Merge branch 'es/contacts'

A helper to read from a set of format-patch output files or a range
of commits and find those who may have insights to the code that
the changes touch by running a series of "git blame" commands.

* es/contacts:
  contrib: contacts: add documentation
  contrib: contacts: add mailmap support
  contrib: contacts: interpret committish akin to format-patch
  contrib: contacts: add ability to parse from committish
  contrib: add git-contacts helper

2 files changed, 282 insertions, 0 deletions

diff --git a/contrib/contacts/git-contacts b/contrib/contacts/git-contacts
new file mode 100755
index 0000000000..d80f7d1b6e
--- /dev/null
+++ b/contrib/contacts/git-contacts
@@ -0,0 +1,188 @@
+#!/usr/bin/perl
+
+# List people who might be interested in a patch.  Useful as the argument to
+# git-send-email --cc-cmd option, and in other situations.
+#
+# Usage: git contacts <file | rev-list option> ...
+
+use strict;
+use warnings;
+use IPC::Open2;
+
+my $since = '5-years-ago';
+my $min_percent = 10;
+my $labels_rx = qr/Signed-off-by|Reviewed-by|Acked-by|Cc/i;
+my %seen;
+
+sub format_contact {
+	my ($name, $email) = @_;
+	return "$name <$email>";
+}
+
+sub parse_commit {
+	my ($commit, $data) = @_;
+	my $contacts = $commit->{contacts};
+	my $inbody = 0;
+	for (split(/^/m, $data)) {
+		if (not $inbody) {
+			if (/^author ([^<>]+) <(\S+)> .+$/) {
+				$contacts->{format_contact($1, $2)} = 1;
+			} elsif (/^$/) {
+				$inbody = 1;
+			}
+		} elsif (/^$labels_rx:\s+([^<>]+)\s+<(\S+?)>$/o) {
+			$contacts->{format_contact($1, $2)} = 1;
+		}
+	}
+}
+
+sub import_commits {
+	my ($commits) = @_;
+	return unless %$commits;
+	my $pid = open2 my $reader, my $writer, qw(git cat-file --batch);
+	for my $id (keys(%$commits)) {
+		print $writer "$id\n";
+		my $line = <$reader>;
+		if ($line =~ /^([0-9a-f]{40}) commit (\d+)/) {
+			my ($cid, $len) = ($1, $2);
+			die "expected $id but got $cid\n" unless $id eq $cid;
+			my $data;
+			# cat-file emits newline after data, so read len+1
+			read $reader, $data, $len + 1;
+			parse_commit($commits->{$id}, $data);
+		}
+	}
+	close $reader;
+	close $writer;
+	waitpid($pid, 0);
+	die "git-cat-file error: $?\n" if $?;
+}
+
+sub get_blame {
+	my ($commits, $source, $start, $len, $from) = @_;
+	$len = 1 unless defined($len);
+	return if $len == 0;
+	open my $f, '-|',
+		qw(git blame --porcelain -C), '-L', "$start,+$len",
+		'--since', $since, "$from^", '--', $source or die;
+	while (<$f>) {
+		if (/^([0-9a-f]{40}) \d+ \d+ \d+$/) {
+			my $id = $1;
+			$commits->{$id} = { id => $id, contacts => {} }
+				unless $seen{$id};
+			$seen{$id} = 1;
+		}
+	}
+	close $f;
+}
+
+sub scan_patches {
+	my ($commits, $id, $f) = @_;
+	my $source;
+	while (<$f>) {
+		if (/^From ([0-9a-f]{40}) Mon Sep 17 00:00:00 2001$/) {
+			$id = $1;
+			$seen{$id} = 1;
+		}
+		next unless $id;
+		if (m{^--- (?:a/(.+)|/dev/null)$}) {
+			$source = $1;
+		} elsif (/^--- /) {
+			die "Cannot parse hunk source: $_\n";
+		} elsif (/^@@ -(\d+)(?:,(\d+))?/ && $source) {
+			get_blame($commits, $source, $1, $2, $id);
+		}
+	}
+}
+
+sub scan_patch_file {
+	my ($commits, $file) = @_;
+	open my $f, '<', $file or die "read failure: $file: $!\n";
+	scan_patches($commits, undef, $f);
+	close $f;
+}
+
+sub parse_rev_args {
+	my @args = @_;
+	open my $f, '-|',
+		qw(git rev-parse --revs-only --default HEAD --symbolic), @args
+		or die;
+	my @revs;
+	while (<$f>) {
+		chomp;
+		push @revs, $_;
+	}
+	close $f;
+	return @revs if scalar(@revs) != 1;
+	return "^$revs[0]", 'HEAD' unless $revs[0] =~ /^-/;
+	return $revs[0], 'HEAD';
+}
+
+sub scan_rev_args {
+	my ($commits, $args) = @_;
+	my @revs = parse_rev_args(@$args);
+	open my $f, '-|', qw(git rev-list --reverse), @revs or die;
+	while (<$f>) {
+		chomp;
+		my $id = $_;
+		$seen{$id} = 1;
+		open my $g, '-|', qw(git show -C --oneline), $id or die;
+		scan_patches($commits, $id, $g);
+		close $g;
+	}
+	close $f;
+}
+
+sub mailmap_contacts {
+	my ($contacts) = @_;
