1 files changed, 308 insertions, 474 deletions

diff --git a/diff-lib.c b/diff-lib.c
index 778cf58244..241a8435eb 100644
--- a/diff-lib.c
+++ b/diff-lib.c
@@ -8,314 +8,114 @@
 #include "diffcore.h"
 #include "revision.h"
 #include "cache-tree.h"
-#include "path-list.h"
+#include "unpack-trees.h"
+#include "refs.h"
+#include "submodule.h"
+#include "dir.h"
 
 /*
  * diff-files
  */
 
-static int read_directory(const char *path, struct path_list *list)
-{
-	DIR *dir;
-	struct dirent *e;
-
-	if (!(dir = opendir(path)))
-		return error("Could not open directory %s", path);
-
-	while ((e = readdir(dir)))
-		if (strcmp(".", e->d_name) && strcmp("..", e->d_name))
-			path_list_insert(xstrdup(e->d_name), list);
-
-	closedir(dir);
-	return 0;
-}
-
-static int queue_diff(struct diff_options *o,
-		const char *name1, const char *name2)
+/*
+ * Has the work tree entity been removed?
+ *
+ * Return 1 if it was removed from the work tree, 0 if an entity to be
+ * compared with the cache entry ce still exists (the latter includes
+ * the case where a directory that is not a submodule repository
+ * exists for ce that is a submodule -- it is a submodule that is not
+ * checked out).  Return negative for an error.
+ */
+static int check_removed(const struct cache_entry *ce, struct stat *st)
 {
-	struct stat st;
-	int mode1 = 0, mode2 = 0;
-
-	if (name1) {
-		if (stat(name1, &st))
-			return error("Could not access '%s'", name1);
-		mode1 = st.st_mode;
-	}
-	if (name2) {
-		if (stat(name2, &st))
-			return error("Could not access '%s'", name2);
-		mode2 = st.st_mode;
-	}
-
-	if (mode1 && mode2 && S_ISDIR(mode1) != S_ISDIR(mode2))
-		return error("file/directory conflict: %s, %s", name1, name2);
-
-	if (S_ISDIR(mode1) || S_ISDIR(mode2)) {
-		char buffer1[PATH_MAX], buffer2[PATH_MAX];
-		struct path_list p1 = {NULL, 0, 0, 1}, p2 = {NULL, 0, 0, 1};
-		int len1 = 0, len2 = 0, i1, i2, ret = 0;
-
-		if (name1 && read_directory(name1, &p1))
-			return -1;
-		if (name2 && read_directory(name2, &p2)) {
-			path_list_clear(&p1, 0);
+	if (lstat(ce->name, st) < 0) {
+		if (errno != ENOENT && errno != ENOTDIR)
 			return -1;
-		}
-
-		if (name1) {
-			len1 = strlen(name1);
-			if (len1 > 0 && name1[len1 - 1] == '/')
-				len1--;
-			memcpy(buffer1, name1, len1);
-			buffer1[len1++] = '/';
-		}
-
-		if (name2) {
-			len2 = strlen(name2);
-			if (len2 > 0 && name2[len2 - 1] == '/')
-				len2--;
-			memcpy(buffer2, name2, len2);
-			buffer2[len2++] = '/';
-		}
-
-		for (i1 = i2 = 0; !ret && (i1 < p1.nr || i2 < p2.nr); ) {
-			const char *n1, *n2;
-			int comp;
-
-			if (i1 == p1.nr)
-				comp = 1;
-			else if (i2 == p2.nr)
-				comp = -1;
-			else
-				comp = strcmp(p1.items[i1].path,
-					p2.items[i2].path);
-
-			if (comp > 0)
-				n1 = NULL;
-			else {
-				n1 = buffer1;
-				strncpy(buffer1 + len1, p1.items[i1++].path,
-						PATH_MAX - len1);
-			}
-
-			if (comp < 0)
-				n2 = NULL;
-			else {
-				n2 = buffer2;
-				strncpy(buffer2 + len2, p2.items[i2++].path,
-						PATH_MAX - len2);
-			}
-
-			ret = queue_diff(o, n1, n2);
-		}
-		path_list_clear(&p1, 0);
-		path_list_clear(&p2, 0);
-
-		return ret;
-	} else {
-		struct diff_filespec *d1, *d2;
-
-		if (o->reverse_diff) {
-			unsigned tmp;
-			const char *tmp_c;
-			tmp = mode1; mode1 = mode2; mode2 = tmp;
-			tmp_c = name1; name1 = name2; name2 = tmp_c;
-		}
-
-		if (!name1)
-			name1 = "/dev/null";
-		if (!name2)
-			name2 = "/dev/null";
-		d1 = alloc_filespec(name1);
-		d2 = alloc_filespec(name2);
-		fill_filespec(d1, null_sha1, mode1);
-		fill_filespec(d2, null_sha1, mode2);
-
-		diff_queue(&diff_queued_diff, d1, d2);
-		return 0;
-	}
-}
-
-static int is_in_index(const char *path)
-{
-	int len = strlen(path);
-	int pos = cache_name_pos(path, len);
-	char c;
-
-	if (pos < 0)
-		return 0;
-	if (strncmp(active_cache[pos]->name, path, len))
-		return 0;
-	c = active_cache[pos]->name[len];
-	return c == '\0' || c == '/';
-}
-
-static int handle_diff_files_args(struct rev_info *revs,
-		int argc, const char **argv, int *silent)
-{
-	*silent = 0;
-
-	/* revs->max_count == -2 means --no-index */
-	while (1 < argc && argv[1][0] == '-') {
-		if (!strcmp(argv[1], "--base"))
-			revs->max_count = 1;
-		else if (!strcmp(argv[1], "--ours"))
-			revs->max_count = 2;
-		else if (!strcmp(argv[1], "--theirs"))
-			revs->max_count = 3;
-		else if (!strcmp(argv[1], "-n") ||
-				!strcmp(argv[1], "--no-index"))
-			revs->max_count = -2;
-		else if (!strcmp(argv[1], "-q"))
-			*silent = 1;
-		else
-			return error("invalid option: %s", argv[1]);
-		argv++; argc--;
+		return 1;
 	}
+	if (has_symlink_leading_path(ce->name, ce_namelen(ce)))
+		return 1;
+	if (S_ISDIR(st->st_mode)) {
+		unsigned char sub[20];
 
