From 1db81a682a2f2a664489c4e94f3b945f70a43a13 Mon Sep 17 00:00:00 2001 From: Dwaipayan Ray Date: Tue, 15 Dec 2020 20:44:20 -0800 Subject: checkpatch: add new exception to repeated word check Recently, commit 4f6ad8aa1eac ("checkpatch: move repeated word test") moved the repeated word test to check for more file types. But after this, if checkpatch.pl is run on MAINTAINERS, it generates several new warnings of the type: WARNING: Possible repeated word: 'git' For example: WARNING: Possible repeated word: 'git' +T: git git://git.kernel.org/pub/scm/linux/kernel/git/rw/uml.git So, the pattern "git git://..." is a false positive in this case. There are several other combinations which may produce a wrong warning message, such as "@size size", ":Begin begin", etc. Extend repeated word check to compare the characters before and after the word matches. If there is a non whitespace character before the first word or a non whitespace character excluding punctuation characters after the second word, then the check is skipped and the warning is avoided. Also add case insensitive word matching to the repeated word check. Link: https://lore.kernel.org/linux-kernel-mentees/81b6a0bb2c7b9256361573f7a13201ebcd4876f1.camel@perches.com/ Link: https://lkml.kernel.org/r/20201017162732.152351-1-dwaipayanray1@gmail.com Signed-off-by: Dwaipayan Ray Suggested-by: Joe Perches Suggested-by: Lukas Bulwahn Acked-by: Joe Perches Cc: Aditya Srivastava Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- scripts/checkpatch.pl | 15 +++++++++++++-- 1 file changed, 13 insertions(+), 2 deletions(-) (limited to 'scripts') diff --git a/scripts/checkpatch.pl b/scripts/checkpatch.pl index fab38b493cef..7e505688257a 100755 --- a/scripts/checkpatch.pl +++ b/scripts/checkpatch.pl @@ -3050,19 +3050,30 @@ sub process { # check for repeated words separated by a single space if ($rawline =~ /^\+/ || $in_commit_log) { + pos($rawline) = 1 if (!$in_commit_log); while ($rawline =~ /\b($word_pattern) (?=($word_pattern))/g) { my $first = $1; my $second = $2; - + my $start_pos = $-[1]; + my $end_pos = $+[2]; if ($first =~ /(?:struct|union|enum)/) { pos($rawline) += length($first) + length($second) + 1; next; } - next if ($first ne $second); + next if (lc($first) ne lc($second)); next if ($first eq 'long'); + # check for character before and after the word matches + my $start_char = ''; + my $end_char = ''; + $start_char = substr($rawline, $start_pos - 1, 1) if ($start_pos > ($in_commit_log ? 0 : 1)); + $end_char = substr($rawline, $end_pos, 1) if ($end_pos < length($rawline)); + + next if ($start_char =~ /^\S$/); + next if (index(" \t.,;?!", $end_char) == -1); + if (WARN("REPEATED_WORD", "Possible repeated word: '$first'\n" . $herecurr) && $fix) { -- cgit v1.2.3