/usr/bin/xscreensaver-getimage-file is in xscreensaver-data 5.36-1ubuntu1.
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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 | #!/usr/bin/perl -w
# Copyright © 2001-2016 Jamie Zawinski <jwz@jwz.org>.
#
# Permission to use, copy, modify, distribute, and sell this software and its
# documentation for any purpose is hereby granted without fee, provided that
# the above copyright notice appear in all copies and that both that
# copyright notice and this permission notice appear in supporting
# documentation. No representations are made about the suitability of this
# software for any purpose. It is provided "as is" without express or
# implied warranty.
#
# This program chooses a random file from under the given directory, and
# prints its name. The file will be an image file whose dimensions are
# larger than a certain minimum size.
#
# If the directory is a URL, it is assumed to be an RSS or Atom feed.
# The images from that feed will be downloaded, cached, and selected from
# at random. The feed will be re-polled periodically, as needed.
#
# The various xscreensaver hacks that manipulate images ("jigsaw", etc.) get
# the image to manipulate by running the "xscreensaver-getimage" program.
#
# Under X11, the "xscreensaver-getimage" program invokes this script,
# depending on the value of the "chooseRandomImages" and "imageDirectory"
# settings in the ~/.xscreensaver file (or .../app-defaults/XScreenSaver).
# The screen savers invoke "xscreensaver-getimage" via utils/grabclient.c,
# which then invokes this script.
#
# Under Cocoa, this script lives inside the .saver bundle, and is invoked
# directly from utils/grabclient.c.
#
# Created: 12-Apr-01.
require 5;
#use diagnostics; # Fails on some MacOS 10.5 systems
use strict;
use POSIX;
use Fcntl;
use Fcntl ':flock'; # import LOCK_* constants
use POSIX ':fcntl_h'; # S_ISDIR was here in Perl 5.6
import Fcntl ':mode' unless defined &S_ISUID; # but it is here in Perl 5.8
# but in Perl 5.10, both of these load, and cause errors!
# So we have to check for S_ISUID instead of S_ISDIR? WTF?
use bytes; # Larry can take Unicode and shove it up his ass sideways.
# Perl 5.8.0 causes us to start getting incomprehensible
# errors about UTF-8 all over the place without this.
use Digest::MD5 qw(md5_base64);
# Some Linux systems don't install LWP by default!
# Only error out if we're actually loading a URL instead of local data.
BEGIN { eval 'use LWP::Simple;' }
my $progname = $0; $progname =~ s@.*/@@g;
my ($version) = ('$Revision: 1.40 $' =~ m/\s(\d[.\d]+)\s/s);
my $verbose = 0;
# Whether to use MacOS X's Spotlight to generate the list of files.
# When set to -1, uses Spotlight if "mdfind" exists.
#
# (In my experience, this isn't actually any faster, and might not find
# everything if your Spotlight index is out of date, which happens often.)
#
my $use_spotlight_p = 0;
# Whether to cache the results of the last run.
#
my $cache_p = 1;
# Regenerate the cache if it is older than this many seconds.
#
my $cache_max_age = 60 * 60 * 3; # 3 hours
# Re-poll RSS/Atom feeds when local copy is older than this many seconds.
#
my $feed_max_age = $cache_max_age;
# This matches files that we are allowed to use as images (case-insensitive.)
# Anything not matching this is ignored. This is so you can point your
# imageDirectory at directory trees that have things other than images in
# them, but it assumes that you gave your images sensible file extensions.
#
my @good_extensions = ('jpg', 'jpeg', 'pjpeg', 'pjpg', 'png', 'gif',
'tif', 'tiff', 'xbm', 'xpm');
my $good_file_re = '\.(' . join("|", @good_extensions) . ')$';
