Apply the mailmap at HEAD to every ident

9 files changed, 153 insertions, 8 deletions

diff --git a/MANUAL.txt b/MANUAL.txt
index fc91125..aa581f0 100644
--- a/MANUAL.txt
+++ b/MANUAL.txt
@@ -235,6 +235,15 @@ enable-log-linecount::
 	and removed lines for each commit on the repository log page. Default
 	value: "0".
 
+enable-mailmap::
+	Flag which, when set to "1", applies the repository's mailmap to every
+	author, committer and tagger shown, so a person who changed name or
+	address appears under one identity in the log, commit, tag, blame and
+	statistics pages, the atom feed and the author search. Only the
+	.mailmap blob at HEAD is read, as git does for a bare repository, and
+	the mailmap.file and mailmap.blob settings are ignored. Default value:
+	"1". See also: "repo.enable-mailmap".
+
 enable-plain-email::
 	Flag which, when set to "0", hides the full author, committer and tagger
 	email addresses wherever they would be shown beside the name. Default
@@ -614,6 +623,10 @@ repo.enable-log-linecount::
 	A flag which can be used to override the global setting
 	"enable-log-linecount". Default value: <enable-log-linecount>.
 
+repo.enable-mailmap::
+	A flag which can be used to override the global setting
+	"enable-mailmap". Default value: <enable-mailmap>.
+
 repo.enable-remote-branches::
 	A flag which can be used to override the global setting
 	"enable-remote-branches". Default value: <enable-remote-branches>.
diff --git a/custom/cgitrc b/custom/cgitrc
index 7ba1e13..9684a0b 100644
--- a/custom/cgitrc
+++ b/custom/cgitrc
@@ -201,6 +201,11 @@ enable-log-filecount=0
 # Default is 0.
 enable-log-linecount=0
 
+# Apply the .mailmap at HEAD to every author, committer and tagger shown, so a
+# person who changed name or address appears under one identity. Values are 0
+# or 1. Default is 1.
+enable-mailmap=1
+
 # Show ages in the log, refs and index columns as an elapsed time such as "3
 # days" rather than a calendar date. Values are 0 or 1. Default is 1.
 enable-relative-dates=1
@@ -497,6 +502,10 @@ enable-plain-email=1
 # global enable-log-linecount value.
 #repo.enable-log-linecount=0
 
+# Per-repo override of enable-mailmap. Values are 0 or 1. Default is the global
+# enable-mailmap value.
+#repo.enable-mailmap=1
+
 # Per-repo override of enable-remote-branches. Values are 0 or 1. Default is the
 # global enable-remote-branches value.
 #repo.enable-remote-branches=0
diff --git a/source/cgit.c b/source/cgit.c
index ae91dd2..36f3b25 100644
--- a/source/cgit.c
+++ b/source/cgit.c
@@ -107,6 +107,7 @@ static void prepare_context(void)
 	ctx.cfg.local_time = 0;
 	ctx.cfg.date_mode = date_mode_from_type(DATE_SHORT);
 	ctx.cfg.enable_header = 1;
+	ctx.cfg.enable_mailmap = 1;
 	ctx.cfg.enable_plain_email = 1;
 	ctx.cfg.enable_relative_dates = 1;
 	ctx.cfg.enable_http_clone = 1;
@@ -239,6 +240,7 @@ static void print_repo(FILE *f, struct cgit_repo *repo)
 	fprintf(f, "repo.enable-gitmodules-links=%d\n", repo->enable_gitmodules_links);
 	fprintf(f, "repo.enable-log-filecount=%d\n", repo->enable_log_filecount);
 	fprintf(f, "repo.enable-log-linecount=%d\n", repo->enable_log_linecount);
+	fprintf(f, "repo.enable-mailmap=%d\n", repo->enable_mailmap);
 	if (repo->about_filter && repo->about_filter != ctx.cfg.about_filter)
 		cgit_fprintf_filter(repo->about_filter, f, "repo.about-filter=");
 	if (repo->commit_filter && repo->commit_filter != ctx.cfg.commit_filter)
@@ -557,6 +559,8 @@ static void apply_config(const char *name, const char *value)
 		ctx.cfg.enable_log_filecount = atoi(value);
 	else if (!strcmp(name, "enable-log-linecount"))
 		ctx.cfg.enable_log_linecount = atoi(value);
+	else if (!strcmp(name, "enable-mailmap"))
+		ctx.cfg.enable_mailmap = atoi(value);
 	else if (!strcmp(name, "enable-relative-dates"))
 		ctx.cfg.enable_relative_dates = atoi(value);
 	else if (!strcmp(name, "enable-remote-branches"))
@@ -1168,6 +1172,8 @@ void cgit_repo_config(struct cgit_repo *repo, const char *name, const char *valu
 		repo->enable_log_filecount = atoi(value);
 	else if (!strcmp(name, "enable-log-linecount"))
 		repo->enable_log_linecount = atoi(value);
+	else if (!strcmp(name, "enable-mailmap"))
+		repo->enable_mailmap = atoi(value);
 	else if (!strcmp(name, "enable-remote-branches"))
 		repo->enable_remote_branches = atoi(value);
 	else if (!strcmp(name, "enable-subject-links"))
diff --git a/source/cgit.h b/source/cgit.h
index d976906..5a9e756 100644
--- a/source/cgit.h
+++ b/source/cgit.h
@@ -88,6 +88,7 @@ struct cgit_repo {
 	int enable_gitmodules_links;
 	int enable_log_filecount;
 	int enable_log_linecount;
+	int enable_mailmap;
 	int enable_remote_branches;
 	int enable_subject_links;
 	int enable_trailers;
@@ -226,6 +227,7 @@ struct cgit_config {
 	int enable_commit_graph;
 	int enable_log_filecount;
 	int enable_log_linecount;
+	int enable_mailmap;
 	int enable_plain_email;
 	int enable_relative_dates;
 	int enable_remote_branches;
diff --git a/source/parsing.c b/source/parsing.c
index c992538..587f44d 100644
--- a/source/parsing.c
+++ b/source/parsing.c
@@ -13,6 +13,8 @@
 #include "parsing.h"
 #include "shared.h"
 
