Merge branch 'jc/fix-tree-walk'

* jc/fix-tree-walk:
  read-tree --debug-unpack
  unpack-trees.c: look ahead in the index
  unpack-trees.c: prepare for looking ahead in the index
  Aggressive three-way merge: fix D/F case
  traverse_trees(): handle D/F conflict case sanely
  more D/F conflict tests
  tests: move convenience regexp to match object names to test-lib.sh

Conflicts:
	builtin-read-tree.c
	unpack-trees.c
	unpack-trees.h

1 files changed, 331 insertions, 58 deletions

diff --git a/unpack-trees.c b/unpack-trees.c
index 0ddbef3e63..75f54cac97 100644
--- a/unpack-trees.c
+++ b/unpack-trees.c
@@ -198,23 +198,142 @@ static inline int call_unpack_fn(struct cache_entry **src, struct unpack_trees_o
 	return ret;
 }
 
-static int unpack_index_entry(struct cache_entry *ce, struct unpack_trees_options *o)
+static void mark_ce_used(struct cache_entry *ce, struct unpack_trees_options *o)
+{
+	ce->ce_flags |= CE_UNPACKED;
+
+	if (o->cache_bottom < o->src_index->cache_nr &&
+	    o->src_index->cache[o->cache_bottom] == ce) {
+		int bottom = o->cache_bottom;
+		while (bottom < o->src_index->cache_nr &&
+		       o->src_index->cache[bottom]->ce_flags & CE_UNPACKED)
+			bottom++;
+		o->cache_bottom = bottom;
+	}
+}
+
+static void mark_all_ce_unused(struct index_state *index)
+{
+	int i;
+	for (i = 0; i < index->cache_nr; i++)
+		index->cache[i]->ce_flags &= ~CE_UNPACKED;
+}
+
+static int locate_in_src_index(struct cache_entry *ce,
+			       struct unpack_trees_options *o)
+{
+	struct index_state *index = o->src_index;
+	int len = ce_namelen(ce);
+	int pos = index_name_pos(index, ce->name, len);
+	if (pos < 0)
+		pos = -1 - pos;
+	return pos;
+}
+
+/*
+ * We call unpack_index_entry() with an unmerged cache entry
+ * only in diff-index, and it wants a single callback.  Skip
+ * the other unmerged entry with the same name.
+ */
+static void mark_ce_used_same_name(struct cache_entry *ce,
+				   struct unpack_trees_options *o)
+{
+	struct index_state *index = o->src_index;
+	int len = ce_namelen(ce);
+	int pos;
+
+	for (pos = locate_in_src_index(ce, o); pos < index->cache_nr; pos++) {
+		struct cache_entry *next = index->cache[pos];
+		if (len != ce_namelen(next) ||
+		    memcmp(ce->name, next->name, len))
+			break;
+		mark_ce_used(next, o);
+	}
+}
+
+static struct cache_entry *next_cache_entry(struct unpack_trees_options *o)
+{
+	const struct index_state *index = o->src_index;
+	int pos = o->cache_bottom;
+
+	while (pos < index->cache_nr) {
+		struct cache_entry *ce = index->cache[pos];
+		if (!(ce->ce_flags & CE_UNPACKED))
+			return ce;
+		pos++;
+	}
+	return NULL;
+}
+
+static void add_same_unmerged(struct cache_entry *ce,
+			      struct unpack_trees_options *o)
+{
+	struct index_state *index = o->src_index;
+	int len = ce_namelen(ce);
+	int pos = index_name_pos(index, ce->name, len);
+
+	if (0 <= pos)
+		die("programming error in a caller of mark_ce_used_same_name");
+	for (pos = -pos - 1; pos < index->cache_nr; pos++) {
+		struct cache_entry *next = index->cache[pos];
+		if (len != ce_namelen(next) ||
+		    memcmp(ce->name, next->name, len))
+			break;
+		add_entry(o, next, 0, 0);
+		mark_ce_used(next, o);
+	}
+}
+
+static int unpack_index_entry(struct cache_entry *ce,
+			      struct unpack_trees_options *o)
 {
 	struct cache_entry *src[5] = { ce, NULL, };
+	int ret;
 
