Received-SPF: pass (google.com: domain of linux-kernel-owner@vger.kernel.org designates 23.128.96.18 as permitted sender) client-ip=23.128.96.18;
Message-ID: <cda9b566ad67976e1acd62b053de50ee44a57250.camel@perches.com>
Subject: [PATCH] checkpatch: Add test for repeated words
From:   Joe Perches <joe@perches.com>
To:     Andrew Morton <akpm@linux-foundation.org>,
        Andy Whitcroft <apw@canonical.com>
Cc:     Randy Dunlap <rdunlap@infradead.org>,
        LKML <linux-kernel@vger.kernel.org>
Date:   Mon, 27 Jul 2020 00:33:42 -0700
In-Reply-To: <16aa5f86f2f899a9156305ead4b7042449278eea.camel@perches.com>
References: <20200726162902.Horde.TCqHYaODbkzEpM-rFzDd8A2@messagerie.si.c-s.fr>
         <b796e912-e945-3cb1-03f8-0f38009634a4@infradead.org>
         <add7c13b1ca24c8cb6f243b99d61c19287020efd.camel@perches.com>
         <4e505c35-8428-89bb-7f9b-bc819382c3cd@infradead.org>
         <16aa5f86f2f899a9156305ead4b7042449278eea.camel@perches.com>
Content-Type: text/plain; charset="ISO-8859-1"
User-Agent: Evolution 3.36.3-0ubuntu1 
MIME-Version: 1.0
Content-Transfer-Encoding: 7bit
Sender: linux-kernel-owner@vger.kernel.org
Precedence: bulk

Try to avoid adding repeated words either on the
same line or consecutive comment lines in a block

e.g.:

duplicated word in comment block

	/*
	 * this is a comment block where the last word of the previous
	 * previous line is also the first word of the next line
	 */

and simple duplication

	/* test this this again */

Inspired-by: Randy Dunlap (rdunlap@infradead.org>
Signed-off-by: Joe Perches <joe@perches.com>
---
 scripts/checkpatch.pl | 38 ++++++++++++++++++++++++++++++++++++++
 1 file changed, 38 insertions(+)

diff --git a/scripts/checkpatch.pl b/scripts/checkpatch.pl
index e9fde28eb0de..c6ef76b72bf3 100755
--- a/scripts/checkpatch.pl
+++ b/scripts/checkpatch.pl
@@ -591,6 +591,8 @@ our @mode_permission_funcs = (
 	["__ATTR", 2],
 );
 
+my $word_pattern = '\b[A-Z]?[a-z]{2,}\b';
+
 #Create a search pattern for all these functions to speed up a loop below
 our $mode_perms_search = "";
 foreach my $entry (@mode_permission_funcs) {
@@ -3340,6 +3342,42 @@ sub process {
 			}
 		}
 
+# check for repeated words separated by a single space
+		if ($rawline =~ /^\+/) {
+			while ($rawline =~ /\b($word_pattern) (?=($word_pattern))/g) {
+
+				my $first = $1;
+				my $second = $2;
+
+				if ($first =~ /(?:struct|union|enum)/) {
+					pos($rawline) += length($first) + length($second) + 1;
+					next;
+				}
+
+				next if ($first ne $second);
+				next if ($first eq 'long');
+
+				if (WARN("REPEATED_WORD",
+					 "Possible repeated word: '$first'\n" . $herecurr) &&
+				    $fix) {
+					$fixed[$fixlinenr] =~ s/\b$first $second\b/$first/;
+				}
+			}
+
+			# if it's a repeated word on consecutive lines in a comment block
+			if ($prevline =~ /$;+\s*$/ &&
+			    $prevrawline =~ /($word_pattern)\s*$/) {
+				my $last_word = $1;
+				if ($rawline =~ /^\+\s*\*\s*$last_word /) {
+					if (WARN("REPEATED_WORD",
+						 "Possible repeated word: '$last_word'\n" . $hereprev) &&
+					    $fix) {
+						$fixed[$fixlinenr] =~ s/(\+\s*\*\s*)$last_word /$1/;
+					}
+				}
+			}
+		}
+
 # check for space before tabs.
 		if ($rawline =~ /^\+/ && $rawline =~ / \t/) {
 			my $herevet = "$here\n" . cat_vet($rawline) . "\n";