Re: [PATCH] checkpatch: Avoid missing typo suggestions

[Joe Perches <joe@perches.com>]

On Wed, 2020-06-03 at 16:19 -0700, Kees Cook wrote:
> My codespell dictionary has a lot of capitalized words. For example:
> 
> MSDOS->MS-DOS
> 
> Since checkpatch uses case-insensitive matching, I get an undefined
> variable warning and then empty suggestions for things like this:
> 
> Use of uninitialized value $typo_fix in concatenation (.) or string at ./scripts/checkpatch.pl line 2958.
> 
> WARNING: 'msdos' may be misspelled - perhaps ''?
> +       struct msdos_dir_entry *de;
> 
> This fixes the matcher to avoid the warning, but it's still a rather
> silly suggestion:
> 
> WARNING: 'msdos' may be misspelled - perhaps 'MS-DOS'?
> +       struct msdos_dir_entry *de;
> 
> So I'm not really sure what to do with this ... filter out bad
> suggestions instead?

Hey Kees.

Maybe this?

btw: My codespell dictionary file moved to
/usr/lib/python3/dist-packages/codespell_lib/data/dictionary.txt

and I had to use --codespell --codespellfile=(above) so
maybe there should be multiple lookups for this file
like the array below.

Are there other standard codespell dictionary locations?
---
 scripts/checkpatch.pl | 31 ++++++++++++++++++++++++++-----
 1 file changed, 26 insertions(+), 5 deletions(-)

diff --git a/scripts/checkpatch.pl b/scripts/checkpatch.pl
index 5f00df2c3f59..52aa0dd53d80 100755
--- a/scripts/checkpatch.pl
+++ b/scripts/checkpatch.pl
@@ -59,7 +59,7 @@ 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/share/codespell/dictionary.txt";
+my $codespellfile;
 my $conststructsfile = "$D/const_structs.checkpatch";
 my $typedefsfile = "";
 my $color = "auto";
@@ -716,7 +716,20 @@ if (open(my $spelling, '<', $spelling_file)) {
 }
 
 if ($codespell) {
-	if (open(my $spelling, '<', $codespellfile)) {
+	if (!defined($codespellfile)) {
+		my @csfiles = ("/usr/share/codespell/dictionary.txt",
+			       "/usr/lib/python3/dist-packages/codespell_lib/data/dictionary.txt");
+		foreach my $csfile (@csfiles) {
+			if (-f $csfile) {
+				$codespellfile = $csfile;
+				last;
+			}
+		}
+	}
+
+	if (!defined($codespellfile)) {
+		warn "No codespell typos will be found - codespell dictionary not found\n";
+	} elsif (open(my $spelling, '<', $codespellfile)) {
 		while (<$spelling>) {
 			my $line = $_;
 
@@ -2963,13 +2976,21 @@ sub process {
 			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 ($typo =~ /^[A-Z]+$/);
+				$typo_fix = $spelling_fix{$typo} if (!defined($typo_fix));
+				$typo_fix = $spelling_fix{uc($typo)} if (!defined($typo_fix));
+				$typo_fix = 'unknown typo fix' if (!defined($typo_fix));
+				if ($typo =~ /^[A-Z]+$/) {
+					$typo_fix = uc($typo_fix);
+				} elsif ($typo =~ /^[A-Z]/) {
+					$typo_fix = ucfirst($typo_fix);
+				}
+
 				my $msg_level = \&WARN;
 				$msg_level = \&CHK if ($file);
 				if (&{$msg_level}("TYPO_SPELLING",
 						  "'$typo' may be misspelled - perhaps '$typo_fix'?\n" . $herecurr) &&
-				    $fix) {
+				    $fix &&
+				    $typo_fix ne 'unknown typo fix') {
 					$fixed[$fixlinenr] =~ s/(^|[^A-Za-z@])($typo)($|[^A-Za-z@])/$1$typo_fix$3/;
 				}
 			}