1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
|
#!/usr/bin/env perl
# $Id$
# Copyright 2011-2020 Norbert Preining
# This file is licensed under the GNU General Public License version 2
# or any later version.
#
# Write parsable list of active CTAN mirrors; run from tl-update-auto cron.
# Needed input:
# http://ctan.org/mirrors (aka CTAN.sites and README.mirrors)
# rsync://comedy.dante.de/MirMon/mirmon.state
use strict;
$^W = 1;
use Data::Dumper;
my $prg;
my $verbose = 0;
exit (&main ());
sub main {
if (@ARGV != 2 && @ARGV != 3) {
die "Usage: $0 [-v] CTAN_SITES MIRMON_STATE.\n";
}
($prg = $0) =~ s,^.*/,,;
if ($ARGV[0] eq "-v") {
$verbose = 1;
shift @ARGV;
}
my %good_urls = read_mstate($ARGV[1]);
my %ctan_sites = read_readme_mirror($ARGV[0], \%good_urls);
$Data::Dumper::Indent = 1;
$Data::Dumper::Sortkeys = 1; # stable output
print Data::Dumper->Dump([\%ctan_sites], [qw(mirrors)]);
return 0;
}
#
# Return hash of good and bad urls from mirmon state data.
#
sub read_mstate {
my ($mstate) = @_;
my %good_urls;
open (MSTATE, "<$mstate") || die "$0: open($mstate) failed: $!\n";
while (<MSTATE>) {
my ($m, $age, $status_last_probe, $time_last_succesful_probe,
$probe_history, $state_history, $last_probe)
= split (' ');
if ($status_last_probe eq "ok") {
$good_urls{$m} = 1;
#warn "probe ok $m\n";
} else {
#warn "probe not ok $m\n";
$good_urls{$m} = 0;
}
}
close(MSTATE);
die "no good urls found in ctan mirmon: $mstate" if keys %good_urls == 0;
return %good_urls;
}
#
# return hash of CTAN.sites info.
#
sub read_readme_mirror {
my ($ctan_sites,$good_urls_ref) = @_;
my %mirrors;
open (CTAN_SITES,"<$ctan_sites") || die "$0: open($ctan_sites) failed: $!\n";
my ($continent,$country,$mirror);
while (<CTAN_SITES>) {
chomp;
if (m/^ (Africa|Asia|Oceania|Europe|North America|South America)/) {
$continent = $1;
warn "got continent $continent\n" if $verbose;
} elsif (m/^ ([-a-zA-Z0-9.]+) \((.*)\)\s*$/) {
$mirror = $1;
$country = $2;
# make many names a little shorter
$country =~ s/^The //;
warn " got country $country, with mirror $mirror\n" if $verbose;
} elsif (m!^ +URL: (ftp|https?|rsync)://([-a-zA-Z0-9.]+)/([-\w/]*)!) {
next if $1 eq "rsync"; # we can't use rsync, so skip
my $protocol = $1;
my $ppath = "$2/$3";
add_mirror(\%mirrors, $continent, $country, $mirror, $protocol, $ppath,
$good_urls_ref);
} else {
last if /^Please send updates/; # quite at final blurb
warn "$prg: ignored CTAN.sites url: $_\n" if /URL:/;
# some other kind of line, e.g., ==== or blank. Silently Ignore.
}
}
die "no ctan mirrors found in $ctan_sites" if keys %mirrors == 0;
return %mirrors;
}
# Subroutine for read_readme_mirror.
#
sub add_mirror {
my ($mirref,$continent,$country,$mirror,$p,$ppath,$good_urls_ref) = @_;
my $url = "$p://$ppath";
#warn "considering $url ($continent $country)";
if (exists $good_urls_ref->{$url}) {
if ($good_urls_ref->{$url}) {
$mirref->{$continent}{$country}{$url} = 1;
warn "ok: $url\n" if $verbose;
} else {
warn "probe not ok, skipped: $url\n" if $verbose;
}
} else {
# CTAN.sites has many more urls than mirmon, so don't worry about it.
warn "not in mirmon file, skipped: $url\n" if $verbose;
# Also the mirmon file has some old urls that aren't in CTAN.sites,
# so don't worry about that direction either, on occasion.
}
}
|