Merge branch 'en/remerge-diff'

"git log --remerge-diff" shows the difference from mechanical merge
result and the result that is actually recorded in a merge commit.

* en/remerge-diff:
  diff-merges: avoid history simplifications when diffing merges
  merge-ort: mark conflict/warning messages from inner merges as omittable
  show, log: include conflict/warning messages in --remerge-diff headers
  diff: add ability to insert additional headers for paths
  merge-ort: format messages slightly different for use in headers
  merge-ort: mark a few more conflict messages as omittable
  merge-ort: capture and print ll-merge warnings in our preferred fashion
  ll-merge: make callers responsible for showing warnings
  log: clean unneeded objects during `log --remerge-diff`
  show, log: provide a --remerge-diff capability

Author: gitster

Documentation/diff-options.txt

@@ -34,7 +34,7 @@ endif::git-diff[]
 endif::git-format-patch[]
 
 ifdef::git-log[]
---diff-merges=(off|none|on|first-parent|1|separate|m|combined|c|dense-combined|cc)::
+--diff-merges=(off|none|on|first-parent|1|separate|m|combined|c|dense-combined|cc|remerge|r)::
 --no-diff-merges::
 	Specify diff format to be used for merge commits. Default is
 	{diff-merges-default} unless `--first-parent` is in use, in which case
@@ -64,6 +64,18 @@ ifdef::git-log[]
 	each of the parents. Separate log entry and diff is generated
 	for each parent.
 +
+--diff-merges=remerge:::
+--diff-merges=r:::
+--remerge-diff:::
+	With this option, two-parent merge commits are remerged to
+	create a temporary tree object -- potentially containing files
+	with conflict markers and such.  A diff is then shown between
+	that temporary tree and the actual merge commit.
++
+The output emitted when this option is used is subject to change, and
+so is its interaction with other options (unless explicitly
+documented).
++
 --diff-merges=combined:::
 --diff-merges=c:::
 -c:::

apply.c

@@ -3494,7 +3494,7 @@ static int three_way_merge(struct apply_state *state,
 {
 	mmfile_t base_file, our_file, their_file;
 	mmbuffer_t result = { NULL };
-	int status;
+	enum ll_merge_result status;
 
 	/* resolve trivial cases first */
 	if (oideq(base, ours))
@@ -3511,6 +3511,9 @@ static int three_way_merge(struct apply_state *state,
 			  &their_file, "theirs",
 			  state->repo->index,
 			  NULL);
+	if (status == LL_MERGE_BINARY_CONFLICT)
+		warning("Cannot merge binary files: %s (%s vs. %s)",
+			path, "ours", "theirs");
 	free(base_file.ptr);
 	free(our_file.ptr);
 	free(their_file.ptr);

builtin/checkout.c

@@ -246,6 +246,7 @@ static int checkout_merged(int pos, const struct checkout *state,
 	struct cache_entry *ce = active_cache[pos];
 	const char *path = ce->name;
 	mmfile_t ancestor, ours, theirs;
+	enum ll_merge_result merge_status;
 	int status;
 	struct object_id oid;
 	mmbuffer_t result_buf;
@@ -276,13 +277,16 @@ static int checkout_merged(int pos, const struct checkout *state,
 	memset(&ll_opts, 0, sizeof(ll_opts));
 	git_config_get_bool("merge.renormalize", &renormalize);
 	ll_opts.renormalize = renormalize;
-	status = ll_merge(&result_buf, path, &ancestor, "base",
-			  &ours, "ours", &theirs, "theirs",
-			  state->istate, &ll_opts);
+	merge_status = ll_merge(&result_buf, path, &ancestor, "base",
+				&ours, "ours", &theirs, "theirs",
+				state->istate, &ll_opts);
 	free(ancestor.ptr);
 	free(ours.ptr);
 	free(theirs.ptr);
-	if (status < 0 || !result_buf.ptr) {
+	if (merge_status == LL_MERGE_BINARY_CONFLICT)
+		warning("Cannot merge binary files: %s (%s vs. %s)",
+			path, "ours", "theirs");
+	if (merge_status < 0 || !result_buf.ptr) {
 		free(result_buf.ptr);
 		return error(_("path '%s': cannot merge"), path);
 	}

builtin/log.c

@@ -35,6 +35,7 @@
 #include "repository.h"
 #include "commit-reach.h"
 #include "range-diff.h"
+#include "tmp-objdir.h"
 
