xref: /linux/scripts/documentation-file-ref-check (revision e1f319fe4d537da79691f1a1da7a20147de33047) 
1#!/usr/bin/env perl
2# SPDX-License-Identifier: GPL-2.0
3#
4# Treewide grep for references to files under Documentation, and report
5# non-existing files in stderr.
6
7use warnings;
8use strict;
9use Getopt::Long qw(:config no_auto_abbrev);
10
11my $scriptname = $0;
12$scriptname =~ s,.*/([^/]+/),$1,;
13
14# Parse arguments
15my $help = 0;
16my $fix = 0;
17
18GetOptions(
19	'fix' => \$fix,
20	'h|help|usage' => \$help,
21);
22
23if ($help != 0) {
24    print "$scriptname [--help] [--fix]\n";
25    exit -1;
26}
27
28# Step 1: find broken references
29print "Finding broken references. This may take a while...  " if ($fix);
30
31my %broken_ref;
32
33open IN, "git grep 'Documentation/'|"
34     or die "Failed to run git grep";
35while (<IN>) {
36	next if (!m/^([^:]+):(.*)/);
37
38	my $f = $1;
39	my $ln = $2;
40
41	# Makefiles contain nasty expressions to parse docs
42	next if ($f =~ m/Makefile/);
43	# Skip this script
44	next if ($f eq $scriptname);
45
46	if ($ln =~ m,\b(\S*)(Documentation/[A-Za-z0-9\_\.\,\~/\*\[\]\?+-]*),) {
47		my $prefix = $1;
48		my $ref = $2;
49		my $base = $2;
50
51		$ref =~ s/[\,\.]+$//;
52
53		my $fulref = "$prefix$ref";
54
55		$fulref =~ s/^(\<file|ref)://;
56		$fulref =~ s/^[\'\`]+//;
57		$fulref =~ s,^\$\(.*\)/,,;
58		$base =~ s,.*/,,;
59
60		# Remove URL false-positives
61		next if ($fulref =~ m/^http/);
62
63		# Check if exists, evaluating wildcards
64		next if (grep -e, glob("$ref $fulref"));
65
66		if ($fix) {
67			if (!($ref =~ m/(scripts|Kconfig|Kbuild)/)) {
68				$broken_ref{$ref}++;
69			}
70		} else {
71			print STDERR "$f: $fulref\n";
72		}
73	}
74}
75
76exit 0 if (!$fix);
77
78# Step 2: Seek for file name alternatives
79print "Auto-fixing broken references. Please double-check the results\n";
80
81foreach my $ref (keys %broken_ref) {
82	my $new =$ref;
83
84	# get just the basename
85	$new =~ s,.*/,,;
86
87	my $f="";
88
89	# usual reason for breakage: DT file moved around
90	if ($ref =~ /devicetree/) {
91		my $search = $new;
92		$search =~ s,^.*/,,;
93		$f = qx(find Documentation/devicetree/ -iname "*$search*") if ($search);
94		if (!$f) {
95			# Manufacturer name may have changed
96			$search =~ s/^.*,//;
97			$f = qx(find Documentation/devicetree/ -iname "*$search*") if ($search);
98		}
99	}
100
101	# usual reason for breakage: file renamed to .rst
102	if (!$f) {
103		$new =~ s/\.txt$/.rst/;
104		$f=qx(find . -iname $new) if ($new);
105	}
106
107	# usual reason for breakage: use dash or underline
108	if (!$f) {
109		$new =~ s/[-_]/[-_]/g;
110		$f=qx(find . -iname $new) if ($new);
111	}
112
113	# Wild guess: seek for the same name on another place
114	if (!$f) {
115		$f = qx(find . -iname $new) if ($new);
116	}
117
118	my @find = split /\s+/, $f;
119
120	if (!$f) {
121		print STDERR "ERROR: Didn't find a replacement for $ref\n";
122	} elsif (scalar(@find) > 1) {
123		print STDERR "WARNING: Won't auto-replace, as found multiple files close to $ref:\n";
124		foreach my $j (@find) {
125			$j =~ s,^./,,;
126			print STDERR "    $j\n";
127		}
128	} else {
129		$f = $find[0];
130		$f =~ s,^./,,;
131		print "INFO: Replacing $ref to $f\n";
132		foreach my $j (qx(git grep -l $ref)) {
133			qx(sed "s\@$ref\@$f\@g" -i $j);
134		}
135	}
136}
137