1 files changed, 301 insertions, 152 deletions

diff --git a/diff-lib.c b/diff-lib.c
index 2c9be60ed9..d7e13cb177 100644
--- a/diff-lib.c
+++ b/diff-lib.c
@@ -7,28 +7,77 @@
 #include "diff.h"
 #include "diffcore.h"
 #include "revision.h"
+#include "cache-tree.h"
+#include "unpack-trees.h"
+#include "refs.h"
+#include "submodule.h"
 
 /*
  * diff-files
  */
 
-int run_diff_files(struct rev_info *revs, int silent_on_removed)
+/*
+ * 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)
+{
+	if (lstat(ce->name, st) < 0) {
+		if (errno != ENOENT && errno != ENOTDIR)
+			return -1;
+		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 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!
+		 */
+		if (!S_ISGITLINK(ce->ce_mode) &&
+		    resolve_gitlink_ref(ce->name, "HEAD", sub))
+			return 1;
+	}
+	return 0;
+}
+
+int run_diff_files(struct rev_info *revs, unsigned int option)
 {
 	int entries, i;
 	int diff_unmerged_stage = revs->max_count;
+	int silent_on_removed = option & DIFF_SILENT_ON_REMOVED;
+	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 = read_cache();
-	if (entries < 0) {
-		perror("read_cache");
-		return -1;
-	}
+	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;
+
+		if (DIFF_OPT_TST(&revs->diffopt, QUICK) &&
+			DIFF_OPT_TST(&revs->diffopt, HAS_CHANGES))
+			break;
 
 		if (!ce_path_match(ce, revs->prune_data))
 			continue;
@@ -40,17 +89,28 @@ int run_diff_files(struct rev_info *revs, int silent_on_removed)
 
 			path_len = ce_namelen(ce);
 
-			dpath = xmalloc (combine_diff_path_size (5, path_len));
+			dpath = xmalloc(combine_diff_path_size(5, path_len));
 			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';
-			dpath->mode = 0;
 			hashclr(dpath->sha1);
 			memset(&(dpath->parent[0]), 0,
-					sizeof(struct combine_diff_parent)*5);
+			       sizeof(struct combine_diff_parent)*5);
+
+			changed = check_removed(ce, &st);
+			if (!changed)
+				dpath->mode = ce_mode_from_stat(ce, st.st_mode);
+			else {
+				if (changed < 0) {
+					perror(ce->name);
+					continue;
+				}
+				if (silent_on_removed)
+					continue;
+			}
 
 			while (i < entries) {
 				struct cache_entry *nce = active_cache[i];
@@ -64,11 +124,10 @@ 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);
+					dpath->parent[stage-2].mode = ce_mode_from_stat(nce, mode);
 					dpath->parent[stage-2].status =
 						DIFF_STATUS_MODIFIED;
 				}
@@ -102,30 +161,40 @@ int run_diff_files(struct rev_info *revs, int silent_on_removed)
 				continue;
 		}
 
-		if (lstat(ce->name, &st) < 0) {
-			if (errno != ENOENT && errno != ENOTDIR) {
+		if (ce_uptodate(ce) || ce_skip_worktree(ce))
+			continue;
+
+		/* If CE_VALID is set, don't look at workdir for file removal */
+		changed = (ce->ce_flags & CE_VALID) ? 0 : check_removed(ce, &st);
+		if (changed) {
+			if (changed < 0) {
 				perror(ce->name);
 				continue;
 			}
 			if (silent_on_removed)
 				continue;
-			diff_addremove(&revs->diffopt, '-', ntohl(ce->ce_mode),
-				       ce->sha1, ce->name, NULL);
+			diff_addremove(&revs->diffopt, '-', ce->ce_mode,
+				       ce->sha1, ce->name, 0);
 			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;
+		changed = ce_match_stat(ce, &st, ce_option);
+		if (S_ISGITLINK(ce->ce_mode)
+		    && !DIFF_OPT_TST(&revs->diffopt, IGNORE_SUBMODULES)
+		    && (!changed || (revs->diffopt.output_format & DIFF_FORMAT_PATCH))
+		    && is_submodule_modified(ce->name)) {
+			changed = 1;
+			dirty_submodule = 1;
+		}
+		if (!changed) {
+			ce_mark_uptodate(ce);
+			if (!DIFF_OPT_TST(&revs->diffopt, FIND_COPIES_HARDER))
+				continue;
+		}
+		oldmode = ce->ce_mode;
+		newmode = ce_mode_from_stat(ce, st.st_mode);
 		diff_change(&revs->diffopt, oldmode, newmode,
 			    ce->sha1, (changed ? null_sha1 : ce->sha1),
-			    ce->name, NULL);
+			    ce->name, 0, dirty_submodule);
 
