gitweb: Map names/emails with mailmap

Commit Message

Emma Brooks Aug. 8, 2020, 9:34 p.m. UTC

Add an option to map names and emails to their canonical forms via a
.mailmap file. This is enabled by default, consistent with the behavior
of Git itself.

Signed-off-by: Emma Brooks <[e-mail]>
---
 Documentation/gitweb.conf.txt |  5 +++
 gitweb/gitweb.perl            | 81 +++++++++++++++++++++++++++++++++--
 2 files changed, 82 insertions(+), 4 deletions(-)

Patch

diff --git a/Documentation/gitweb.conf.txt b/Documentation/gitweb.conf.txt
index 7963a79ba9..2d7551a6a5 100644
--- a/Documentation/gitweb.conf.txt
+++ b/Documentation/gitweb.conf.txt
@@ -751,6 +751,11 @@  default font sizes or lineheights are changed (e.g. via adding extra
 CSS stylesheet in `@stylesheets`), it may be appropriate to change
 these values.
 
+mailmap::
+	Use mailmap to find the canonical name/email for
+	committers/authors (see linkgit:git-shortlog[1]). Enabled by
+	default.
+
 highlight::
 	Server-side syntax highlight support in "blob" view.  It requires
 	`$highlight_bin` program to be available (see the description of
diff --git a/gitweb/gitweb.perl b/gitweb/gitweb.perl
index 0959a782ec..1ca495b8b4 100755
--- a/gitweb/gitweb.perl
+++ b/gitweb/gitweb.perl
@@ -505,6 +505,12 @@  sub evaluate_uri {
 		'override' => 0,
 		'default' => ['']},
 
+	# Enable reading mailmap to determine canonical author
+	# information. Enabled by default.
+	'mailmap' => {
+		'override' => 0,
+		'default' => [1]},
+
 	# Enable displaying how much time and how many git commands
 	# it took to generate and display page.  Disabled by default.
 	# Project specific override is not supported.
@@ -3490,6 +3496,63 @@  sub parse_tag {
 	return %tag
 }
 
+# Contents of mailmap stored as a referance to a hash with keys in the format
+# of "name <email>" or "<email>", and values that are hashes containing a
+# replacement "name" and/or "email". If set (even if empty) the mailmap has
+# already been read.
+my $mailmap;
+
+sub read_mailmap {
+	my %mailmap = ();
+	open my $fd, '-|', quote_command(
+		git_cmd(), 'cat-file', 'blob', 'HEAD:.mailmap') . ' 2> /dev/null'
+		or die_error(500, 'Failed to read mailmap');
+	return \%mailmap if eof $fd;
+	foreach (split '\n', <$fd>) {
+		next if (/^#/);
+		if (/(.*)\s+ <([^<>]+)>\s+ ((?:.*\s+)? <[^<>]+>) (?:\s+\#)/x ||
+		    /(.*)\s+ <([^<>]+)>\s+ ((?:.*\s+)? <[^<>]+>)/x) {
+			# New Name <new@email> <old@email>
+			# New Name <new@email> Old Name <old@email>
+			$mailmap{$3} = ();
+			($mailmap{$3}{name} = $1) =~ s/^\s+|\s+$//g;
+			$mailmap{$3}{email} = $2;
+		} elsif (/(?: <([^<>]+)>\s+ | (.+)\s+ ) (<[^<>]+>) (?:\s+\#)/x ||
+		         /(?: <([^<>]+)>\s+ | (.+)\s+ ) (<[^<>]+>)/x) {
+			# New Name <old@email>
+			# <new@email> <old@email>
+			$mailmap{$3} = ();
+			if ($1) {
+				$mailmap{$3}{email} = $1;
+			} else {
+				($mailmap{$3}{name} = $2) =~ s/^\s+|\s+$//g;
+			}
+		}
+	}
+	return \%mailmap;
+}
+
+# Map author name and email based on mailmap. A more specific match
+# ("name <email>") is preferred to a less specific one ("<email>").
+sub map_author {
+	my $name = shift;
+	my $email = shift;
+
+	if (!$mailmap) {
+		$mailmap = read_mailmap;
+	}
+
+	if ($mailmap->{"$name <$email>"}) {
+		$name = $mailmap->{"$name <$email>"}{name} || $name;
+		$email = $mailmap->{"$name <$email>"}{email} || $email;
+	} elsif ($mailmap->{"<$email>"}) {
+		$name = $mailmap->{"<$email>"}{name} || $name;
+		$email = $mailmap->{"<$email>"}{email} || $email;
+	}
+
+	return ($name, $email);
+}
+
 sub parse_commit_text {
 	my ($commit_text, $withparents) = @_;
 	my @commit_lines = split '\n', $commit_text;
@@ -3517,8 +3580,13 @@  sub parse_commit_text {
 			$co{'author_epoch'} = $2;
 			$co{'author_tz'} = $3;
 			if ($co{'author'} =~ m/^([^<]+) <([^>]*)>/) {
-				$co{'author_name'}  = $1;
-				$co{'author_email'} = $2;
+				my ($name, $email) = @_;
+				if (gitweb_check_feature('mailmap')) {
+					($name, $email) = map_author($1, $2);
+					$co{'author'} = "$name <$email>";
+				}
+				$co{'author_name'}  = $name;
+				$co{'author_email'} = $email;
 			} else {
 				$co{'author_name'} = $co{'author'};
 			}
@@ -3527,8 +3595,13 @@  sub parse_commit_text {
 			$co{'committer_epoch'} = $2;
 			$co{'committer_tz'} = $3;
 			if ($co{'committer'} =~ m/^([^<]+) <([^>]*)>/) {
-				$co{'committer_name'}  = $1;
-				$co{'committer_email'} = $2;
+				my ($name, $email) = @_;
+				if (gitweb_check_feature('mailmap')) {
+					($name, $email) = map_author($1, $2);
+					$co{'committer'} = "$name <$email>";
+				}
+				$co{'committer_name'}  = $name;
+				$co{'committer_email'} = $email;
 			} else {
 				$co{'committer_name'} = $co{'committer'};
 			}