# This matches file extensions that might occur in an image directory,
# and that are never used in the name of a subdirectory. This is an
# optimization that prevents us from having to stat() those files to
# tell whether they are directories or not. (It speeds things up a
# lot. Don't give your directories stupid names.)
#
my @nondir_extensions = ('ai', 'bmp', 'bz2', 'cr2', 'crw', 'db',
'dmg', 'eps', 'gz', 'hqx', 'htm', 'html', 'icns', 'ilbm', 'mov',
'nef', 'pbm', 'pdf', 'pl', 'ppm', 'ps', 'psd', 'sea', 'sh', 'shtml',
'tar', 'tgz', 'thb', 'txt', 'xcf', 'xmp', 'Z', 'zip' );
my $nondir_re = '\.(' . join("|", @nondir_extensions) . ')$';
# JPEG, GIF, and PNG files that are are smaller than this are rejected:
# this is so that you can use an image directory that contains both big
# images and thumbnails, and have it only select the big versions.
#
my $min_image_width = 255;
my $min_image_height = 255;
my @all_files = (); # list of "good" files we've collected
my %seen_inodes; # for breaking recursive symlink loops
# For diagnostic messages:
#
my $dir_count = 1; # number of directories seen
my $stat_count = 0; # number of files/dirs stat'ed
my $skip_count_unstat = 0; # number of files skipped without stat'ing
my $skip_count_stat = 0; # number of files skipped after stat
sub find_all_files($);
sub find_all_files($) {
my ($dir) = @_;
print STDERR "$progname: + reading dir $dir/...\n" if ($verbose > 1);
my $dd;
if (! opendir ($dd, $dir)) {
print STDERR "$progname: couldn't open $dir: $!\n" if ($verbose);
return;
}
my @files = readdir ($dd);
closedir ($dd);
my @dirs = ();
foreach my $file (@files) {
next if ($file =~ m/^\./); # silently ignore dot files/dirs
if ($file =~ m/[~%\#]$/) { # ignore backup files (and dirs...)
$skip_count_unstat++;
print STDERR "$progname: - skip file $file\n" if ($verbose > 1);
}
$file = "$dir/$file";
if ($file =~ m/$good_file_re/io) {
#
# Assume that files ending in .jpg exist and are not directories.
#
push @all_files, $file;
print STDERR "$progname: - found file $file\n" if ($verbose > 1);
} elsif ($file =~ m/$nondir_re/io) {
#
# Assume that files ending in .html are not directories.
#
$skip_count_unstat++;
print STDERR "$progname: -- skip file $file\n" if ($verbose > 1);
} else {
#
# Now we need to stat the file to see if it's a subdirectory.
#
# Note: we could use the trick of checking "nlinks" on the parent
# directory to see if this directory contains any subdirectories,
# but that would exclude any symlinks to directories.
#
my @st = stat($file);
my ($dev,$ino,$mode,$nlink,$uid,$gid,$rdev,$size,
$atime,$mtime,$ctime,$blksize,$blocks) = @st;
$stat_count++;
if ($#st == -1) {
if ($verbose) {
my $ll = readlink $file;
if (defined ($ll)) {
print STDERR "$progname: + dangling symlink: $file -> $ll\n";
} else {
print STDERR "$progname: + unreadable: $file\n";
}
}
next;
}
next if ($seen_inodes{"$dev:$ino"}); # break symlink loops
$seen_inodes{"$dev:$ino"} = 1;
if (S_ISDIR($mode)) {
push @dirs, $file;
$dir_count++;
print STDERR "$progname: + found dir $file\n" if ($verbose > 1);
} else {
$skip_count_stat++;
print STDERR "$progname: + skip file $file\n" if ($verbose > 1);
}
}
}
foreach (@dirs) {
find_all_files ($_);
}
}
sub spotlight_all_files($) {
my ($dir) = @_;
my @terms = ();