-	if (revs->max_count == -1 && revs->diffopt.nr_paths == 2) {
 		/*
-		 * If two files are specified, and at least one is untracked,
-		 * default to no-index.
+		 * If ce is already a gitlink, we can have a plain
+		 * directory (i.e. the submodule is not checked out),
+		 * or a checked out submodule.  Either case this is not
+		 * a case where something was removed from the work tree,
+		 * so we will return 0.
+		 *
+		 * Otherwise, if the directory is not a submodule
+		 * repository, that means ce which was a blob turned into
+		 * a directory --- the blob was removed!
 		 */
-		read_cache();
-		if (!is_in_index(revs->diffopt.paths[0]) ||
-					!is_in_index(revs->diffopt.paths[1]))
-			revs->max_count = -2;
-	}
-
-	/*
-	 * Make sure there are NO revision (i.e. pending object) parameter,
-	 * rev.max_count is reasonable (0 <= n <= 3),
-	 * there is no other revision filtering parameters.
-	 */
-	if (revs->pending.nr || revs->max_count > 3 ||
-	    revs->min_age != -1 || revs->max_age != -1)
-		return error("no revision allowed with diff-files");
-
-	if (revs->max_count == -1 &&
-	    (revs->diffopt.output_format & DIFF_FORMAT_PATCH))
-		revs->combine_merges = revs->dense_combined_merges = 1;
-
-	return 0;
-}
-
-static int is_outside_repo(const char *path, int nongit, const char *prefix)
-{
-	int i;
-	if (nongit || !strcmp(path, "-") || path[0] == '/')
-		return 1;
-	if (prefixcmp(path, "../"))
-		return 0;
-	if (!prefix)
-		return 1;
-	for (i = strlen(prefix); !prefixcmp(path, "../"); ) {
-		while (i > 0 && prefix[i - 1] != '/')
-			i--;
-		if (--i < 0)
+		if (!S_ISGITLINK(ce->ce_mode) &&
+		    resolve_gitlink_ref(ce->name, "HEAD", sub))
 			return 1;
-		path += 3;
-	}
-	return 0;
-}
-
-int setup_diff_no_index(struct rev_info *revs,
-		int argc, const char ** argv, int nongit, const char *prefix)
-{
-	int i;
-	for (i = 1; i < argc; i++)
-		if (argv[i][0] != '-')
-			break;
-		else if (!strcmp(argv[i], "--")) {
-			i++;
-			break;
-		} else if (i < argc - 3 && !strcmp(argv[i], "--no-index")) {
-			i = argc - 3;
-			break;
-		}
-	if (argc != i + 2 || (!is_outside_repo(argv[i + 1], nongit, prefix) &&
-				!is_outside_repo(argv[i], nongit, prefix)))
-		return -1;
-
-	diff_setup(&revs->diffopt);
-	for (i = 1; i < argc - 2; )
-		if (!strcmp(argv[i], "--no-index"))
-			i++;
-		else {
-			int j = diff_opt_parse(&revs->diffopt,
-					argv + i, argc - i);
-			if (!j)
-				die("invalid diff option/value: %s", argv[i]);
-			i += j;
-		}
-
-	if (prefix) {
-		int len = strlen(prefix);
-
-		revs->diffopt.paths = xcalloc(2, sizeof(char*));
-		for (i = 0; i < 2; i++) {
-			const char *p;
-			p = prefix_filename(prefix, len, argv[argc - 2 + i]);
-			revs->diffopt.paths[i] = xstrdup(p);
-		}
 	}
-	else
-		revs->diffopt.paths = argv + argc - 2;
-	revs->diffopt.nr_paths = 2;
-	revs->max_count = -2;
 	return 0;
 }
 
