scripts/documentation-file-ref-check

   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
   7 use warnings;
   8 use strict;
   9 use Getopt::Long qw(:config no_auto_abbrev);
  10
  11 my $scriptname = $0;
  12 $scriptname =~ s,.*/([^/]+/),$1,;
  13
  14 # Parse arguments
  15 my $help = 0;
  16 my $fix = 0;
  17
  18 GetOptions(
  19         'fix' => \$fix,
  20         'h|help|usage' => \$help,
  21 );
  22
  23 if ($help != 0) {
  24     print "$scriptname [--help] [--fix-rst]\n";
  25     exit -1;
  26 }
  27
  28 # Step 1: find broken references
  29 print "Finding broken references. This may take a while...  " if ($fix);
  30
  31 my %broken_ref;
  32
  33 open IN, "git grep 'Documentation/'|"
  34      or die "Failed to run git grep";
  35 while (<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/(devicetree|scripts|Kconfig|Kbuild)/)) {
  68                                 $broken_ref{$ref}++;
  69                         }
  70                 } else {
  71                         print STDERR "$f: $fulref\n";
  72                 }
  73         }
  74 }
  75
  76 exit 0 if (!$fix);
  77
  78 # Step 2: Seek for file name alternatives
  79 print "Auto-fixing broken references. Please double-check the results\n";
  80
  81 foreach my $ref (keys %broken_ref) {
  82         my $new =$ref;
  83
  84         # get just the basename
  85         $new =~ s,.*/,,;
  86
  87         # Seek for the same name on another place, as it may have been moved
  88         my $f="";
  89
  90         $f = qx(find . -iname $new) if ($new);
  91
  92         # usual reason for breakage: file renamed to .rst
  93         if (!$f) {
  94                 $new =~ s/\.txt$/.rst/;
  95                 $f=qx(find . -iname $new) if ($new);
  96         }
  97
  98         my @find = split /\s+/, $f;
  99
 100         if (!$f) {
 101                 print STDERR "ERROR: Didn't find a replacement for $ref\n";
 102         } elsif (scalar(@find) > 1) {
 103                 print STDERR "WARNING: Won't auto-replace, as found multiple files close to $ref:\n";
 104                 foreach my $j (@find) {
 105                         $j =~ s,^./,,;
 106                         print STDERR "    $j\n";
 107                 }
 108         } else {
 109                 $f = $find[0];
 110                 $f =~ s,^./,,;
 111                 print "INFO: Replacing $ref to $f\n";
 112                 foreach my $j (qx(git grep -l $ref)) {
 113                         qx(sed "s\@$ref\@$f\@g" -i $j);
 114                 }
 115         }
 116 }