[PATCH] checkpatch: Improve GIT_COMMIT_ID test

From: Joe Perches
Date: Fri Aug 20 2021 - 17:46:57 EST

The preferred git commit id reference has the form

commit <SHA-1> ("Title line")

where SHA-1 is the commit hex hash with a minimum lenth of 12 and
("Title line") is the complete title line of the commit with a (" prefix
and ") suffix.

The current tests fail when the "Title line" has one or more embedded
double quotes.

Improve the test that finds the commit SHA-1 hex hash then ("Title line")
by using $balanced_parens for a maximum of 3 consecutive lines.

Signed-off-by: Joe Perches <joe@xxxxxxxxxxx>
---
scripts/checkpatch.pl | 82 +++++++++++++++++++++++++++----------------
1 file changed, 51 insertions(+), 31 deletions(-)

diff --git a/scripts/checkpatch.pl b/scripts/checkpatch.pl
index 161ce7fe5d1e5..7c33ffafa3f0c 100755
--- a/scripts/checkpatch.pl
+++ b/scripts/checkpatch.pl
@@ -1181,7 +1181,8 @@ sub git_commit_info {
# git log --format='%H %s' -1 $line |
# echo "commit $(cut -c 1-12,41-)"
# done
- } elsif ($lines[0] =~ /^fatal: ambiguous argument '$commit': unknown revision or path not in the working tree\./) {
+ } elsif ($lines[0] =~ /^fatal: ambiguous argument '$commit': unknown revision or path not in the working tree\./ ||
+ $lines[0] =~ /^fatal: bad object $commit/) {
$id = undef;
} else {
$id = substr($lines[0], 0, 12);
@@ -2587,6 +2588,8 @@ sub process {
my $reported_maintainer_file = 0;
my $non_utf8_charset = 0;

+ my $last_git_commit_id_linenr = -1;
+
my $last_blank_line = 0;
my $last_coalesced_string_linenr = -1;

@@ -3170,10 +3173,20 @@ sub process {
}

# Check for git id commit length and improperly formed commit descriptions
- if ($in_commit_log && !$commit_log_possible_stack_dump &&
+# A correctly formed commit description is:
+# commit <SHA-1 hash length 12+ chars> ("Complete commit subject")
+# with the commit subject '("' prefix and '")' suffix
+# This is a fairly compilicated block as it tests for what appears to be
+# bare SHA-1 hash with minimum length of 5. It also avoids several types of
+# possible SHA-1 matches.
+# A commit match can span multiple lines so this block attempts to find a
+# complete typical commit on a maximum of 3 lines
+ if ($perl_version_ok
+ $in_commit_log && !$commit_log_possible_stack_dump &&
$line !~ /^\s*(?:Link|Patchwork|http|https|BugLink|base-commit):/i &&
$line !~ /^This reverts commit [0-9a-f]{7,40}/ &&
- ($line =~ /\bcommit\s+[0-9a-f]{5,}\b/i ||
+ (($line =~ /\bcommit\s+[0-9a-f]{5,}\b/i ||
+ ($line =~ /\bcommit\s*$/i && defined($rawlines[$linenr]) && $rawlines[$linenr] =~ /^\s*[0-9a-f]{5,}\b/i)) ||
($line =~ /(?:\s|^)[0-9a-f]{12,40}(?:[\s"'\(\[]|$)/i &&
$line !~ /[\<\[][0-9a-f]{12,40}[\>\]]/i &&
$line !~ /\bfixes:\s*[0-9a-f]{12,40}/i))) {
@@ -3183,49 +3196,56 @@ sub process {
my $long = 0;
my $case = 1;
my $space = 1;
- my $hasdesc = 0;
- my $hasparens = 0;
my $id = '0123456789ab';
my $orig_desc = "commit description";
my $description = "";
+ my $herectx = $herecurr;
+ my $has_parens = 0;
+ my $has_quotes = 0;
+
+ my $input = $line;
+ if ($line =~ /(?:\bcommit\s+[0-9a-f]{5,}|\bcommit\s*$)/i) {
+ for (my $n = 0; $n < 2; $n++) {
+ if ($input =~ /\bcommit\s+[0-9a-f]{5,}\s*($balanced_parens)/i) {
+ $orig_desc = $1;
+ $has_parens = 1;
+ # Always strip leading/trailing parens then double quotes if existing
+ $orig_desc = substr($orig_desc, 1, -1);
+ if ($orig_desc =~ /^".*"$/) {
+ $orig_desc = substr($orig_desc, 1, -1);
+ $has_quotes = 1;
+ }
+ last;
+ }
+ last if ($#lines < $linenr + $n);
+ $input .= " " . trim($rawlines[$linenr + $n]);
+ $herectx .= "$rawlines[$linenr + $n]\n";
+ }
+ $herectx = $herecurr if (!$has_parens);
+ }

