linux-kernel - [PATCH] checkpatch: Add optional --codespell dictionary to find more typos

lists.openwall.net		lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC
Open Source and information security mailing list archives

Hash Suite: Windows password security audit tool. GUI, reports in PDF.

[<prev] [next>] [thread-next>] [day] [month] [year] [list]

Message-ID: <1425581555.31859.27.camel@perches.com>
Date:	Thu, 05 Mar 2015 10:52:35 -0800
From:	Joe Perches <joe@...ches.com>
To:	Andrew Morton <akpm@...ux-foundation.org>
Cc:	Andy Whitcroft <apw@...onical.com>,
	Kees Cook <keescook@...omium.org>,
	Masanari Iida <standby24x7@...il.com>,
	Lucas De Marchi <lucas.de.marchi@...il.com>,
	codespell@...glegroups.com, LKML <linux-kernel@...r.kernel.org>
Subject: [PATCH] checkpatch: Add optional --codespell dictionary to find
 more typos

If a codespell dictionary exists, use it if desired.
default is off, maybe it could be turned on later.

codespell's dictionary format allows multiple possible corrections,
ignore that for now and only use the first suggestion.

Also add \b to spelling test so that consecutive misspelled words
are found properly.

Signed-off-by: Joe Perches <joe@...ches.com>
---
 scripts/checkpatch.pl | 38 ++++++++++++++++++++++++++++++++++----
 1 file changed, 34 insertions(+), 4 deletions(-)

diff --git a/scripts/checkpatch.pl b/scripts/checkpatch.pl
index c061a63..6b79beb 100755
--- a/scripts/checkpatch.pl
+++ b/scripts/checkpatch.pl
@@ -47,6 +47,8 @@ my $ignore_perl_version = 0;
 my $minimum_perl_version = 5.10.0;
 my $min_conf_desc_length = 4;
 my $spelling_file = "$D/spelling.txt";
+my $codespell = 0;
+my $codespellfile = "/usr/local/share/codespell/dictionary.txt";
 
 sub help {
 	my ($exitcode) = @_;
@@ -88,6 +90,9 @@ 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.
@@ -146,6 +151,8 @@ 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);
@@ -449,7 +456,6 @@ my $misspellings;
 my %spelling_fix;
 
 if (open(my $spelling, '<', $spelling_file)) {
-	my @spelling_list;
 	while (<$spelling>) {
 		my $line = $_;
 
@@ -461,15 +467,39 @@ if (open(my $spelling, '<', $spelling_file)) {
 
 		my ($suspect, $fix) = split(/\|\|/, $line);
 
-		push(@spelling_list, $suspect);
 		$spelling_fix{$suspect} = $fix;
 	}
 	close($spelling);
-	$misspellings = join("|", @spelling_list);
 } else {
 	warn "No typos will be found - file '$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 $all = "(?x:  \n" . join("|\n  ", @typeList) . "\n)";
@@ -2305,7 +2335,7 @@ sub process {
 # Check for various typo / spelling mistakes
 		if (defined($misspellings) &&
 		    ($in_commit_log || $line =~ /^(?:\+|Subject:)/i)) {
-			while ($rawline =~ /(?:^|[^a-z@])($misspellings)(?:$|[^a-z@])/gi) {
+			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]/);


--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@...r.kernel.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Please read the FAQ at  http://www.tux.org/lkml/