checkpatch: look for common misspellings

Check for misspellings, based on Debian's lintian list.  Several false
positives were removed, and several additional words added that were
common in the kernel:

	backword backwords
	invalide valide
	recieves
	singed unsinged

While going back and fixing existing spelling mistakes isn't a high
priority, it'd be nice to try to catch them before they hit the tree.

In the 13830 commits between 3.15 and 3.16, the script would have noticed
560 spelling mistakes. The top 25 are shown here:

$ git log --pretty=oneline v3.15..v3.16 | wc -l
13830
$ git log --format='%H' v3.15..v3.16 | \
   while read commit ; do \
     echo "commit $commit" ; \
     git log --format=email --stat -p -1 $commit | \
       ./scripts/checkpatch.pl --types=typo_spelling --no-summary - ; \
   done | tee spell_v3.15..v3.16.txt | grep "may be misspelled" | \
   awk '{print $2}' | tr A-Z a-z | sort | uniq -c | sort -rn
     21 'seperate'
     17 'endianess'
     15 'sucess'
     13 'noticable'
     11 'occured'
     11 'accomodate'
     10 'interrup'
      9 'prefered'
      8 'unecessary'
      8 'explicitely'
      7 'supress'
      7 'overriden'
      7 'immediatly'
      7 'funtion'
      7 'defult'
      7 'childs'
      6 'succesful'
      6 'splitted'
      6 'specifc'
      6 'reseting'
      6 'recieve'
      6 'changable'
      5 'tmis'
      5 'singed'
      5 'preceeding'

Thanks to Joe Perches for rewrites, suggestions, additional misspelling
entries, and testing.

Signed-off-by: Kees Cook <keescook@chromium.org>
Acked-by: Joe Perches <joe@perches.com>
Cc: Masanari Iida <standby24x7@gmail.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

1 files changed, 43 insertions, 1 deletions

diff --git a/scripts/checkpatch.pl b/scripts/checkpatch.pl
index 7a360a8..74bba23 100755
--- a/scripts/checkpatch.pl
+++ b/scripts/checkpatch.pl
@@ -9,7 +9,8 @@ use strict;
 use POSIX;
 
 my $P = $0;
-$P =~ s@.*/@@g;
+$P =~ s@(.*)/@@g;
+my $D = $1;
 
 my $V = '0.32';
 
@@ -44,6 +45,7 @@ my $max_line_length = 80;
 my $ignore_perl_version = 0;
 my $minimum_perl_version = 5.10.0;
 my $min_conf_desc_length = 4;
+my $spelling_file = "$D/spelling.txt";
 
 sub help {
 	my ($exitcode) = @_;
@@ -434,6 +436,29 @@ 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_list;
+my %spelling_fix;
+open(my $spelling, '<', $spelling_file)
+    or die "$P: Can't open $spelling_file for reading: $!\n";
+while (<$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);
+
+	push(@spelling_list, $suspect);
+	$spelling_fix{$suspect} = $fix;
+}
+close($spelling);
+$misspellings = join("|", @spelling_list);
+
 sub build_types {
 	my $mods = "(?x:  \n" . join("|\n  ", @modifierList) . "\n)";
 	my $all = "(?x:  \n" . join("|\n  ", @typeList) . "\n)";
@@ -2220,6 +2245,23 @@ sub process {
 			    "8-bit UTF-8 used in possible commit log\n" . $herecurr);
 		}
 
+# Check for various typo / spelling mistakes
+		if ($in_commit_log || $line =~ /^\+/) {
+			while ($rawline =~ /(?:^|[^a-z@])($misspellings)(?:$|[^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 =~ /^-/);