diff options
author | Joe Perches <joe@perches.com> | 2011-11-01 01:13:12 +0100 |
---|---|---|
committer | Linus Torvalds <torvalds@linux-foundation.org> | 2011-11-01 01:30:57 +0100 |
commit | 15662b3e8644905032c2e26808401a487d4e90c1 (patch) | |
tree | 0eae1a68779bd314459a2bff55c43e266329015d /scripts | |
parent | kernel.h/checkpatch: mark strict_strto<foo> and simple_strto<foo> as obsolete (diff) | |
download | linux-15662b3e8644905032c2e26808401a487d4e90c1.tar.xz linux-15662b3e8644905032c2e26808401a487d4e90c1.zip |
checkpatch: add a --strict check for utf-8 in commit logs
Some find using utf-8 in commit logs inappropriate.
Some patch commit logs contain unintended utf-8 characters when doing
things like copy/pasting compilation output.
Look for the start of any commit log by skipping initial lines that look
like email headers and "From: " lines.
Stop looking for utf-8 at the first signature line.
Signed-off-by: Joe Perches <joe@perches.com>
Suggested-by: Andrew Morton <akpm@linux-foundation.org>
Cc: Andy Whitcroft <apw@shadowen.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Diffstat (limited to 'scripts')
-rwxr-xr-x | scripts/checkpatch.pl | 30 |
1 files changed, 26 insertions, 4 deletions
diff --git a/scripts/checkpatch.pl b/scripts/checkpatch.pl index 5ba679c8cde6..5e93342d22f9 100755 --- a/scripts/checkpatch.pl +++ b/scripts/checkpatch.pl @@ -240,9 +240,8 @@ our $NonptrType; our $Type; our $Declare; -our $UTF8 = qr { - [\x09\x0A\x0D\x20-\x7E] # ASCII - | [\xC2-\xDF][\x80-\xBF] # non-overlong 2-byte +our $NON_ASCII_UTF8 = qr{ + [\xC2-\xDF][\x80-\xBF] # non-overlong 2-byte | \xE0[\xA0-\xBF][\x80-\xBF] # excluding overlongs | [\xE1-\xEC\xEE\xEF][\x80-\xBF]{2} # straight 3-byte | \xED[\x80-\x9F][\x80-\xBF] # excluding surrogates @@ -251,6 +250,11 @@ our $UTF8 = qr { | \xF4[\x80-\x8F][\x80-\xBF]{2} # plane 16 }x; +our $UTF8 = qr{ + [\x09\x0A\x0D\x20-\x7E] # ASCII + | $NON_ASCII_UTF8 +}x; + our $typeTypedefs = qr{(?x: (?:__)?(?:u|s|be|le)(?:8|16|32|64)| atomic_t @@ -1330,6 +1334,9 @@ sub process { my $signoff = 0; my $is_patch = 0; + my $in_header_lines = 1; + my $in_commit_log = 0; #Scanning lines before patch + our @report = (); our $cnt_lines = 0; our $cnt_error = 0; @@ -1497,7 +1504,6 @@ sub process { if ($line =~ /^diff --git.*?(\S+)$/) { $realfile = $1; $realfile =~ s@^([^/]*)/@@; - } elsif ($line =~ /^\+\+\+\s+(\S+)/) { $realfile = $1; $realfile =~ s@^([^/]*)/@@; @@ -1536,6 +1542,7 @@ sub process { # Check the patch for a signoff: if ($line =~ /^\s*signed-off-by:/i) { $signoff++; + $in_commit_log = 0; } # Check signature styles @@ -1613,6 +1620,21 @@ sub process { "Invalid UTF-8, patch and commit message should be encoded in UTF-8\n" . $hereptr); } +# Check if it's the start of a commit log +# (not a header line and we haven't seen the patch filename) + if ($in_header_lines && $realfile =~ /^$/ && + $rawline !~ /^(commit\b|from\b|\w+:).+$/i) { + $in_header_lines = 0; + $in_commit_log = 1; + } + +# Still not yet in a patch, check for any UTF-8 + if ($in_commit_log && $realfile =~ /^$/ && + $rawline =~ /$NON_ASCII_UTF8/) { + CHK("UTF8_BEFORE_PATCH", + "8-bit UTF-8 used in possible commit log\n" . $herecurr); + } + # ignore non-hunk lines and lines being removed next if (!$hunk_line || $line =~ /^-/); |