1 |
#!/usr/local/bin/perl -w |
2 |
use strict; |
3 |
use File::Find; |
4 |
use Getopt::Long; |
5 |
use File::Which; |
6 |
|
7 |
my $collection; # name which will be inserted |
8 |
my $path_add; # add additional info in path |
9 |
my $verbose; |
10 |
|
11 |
#$verbose = 1; |
12 |
|
13 |
my $result = GetOptions( |
14 |
"collection=s" => \$collection, |
15 |
"path=s" => \$path_add, |
16 |
"verbose!" => \$verbose, |
17 |
"debug!" => \$verbose, |
18 |
); |
19 |
|
20 |
my $dir = shift @ARGV || die "usage: $0 [dir]"; |
21 |
|
22 |
my $basedir = $0; |
23 |
$basedir =~ s,/[^/]+$,/,; |
24 |
require "$basedir/filter.pm"; |
25 |
|
26 |
my $pdftotext = which('pdftotext'); |
27 |
|
28 |
select(STDERR); $|=1; |
29 |
select(STDOUT); $|=1; |
30 |
|
31 |
print STDERR "using $pdftotext to convert pdf into html\n" if ($pdftotext && $verbose); |
32 |
|
33 |
find({ wanted => \&file, |
34 |
follow => 1, |
35 |
no_chdir => 1 |
36 |
}, $dir); |
37 |
|
38 |
sub dump_contents($$$) { |
39 |
my ($contents,$mtime,$path) = @_; |
40 |
|
41 |
return if (! $contents); # don't die on empty files |
42 |
|
43 |
use bytes; |
44 |
my $size = length $contents; |
45 |
|
46 |
print STDERR " [$size]" if ($verbose); |
47 |
|
48 |
# Output the document (to swish) |
49 |
print <<EOF; |
50 |
Path-Name: $path |
51 |
Content-Length: $size |
52 |
Last-Mtime: $mtime |
53 |
Document-Type: HTML |
54 |
|
55 |
EOF |
56 |
print $contents; |
57 |
|
58 |
} |
59 |
|
60 |
sub file { |
61 |
|
62 |
my $path = $_; |
63 |
my $contents; |
64 |
|
65 |
if ($pdftotext && -f $path && $path =~ m/\.pdf$/i) { |
66 |
|
67 |
print STDERR "$path {converting}" if ($verbose); |
68 |
|
69 |
open(F,"$pdftotext -htmlmeta \"$path\" - |") || die "can't open $pdftotext with '$path'"; |
70 |
my $html; |
71 |
while(<F>) { |
72 |
# XXX why pdftotext barks if I try to use this is beyond me. |
73 |
#$contents .= $_; |
74 |
|
75 |
$html .= $_; |
76 |
} |
77 |
close(F); |
78 |
|
79 |
my ($pre_html,$pages,$post_html) = ('<html><head><title>$path :: page ##page_nr##</title></head><body><pre>',$html,'</pre></body></html>'); |
80 |
|
81 |
($pre_html,$pages,$post_html) = ($1,$2,$3) if ($html =~ m/^(<html>.+?<pre>)(.+)(<\/pre>.+?)$/si); |
82 |
|
83 |
if ($collection) { |
84 |
$pre_html =~ s/<title>(.+?)<\/title>/<title>$collection :: page ##page_nr##<\/title>/si; |
85 |
} else { |
86 |
$pre_html =~ s/<title>(.+?)<\/title>/<title>$1 :: page ##page_nr##<\/title>/si; |
87 |
} |
88 |
|
89 |
my $page_nr = 1; |
90 |
foreach my $page (split(/\f/s,$pages)) { |
91 |
print STDERR " $page_nr" if ($verbose); |
92 |
my $pre_tmp = $pre_html; |
93 |
$pre_tmp =~ s/##page_nr##/$page_nr<\/title>/s; |
94 |
dump_contents($pre_tmp . $page . $post_html,time(), $path) if ($page !~ m/^\s*$/s); |
95 |
$page_nr++; |
96 |
} |
97 |
|
98 |
} else { |
99 |
|
100 |
return if (! -f $path || ! m/\.html*$/i); |
101 |
|
102 |
# skip index files |
103 |
return if (m/index_[a-z]\.html*/i || m/index_symbol\.html*/i); |
104 |
|
105 |
open(F,"$path") || die "can't open file: $path"; |
106 |
print STDERR "$path" if ($verbose); |
107 |
while(<F>) { |
108 |
$contents .= "$_"; |
109 |
} |
110 |
$contents .= "\n\n"; |
111 |
|
112 |
$contents = filter($contents,$collection); |
113 |
|
114 |
# add optional components to path |
115 |
$path .= " $path_add" if ($path_add); |
116 |
|
117 |
dump_contents($contents,time(), $path); |
118 |
} |
119 |
|
120 |
print STDERR "\n" if ($verbose); |
121 |
# die "zero size content in '$path'" if (! $contents); |
122 |
|
123 |
} |
124 |
|