cat-file: add mailmap support

git-cat-file is used by tools like GitLab to get commit tag contents
that are then displayed to users. This content which has author,
committer or tagger information, could benefit from passing through the
mailmap mechanism before being sent or displayed.

This patch adds --[no-]use-mailmap command line option to the git
cat-file command. It also adds --[no-]mailmap option as an alias to
--[no-]use-mailmap.

This patch also introduces new test cases to test the mailmap mechanism in
git cat-file command.

Mentored-by: Christian Couder <[email protected]>
Mentored-by: John Cai <[email protected]>
Helped-by: Phillip Wood <[email protected]>
Helped-by: Johannes Schindelin <[email protected]>
Signed-off-by: Siddharth Asthana <[email protected]>
Signed-off-by: Junio C Hamano <[email protected]>

Author: edith007

Documentation/git-cat-file.txt

@@ -63,6 +63,12 @@ OPTIONS
 	or to ask for a "blob" with `<object>` being a tag object that
 	points at it.
 
+--[no-]mailmap::
+--[no-]use-mailmap::
+       Use mailmap file to map author, committer and tagger names
+       and email addresses to canonical real names and email addresses.
+       See linkgit:git-shortlog[1].
+
 --textconv::
 	Show the content as transformed by a textconv filter. In this case,
 	`<object>` has to be of the form `<tree-ish>:<path>`, or `:<path>` in

builtin/cat-file.c

@@ -16,6 +16,7 @@
 #include "packfile.h"
 #include "object-store.h"
 #include "promisor-remote.h"
+#include "mailmap.h"
 
 enum batch_mode {
 	BATCH_MODE_CONTENTS,
@@ -36,6 +37,22 @@ struct batch_options {
 
 static const char *force_path;
 
+static struct string_list mailmap = STRING_LIST_INIT_NODUP;
+static int use_mailmap;
+
+static char *replace_idents_using_mailmap(char *, size_t *);
+
+static char *replace_idents_using_mailmap(char *object_buf, size_t *size)
+{
+	struct strbuf sb = STRBUF_INIT;
+	const char *headers[] = { "author ", "committer ", "tagger ", NULL };
+
+	strbuf_attach(&sb, object_buf, *size, *size + 1);
+	apply_mailmap_to_header(&sb, headers, &mailmap);
+	*size = sb.len;
+	return strbuf_detach(&sb, NULL);
+}
+
 static int filter_object(const char *path, unsigned mode,
 			 const struct object_id *oid,
 			 char **buf, unsigned long *size)
@@ -152,6 +169,12 @@ static int cat_one_file(int opt, const char *exp_type, const char *obj_name,
 		if (!buf)
 			die("Cannot read object %s", obj_name);
 
+		if (use_mailmap) {
+			size_t s = size;
+			buf = replace_idents_using_mailmap(buf, &s);
+			size = cast_size_t_to_ulong(s);
+		}
+
 		/* otherwise just spit out the data */
 		break;
 
@@ -183,6 +206,12 @@ static int cat_one_file(int opt, const char *exp_type, const char *obj_name,
 		}
 		buf = read_object_with_reference(the_repository, &oid,
 						 exp_type_id, &size, NULL);
+
+		if (use_mailmap) {
+			size_t s = size;
+			buf = replace_idents_using_mailmap(buf, &s);
+			size = cast_size_t_to_ulong(s);
+		}
 		break;
 	}
 	default:
@@ -348,11 +377,18 @@ static void print_object_or_die(struct batch_options *opt, struct expand_data *d
 		void *contents;
 
 		contents = read_object_file(oid, &type, &size);
+
+		if (use_mailmap) {
+			size_t s = size;
+			contents = replace_idents_using_mailmap(contents, &s);
+			size = cast_size_t_to_ulong(s);
+		}
+
 		if (!contents)
 			die("object %s disappeared", oid_to_hex(oid));
 		if (type != data->type)
 			die("object %s changed type!?", oid_to_hex(oid));
-		if (data->info.sizep && size != data->size)
+		if (data->info.sizep && size != data->size && !use_mailmap)
 			die("object %s changed size!?", oid_to_hex(oid));
 