- if ($line =~ /\b(c)ommit\s+([0-9a-f]{5,})\b/i) {
+ if ($input =~ /\b(c)ommit\s+([0-9a-f]{5,})\b/i) {
$init_char = $1;
$orig_commit = lc($2);
- } elsif ($line =~ /\b([0-9a-f]{12,40})\b/i) {
+ $short = 0 if ($input =~ /\bcommit\s+[0-9a-f]{12,40}/i);
+ $long = 1 if ($input =~ /\bcommit\s+[0-9a-f]{41,}/i);
+ $space = 0 if ($input =~ /\bcommit [0-9a-f]/i);
+ $case = 0 if ($input =~ /\b[Cc]ommit\s+[0-9a-f]{5,40}[^A-F]/);
+ } elsif ($input =~ /\b([0-9a-f]{12,40})\b/i) {
$orig_commit = lc($1);
}

- $short = 0 if ($line =~ /\bcommit\s+[0-9a-f]{12,40}/i);
- $long = 1 if ($line =~ /\bcommit\s+[0-9a-f]{41,}/i);
- $space = 0 if ($line =~ /\bcommit [0-9a-f]/i);
- $case = 0 if ($line =~ /\b[Cc]ommit\s+[0-9a-f]{5,40}[^A-F]/);
- if ($line =~ /\bcommit\s+[0-9a-f]{5,}\s+\("([^"]+)"\)/i) {
- $orig_desc = $1;
- $hasparens = 1;
- } elsif ($line =~ /\bcommit\s+[0-9a-f]{5,}\s*$/i &&
- defined $rawlines[$linenr] &&
- $rawlines[$linenr] =~ /^\s*\("([^"]+)"\)/) {
- $orig_desc = $1;
- $hasparens = 1;
- } elsif ($line =~ /\bcommit\s+[0-9a-f]{5,}\s+\("[^"]+$/i &&
- defined $rawlines[$linenr] &&
- $rawlines[$linenr] =~ /^\s*[^"]+"\)/) {
- $line =~ /\bcommit\s+[0-9a-f]{5,}\s+\("([^"]+)$/i;
- $orig_desc = $1;
- $rawlines[$linenr] =~ /^\s*([^"]+)"\)/;
- $orig_desc .= " " . $1;
- $hasparens = 1;
- }
-
($id, $description) = git_commit_info($orig_commit,
$id, $orig_desc);

if (defined($id) &&
- ($short || $long || $space || $case || ($orig_desc ne $description) || !$hasparens)) {
+ ($short || $long || $space || $case || ($orig_desc ne $description) || !$has_quotes) &&
+ $last_git_commit_id_linenr != $linenr - 1) {
ERROR("GIT_COMMIT_ID",
- "Please use git commit description style 'commit <12+ chars of sha1> (\"<title line>\")' - ie: '${init_char}ommit $id (\"$description\")'\n" . $herecurr);
+ "Please use git commit description style 'commit <12+ chars of sha1> (\"<title line>\")' - ie: '${init_char}ommit $id (\"$description\")'\n" . $herectx);
}
+ #don't report the next line if this line ends in commit and the sha1 hash is the next line
+ $last_git_commit_id_linenr = $linenr if ($line =~ /\bcommit\s*$/i);
}

# Check for added, moved or deleted files
--
2.30.0