Merge branch 'jc/diff'

* jc/diff:
  builtin-diff: call it "git-diff", really.
  builtin-diff.c: die() formatting type fix.
  built-in diff: assorted updates.
  built-in diff.

8 files changed, 407 insertions, 94 deletions

diff --git a/Makefile b/Makefile
index 67559c9f4..c0d444b56 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-diff.sh git-fetch.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$X \
-	git-count-objects$X git-push$X
+	git-count-objects$X git-diff$X git-push$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-count.o builtin-push.o
+	builtin-log.o builtin-help.o builtin-count.o builtin-diff.o builtin-push.o
 
 GITLIBS = $(LIB_FILE) $(XDIFF_LIB)
 LIBS = $(GITLIBS) -lz
diff --git a/builtin-diff.c b/builtin-diff.c
new file mode 100644
index 000000000..636edbf2a
--- /dev/null
+++ b/builtin-diff.c
@@ -0,0 +1,369 @@
+/*
+ * Builtin "git diff"
+ *
+ * Copyright (c) 2006 Junio C Hamano
+ */
+#include "cache.h"
+#include "commit.h"
+#include "blob.h"
+#include "tag.h"
+#include "diff.h"
+#include "diffcore.h"
+#include "revision.h"
+#include "log-tree.h"
+#include "builtin.h"
+
+/* NEEDSWORK: struct object has place for name but we _do_
+ * know mode when we extracted the blob out of a tree, which
+ * we currently lose.
+ */
+struct blobinfo {
+	unsigned char sha1[20];
+	const char *name;
+};
+
+static const char builtin_diff_usage[] =
+"diff <options> <rev>{0,2} -- <path>*";
+
+static int builtin_diff_files(struct rev_info *revs,
+			      int argc, const char **argv)
+{
+	int silent = 0;
+	while (1 < argc) {
+		const char *arg = argv[1];
+		if (!strcmp(arg, "--base"))
+			revs->max_count = 1;
+		else if (!strcmp(arg, "--ours"))
+			revs->max_count = 2;
+		else if (!strcmp(arg, "--theirs"))
+			revs->max_count = 3;
+		else if (!strcmp(arg, "-q"))
+			silent = 1;
+		else if (!strcmp(arg, "--raw"))
+			revs->diffopt.output_format = DIFF_FORMAT_RAW;
+		else
+			usage(builtin_diff_usage);
+		argv++; argc--;
+	}
+	/*
+	 * Make sure there are NO revision (i.e. pending object) parameter,
+	 * specified rev.max_count is reasonable (0 <= n <= 3), and
+	 * there is no other revision filtering parameter.
+	 */
+	if (revs->pending_objects ||
+	    revs->min_age != -1 ||
+	    revs->max_age != -1 ||
+	    3 < revs->max_count)
+		usage(builtin_diff_usage);
+	if (revs->max_count < 0 &&
+	    (revs->diffopt.output_format == DIFF_FORMAT_PATCH))
+		revs->combine_merges = revs->dense_combined_merges = 1;
+	/*
+	 * Backward compatibility wart - "diff-files -s" used to
+	 * defeat the common diff option "-s" which asked for
+	 * DIFF_FORMAT_NO_OUTPUT.
+	 */
+	if (revs->diffopt.output_format == DIFF_FORMAT_NO_OUTPUT)
+		revs->diffopt.output_format = DIFF_FORMAT_RAW;
+	return run_diff_files(revs, silent);
+}
+
+static void stuff_change(struct diff_options *opt,
+			 unsigned old_mode, unsigned new_mode,
+			 const unsigned char *old_sha1,
+			 const unsigned char *new_sha1,
+			 const char *old_name,
+			 const char *new_name)
+{
+	struct diff_filespec *one, *two;
+
+	if (memcmp(null_sha1, old_sha1, 20) &&
+	    memcmp(null_sha1, new_sha1, 20) &&
+	    !memcmp(old_sha1, new_sha1, 20))
+		return;
+
+	if (opt->reverse_diff) {
+		unsigned tmp;
+		const
+			const unsigned char *tmp_u;
+		const char *tmp_c;
+		tmp = old_mode; old_mode = new_mode; new_mode = tmp;
+		tmp_u = old_sha1; old_sha1 = new_sha1; new_sha1 = tmp_u;
+		tmp_c = old_name; old_name = new_name; new_name = tmp_c;
+	}
+	one = alloc_filespec(old_name);
+	two = alloc_filespec(new_name);
+	fill_filespec(one, old_sha1, old_mode);
+	fill_filespec(two, new_sha1, new_mode);
+
+	/* NEEDSWORK: shouldn't this part of diffopt??? */