# "public.image" matches all (indexed) images, including Photoshop, etc.
# push @terms, "kMDItemContentTypeTree == 'public.image'";
foreach (@good_extensions) {
# kMDItemFSName hits the file system every time: much worse than "find".
# push @terms, "kMDItemFSName == '*.$_'";
# kMDItemDisplayName matches against the name in the Spotlight index,
# but won't find files that (for whatever reason) didn't get indexed.
push @terms, "kMDItemDisplayName == '*.$_'";
}
$dir =~ s@([^-_/a-z\d.,])@\\$1@gsi; # quote for sh
my $cmd = "mdfind -onlyin $dir \"" . join (' || ', @terms) . "\"";
print STDERR "$progname: executing: $cmd\n" if ($verbose > 1);
@all_files = split (/[\r\n]+/, `$cmd`);
}
# If we're using cacheing, read the cache file and return its contents,
# if any. This also holds an exclusive lock on the cache file, which
# has the additional benefit that if two copies of this program are
# running at once, one will wait for the other, instead of both of
# them spanking the same file system at the same time.
#
my $cache_fd = undef;
my $cache_file_name = undef;
my $read_cache_p = 0;
sub read_cache($) {
my ($dir) = @_;
return () unless ($cache_p);
my $dd = "$ENV{HOME}/Library/Caches"; # MacOS location
if (-d $dd) {
$cache_file_name = "$dd/org.jwz.xscreensaver.getimage.cache";
} elsif (-d "$ENV{HOME}/.cache") { # Gnome "FreeDesktop XDG" location
$dd = "$ENV{HOME}/.cache/xscreensaver";
if (! -d $dd) { mkdir ($dd) || error ("mkdir $dd: $!"); }
$cache_file_name = "$dd/xscreensaver-getimage.cache"
} elsif (-d "$ENV{HOME}/tmp") { # If ~/.tmp/ exists, use it.
$cache_file_name = "$ENV{HOME}/tmp/.xscreensaver-getimage.cache";
} else {
$cache_file_name = "$ENV{HOME}/.xscreensaver-getimage.cache";
}
print STDERR "$progname: awaiting lock: $cache_file_name\n"
if ($verbose > 1);
my $file = $cache_file_name;
open ($cache_fd, '+>>', $file) || error ("unable to write $file: $!");
flock ($cache_fd, LOCK_EX) || error ("unable to lock $file: $!");
seek ($cache_fd, 0, 0) || error ("unable to rewind $file: $!");
my $mtime = (stat($cache_fd))[9];
if ($mtime + $cache_max_age < time) {
print STDERR "$progname: cache is too old\n" if ($verbose);
return ();
}
my $odir = <$cache_fd>;
$odir =~ s/[\r\n]+$//s if defined ($odir);
if (!defined ($odir) || ($dir ne $odir)) {
print STDERR "$progname: cache is for $odir, not $dir\n"
if ($verbose && $odir);
return ();
}
my @files = ();
while (<$cache_fd>) {
s/[\r\n]+$//s;
push @files, "$odir/$_";
}
print STDERR "$progname: " . ($#files+1) . " files in cache\n"
if ($verbose);
$read_cache_p = 1;
return @files;
}
sub write_cache($) {
my ($dir) = @_;
return unless ($cache_p);
# If we read the cache, just close it without rewriting it.
# If we didn't read it, then write it now.
if (! $read_cache_p) {
truncate ($cache_fd, 0) ||
error ("unable to truncate $cache_file_name: $!");
seek ($cache_fd, 0, 0) ||
error ("unable to rewind $cache_file_name: $!");
if ($#all_files >= 0) {
print $cache_fd "$dir\n";
foreach (@all_files) {
my $f = $_; # stupid Perl. do this to avoid modifying @all_files!
