Merge branch 'en/merge-ort-recursive'

The ORT merge strategy learned to synthesize virtual ancestor tree
by recursively merging multiple merge bases together, just like the
recursive backend has done for years.

* en/merge-ort-recursive:
  merge-ort: implement merge_incore_recursive()
  merge-ort: make clear_internal_opts() aware of partial clearing
  merge-ort: copy a few small helper functions from merge-recursive.c
  commit: move reverse_commit_list() from merge-recursive

Author: gitster

commit.c

@@ -574,6 +574,17 @@ struct commit_list *copy_commit_list(struct commit_list *list)
 	return head;
 }
 
+struct commit_list *reverse_commit_list(struct commit_list *list)
+{
+	struct commit_list *next = NULL, *current, *backup;
+	for (current = list; current; current = backup) {
+		backup = current->next;
+		current->next = next;
+		next = current;
+	}
+	return next;
+}
+
 void free_commit_list(struct commit_list *list)
 {
 	while (list)

commit.h

@@ -179,6 +179,9 @@ void commit_list_sort_by_date(struct commit_list **list);
 /* Shallow copy of the input list */
 struct commit_list *copy_commit_list(struct commit_list *list);
 
+/* Modify list in-place to reverse it, returning new head; list will be tail */
+struct commit_list *reverse_commit_list(struct commit_list *list);
+
 void free_commit_list(struct commit_list *list);
 
 struct rev_info; /* in revision.h, it circularly uses enum cmit_fmt */

merge-ort.c

@@ -17,8 +17,10 @@
 #include "cache.h"
 #include "merge-ort.h"
 
+#include "alloc.h"
 #include "blob.h"
 #include "cache-tree.h"
+#include "commit.h"
 #include "commit-reach.h"
 #include "diff.h"
 #include "diffcore.h"
@@ -251,10 +253,11 @@ static void free_strmap_strings(struct strmap *map)
 	}
 }
 
-static void clear_internal_opts(struct merge_options_internal *opti,
-				int reinitialize)
+static void clear_or_reinit_internal_opts(struct merge_options_internal *opti,
+					  int reinitialize)
 {
-	assert(!reinitialize);
+	void (*strmap_func)(struct strmap *, int) =
+		reinitialize ? strmap_partial_clear : strmap_clear;
 
 	/*
 	 * We marked opti->paths with strdup_strings = 0, so that we
@@ -264,14 +267,14 @@ static void clear_internal_opts(struct merge_options_internal *opti,
 	 * to deallocate them.
 	 */
 	free_strmap_strings(&opti->paths);
-	strmap_clear(&opti->paths, 1);
+	strmap_func(&opti->paths, 1);
 
 	/*
 	 * All keys and values in opti->conflicted are a subset of those in
 	 * opti->paths.  We don't want to deallocate anything twice, so we
 	 * don't free the keys and we pass 0 for free_values.
 	 */
-	strmap_clear(&opti->conflicted, 0);
+	strmap_func(&opti->conflicted, 0);
 
 	/*
 	 * opti->paths_to_free is similar to opti->paths; we created it with
@@ -1342,12 +1345,29 @@ void merge_finalize(struct merge_options *opt,
 
 	assert(opt->priv == NULL);
 
-	clear_internal_opts(opti, 0);
+	clear_or_reinit_internal_opts(opti, 0);
 	FREE_AND_NULL(opti);
 }
 
 /*** Function Grouping: helper functions for merge_incore_*() ***/
 
+static inline void set_commit_tree(struct commit *c, struct tree *t)
+{
+	c->maybe_tree = t;
+}
+
+static struct commit *make_virtual_commit(struct repository *repo,
+					  struct tree *tree,
+					  const char *comment)
+{
+	struct commit *commit = alloc_commit_node(repo);
+
+	set_merge_remote_desc(commit, comment, (struct object *)commit);
+	set_commit_tree(commit, tree);
+	commit->object.parsed = 1;
+	return commit;
+}
+
 static void merge_start(struct merge_options *opt, struct merge_result *result)
 {
 	/* Sanity checks on opt */
@@ -1445,6 +1465,89 @@ static void merge_ort_nonrecursive_internal(struct merge_options *opt,
 	}
 }
 
