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

Contents of /trunk/spider/progspider

Parent Directory Parent Directory | Revision Log Revision Log


Revision 56 - (show annotations)
Fri Jan 23 13:10:40 2004 UTC (20 years, 2 months ago) by dpavlin
File size: 1307 byte(s)
better support for DocBook generated files

1 #!/usr/local/bin/perl -w
2 use strict;
3 use File::Find;
4 use Getopt::Long;
5
6 my $collection; # name which will be inserted
7 my $path_add; # add additional info in path
8 my $verbose;
9
10 my $result = GetOptions(
11 "collection=s" => \$collection,
12 "path=s" => \$path_add,
13 "verbose!" => \$verbose,
14 "debug!" => \$verbose,
15 );
16
17 my $dir = shift @ARGV || die "usage: $0 [dir]";
18
19
20 my $basedir = $0;
21 $basedir =~ s,/[^/]+$,/,;
22 require "$basedir/filter.pm";
23
24
25 find({ wanted => \&file,
26 follow => 1,
27 no_chdir => 1
28 }, $dir);
29
30 sub file {
31
32 return if (! -f || ! m/\.html*/i);
33
34 # skip index files
35 return if (m/index_[a-z]\.html*/i || m/index_symbol\.html*/i);
36
37 my $path = $_;
38
39 open(F,"$path") || die "can't open file: $path";
40 print STDERR "$path" if ($verbose);
41 my $contents;
42 while(<F>) {
43 $contents .= "$_";
44 }
45 $contents .= "\n\n";
46
47 $contents = filter($contents,$collection);
48
49 # die "zero size content in '$path'" if (! $contents);
50 return if (! $contents); # don't die on empty files
51
52 my $mtime = time;
53 use bytes;
54 my $size = length $contents;
55
56 print STDERR " [$size]\n" if ($verbose);
57
58 # add optional components to path
59 $path .= " $path_add" if ($path_add);
60
61 # Output the document (to swish)
62 print <<EOF;
63 Path-Name: $path
64 Content-Length: $size
65 Last-Mtime: $mtime
66 Document-Type: HTML
67
68 EOF
69 print $contents;
70
71 }

Properties

Name Value
cvs2svn:cvs-rev 1.4
svn:executable *

  ViewVC Help
Powered by ViewVC 1.1.26