$f =~ s@^\Q$dir/@@so || die; # remove $dir from front
print $cache_fd "$f\n";
}
}
print STDERR "$progname: cached " . ($#all_files+1) . " files\n"
if ($verbose);
}
flock ($cache_fd, LOCK_UN) ||
error ("unable to unlock $cache_file_name: $!");
close ($cache_fd);
$cache_fd = undef;
}
sub html_unquote($) {
my ($h) = @_;
# This only needs to handle entities that occur in RSS, not full HTML.
my %ent = ( 'amp' => '&', 'lt' => '<', 'gt' => '>',
'quot' => '"', 'apos' => "'" );
$h =~ s/(&(\#)?([[:alpha:]\d]+);?)/
{
my ($o, $c) = ($1, $3);
if (! defined($2)) {
$c = $ent{$c}; # for <
} else {
if ($c =~ m@^x([\dA-F]+)$@si) { # for A
$c = chr(hex($1));
} elsif ($c =~ m@^\d+$@si) { # for A
$c = chr($c);
} else {
$c = undef;
}
}
($c || $o);
}
/gexi;
return $h;
}
# Figure out what the proxy server should be, either from environment
# variables or by parsing the output of the (MacOS) program "scutil",
# which tells us what the system-wide proxy settings are.
#
sub set_proxy($) {
my ($ua) = @_;
my $proxy_data = `scutil --proxy 2>/dev/null`;
foreach my $proto ('http', 'https') {
my ($server) = ($proxy_data =~ m/\b${proto}Proxy\s*:\s*([^\s]+)/si);
my ($port) = ($proxy_data =~ m/\b${proto}Port\s*:\s*([^\s]+)/si);
my ($enable) = ($proxy_data =~ m/\b${proto}Enable\s*:\s*([^\s]+)/si);
if ($server && $enable) {
# Note: this ignores the "ExceptionsList".
my $proto2 = 'http';
$ENV{"${proto}_proxy"} = ("${proto2}://" . $server .
($port ? ":$port" : "") . "/");
print STDERR "$progname: MacOS $proto proxy: " .
$ENV{"${proto}_proxy"} . "\n"
if ($verbose > 2);
}
}
$ua->env_proxy();
}
sub init_lwp() {
if (! defined ($LWP::Simple::ua)) {
error ("\n\n\tPerl is broken. Do this to repair it:\n" .
"\n\tsudo cpan LWP::Simple\n");
}
set_proxy ($LWP::Simple::ua);
}
# Returns a list of the image enclosures in the RSS or Atom feed.
# Elements of the list are references, [ "url", "guid" ].
#
sub parse_feed($);
sub parse_feed($) {
my ($url) = @_;
init_lwp();
$LWP::Simple::ua->agent ("$progname/$version");
$LWP::Simple::ua->timeout (10); # bail sooner than the default of 3 minutes
my $body = (LWP::Simple::get($url) || '');
if ($body !~ m@^<\?xml\s@si) {
# Not an RSS/Atom feed. Try RSS autodiscovery.
# (Great news, everybody: Flickr no longer provides RSS for "Sets",
# only for "Photostreams", and only the first 20 images of those.
# Thanks, assholes.)
error ("null response: $url")
if ($body =~ m/^\s*$/s);
error ("not an RSS or Atom feed, or HTML: $url")
unless ($body =~ m@<(HEAD|BODY|A|IMG)\b@si);