-	o->pos++;
+	mark_ce_used(ce, o);
 	if (ce_stage(ce)) {
 		if (o->skip_unmerged) {
 			add_entry(o, ce, 0, 0);
 			return 0;
 		}
 	}
-	return call_unpack_fn(src, o);
+	ret = call_unpack_fn(src, o);
+	if (ce_stage(ce))
+		mark_ce_used_same_name(ce, o);
+	return ret;
+}
+
+static int find_cache_pos(struct traverse_info *, const struct name_entry *);
+
+static void restore_cache_bottom(struct traverse_info *info, int bottom)
+{
+	struct unpack_trees_options *o = info->data;
+
+	if (o->diff_index_cached)
+		return;
+	o->cache_bottom = bottom;
+}
+
+static int switch_cache_bottom(struct traverse_info *info)
+{
+	struct unpack_trees_options *o = info->data;
+	int ret, pos;
+
+	if (o->diff_index_cached)
+		return 0;
+	ret = o->cache_bottom;
+	pos = find_cache_pos(info->prev, &info->name);
+
+	if (pos < -1)
+		o->cache_bottom = -2 - pos;
+	else if (pos < 0)
+		o->cache_bottom = o->src_index->cache_nr;
+	return ret;
 }
 
 static int traverse_trees_recursive(int n, unsigned long dirmask, unsigned long df_conflicts, struct name_entry *names, struct traverse_info *info)
 {
-	int i;
+	int i, ret, bottom;
 	struct tree_desc t[MAX_UNPACK_TREES];
 	struct traverse_info newinfo;
 	struct name_entry *p;
@@ -235,7 +354,11 @@ static int traverse_trees_recursive(int n, unsigned long dirmask, unsigned long
 			sha1 = names[i].sha1;
 		fill_tree_descriptor(t+i, sha1);
 	}
-	return traverse_trees(n, t, &newinfo);
+
+	bottom = switch_cache_bottom(&newinfo);
+	ret = traverse_trees(n, t, &newinfo);
+	restore_cache_bottom(&newinfo, bottom);
+	return ret;
 }
 
 /*
@@ -284,6 +407,20 @@ static int compare_entry(const struct cache_entry *ce, const struct traverse_inf
 	return ce_namelen(ce) > traverse_path_len(info, n);
 }
 
+static int ce_in_traverse_path(const struct cache_entry *ce,
+			       const struct traverse_info *info)
+{
+	if (!info->prev)
+		return 1;
+	if (do_compare_entry(ce, info->prev, &info->name))
+		return 0;
+	/*
+	 * If ce (blob) is the same name as the path (which is a tree
+	 * we will be descending into), it won't be inside it.
+	 */
+	return (info->pathlen < ce_namelen(ce));
+}
+
 static struct cache_entry *create_ce_entry(const struct traverse_info *info, const struct name_entry *n, int stage)
 {
 	int len = traverse_path_len(info, n);
@@ -360,6 +497,114 @@ static int unpack_failed(struct unpack_trees_options *o, const char *message)
 	return -1;
 }
 
