Merge http://members.cox.net/junkio/git-jc.git/

diff-tree-helper.c

@@ -35,7 +35,7 @@ static int parse_oneside_change(const char *cp, struct diff_spec *one,
 	if (strncmp(cp, "\tblob\t", 6))
 		return -1;
 	cp += 6;
-	if (get_sha1_hex(cp, one->u.sha1))
+	if (get_sha1_hex(cp, one->blob_sha1))
 		return -1;
 	cp += 40;
 	if (*cp++ != '\t')
@@ -83,13 +83,13 @@ static int parse_diff_tree_output(const char *buf,
 		if (strncmp(cp, "\tblob\t", 6))
 			return -1;
 		cp += 6;
-		if (get_sha1_hex(cp, old.u.sha1))
+		if (get_sha1_hex(cp, old.blob_sha1))
 			return -1;
 		cp += 40;
 		if (strncmp(cp, "->", 2))
 			return -1;
 		cp += 2;
-		if (get_sha1_hex(cp, new.u.sha1))
+		if (get_sha1_hex(cp, new.blob_sha1))
 			return -1;
 		cp += 40;
 		if (*cp++ != '\t')

diff.c

@@ -83,7 +83,7 @@ static void builtin_diff(const char *name,
 {
 	int i, next_at;
 	const char *diff_cmd = "diff -L'%s%s' -L'%s%s'";
-	const char *diff_arg  = "'%s' '%s'";
+	const char *diff_arg  = "'%s' '%s'||:"; /* "||:" is to return 0 */
 	const char *input_name_sq[2];
 	const char *path0[2];
 	const char *path1[2];
@@ -132,11 +132,50 @@ static void builtin_diff(const char *name,
 	execlp("/bin/sh","sh", "-c", cmd, NULL);
 }
 
+/*
+ * Given a name and sha1 pair, if the dircache tells us the file in
+ * the work tree has that object contents, return true, so that
+ * prepare_temp_file() does not have to inflate and extract.
+ */
+static int work_tree_matches(const char *name, const unsigned char *sha1)
+{
+	struct cache_entry *ce;
+	struct stat st;
+	int pos, len;
+	
+	/* We do not read the cache ourselves here, because the
+	 * benchmark with my previous version that always reads cache
+	 * shows that it makes things worse for diff-tree comparing
+	 * two linux-2.6 kernel trees in an already checked out work
+	 * tree.  This is because most diff-tree comparison deals with
+	 * only a small number of files, while reading the cache is
+	 * expensive for a large project, and its cost outweighs the
+	 * savings we get by not inflating the object to a temporary
+	 * file.  Practically, this code only helps when we are used
+	 * by diff-cache --cached, which does read the cache before
+	 * calling us.
+	 */ 
+	if (!active_cache)
+		return 0;
+
+	len = strlen(name);
+	pos = cache_name_pos(name, len);
+	if (pos < 0)
+		return 0;
+	ce = active_cache[pos];
+	if ((stat(name, &st) < 0) ||
+	    cache_match_stat(ce, &st) ||
+	    memcmp(sha1, ce->sha1, 20))
+		return 0;
+	return 1;
+}
+
 static void prepare_temp_file(const char *name,
 			      struct diff_tempfile *temp,
 			      struct diff_spec *one)
 {
 	static unsigned char null_sha1[20] = { 0, };
+	int use_work_tree = 0;
 
 	if (!one->file_valid) {
 	not_a_valid_file:
@@ -150,20 +189,22 @@ static void prepare_temp_file(const char *name,
 	}
 
 	if (one->sha1_valid &&
-	    !memcmp(one->u.sha1, null_sha1, sizeof(null_sha1))) {
-		one->sha1_valid = 0;
-		one->u.name = name;
-	}
+	    (!memcmp(one->blob_sha1, null_sha1, sizeof(null_sha1)) ||
+	     work_tree_matches(name, one->blob_sha1)))
+		use_work_tree = 1;
 
-	if (!one->sha1_valid) {
+	if (!one->sha1_valid || use_work_tree) {
 		struct stat st;
-		temp->name = one->u.name;
+		temp->name = name;
 		if (stat(temp->name, &st) < 0) {
 			if (errno == ENOENT)
 				goto not_a_valid_file;
 			die("stat(%s): %s", temp->name, strerror(errno));
 		}
-		strcpy(temp->hex, sha1_to_hex(null_sha1));
+		if (!one->sha1_valid)
+			strcpy(temp->hex, sha1_to_hex(null_sha1));
+		else
+			strcpy(temp->hex, sha1_to_hex(one->blob_sha1));
 		sprintf(temp->mode, "%06o",
 			S_IFREG |ce_permissions(st.st_mode));
 	}
@@ -173,10 +214,10 @@ static void prepare_temp_file(const char *name,
 		char type[20];
 		unsigned long size;
 
