Merge branch 'sa/cat-file-mailmap'

"git cat-file" learned an option to use the mailmap when showing
commit and tag objects.

* sa/cat-file-mailmap:
  cat-file: add mailmap support
  ident: rename commit_rewrite_person() to apply_mailmap_to_header()
  ident: move commit_rewrite_person() to ident.c
  revision: improve commit_rewrite_person()

6 files changed, 190 insertions, 48 deletions

diff --git a/Documentation/git-cat-file.txt b/Documentation/git-cat-file.txt
index 24a811f..1880e9b 100644
--- a/Documentation/git-cat-file.txt
+++ b/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
diff --git a/builtin/cat-file.c b/builtin/cat-file.c
index f42782e..cbccb55 100644
--- a/builtin/cat-file.c
+++ b/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)
@@ -160,6 +177,12 @@ 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;
 
@@ -193,6 +216,12 @@ 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:
@@ -360,11 +389,18 @@ 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);
@@ -856,6 +892,8 @@ 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"),
@@ -898,6 +936,9 @@ 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;
diff --git a/cache.h b/cache.h
index ac5ab4e..4aa1bd0 100644
--- a/cache.h
+++ b/cache.h
@@ -1689,6 +1689,12 @@ struct ident_split {
 int split_ident_line(struct ident_split *, const char *, int);
 
 /*
+ * Given a commit or tag object buffer and the commit or tag headers, replaces
+ * the idents in the headers with their canonical versions using the mailmap mechanism.
+ */
+void apply_mailmap_to_header(struct strbuf *, const char **, struct string_list *);
+
+/*
  * Compare split idents for equality or strict ordering. Note that we
  * compare only the ident part of the line, ignoring any timestamp.
  *
diff --git a/ident.c b/ident.c
index 89ca5b4..7f66bed 100644
--- a/ident.c
+++ b/ident.c
@@ -8,6 +8,7 @@
 #include "cache.h"
 #include "config.h"
 #include "date.h"
+#include "mailmap.h"
 
 static struct strbuf git_default_name = STRBUF_INIT;
 static struct strbuf git_default_email = STRBUF_INIT;
@@ -346,6 +347,79 @@ person_only:
 	return 0;
 }
 
+/*
+ * Returns the difference between the new and old length of the ident line.
+ */
+static ssize_t rewrite_ident_line(const char *person, size_t len,
+				   struct strbuf *buf,
+				   struct string_list *mailmap)
+{
+	size_t namelen, maillen;
+	const char *name;
+	const char *mail;
+	struct ident_split ident;
+
+	if (split_ident_line(&ident, person, len))
+		return 0;
+
+	mail = ident.mail_begin;
+	maillen = ident.mail_end - ident.mail_begin;
+	name = ident.name_begin;
+	namelen = ident.name_end - ident.name_begin;
+
+	if (map_user(mailmap, &mail, &maillen, &name, &namelen)) {
+		struct strbuf namemail = STRBUF_INIT;
+		size_t newlen;
+
+		strbuf_addf(&namemail, "%.*s <%.*s>",
+			    (int)namelen, name, (int)maillen, mail);
+
+		strbuf_splice(buf, ident.name_begin - buf->buf,
+			      ident.mail_end - ident.name_begin + 1,
+			      namemail.buf, namemail.len);
+		newlen = namemail.len;
+
+		strbuf_release(&namemail);
+
+		return newlen - (ident.mail_end - ident.name_begin);
+	}
+
+	return 0;
+}
+
+void apply_mailmap_to_header(struct strbuf *buf, const char **header,
+			       struct string_list *mailmap)
+{
+	size_t buf_offset = 0;
+
+	if (!mailmap)
+		return;
+
+	for (;;) {
+		const char *person, *line;
+		size_t i;
+		int found_header = 0;
+
+		line = buf->buf + buf_offset;
+		if (!*line || *line == '\n')
+			return; /* End of headers */
+
+		for (i = 0; header[i]; i++)
+			if (skip_prefix(line, header[i], &person)) {
+				const char *endp = strchrnul(person, '\n');
+				found_header = 1;
+				buf_offset += endp - line;
+				buf_offset += rewrite_ident_line(person, endp - person, buf, mailmap);
+				break;
+			}
+
+		if (!found_header) {
+			buf_offset = strchrnul(line, '\n') - buf->buf;
+			if (buf->buf[buf_offset] == '\n')
+				buf_offset++;
+		}
+	}
+}
 