+/* NEEDSWORK: give this a better name and share with tree-walk.c */
+static int name_compare(const char *a, int a_len,
+			const char *b, int b_len)
+{
+	int len = (a_len < b_len) ? a_len : b_len;
+	int cmp = memcmp(a, b, len);
+	if (cmp)
+		return cmp;
+	return (a_len - b_len);
+}
+
+/*
+ * The tree traversal is looking at name p.  If we have a matching entry,
+ * return it.  If name p is a directory in the index, do not return
+ * anything, as we will want to match it when the traversal descends into
+ * the directory.
+ */
+static int find_cache_pos(struct traverse_info *info,
+			  const struct name_entry *p)
+{
+	int pos;
+	struct unpack_trees_options *o = info->data;
+	struct index_state *index = o->src_index;
+	int pfxlen = info->pathlen;
+	int p_len = tree_entry_len(p->path, p->sha1);
+
+	for (pos = o->cache_bottom; pos < index->cache_nr; pos++) {
+		struct cache_entry *ce = index->cache[pos];
+		const char *ce_name, *ce_slash;
+		int cmp, ce_len;
+
+		if (!ce_in_traverse_path(ce, info))
+			continue;
+		if (ce->ce_flags & CE_UNPACKED)
+			continue;
+		ce_name = ce->name + pfxlen;
+		ce_slash = strchr(ce_name, '/');
+		if (ce_slash)
+			ce_len = ce_slash - ce_name;
+		else
+			ce_len = ce_namelen(ce) - pfxlen;
+		cmp = name_compare(p->path, p_len, ce_name, ce_len);
+		/*
+		 * Exact match; if we have a directory we need to
+		 * delay returning it.
+		 */
+		if (!cmp)
+			return ce_slash ? -2 - pos : pos;
+		if (0 < cmp)
+			continue; /* keep looking */
+		/*
+		 * ce_name sorts after p->path; could it be that we
+		 * have files under p->path directory in the index?
+		 * E.g.  ce_name == "t-i", and p->path == "t"; we may
+		 * have "t/a" in the index.
+		 */
+		if (p_len < ce_len && !memcmp(ce_name, p->path, p_len) &&
+		    ce_name[p_len] < '/')
+			continue; /* keep looking */
+		break;
+	}
+	return -1;
+}
+
+static struct cache_entry *find_cache_entry(struct traverse_info *info,
+					    const struct name_entry *p)
+{
+	int pos = find_cache_pos(info, p);
+	struct unpack_trees_options *o = info->data;
+
+	if (0 <= pos)
+		return o->src_index->cache[pos];
+	else
+		return NULL;
+}
+
+static void debug_path(struct traverse_info *info)
+{
+	if (info->prev) {
+		debug_path(info->prev);
+		if (*info->prev->name.path)
+			putchar('/');
+	}
+	printf("%s", info->name.path);
+}
+
+static void debug_name_entry(int i, struct name_entry *n)
+{
+	printf("ent#%d %06o %s\n", i,
+	       n->path ? n->mode : 0,
+	       n->path ? n->path : "(missing)");
+}
+
+static void debug_unpack_callback(int n,
+				  unsigned long mask,
+				  unsigned long dirmask,
+				  struct name_entry *names,
+				  struct traverse_info *info)
+{
+	int i;
+	printf("* unpack mask %lu, dirmask %lu, cnt %d ",
+	       mask, dirmask, n);
+	debug_path(info);
+	putchar('\n');
+	for (i = 0; i < n; i++)
+		debug_name_entry(i, names + i);
+}
+
 static int unpack_callback(int n, unsigned long mask, unsigned long dirmask, struct name_entry *names, struct traverse_info *info)
 {
 	struct cache_entry *src[MAX_UNPACK_TREES + 1] = { NULL, };
@@ -370,25 +615,38 @@ static int unpack_callback(int n, unsigned long mask, unsigned long dirmask, str
 	while (!p->mode)
 		p++;
 
+	if (o->debug_unpack)
+		debug_unpack_callback(n, mask, dirmask, names, info);
+
 	/* Are we supposed to look at the index too? */
 	if (o->merge) {
-		while (o->pos < o->src_index->cache_nr) {
-			struct cache_entry *ce = o->src_index->cache[o->pos];
-			int cmp = compare_entry(ce, info, p);
+		while (1) {
+			int cmp;
+			struct cache_entry *ce;
+
+			if (o->diff_index_cached)
+				ce = next_cache_entry(o);
+			else
+				ce = find_cache_entry(info, p);
+
+			if (!ce)
+				break;
+			cmp = compare_entry(ce, info, p);
 			if (cmp < 0) {
 				if (unpack_index_entry(ce, o) < 0)
 					return unpack_failed(o, NULL);
 				continue;
 			}
 			if (!cmp) {
-				o->pos++;
 				if (ce_stage(ce)) {
 					/*
-					 * If we skip unmerged index entries, we'll skip this
-					 * entry *and* the tree entries associated with it!
+					 * If we skip unmerged index
+					 * entries, we'll skip this
+					 * entry *and* the tree
+					 * entries associated with it!
 					 */
 					if (o->skip_unmerged) {
-						add_entry(o, ce, 0, 0);
+						add_same_unmerged(ce, o);
 						return mask;
 					}
 				}
@@ -401,6 +659,13 @@ static int unpack_callback(int n, unsigned long mask, unsigned long dirmask, str
 	if (unpack_nondirectories(n, mask, dirmask, src, names, info) < 0)
 		return -1;
 
