Merge branch 'mv/log-follow-mergy' into seen

"git log --follow" has been updated to handle non-linear history, in
which the path being tracked gets renamed differently in multiple
history lines, better.

* mv/log-follow-mergy:
  log: improve --follow following renames for non-linear history

Documentation/config/log.adoc

@@ -53,8 +53,7 @@ This is the same as the `--decorate` option of the `git log`.
 `log.follow`::
 	If `true`, `git log` will act as if the `--follow` option was used when
 	a single <path> is given.  This has the same limitations as `--follow`,
-	i.e. it cannot be used to follow multiple files and does not work well
-	on non-linear history.
+	i.e. it cannot be used to follow multiple files.
 
 `log.graphColors`::
 	A list of colors, separated by commas, that can be used to draw

log-tree.c

@@ -3,6 +3,7 @@
 
 #include "git-compat-util.h"
 #include "commit-reach.h"
+#include "commit-slab.h"
 #include "config.h"
 #include "diff.h"
 #include "diffcore.h"
@@ -1089,6 +1090,96 @@ static int do_remerge_diff(struct rev_info *opt,
 	return !opt->loginfo;
 }
 
+/* Per-commit path storage for --follow across merges */
+define_commit_slab(follow_pathspec_slab, char *);
+
+static const char *pathspec_single_path(const struct pathspec *ps)
+{
+	if (ps->nr != 1)
+		return NULL;
+	return ps->items[0].match;
+}
+
+static void set_pathspec_to_single_path(struct pathspec *ps, const char *path)
+{
+	const char *paths[2] = { path, NULL };
+
+	clear_pathspec(ps);
+	parse_pathspec(ps,
+		       PATHSPEC_ALL_MAGIC & ~PATHSPEC_LITERAL,
+		       PATHSPEC_LITERAL_PATH, "", paths);
+}
+
+static void remember_follow_pathspec(struct rev_info *opt,
+				     struct commit *c, const char *path)
+{
+	char **slot;
+
+	if (!path)
+		return;
+	if (!opt->follow_pathspec_slab) {
+		opt->follow_pathspec_slab = xmalloc(sizeof(*opt->follow_pathspec_slab));
+		init_follow_pathspec_slab(opt->follow_pathspec_slab);
+	}
+	slot = follow_pathspec_slab_at(opt->follow_pathspec_slab, c);
+	if (*slot && !strcmp(*slot, path))
+		return;
+	free(*slot);
+	*slot = xstrdup(path);
+}
+
+static const char *recall_follow_pathspec(struct rev_info *opt,
+					  struct commit *c)
+{
+	char **slot;
+
+	if (!opt->follow_pathspec_slab)
+		return NULL;
+	slot = follow_pathspec_slab_peek(opt->follow_pathspec_slab, c);
+	return slot ? *slot : NULL;
+}
+
+static void free_follow_pathspec_slot(char **slot)
+{
+	FREE_AND_NULL(*slot);
+}
+
+void release_follow_pathspec_slab(struct rev_info *opt)
+{
+	if (!opt->follow_pathspec_slab)
+		return;
+	deep_clear_follow_pathspec_slab(opt->follow_pathspec_slab,
+					free_follow_pathspec_slot);
+	FREE_AND_NULL(opt->follow_pathspec_slab);
+}
+
+/* Compute a path to follow in parent, if there is one */
+static void propagate_follow_pathspec_to_parent(struct rev_info *opt,
+						struct commit *commit,
+						struct commit *parent)
+{
+	struct diff_options diff_opts;
+	const char *path;
+
+	parse_commit_or_die(parent);
+	repo_diff_setup(opt->diffopt.repo, &diff_opts);
+	copy_pathspec(&diff_opts.pathspec, &opt->diffopt.pathspec);
+	diff_opts.flags.recursive = 1;
+	diff_opts.flags.follow_renames = 1;
+	diff_opts.output_format = DIFF_FORMAT_NO_OUTPUT;
+	diff_setup_done(&diff_opts);
+	diff_tree_oid(get_commit_tree_oid(parent),
+		      get_commit_tree_oid(commit),
+		      "", &diff_opts);
+
+	path = pathspec_single_path(&diff_opts.pathspec);
+	if (path)
+		remember_follow_pathspec(opt, parent, path);
+
+	diff_queue_clear(&diff_queued_diff);
+	diff_free(&diff_opts);
+}
+
 /*
  * Show the diff of a commit.
  *
@@ -1185,6 +1276,16 @@ int log_tree_commit(struct rev_info *opt, struct commit *commit)
 	opt->loginfo = &log;
 	opt->diffopt.no_free = 1;
 