-		blob = read_sha1_file(one->u.sha1, type, &size);
+		blob = read_sha1_file(one->blob_sha1, type, &size);
 		if (!blob || strcmp(type, "blob"))
 			die("unable to read blob object for %s (%s)",
-			    name, sha1_to_hex(one->u.sha1));
+			    name, sha1_to_hex(one->blob_sha1));
 
 		strcpy(temp->tmp_path, ".diff_XXXXXX");
 		fd = mkstemp(temp->tmp_path);
@@ -187,7 +228,7 @@ static void prepare_temp_file(const char *name,
 		close(fd);
 		free(blob);
 		temp->name = temp->tmp_path;
-		strcpy(temp->hex, sha1_to_hex(one->u.sha1));
+		strcpy(temp->hex, sha1_to_hex(one->blob_sha1));
 		temp->hex[40] = 0;
 		sprintf(temp->mode, "%06o", one->mode);
 	}
@@ -261,16 +302,20 @@ void run_external_diff(const char *name,
 			printf("* Unmerged path %s\n", name);
 		exit(0);
 	}
-	if (waitpid(pid, &status, 0) < 0 || !WIFEXITED(status)) {
-		/* We do not check the exit status because typically
+	if (waitpid(pid, &status, 0) < 0 ||
+	    !WIFEXITED(status) || WEXITSTATUS(status)) {
+		/* Earlier we did not check the exit status because
 		 * diff exits non-zero if files are different, and
-		 * we are not interested in knowing that.  We *knew*
-		 * they are different and that's why we ran diff
-		 * in the first place!  However if it dies by a signal,
-		 * we stop processing immediately.
+		 * we are not interested in knowing that.  It was a
+		 * mistake which made it harder to quit a diff-*
+		 * session that uses the git-apply-patch-script as
+		 * the GIT_EXTERNAL_DIFF.  A custom GIT_EXTERNAL_DIFF
+		 * should also exit non-zero only when it wants to
+		 * abort the entire diff-* session.
 		 */
 		remove_tempfile();
-		die("external diff died unexpectedly.\n");
+		fprintf(stderr, "external diff died, stopping at %s.\n", name);
+		exit(1);
 	}
 	remove_tempfile();
 }
@@ -282,7 +327,7 @@ void diff_addremove(int addremove, unsigned mode,
 	char concatpath[PATH_MAX];
 	struct diff_spec spec[2], *one, *two;
 
-	memcpy(spec[0].u.sha1, sha1, 20);
+	memcpy(spec[0].blob_sha1, sha1, 20);
 	spec[0].mode = mode;
 	spec[0].sha1_valid = spec[0].file_valid = 1;
 	spec[1].file_valid = 0;
@@ -307,9 +352,9 @@ void diff_change(unsigned old_mode, unsigned new_mode,
 	char concatpath[PATH_MAX];
 	struct diff_spec spec[2];
 
-	memcpy(spec[0].u.sha1, old_sha1, 20);
+	memcpy(spec[0].blob_sha1, old_sha1, 20);
 	spec[0].mode = old_mode;
-	memcpy(spec[1].u.sha1, new_sha1, 20);
+	memcpy(spec[1].blob_sha1, new_sha1, 20);
 	spec[1].mode = new_mode;
 	spec[0].sha1_valid = spec[0].file_valid = 1;
 	spec[1].sha1_valid = spec[1].file_valid = 1;

diff.h

@@ -20,15 +20,12 @@ extern void diff_unmerge(const char *path);
 /* These are for diff-tree-helper */
 
 struct diff_spec {
-	union {
-		const char *name;       /* path on the filesystem */
-		unsigned char sha1[20]; /* blob object ID */
-	} u;
+	unsigned char blob_sha1[20];
 	unsigned short mode;	 /* file mode */
-	unsigned sha1_valid : 1; /* if true, use u.sha1 and trust mode.
-				  * (however with a NULL SHA1, read them
-				  * from the file!).
-				  * if false, use u.name and read mode from
+	unsigned sha1_valid : 1; /* if true, use blob_sha1 and trust mode;
+				  * however with a NULL SHA1, read them
+				  * from the file system.
+				  * if false, use the name and read mode from
 				  * the filesystem.
 				  */
 	unsigned file_valid : 1; /* if false the file does not even exist */

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;
@@ -309,12 +314,27 @@ 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();

git-apply-patch-script

@@ -19,40 +19,60 @@ then
     echo >&2 "Unresolved patch conflicts in the previous run found."
     exit 1
 fi
-# This will say "patching ..." so we do not say anything outselves.
 
