1 |
#!/opt/bin/perl |
2 |
# |
3 |
# Usage: dump-dinfo >main.tsv |
4 |
# dump the d-info database to stdout as tab-seperated lines. |
5 |
# find out the rest of the format yourself. |
6 |
# |
7 |
# COPYRIGHT: (c)2003 Marc Lehmann, Paul Bettinger |
8 |
# AUTHORS: Marc A. Lehmann <dinfo@plan9.de>, Paul Bettinger <dinfo@n8geil.de> |
9 |
# LICENSE: This file is licensed under the General Public License (GPL) |
10 |
# http://www.gnu.org/licenses/licenses.html#GPL |
11 |
|
12 |
$PFX = "/opt/dinfo/data"; # the directory where the dinfo datafiles are |
13 |
$VERSION = 0.01; |
14 |
|
15 |
use Compress::Zlib; |
16 |
|
17 |
sub inf($) { |
18 |
my ($inf, $status) = inflateInit -WindowBits => -15; |
19 |
die $status if $status < -1; |
20 |
|
21 |
my ($out, $status) = $inf->inflate ($_[0]); |
22 |
die $status if $status < -1; |
23 |
|
24 |
$out; |
25 |
} |
26 |
|
27 |
sub street_names { |
28 |
my (@res, @idx, $idx); |
29 |
|
30 |
open my $fh_dat, "<", "$PFX/street.dat" |
31 |
or die "$PFX/street.dat: $!"; |
32 |
open my $fh_idx, "<", "$PFX/street.idx" |
33 |
or die "$PFX/street.idx: $!"; |
34 |
|
35 |
push @idx, unpack "x10 V", $idx |
36 |
while 32 == sysread $fh_idx, $idx, 32; |
37 |
push @idx, -s "$PFX/street.dat"; |
38 |
|
39 |
for (0 .. $#idx - 1) { |
40 |
my ($ofs, $end) = ($idx[$_], $idx[$_+1]); |
41 |
|
42 |
sysseek $fh_dat, $ofs, 0 |
43 |
or die "seek_street.dat: $!"; |
44 |
$end - $ofs == sysread $fh_dat, my $buf, $end - $ofs |
45 |
or die "read_street.dat: short read ($!)"; |
46 |
|
47 |
push @res, split /\x00/, inf $buf; |
48 |
} |
49 |
|
50 |
\@res; |
51 |
} |
52 |
|
53 |
sub dump_dinfo { |
54 |
my $street = street_names; |
55 |
my (@idx, $idx); |
56 |
|
57 |
my @cols = qw(name vorname zusatz1 zusatz2 zusatz3 vorwahl nummer strasse hausnr plz ort ortsteil branche); |
58 |
|
59 |
open $_, ">", "data/dump/$_" for @cols; |
60 |
|
61 |
push @$street, ""; |
62 |
|
63 |
open my $fh_idx, "<", "$PFX/main.idx" |
64 |
or die "$PFX/main.dat: $!"; |
65 |
open my $fh_dat, "<", "$PFX/main.dat" |
66 |
or die "$PFX/main.dat: $!"; |
67 |
|
68 |
push @idx, unpack "V", $idx |
69 |
while 24 == sysread $fh_idx, $idx, 24; |
70 |
push @idx, (-s "$PFX/main.dat") - 26; |
71 |
|
72 |
for (0 .. $#idx - 1) { |
73 |
print STDERR "\r$_ ($#idx)"; |
74 |
|
75 |
my ($ofs, $end) = ($idx[$_], $idx[$_+1]); |
76 |
|
77 |
sysseek $fh_dat, $ofs + 26, 0 |
78 |
or die "seek_main.dat: $!"; |
79 |
$end - $ofs == sysread $fh_dat, my $buf, $end - $ofs |
80 |
or die "read_main.dat: short read ($!)"; |
81 |
|
82 |
my @data = map inf $buf, 0 .. 12; |
83 |
|
84 |
$_ = [split /\x00/, $_, -1] for @data[0..5, 7..12]; |
85 |
|
86 |
$data[6] = [ |
87 |
map { $_ < $#$street ? $_ : $#street } |
88 |
map { unpack "V", "$_\x00" } |
89 |
split /(...)/s, $data[6] |
90 |
]; |
91 |
|
92 |
for (0 .. $#{$data[0]} - 1) { |
93 |
print {$cols[0]} $data[0][$_], "\0"; |
94 |
print {$cols[1]} $data[1][$_], "\0"; |
95 |
print {$cols[2]} $data[2][$_], "\0"; |
96 |
print {$cols[3]} $data[3][$_*2+0], "\0"; |
97 |
print {$cols[4]} $data[3][$_*2+1], "\0"; |
98 |
print {$cols[5]} $data[4][$_], "\0"; |
99 |
print {$cols[6]} $data[5][$_], "\0"; |
100 |
print {$cols[7]} $street->[$data[6][$_]], "\0"; |
101 |
print {$cols[8]} $data[7][$_], "\0"; |
102 |
print {$cols[9]} $data[8][$_], "\0"; |
103 |
print {$cols[10]} $data[9][$_], "\0"; |
104 |
print {$cols[11]} $data[10][$_], "\0"; |
105 |
print {$cols[12]} $data[11][$_], "\0"; |
106 |
} |
107 |
} |
108 |
} |
109 |
|
110 |
dump_dinfo; |
111 |
|