+	my %mapped;
+	my $pid = open2 my $reader, my $writer, qw(git check-mailmap --stdin);
+	for my $contact (keys(%$contacts)) {
+		print $writer "$contact\n";
+		my $canonical = <$reader>;
+		chomp $canonical;
+		$mapped{$canonical} += $contacts->{$contact};
+	}
+	close $reader;
+	close $writer;
+	waitpid($pid, 0);
+	die "git-check-mailmap error: $?\n" if $?;
+	return \%mapped;
+}
+
+if (!@ARGV) {
+	die "No input revisions or patch files\n";
+}
+
+my (@files, @rev_args);
+for (@ARGV) {
+	if (-e) {
+		push @files, $_;
+	} else {
+		push @rev_args, $_;
+	}
+}
+
+my %commits;
+for (@files) {
+	scan_patch_file(\%commits, $_);
+}
+if (@rev_args) {
+	scan_rev_args(\%commits, \@rev_args)
+}
+import_commits(\%commits);
+
+my $contacts = {};
+for my $commit (values %commits) {
+	for my $contact (keys %{$commit->{contacts}}) {
+		$contacts->{$contact}++;
+	}
+}
+$contacts = mailmap_contacts($contacts);
+
+my $ncommits = scalar(keys %commits);
+for my $contact (keys %$contacts) {
+	my $percent = $contacts->{$contact} * 100 / $ncommits;
+	next if $percent < $min_percent;
+	print "$contact\n";
+}
diff --git a/contrib/contacts/git-contacts.txt b/contrib/contacts/git-contacts.txt
new file mode 100644
index 0000000000..dd914d1261
--- /dev/null
+++ b/contrib/contacts/git-contacts.txt
@@ -0,0 +1,94 @@
+git-contacts(1)
+===============
+
+NAME
+----
+git-contacts - List people who might be interested in a set of changes
+
+
+SYNOPSIS
+--------
+[verse]
+'git contacts' (<patch>|<range>|<rev>)...
+
+
+DESCRIPTION
+-----------
+
+Given a set of changes, specified as patch files or revisions, determine people
+who might be interested in those changes.  This is done by consulting the
+history of each patch or revision hunk to find people mentioned by commits
+which touched the lines of files under consideration.
+
+Input consists of one or more patch files or revision arguments.  A revision
+argument can be a range or a single `<rev>` which is interpreted as
+`<rev>..HEAD`, thus the same revision arguments are accepted as for
+linkgit:git-format-patch[1]. Patch files and revision arguments can be combined
+in the same invocation.
+
+This command can be useful for determining the list of people with whom to
+discuss proposed changes, or for finding the list of recipients to Cc: when
+submitting a patch series via `git send-email`. For the latter case, `git
+contacts` can be used as the argument to `git send-email`'s `--cc-cmd` option.
+
+
+DISCUSSION
+----------
+
+`git blame` is invoked for each hunk in a patch file or revision.  For each
+commit mentioned by `git blame`, the commit message is consulted for people who
+authored, reviewed, signed, acknowledged, or were Cc:'d.  Once the list of
+participants is known, each person's relevance is computed by considering how
+many commits mentioned that person compared with the total number of commits
+under consideration.  The final output consists only of participants who exceed
+a minimum threshold of participation.
+
+
+OUTPUT
+------
+
+For each person of interest, a single line is output, terminated by a newline.
+If the person's name is known, ``Name $$<user@host>$$'' is printed; otherwise
+only ``$$<user@host>$$'' is printed.
+
+
+EXAMPLES
+--------
+
+* Consult patch files:
++
+------------
+$ git contacts feature/*.patch
+------------
+
+* Revision range:
++
+------------
+$ git contacts R1..R2
+------------
+
+* From a single revision to `HEAD`:
++
+------------
+$ git contacts origin
+------------
+
+* Helper for `git send-email`:
++
+------------
+$ git send-email --cc-cmd='git contacts' feature/*.patch
+------------
+
+
+LIMITATIONS
+-----------
+
+Several conditions controlling a person's significance are currently
+hard-coded, such as minimum participation level (10%), blame date-limiting (5
+years), and `-C` level for detecting moved and copied lines (a single `-C`). In
+the future, these conditions may become configurable.
+
+
+GIT
+---
+Part of the linkgit:git[1] suite