-diff -u -L "a/$name" -L "b/$name" "$tmp1" "$tmp2" | patch -p1
-test -f "$name.rej" || {
-    case "$mode1,$mode2" in
-    .,?x)
-	# newly created
-	case "$mode2" in
-	+x)
-	    echo >&2 "created $name with mode +x."
-	    chmod "$mode2" "$name"
-	    ;;
-	-x)
-	    echo >&2 "created $name."
-	    ;;
-	esac
-	git-update-cache --add -- "$name"
+case "$mode1,$mode2" in
+.,?x)
+    # newly created
+    dir=$(dirname "$name")
+    case "$dir" in '' | .) ;; *) mkdir -p "$dir" esac || {
+	echo >&2 "cannot create leading path for $name."
+	exit 1
+    }
+    if test -f "$name"
+    then
+	echo >&2 "file $name to be created already exists."
+	exit 1
+    fi
+    cat "$tmp2" >"$name" || {
+	echo >&2 "cannot create $name."
+	exit 1
+    } 
+    case "$mode2" in
+    +x)
+	echo >&2 "created $name with mode +x."
+	chmod "$mode2" "$name"
 	;;
-    ?x,.)
-	# deleted
-	echo >&2 "deleted $name."
-	rm -f "$name"
-	git-update-cache --remove -- "$name"
+    -x)
+	echo >&2 "created $name."
 	;;
+    esac
+    git-update-cache --add -- "$name"
+    ;;
+?x,.)
+    # deleted
+    echo >&2 "deleted $name."
+    rm -f "$name" || {
+	echo >&2 "cannot remove $name";
+	exit 1
+    }
+    git-update-cache --remove -- "$name"
+    ;;
+*)
+    # changed
+    dir=$(dirname "$name")
+    case "$dir" in '' | .) ;; *) mkdir -p "$dir" esac || {
+	echo >&2 "cannot create leading path for $name."
+	exit 1
+    }
+    # This will say "patching ..." so we do not say anything outselves.
+    diff -u -L "a/$name" -L "b/$name" "$tmp1" "$tmp2" | patch -p1 || exit
+
+    case "$mode1,$mode2" in
+    "$mode2,$mode1") ;;
     *)
-	# changed
-	case "$mode1,$mode2" in
-	"$mode2,$mode1") ;;
-	*)
-	    echo >&2 "changing mode from $mode1 to $mode2."
-	    chmod "$mode2" "$name"
-	    ;;
-	esac
-	git-update-cache -- "$name"
+	echo >&2 "changing mode from $mode1 to $mode2."
+	chmod "$mode2" "$name"
+	;;
     esac
-}
-exit 0
+    git-update-cache -- "$name"
+esac

git-prune-script

@@ -1,4 +1,36 @@
 #!/bin/sh
-REFS=$(cat .git/refs/*/*)
-[ "$REFS" ] || exit 1
-git-fsck-cache --unreachable $REFS | grep unreachable | cut -d' ' -f3 | sed 's:^\(..\):.git/objects/\1/:' | xargs -r 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
+}