+	if (src[0]) {
+		if (ce_stage(src[0]))
+			mark_ce_used_same_name(src[0], o);
+		else
+			mark_ce_used(src[0], o);
+	}
+
 	/* Now handle any directories.. */
 	if (dirmask) {
 		unsigned long conflicts = mask & ~dirmask;
@@ -417,11 +682,13 @@ static int unpack_callback(int n, unsigned long mask, unsigned long dirmask, str
 			matches = cache_tree_matches_traversal(o->src_index->cache_tree,
 							       names, info);
 			/*
-			 * Everything under the name matches.  Adjust o->pos to
-			 * skip the entire hierarchy.
+			 * Everything under the name matches; skip the
+			 * entire hierarchy.  diff_index_cached codepath
+			 * special cases D/F conflicts in such a way that
+			 * it does not do any look-ahead, so this is safe.
 			 */
 			if (matches) {
-				o->pos += matches;
+				o->cache_bottom += matches;
 				return mask;
 			}
 		}
@@ -465,11 +732,10 @@ int unpack_trees(unsigned len, struct tree_desc *t, struct unpack_trees_options
 
 	memset(&o->result, 0, sizeof(o->result));
 	o->result.initialized = 1;
-	if (o->src_index) {
-		o->result.timestamp.sec = o->src_index->timestamp.sec;
-		o->result.timestamp.nsec = o->src_index->timestamp.nsec;
-	}
+	o->result.timestamp.sec = o->src_index->timestamp.sec;
+	o->result.timestamp.nsec = o->src_index->timestamp.nsec;
 	o->merge_size = len;
+	mark_all_ce_unused(o->src_index);
 
 	if (!dfc)
 		dfc = xcalloc(1, cache_entry_size(0));
@@ -483,22 +749,38 @@ int unpack_trees(unsigned len, struct tree_desc *t, struct unpack_trees_options
 		info.fn = unpack_callback;
 		info.data = o;
 
-		if (traverse_trees(len, t, &info) < 0) {
-			ret = unpack_failed(o, NULL);
-			goto done;
+		if (o->prefix) {
+			/*
+			 * Unpack existing index entries that sort before the
+			 * prefix the tree is spliced into.  Note that o->merge
+			 * is always true in this case.
+			 */
+			while (1) {
+				struct cache_entry *ce = next_cache_entry(o);
+				if (!ce)
+					break;
+				if (ce_in_traverse_path(ce, &info))
+					break;
+				if (unpack_index_entry(ce, o) < 0)
+					goto return_failed;
+			}
 		}
+
+		if (traverse_trees(len, t, &info) < 0)
+			goto return_failed;
 	}
 
 	/* Any left-over entries in the index? */
 	if (o->merge) {
-		while (o->pos < o->src_index->cache_nr) {
-			struct cache_entry *ce = o->src_index->cache[o->pos];
-			if (unpack_index_entry(ce, o) < 0) {
-				ret = unpack_failed(o, NULL);
-				goto done;
-			}
+		while (1) {
+			struct cache_entry *ce = next_cache_entry(o);
+			if (!ce)
+				break;
+			if (unpack_index_entry(ce, o) < 0)
+				goto return_failed;
 		}
 	}
+	mark_all_ce_unused(o->src_index);
 
 	if (o->trivial_merges_only && o->nontrivial_merge) {
 		ret = unpack_failed(o, "Merge requires file-level merging");
@@ -543,6 +825,11 @@ done:
 		free(el.excludes);
 
 	return ret;
+
+return_failed:
+	mark_all_ce_unused(o->src_index);
+	ret = unpack_failed(o, NULL);
+	goto done;
 }
 