+	diff_queue(&diff_queued_diff, one, two);
+}
+
+static int builtin_diff_b_f(struct rev_info *revs,
+			    int argc, const char **argv,
+			    struct blobinfo *blob,
+			    const char *path)
+{
+	/* Blob vs file in the working tree*/
+	struct stat st;
+
+	while (1 < argc) {
+		const char *arg = argv[1];
+		if (!strcmp(arg, "--raw"))
+			revs->diffopt.output_format = DIFF_FORMAT_RAW;
+		else
+			usage(builtin_diff_usage);
+		argv++; argc--;
+	}
+	if (lstat(path, &st))
+		die("'%s': %s", path, strerror(errno));
+	if (!(S_ISREG(st.st_mode) || S_ISLNK(st.st_mode)))
+		die("'%s': not a regular file or symlink", path);
+	stuff_change(&revs->diffopt,
+		     canon_mode(st.st_mode), canon_mode(st.st_mode),
+		     blob[0].sha1, null_sha1,
+		     blob[0].name, path);
+	diffcore_std(&revs->diffopt);
+	diff_flush(&revs->diffopt);
+	return 0;
+}
+
+static int builtin_diff_blobs(struct rev_info *revs,
+			      int argc, const char **argv,
+			      struct blobinfo *blob)
+{
+	/* Blobs */
+	unsigned mode = canon_mode(S_IFREG | 0644);
+
+	while (1 < argc) {
+		const char *arg = argv[1];
+		if (!strcmp(arg, "--raw"))
+			revs->diffopt.output_format = DIFF_FORMAT_RAW;
+		else
+			usage(builtin_diff_usage);
+		argv++; argc--;
+	}
+	stuff_change(&revs->diffopt,
+		     mode, mode,
+		     blob[0].sha1, blob[1].sha1,
+		     blob[1].name, blob[1].name);
+	diffcore_std(&revs->diffopt);
+	diff_flush(&revs->diffopt);
+	return 0;
+}
+
+static int builtin_diff_index(struct rev_info *revs,
+			      int argc, const char **argv)
+{
+	int cached = 0;
+	while (1 < argc) {
+		const char *arg = argv[1];
+		if (!strcmp(arg, "--cached"))
+			cached = 1;
+		else if (!strcmp(arg, "--raw"))
+			revs->diffopt.output_format = DIFF_FORMAT_RAW;
+		else
+			usage(builtin_diff_usage);
+		argv++; argc--;
+	}
+	/*
+	 * Make sure there is one revision (i.e. pending object),
+	 * and there is no revision filtering parameters.
+	 */
+	if (!revs->pending_objects || revs->pending_objects->next ||
+	    revs->max_count != -1 || revs->min_age != -1 ||
+	    revs->max_age != -1)
+		usage(builtin_diff_usage);
+	return run_diff_index(revs, cached);
+}
+
+static int builtin_diff_tree(struct rev_info *revs,
+			     int argc, const char **argv,
+			     struct object_list *ent)
+{
+	const unsigned char *(sha1[2]);
+	int swap = 1;
+	while (1 < argc) {
+		const char *arg = argv[1];
+		if (!strcmp(arg, "--raw"))
+			revs->diffopt.output_format = DIFF_FORMAT_RAW;
+		else
+			usage(builtin_diff_usage);
+		argv++; argc--;
+	}
+
+	/* We saw two trees, ent[0] and ent[1].
+	 * unless ent[0] is unintesting, they are swapped
+	 */
+	if (ent[0].item->flags & UNINTERESTING)
+		swap = 0;
+	sha1[swap] = ent[0].item->sha1;
+	sha1[1-swap] = ent[1].item->sha1;
+	diff_tree_sha1(sha1[0], sha1[1], "", &revs->diffopt);
+	log_tree_diff_flush(revs);
+	return 0;
+}
+
+static int builtin_diff_combined(struct rev_info *revs,
+				 int argc, const char **argv,
+				 struct object_list *ent,
+				 int ents)
+{
+	const unsigned char (*parent)[20];
+	int i;
+
+	while (1 < argc) {
+		const char *arg = argv[1];
+		if (!strcmp(arg, "--raw"))
+			revs->diffopt.output_format = DIFF_FORMAT_RAW;
+		else
+			usage(builtin_diff_usage);
+		argv++; argc--;
+	}
+	if (!revs->dense_combined_merges && !revs->combine_merges)
+		revs->dense_combined_merges = revs->combine_merges = 1;
+	parent = xmalloc(ents * sizeof(*parent));
+	/* Again, the revs are all reverse */
+	for (i = 0; i < ents; i++)
+		memcpy(parent + i, ent[ents - 1 - i].item->sha1, 20);
+	diff_tree_combined(parent[0], parent + 1, ents - 1,
+			   revs->dense_combined_merges, revs);
+	return 0;
+}
+
+static void add_head(struct rev_info *revs)
