Merge branch 'jk/mailmap-from-blob'

Allow us to read, and default to read, mailmap files from the tip
of the history in bare repositories.  This will help running tools
like shortlog in server settings.

* jk/mailmap-from-blob:
  mailmap: default mailmap.blob in bare repositories
  mailmap: fix some documentation loose-ends for mailmap.blob
  mailmap: clean up read_mailmap error handling
  mailmap: support reading mailmap from blobs
  mailmap: refactor mailmap parsing for non-file sources

7 files changed, 214 insertions, 38 deletions

diff --git a/Documentation/config.txt b/Documentation/config.txt
index 50a2288999..0e206759fd 100644
--- a/Documentation/config.txt
+++ b/Documentation/config.txt
@@ -1521,6 +1521,14 @@ mailmap.file::
 	subdirectory, or somewhere outside of the repository itself.
 	See linkgit:git-shortlog[1] and linkgit:git-blame[1].
 
+mailmap.blob::
+	Like `mailmap.file`, but consider the value as a reference to a
+	blob in the repository. If both `mailmap.file` and
+	`mailmap.blob` are given, both are parsed, with entries from
+	`mailmap.file` taking precedence. In a bare repository, this
+	defaults to `HEAD:.mailmap`. In a non-bare repository, it
+	defaults to empty.
+
 man.viewer::
 	Specify the programs that may be used to display help in the
 	'man' format. See linkgit:git-help[1].
diff --git a/Documentation/git-log.txt b/Documentation/git-log.txt
index 585dac40ba..08a185db7f 100644
--- a/Documentation/git-log.txt
+++ b/Documentation/git-log.txt
@@ -167,7 +167,7 @@ log.showroot::
 	`git log -p` output would be shown without a diff attached.
 	The default is `true`.
 
-mailmap.file::
+mailmap.*::
 	See linkgit:git-shortlog[1].
 
 notes.displayRef::
diff --git a/Documentation/mailmap.txt b/Documentation/mailmap.txt
index dd89fca3f8..4a8c276529 100644
--- a/Documentation/mailmap.txt
+++ b/Documentation/mailmap.txt
@@ -1,5 +1,6 @@
 If the file `.mailmap` exists at the toplevel of the repository, or at
-the location pointed to by the mailmap.file configuration option, it
+the location pointed to by the mailmap.file or mailmap.blob
+configuration options, it
 is used to map author and committer names and email addresses to
 canonical real names and email addresses.
 
diff --git a/cache.h b/cache.h
index 8f89f17a0c..8ceb6b8e8d 100644
--- a/cache.h
+++ b/cache.h
@@ -1164,6 +1164,7 @@ extern int author_ident_sufficiently_given(void);
 extern const char *git_commit_encoding;
 extern const char *git_log_output_encoding;
 extern const char *git_mailmap_file;
+extern const char *git_mailmap_blob;
 
 /* IO helper functions */
 extern void maybe_flush_or_die(FILE *, const char *);
diff --git a/config.c b/config.c
index fb3f8681ee..97364c03fc 100644
--- a/config.c
+++ b/config.c
@@ -839,6 +839,8 @@ static int git_default_mailmap_config(const char *var, const char *value)
 {
 	if (!strcmp(var, "mailmap.file"))
 		return git_config_string(&git_mailmap_file, var, value);
+	if (!strcmp(var, "mailmap.blob"))
+		return git_config_string(&git_mailmap_blob, var, value);
 
 	/* Add other config variables here and to Documentation/config.txt. */
 	return 0;
diff --git a/mailmap.c b/mailmap.c
index ea4b471ede..b16542febe 100644
--- a/mailmap.c
+++ b/mailmap.c
@@ -10,6 +10,7 @@ static inline void debug_mm(const char *format, ...) {}
 #endif
 
 const char *git_mailmap_file;
+const char *git_mailmap_blob;
 
 struct mailmap_info {
 	char *name;
@@ -129,54 +130,119 @@ static char *parse_name_and_email(char *buffer, char **name,
 	return (*right == '\0' ? NULL : right);
 }
 