# Find the first <link> with RSS or Atom in it, and use that instead.
$body =~ s@<LINK\s+([^<>]*)>@{
my $p = $1;
if ($p =~ m! \b REL \s* = \s* ['"]? alternate \b!six &&
$p =~ m! \b TYPE \s* = \s* ['"]? application/(atom|rss) !six &&
$p =~ m! \b HREF \s* = \s* ['"] ( [^<>'"]+ ) !six
) {
my $u2 = html_unquote ($1);
if ($u2 =~ m!^/!s) {
my ($h) = ($url =~ m!^([a-z]+://[^/]+)!si);
$u2 = "$h$u2";
}
print STDERR "$progname: found feed: $u2\n"
if ($verbose);
return parse_feed ($u2);
}
'';
}@gsexi;
error ("no RSS or Atom feed for HTML page: $url");
}
$body =~ s@(<ENTRY|<ITEM)@\001$1@gsi;
my @items = split(/\001/, $body);
shift @items;
my @imgs = ();
my %ids;
foreach my $item (@items) {
my $iurl = undef;
my $id = undef;
# First look for <link rel="enclosure" href="...">
#
if (! $iurl) {
$item =~ s!(<LINK[^<>]*>)!{
my $link = $1;
my ($rel) = ($link =~ m/\bREL\s*=\s*[\"\']?([^<>\'\"]+)/si);
my ($type) = ($link =~ m/\bTYPE\s*=\s*[\"\']?([^<>\'\"]+)/si);
my ($href) = ($link =~ m/\bHREF\s*=\s*[\"\']([^<>\'\"]+)/si);
if ($rel && lc($rel) eq 'enclosure') {
if ($type) {
$href = undef unless ($type =~ m@^image/@si); # omit videos
}
$iurl = html_unquote($href) if $href;
}
$link;
}!gsexi;
}
# Then look for <media:content url="...">
#
if (! $iurl) {
$item =~ s!(<MEDIA:CONTENT[^<>]*>)!{
my $link = $1;
my ($href) = ($link =~ m/\bURL\s*=\s*[\"\']([^<>\'\"]+)/si);
$iurl = html_unquote($href) if $href;
$link;
}!gsexi;
}
# Then look for <enclosure url="..."/>
#
if (! $iurl) {
$item =~ s!(<ENCLOSURE[^<>]*>)!{
my $link = $1;
my ($type) = ($link =~ m/\bTYPE\s*=\s*[\"\']?([^<>\'\"]+)/si);
my ($href) = ($link =~ m/\bURL\s*=\s*[\"\']([^<>\'\"]+)/si);
$iurl = html_unquote($href)
if ($href && $type && $type =~ m@^image/@si); # omit videos
$link;
}!gsexi;
}
# Ok, maybe there's an image in the <url> field?
#
if (! $iurl) {
$item =~ s!((<URL\b[^<>]*>)([^<>]*))!{
my ($all, $u2) = ($1, $3);
$iurl = html_unquote($u2) if ($u2 =~ m/$good_file_re/io);
$all;
}!gsexi;
}
# Then look for <description>... with an <img src="..."> inside.
#
if (! $iurl) {
$item =~ s!(<description[^<>]*>.*?</description>)!{
my $desc = $1;
$desc = html_unquote($desc);
my ($href) = ($desc =~ m@<IMG[^<>]*\bSRC=[\"\']?([^\"\'<>]+)@si);
$iurl = $href if ($href);
$desc;
}!gsexi;
}
# Could also do <content:encoded>, but the above probably covers all
# of the real-world possibilities.
# Find a unique ID for this image, to defeat image farms.
# First look for <id>...</id>
($id) = ($item =~ m!<ID\b[^<>]*>\s*([^<>]+?)\s*</ID>!si) unless $id;
# Then look for <guid isPermaLink=...> ... </guid>
($id) = ($item =~ m!<GUID\b[^<>]*>\s*([^<>]+?)\s*</GUID>!si) unless $id;
# Then look for <link> ... </link>
($id) = ($item =~ m!<LINK\b[^<>]*>\s*([^<>]+?)\s*</LINK>!si) unless $id;
if ($iurl) {
$id = $iurl unless $id;
my $o = $ids{$id};
if (! $o) {
$ids{$id} = $iurl;
my @P = ($iurl, $id);
push @imgs, \@P;
} elsif ($iurl ne $o) {
print STDERR "$progname: WARNING: dup ID \"$id\"" .