 #define MAIL_DEFAULT_WRAP 72
 #define COVER_FROM_AUTO_MAX_SUBJECT_LEN 100
@@ -422,6 +423,13 @@ static int cmd_log_walk(struct rev_info *rev)
 	int saved_nrl = 0;
 	int saved_dcctc = 0;
 
+	if (rev->remerge_diff) {
+		rev->remerge_objdir = tmp_objdir_create("remerge-diff");
+		if (!rev->remerge_objdir)
+			die(_("unable to create temporary object directory"));
+		tmp_objdir_replace_primary_odb(rev->remerge_objdir, 1);
+	}
+
 	if (rev->early_output)
 		setup_early_output();
 
@@ -464,6 +472,11 @@ static int cmd_log_walk(struct rev_info *rev)
 	rev->diffopt.no_free = 0;
 	diff_free(&rev->diffopt);
 
+	if (rev->remerge_diff) {
+		tmp_objdir_destroy(rev->remerge_objdir);
+		rev->remerge_objdir = NULL;
+	}
+
 	if (rev->diffopt.output_format & DIFF_FORMAT_CHECKDIFF &&
 	    rev->diffopt.flags.check_failed) {
 		return 02;
@@ -1958,6 +1971,8 @@ int cmd_format_patch(int argc, const char **argv, const char *prefix)
 		die(_("--name-status does not make sense"));
 	if (rev.diffopt.output_format & DIFF_FORMAT_CHECKDIFF)
 		die(_("--check does not make sense"));
+	if (rev.remerge_diff)
+		die(_("--remerge-diff does not make sense"));
 
 	if (!use_patch_format &&
 		(!rev.diffopt.output_format ||

diff-merges.c

@@ -17,12 +17,14 @@ static void suppress(struct rev_info *revs)
 	revs->combined_all_paths = 0;
 	revs->merges_imply_patch = 0;
 	revs->merges_need_diff = 0;
+	revs->remerge_diff = 0;
 }
 
 static void set_separate(struct rev_info *revs)
 {
 	suppress(revs);
 	revs->separate_merges = 1;
+	revs->simplify_history = 0;
 }
 
 static void set_first_parent(struct rev_info *revs)
@@ -45,6 +47,13 @@ static void set_dense_combined(struct rev_info *revs)
 	revs->dense_combined_merges = 1;
 }
 
+static void set_remerge_diff(struct rev_info *revs)
+{
+	suppress(revs);
+	revs->remerge_diff = 1;
+	revs->simplify_history = 0;
+}
+
 static diff_merges_setup_func_t func_by_opt(const char *optarg)
 {
 	if (!strcmp(optarg, "off") || !strcmp(optarg, "none"))
@@ -57,6 +66,8 @@ static diff_merges_setup_func_t func_by_opt(const char *optarg)
 		return set_combined;
 	else if (!strcmp(optarg, "cc") || !strcmp(optarg, "dense-combined"))
 		return set_dense_combined;
+	else if (!strcmp(optarg, "r") || !strcmp(optarg, "remerge"))
+		return set_remerge_diff;
 	else if (!strcmp(optarg, "m") || !strcmp(optarg, "on"))
 		return set_to_default;
 	return NULL;
@@ -110,6 +121,9 @@ int diff_merges_parse_opts(struct rev_info *revs, const char **argv)
 	} else if (!strcmp(arg, "--cc")) {
 		set_dense_combined(revs);
 		revs->merges_imply_patch = 1;
+	} else if (!strcmp(arg, "--remerge-diff")) {
+		set_remerge_diff(revs);
+		revs->merges_imply_patch = 1;
 	} else if (!strcmp(arg, "--no-diff-merges")) {
 		suppress(revs);
 	} else if (!strcmp(arg, "--combined-all-paths")) {

diff.c

@@ -28,6 +28,7 @@
 #include "help.h"
 #include "promisor-remote.h"
 #include "dir.h"
+#include "strmap.h"
 
 #ifdef NO_FAST_WORKING_DIRECTORY
 #define FAST_WORKING_DIRECTORY 0
@@ -3353,6 +3354,31 @@ struct userdiff_driver *get_textconv(struct repository *r,
 	return userdiff_get_textconv(r, one->driver);
 }
 