+	/* Any recorded path for this commit? If so, restore it */
+	if (opt->diffopt.flags.follow_renames) {
+		const char *stored = recall_follow_pathspec(opt, commit);
+		if (stored) {
+			const char *current = pathspec_single_path(&opt->diffopt.pathspec);
+			if (!current || strcmp(current, stored))
+				set_pathspec_to_single_path(&opt->diffopt.pathspec, stored);
+		}
+	}
+
 	if (opt->track_linear && !opt->linear && !opt->reverse_output_stage)
 		fprintf(opt->diffopt.file, "\n%s\n", opt->break_bar);
 	shown = log_tree_diff(opt, commit, &log);
@@ -1197,6 +1298,21 @@ int log_tree_commit(struct rev_info *opt, struct commit *commit)
 		fprintf(opt->diffopt.file, "\n%s\n", opt->break_bar);
 	if (shown)
 		show_diff_of_diff(opt);
+
+	/* Record what path each parent of this commit should use */
+	if (opt->diffopt.flags.follow_renames) {
+		struct commit_list *parents = get_saved_parents(opt, commit);
+		if (parents && parents->next) {
+			struct commit_list *p;
+			for (p = parents; p; p = p->next)
+				propagate_follow_pathspec_to_parent(opt, commit,
+								    p->item);
+		} else if (parents) {
+			remember_follow_pathspec(opt, parents->item,
+				pathspec_single_path(&opt->diffopt.pathspec));
+		}
+	}
+
 	opt->loginfo = NULL;
 	maybe_flush_or_die(opt->diffopt.file, "stdout");
 	opt->diffopt.no_free = no_free;

log-tree.h

@@ -26,6 +26,7 @@ struct decoration_options {
 int parse_decorate_color_config(const char *var, const char *slot_name, const char *value);
 int log_tree_diff_flush(struct rev_info *);
 int log_tree_commit(struct rev_info *, struct commit *);
+void release_follow_pathspec_slab(struct rev_info *);
 void show_log(struct rev_info *opt);
 void format_decorations(struct strbuf *sb, const struct commit *commit,
 			enum git_colorbool use_color, const struct decoration_options *opts);

revision.c

@@ -26,6 +26,7 @@
 #include "decorate.h"
 #include "string-list.h"
 #include "line-log.h"
+#include "log-tree.h"
 #include "mailmap.h"
 #include "commit-slab.h"
 #include "cache-tree.h"
@@ -3302,6 +3303,7 @@ void release_revisions(struct rev_info *revs)
 	line_log_free(revs);
 	oidset_clear(&revs->missing_commits);
 	release_revisions_bloom_keyvecs(revs);
+	release_follow_pathspec_slab(revs);
 }
 
 static void add_child(struct rev_info *revs, struct commit *parent, struct commit *child)

revision.h

@@ -66,6 +66,7 @@ struct repository;
 struct rev_info;
 struct string_list;
 struct saved_parents;
+struct follow_pathspec_slab;
 struct bloom_keyvec;
 struct bloom_filter_settings;
 struct option;
@@ -363,6 +364,9 @@ struct rev_info {
 	/* copies of the parent lists, for --full-diff display */
 	struct saved_parents *saved_parents_slab;
 
+	/* per-commit pathspec for --follow across merges */
+	struct follow_pathspec_slab *follow_pathspec_slab;
+
 	struct commit_list *previous_parents;
 	struct commit_list *ancestry_path_bottoms;
 	const char *break_bar;

t/meson.build

@@ -580,6 +580,7 @@ integration_tests = [
   't4216-log-bloom.sh',
   't4217-log-limit.sh',
   't4218-log-graph-indentation.sh',
+  't4219-log-follow-merge.sh',
   't4252-am-options.sh',
   't4253-am-keep-cr-dos.sh',
   't4254-am-corrupt.sh',

