ci: validate "linkgit:" in documentation

It is easy to add incorrect "linkgit:<page>[<section>]" references
to our documentation suite.  Catch these common classes of errors:

 * Referring to Documentation/<page>.txt that does not exist.

 * Referring to a <page> outside the Git suite.  In general, <page>
   must begin with "git".

 * Listing the manual <section> incorrectly.  The first line of the
   Documentation/<page>.txt must end with "(<section>)".

with a new script "ci/lint-gitlink", and drive it from "make check-docs".

Signed-off-by: Junio C Hamano <gitster@pobox.com>

1 files changed, 71 insertions, 0 deletions

diff --git a/Documentation/lint-gitlink.perl b/Documentation/lint-gitlink.perl
new file mode 100755
index 0000000..476cc30
--- /dev/null
+++ b/Documentation/lint-gitlink.perl
@@ -0,0 +1,71 @@
+#!/usr/bin/perl
+
+use File::Find;
+use Getopt::Long;
+
+my $basedir = ".";
+GetOptions("basedir=s" => \$basedir)
+	or die("Cannot parse command line arguments\n");
+
+my $found_errors = 0;
+
+sub report {
+	my ($where, $what, $error) = @_;
+	print "$where: $error: $what\n";
+	$found_errors = 1;
+}
+
+sub grab_section {
+	my ($page) = @_;
+	open my $fh, "<", "$basedir/$page.txt";
+	my $firstline = <$fh>;
+	chomp $firstline;
+	close $fh;
+	my ($section) = ($firstline =~ /.*\((\d)\)$/);
+	return $section;
+}
+
+sub lint {
+	my ($file) = @_;
+	open my $fh, "<", $file
+		or return;
+	while (<$fh>) {
+		my $where = "$file:$.";
+		while (s/linkgit:((.*?)\[(\d)\])//) {
+			my ($target, $page, $section) = ($1, $2, $3);
+
+			# De-AsciiDoc
+			$page =~ s/{litdd}/--/g;
+
+			if ($page !~ /^git/) {
+				report($where, $target, "nongit link");
+				next;
+			}
+			if (! -f "$basedir/$page.txt") {
+				report($where, $target, "no such source");
+				next;
+			}
+			$real_section = grab_section($page);
+			if ($real_section != $section) {
+				report($where, $target,
+					"wrong section (should be $real_section)");
+				next;
+			}
+		}
+	}
+	close $fh;
+}
+
+sub lint_it {
+	lint($File::Find::name) if -f && /\.txt$/;
+}
+
+if (!@ARGV) {
+	find({ wanted => \&lint_it, no_chdir => 1 }, $basedir);
+} else {
+	for (@ARGV) {
+		lint($_);
+	}
+}
+
+exit $found_errors;