-static int read_single_mailmap(struct string_list *map, const char *filename, char **repo_abbrev)
+static void read_mailmap_line(struct string_list *map, char *buffer,
+			      char **repo_abbrev)
+{
+	char *name1 = NULL, *email1 = NULL, *name2 = NULL, *email2 = NULL;
+	if (buffer[0] == '#') {
+		static const char abbrev[] = "# repo-abbrev:";
+		int abblen = sizeof(abbrev) - 1;
+		int len = strlen(buffer);
+
+		if (!repo_abbrev)
+			return;
+
+		if (len && buffer[len - 1] == '\n')
+			buffer[--len] = 0;
+		if (!strncmp(buffer, abbrev, abblen)) {
+			char *cp;
+
+			if (repo_abbrev)
+				free(*repo_abbrev);
+			*repo_abbrev = xmalloc(len);
+
+			for (cp = buffer + abblen; isspace(*cp); cp++)
+				; /* nothing */
+			strcpy(*repo_abbrev, cp);
+		}
+		return;
+	}
+	if ((name2 = parse_name_and_email(buffer, &name1, &email1, 0)) != NULL)
+		parse_name_and_email(name2, &name2, &email2, 1);
+
+	if (email1)
+		add_mapping(map, name1, email1, name2, email2);
+}
+
+static int read_mailmap_file(struct string_list *map, const char *filename,
+			     char **repo_abbrev)
 {
 	char buffer[1024];
-	FILE *f = (filename == NULL ? NULL : fopen(filename, "r"));
+	FILE *f;
 
-	if (f == NULL)
-		return 1;
-	while (fgets(buffer, sizeof(buffer), f) != NULL) {
-		char *name1 = NULL, *email1 = NULL, *name2 = NULL, *email2 = NULL;
-		if (buffer[0] == '#') {
-			static const char abbrev[] = "# repo-abbrev:";
-			int abblen = sizeof(abbrev) - 1;
-			int len = strlen(buffer);
-
-			if (!repo_abbrev)
-				continue;
-
-			if (len && buffer[len - 1] == '\n')
-				buffer[--len] = 0;
-			if (!strncmp(buffer, abbrev, abblen)) {
-				char *cp;
-
-				if (repo_abbrev)
-					free(*repo_abbrev);
-				*repo_abbrev = xmalloc(len);
-
-				for (cp = buffer + abblen; isspace(*cp); cp++)
-					; /* nothing */
-				strcpy(*repo_abbrev, cp);
-			}
-			continue;
-		}
-		if ((name2 = parse_name_and_email(buffer, &name1, &email1, 0)) != NULL)
-			parse_name_and_email(name2, &name2, &email2, 1);
+	if (!filename)
+		return 0;
 
-		if (email1)
-			add_mapping(map, name1, email1, name2, email2);
+	f = fopen(filename, "r");
+	if (!f) {
+		if (errno == ENOENT)
+			return 0;
+		return error("unable to open mailmap at %s: %s",
+			     filename, strerror(errno));
 	}
+
+	while (fgets(buffer, sizeof(buffer), f) != NULL)
+		read_mailmap_line(map, buffer, repo_abbrev);
 	fclose(f);
 	return 0;
 }
 
+static void read_mailmap_buf(struct string_list *map,
+			     const char *buf, unsigned long len,
+			     char **repo_abbrev)
+{
+	while (len) {
+		const char *end = strchrnul(buf, '\n');
+		unsigned long linelen = end - buf + 1;
+		char *line = xmemdupz(buf, linelen);
+
+		read_mailmap_line(map, line, repo_abbrev);
+
+		free(line);
+		buf += linelen;
+		len -= linelen;
+	}
+}
+
+static int read_mailmap_blob(struct string_list *map,
+			     const char *name,
+			     char **repo_abbrev)
+{
+	unsigned char sha1[20];
+	char *buf;
+	unsigned long size;
+	enum object_type type;
+
+	if (!name)
+		return 0;
+	if (get_sha1(name, sha1) < 0)
+		return 0;
+
+	buf = read_sha1_file(sha1, &type, &size);
+	if (!buf)
+		return error("unable to read mailmap object at %s", name);
+	if (type != OBJ_BLOB)
+		return error("mailmap is not a blob: %s", name);
+
+	read_mailmap_buf(map, buf, size, repo_abbrev);
+
+	free(buf);
+	return 0;
+}
+
 int read_mailmap(struct string_list *map, char **repo_abbrev)
 {
+	int err = 0;
+
 	map->strdup_strings = 1;
-	/* each failure returns 1, so >1 means both calls failed */
-	return read_single_mailmap(map, ".mailmap", repo_abbrev) +
-	       read_single_mailmap(map, git_mailmap_file, repo_abbrev) > 1;
+
+	if (!git_mailmap_blob && is_bare_repository())
+		git_mailmap_blob = "HEAD:.mailmap";
+
+	err |= read_mailmap_file(map, ".mailmap", repo_abbrev);
+	err |= read_mailmap_blob(map, git_mailmap_blob, repo_abbrev);
+	err |= read_mailmap_file(map, git_mailmap_file, repo_abbrev);
+	return err;
 }
 