" for \"$o\" and \"$iurl\"\n";
}
}
}
return @imgs;
}
# Like md5_base64 but uses filename-safe characters.
#
sub md5_file($) {
my ($s) = @_;
$s = md5_base64($s);
$s =~ s@[/]@_@gs;
$s =~ s@[+]@-@gs;
return $s;
}
# Given the URL of an image, download it into the given directory
# and return the file name.
#
sub download_image($$$) {
my ($url, $uid, $dir) = @_;
my $url2 = $url;
$url2 =~ s/\#.*$//s; # Omit search terms after file extension
$url2 =~ s/\?.*$//s;
my ($ext) = ($url2 =~ m@\.([a-z\d]+)$@si);
# If the feed hasn't put a sane extension on their URLs, nothing's going
# to work. This code assumes that file names have extensions, even the
# ones in the cache directory.
#
if (! $ext) {
print STDERR "$progname: skipping extensionless URL: $url\n"
if ($verbose > 1);
return undef;
}
# Don't bother downloading files that we will reject anyway.
#
if (! ($url2 =~ m/$good_file_re/io)) {
print STDERR "$progname: skipping non-image URL: $url\n"
if ($verbose > 1);
return undef;
}
my $file = md5_file ($uid);
$file .= '.' . lc($ext) if $ext;
# Don't bother doing If-Modified-Since to see if the URL has changed.
# If we have already downloaded it, assume it's good.
if (-f "$dir/$file") {
print STDERR "$progname: exists: $dir/$file for $uid / $url\n"
if ($verbose > 1);
return $file;
}
# Special-case kludge for Flickr:
# Their RSS feeds sometimes include only the small versions of the images.
# So if the URL ends in one of the "small-size" letters, change it to "b".
#
# _o orig, 1600 +
# _k large, 2048 max
# _h large, 1600 max
# _b large, 1024 max
# _c medium, 800 max
# _z medium, 640 max
# "" medium, 500 max
# _n small, 320 max
# _m small, 240 max
# _t thumb, 100 max
# _q square, 150x150
# _s square, 75x75
#
$url =~ s@_[sqtmnzc](\.[a-z]+)$@_b$1@si
if ($url =~ m@^https?://[^/?#&]*?flickr\.com/@si);
print STDERR "$progname: downloading: $dir/$file for $uid / $url\n"
if ($verbose > 1);
init_lwp();
$LWP::Simple::ua->agent ("$progname/$version");
my $status = LWP::Simple::mirror ($url, "$dir/$file");
if (!LWP::Simple::is_success ($status)) {
print STDERR "$progname: error $status: $url\n"; # keep going
}
return $file;
}
sub mirror_feed($) {
my ($url) = @_;
if ($url !~ m/^https?:/si) { # not a URL: local directory.
return (undef, $url);
}
my $dir = "$ENV{HOME}/Library/Caches"; # MacOS location
if (-d $dir) {
$dir = "$dir/org.jwz.xscreensaver.feeds";
} elsif (-d "$ENV{HOME}/.cache") { # Gnome "FreeDesktop XDG" location
$dir = "$ENV{HOME}/.cache/xscreensaver";
if (! -d $dir) { mkdir ($dir) || error ("mkdir $dir: $!"); }
$dir .= "/feeds";
if (! -d $dir) { mkdir ($dir) || error ("mkdir $dir: $!"); }
} elsif (-d "$ENV{HOME}/tmp") { # If ~/.tmp/ exists, use it.
$dir = "$ENV{HOME}/tmp/.xscreensaver-feeds";
} else {
$dir = "$ENV{HOME}/.xscreensaver-feeds";
}
if (! -d $dir) {
mkdir ($dir) || error ("mkdir $dir: $!");
print STDERR "$progname: mkdir $dir/\n" if ($verbose);
}
# MD5 for directory name to use for cache of a feed URL.
$dir .= '/' . md5_file ($url);
if (! -d $dir) {
mkdir ($dir) || error ("mkdir $dir: $!");
print STDERR "$progname: mkdir $dir/ for $url\n" if ($verbose);
