1 |
#! /usr/bin/perl |
#! /usr/bin/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. |
# 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 |
6 |
|
# can be used as is for non-UTF-8 testing, but you have to uncomment the |
7 |
|
# "use utf8" lines in order to to UTF-8 stuff (and you mustn't uncomment them |
8 |
|
# for non-UTF-8 use). |
9 |
|
|
10 |
|
|
11 |
# Function for turning a string into a string of printing chars |
# Function for turning a string into a string of printing chars. There are |
12 |
|
# currently problems with UTF-8 strings; this fudges round them. |
13 |
|
|
14 |
sub pchars { |
sub pchars { |
15 |
my($t) = ""; |
my($t) = ""; |
16 |
|
|
17 |
foreach $c (split(//, $_[0])) |
if ($utf8) |
18 |
{ |
{ |
19 |
if (ord $c >= 32 && ord $c < 127) { $t .= $c; } |
# use utf8; <=============== For UTF-8 in Perl 5.6 |
20 |
else { $t .= sprintf("\\x%02x", ord $c); } |
@p = unpack('U*', $_[0]); |
21 |
|
foreach $c (@p) |
22 |
|
{ |
23 |
|
if ($c >= 32 && $c < 127) { $t .= chr $c; } |
24 |
|
else { $t .= sprintf("\\x{%02x}", $c); } |
25 |
|
} |
26 |
} |
} |
27 |
|
|
28 |
|
else |
29 |
|
{ |
30 |
|
foreach $c (split(//, $_[0])) |
31 |
|
{ |
32 |
|
if (ord $c >= 32 && ord $c < 127) { $t .= $c; } |
33 |
|
else { $t .= sprintf("\\x%02x", ord $c); } |
34 |
|
} |
35 |
|
} |
36 |
|
|
37 |
$t; |
$t; |
38 |
} |
} |
39 |
|
|
84 |
chomp($pattern); |
chomp($pattern); |
85 |
$pattern =~ s/\s+$//; |
$pattern =~ s/\s+$//; |
86 |
|
|
87 |
# The private /+ modifier means "print $' afterwards". We use it |
# The private /+ modifier means "print $' afterwards". |
|
# only on the end of patterns to make it easy to chop off here. |
|
88 |
|
|
89 |
$showrest = ($pattern =~ s/\+(?=[a-z]*$)//); |
$showrest = ($pattern =~ s/\+(?=[a-z]*$)//); |
90 |
|
|
91 |
|
# The private /8 modifier means "operate in UTF-8". Currently, Perl |
92 |
|
# has bugs that we try to work around using this flag. |
93 |
|
|
94 |
|
$utf8 = ($pattern =~ s/8(?=[a-z]*$)//); |
95 |
|
|
96 |
# Check that the pattern is valid |
# Check that the pattern is valid |
97 |
|
|
98 |
eval "\$_ =~ ${pattern}"; |
if ($utf8) |
99 |
|
{ |
100 |
|
# use utf8; <=============== For UTF-8 in Perl 5.6 |
101 |
|
eval "\$_ =~ ${pattern}"; |
102 |
|
} |
103 |
|
else |
104 |
|
{ |
105 |
|
eval "\$_ =~ ${pattern}"; |
106 |
|
} |
107 |
|
|
108 |
if ($@) |
if ($@) |
109 |
{ |
{ |
110 |
printf $outfile "Error: $@"; |
printf $outfile "Error: $@"; |
145 |
|
|
146 |
@subs = (); |
@subs = (); |
147 |
|
|
148 |
eval "${cmd} (\$x =~ ${pattern}) {" . |
$pushes = "push \@subs,\$&;" . |
|
"push \@subs,\$&;" . |
|
149 |
"push \@subs,\$1;" . |
"push \@subs,\$1;" . |
150 |
"push \@subs,\$2;" . |
"push \@subs,\$2;" . |
151 |
"push \@subs,\$3;" . |
"push \@subs,\$3;" . |
164 |
"push \@subs,\$16;" . |
"push \@subs,\$16;" . |
165 |
"push \@subs,\$'; }"; |
"push \@subs,\$'; }"; |
166 |
|
|
167 |
|
if ($utf8) |
168 |
|
{ |
169 |
|
# use utf8; <=============== For UTF-8 in Perl 5.6 |
170 |
|
eval "${cmd} (\$x =~ ${pattern}) {" . $pushes; |
171 |
|
} |
172 |
|
else |
173 |
|
{ |
174 |
|
eval "${cmd} (\$x =~ ${pattern}) {" . $pushes; |
175 |
|
} |
176 |
|
|
177 |
if ($@) |
if ($@) |
178 |
{ |
{ |
179 |
printf $outfile "Error: $@\n"; |
printf $outfile "Error: $@\n"; |