 void clear_mailmap(struct string_list *map)
diff --git a/t/t4203-mailmap.sh b/t/t4203-mailmap.sh
index 1f182f612c..aae30d97b1 100755
--- a/t/t4203-mailmap.sh
+++ b/t/t4203-mailmap.sh
@@ -149,6 +149,104 @@ test_expect_success 'No mailmap files, but configured' '
 	test_cmp expect actual
 '
 
+test_expect_success 'setup mailmap blob tests' '
+	git checkout -b map &&
+	test_when_finished "git checkout master" &&
+	cat >just-bugs <<-\EOF &&
+	Blob Guy <bugs@company.xx>
+	EOF
+	cat >both <<-\EOF &&
+	Blob Guy <author@example.com>
+	Blob Guy <bugs@company.xx>
+	EOF
+	git add just-bugs both &&
+	git commit -m "my mailmaps" &&
+	echo "Repo Guy <author@example.com>" >.mailmap &&
+	echo "Internal Guy <author@example.com>" >internal.map
+'
+
+test_expect_success 'mailmap.blob set' '
+	cat >expect <<-\EOF &&
+	Blob Guy (1):
+	      second
+
+	Repo Guy (1):
+	      initial
+
+	EOF
+	git -c mailmap.blob=map:just-bugs shortlog HEAD >actual &&
+	test_cmp expect actual
+'
+
+test_expect_success 'mailmap.blob overrides .mailmap' '
+	cat >expect <<-\EOF &&
+	Blob Guy (2):
+	      initial
+	      second
+
+	EOF
+	git -c mailmap.blob=map:both shortlog HEAD >actual &&
+	test_cmp expect actual
+'
+
+test_expect_success 'mailmap.file overrides mailmap.blob' '
+	cat >expect <<-\EOF &&
+	Blob Guy (1):
+	      second
+
+	Internal Guy (1):
+	      initial
+
+	EOF
+	git \
+	  -c mailmap.blob=map:both \
+	  -c mailmap.file=internal.map \
+	  shortlog HEAD >actual &&
+	test_cmp expect actual
+'
+
+test_expect_success 'mailmap.blob can be missing' '
+	cat >expect <<-\EOF &&
+	Repo Guy (1):
+	      initial
+
+	nick1 (1):
+	      second
+
+	EOF
+	git -c mailmap.blob=map:nonexistent shortlog HEAD >actual &&
+	test_cmp expect actual
+'
+
+test_expect_success 'mailmap.blob defaults to off in non-bare repo' '
+	git init non-bare &&
+	(
+		cd non-bare &&
+		test_commit one .mailmap "Fake Name <author@example.com>" &&
+		echo "     1	Fake Name" >expect &&
+		git shortlog -ns HEAD >actual &&
+		test_cmp expect actual &&
+		rm .mailmap &&
+		echo "     1	A U Thor" >expect &&
+		git shortlog -ns HEAD >actual &&
+		test_cmp expect actual
+	)
+'
+
+test_expect_success 'mailmap.blob defaults to HEAD:.mailmap in bare repo' '
+	git clone --bare non-bare bare &&
+	(
+		cd bare &&
+		echo "     1	Fake Name" >expect &&
+		git shortlog -ns HEAD >actual &&
+		test_cmp expect actual
+	)
+'
+
+test_expect_success 'cleanup after mailmap.blob tests' '
+	rm -f .mailmap
+'
+
 # Extended mailmap configurations should give us the following output for shortlog
 cat >expect <<\EOF
 A U Thor <author@example.com> (1):