1 files changed, 161 insertions, 131 deletions

diff --git a/diff-lib.c b/diff-lib.c
index 0c74ef5cbe..0d8c5358e4 100644
--- a/diff-lib.c
+++ b/diff-lib.c
@@ -10,6 +10,8 @@
 #include "cache-tree.h"
 #include "unpack-trees.h"
 #include "refs.h"
+#include "submodule.h"
+#include "dir.h"
 
 /*
  * diff-files
@@ -54,11 +56,38 @@ static int check_removed(const struct cache_entry *ce, struct stat *st)
 	return 0;
 }
 
+/*
+ * 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 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;
+	}
+	return changed;
+}
+
 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);
 
@@ -68,22 +97,25 @@ int run_diff_files(struct rev_info *revs, unsigned int option)
 		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_OPT_TST(&revs->diffopt, QUIET) &&
-			DIFF_OPT_TST(&revs->diffopt, HAS_CHANGES))
+		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);
 
@@ -91,24 +123,23 @@ int run_diff_files(struct rev_info *revs, unsigned int option)
 			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);
 
 			changed = check_removed(ce, &st);
 			if (!changed)
-				dpath->mode = ce_mode_from_stat(ce, st.st_mode);
+				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;
 			}
+			dpath->mode = wt_mode;
 
 			while (i < entries) {
 				struct cache_entry *nce = active_cache[i];
@@ -124,7 +155,7 @@ int run_diff_files(struct rev_info *revs, unsigned int option)
 				if (2 <= stage) {
 					int mode = nce->ce_mode;
 					num_compare_stages++;
-					hashcpy(dpath->parent[stage-2].sha1, nce->sha1);
+					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;
@@ -154,38 +185,58 @@ int run_diff_files(struct rev_info *revs, unsigned int option)
 			 * 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 (ce_uptodate(ce))
+		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);
+		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)
+			} else if (ce->ce_flags & CE_INTENT_TO_ADD) {
+				diff_addremove(&revs->diffopt, '+', ce->ce_mode,
+					       EMPTY_BLOB_SHA1_BIN, 0,
+					       ce->name, 0);
 				continue;
-			diff_addremove(&revs->diffopt, '-', ce->ce_mode,
-				       ce->sha1, ce->name);
-			continue;
+			}
+
+			changed = match_stat_with_submodule(&revs->diffopt, ce, &st,
+							    ce_option, &dirty_submodule);
+			newmode = ce_mode_from_stat(ce, st.st_mode);
 		}
-		changed = ce_match_stat(ce, &st, ce_option);
-		if (!changed) {
+
+		if (!changed && !dirty_submodule) {
 			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);
+		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);
+			    old_sha1, new_sha1,
+			    !is_null_sha1(old_sha1),
+			    !is_null_sha1(new_sha1),
+			    ce->name, 0, dirty_submodule);
 
 	}
 	diffcore_std(&revs->diffopt);
@@ -200,17 +251,20 @@ int run_diff_files(struct rev_info *revs, unsigned int option)
 /* A file entry went away or appeared */
 static void diff_index_show_file(struct rev_info *revs,
 				 const char *prefix,
-				 struct cache_entry *ce,
-				 const 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], mode,
-		       sha1, ce->name);
+		       sha1, sha1_valid, ce->name, dirty_submodule);
 }
 
-static int get_stat_data(struct cache_entry *ce,
+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)
 {
 	const unsigned char *sha1 = ce->sha1;
 	unsigned int mode = ce->ce_mode;
@@ -229,7 +283,8 @@ static int get_stat_data(struct cache_entry *ce,
 			}
 			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 = null_sha1;
@@ -242,35 +297,39 @@ 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)
 {
 	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.
+	 * 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;
 	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;
 	}
 
@@ -282,30 +341,30 @@ 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 = mode;
-		hashclr(p->sha1);
+		oidclr(&p->oid);
 		memset(p->parent, 0, 2 * sizeof(struct combine_diff_parent));
 		p->parent[0].status = DIFF_STATUS_MODIFIED;
 		p->parent[0].mode = new->ce_mode;
-		hashcpy(p->parent[0].sha1, new->sha1);
+		hashcpy(p->parent[0].oid.hash, new->sha1);
 		p->parent[1].status = DIFF_STATUS_MODIFIED;
 		p->parent[1].mode = old->ce_mode;
-		hashcpy(p->parent[1].sha1, old->sha1);
+		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) &&
+	if (mode == oldmode && !hashcmp(sha1, old->sha1) && !dirty_submodule &&
 	    !DIFF_OPT_TST(&revs->diffopt, FIND_COPIES_HARDER))
 		return 0;
 
 	diff_change(&revs->diffopt, oldmode, mode,
-		    old->sha1, sha1, old->name);
+		    old->sha1, sha1, 1, !is_null_sha1(sha1),
+		    old->name, 0, dirty_submodule);
 	return 0;
 }
 
@@ -316,14 +375,22 @@ static int show_modified(struct rev_info *revs,
  * 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)
+			   const struct cache_entry *idx,
+			   const struct cache_entry *tree)
 {
 	struct rev_info *revs = o->unpack_data;
 	int match_missing, cached;
 