+{
+	unsigned char sha1[20];
+	struct object *obj;
+	if (get_sha1("HEAD", sha1))
+		return;
+	obj = parse_object(sha1);
+	if (!obj)
+		return;
+	add_object(obj, &revs->pending_objects, NULL, "HEAD");
+}
+
+int cmd_diff(int argc, const char **argv, char **envp)
+{
+	struct rev_info rev;
+	struct object_list *list, ent[100];
+	int ents = 0, blobs = 0, paths = 0;
+	const char *path = NULL;
+	struct blobinfo blob[2];
+
+	/*
+	 * We could get N tree-ish in the rev.pending_objects list.
+	 * Also there could be M blobs there, and P pathspecs.
+	 *
+	 * N=0, M=0:
+	 *	cache vs files (diff-files)
+	 * N=0, M=2:
+	 *      compare two random blobs.  P must be zero.
+	 * N=0, M=1, P=1:
+	 *	compare a blob with a working tree file.
+	 *
+	 * N=1, M=0:
+	 *      tree vs cache (diff-index --cached)
+	 *
+	 * N=2, M=0:
+	 *      tree vs tree (diff-tree)
+	 *
+	 * Other cases are errors.
+	 */
+
+	git_config(git_diff_config);
+	init_revisions(&rev);
+	rev.diffopt.output_format = DIFF_FORMAT_PATCH;
+
+	argc = setup_revisions(argc, argv, &rev, NULL);
+	/* Do we have --cached and not have a pending object, then
+	 * default to HEAD by hand.  Eek.
+	 */
+	if (!rev.pending_objects) {
+		int i;
+		for (i = 1; i < argc; i++) {
+			const char *arg = argv[i];
+			if (!strcmp(arg, "--"))
+				break;
+			else if (!strcmp(arg, "--cached")) {
+				add_head(&rev);
+				break;
+			}
+		}
+	}
+
+	for (list = rev.pending_objects; list; list = list->next) {
+		struct object *obj = list->item;
+		const char *name = list->name;
+		int flags = (obj->flags & UNINTERESTING);
+		if (!obj->parsed)
+			obj = parse_object(obj->sha1);
+		obj = deref_tag(obj, NULL, 0);
+		if (!obj)
+			die("invalid object '%s' given.", name);
+		if (!strcmp(obj->type, commit_type))
+			obj = &((struct commit *)obj)->tree->object;
+		if (!strcmp(obj->type, tree_type)) {
+			if (ARRAY_SIZE(ent) <= ents)
+				die("more than %d trees given: '%s'",
+				    (int) ARRAY_SIZE(ent), name);
+			obj->flags |= flags;
+			ent[ents].item = obj;
+			ent[ents].name = name;
+			ents++;
+			continue;
+		}
+		if (!strcmp(obj->type, blob_type)) {
+			if (2 <= blobs)
+				die("more than two blobs given: '%s'", name);
+			memcpy(blob[blobs].sha1, obj->sha1, 20);
+			blob[blobs].name = name;
+			blobs++;
+			continue;
+
+		}
+		die("unhandled object '%s' given.", name);
+	}
+	if (rev.prune_data) {
+		const char **pathspec = rev.prune_data;
+		while (*pathspec) {
+			if (!path)
+				path = *pathspec;
+			paths++;
+			pathspec++;
+		}
+	}
+
+	/*
+	 * Now, do the arguments look reasonable?
+	 */
+	if (!ents) {
+		switch (blobs) {
+		case 0:
+			return builtin_diff_files(&rev, argc, argv);
+			break;
+		case 1:
+			if (paths != 1)
+				usage(builtin_diff_usage);
+			return builtin_diff_b_f(&rev, argc, argv, blob, path);
+			break;
+		case 2:
+			if (paths)
+				usage(builtin_diff_usage);
+			return builtin_diff_blobs(&rev, argc, argv, blob);
+			break;
+		default:
+			usage(builtin_diff_usage);
+		}
+	}
+	else if (blobs)
+		usage(builtin_diff_usage);
+	else if (ents == 1)
+		return builtin_diff_index(&rev, argc, argv);
+	else if (ents == 2)
+		return builtin_diff_tree(&rev, argc, argv, ent);
+	else
+		return builtin_diff_combined(&rev, argc, argv, ent, ents);
+	usage(builtin_diff_usage);
+}
diff --git a/builtin.h b/builtin.h
index dca69632d..bb63f0729 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_diff(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/combine-diff.c b/combine-diff.c
index ca36f5d5e..8a8fe3863 100644
--- a/combine-diff.c
+++ b/combine-diff.c
@@ -831,15 +831,16 @@ void show_combined_diff(struct combine_diff_path *p,
 	}
 }
 
