Merge branch 'ms/mailmap'

* ms/mailmap:
  Move mailmap documentation into separate file
  Change current mailmap usage to do matching on both name and email of author/committer.
  Add map_user() and clear_mailmap() to mailmap
  Add find_insert_index, insert_at_index and clear_func functions to string_list
  Add mailmap.file as configurational option for mailmap location

Documentation/config.txt

@@ -1019,6 +1019,14 @@ log.showroot::
 	Tools like linkgit:git-log[1] or linkgit:git-whatchanged[1], which
 	normally hide the root commit will now show it. True by default.
 
+mailmap.file::
+	The location of an augmenting mailmap file. The default
+	mailmap, located in the root of the repository, is loaded
+	first, then the mailmap file pointed to by this variable.
+	The location of the mailmap file may be in a repository
+	subdirectory, or somewhere outside of the repository itself.
+	See linkgit:git-shortlog[1] and linkgit:git-blame[1].
+
 man.viewer::
 	Specify the programs that may be used to display help in the
 	'man' format. See linkgit:git-help[1].

Documentation/git-blame.txt

@@ -184,6 +184,12 @@ there is ever added information (like the commit encoding or extended
 commit commentary), a blame viewer won't ever care.
 
 
+MAPPING AUTHORS
+---------------
+
+include::mailmap.txt[]
+
+
 SEE ALSO
 --------
 linkgit:git-annotate[1]

Documentation/git-shortlog.txt

@@ -45,45 +45,16 @@ OPTIONS
 	and subsequent lines are indented by `indent2` spaces. `width`,
 	`indent1`, and `indent2` default to 76, 6 and 9 respectively.
 
-FILES
------
-
-If a file `.mailmap` exists at the toplevel of the repository,
-it is used to map an author email address to a canonical real name. This
-can be used to coalesce together commits by the same person where their
-name was spelled differently (whether with the same email address or
-not).
-
-Each line in the file consists, in this order, of the canonical real name
-of an author, whitespace, and an email address (enclosed by '<' and '>')
-to map to the name. Use hash '#' for comments, either on their own line,
-or after the email address.
-
-A canonical name may appear in more than one line, associated with
-different email addresses, but it doesn't make sense for a given address
-to appear more than once (if that happens, a later line overrides the
-earlier ones).
-
-So, for example, if your history contains commits by two authors, Jane
-and Joe, whose names appear in the repository under several forms:
-
-------------
-Joe Developer <joe@example.com>
-Joe R. Developer <joe@example.com>
-Jane Doe <jane@example.com>
-Jane Doe <jane@laptop.(none)>
-Jane D. <jane@desktop.(none)>
-------------
-
-Then, supposing Joe wants his middle name initial used, and Jane prefers
-her family name fully spelled out, a proper `.mailmap` file would look like:
-
-------------
-# Note how we don't need an entry for <jane@laptop.(none)>, because the
-# real name of that author is correct already, and coalesced directly.
-Jane Doe <jane@desktop.(none)>
-Joe R. Developer <joe@example.com>
-------------
+
+MAPPING AUTHORS
+---------------
+
+The `.mailmap` feature is used to coalesce together commits by the same
+person in the shortlog, where their name and/or email address was
+spelled differently.
+
+include::mailmap.txt[]
+
 
 Author
 ------

Documentation/mailmap.txt

@@ -0,0 +1,75 @@
+If the file `.mailmap` exists at the toplevel of the repository, or at
+the location pointed to by the mailmap.file configuration option, it
+is used to map author and committer names and email addresses to
+canonical real names and email addresses.
+
+In the simple form, each line in the file consists of the canonical
+real name of an author, whitespace, and an email address used in the
+commit (enclosed by '<' and '>') to map to the name. Thus, looks like
+this
+--
+	Proper Name <commit@email.xx>
+--
+
+The more complex forms are
+--
+	<proper@email.xx> <commit@email.xx>
+--
+which allows mailmap to replace only the email part of a commit, and
+--
+	Proper Name <proper@email.xx> <commit@email.xx>
+--
+which allows mailmap to replace both the name and the email of a
+commit matching the specified commit email address, and
+--
+	Proper Name <proper@email.xx> Commit Name <commit@email.xx>
+--
+which allows mailmap to replace both the name and the email of a
+commit matching both the specified commit name and email address.
+
+Example 1: Your history contains commits by two authors, Jane
+and Joe, whose names appear in the repository under several forms:
+
+------------
+Joe Developer <joe@example.com>
+Joe R. Developer <joe@example.com>
+Jane Doe <jane@example.com>
+Jane Doe <jane@laptop.(none)>
+Jane D. <jane@desktop.(none)>
+------------
+
+Now suppose that Joe wants his middle name initial used, and Jane
+prefers her family name fully spelled out. A proper `.mailmap` file
+would look like:
+
+------------
+Jane Doe         <jane@desktop.(none)>
+Joe R. Developer <joe@example.com>
+------------
+
+Note how we don't need an entry for <jane@laptop.(none)>, because the
+real name of that author is correct already.
+
+Example 2: Your repository contains commits from the following
+authors:
+
+------------
+nick1 <bugs@company.xx>
+nick2 <bugs@company.xx>
+nick2 <nick2@company.xx>
+santa <me@company.xx>
+claus <me@company.xx>
+CTO <cto@coompany.xx>
+------------
+
+Then, you might want a `.mailmap` file looking like:
+------------
+<cto@company.xx>                       <cto@coompany.xx>
+Some Dude <some@dude.xx>         nick1 <bugs@company.xx>
+Other Author <other@author.xx>   nick2 <bugs@company.xx>
+Other Author <other@author.xx>         <nick2@company.xx>
+Santa Claus <santa.claus@northpole.xx> <me@company.xx>
+------------
+
+Use hash '#' for comments that are either on their own line, or after
+the email address.

