chainlint: latch line numbers at which each token starts and ends

When chainlint detects problems in a test, it prints out the name of the
test script, the name of the problematic test, and a copy of the test
definition with "?!FOO?!" annotations inserted at the locations where
problems were detected. Taken together this information is sufficient
for the test author to identify the problematic code in the original
test definition. However, in a lengthy script or a lengthy test
definition, the author may still end up using the editor's search
feature to home in on the exact problem location.

To further assist the test author, an upcoming change will display line
numbers along with the annotated test definition, thus allowing the
author to jump directly to each problematic line. As preparation,
upgrade Lexer to latch the line numbers at which each token starts and
ends, and return that information with the token itself.

Signed-off-by: Eric Sunshine <sunshine@sunshineco.com>
Signed-off-by: Taylor Blau <me@ttaylorr.com>
This commit is contained in:
Eric Sunshine 2022-11-11 07:34:53 +00:00 committed by Taylor Blau
parent 5451877f87
commit bf42f0a030

View file

@ -67,6 +67,7 @@ sub new {
bless {
parser => $parser,
buff => $s,
lineno => 1,
heretags => []
} => $class;
}
@ -97,7 +98,9 @@ sub scan_op {
sub scan_sqstring {
my $self = shift @_;
${$self->{buff}} =~ /\G([^']*'|.*\z)/sgc;
return "'" . $1;
my $s = $1;
$self->{lineno} += () = $s =~ /\n/sg;
return "'" . $s;
}
sub scan_dqstring {
@ -115,7 +118,7 @@ sub scan_dqstring {
if ($c eq '\\') {
$s .= '\\', last unless $$b =~ /\G(.)/sgc;
$c = $1;
next if $c eq "\n"; # line splice
$self->{lineno}++, next if $c eq "\n"; # line splice
# backslash escapes only $, `, ", \ in dq-string
$s .= '\\' unless $c =~ /^[\$`"\\]$/;
$s .= $c;
@ -123,6 +126,7 @@ sub scan_dqstring {
}
die("internal error scanning dq-string '$c'\n");
}
$self->{lineno} += () = $s =~ /\n/sg;
return $s;
}
@ -137,6 +141,7 @@ sub scan_balanced {
$depth--;
last if $depth == 0;
}
$self->{lineno} += () = $s =~ /\n/sg;
return $s;
}
@ -163,8 +168,11 @@ sub swallow_heredocs {
my $b = $self->{buff};
my $tags = $self->{heretags};
while (my $tag = shift @$tags) {
my $start = pos($$b);
my $indent = $tag =~ s/^\t// ? '\\s*' : '';
$$b =~ /(?:\G|\n)$indent\Q$tag\E(?:\n|\z)/gc;
my $body = substr($$b, $start, pos($$b) - $start);
$self->{lineno} += () = $body =~ /\n/sg;
}
}
@ -172,11 +180,12 @@ sub scan_token {
my $self = shift @_;
my $b = $self->{buff};
my $token = '';
my $start;
my ($start, $startln);
RESTART:
$startln = $self->{lineno};
$$b =~ /\G[ \t]+/gc; # skip whitespace (but not newline)
$start = pos($$b) || 0;
return ["\n", $start, pos($$b)] if $$b =~ /\G#[^\n]*(?:\n|\z)/gc; # comment
$self->{lineno}++, return ["\n", $start, pos($$b), $startln, $startln] if $$b =~ /\G#[^\n]*(?:\n|\z)/gc; # comment
while (1) {
# slurp up non-special characters
$token .= $1 if $$b =~ /\G([^\\;&|<>(){}'"\$\s]+)/gc;
@ -188,20 +197,20 @@ sub scan_token {
$token .= $self->scan_sqstring(), next if $c eq "'";
$token .= $self->scan_dqstring(), next if $c eq '"';
$token .= $c . $self->scan_dollar(), next if $c eq '$';
$self->swallow_heredocs(), $token = $c, last if $c eq "\n";
$self->{lineno}++, $self->swallow_heredocs(), $token = $c, last if $c eq "\n";
$token = $self->scan_op($c), last if $c =~ /^[;&|<>]$/;
$token = $c, last if $c =~ /^[(){}]$/;
if ($c eq '\\') {
$token .= '\\', last unless $$b =~ /\G(.)/sgc;
$c = $1;
next if $c eq "\n" && length($token); # line splice
goto RESTART if $c eq "\n"; # line splice
$self->{lineno}++, next if $c eq "\n" && length($token); # line splice
$self->{lineno}++, goto RESTART if $c eq "\n"; # line splice
$token .= '\\' . $c;
next;
}
die("internal error scanning character '$c'\n");
}
return length($token) ? [$token, $start, pos($$b)] : undef;
return length($token) ? [$token, $start, pos($$b), $startln, $self->{lineno}] : undef;
}
# ShellParser parses POSIX shell scripts (with minor extensions for Bash). It