static unsigned char head_sha1[20];
 
 static void check_connectivity(void)
@@ -275,8 +276,12 @@ int main(int argc, char **argv)
 			show_root = 1;
 			continue;
 		}
+		if (!strcmp(arg, "--cache")) {
+			keep_cache_objects = 1;
+			continue;
+		}
 		if (*arg == '-')
-			usage("fsck-cache [--tags] [[--unreachable] <head-sha1>*]");
+			usage("fsck-cache [--tags] [[--unreachable] [--cache] <head-sha1>*]");
 	}
 
 	sha1_dir = getenv(DB_ENVIRONMENT) ? : DEFAULT_DB_ENVIRONMENT;
@@ -311,12 +316,27 @@ int main(int argc, char **argv)
 		error("expected sha1, got %s", arg);
 	}
 
-	if (!heads) {
+	if (keep_cache_objects) {
+		int i;
+		read_cache();
+		for (i = 0; i < active_nr; i++) {
+			struct blob *blob = lookup_blob(active_cache[i]->sha1);
+			struct object *obj;
+			if (!blob)
+				continue;
+			obj = &blob->object;
+			obj->used = 1;
+			mark_reachable(obj, REACHABLE);
+		}
+	}
+
+	if (!heads && !keep_cache_objects) {
 		if (show_unreachable) {
-			fprintf(stderr, "unable to do reachability without a head\n");
+			fprintf(stderr, "unable to do reachability without a head nor --cache\n");
 			show_unreachable = 0; 
 		}
-		fprintf(stderr, "expect dangling commits - potential heads - due to lack of head information\n");
+		if (!heads)
+			fprintf(stderr, "expect dangling commits - potential heads - due to lack of head information\n");
 	}
 
 	check_connectivity();
diff --git a/git-prune-script b/git-prune-script
index b6e927a..30a989e 100755
--- a/git-prune-script
+++ b/git-prune-script
@@ -1,2 +1,37 @@
 #!/bin/sh
-git-fsck-cache --unreachable $(cat .git/HEAD ) | grep unreachable | cut -d' ' -f3 | sed 's:^\(..\):.git/objects/\1/:' | xargs rm
+
+dryrun=
+while case "$#" in 0) break ;; esac
+do
+    case "$1" in
+    -n) dryrun=echo ;;
+    --) break ;;
+    -*) echo >&2 "usage: git-prune-script [ -n ] [ heads... ]"; exit 1 ;;
+    *)  break ;;
+    esac
+    shift;
+done
+
+# Defaulting to include .git/refs/*/* may be debatable from the
+# purist POV but power users can always give explicit parameters
+# to the script anyway.
+
+case "$#" in
+0)
+    x_40='[0-9a-f][0-9a-f][0-9a-f][0-9a-f][0-9a-f]'
+    x_40="$x_40$x_40$x_40$x_40$x_40$x_40$x_40$x_40"
+    set x $(sed -ne "/^$x_40\$/p" .git/HEAD .git/refs/*/* 2>/dev/null)
+    shift ;;
+esac
+
+git-fsck-cache --cache --unreachable "$@" |
+sed -ne '/unreachable /{
+    s/unreachable [^ ][^ ]* //
+    s|\(..\)|\1/|p
+}' | {
+	case "$SHA1_FILE_DIRECTORY" in
+	'') cd .git/objects/ ;;
+	*) cd "$SHA1_FILE_DIRECTORY" ;;
+	esac || exit
+	xargs -r $dryrun rm -f
+}