Documentation/pretty-formats.txt

@@ -101,16 +101,18 @@ The placeholders are:
 - '%P': parent hashes
 - '%p': abbreviated parent hashes
 - '%an': author name
-- '%aN': author name (respecting .mailmap)
+- '%aN': author name (respecting .mailmap, see linkgit:git-shortlog[1] or linkgit:git-blame[1])
 - '%ae': author email
+- '%aE': author email (respecting .mailmap, see linkgit:git-shortlog[1] or linkgit:git-blame[1])
 - '%ad': author date (format respects --date= option)
 - '%aD': author date, RFC2822 style
 - '%ar': author date, relative
 - '%at': author date, UNIX timestamp
 - '%ai': author date, ISO 8601 format
 - '%cn': committer name
-- '%cN': committer name (respecting .mailmap)
+- '%cN': committer name (respecting .mailmap, see linkgit:git-shortlog[1] or linkgit:git-blame[1])
 - '%ce': committer email
+- '%cE': committer email (respecting .mailmap, see linkgit:git-shortlog[1] or linkgit:git-blame[1])
 - '%cd': committer date
 - '%cD': committer date, RFC2822 style
 - '%cr': committer date, relative

builtin-blame.c

@@ -1264,11 +1264,12 @@ struct commit_info
  * Parse author/committer line in the commit object buffer
  */
 static void get_ac_line(const char *inbuf, const char *what,
-			int bufsz, char *person, const char **mail,
+			int person_len, char *person,
+			int mail_len, char *mail,
 			unsigned long *time, const char **tz)
 {
 	int len, tzlen, maillen;
-	char *tmp, *endp, *timepos;
+	char *tmp, *endp, *timepos, *mailpos;
 
 	tmp = strstr(inbuf, what);
 	if (!tmp)
@@ -1279,10 +1280,11 @@ static void get_ac_line(const char *inbuf, const char *what,
 		len = strlen(tmp);
 	else
 		len = endp - tmp;
-	if (bufsz <= len) {
+	if (person_len <= len) {
 	error_out:
 		/* Ugh */
-		*mail = *tz = "(unknown)";
+		*tz = "(unknown)";
+		strcpy(mail, *tz);
 		*time = 0;
 		return;
 	}
@@ -1305,9 +1307,10 @@ static void get_ac_line(const char *inbuf, const char *what,
 	*tmp = 0;
 	while (*tmp != ' ')
 		tmp--;
-	*mail = tmp + 1;
+	mailpos = tmp + 1;
 	*tmp = 0;
 	maillen = timepos - tmp;
+	memcpy(mail, mailpos, maillen);
 
 	if (!mailmap.nr)
 		return;
@@ -1316,20 +1319,23 @@ static void get_ac_line(const char *inbuf, const char *what,
 	 * mailmap expansion may make the name longer.
 	 * make room by pushing stuff down.
 	 */
-	tmp = person + bufsz - (tzlen + 1);
+	tmp = person + person_len - (tzlen + 1);
 	memmove(tmp, *tz, tzlen);
 	tmp[tzlen] = 0;
 	*tz = tmp;
 
-	tmp = tmp - (maillen + 1);
-	memmove(tmp, *mail, maillen);
-	tmp[maillen] = 0;
-	*mail = tmp;
-
 	/*
-	 * Now, convert e-mail using mailmap
+	 * Now, convert both name and e-mail using mailmap
 	 */
-	map_email(&mailmap, tmp + 1, person, tmp-person-1);
+	if(map_user(&mailmap, mail+1, mail_len-1, person, tmp-person-1)) {
+		/* Add a trailing '>' to email, since map_user returns plain emails
+		   Note: It already has '<', since we replace from mail+1 */
+		mailpos = memchr(mail, '\0', mail_len);
+		if (mailpos && mailpos-mail < mail_len - 1) {
+			*mailpos = '>';
+			*(mailpos+1) = '\0';
+		}
+	}
 }
 
 static void get_commit_info(struct commit *commit,
@@ -1338,8 +1344,10 @@ static void get_commit_info(struct commit *commit,
 {
 	int len;
 	char *tmp, *endp, *reencoded, *message;
-	static char author_buf[1024];
-	static char committer_buf[1024];
+	static char author_name[1024];
+	static char author_mail[1024];
+	static char committer_name[1024];
+	static char committer_mail[1024];
 	static char summary_buf[1024];
 