local-pull.c

@@ -39,12 +39,19 @@ int fetch(unsigned char *sha1)
 	filename[object_name_start+1] = hex[1];
 	filename[object_name_start+2] = '/';
 	strcpy(filename + object_name_start + 3, hex + 2);
-	if (use_link && !link(filename, dest_filename)) {
-		say("Hardlinked %s.\n", hex);
-		return 0;
+	if (use_link) {
+		if (!link(filename, dest_filename)) {
+			say("link %s\n", hex);
+			return 0;
+		}
+		/* If we got ENOENT there is no point continuing. */
+		if (errno == ENOENT) {
+			fprintf(stderr, "does not exist %s\n", filename);
+			return -1;
+		}
 	}
 	if (use_symlink && !symlink(filename, dest_filename)) {
-		say("Symlinked %s.\n", hex);
+		say("symlink %s\n", hex);
 		return 0;
 	}
 	if (use_filecopy) {
@@ -54,13 +61,13 @@ int fetch(unsigned char *sha1)
 		ifd = open(filename, O_RDONLY);
 		if (ifd < 0 || fstat(ifd, &st) < 0) {
 			close(ifd);
-			fprintf(stderr, "Cannot open %s\n", filename);
+			fprintf(stderr, "cannot open %s\n", filename);
 			return -1;
 		}
 		map = mmap(NULL, st.st_size, PROT_READ, MAP_PRIVATE, ifd, 0);
 		close(ifd);
 		if (-1 == (int)(long)map) {
-			fprintf(stderr, "Cannot mmap %s\n", filename);
+			fprintf(stderr, "cannot mmap %s\n", filename);
 			return -1;
 		}
 		ofd = open(dest_filename, O_WRONLY | O_CREAT | O_EXCL, 0666);
@@ -69,13 +76,13 @@ int fetch(unsigned char *sha1)
 		munmap(map, st.st_size);
 		close(ofd);
 		if (status)
-			fprintf(stderr, "Cannot write %s (%ld bytes)\n",
+			fprintf(stderr, "cannot write %s (%ld bytes)\n",
 				dest_filename, st.st_size);
 		else
-			say("Copied %s.\n", hex);
+			say("copy %s\n", hex);
 		return status;
 	}
-	fprintf(stderr, "No copy method was provided to copy %s.\n", hex);
+	fprintf(stderr, "failed to copy %s with given copy methods.\n", hex);
 	return -1;
 }
 

pull.c

@@ -7,12 +7,31 @@
 int get_tree = 0;
 int get_history = 0;
 int get_all = 0;
+static unsigned char current_commit_sha1[20];
 
-static int make_sure_we_have_it(unsigned char *sha1)
+static const char commitS[] = "commit";
+static const char treeS[] = "tree";
+static const char blobS[] = "blob";
+
+static void report_missing(const char *what, const unsigned char *missing)
+{
+	char missing_hex[41];
+
+	strcpy(missing_hex, sha1_to_hex(missing));;
+	fprintf(stderr,
+		"Cannot obtain needed %s %s\nwhile processing commit %s.\n",
+		what, missing_hex, sha1_to_hex(current_commit_sha1));
+}
+
+static int make_sure_we_have_it(const char *what, unsigned char *sha1)
 {
+	int status;
 	if (has_sha1_file(sha1))
 		return 0;
-	return fetch(sha1);	
+	status = fetch(sha1);
+	if (status && what)
+		report_missing(what, sha1);
+	return status;
 }
 
 static int process_tree(unsigned char *sha1)
@@ -24,7 +43,8 @@ static int process_tree(unsigned char *sha1)
 		return -1;
 
 	for (entries = tree->entries; entries; entries = entries->next) {
-		if (make_sure_we_have_it(entries->item.tree->object.sha1))
+		const char *what = entries->directory ? treeS : blobS;
+		if (make_sure_we_have_it(what, entries->item.tree->object.sha1))
 			return -1;
 		if (entries->directory) {
 			if (process_tree(entries->item.tree->object.sha1))
@@ -38,14 +58,14 @@ static int process_commit(unsigned char *sha1)
 {
 	struct commit *obj = lookup_commit(sha1);
 
-	if (make_sure_we_have_it(sha1))
+	if (make_sure_we_have_it(commitS, sha1))
 		return -1;
 
 	if (parse_commit(obj))
 		return -1;
 
 	if (get_tree) {
-		if (make_sure_we_have_it(obj->tree->object.sha1))
+		if (make_sure_we_have_it(treeS, obj->tree->object.sha1))
 			return -1;
 		if (process_tree(obj->tree->object.sha1))
 			return -1;
@@ -57,7 +77,8 @@ static int process_commit(unsigned char *sha1)
 		for (; parents; parents = parents->next) {
 			if (has_sha1_file(parents->item->object.sha1))
 				continue;
-			if (make_sure_we_have_it(parents->item->object.sha1)) {
+			if (make_sure_we_have_it(NULL,
+						 parents->item->object.sha1)) {
 				/* The server might not have it, and
 				 * we don't mind. 
 				 */
@@ -65,6 +86,7 @@ static int process_commit(unsigned char *sha1)
 			}
 			if (process_commit(parents->item->object.sha1))
 				return -1;
+			memcpy(current_commit_sha1, sha1, 20);
 		}
 	}
 	return 0;
@@ -77,8 +99,9 @@ int pull(char *target)
 	retval = get_sha1_hex(target, sha1);
 	if (retval)
 		return retval;
-	retval = make_sure_we_have_it(sha1);
+	retval = make_sure_we_have_it(commitS, sha1);
 	if (retval)
 		return retval;
+	memcpy(current_commit_sha1, sha1, 20);
 	return process_commit(sha1);
 }