-int run_diff_files_cmd(struct rev_info *revs, int argc, const char **argv)
+/*
+ * Has a file changed or has a submodule new commits or a dirty work tree?
+ *
+ * Return 1 when changes are detected, 0 otherwise. If the DIRTY_SUBMODULES
+ * option is set, the caller does not only want to know if a submodule is
+ * modified at all but wants to know all the conditions that are met (new
+ * commits, untracked content and/or modified content).
+ */
+static int match_stat_with_submodule(struct diff_options *diffopt,
+				     const struct cache_entry *ce,
+				     struct stat *st, unsigned ce_option,
+				     unsigned *dirty_submodule)
 {
-	int silent_on_removed;
-
-	if (handle_diff_files_args(revs, argc, argv, &silent_on_removed))
-		return -1;
-
-	if (revs->max_count == -2) {
-		if (revs->diffopt.nr_paths != 2)
-			return error("need two files/directories with --no-index");
-		if (queue_diff(&revs->diffopt, revs->diffopt.paths[0],
-				revs->diffopt.paths[1]))
-			return -1;
-		diffcore_std(&revs->diffopt);
-		diff_flush(&revs->diffopt);
-		/*
-		 * The return code for --no-index imitates diff(1):
-		 * 0 = no changes, 1 = changes, else error
-		 */
-		return revs->diffopt.found_changes;
+	int changed = ce_match_stat(ce, st, ce_option);
+	if (S_ISGITLINK(ce->ce_mode)) {
+		unsigned orig_flags = diffopt->flags;
+		if (!DIFF_OPT_TST(diffopt, OVERRIDE_SUBMODULE_CONFIG))
+			set_diffopt_flags_from_submodule_config(diffopt, ce->name);
+		if (DIFF_OPT_TST(diffopt, IGNORE_SUBMODULES))
+			changed = 0;
+		else if (!DIFF_OPT_TST(diffopt, IGNORE_DIRTY_SUBMODULES)
+		    && (!changed || DIFF_OPT_TST(diffopt, DIRTY_SUBMODULES)))
+			*dirty_submodule = is_submodule_modified(ce->name, DIFF_OPT_TST(diffopt, IGNORE_UNTRACKED_IN_SUBMODULES));
+		diffopt->flags = orig_flags;
 	}
-
-	if (read_cache() < 0) {
-		perror("read_cache");
-		return -1;
-	}
-	return run_diff_files(revs, silent_on_removed);
+	return changed;
 }
 
-int run_diff_files(struct rev_info *revs, int silent_on_removed)
+int run_diff_files(struct rev_info *revs, unsigned int option)
 {
 	int entries, i;
 	int diff_unmerged_stage = revs->max_count;
+	unsigned ce_option = ((option & DIFF_RACY_IS_MODIFIED)
+			      ? CE_MATCH_RACY_IS_DIRTY : 0);
+
+	diff_set_mnemonic_prefix(&revs->diffopt, "i/", "w/");
 
 	if (diff_unmerged_stage < 0)
 		diff_unmerged_stage = 2;
 	entries = active_nr;
 	for (i = 0; i < entries; i++) {
-		struct stat st;
 		unsigned int oldmode, newmode;
 		struct cache_entry *ce = active_cache[i];
 		int changed;
+		unsigned dirty_submodule = 0;
+		const unsigned char *old_sha1, *new_sha1;
+
+		if (diff_can_quit_early(&revs->diffopt))
+			break;
 