 		batch_write(opt, contents, size);
@@ -843,6 +879,8 @@ int cmd_cat_file(int argc, const char **argv, const char *prefix)
 		OPT_CMDMODE('s', NULL, &opt, N_("show object size"), 's'),
 		OPT_BOOL(0, "allow-unknown-type", &unknown_type,
 			  N_("allow -s and -t to work with broken/corrupt objects")),
+		OPT_BOOL(0, "use-mailmap", &use_mailmap, N_("use mail map file")),
+		OPT_ALIAS(0, "mailmap", "use-mailmap"),
 		/* Batch mode */
 		OPT_GROUP(N_("Batch objects requested on stdin (or --batch-all-objects)")),
 		OPT_CALLBACK_F(0, "batch", &batch, N_("format"),
@@ -885,6 +923,9 @@ int cmd_cat_file(int argc, const char **argv, const char *prefix)
 	opt_cw = (opt == 'c' || opt == 'w');
 	opt_epts = (opt == 'e' || opt == 'p' || opt == 't' || opt == 's');
 
+	if (use_mailmap)
+		read_mailmap(&mailmap);
+
 	/* --batch-all-objects? */
 	if (opt == 'b')
 		batch.all_objects = 1;

t/t4203-mailmap.sh

@@ -963,4 +963,63 @@ test_expect_success SYMLINKS 'symlinks not respected in-tree' '
 	test_cmp expect actual
 '
 
+test_expect_success 'prepare for cat-file --mailmap' '
+	rm -f .mailmap &&
+	git commit --allow-empty -m foo --author="Orig <[email protected]>"
+'
+
+test_expect_success '--no-use-mailmap disables mailmap in cat-file' '
+	test_when_finished "rm .mailmap" &&
+	cat >.mailmap <<-EOF &&
+	A U Thor <[email protected]> Orig <[email protected]>
+	EOF
+	cat >expect <<-EOF &&
+	author Orig <[email protected]>
+	EOF
+	git cat-file --no-use-mailmap commit HEAD >log &&
+	sed -n "/^author /s/\([^>]*>\).*/\1/p" log >actual &&
+	test_cmp expect actual
+'
+
+test_expect_success '--use-mailmap enables mailmap in cat-file' '
+	test_when_finished "rm .mailmap" &&
+	cat >.mailmap <<-EOF &&
+	A U Thor <[email protected]> Orig <[email protected]>
+	EOF
+	cat >expect <<-EOF &&
+	author A U Thor <[email protected]>
+	EOF
+	git cat-file --use-mailmap commit HEAD >log &&
+	sed -n "/^author /s/\([^>]*>\).*/\1/p" log >actual &&
+	test_cmp expect actual
+'
+
+test_expect_success '--no-mailmap disables mailmap in cat-file for annotated tag objects' '
+	test_when_finished "rm .mailmap" &&
+	cat >.mailmap <<-EOF &&
+	Orig <[email protected]> C O Mitter <[email protected]>
+	EOF
+	cat >expect <<-EOF &&
+	tagger C O Mitter <[email protected]>
+	EOF
+	git tag -a -m "annotated tag" v1 &&
+	git cat-file --no-mailmap -p v1 >log &&
+	sed -n "/^tagger /s/\([^>]*>\).*/\1/p" log >actual &&
+	test_cmp expect actual
+'
+
+test_expect_success '--mailmap enables mailmap in cat-file for annotated tag objects' '
+	test_when_finished "rm .mailmap" &&
+	cat >.mailmap <<-EOF &&
+	Orig <[email protected]> C O Mitter <[email protected]>
+	EOF
+	cat >expect <<-EOF &&
+	tagger Orig <[email protected]>
+	EOF
+	git tag -a -m "annotated tag" v2 &&
+	git cat-file --mailmap -p v2 >log &&
+	sed -n "/^tagger /s/\([^>]*>\).*/\1/p" log >actual &&
+	test_cmp expect actual
+'
+
 test_done