}
# At this point, we have the directory corresponding to this URL.
# Now check to see if the files in it are up to date, and download
# them if not.
my $stamp = '.timestamp';
my $lock = "$dir/$stamp";
print STDERR "$progname: awaiting lock: $lock\n"
if ($verbose > 1);
my $mtime = ((stat($lock))[9]) || 0;
my $lock_fd;
open ($lock_fd, '+>>', $lock) || error ("unable to write $lock: $!");
flock ($lock_fd, LOCK_EX) || error ("unable to lock $lock: $!");
seek ($lock_fd, 0, 0) || error ("unable to rewind $lock: $!");
my $poll_p = ($mtime + $feed_max_age < time);
# --no-cache cmd line arg means poll again right now.
$poll_p = 1 unless ($cache_p);
# Even if the cache is young, make sure there is at least one file,
# and re-check if not.
#
if (! $poll_p) {
my $count = 0;
opendir (my $dirh, $dir) || error ("$dir: $!");
foreach my $f (readdir ($dirh)) {
next if ($f =~ m/^\./s);
$count++;
last;
}
closedir $dirh;
if ($count <= 0) {
print STDERR "$progname: no files in cache of $url\n" if ($verbose);
$poll_p = 1;
}
}
if ($poll_p) {
print STDERR "$progname: loading $url\n" if ($verbose);
my %files;
opendir (my $dirh, $dir) || error ("$dir: $!");
foreach my $f (readdir ($dirh)) {
next if ($f eq '.' || $f eq '..');
$files{$f} = 0; # 0 means "file exists, should be deleted"
}
closedir $dirh;
$files{$stamp} = 1;
# Download each image currently in the feed.
#
my $count = 0;
my @urls = parse_feed ($url);
print STDERR "$progname: " . ($#urls + 1) . " images\n"
if ($verbose > 1);
foreach my $p (@urls) {
my ($furl, $id) = @$p;
my $f = download_image ($furl, $id, $dir);
next unless $f;
$files{$f} = 1; # Got it, don't delete
$count++;
}
my $empty_p = ($count <= 0);
# Now delete any files that are no longer in the feed.
# But if there was nothing in the feed (network failure?)
# then don't blow away the old files.
#
my $kept = 0;
foreach my $f (keys(%files)) {
if ($count <= 0) {
$kept++;
} elsif ($files{$f}) {
$kept++;
} else {
if (unlink ("$dir/$f")) {
print STDERR "$progname: rm $dir/$f\n" if ($verbose > 1);
} else {
print STDERR "$progname: rm $dir/$f: $!\n"; # don't bail
}
}
}
# Both feed and cache are empty. No files at all. Bail.
error ("empty feed: $url") if ($kept <= 1);
# Feed is empty, but we have some files from last time. Warn.
print STDERR "$progname: empty feed: using cache: $url\n"
if ($empty_p);
$mtime = time(); # update the timestamp
} else {
# Not yet time to re-check the URL.
print STDERR "$progname: using cache: $url\n" if ($verbose);
}
# Unlock and update the write date on the .timestamp file.
#
truncate ($lock_fd, 0) || error ("unable to truncate $lock: $!");
seek ($lock_fd, 0, 0) || error ("unable to rewind $lock: $!");
utime ($mtime, $mtime, $lock_fd) || error ("unable to touch $lock: $!");
flock ($lock_fd, LOCK_UN) || error ("unable to unlock $lock: $!");
close ($lock_fd);
$lock_fd = undef;
print STDERR "$progname: unlocked $lock\n" if ($verbose > 1);
# Don't bother using the imageDirectory cache. We know that this directory
# is flat, and we can assume that an RSS feed doesn't contain 100,000 images
# like ~/Pictures/ might.
#
$cache_p = 0;
# Return the URL and directory name of the files of that URL's local cache.
#
return ($url, $dir);
}
sub find_random_file($) {
my ($dir) = @_;
if ($use_spotlight_p == -1) {
$use_spotlight_p = 0;
if (-x '/usr/bin/mdfind') {
$use_spotlight_p = 1;
}
}
my $url;
($url, $dir) = mirror_feed ($dir);
if ($url) {
$use_spotlight_p = 0;
print STDERR "$progname: $dir is cache for $url\n" if ($verbose > 1);
}
@all_files = read_cache ($dir);
if ($#all_files >= 0) {
# got it from the cache...
} elsif ($use_spotlight_p) {
print STDERR "$progname: spotlighting $dir...\n" if ($verbose);
spotlight_all_files ($dir);
print STDERR "$progname: found " . ($#all_files+1) .