 static void ident_env_hint(enum want_ident whose_ident)
 {
diff --git a/revision.c b/revision.c
index 0c6e26c..87f1c11 100644
--- a/revision.c
+++ b/revision.c
@@ -3791,51 +3791,6 @@ int rewrite_parents(struct rev_info *revs, struct commit *commit,
 	return 0;
 }
 
-static int commit_rewrite_person(struct strbuf *buf, const char *what, struct string_list *mailmap)
-{
-	char *person, *endp;
-	size_t len, namelen, maillen;
-	const char *name;
-	const char *mail;
-	struct ident_split ident;
-
-	person = strstr(buf->buf, what);
-	if (!person)
-		return 0;
-
-	person += strlen(what);
-	endp = strchr(person, '\n');
-	if (!endp)
-		return 0;
-
-	len = endp - person;
-
-	if (split_ident_line(&ident, person, len))
-		return 0;
-
-	mail = ident.mail_begin;
-	maillen = ident.mail_end - ident.mail_begin;
-	name = ident.name_begin;
-	namelen = ident.name_end - ident.name_begin;
-
-	if (map_user(mailmap, &mail, &maillen, &name, &namelen)) {
-		struct strbuf namemail = STRBUF_INIT;
-
-		strbuf_addf(&namemail, "%.*s <%.*s>",
-			    (int)namelen, name, (int)maillen, mail);
-
-		strbuf_splice(buf, ident.name_begin - buf->buf,
-			      ident.mail_end - ident.name_begin + 1,
-			      namemail.buf, namemail.len);
-
-		strbuf_release(&namemail);
-
-		return 1;
-	}
-
-	return 0;
-}
-
 static int commit_match(struct commit *commit, struct rev_info *opt)
 {
 	int retval;
@@ -3868,11 +3823,12 @@ static int commit_match(struct commit *commit, struct rev_info *opt)
 		strbuf_addstr(&buf, message);
 
 	if (opt->grep_filter.header_list && opt->mailmap) {
+		const char *commit_headers[] = { "author ", "committer ", NULL };
+
 		if (!buf.len)
 			strbuf_addstr(&buf, message);
 
-		commit_rewrite_person(&buf, "\nauthor ", opt->mailmap);
-		commit_rewrite_person(&buf, "\ncommitter ", opt->mailmap);
+		apply_mailmap_to_header(&buf, commit_headers, opt->mailmap);
 	}
 
 	/* Append "fake" message parts as needed */
diff --git a/t/t4203-mailmap.sh b/t/t4203-mailmap.sh
index 0b2d21e..cd1cab3 100755
--- a/t/t4203-mailmap.sh
+++ b/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 <orig@example.com>"
+'
+
+test_expect_success '--no-use-mailmap disables mailmap in cat-file' '
+	test_when_finished "rm .mailmap" &&
+	cat >.mailmap <<-EOF &&
+	A U Thor <author@example.com> Orig <orig@example.com>
+	EOF
+	cat >expect <<-EOF &&
+	author Orig <orig@example.com>
+	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 <author@example.com> Orig <orig@example.com>
+	EOF
+	cat >expect <<-EOF &&
+	author A U Thor <author@example.com>
+	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 <orig@example.com> C O Mitter <committer@example.com>
+	EOF
+	cat >expect <<-EOF &&
+	tagger C O Mitter <committer@example.com>
+	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 <orig@example.com> C O Mitter <committer@example.com>
+	EOF
+	cat >expect <<-EOF &&
+	tagger Orig <orig@example.com>
+	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