+/*
+ * Originally from merge_recursive_internal(); somewhat adapted, though.
+ */
+static void merge_ort_internal(struct merge_options *opt,
+			       struct commit_list *merge_bases,
+			       struct commit *h1,
+			       struct commit *h2,
+			       struct merge_result *result)
+{
+	struct commit_list *iter;
+	struct commit *merged_merge_bases;
+	const char *ancestor_name;
+	struct strbuf merge_base_abbrev = STRBUF_INIT;
+
+	if (!merge_bases) {
+		merge_bases = get_merge_bases(h1, h2);
+		/* See merge-ort.h:merge_incore_recursive() declaration NOTE */
+		merge_bases = reverse_commit_list(merge_bases);
+	}
+
+	merged_merge_bases = pop_commit(&merge_bases);
+	if (merged_merge_bases == NULL) {
+		/* if there is no common ancestor, use an empty tree */
+		struct tree *tree;
+
+		tree = lookup_tree(opt->repo, opt->repo->hash_algo->empty_tree);
+		merged_merge_bases = make_virtual_commit(opt->repo, tree,
+							 "ancestor");
+		ancestor_name = "empty tree";
+	} else if (merge_bases) {
+		ancestor_name = "merged common ancestors";
+	} else {
+		strbuf_add_unique_abbrev(&merge_base_abbrev,
+					 &merged_merge_bases->object.oid,
+					 DEFAULT_ABBREV);
+		ancestor_name = merge_base_abbrev.buf;
+	}
+
+	for (iter = merge_bases; iter; iter = iter->next) {
+		const char *saved_b1, *saved_b2;
+		struct commit *prev = merged_merge_bases;
+
+		opt->priv->call_depth++;
+		/*
+		 * When the merge fails, the result contains files
+		 * with conflict markers. The cleanness flag is
+		 * ignored (unless indicating an error), it was never
+		 * actually used, as result of merge_trees has always
+		 * overwritten it: the committed "conflicts" were
+		 * already resolved.
+		 */
+		saved_b1 = opt->branch1;
+		saved_b2 = opt->branch2;
+		opt->branch1 = "Temporary merge branch 1";
+		opt->branch2 = "Temporary merge branch 2";
+		merge_ort_internal(opt, NULL, prev, iter->item, result);
+		if (result->clean < 0)
+			return;
+		opt->branch1 = saved_b1;
+		opt->branch2 = saved_b2;
+		opt->priv->call_depth--;
+
+		merged_merge_bases = make_virtual_commit(opt->repo,
+							 result->tree,
+							 "merged tree");
+		commit_list_insert(prev, &merged_merge_bases->parents);
+		commit_list_insert(iter->item,
+				   &merged_merge_bases->parents->next);
+
+		clear_or_reinit_internal_opts(opt->priv, 1);
+	}
+
+	opt->ancestor = ancestor_name;
+	merge_ort_nonrecursive_internal(opt,
+					repo_get_commit_tree(opt->repo,
+							     merged_merge_bases),
+					repo_get_commit_tree(opt->repo, h1),
+					repo_get_commit_tree(opt->repo, h2),
+					result);
+	strbuf_release(&merge_base_abbrev);
+	opt->ancestor = NULL;  /* avoid accidental re-use of opt->ancestor */
+}
+
 void merge_incore_nonrecursive(struct merge_options *opt,
 			       struct tree *merge_base,
 			       struct tree *side1,
@@ -1462,5 +1565,9 @@ void merge_incore_recursive(struct merge_options *opt,
 			    struct commit *side2,
 			    struct merge_result *result)
 {
-	die("Not yet implemented");
+	/* We set the ancestor label based on the merge_bases */
+	assert(opt->ancestor == NULL);
+
+	merge_start(opt, result);
+	merge_ort_internal(opt, merge_bases, side1, side2, result);
 }

merge-ort.h

@@ -34,6 +34,16 @@ struct merge_result {
 /*
  * rename-detecting three-way merge with recursive ancestor consolidation.
  * working tree and index are untouched.
+ *
+ * merge_bases will be consumed (emptied) so make a copy if you need it.
+ *
+ * NOTE: empirically, the recursive algorithm will perform better if you
+ *       pass the merge_bases in the order of oldest commit to the
+ *       newest[1][2].
+ *
+ *       [1] https://lore.kernel.org/git/[email protected]/
+ *       [2] commit 8918b0c9c2 ("merge-recur: try to merge older merge bases
+ *           first", 2006-08-09)
  */
 void merge_incore_recursive(struct merge_options *opt,
 			    struct commit_list *merge_bases,

merge-recursive.c

@@ -3517,17 +3517,6 @@ static int merge_trees_internal(struct merge_options *opt,
 	return clean;
 }
 
-static struct commit_list *reverse_commit_list(struct commit_list *list)
-{
-	struct commit_list *next = NULL, *current, *backup;
-	for (current = list; current; current = backup) {
-		backup = current->next;
-		current->next = next;
-		next = current;
-	}
-	return next;
-}
-
 /*
  * Merge the commits h1 and h2, returning a flag (int) indicating the
  * cleanness of the merge.  Also, if opt->priv->call_depth, create a