 	/*
@@ -1357,19 +1365,23 @@ static void get_commit_info(struct commit *commit,
 	}
 	reencoded = reencode_commit_message(commit, NULL);
 	message   = reencoded ? reencoded : commit->buffer;
-	ret->author = author_buf;
+	ret->author = author_name;
+	ret->author_mail = author_mail;
 	get_ac_line(message, "\nauthor ",
-		    sizeof(author_buf), author_buf, &ret->author_mail,
+		    sizeof(author_name), author_name,
+		    sizeof(author_mail), author_mail,
 		    &ret->author_time, &ret->author_tz);
 
 	if (!detailed) {
 		free(reencoded);
 		return;
 	}
 
-	ret->committer = committer_buf;
+	ret->committer = committer_name;
+	ret->committer_mail = committer_mail;
 	get_ac_line(message, "\ncommitter ",
-		    sizeof(committer_buf), committer_buf, &ret->committer_mail,
+		    sizeof(committer_name), committer_name,
+		    sizeof(committer_mail), committer_mail,
 		    &ret->committer_time, &ret->committer_tz);
 
 	ret->summary = summary_buf;
@@ -2396,7 +2408,7 @@ int cmd_blame(int argc, const char **argv, const char *prefix)
 		die("reading graft file %s failed: %s",
 		    revs_file, strerror(errno));
 
-	read_mailmap(&mailmap, ".mailmap", NULL);
+	read_mailmap(&mailmap, NULL);
 
 	if (!incremental)
 		setup_pager();

builtin-shortlog.c

@@ -40,6 +40,7 @@ static void insert_one_record(struct shortlog *log,
 	char *buffer, *p;
 	struct string_list_item *item;
 	char namebuf[1024];
+	char emailbuf[1024];
 	size_t len;
 	const char *eol;
 	const char *boemail, *eoemail;
@@ -51,7 +52,19 @@ static void insert_one_record(struct shortlog *log,
 	eoemail = strchr(boemail, '>');
 	if (!eoemail)
 		return;
-	if (!map_email(&log->mailmap, boemail+1, namebuf, sizeof(namebuf))) {
+
+	/* copy author name to namebuf, to support matching on both name and email */
+	memcpy(namebuf, author, boemail - author);
+	len = boemail - author;
+	while(len > 0 && isspace(namebuf[len-1]))
+		len--;
+	namebuf[len] = 0;
+
+	/* copy email name to emailbuf, to allow email replacement as well */
+	memcpy(emailbuf, boemail+1, eoemail - boemail);
+	emailbuf[eoemail - boemail - 1] = 0;
+
+	if (!map_user(&log->mailmap, emailbuf, sizeof(emailbuf), namebuf, sizeof(namebuf))) {
 		while (author < boemail && isspace(*author))
 			author++;
 		for (len = 0;
@@ -67,8 +80,8 @@ static void insert_one_record(struct shortlog *log,
 
 	if (log->email) {
 		size_t room = sizeof(namebuf) - len - 1;
-		int maillen = eoemail - boemail + 1;
-		snprintf(namebuf + len, room, " %.*s", maillen, boemail);
+		int maillen = strlen(emailbuf);
+		snprintf(namebuf + len, room, " <%.*s>", maillen, emailbuf);
 	}
 
 	item = string_list_insert(namebuf, &log->list);
@@ -219,7 +232,7 @@ void shortlog_init(struct shortlog *log)
 {
 	memset(log, 0, sizeof(*log));
 
-	read_mailmap(&log->mailmap, ".mailmap", &log->common_repo_prefix);
+	read_mailmap(&log->mailmap, &log->common_repo_prefix);
 
 	log->list.strdup_strings = 1;
 	log->wrap = DEFAULT_WRAPLEN;
@@ -248,6 +261,7 @@ int cmd_shortlog(int argc, const char **argv, const char *prefix)
 	struct parse_opt_ctx_t ctx;
 
 	prefix = setup_git_directory_gently(&nongit);
+	git_config(git_default_config, NULL);
 	shortlog_init(&log);
 	init_revisions(&rev, prefix);
 	parse_options_start(&ctx, argc, argv, PARSE_OPT_KEEP_DASHDASH |
@@ -320,6 +334,5 @@ void shortlog_output(struct shortlog *log)
 
 	log->list.strdup_strings = 1;
 	string_list_clear(&log->list, 1);
-	log->mailmap.strdup_strings = 1;
-	string_list_clear(&log->mailmap, 1);
+	clear_mailmap(&log->mailmap);
 }

cache.h

@@ -868,6 +868,7 @@ extern int user_ident_explicitly_given;
 
 extern const char *git_commit_encoding;
 extern const char *git_log_output_encoding;
+extern const char *git_mailmap_file;
 
 /* IO helper functions */
 extern void maybe_flush_or_die(FILE *, const char *);