+	/* i-t-a entries do not actually exist in the index */
+	if (idx && (idx->ce_flags & CE_INTENT_TO_ADD)) {
+		idx = NULL;
+		if (!tree)
+			return;	/* nothing to diff.. */
+	}
+
 	/* if the entry is not checked out, don't examine work tree */
-	cached = o->index_only || (idx && (idx->ce_flags & CE_VALID));
+	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".
@@ -334,8 +401,10 @@ static void do_oneway_diff(struct unpack_trees_options *o,
 	match_missing = !revs->ignore_merges;
 
 	if (cached && idx && ce_stage(idx)) {
-		diff_unmerge(&revs->diffopt, idx->name, idx->ce_mode,
-			     idx->sha1);
+		struct diff_filepair *pair;
+		pair = diff_unmerge(&revs->diffopt, idx->name);
+		if (tree)
+			fill_filespec(pair->one, tree->sha1, 1, tree->ce_mode);
 		return;
 	}
 
@@ -351,7 +420,7 @@ static void do_oneway_diff(struct unpack_trees_options *o,
 	 * Something removed from the tree?
 	 */
 	if (!idx) {
-		diff_index_show_file(revs, "-", tree, tree->sha1, tree->ce_mode);
+		diff_index_show_file(revs, "-", tree, tree->sha1, 1, tree->ce_mode, 0);
 		return;
 	}
 
@@ -359,21 +428,6 @@ static void do_oneway_diff(struct unpack_trees_options *o,
 	show_modified(revs, tree, idx, 1, cached, match_missing);
 }
 
-static inline void skip_same_name(struct cache_entry *ce, struct unpack_trees_options *o)
-{
-	int len = ce_namelen(ce);
-	const struct index_state *index = o->src_index;
-
-	while (o->pos < index->cache_nr) {
-		struct cache_entry *next = index->cache[o->pos];
-		if (len != ce_namelen(next))
-			break;
-		if (memcmp(ce->name, next->name, len))
-			break;
-		o->pos++;
-	}
-}
-
 /*
  * The unpack_trees() interface is designed for merging, so
  * the different source entries are designed primarily for
@@ -383,21 +437,19 @@ static inline void skip_same_name(struct cache_entry *ce, struct unpack_trees_op
  * For diffing, the index is more important, and we only have a
  * single tree.
  *
- * We're supposed to return how many index entries we want to skip.
+ * 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 int oneway_diff(struct cache_entry **src, struct unpack_trees_options *o)
+static int oneway_diff(const struct cache_entry * const *src,
+		       struct unpack_trees_options *o)
 {
-	struct cache_entry *idx = src[0];
-	struct cache_entry *tree = src[1];
+	const struct cache_entry *idx = src[0];
+	const struct cache_entry *tree = src[1];
 	struct rev_info *revs = o->unpack_data;
 
-	if (idx && ce_stage(idx))
-		skip_same_name(idx, o);
-
 	/*
 	 * Unpack-trees generates a DF/conflict entry if
 	 * there was a directory in the index and a tree
@@ -407,26 +459,30 @@ static int oneway_diff(struct cache_entry **src, struct unpack_trees_options *o)
 	if (tree == o->df_conflict_entry)
 		tree = NULL;
 
-	if (ce_path_match(idx ? idx : tree, revs->prune_data))
+	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)
 {
-	struct object *ent;
 	struct tree *tree;
-	const char *tree_name;
-	struct unpack_trees_options opts;
 	struct tree_desc t;
+	struct unpack_trees_options opts;
 
-	ent = revs->pending.objects[0].item;
-	tree_name = revs->pending.objects[0].name;
-	tree = parse_tree_indirect(ent->sha1);
+	tree = parse_tree_indirect(tree_sha1);
 	if (!tree)
-		return error("bad tree object %s", tree_name);
-
+		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;
@@ -437,12 +493,23 @@ int run_diff_index(struct rev_info *revs, int cached)
 	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);
-	if (unpack_trees(1, &t, &opts))
+	return unpack_trees(1, &t, &opts);
+}
+
+int run_diff_index(struct rev_info *revs, int cached)
+{
+	struct object_array_entry *ent;
+
+	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 0;
@@ -450,53 +517,13 @@ int run_diff_index(struct rev_info *revs, int cached)
 
 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;
+	copy_pathspec(&revs.prune_data, &opt->pathspec);
+	revs.diffopt = *opt;
 
-	init_tree_desc(&t, tree->buffer, tree->size);
-	if (unpack_trees(1, &t, &opts))
+	if (diff_cache(&revs, tree_sha1, NULL, 1))
 		exit(128);
 	return 0;
 }
@@ -504,10 +531,13 @@ int do_diff_cache(const unsigned char *tree_sha1, struct diff_options *opt)
 int index_differs_from(const char *def, int diff_flags)
 {
 	struct rev_info rev;
+	struct setup_revision_opt opt;
 
 	init_revisions(&rev, NULL);
-	setup_revisions(0, NULL, &rev, def);
-	DIFF_OPT_SET(&rev.diffopt, QUIET);
+	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);