/[pcre]/code/trunk/perltest
ViewVC logotype

Diff of /code/trunk/perltest

Parent Directory Parent Directory | Revision Log Revision Log | View Patch Patch

revision 23 by nigel, Sat Feb 24 21:38:41 2007 UTC revision 63 by nigel, Sat Feb 24 21:40:03 2007 UTC
# Line 1  Line 1 
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    
# Line 53  for (;;) Line 73  for (;;)
73    
74    $pattern = $_;    $pattern = $_;
75    
   $delimiter = substr($_, 0, 1);  
76    while ($pattern !~ /^\s*(.).*\1/s)    while ($pattern !~ /^\s*(.).*\1/s)
77      {      {
78      printf "    > " if $infile eq "STDIN";      printf "    > " if $infile eq "STDIN";
# Line 65  for (;;) Line 84  for (;;)
84     chomp($pattern);     chomp($pattern);
85     $pattern =~ s/\s+$//;     $pattern =~ s/\s+$//;
86    
87      # The private /+ modifier means "print $' afterwards".
88    
89      $showrest = ($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: $@";
111      next NEXT_RE;      next NEXT_RE;
112      }      }
113    
114      # If the /g modifier is present, we want to put a loop round the matching;
115      # otherwise just a single "if".
116    
117      $cmd = ($pattern =~ /g[a-z]*$/)? "while" : "if";
118    
119      # If the pattern is actually the null string, Perl uses the most recently
120      # executed (and successfully compiled) regex is used instead. This is a
121      # nasty trap for the unwary! The PCRE test suite does contain null strings
122      # in places - if they are allowed through here all sorts of weird and
123      # unexpected effects happen. To avoid this, we replace such patterns with
124      # a non-null pattern that has the same effect.
125    
126      $pattern = "/(?#)/$2" if ($pattern =~ /^(.)\1(.*)$/);
127    
128    # Read data lines and test them    # Read data lines and test them
129    
130    for (;;)    for (;;)
# Line 88  for (;;) Line 139  for (;;)
139    
140      last if ($_ eq "");      last if ($_ eq "");
141    
142      $_ = eval "\"$_\"";   # To get escapes processed      $x = eval "\"$_\"";   # To get escapes processed
143    
144        # Empty array for holding results, then do the matching.
145    
146      $ok = 0;      @subs = ();
147      eval "if (\$_ =~ ${pattern}) {" .  
148           "\$z = \$&;" .      $pushes = "push \@subs,\$&;" .
149           "\$a = \$1;" .           "push \@subs,\$1;" .
150           "\$b = \$2;" .           "push \@subs,\$2;" .
151           "\$c = \$3;" .           "push \@subs,\$3;" .
152           "\$d = \$4;" .           "push \@subs,\$4;" .
153           "\$e = \$5;" .           "push \@subs,\$5;" .
154           "\$f = \$6;" .           "push \@subs,\$6;" .
155           "\$g = \$7;" .           "push \@subs,\$7;" .
156           "\$h = \$8;" .           "push \@subs,\$8;" .
157           "\$i = \$9;" .           "push \@subs,\$9;" .
158           "\$j = \$10;" .           "push \@subs,\$10;" .
159           "\$k = \$11;" .           "push \@subs,\$11;" .
160           "\$l = \$12;" .           "push \@subs,\$12;" .
161           "\$m = \$13;" .           "push \@subs,\$13;" .
162           "\$n = \$14;" .           "push \@subs,\$14;" .
163           "\$o = \$15;" .           "push \@subs,\$15;" .
164           "\$p = \$16;" .           "push \@subs,\$16;" .
165           "\$ok = 1; }";           "push \@subs,\$'; }";
166    
167        if ($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: $@\n";
180        next NEXT_RE;        next NEXT_RE;
181        }        }
182      elsif (!$ok)      elsif (scalar(@subs) == 0)
183        {        {
184        printf $outfile "No match\n";        printf $outfile "No match\n";
185        }        }
186      else      else
187        {        {
188        @subs = ($z,$a,$b,$c,$d,$e,$f,$g,$h,$i,$j,$k,$l,$m,$n,$o,$p);        while (scalar(@subs) != 0)
       $last_printed = 0;  
       for ($i = 0; $i <= 17; $i++)  
189          {          {
190          if ($i == 0 || defined $subs[$i])          printf $outfile (" 0: %s\n", &pchars($subs[0]));
191            printf $outfile (" 0+ %s\n", &pchars($subs[17])) if $showrest;
192            $last_printed = 0;
193            for ($i = 1; $i <= 16; $i++)
194            {            {
195            while ($last_printed++ < $i-1)            if (defined $subs[$i])
196              { printf $outfile ("%2d: <unset>\n", $last_printed); }              {
197            printf $outfile ("%2d: %s\n", $i, &pchars($subs[$i]));              while ($last_printed++ < $i-1)
198            $last_printed = $i;                { printf $outfile ("%2d: <unset>\n", $last_printed); }
199                printf $outfile ("%2d: %s\n", $i, &pchars($subs[$i]));
200                $last_printed = $i;
201                }
202            }            }
203            splice(@subs, 0, 18);
204          }          }
205        }        }
206      }      }

Legend:
Removed from v.23  
changed lines
  Added in v.63

  ViewVC Help
Powered by ViewVC 1.1.5