checkpatch: Port spelling to checkpatch

Pick commit 66b47b4a9dad0 checkpatch: look for common misspellings
from the Linux kernel for spelling check from Kees Cook

In addition pulled in additional changes
commit ebfd7d6237531 checkpatch: add optional --codespell dictionary to find more typos
from the Linux kernel for codespell from Joe Perches

commit f1a63678554f8 checkpatch: remove local from codespell path
from the Linux kernel for dictionary path from Maxim Uvarov

Signed-off-by: Dan Murphy <dmurphy@ti.com>
Reviewed-by: Tom Rini <trini@konsulko.com>

1 files changed, 81 insertions, 0 deletions

diff --git a/scripts/checkpatch.pl b/scripts/checkpatch.pl
index 84f57566fd..3afc870f0f 100755
--- a/scripts/checkpatch.pl
+++ b/scripts/checkpatch.pl
@@ -7,9 +7,12 @@
 
 use strict;
 use POSIX;
+use File::Basename;
+use Cwd 'abs_path';
 
 my $P = $0;
 $P =~ s@.*/@@g;
+my $D = dirname(abs_path($P));
 
 my $V = '0.32';
 
@@ -42,6 +45,9 @@ my $configuration_file = ".checkpatch.conf";
 my $max_line_length = 80;
 my $ignore_perl_version = 0;
 my $minimum_perl_version = 5.10.0;
+my $spelling_file = "$D/spelling.txt";
+my $codespell = 0;
+my $codespellfile = "/usr/share/codespell/dictionary.txt";
 
 sub help {
 	my ($exitcode) = @_;
@@ -82,6 +88,9 @@ Options:
                              file.  It's your fault if there's no backup or git
   --ignore-perl-version      override checking of perl version.  expect
                              runtime errors.
+  --codespell                Use the codespell dictionary for spelling/typos
+                             (default:/usr/local/share/codespell/dictionary.txt)
+  --codespellfile            Use this codespell dictionary
   -h, --help, --version      display this help and exit
 
 When FILE is - read standard input.
@@ -139,6 +148,8 @@ GetOptions(
 	'ignore-perl-version!' => \$ignore_perl_version,
 	'debug=s'	=> \%debug,
 	'test-only=s'	=> \$tst_only,
+	'codespell!'    => \$codespell,
+	'codespellfile=s' => \$codespellfile,
 	'h|help'	=> \$help,
 	'version'	=> \$help
 ) or help(1);
@@ -387,6 +398,56 @@ our $allowed_asm_includes = qr{(?x:
 )};
 # memory.h: ARM has a custom one
 
+# Load common spelling mistakes and build regular expression list.
+my $misspellings;
+my %spelling_fix;
+
+if (open(my $spelling, '<', $spelling_file)) {
+	while (<$spelling>) {
+		my $line = $_;
+
+		$line =~ s/\s*\n?$//g;
+		$line =~ s/^\s*//g;
+
+		next if ($line =~ m/^\s*#/);
+		next if ($line =~ m/^\s*$/);
+
+		my ($suspect, $fix) = split(/\|\|/, $line);
+
+		$spelling_fix{$suspect} = $fix;
+	}
+	close($spelling);
+} else {
+	warn "No typos will be found - file '$spelling_file': $!\n";
+}
+
+if ($codespell) {
+	if (open(my $spelling, '<', $codespellfile)) {
+		while (<$spelling>) {
+			my $line = $_;
+
+			$line =~ s/\s*\n?$//g;
+			$line =~ s/^\s*//g;
+
+			next if ($line =~ m/^\s*#/);
+			next if ($line =~ m/^\s*$/);
+			next if ($line =~ m/, disabled/i);
+
+			$line =~ s/,.*$//;
+
+			my ($suspect, $fix) = split(/->/, $line);
+
+			$spelling_fix{$suspect} = $fix;
+		}
+		close($spelling);
+	} else {
+		warn "No codespell typos will be found - file '$codespellfile': $!\n";
+	}
+}
+
+$misspellings = join("|", sort keys %spelling_fix) if keys %spelling_fix;
+
+
 sub build_types {
 	my $mods = "(?x:  \n" . join("|\n  ", @modifierList) . "\n)";
 	my $all = "(?x:  \n" . join("|\n  ", @typeList) . "\n)";
@@ -528,6 +589,8 @@ my @rawlines = ();
 my @lines = ();
 my @fixed = ();
 my $vname;
+my $fixlinenr = -1;
+
 for my $filename (@ARGV) {
 	my $FILE;
 	if ($file) {
@@ -1950,6 +2013,24 @@ sub process {
 			    "8-bit UTF-8 used in possible commit log\n" . $herecurr);
 		}
 
+# Check for various typo / spelling mistakes
+		if (defined($misspellings) &&
+		    ($in_commit_log || $line =~ /^(?:\+|Subject:)/i)) {
+			while ($rawline =~ /(?:^|[^a-z@])($misspellings)(?:\b|$|[^a-z@])/gi) {
+				my $typo = $1;
+				my $typo_fix = $spelling_fix{lc($typo)};
+				$typo_fix = ucfirst($typo_fix) if ($typo =~ /^[A-Z]/);
+				$typo_fix = uc($typo_fix) if ($typo =~ /^[A-Z]+$/);
+				my $msg_type = \&WARN;
+				$msg_type = \&CHK if ($file);
+				if (&{$msg_type}("TYPO_SPELLING",
+						 "'$typo' may be misspelled - perhaps '$typo_fix'?\n" . $herecurr) &&
+				    $fix) {
+					$fixed[$fixlinenr] =~ s/(^|[^A-Za-z@])($typo)($|[^A-Za-z@])/$1$typo_fix$3/;
+				}
+			}
+		}
+
 # ignore non-hunk lines and lines being removed
 		next if (!$hunk_line || $line =~ /^-/);