+#include <mailmap.h>
+
 static char *substr(const char *start, const char *end)
 {
 	size_t len;
@@ -29,22 +31,45 @@ static char *substr(const char *start, const char *end)
 	return buf;
 }
 
+/*
+ * The repository's mailmap, read once per request and applied to every ident
+ * a page shows. Only the blob at HEAD is read, the way git reads a bare
+ * repository, so a repository cannot point the reader at a file on the server.
+ */
+static struct string_list mailmap = STRING_LIST_INIT_DUP;
+static int mailmap_read;
+
+struct string_list *cgit_mailmap(void)
+{
+	if (!ctx.repo || !ctx.repo->enable_mailmap)
+		return NULL;
+	if (!mailmap_read) {
+		mailmap_read = 1;
+		read_mailmap_blob(the_repository, &mailmap, "HEAD:.mailmap");
+	}
+	return mailmap.nr ? &mailmap : NULL;
+}
+
 static void parse_user(const char *line, char **name, char **email, timestamp_t *date, int *tz)
 {
 	struct ident_split ident;
 	struct strbuf address = STRBUF_INIT;
-	ptrdiff_t email_len;
+	struct string_list *map;
+	const char *name_start, *mail_start;
+	size_t name_len, mail_len;
 
 	if (!split_ident_line(&ident, line, strchrnul(line, '\n') - line)) {
-		*name = substr(ident.name_begin, ident.name_end);
+		name_start = ident.name_begin;
+		name_len = ident.name_end - ident.name_begin;
+		mail_start = ident.mail_begin;
+		mail_len = ident.mail_end - ident.mail_begin;
+		map = cgit_mailmap();
+		if (map)
+			map_user(map, &mail_start, &mail_len, &name_start, &name_len);
+		*name = xmemdupz(name_start, name_len);
 
-		// Assembled rather than formatted. The length is a pointer
-		// difference, and the precision of a %.*s conversion has to be
-		// an int, which cannot hold one on a 64 bit host.
-		email_len = ident.mail_end - ident.mail_begin;
 		strbuf_addch(&address, '<');
-		if (email_len > 0)
-			strbuf_add(&address, ident.mail_begin, email_len);
+		strbuf_add(&address, mail_start, mail_len);
 		strbuf_addch(&address, '>');
 		*email = strbuf_detach(&address, NULL);
 
diff --git a/source/parsing.h b/source/parsing.h
index b1dc9f1..d213429 100644
--- a/source/parsing.h
+++ b/source/parsing.h
@@ -14,6 +14,7 @@
 // storing them in ctx.qry.
 extern void cgit_parse_url(const char *url);
 