-		if (!ce_path_match(ce, revs->prune_data))
+		if (!ce_path_match(ce, &revs->prune_data, NULL))
 			continue;
 
 		if (ce_stage(ce)) {
 			struct combine_diff_path *dpath;
+			struct diff_filepair *pair;
+			unsigned int wt_mode = 0;
 			int num_compare_stages = 0;
 			size_t path_len;
+			struct stat st;
 
 			path_len = ce_namelen(ce);
 
@@ -323,23 +123,23 @@ int run_diff_files(struct rev_info *revs, int silent_on_removed)
 			dpath->path = (char *) &(dpath->parent[5]);
 
 			dpath->next = NULL;
-			dpath->len = path_len;
 			memcpy(dpath->path, ce->name, path_len);
 			dpath->path[path_len] = '\0';
-			hashclr(dpath->sha1);
+			oidclr(&dpath->oid);
 			memset(&(dpath->parent[0]), 0,
 			       sizeof(struct combine_diff_parent)*5);
 
-			if (lstat(ce->name, &st) < 0) {
-				if (errno != ENOENT && errno != ENOTDIR) {
+			changed = check_removed(ce, &st);
+			if (!changed)
+				wt_mode = ce_mode_from_stat(ce, st.st_mode);
+			else {
+				if (changed < 0) {
 					perror(ce->name);
 					continue;
 				}
-				if (silent_on_removed)
-					continue;
+				wt_mode = 0;
 			}
-			else
-				dpath->mode = canon_mode(st.st_mode);
+			dpath->mode = wt_mode;
 
 			while (i < entries) {
 				struct cache_entry *nce = active_cache[i];
@@ -353,11 +153,10 @@ int run_diff_files(struct rev_info *revs, int silent_on_removed)
 				 */
 				stage = ce_stage(nce);
 				if (2 <= stage) {
-					int mode = ntohl(nce->ce_mode);
+					int mode = nce->ce_mode;
 					num_compare_stages++;
-					hashcpy(dpath->parent[stage-2].sha1, nce->sha1);
-					dpath->parent[stage-2].mode =
-						canon_mode(mode);
+					hashcpy(dpath->parent[stage-2].oid.hash, nce->sha1);
+					dpath->parent[stage-2].mode = ce_mode_from_stat(nce, mode);
 					dpath->parent[stage-2].status =
 						DIFF_STATUS_MODIFIED;
 				}
@@ -386,38 +185,53 @@ int run_diff_files(struct rev_info *revs, int silent_on_removed)
 			 * Show the diff for the 'ce' if we found the one
 			 * from the desired stage.
 			 */
-			diff_unmerge(&revs->diffopt, ce->name, 0, null_sha1);
+			pair = diff_unmerge(&revs->diffopt, ce->name);
+			if (wt_mode)
+				pair->two->mode = wt_mode;
 			if (ce_stage(ce) != diff_unmerged_stage)
 				continue;
 		}
 
-		if (lstat(ce->name, &st) < 0) {
-			if (errno != ENOENT && errno != ENOTDIR) {
-				perror(ce->name);
+		if (ce_uptodate(ce) || ce_skip_worktree(ce))
+			continue;
+
+		/* If CE_VALID is set, don't look at workdir for file removal */
+		if (ce->ce_flags & CE_VALID) {
+			changed = 0;
+			newmode = ce->ce_mode;
+		} else {
+			struct stat st;
+
+			changed = check_removed(ce, &st);
+			if (changed) {
+				if (changed < 0) {
+					perror(ce->name);
+					continue;
+				}
+				diff_addremove(&revs->diffopt, '-', ce->ce_mode,
+					       ce->sha1, !is_null_sha1(ce->sha1),
+					       ce->name, 0);
 				continue;
 			}
-			if (silent_on_removed)
+
+			changed = match_stat_with_submodule(&revs->diffopt, ce, &st,
+							    ce_option, &dirty_submodule);
+			newmode = ce_mode_from_stat(ce, st.st_mode);
+		}
+
+		if (!changed && !dirty_submodule) {
+			ce_mark_uptodate(ce);
+			if (!DIFF_OPT_TST(&revs->diffopt, FIND_COPIES_HARDER))
 				continue;
-			diff_addremove(&revs->diffopt, '-', ntohl(ce->ce_mode),
-				       ce->sha1, ce->name, NULL);
-			continue;
 		}
-		changed = ce_match_stat(ce, &st, 0);
-		if (!changed && !revs->diffopt.find_copies_harder)
-			continue;
-		oldmode = ntohl(ce->ce_mode);
-
-		newmode = canon_mode(st.st_mode);
-		if (!trust_executable_bit &&
-		    S_ISREG(newmode) && S_ISREG(oldmode) &&
-		    ((newmode ^ oldmode) == 0111))
-			newmode = oldmode;
-		else if (!has_symlinks &&
-		    S_ISREG(newmode) && S_ISLNK(oldmode))
-			newmode = oldmode;
+		oldmode = ce->ce_mode;
+		old_sha1 = ce->sha1;
+		new_sha1 = changed ? null_sha1 : ce->sha1;
 		diff_change(&revs->diffopt, oldmode, newmode,
-			    ce->sha1, (changed ? null_sha1 : ce->sha1),
-			    ce->name, NULL);
+			    old_sha1, new_sha1,
+			    !is_null_sha1(old_sha1),
+			    !is_null_sha1(new_sha1),
+			    ce->name, 0, dirty_submodule);
 