 	}
 	diffcore_std(&revs->diffopt);
@@ -141,26 +210,30 @@ int run_diff_files(struct rev_info *revs, int silent_on_removed)
 static void diff_index_show_file(struct rev_info *revs,
 				 const char *prefix,
 				 struct cache_entry *ce,
-				 unsigned char *sha1, unsigned int mode)
+				 const unsigned char *sha1, 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, ce->name, dirty_submodule);
 }
 
 static int get_stat_data(struct cache_entry *ce,
-			 unsigned char **sha1p,
+			 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;
@@ -168,11 +241,16 @@ static int get_stat_data(struct cache_entry *ce,
 			return -1;
 		}
 		changed = ce_match_stat(ce, &st, 0);
+		if (S_ISGITLINK(ce->ce_mode)
+		    && !DIFF_OPT_TST(diffopt, IGNORE_SUBMODULES)
+		    && (!changed || (diffopt->output_format & DIFF_FORMAT_PATCH))
+		    && is_submodule_modified(ce->name)) {
+			changed = 1;
+			*dirty_submodule = 1;
+		}
 		if (changed) {
-			mode = create_ce_mode(st.st_mode);
-			if (!trust_executable_bit && S_ISREG(st.st_mode))
-				mode = ce->ce_mode;
-			sha1 = no_sha1;
+			mode = ce_mode_from_stat(ce, st.st_mode);
+			sha1 = null_sha1;
 		}
 	}
 
@@ -185,16 +263,19 @@ static void show_new_file(struct rev_info *revs,
 			  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
+	/*
+	 * New file in the index: it might actually be different in
 	 * the working copy.
 	 */
-	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, mode, dirty_submodule);
 }
 
 static int show_modified(struct rev_info *revs,
@@ -204,12 +285,14 @@ static int show_modified(struct rev_info *revs,
 			 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, old->ce_mode, 0);
 		return -1;
 	}
 
@@ -224,14 +307,14 @@ static int show_modified(struct rev_info *revs,
 		p->len = pathlen;
 		memcpy(p->path, new->name, pathlen);
 		p->path[pathlen] = 0;
-		p->mode = ntohl(mode);
+		p->mode = mode;
 		hashclr(p->sha1);
 		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);
+		p->parent[0].mode = new->ce_mode;
 		hashcpy(p->parent[0].sha1, new->sha1);
 		p->parent[1].status = DIFF_STATUS_MODIFIED;
-		p->parent[1].mode = ntohl(old->ce_mode);
+		p->parent[1].mode = old->ce_mode;
 		hashcpy(p->parent[1].sha1, old->sha1);
 		show_combined_diff(p, 2, revs->dense_combined_merges, revs);
 		free(p);
@@ -240,135 +323,201 @@ static int show_modified(struct rev_info *revs,
 
 	oldmode = old->ce_mode;
 	if (mode == oldmode && !hashcmp(sha1, old->sha1) &&
-	    !revs->diffopt.find_copies_harder)
+	    !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, 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,
+	struct cache_entry *idx,
+	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)) {
+		diff_unmerge(&revs->diffopt, idx->name, idx->ce_mode,
+			     idx->sha1);
+		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, 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(struct cache_entry **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);
-	}
+	struct cache_entry *idx = src[0];
+	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))
+		do_oneway_diff(o, idx, tree);
+
+	return 0;
 }
 
 int run_diff_index(struct rev_info *revs, int cached)
 {
-	int ret;
 	struct object *ent;
 	struct tree *tree;
 	const char *tree_name;
-	int match_missing = 0;
-
-	/* 
-	 * Backward compatibility wart - "diff-index -m" does
-	 * not mean "do not ignore merges", but totally different.
-	 */
-	if (!revs->ignore_merges)
-		match_missing = 1;
-
-	if (read_cache() < 0) {
-		perror("read_cache");
-		return -1;
-	}
-	mark_merge_entries();
+	struct unpack_trees_options opts;
+	struct tree_desc t;
 
 	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);
+
+	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;
+
+	init_tree_desc(&t, tree->buffer, tree->size);
+	if (unpack_trees(1, &t, &opts))
+		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;
+	struct unpack_trees_options opts;
+	struct tree_desc t;
+
+	/*
+	 * 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_flags |= CE_REMOVE;
+		}
+		*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));
+
+	memset(&opts, 0, sizeof(opts));
+	opts.head_idx = 1;
+	opts.index_only = 1;
+	opts.diff_index_cached = !DIFF_OPT_TST(opt, FIND_COPIES_HARDER);
+	opts.merge = 1;
+	opts.fn = oneway_diff;
+	opts.unpack_data = &revs;
+	opts.src_index = &the_index;
+	opts.dst_index = &the_index;
+
+	init_tree_desc(&t, tree->buffer, tree->size);
+	if (unpack_trees(1, &t, &opts))
+		exit(128);
+	return 0;
+}
+
+int index_differs_from(const char *def, int diff_flags)
+{
+	struct rev_info rev;
+
+	init_revisions(&rev, NULL);
+	setup_revisions(0, NULL, &rev, def);
+	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);
 }