t/t4219-log-follow-merge.sh

@@ -0,0 +1,129 @@
+#!/bin/sh
+
+test_description='Test --follow follows renames across merges'
+
+GIT_TEST_DEFAULT_INITIAL_BRANCH_NAME=master
+export GIT_TEST_DEFAULT_INITIAL_BRANCH_NAME
+
+. ./test-lib.sh
+
+test_expect_success 'setup subtree-merged repository' '
+	git init inner &&
+	echo inner >inner/inner.txt &&
+	git -C inner add inner.txt &&
+	git -C inner commit -m "inner init" &&
+
+	git init outer &&
+	echo outer >outer/outer.txt &&
+	git -C outer add outer.txt &&
+	git -C outer commit -m "outer init" &&
+
+	git -C outer fetch ../inner master &&
+	git -C outer merge -s ours --no-commit --allow-unrelated-histories \
+		FETCH_HEAD &&
+	git -C outer read-tree --prefix=inner/ -u FETCH_HEAD &&
+	git -C outer commit -m "Merge inner repo into inner/ subdirectory"
+'
+
+test_expect_success '--follow finds the pre-merge commit through a subtree merge' '
+	git -C outer log --follow --pretty=tformat:%s inner/inner.txt >actual &&
+	echo "inner init" >expect &&
+	test_cmp expect actual
+'
+
+test_expect_success 'setup merge of two branches that both renamed a file to README' '
+	git init foo &&
+	mkdir foo/foo &&
+	echo "foo readme" >foo/foo/README &&
+	git -C foo add foo/README &&
+	git -C foo commit -m "add foo README" &&
+
+	git -C foo mv foo/README README &&
+	git -C foo commit -m "promote foo README to toplevel" &&
+
+	echo "foo c" >foo/foo.c &&
+	git -C foo add foo.c &&
+	git -C foo commit -m "add foo C impl" &&
+
+	git init bar &&
+	mkdir bar/bar &&
+	echo "bar readme" >bar/bar/README &&
+	git -C bar add bar/README &&
+	git -C bar commit -m "add bar README" &&
+
+	git -C bar mv bar/README README &&
+	git -C bar commit -m "promote bar README to toplevel" &&
+
+	echo "bar c" >bar/bar.c &&
+	git -C bar add bar.c &&
+	git -C bar commit -m "add bar C impl" &&
+
+	git -C foo fetch ../bar master &&
+	git -C foo merge -s ours --no-commit --allow-unrelated-histories \
+		FETCH_HEAD &&
+	git -C foo checkout FETCH_HEAD -- bar.c &&
+	git -C foo commit -m "merge bar into foo"
+'
+
+test_expect_success '--follow follows renames across both sides of a merge' '
+	git -C foo log --follow --pretty=tformat:%s README >actual &&
+	sort actual >actual.sorted &&
+	cat >expect <<-\EOF &&
+	add bar README
+	add foo README
+	promote bar README to toplevel
+	promote foo README to toplevel
+	EOF
+	test_cmp expect actual.sorted
+'
+
+test_expect_success 'setup diamond with renames on both sides of a fork' '
+	git init diamond &&
+	test_lines="line 1\nline 2\nline 3\nline 4\nline 5\n" &&
+
+	printf "$test_lines" >diamond/path0 &&
+	git -C diamond add path0 &&
+	git -C diamond commit -m "A: add path0" &&
+
+	git -C diamond checkout -b upper &&
+	printf "line 1\nline 2\nline 3 modified by B\nline 4\nline 5\n" \
+		>diamond/path0 &&
+	git -C diamond commit -am "B: modify path0 on upper" &&
+	git -C diamond mv path0 path1 &&
+	git -C diamond commit -m "X: rename path0 to path1" &&
+
+	git -C diamond checkout -b lower master &&
+	printf "line 1\nline 2\nline 3 modified by C\nline 4\nline 5\n" \
+		>diamond/path0 &&
+	git -C diamond commit -am "C: modify path0 on lower" &&
+	git -C diamond mv path0 path2 &&
+	git -C diamond commit -m "Y: rename path0 to path2" &&
+
+	git -C diamond checkout upper &&
+	git -C diamond merge -s ours --no-commit lower &&
+	git -C diamond rm path1 &&
+	printf "line 1\nline 2\nline 3 merged\nline 4\nline 5\n" \
+		>diamond/path &&
+	git -C diamond add path &&
+	git -C diamond commit -m "M: merge with rename to path" &&
+
+	printf "line 1\nline 2\nline 3 merged again\nline 4\nline 5\n" \
+		>diamond/path &&
+	git -C diamond commit -am "Z: modify path"
+'
+
+test_expect_success '--follow follows renames through a fork in a single history' '
+	git -C diamond log --follow --pretty=tformat:%s path >actual &&
+	sort actual >actual.sorted &&
+	cat >expect <<-\EOF &&
+	A: add path0
+	B: modify path0 on upper
+	C: modify path0 on lower
+	X: rename path0 to path1
+	Y: rename path0 to path2
+	Z: modify path
+	EOF
+	test_cmp expect actual.sorted
+'
+
+test_done