 	}
 	diffcore_std(&revs->diffopt);
@@ -432,37 +246,43 @@ int run_diff_files(struct rev_info *revs, int silent_on_removed)
 /* A file entry went away or appeared */
 static void diff_index_show_file(struct rev_info *revs,
 				 const char *prefix,
-				 struct cache_entry *ce,
-				 unsigned char *sha1, unsigned int mode)
+				 const struct cache_entry *ce,
+				 const unsigned char *sha1, int sha1_valid,
+				 unsigned int mode,
+				 unsigned dirty_submodule)
 {
-	diff_addremove(&revs->diffopt, prefix[0], ntohl(mode),
-		       sha1, ce->name, NULL);
+	diff_addremove(&revs->diffopt, prefix[0], mode,
+		       sha1, sha1_valid, ce->name, dirty_submodule);
 }
 
-static int get_stat_data(struct cache_entry *ce,
-			 unsigned char **sha1p,
+static int get_stat_data(const struct cache_entry *ce,
+			 const unsigned char **sha1p,
 			 unsigned int *modep,
-			 int cached, int match_missing)
+			 int cached, int match_missing,
+			 unsigned *dirty_submodule, struct diff_options *diffopt)
 {
-	unsigned char *sha1 = ce->sha1;
+	const unsigned char *sha1 = ce->sha1;
 	unsigned int mode = ce->ce_mode;
 
-	if (!cached) {
-		static unsigned char no_sha1[20];
+	if (!cached && !ce_uptodate(ce)) {
 		int changed;
 		struct stat st;
-		if (lstat(ce->name, &st) < 0) {
-			if (errno == ENOENT && match_missing) {
+		changed = check_removed(ce, &st);
+		if (changed < 0)
+			return -1;
+		else if (changed) {
+			if (match_missing) {
 				*sha1p = sha1;
 				*modep = mode;
 				return 0;
 			}
 			return -1;
 		}
-		changed = ce_match_stat(ce, &st, 0);
+		changed = match_stat_with_submodule(diffopt, ce, &st,
+						    0, dirty_submodule);
 		if (changed) {
 			mode = ce_mode_from_stat(ce, st.st_mode);
-			sha1 = no_sha1;
+			sha1 = null_sha1;
 		}
 	}
 
@@ -472,34 +292,39 @@ static int get_stat_data(struct cache_entry *ce,
 }
 
 static void show_new_file(struct rev_info *revs,
-			  struct cache_entry *new,
+			  const struct cache_entry *new,
 			  int cached, int match_missing)
 {
-	unsigned char *sha1;
+	const unsigned char *sha1;
 	unsigned int mode;
+	unsigned dirty_submodule = 0;
 
-	/* New file in the index: it might actually be different in
-	 * the working copy.
+	/*
+	 * New file in the index: it might actually be different in
+	 * the working tree.
 	 */
-	if (get_stat_data(new, &sha1, &mode, cached, match_missing) < 0)
+	if (get_stat_data(new, &sha1, &mode, cached, match_missing,
+	    &dirty_submodule, &revs->diffopt) < 0)
 		return;
 
-	diff_index_show_file(revs, "+", new, sha1, mode);
+	diff_index_show_file(revs, "+", new, sha1, !is_null_sha1(sha1), mode, dirty_submodule);
 }
 
 static int show_modified(struct rev_info *revs,
-			 struct cache_entry *old,
-			 struct cache_entry *new,
+			 const struct cache_entry *old,
+			 const struct cache_entry *new,
 			 int report_missing,
 			 int cached, int match_missing)
 {
 	unsigned int mode, oldmode;
-	unsigned char *sha1;
+	const unsigned char *sha1;
+	unsigned dirty_submodule = 0;
 
