1 |
#! /usr/bin/perl |
#! /usr/bin/env perl |
2 |
|
|
3 |
# Program for testing regular expressions with perl to check that PCRE handles |
# Program for testing regular expressions with perl to check that PCRE handles |
4 |
# them the same. This is the version that supports /8 for UTF-8 testing. As it |
# them the same. This is the version that supports /8 for UTF-8 testing. As it |
5 |
# stands, it requires at least Perl 5.8 for UTF-8 support. For Perl 5.6, it |
# stands, it requires at least Perl 5.8 for UTF-8 support. However, it needs to |
6 |
# can be used as is for non-UTF-8 testing, but you have to uncomment the |
# have "use utf8" at the start for running the UTF-8 tests, but *not* for the |
7 |
# "use utf8" lines in order to to UTF-8 stuff (and you mustn't uncomment them |
# other tests. The only way I've found for doing this is to cat this line in |
8 |
# for non-UTF-8 use). |
# explicitly in the RunPerlTest script. |
9 |
|
|
10 |
|
# use locale; # With this included, \x0b matches \s! |
11 |
|
|
12 |
# Function for turning a string into a string of printing chars. There are |
# Function for turning a string into a string of printing chars. There are |
13 |
# currently problems with UTF-8 strings; this fudges round them. |
# currently problems with UTF-8 strings; this fudges round them. |
17 |
|
|
18 |
if ($utf8) |
if ($utf8) |
19 |
{ |
{ |
|
# use utf8; <=============== For UTF-8 in Perl 5.6 |
|
20 |
@p = unpack('U*', $_[0]); |
@p = unpack('U*', $_[0]); |
21 |
foreach $c (@p) |
foreach $c (@p) |
22 |
{ |
{ |
38 |
} |
} |
39 |
|
|
40 |
|
|
|
|
|
41 |
# Read lines from named file or stdin and write to named file or stdout; lines |
# Read lines from named file or stdin and write to named file or stdout; lines |
42 |
# consist of a regular expression, in delimiters and optionally followed by |
# consist of a regular expression, in delimiters and optionally followed by |
43 |
# options, followed by a set of test data, terminated by an empty line. |
# options, followed by a set of test data, terminated by an empty line. |
87 |
|
|
88 |
$showrest = ($pattern =~ s/\+(?=[a-z]*$)//); |
$showrest = ($pattern =~ s/\+(?=[a-z]*$)//); |
89 |
|
|
90 |
# The private /8 modifier means "operate in UTF-8". Currently, Perl |
# Remove /8 from a UTF-8 pattern. |
|
# has bugs that we try to work around using this flag. |
|
91 |
|
|
92 |
$utf8 = ($pattern =~ s/8(?=[a-z]*$)//); |
$utf8 = $pattern =~ s/8(?=[a-z]*$)//; |
93 |
|
|
94 |
# Check that the pattern is valid |
# Remove /J from a pattern with duplicate names. |
95 |
|
|
96 |
if ($utf8) |
$pattern =~ s/J(?=[a-z]*$)//; |
|
{ |
|
|
# use utf8; <=============== For UTF-8 in Perl 5.6 |
|
|
eval "\$_ =~ ${pattern}"; |
|
|
} |
|
|
else |
|
|
{ |
|
|
eval "\$_ =~ ${pattern}"; |
|
|
} |
|
97 |
|
|
98 |
|
# Check that the pattern is valid |
99 |
|
|
100 |
|
eval "\$_ =~ ${pattern}"; |
101 |
if ($@) |
if ($@) |
102 |
{ |
{ |
103 |
printf $outfile "Error: $@"; |
printf $outfile "Error: $@"; |
131 |
s/^\s+//; |
s/^\s+//; |
132 |
|
|
133 |
last if ($_ eq ""); |
last if ($_ eq ""); |
|
|
|
134 |
$x = eval "\"$_\""; # To get escapes processed |
$x = eval "\"$_\""; # To get escapes processed |
135 |
|
|
136 |
# Empty array for holding results, then do the matching. |
# Empty array for holding results, then do the matching. |
156 |
"push \@subs,\$16;" . |
"push \@subs,\$16;" . |
157 |
"push \@subs,\$'; }"; |
"push \@subs,\$'; }"; |
158 |
|
|
159 |
if ($utf8) |
eval "${cmd} (\$x =~ ${pattern}) {" . $pushes; |
|
{ |
|
|
# use utf8; <=============== For UTF-8 in Perl 5.6 |
|
|
eval "${cmd} (\$x =~ ${pattern}) {" . $pushes; |
|
|
} |
|
|
else |
|
|
{ |
|
|
eval "${cmd} (\$x =~ ${pattern}) {" . $pushes; |
|
|
} |
|
160 |
|
|
161 |
if ($@) |
if ($@) |
162 |
{ |
{ |