+extern struct string_list *cgit_mailmap(void);
 extern struct commitinfo *cgit_parse_commit(struct commit *commit);
 extern struct taginfo *cgit_parse_tag(struct tag *tag);
 
diff --git a/source/shared.c b/source/shared.c
index 59712ce..6ac2353 100644
--- a/source/shared.c
+++ b/source/shared.c
@@ -213,6 +213,7 @@ struct cgit_repo *cgit_add_repo(const char *url)
 	repo->enable_gitmodules_links = ctx.cfg.enable_gitmodules_links;
 	repo->enable_log_filecount = ctx.cfg.enable_log_filecount;
 	repo->enable_log_linecount = ctx.cfg.enable_log_linecount;
+	repo->enable_mailmap = ctx.cfg.enable_mailmap;
 	repo->enable_remote_branches = ctx.cfg.enable_remote_branches;
 	repo->enable_subject_links = ctx.cfg.enable_subject_links;
 	repo->enable_trailers = ctx.cfg.enable_trailers;
diff --git a/source/ui-log.c b/source/ui-log.c
index 8fe58f9..316df75 100644
--- a/source/ui-log.c
+++ b/source/ui-log.c
@@ -492,6 +492,8 @@ void cgit_print_log(const char *tip, int ofs, int cnt, char *grep, char *pattern
 		strvec_push(&rev_argv, path);
 
 	repo_init_revisions(the_repository, &rev, NULL);
+	// The author and committer searches then match the mapped idents.
+	rev.mailmap = cgit_mailmap();
 	rev.abbrev = DEFAULT_ABBREV;
 	rev.commit_format = CMIT_FMT_DEFAULT;
 	rev.verbose_header = 1;
diff --git a/tests/t0208-mailmap.sh b/tests/t0208-mailmap.sh
new file mode 100755
index 0000000..ca08de0
--- /dev/null
+++ b/tests/t0208-mailmap.sh
@@ -0,0 +1,86 @@
+#!/bin/sh
+
+# The mailmap. A repository whose commits and tag carry an old ident gets a
+# .mailmap at HEAD renaming it, and the log, commit, tag, atom and search
+# pages are checked for the new name, then the flag is turned off globally and
+# for the one repository.
+
+test_description='Check the mailmap is applied to idents'
+CGIT_TEST_NO_CREATE_REPOS=YesPlease
+. ./setup.sh
+
+test_expect_success 'create a repository with a mailmap at its head' '
+	test_create_repo repos/mapped &&
+	(
+		cd repos/mapped &&
+		echo content >file &&
+		git add file &&
+		GIT_AUTHOR_NAME="Old Name" GIT_AUTHOR_EMAIL=old@example.com \
+			git commit -m "first commit" &&
+		GIT_COMMITTER_NAME="Old Name" GIT_COMMITTER_EMAIL=old@example.com \
+			git tag -a -m "a tag" v1 &&
+		echo "New Name <new@example.com> <old@example.com>" >.mailmap &&
+		git add .mailmap &&
+		git commit -m "add the mailmap"
+	)
+'
+
+test_expect_success 'point cgit at it' '
+	cat >cgitrc <<-EOF
+	virtual-root=/
+	cache-size=0
+	repo.url=mapped
+	repo.path=$PWD/repos/mapped/.git
+	EOF
+'
+
+test_expect_success 'the log shows the mapped author' '
+	cgit_url "mapped/log/" >tmp &&
+	grep ">first commit</a>" tmp &&
+	grep "<td class=.col-author.>New Name</td>" tmp &&
+	! grep "Old Name" tmp
+'
+
+test_expect_success 'the commit page shows the mapped author and address' '
+	first=$(git -C repos/mapped rev-parse HEAD~1) &&
+	cgit_url "mapped/commit/&id=$first" >tmp &&
+	grep "<th>author</th><td>New Name &lt;new@example.com&gt;</td>" tmp &&
+	! grep "old@example.com" tmp
+'
+
+test_expect_success 'the tag page shows the mapped tagger' '
+	cgit_url "mapped/tag/&h=v1" >tmp &&
+	grep "New Name &lt;new@example.com&gt;" tmp &&
+	! grep "Old Name" tmp
+'
+
+test_expect_success 'the atom feed uses the mapped name and address' '
+	cgit_url "mapped/atom/" >tmp &&
+	grep "<name>New Name</name>" tmp &&
+	grep "<email>new@example.com</email>" tmp &&
+	! grep "Old Name" tmp
+'
+
+test_expect_success 'the author search matches the mapped name' '
+	cgit_query "url=mapped/log/&qt=author&q=New+Name" >tmp &&
+	grep ">first commit</a>" tmp &&
+	cgit_query "url=mapped/log/&qt=author&q=Nobody" >tmp &&
+	! grep ">first commit</a>" tmp
+'
+
+test_expect_success 'with the flag off the old ident shows' '
+	{
+		echo "enable-mailmap=0" &&
+		cat cgitrc
+	} >cgitrc-off &&
+	CGIT_CONFIG="$PWD/cgitrc-off" QUERY_STRING="url=mapped/log/" cgit >tmp &&
+	grep "<td class=.col-author.>Old Name</td>" tmp
+'
+
+test_expect_success 'the repository flag overrides the global one' '
+	echo "repo.enable-mailmap=0" >>cgitrc &&
+	cgit_url "mapped/log/" >tmp &&
+	grep "<td class=.col-author.>Old Name</td>" tmp
+'
+
+test_done