-	if (get_stat_data(new, &sha1, &mode, cached, match_missing) < 0) {
+	if (get_stat_data(new, &sha1, &mode, cached, match_missing,
+			  &dirty_submodule, &revs->diffopt) < 0) {
 		if (report_missing)
 			diff_index_show_file(revs, "-", old,
-					     old->sha1, old->ce_mode);
+					     old->sha1, 1, old->ce_mode, 0);
 		return -1;
 	}
 
@@ -511,191 +336,200 @@ static int show_modified(struct rev_info *revs,
 		p = xmalloc(combine_diff_path_size(2, pathlen));
 		p->path = (char *) &p->parent[2];
 		p->next = NULL;
-		p->len = pathlen;
 		memcpy(p->path, new->name, pathlen);
 		p->path[pathlen] = 0;
-		p->mode = ntohl(mode);
-		hashclr(p->sha1);
+		p->mode = mode;
+		oidclr(&p->oid);
 		memset(p->parent, 0, 2 * sizeof(struct combine_diff_parent));
 		p->parent[0].status = DIFF_STATUS_MODIFIED;
-		p->parent[0].mode = ntohl(new->ce_mode);
-		hashcpy(p->parent[0].sha1, new->sha1);
+		p->parent[0].mode = new->ce_mode;
+		hashcpy(p->parent[0].oid.hash, new->sha1);
 		p->parent[1].status = DIFF_STATUS_MODIFIED;
-		p->parent[1].mode = ntohl(old->ce_mode);
-		hashcpy(p->parent[1].sha1, old->sha1);
+		p->parent[1].mode = old->ce_mode;
+		hashcpy(p->parent[1].oid.hash, old->sha1);
 		show_combined_diff(p, 2, revs->dense_combined_merges, revs);
 		free(p);
 		return 0;
 	}
 
 	oldmode = old->ce_mode;
-	if (mode == oldmode && !hashcmp(sha1, old->sha1) &&
-	    !revs->diffopt.find_copies_harder)
+	if (mode == oldmode && !hashcmp(sha1, old->sha1) && !dirty_submodule &&
+	    !DIFF_OPT_TST(&revs->diffopt, FIND_COPIES_HARDER))
 		return 0;
 
-	mode = ntohl(mode);
-	oldmode = ntohl(oldmode);
-
 	diff_change(&revs->diffopt, oldmode, mode,
-		    old->sha1, sha1, old->name, NULL);
+		    old->sha1, sha1, 1, !is_null_sha1(sha1),
+		    old->name, 0, dirty_submodule);
 	return 0;
 }
 
-static int diff_cache(struct rev_info *revs,
-		      struct cache_entry **ac, int entries,
-		      const char **pathspec,
-		      int cached, int match_missing)
+/*
+ * This gets a mix of an existing index and a tree, one pathname entry
+ * at a time. The index entry may be a single stage-0 one, but it could
+ * also be multiple unmerged entries (in which case idx_pos/idx_nr will
+ * give you the position and number of entries in the index).
+ */
+static void do_oneway_diff(struct unpack_trees_options *o,
+			   const struct cache_entry *idx,
+			   const struct cache_entry *tree)
 {
-	while (entries) {
-		struct cache_entry *ce = *ac;
-		int same = (entries > 1) && ce_same_name(ce, ac[1]);
-
-		if (!ce_path_match(ce, pathspec))
-			goto skip_entry;
-
-		switch (ce_stage(ce)) {
-		case 0:
-			/* No stage 1 entry? That means it's a new file */
-			if (!same) {
-				show_new_file(revs, ce, cached, match_missing);
-				break;
-			}
-			/* Show difference between old and new */
-			show_modified(revs, ac[1], ce, 1,
-				      cached, match_missing);
-			break;
-		case 1:
-			/* No stage 3 (merge) entry?
-			 * That means it's been deleted.
-			 */
-			if (!same) {
-				diff_index_show_file(revs, "-", ce,
-						     ce->sha1, ce->ce_mode);
-				break;
-			}
-			/* We come here with ce pointing at stage 1
-			 * (original tree) and ac[1] pointing at stage
-			 * 3 (unmerged).  show-modified with
-			 * report-missing set to false does not say the
-			 * file is deleted but reports true if work
-			 * tree does not have it, in which case we
-			 * fall through to report the unmerged state.
-			 * Otherwise, we show the differences between
-			 * the original tree and the work tree.
-			 */
-			if (!cached &&
-			    !show_modified(revs, ce, ac[1], 0,
-					   cached, match_missing))
-				break;
-			diff_unmerge(&revs->diffopt, ce->name,
-				     ntohl(ce->ce_mode), ce->sha1);
-			break;
-		case 3:
-			diff_unmerge(&revs->diffopt, ce->name,
-				     0, null_sha1);
-			break;
+	struct rev_info *revs = o->unpack_data;
+	int match_missing, cached;
 