-void diff_tree_combined_merge(const unsigned char *sha1,
-			     int dense, struct rev_info *rev)
+void diff_tree_combined(const unsigned char *sha1,
+			const unsigned char parent[][20],
+			int num_parent,
+			int dense,
+			struct rev_info *rev)
 {
 	struct diff_options *opt = &rev->diffopt;
-	struct commit *commit = lookup_commit(sha1);
 	struct diff_options diffopts;
-	struct commit_list *parents;
 	struct combine_diff_path *p, *paths = NULL;
-	int num_parent, i, num_paths;
+	int i, num_paths;
 	int do_diffstat;
 
 	do_diffstat = (opt->output_format == DIFF_FORMAT_DIFFSTAT ||
@@ -849,17 +850,8 @@ void diff_tree_combined_merge(const unsigned char *sha1,
 	diffopts.with_stat = 0;
 	diffopts.recursive = 1;
 
-	/* count parents */
-	for (parents = commit->parents, num_parent = 0;
-	     parents;
-	     parents = parents->next, num_parent++)
-		; /* nothing */
-
 	/* find set of paths that everybody touches */
-	for (parents = commit->parents, i = 0;
-	     parents;
-	     parents = parents->next, i++) {
-		struct commit *parent = parents->item;
+	for (i = 0; i < num_parent; i++) {
 		/* show stat against the first parent even
 		 * when doing combined diff.
 		 */
@@ -867,8 +859,7 @@ void diff_tree_combined_merge(const unsigned char *sha1,
 			diffopts.output_format = DIFF_FORMAT_DIFFSTAT;
 		else
 			diffopts.output_format = DIFF_FORMAT_NO_OUTPUT;
-		diff_tree_sha1(parent->object.sha1, commit->object.sha1, "",
-			       &diffopts);
+		diff_tree_sha1(parent[i], sha1, "", &diffopts);
 		diffcore_std(&diffopts);
 		paths = intersect_paths(paths, i, num_parent);
 
@@ -907,3 +898,25 @@ void diff_tree_combined_merge(const unsigned char *sha1,
 		free(tmp);
 	}
 }
+
+void diff_tree_combined_merge(const unsigned char *sha1,
+			     int dense, struct rev_info *rev)
+{
+	int num_parent;
+	const unsigned char (*parent)[20];
+	struct commit *commit = lookup_commit(sha1);
+	struct commit_list *parents;
+
+	/* count parents */
+	for (parents = commit->parents, num_parent = 0;
+	     parents;
+	     parents = parents->next, num_parent++)
+		; /* nothing */
+
+	parent = xmalloc(num_parent * sizeof(*parent));
+	for (parents = commit->parents, num_parent = 0;
+	     parents;
+	     parents = parents->next, num_parent++)
+		memcpy(parent + num_parent, parents->item->object.sha1, 20);
+	diff_tree_combined(sha1, parent, num_parent, dense, rev);
+}
diff --git a/diff.h b/diff.h
index 7150b9038..b3b2c4dd2 100644
--- a/diff.h
+++ b/diff.h
@@ -75,6 +75,8 @@ struct combine_diff_path {
 extern void show_combined_diff(struct combine_diff_path *elem, int num_parent,
 			      int dense, struct rev_info *);
 