 /* Here come the merge functions */
@@ -661,7 +948,9 @@ static int verify_clean_subdirectory(struct cache_entry *ce, const char *action,
 	 * in that directory.
 	 */
 	namelen = strlen(ce->name);
-	for (i = o->pos; i < o->src_index->cache_nr; i++) {
+	for (i = locate_in_src_index(ce, o);
+	     i < o->src_index->cache_nr;
+	     i++) {
 		struct cache_entry *ce2 = o->src_index->cache[i];
 		int len = ce_namelen(ce2);
 		if (len < namelen ||
@@ -669,12 +958,14 @@ static int verify_clean_subdirectory(struct cache_entry *ce, const char *action,
 		    ce2->name[namelen] != '/')
 			break;
 		/*
-		 * ce2->name is an entry in the subdirectory.
+		 * ce2->name is an entry in the subdirectory to be
+		 * removed.
 		 */
 		if (!ce_stage(ce2)) {
 			if (verify_uptodate(ce2, o))
 				return -1;
 			add_entry(o, ce2, CE_REMOVE, 0);
+			mark_ce_used(ce2, o);
 		}
 		cnt++;
 	}
@@ -731,7 +1022,6 @@ static int verify_absent_1(struct cache_entry *ce, const char *action,
 		return 0;
 
 	if (!lstat(ce->name, &st)) {
-		int ret;
 		int dtype = ce_to_dtype(ce);
 		struct cache_entry *result;
 
@@ -759,28 +1049,8 @@ static int verify_absent_1(struct cache_entry *ce, const char *action,
 			 * files that are in "foo/" we would lose
 			 * them.
 			 */
-			ret = verify_clean_subdirectory(ce, action, o);
-			if (ret < 0)
-				return ret;
-
-			/*
-			 * If this removed entries from the index,
-			 * what that means is:
-			 *
-			 * (1) the caller unpack_callback() saw path/foo
-			 * in the index, and it has not removed it because
-			 * it thinks it is handling 'path' as blob with
-			 * D/F conflict;
-			 * (2) we will return "ok, we placed a merged entry
-			 * in the index" which would cause o->pos to be
-			 * incremented by one;
-			 * (3) however, original o->pos now has 'path/foo'
-			 * marked with "to be removed".
-			 *
-			 * We need to increment it by the number of
-			 * deleted entries here.
-			 */
-			o->pos += ret;
+			if (verify_clean_subdirectory(ce, action, o) < 0)
+				return -1;
 			return 0;
 		}
 
@@ -927,7 +1197,8 @@ int threeway_merge(struct cache_entry **stages, struct unpack_trees_options *o)
 		remote = NULL;
 	}
 
-	/* First, if there's a #16 situation, note that to prevent #13
+	/*
+	 * First, if there's a #16 situation, note that to prevent #13
 	 * and #14.
 	 */
 	if (!same(remote, head)) {
@@ -941,7 +1212,8 @@ int threeway_merge(struct cache_entry **stages, struct unpack_trees_options *o)
 		}
 	}
 
-	/* We start with cases where the index is allowed to match
+	/*
+	 * We start with cases where the index is allowed to match
 	 * something other than the head: #14(ALT) and #2ALT, where it
 	 * is permitted to match the result instead.
 	 */
@@ -971,12 +1243,13 @@ int threeway_merge(struct cache_entry **stages, struct unpack_trees_options *o)
 	if (!head && !remote && any_anc_missing)
 		return 0;
 
-	/* Under the new "aggressive" rule, we resolve mostly trivial
+	/*
+	 * Under the "aggressive" rule, we resolve mostly trivial
 	 * cases that we historically had git-merge-one-file resolve.
 	 */
 	if (o->aggressive) {
-		int head_deleted = !head && !df_conflict_head;
-		int remote_deleted = !remote && !df_conflict_remote;
+		int head_deleted = !head;
+		int remote_deleted = !remote;
 		struct cache_entry *ce = NULL;
 
 		if (index)