-		default:
-			die("impossible cache entry stage");
-		}
+	/* if the entry is not checked out, don't examine work tree */
+	cached = o->index_only ||
+		(idx && ((idx->ce_flags & CE_VALID) || ce_skip_worktree(idx)));
+	/*
+	 * Backward compatibility wart - "diff-index -m" does
+	 * not mean "do not ignore merges", but "match_missing".
+	 *
+	 * But with the revision flag parsing, that's found in
+	 * "!revs->ignore_merges".
+	 */
+	match_missing = !revs->ignore_merges;
 
-skip_entry:
-		/*
-		 * Ignore all the different stages for this file,
-		 * we've handled the relevant cases now.
-		 */
-		do {
-			ac++;
-			entries--;
-		} while (entries && ce_same_name(ce, ac[0]));
+	if (cached && idx && ce_stage(idx)) {
+		struct diff_filepair *pair;
+		pair = diff_unmerge(&revs->diffopt, idx->name);
+		if (tree)
+			fill_filespec(pair->one, tree->sha1, 1, tree->ce_mode);
+		return;
 	}
-	return 0;
+
+	/*
+	 * Something added to the tree?
+	 */
+	if (!tree) {
+		show_new_file(revs, idx, cached, match_missing);
+		return;
+	}
+
+	/*
+	 * Something removed from the tree?
+	 */
+	if (!idx) {
+		diff_index_show_file(revs, "-", tree, tree->sha1, 1, tree->ce_mode, 0);
+		return;
+	}
+
+	/* Show difference between old and new */
+	show_modified(revs, tree, idx, 1, cached, match_missing);
 }
 
 /*
- * This turns all merge entries into "stage 3". That guarantees that
- * when we read in the new tree (into "stage 1"), we won't lose sight
- * of the fact that we had unmerged entries.
+ * The unpack_trees() interface is designed for merging, so
+ * the different source entries are designed primarily for
+ * the source trees, with the old index being really mainly
+ * used for being replaced by the result.
+ *
+ * For diffing, the index is more important, and we only have a
+ * single tree.
+ *
+ * We're supposed to advance o->pos to skip what we have already processed.
+ *
+ * This wrapper makes it all more readable, and takes care of all
+ * the fairly complex unpack_trees() semantic requirements, including
+ * the skipping, the path matching, the type conflict cases etc.
  */
-static void mark_merge_entries(void)
+static int oneway_diff(const struct cache_entry * const *src,
+		       struct unpack_trees_options *o)
 {
-	int i;
-	for (i = 0; i < active_nr; i++) {
-		struct cache_entry *ce = active_cache[i];
-		if (!ce_stage(ce))
-			continue;
-		ce->ce_flags |= htons(CE_STAGEMASK);
+	const struct cache_entry *idx = src[0];
+	const struct cache_entry *tree = src[1];
+	struct rev_info *revs = o->unpack_data;
+
+	/*
+	 * Unpack-trees generates a DF/conflict entry if
+	 * there was a directory in the index and a tree
+	 * in the tree. From a diff standpoint, that's a
+	 * delete of the tree and a create of the file.
+	 */
+	if (tree == o->df_conflict_entry)
+		tree = NULL;
+
+	if (ce_path_match(idx ? idx : tree, &revs->prune_data, NULL)) {
+		do_oneway_diff(o, idx, tree);
+		if (diff_can_quit_early(&revs->diffopt)) {
+			o->exiting_early = 1;
+			return -1;
+		}
 	}
+
+	return 0;
 }
 
-int run_diff_index(struct rev_info *revs, int cached)
+static int diff_cache(struct rev_info *revs,
+		      const unsigned char *tree_sha1,
+		      const char *tree_name,
+		      int cached)
 {
-	int ret;
-	struct object *ent;
 	struct tree *tree;
-	const char *tree_name;
-	int match_missing = 0;
+	struct tree_desc t;
+	struct unpack_trees_options opts;
 