+extern void diff_tree_combined(const unsigned char *sha1, const unsigned char parent[][20], int num_parent, int dense, struct rev_info *rev);
+
 extern void diff_tree_combined_merge(const unsigned char *sha1, int, struct rev_info *);
 
 extern void diff_addremove(struct diff_options *,
diff --git a/git-diff.sh b/git-diff.sh
deleted file mode 100755
index 0fe677074..000000000
--- a/git-diff.sh
+++ /dev/null
@@ -1,74 +0,0 @@
-#!/bin/sh
-#
-# Copyright (c) 2005 Linus Torvalds
-# Copyright (c) 2005 Junio C Hamano
-
-USAGE='[ --diff-options ] <ent>{0,2} [<path>...]'
-SUBDIRECTORY_OK='Yes'
-. git-sh-setup
-
-rev=$(git-rev-parse --revs-only --no-flags --sq "$@") || exit
-flags=$(git-rev-parse --no-revs --flags --sq "$@")
-files=$(git-rev-parse --no-revs --no-flags --sq "$@")
-
-# I often say 'git diff --cached -p' and get scolded by git-diff-files, but
-# obviously I mean 'git diff --cached -p HEAD' in that case.
-case "$rev" in
-'')
-	case " $flags " in
-	*" '--cached' "*)
-		rev='HEAD '
-		;;
-	esac
-esac
-
-# If we have -[123] --ours --theirs --base, don't do --cc by default.
-case " $flags " in
-*" '-"[123]"' "* | *" '--ours' "* | *" '--base' "* | *" '--theirs' "*)
-	cc_or_p=-p ;;
-*)
-	cc_or_p=--cc ;;
-esac
-
-# If we do not have --name-status, --name-only, -r, -c or --stat,
-# default to --cc.
-case " $flags " in
-*" '--name-status' "* | *" '--name-only' "* | *" '-r' "* | *" '-c' "* | \
-*" '--stat' "*)
-	;;
-*)
-	flags="$flags'$cc_or_p' " ;;
-esac
-
-# If we do not have -B, -C, -r, nor -p, default to -M.
-case " $flags " in
-*" '-"[BCMrp]* | *" '--find-copies-harder' "*)
-	;; # something like -M50.
-*)
-	flags="$flags'-M' " ;;
-esac
-
-case "$rev" in
-?*' '?*' '?*)
-	usage
-	;;
-?*' '^?*)
-	begin=$(expr "$rev" : '.*^.\([0-9a-f]*\).*') &&
-	end=$(expr "$rev" : '.\([0-9a-f]*\). .*') || exit
-	cmd="git-diff-tree $flags $begin $end -- $files"
-	;;
-?*' '?*)
-	cmd="git-diff-tree $flags $rev -- $files"
-	;;
-?*' ')
-	cmd="git-diff-index $flags $rev -- $files"
-	;;
-'')
-	cmd="git-diff-files $flags -- $files"
-	;;
-*)
-	usage
-	;;
-esac
-
-eval "$cmd"
diff --git a/git.c b/git.c
index 4d3a5a30a..49ba5189d 100644
--- a/git.c
+++ b/git.c
@@ -48,6 +48,7 @@ static void handle_internal_command(int argc, const char **argv, char **envp)
 		{ "show", cmd_show },
 		{ "push", cmd_push },
 		{ "count-objects", cmd_count_objects },
+		{ "diff", cmd_diff },
 	};
 	int i;
 
diff --git a/revision.c b/revision.c
index c6e8702f3..f8ee38e54 100644
--- a/revision.c
+++ b/revision.c
@@ -694,6 +694,7 @@ int setup_revisions(int argc, const char **argv, struct rev_info *revs, const ch
 			}
 			if (!strcmp(arg, "-c")) {
 				revs->diff = 1;
+				revs->dense_combined_merges = 0;
 				revs->combine_merges = 1;
 				continue;
 			}