chainlint.pl: add parser to identify test definitions
Finish fleshing out chainlint.pl by adding ScriptParser, a parser which scans shell scripts for tests defined by test_expect_success() and test_expect_failure(), plucks the test body from each definition, and passes it to TestParser for validation. It recognizes test definitions not only at the top-level of test scripts but also tests synthesized within compound commands such as loops and function. Signed-off-by: Eric Sunshine <sunshine@sunshineco.com> Signed-off-by: Junio C Hamano <gitster@pobox.com>
Eric Sunshine committed
Sep 1, 2022 at 00:29 UTC
d99ebd6d2e57baa3ec45b939d40cf939b85301a3
1 file changed
+60
-3
t/chainlint.pl
+60
-3
@@ -487,18 +487,75 @@ DONE:
487
$self->SUPER::accumulate($tokens, $cmd);
488
}
489
490
+# ScriptParser is a subclass of ShellParser which identifies individual test
491
+# definitions within test scripts, and passes each test body through TestParser
492
+# to identify possible problems. ShellParser detects test definitions not only
493
+# at the top-level of test scripts but also within compound commands such as
494
+# loops and function definitions.
495
package ScriptParser;
496
497
+use base 'ShellParser';
498
+
499
sub new {
500
my $class = shift @_;
494
- my $self = bless {} => $class;
495
- $self->{output} = [];
501
+ my $self = $class->SUPER::new(@_);
502
$self->{ntests} = 0;
503
return $self;
504
}
505
506
+# extract the raw content of a token, which may be a single string or a
507
+# composition of multiple strings and non-string character runs; for instance,
508
+# `"test body"` unwraps to `test body`; `word"a b"42'c d'` to `worda b42c d`
509
+sub unwrap {
510
+ my $token = @_ ? shift @_ : $_;
511
+ # simple case: 'sqstring' or "dqstring"
512
+ return $token if $token =~ s/^'([^']*)'$/$1/;
513
+ return $token if $token =~ s/^"([^"]*)"$/$1/;
514
+
515
+ # composite case
516
+ my ($s, $q, $escaped);
517
+ while (1) {
518
+ # slurp up non-special characters
519
+ $s .= $1 if $token =~ /\G([^\\'"]*)/gc;
520
+ # handle special characters
521
+ last unless $token =~ /\G(.)/sgc;
522
+ my $c = $1;
523
+ $q = undef, next if defined($q) && $c eq $q;
524
+ $q = $c, next if !defined($q) && $c =~ /^['"]$/;
525
+ if ($c eq '\\') {
526
+ last unless $token =~ /\G(.)/sgc;
527
+ $c = $1;
528
+ $s .= '\\' if $c eq "\n"; # preserve line splice
529
+ }
530
+ $s .= $c;
531
+ }
532
+ return $s
533
+}
534
+
535
+sub check_test {
536
+ my $self = shift @_;
537
+ my ($title, $body) = map(unwrap, @_);
538
+ $self->{ntests}++;
539
+ my $parser = TestParser->new(\$body);
540
+ my @tokens = $parser->parse();
541
+ return unless $emit_all || grep(/\?![^?]+\?!/, @tokens);
542
+ my $checked = join(' ', @tokens);
543
+ $checked =~ s/^\n//;
544
+ $checked =~ s/^ //mg;
545
+ $checked =~ s/ $//mg;
546
+ $checked .= "\n" unless $checked =~ /\n$/;
547
+ push(@{$self->{output}}, "# chainlint: $title\n$checked");
548
+}
549
+
550
sub parse_cmd {
501
- return undef;
551
+ my $self = shift @_;
552
+ my @tokens = $self->SUPER::parse_cmd();
553
+ return @tokens unless @tokens && $tokens[0] =~ /^test_expect_(?:success|failure)$/;
554
+ my $n = $#tokens;
555
+ $n-- while $n >= 0 && $tokens[$n] =~ /^(?:[;&\n|]|&&|\|\|)$/;
556
+ $self->check_test($tokens[1], $tokens[2]) if $n == 2; # title body
557
+ $self->check_test($tokens[2], $tokens[3]) if $n > 2; # prereq title body
558
+ return @tokens;
559
}
560
561
# main contains high-level functionality for processing command-line switches,