-	/* 
-	 * Backward compatibility wart - "diff-index -m" does
-	 * not mean "do not ignore merges", but totally different.
-	 */
-	if (!revs->ignore_merges)
-		match_missing = 1;
+	tree = parse_tree_indirect(tree_sha1);
+	if (!tree)
+		return error("bad tree object %s",
+			     tree_name ? tree_name : sha1_to_hex(tree_sha1));
+	memset(&opts, 0, sizeof(opts));
+	opts.head_idx = 1;
+	opts.index_only = cached;
+	opts.diff_index_cached = (cached &&
+				  !DIFF_OPT_TST(&revs->diffopt, FIND_COPIES_HARDER));
+	opts.merge = 1;
+	opts.fn = oneway_diff;
+	opts.unpack_data = revs;
+	opts.src_index = &the_index;
+	opts.dst_index = NULL;
+	opts.pathspec = &revs->diffopt.pathspec;
+	opts.pathspec->recursive = 1;
+
+	init_tree_desc(&t, tree->buffer, tree->size);
+	return unpack_trees(1, &t, &opts);
+}
 
-	mark_merge_entries();
+int run_diff_index(struct rev_info *revs, int cached)
+{
+	struct object_array_entry *ent;
 
-	ent = revs->pending.objects[0].item;
-	tree_name = revs->pending.objects[0].name;
-	tree = parse_tree_indirect(ent->sha1);
-	if (!tree)
-		return error("bad tree object %s", tree_name);
-	if (read_tree(tree, 1, revs->prune_data))
-		return error("unable to read tree object %s", tree_name);
-	ret = diff_cache(revs, active_cache, active_nr, revs->prune_data,
-			 cached, match_missing);
+	ent = revs->pending.objects;
+	if (diff_cache(revs, ent->item->sha1, ent->name, cached))
+		exit(128);
+
+	diff_set_mnemonic_prefix(&revs->diffopt, "c/", cached ? "i/" : "w/");
+	diffcore_fix_diff_index(&revs->diffopt);
 	diffcore_std(&revs->diffopt);
 	diff_flush(&revs->diffopt);
-	return ret;
+	return 0;
 }
 
 int do_diff_cache(const unsigned char *tree_sha1, struct diff_options *opt)
 {
-	struct tree *tree;
 	struct rev_info revs;
-	int i;
-	struct cache_entry **dst;
-	struct cache_entry *last = NULL;
-
-	/*
-	 * This is used by git-blame to run diff-cache internally;
-	 * it potentially needs to repeatedly run this, so we will
-	 * start by removing the higher order entries the last round
-	 * left behind.
-	 */
-	dst = active_cache;
-	for (i = 0; i < active_nr; i++) {
-		struct cache_entry *ce = active_cache[i];
-		if (ce_stage(ce)) {
-			if (last && !strcmp(ce->name, last->name))
-				continue;
-			cache_tree_invalidate_path(active_cache_tree,
-						   ce->name);
-			last = ce;
-			ce->ce_mode = 0;
-			ce->ce_flags &= ~htons(CE_STAGEMASK);
-		}
-		*dst++ = ce;
-	}
-	active_nr = dst - active_cache;
 
 	init_revisions(&revs, NULL);
-	revs.prune_data = opt->paths;
-	tree = parse_tree_indirect(tree_sha1);
-	if (!tree)
-		die("bad tree object %s", sha1_to_hex(tree_sha1));
-	if (read_tree(tree, 1, opt->paths))
-		return error("unable to read tree %s", sha1_to_hex(tree_sha1));
-	return diff_cache(&revs, active_cache, active_nr, revs.prune_data,
-			  1, 0);
+	copy_pathspec(&revs.prune_data, &opt->pathspec);
+	revs.diffopt = *opt;
+
+	if (diff_cache(&revs, tree_sha1, NULL, 1))
+		exit(128);
+	return 0;
+}
+
+int index_differs_from(const char *def, int diff_flags)
+{
+	struct rev_info rev;
+	struct setup_revision_opt opt;
+
+	init_revisions(&rev, NULL);
+	memset(&opt, 0, sizeof(opt));
+	opt.def = def;
+	setup_revisions(0, NULL, &rev, &opt);
+	DIFF_OPT_SET(&rev.diffopt, QUICK);
+	DIFF_OPT_SET(&rev.diffopt, EXIT_WITH_STATUS);
+	rev.diffopt.flags |= diff_flags;
+	run_diff_index(&rev, 1);
+	if (rev.pending.alloc)
+		free(rev.pending.objects);
+	return (DIFF_OPT_TST(&rev.diffopt, HAS_CHANGES) != 0);
 }