/usr/bin/webcheckout is in myrepos 1.20141024.
This file is owned by root:root, with mode 0o755.
The actual contents of the file can be viewed below.
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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 | #!/usr/bin/perl
=head1 NAME
webcheckout - check out repositories referenced on a web page
=head1 SYNOPSIS
B<webcheckout> [options] url [destdir]
=head1 DESCRIPTION
B<webcheckout> downloads an url and parses it, looking for version control
repositories referenced by the page. It checks out each repository into
a subdirectory of the current directory, using whatever VCS program is
appropriate for that repository (git, svn, etc).
The information about the repositories is embedded in the web page using
the rel=vcs-* microformat, which is documented at
<http://kitenet.net/~joey/rfc/rel-vcs/>.
If the optional destdir parameter is specified, VCS programs will be asked
to check out repositories into that directory. If there are multiple
repositories to check out, each will be checked out into a separate
subdirectory of the destdir.
=head1 OPTIONS
=over 4
=item -a, --auth
Prefer authenticated repositories. By default, webcheckout will use
anonymous repositories when possible. If you have an account that
allows you to use authenticated repositories, you might want to use this
option.
=item --no-act, -n
Do not actually check anything out, just print out the commands that would
be run to check out the repositories.
=item --quiet, -q
Quiet mode. Do not print out the commands being run. (The VCS commands
may still be noisy however.)
=back
=head1 PREREQUISITES
To use this program you will need lots of VCS programs installed,
obviously. It also depends on the perl LWP and HTML::Parser modules.
If the perl URI module is installed, webcheckout can heuristically guess
what you mean by partial URLs, such as "kitenet.net/~joey"'
=head1 AUTHOR
Copyright 2009 Joey Hess <joey@kitenet.net>
Licensed under the GNU GPL version 2 or higher.
This program is included in myrepos <http://myrepos.branchable.com/>
=cut
use LWP::Simple;
use HTML::Parser;
use Getopt::Long;
use warnings;
use strict;
# What to download.
my $url;
# Controls whether to print what is being done.
my $quiet=0;
# Controls whether to actually check anything out.
my $noact=0;
# Controls whether to perfer repos that use authentication.
my $want_auth=0;
# Controls where to check out to. If not set, the VCS is allowed to
# decide.
my $destdir;
# how to perform checkouts
my %handlers=(
git => sub { doit("git", "clone", shift, $destdir) },
svn => sub { doit("svn", "checkout", shift, $destdir) },
bzr => sub { doit("bzr", "branch", shift, $destdir) },
);
# Regexps matching urls that are used for anonymous
# repository checkouts. The order is significant:
# urls matching earlier in the list are preferred over
# those matching later.
my @anon_urls=(
qr/^git:\/\//i,
qr/^bzr:\/\//i,
qr/^svn:\/\//i,
qr/^http:\/\//i, # generally the worst transport
);
sub getopts {
Getopt::Long::Configure("bundling", "no_permute");
my $result=GetOptions(
"q|quiet" => \$quiet,
"n|noact" => \$noact,
"a|auth", => \$want_auth,
);
if (! $result || @ARGV < 1) {
die "usage: webcheckout [options] url [destdir]\n";
}
$url=shift @ARGV;
$destdir=shift @ARGV;
eval q{use URI::Heuristic};
if (! $@) {
$url=URI::Heuristic::uf_uristr($url);
}
if ($noact) {
$quiet=0;
}
}
sub doit {
my @args=grep { defined } @_;
print join(" ", @args)."\n" unless $quiet;
return 0 if $noact;
return system(@args);
}
# Is repo a better than repo b?
sub better {
my ($a, $b)=@_;
my @anon;
foreach my $r (@anon_urls) {
if ($a->{href} =~ /$r/) {
push @anon, $a;
}
elsif ($b->{href} =~ /$r/) {
push @anon, $b;
}
}
if ($want_auth) {
# Whichever is authed is better.
return 1 if ! @anon || ! grep { $_ eq $a } @anon;
return 0 if ! grep { $_ eq $b } @anon;
# Neither is authed, so the better anon method wins.
return $anon[0] == $a;
}
else {
# Better anon method wins.
return @anon && $anon[0] == $a;
}
}
# Eliminate duplicate repositories from list.
# Duplicate repositories have the same title, or the same href.
sub dedup {
my %seenhref;
my %bytitle;
my @others;
foreach my $repo (@_) {
if (exists $repo->{title} &&
length $repo->{title}) {
if (exists $bytitle{$repo->{title}}) {
my $other=$bytitle{$repo->{title}};
next unless better($repo, $other);
delete $bytitle{$other->{title}}
}
if (! $seenhref{$repo->{href}}++) {
$bytitle{$repo->{title}}=$repo;
}
}
else {
push @others, $repo;
}
}
return values %bytitle, @others;
}
sub parse {
my $page=shift;
my @ret;
my $parser=HTML::Parser->new(api_version => 3);
my $abody=undef;
my $aref=undef;
$parser->handler(start => sub {
my $tagname=shift;
my $attr=shift;
return if ! exists $attr->{href} || ! length $attr->{href};
return if ! exists $attr->{rel} || $attr->{rel} !~ /^vcs-(.+)/i;
$attr->{type}=lc($1);
# need to collect the body of the <a> tag if there is no title
if ($tagname eq "a" && ! exists $attr->{title}) {
$abody="";
$aref=$attr;
}
push @ret, $attr;
}, "tagname, attr");
$parser->handler(text => sub {
if (defined $aref) {
$abody.=join(" ", @_);
}
}, "text");
$parser->handler(end => sub {
my $tagname=shift;
if ($tagname eq "a" && defined $aref) {
$aref->{title}=$abody;
$aref=undef;
$abody=undef;
}
}, "tagname");
$parser->report_tags(qw{link a});
$parser->parse($page);
$parser->eof;
return @ret;
}
getopts();
my $page=get($url);
if (! defined $page) {
die "failed to download $url\n";
}
my @repos=dedup(parse($page));
if (! @repos) {
die "no repositories found on $url\n";
}
#use Data::Dumper;
#print Dumper(\@repos);
#exit;
if (defined $destdir && @repos > 1) {
# create subdirs of $destdir for the multiple repos
if (! $noact) {
mkdir($destdir);
chdir($destdir) || die "failed to chdir to $destdir: $!";
}
$destdir=undef;
}
my $errors=0;
foreach my $repo (@repos) {
my $handler=$handlers{$repo->{type}};
if ($handler) {
if ($handler->($repo->{href}) != 0) {
print STDERR "failed to checkout ".$repo->{href}."\n";
$errors++;
}
}
else {
print STDERR "unknown repository type ".$repo->{type}.
" for ".$repo->{href}."\n";
$errors++;
}
}
exit($errors > 0);
|