embedaddon/pcre/perltest.pl - diff

Return to perltest.pl CVS log

Up to [ELWIX - Embedded LightWeight unIX -] / embedaddon / pcre

Diff for /embedaddon/pcre/perltest.pl between versions 1.1 and 1.1.1.4

version 1.1, 2012/02/21 23:05:51	version 1.1.1.4, 2014/06/15 19:46:04
Line 1	Line 1
#! /usr/bin/env perl	#! /usr/bin/env perl

# Program for testing regular expressions with perl to check that PCRE handles	# Program for testing regular expressions with perl to check that PCRE handles
# them the same. This is the version that supports /8 for UTF-8 testing. As it	# them the same. This version needs to have "use utf8" at the start for running
# stands, it requires at least Perl 5.8 for UTF-8 support. However, it needs to	# the UTF-8 tests, but not for the other tests. The only way I've found for
# have "use utf8" at the start for running the UTF-8 tests, but not for the	# doing this is to cat this line in explicitly in the RunPerlTest script. I've
# other tests. The only way I've found for doing this is to cat this line in	# also used this method to supply "require Encode" for the UTF-8 tests, so that
# explicitly in the RunPerlTest script.	# the main test will still run where Encode is not installed.

# use locale; # With this included, \x0b matches \s!	#use utf8;
	#require Encode;

# Function for turning a string into a string of printing chars. There are	# Function for turning a string into a string of printing chars.
# currently problems with UTF-8 strings; this fudges round them.

sub pchars {	sub pchars {
my($t) = "";	my($t) = "";
Line 21 if ($utf8)	Line 21 if ($utf8)
foreach $c (@p)	foreach $c (@p)
{	{
if ($c >= 32 && $c < 127) { $t .= chr $c; }	if ($c >= 32 && $c < 127) { $t .= chr $c; }
else { $t .= sprintf("\\x{%02x}", $c); }	else { $t .= sprintf("\\x{%02x}", $c);
	}
}	}
}	}

else	else
{	{
foreach $c (split(//, $_[0]))	foreach $c (split(//, $_[0]))
Line 68 for (;;)	Line 68 for (;;)
printf " re> " if $infile eq "STDIN";	printf " re> " if $infile eq "STDIN";
last if ! ($_ = <$infile>);	last if ! ($_ = <$infile>);
printf $outfile "$_" if $infile ne "STDIN";	printf $outfile "$_" if $infile ne "STDIN";
next if ($_ eq "");	next if ($_ =~ /^\s*$/ \|\| $_ =~ /^< forbid/);

$pattern = $_;	$pattern = $_;

Line 103 for (;;)	Line 103 for (;;)

$pattern =~ s/K(?=[a-zA-Z]*$)//;	$pattern =~ s/K(?=[a-zA-Z]*$)//;

# Remove /W from a pattern (asks pcretest to set PCRE_UCP)	# /W asks pcretest to set PCRE_UCP; change this to /u for Perl

$pattern =~ s/W(?=[a-zA-Z]*$)//;	$pattern =~ s/W(?=[a-zA-Z]*$)/u/;

# Remove /S or /SS from a pattern (asks pcretest to study or not to study)	# Remove /S or /SS from a pattern (asks pcretest to study or not to study)

$pattern =~ s/S(?=[a-zA-Z]*$)//g;	$pattern =~ s/S(?=[a-zA-Z]*$)//g;

# Remove /Y from a pattern (asks pcretest to disable PCRE optimization)	# Remove /Y and /O from a pattern (disable PCRE optimizations)

$pattern =~ s/Y(?=[a-zA-Z]*$)//;	$pattern =~ s/[YO](?=[a-zA-Z]*$)//;

# Check that the pattern is valid	# Check that the pattern is valid

Line 192 for (;;)	Line 192 for (;;)
{	{
printf $outfile "No match";	printf $outfile "No match";
if (defined $REGERROR && $REGERROR != 1)	if (defined $REGERROR && $REGERROR != 1)
{ print $outfile (", mark = $REGERROR"); }	{ printf $outfile (", mark = %s", &pchars($REGERROR)); }
printf $outfile "\n";	printf $outfile "\n";
}	}
else	else
Line 214 for (;;)	Line 214 for (;;)
}	}
splice(@subs, 0, 18);	splice(@subs, 0, 18);
}	}

	# It seems that $REGMARK is not marked as UTF-8 even when use utf8 is
	# set and the input pattern was a UTF-8 string. We can, however, force
	# it to be so marked.

if (defined $REGMARK && $REGMARK != 1)	if (defined $REGMARK && $REGMARK != 1)
{ print $outfile ("MK: $REGMARK\n"); }	{
	$xx = $REGMARK;
	$xx = Encode::decode_utf8($xx) if $utf8;
	printf $outfile ("MK: %s\n", &pchars($xx));
	}
}	}
}	}
}	}

FreeBSD-CVSweb <freebsd-cvsweb@FreeBSD.org>

Removed from v.1.1
changed lines
	Added in v.1.1.1.4