/[bfilter]/trunk/bfilter.pl
This is repository of my old source code which isn't updated any more. Go to git.rot13.org for current projects!
ViewVC logotype

Diff of /trunk/bfilter.pl

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

revision 4 by dpavlin, Tue Sep 7 09:16:06 2004 UTC revision 25 by dpavlin, Wed Sep 15 15:30:04 2004 UTC
# Line 7  use locale; Line 7  use locale;
7  # maximum entries  # maximum entries
8  my $max = 0;  my $max = 0;
9  # minimum letters to search by  # minimum letters to search by
10  my $min_len = 2;  my $min_len = shift @ARGV || 3;
11  # if more than x elements, warn to increase min_len  # if more than x elements, warn to increase min_len
12  my $increase_at = 500;  my $increase_at = 500;
13    
14    # name of generated index
15    my $headlines = 'headlines';
16    
17  my $debug = 1;  my $debug = 1;
18    
19  sub print_file {  sub print_file {
# Line 23  sub print_file { Line 26  sub print_file {
26  }  }
27    
28  print qq{  print qq{
29  var headlines = Array();  var $headlines = new Object();
30  };  };
31    
32  my @part_arr;  my @part_arr;
# Line 32  my $total = 0; Line 35  my $total = 0;
35    
36  my $max_elements = 0;  my $max_elements = 0;
37    
38    sub escape_js {
39            my $t = shift || return;
40            $t =~ s/(['\\])/\\$1/g && print STDERR "ESCAPED '$t'\n";
41            return $t;
42    }
43    
44  while(<STDIN>) {  while(<STDIN>) {
45          chomp;          chomp;
46    
47          # escape single quote          if (!m/\t/ || m/\t$/) {
48          s/'/\\'/g;                  print STDERR "SKIP '$_': no tab\n";
49                    next;
50            }
51    
52            my @data = split(/\t+/,$_);
53    
54            my $headline = shift @data || die "need at least headline!";
55    
56            if (length($headline) < $min_len) {
57                    print STDERR "SKIP '$_': too short\n";
58                    next;
59            }
60    
61    
62          # split into min_len part and rest          # split into min_len part and rest
63          my ($part,$rest) = ( substr($_,0,$min_len), substr($_,$min_len) );          my ($part,$rest) = ( substr($headline,0,$min_len), substr($headline,$min_len) );
64    
65          # make part lowercase          # make part lowercase
66          $part = lc($part);          $part = lc($part);
# Line 48  while(<STDIN>) { Line 69  while(<STDIN>) {
69    
70          # new part?          # new part?
71          if ($part ne $last_part) {          if ($part ne $last_part) {
72                  print STDERR $last_part,"\t",$#part_arr+1,"\n" if ($debug);                  print STDERR $last_part,"\t",$#part_arr+1,"\n" if ($debug && $#part_arr > $increase_at);
73                  $max_elements = $#part_arr if ($#part_arr > $max_elements);                  $max_elements = $#part_arr if ($#part_arr > $max_elements);
74                  print "headlines['$last_part'] = Array(\n ",join(",\n ",@part_arr),");\n" if (@part_arr);                  print "${headlines}['",escape_js($last_part),"'] = [\n ",join(",\n ",@part_arr),"];\n" if (@part_arr);
75                  $total += $#part_arr;                  $total += $#part_arr;
76                  @part_arr = ();                  @part_arr = ();
77                  $last_part = $part;                  $last_part = $part;
78          }          }
79          push @part_arr, "'$_'";          push @part_arr, "['".escape_js($headline)."','".join("','",map { escape_js($_) } @data)."']";
80    
81          # break out?          # break out?
82          last if ($max && $total > $max);          last if ($max && $total > $max);
83  }  }
84    
85  print "headlines['$last_part'] = Array(\n ",join(",\n ",@part_arr),");\n" if (@part_arr);  print "${headlines}['",escape_js($last_part)."'] = [\n ",join(",\n ",@part_arr),"];\n" if (@part_arr);
86  print "var min_len = $min_len;\n";  print qq{
87  print "// index elements: $total\n";  
88    ${headlines}.min_len = $min_len;
89    ${headlines}.length = $total;
90    
91    };
92    
93  print STDERR "You have more than $increase_at elements in one array,\nyou whould probably increase min_len to ",$min_len+1," or higher.\n" if ($max_elements > $increase_at);  print STDERR "You have more than $increase_at elements, so you should\nincrease min_len to ",$min_len+1," or higher for performance benefit.\n" if ($max_elements > $increase_at);

Legend:
Removed from v.4  
changed lines
  Added in v.25

  ViewVC Help
Powered by ViewVC 1.1.26