+static struct strbuf *additional_headers(struct diff_options *o,
+					 const char *path)
+{
+	if (!o->additional_path_headers)
+		return NULL;
+	return strmap_get(o->additional_path_headers, path);
+}
+
+static void add_formatted_headers(struct strbuf *msg,
+				  struct strbuf *more_headers,
+				  const char *line_prefix,
+				  const char *meta,
+				  const char *reset)
+{
+	char *next, *newline;
+
+	for (next = more_headers->buf; *next; next = newline) {
+		newline = strchrnul(next, '\n');
+		strbuf_addf(msg, "%s%s%.*s%s\n", line_prefix, meta,
+			    (int)(newline - next), next, reset);
+		if (*newline)
+			newline++;
+	}
+}
+
 static void builtin_diff(const char *name_a,
 			 const char *name_b,
 			 struct diff_filespec *one,
@@ -3411,6 +3437,17 @@ static void builtin_diff(const char *name_a,
 	b_two = quote_two(b_prefix, name_b + (*name_b == '/'));
 	lbl[0] = DIFF_FILE_VALID(one) ? a_one : "/dev/null";
 	lbl[1] = DIFF_FILE_VALID(two) ? b_two : "/dev/null";
+	if (!DIFF_FILE_VALID(one) && !DIFF_FILE_VALID(two)) {
+		/*
+		 * We should only reach this point for pairs from
+		 * create_filepairs_for_header_only_notifications().  For
+		 * these, we should avoid the "/dev/null" special casing
+		 * above, meaning we avoid showing such pairs as either
+		 * "new file" or "deleted file" below.
+		 */
+		lbl[0] = a_one;
+		lbl[1] = b_two;
+	}
 	strbuf_addf(&header, "%s%sdiff --git %s %s%s\n", line_prefix, meta, a_one, b_two, reset);
 	if (lbl[0][0] == '/') {
 		/* /dev/null */
@@ -4275,6 +4312,7 @@ static void fill_metainfo(struct strbuf *msg,
 	const char *set = diff_get_color(use_color, DIFF_METAINFO);
 	const char *reset = diff_get_color(use_color, DIFF_RESET);
 	const char *line_prefix = diff_line_prefix(o);
+	struct strbuf *more_headers = NULL;
 
 	*must_show_header = 1;
 	strbuf_init(msg, PATH_MAX * 2 + 300);
@@ -4311,6 +4349,11 @@ static void fill_metainfo(struct strbuf *msg,
 	default:
 		*must_show_header = 0;
 	}
+	if ((more_headers = additional_headers(o, name))) {
+		add_formatted_headers(msg, more_headers,
+				      line_prefix, set, reset);
+		*must_show_header = 1;
+	}
 	if (one && two && !oideq(&one->oid, &two->oid)) {
 		const unsigned hexsz = the_hash_algo->hexsz;
 		int abbrev = o->abbrev ? o->abbrev : DEFAULT_ABBREV;
@@ -5803,12 +5846,27 @@ int diff_unmodified_pair(struct diff_filepair *p)
 
 static void diff_flush_patch(struct diff_filepair *p, struct diff_options *o)
 {
-	if (diff_unmodified_pair(p))
+	int include_conflict_headers =
+	    (additional_headers(o, p->one->path) &&
+	     (!o->filter || filter_bit_tst(DIFF_STATUS_UNMERGED, o)));
+
+	/*
+	 * Check if we can return early without showing a diff.  Note that
+	 * diff_filepair only stores {oid, path, mode, is_valid}
+	 * information for each path, and thus diff_unmodified_pair() only
+	 * considers those bits of info.  However, we do not want pairs
+	 * created by create_filepairs_for_header_only_notifications()
+	 * (which always look like unmodified pairs) to be ignored, so
+	 * return early if both p is unmodified AND we don't want to
+	 * include_conflict_headers.
+	 */
+	if (diff_unmodified_pair(p) && !include_conflict_headers)
 		return;
 
+	/* Actually, we can also return early to avoid showing tree diffs */
 	if ((DIFF_FILE_VALID(p->one) && S_ISDIR(p->one->mode)) ||
 	    (DIFF_FILE_VALID(p->two) && S_ISDIR(p->two->mode)))
-		return; /* no tree diffs in patch format */
+		return;
 
 	run_diff(p, o);
 }
@@ -5839,10 +5897,17 @@ static void diff_flush_checkdiff(struct diff_filepair *p,
 	run_checkdiff(p, o);
 }
 
