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

Diff of /code/trunk/perltest.pl

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

revision 3 by nigel, Sat Feb 24 21:38:01 2007 UTC revision 91 by nigel, Sat Feb 24 21:41:34 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. However, it needs to
6    # have "use utf8" at the start for running the UTF-8 tests, but *not* for the
7    # other tests. The only way I've found for doing this is to cat this line in
8    # 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  # Function for turning a string into a string of printing chars. There are
13    # currently problems with UTF-8 strings; this fudges round them.
14    
15  sub pchars {  sub pchars {
16  my($t) = "";  my($t) = "";
17    
18  foreach $c (split(//, @_[0]))  if ($utf8)
19    {    {
20    if (ord $c >= 32 && ord $c < 127) { $t .= $c; }    @p = unpack('U*', $_[0]);
21      else { $t .= sprintf("\\x%02x", ord $c); }    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    
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.
# Line 39  if (@ARGV > 1) Line 58  if (@ARGV > 1)
58    }    }
59  else { $outfile = "STDOUT"; }  else { $outfile = "STDOUT"; }
60    
61  printf($outfile "Perl Regular Expressions\n\n");  printf($outfile "Perl $] Regular Expressions\n\n");
62    
63  # Main loop  # Main loop
64    
# Line 53  for (;;) Line 72  for (;;)
72    
73    $pattern = $_;    $pattern = $_;
74    
   $delimiter = substr($_, 0, 1);  
75    while ($pattern !~ /^\s*(.).*\1/s)    while ($pattern !~ /^\s*(.).*\1/s)
76      {      {
77      printf "    > " if $infile eq "STDIN";      printf "    > " if $infile eq "STDIN";
# Line 65  for (;;) Line 83  for (;;)
83     chomp($pattern);     chomp($pattern);
84     $pattern =~ s/\s+$//;     $pattern =~ s/\s+$//;
85    
86      # The private /+ modifier means "print $' afterwards".
87    
88      $showrest = ($pattern =~ s/\+(?=[a-z]*$)//);
89    
90      # Remove /8 from a UTF-8 pattern.
91    
92      $utf8 = $pattern =~ s/8(?=[a-z]*$)//;
93    
94    # Check that the pattern is valid    # Check that the pattern is valid
95    
96    eval "\$_ =~ ${pattern}";    eval "\$_ =~ ${pattern}";
97    if ($@)    if ($@)
98      {      {
99      printf $outfile "Error: $@\n";      printf $outfile "Error: $@";
100      next NEXT_RE;      next NEXT_RE;
101      }      }
102    
103      # If the /g modifier is present, we want to put a loop round the matching;
104      # otherwise just a single "if".
105    
106      $cmd = ($pattern =~ /g[a-z]*$/)? "while" : "if";
107    
108      # If the pattern is actually the null string, Perl uses the most recently
109      # executed (and successfully compiled) regex is used instead. This is a
110      # nasty trap for the unwary! The PCRE test suite does contain null strings
111      # in places - if they are allowed through here all sorts of weird and
112      # unexpected effects happen. To avoid this, we replace such patterns with
113      # a non-null pattern that has the same effect.
114    
115      $pattern = "/(?#)/$2" if ($pattern =~ /^(.)\1(.*)$/);
116    
117    # Read data lines and test them    # Read data lines and test them
118    
119    for (;;)    for (;;)
# Line 87  for (;;) Line 127  for (;;)
127      s/^\s+//;      s/^\s+//;
128    
129      last if ($_ eq "");      last if ($_ eq "");
130        $x = eval "\"$_\"";   # To get escapes processed
131    
132        # Empty array for holding results, then do the matching.
133    
134        @subs = ();
135    
136      $_ = eval "\"$_\"";   # To get escapes processed      $pushes = "push \@subs,\$&;" .
137             "push \@subs,\$1;" .
138             "push \@subs,\$2;" .
139             "push \@subs,\$3;" .
140             "push \@subs,\$4;" .
141             "push \@subs,\$5;" .
142             "push \@subs,\$6;" .
143             "push \@subs,\$7;" .
144             "push \@subs,\$8;" .
145             "push \@subs,\$9;" .
146             "push \@subs,\$10;" .
147             "push \@subs,\$11;" .
148             "push \@subs,\$12;" .
149             "push \@subs,\$13;" .
150             "push \@subs,\$14;" .
151             "push \@subs,\$15;" .
152             "push \@subs,\$16;" .
153             "push \@subs,\$'; }";
154    
155      $ok = 0;      eval "${cmd} (\$x =~ ${pattern}) {" . $pushes;
     eval "if (\$_ =~ ${pattern}) {" .  
          "\$z = \$&;" .  
          "\$a = \$1;" .  
          "\$b = \$2;" .  
          "\$c = \$3;" .  
          "\$d = \$4;" .  
          "\$e = \$5;" .  
          "\$f = \$6;" .  
          "\$g = \$7;" .  
          "\$h = \$8;" .  
          "\$i = \$9;" .  
          "\$j = \$10;" .  
          "\$k = \$11;" .  
          "\$l = \$12;" .  
          "\$m = \$13;" .  
          "\$n = \$14;" .  
          "\$o = \$15;" .  
          "\$p = \$16;" .  
          "\$ok = 1; }";  
156    
157      if ($@)      if ($@)
158        {        {
159        printf $outfile "Error: $@\n";        printf $outfile "Error: $@\n";
160        next NEXT_RE;        next NEXT_RE;
161        }        }
162      elsif (!$ok)      elsif (scalar(@subs) == 0)
163        {        {
164        printf $outfile "No match\n";        printf $outfile "No match\n";
165        }        }
166      else      else
167        {        {
168        @subs = ($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; $i++)  
169          {          {
170          if ($i == 0 || defined $subs[$i])          printf $outfile (" 0: %s\n", &pchars($subs[0]));
171            printf $outfile (" 0+ %s\n", &pchars($subs[17])) if $showrest;
172            $last_printed = 0;
173            for ($i = 1; $i <= 16; $i++)
174            {            {
175            while ($last_printed++ < $i-1)            if (defined $subs[$i])
176              { printf $outfile ("%2d: <unset>\n", $last_printed); }              {
177            printf $outfile ("%2d: %s\n", $i, &pchars($subs[$i]));              while ($last_printed++ < $i-1)
178            $last_printed = $i;                { printf $outfile ("%2d: <unset>\n", $last_printed); }
179                printf $outfile ("%2d: %s\n", $i, &pchars($subs[$i]));
180                $last_printed = $i;
181                }
182            }            }
183            splice(@subs, 0, 18);
184          }          }
185        }        }
186      }      }
187    }    }
188    
189  printf $outfile "\n";  # printf $outfile "\n";
190    
191  # End  # End
Legend:
Removed from v.3  
changed lines
  Added in v.91
webmaster@exim.org
 ViewVC Help
Powered by ViewVC 1.1.12