-int diff_queue_is_empty(void)
+int diff_queue_is_empty(struct diff_options *o)
 {
 	struct diff_queue_struct *q = &diff_queued_diff;
 	int i;
+	int include_conflict_headers =
+	    (o->additional_path_headers &&
+	     (!o->filter || filter_bit_tst(DIFF_STATUS_UNMERGED, o)));
+
+	if (include_conflict_headers)
+		return 0;
+
 	for (i = 0; i < q->nr; i++)
 		if (!diff_unmodified_pair(q->queue[i]))
 			return 0;
@@ -6276,6 +6341,54 @@ void diff_warn_rename_limit(const char *varname, int needed, int degraded_cc)
 		warning(_(rename_limit_advice), varname, needed);
 }
 
+static void create_filepairs_for_header_only_notifications(struct diff_options *o)
+{
+	struct strset present;
+	struct diff_queue_struct *q = &diff_queued_diff;
+	struct hashmap_iter iter;
+	struct strmap_entry *e;
+	int i;
+
+	strset_init_with_options(&present, /*pool*/ NULL, /*strdup*/ 0);
+
+	/*
+	 * Find out which paths exist in diff_queued_diff, preferring
+	 * one->path for any pair that has multiple paths.
+	 */
+	for (i = 0; i < q->nr; i++) {
+		struct diff_filepair *p = q->queue[i];
+		char *path = p->one->path ? p->one->path : p->two->path;
+
+		if (strmap_contains(o->additional_path_headers, path))
+			strset_add(&present, path);
+	}
+
+	/*
+	 * Loop over paths in additional_path_headers; for each NOT already
+	 * in diff_queued_diff, create a synthetic filepair and insert that
+	 * into diff_queued_diff.
+	 */
+	strmap_for_each_entry(o->additional_path_headers, &iter, e) {
+		if (!strset_contains(&present, e->key)) {
+			struct diff_filespec *one, *two;
+			struct diff_filepair *p;
+
+			one = alloc_filespec(e->key);
+			two = alloc_filespec(e->key);
+			fill_filespec(one, null_oid(), 0, 0);
+			fill_filespec(two, null_oid(), 0, 0);
+			p = diff_queue(q, one, two);
+			p->status = DIFF_STATUS_MODIFIED;
+		}
+	}
+
+	/* Re-sort the filepairs */
+	diffcore_fix_diff_index();
+
+	/* Cleanup */
+	strset_clear(&present);
+}
+
 static void diff_flush_patch_all_file_pairs(struct diff_options *o)
 {
 	int i;
@@ -6288,6 +6401,9 @@ static void diff_flush_patch_all_file_pairs(struct diff_options *o)
 	if (o->color_moved)
 		o->emitted_symbols = &esm;
 
+	if (o->additional_path_headers)
+		create_filepairs_for_header_only_notifications(o);
+
 	for (i = 0; i < q->nr; i++) {
 		struct diff_filepair *p = q->queue[i];
 		if (check_pair_status(p))
@@ -6358,7 +6474,7 @@ void diff_flush(struct diff_options *options)
 	 * Order: raw, stat, summary, patch
 	 * or:    name/name-status/checkdiff (other bits clear)
 	 */
-	if (!q->nr)
+	if (!q->nr && !options->additional_path_headers)
 		goto free_queue;
 
 	if (output_format & (DIFF_FORMAT_RAW |

diff.h

@@ -395,6 +395,7 @@ struct diff_options {
 
 	struct repository *repo;
 	struct option *parseopts;
+	struct strmap *additional_path_headers;
 
 	int no_free;
 };
@@ -593,7 +594,7 @@ void diffcore_fix_diff_index(void);
 "                show all files diff when -S is used and hit is found.\n" \
 "  -a  --text    treat all files as text.\n"
 
-int diff_queue_is_empty(void);
+int diff_queue_is_empty(struct diff_options *o);
 void diff_flush(struct diff_options*);
 void diff_free(struct diff_options*);
 void diff_warn_rename_limit(const char *varname, int needed, int degraded_cc);