" file" . ($#all_files == 0 ? "" : "s") .
" via Spotlight\n"
if ($verbose);
} else {
print STDERR "$progname: recursively reading $dir...\n" if ($verbose);
find_all_files ($dir);
print STDERR "$progname: " .
"f=" . ($#all_files+1) . "; " .
"d=$dir_count; " .
"s=$stat_count; " .
"skip=${skip_count_unstat}+$skip_count_stat=" .
($skip_count_unstat + $skip_count_stat) .
".\n"
if ($verbose);
}
write_cache ($dir);
if ($#all_files < 0) {
print STDERR "$progname: no files in $dir\n";
exit 1;
}
my $max_tries = 50;
for (my $i = 0; $i < $max_tries; $i++) {
# Default to random image
my $n = int (rand ($#all_files + 1));
# But check if the user wants a sequential image
if (open(IN, "<$ENV{HOME}/.xscreensaver-image-index")) {
read(IN, $n, 8);
close(IN);
$n++;
if (open (IN, ">$ENV{HOME}/.xscreensaver-image-index")) {
print(IN $n--);
close(IN);
}
}
my $file = $all_files[$n];
if (large_enough_p ($file)) {
if (! $url) {
$file =~ s@^\Q$dir/@@so || die; # remove $dir from front
}
return $file;
}
}
print STDERR "$progname: no suitable images in $dir " .
"(after $max_tries tries)\n";
# If we got here, blow away the cache. Maybe it's stale.
unlink $cache_file_name if $cache_file_name;
exit 1;
}
sub large_enough_p($) {
my ($file) = @_;
my ($w, $h) = image_file_size ($file);
if (!defined ($h)) {
# Nonexistent files are obviously too small!
# Already printed $verbose message about the file not existing.
return 0 unless -f $file;
print STDERR "$progname: $file: unable to determine image size\n"
if ($verbose);
# Assume that unknown files are of good sizes: this will happen if
# they matched $good_file_re, but we don't have code to parse them.
# (This will also happen if the file is junk...)
return 1;
}
if ($w < $min_image_width || $h < $min_image_height) {
print STDERR "$progname: $file: too small ($w x $h)\n" if ($verbose);
return 0;
}
print STDERR "$progname: $file: $w x $h\n" if ($verbose);
return 1;
}
# Given the raw body of a GIF document, returns the dimensions of the image.
#
sub gif_size($) {
my ($body) = @_;
my $type = substr($body, 0, 6);
my $s;
return () unless ($type =~ /GIF8[7,9]a/);
$s = substr ($body, 6, 10);
my ($a,$b,$c,$d) = unpack ("C"x4, $s);
return (($b<<8|$a), ($d<<8|$c));
}
# Given the raw body of a JPEG document, returns the dimensions of the image.
#
sub jpeg_size($) {
my ($body) = @_;
my $i = 0;
my $L = length($body);
my $c1 = substr($body, $i, 1); $i++;
my $c2 = substr($body, $i, 1); $i++;
return () unless (ord($c1) == 0xFF && ord($c2) == 0xD8);
my $ch = "0";
while (ord($ch) != 0xDA && $i < $L) {
# Find next marker, beginning with 0xFF.
while (ord($ch) != 0xFF) {
return () if (length($body) <= $i);
$ch = substr($body, $i, 1); $i++;
}
# markers can be padded with any number of 0xFF.
while (ord($ch) == 0xFF) {
return () if (length($body) <= $i);
$ch = substr($body, $i, 1); $i++;
}
# $ch contains the value of the marker.
my $marker = ord($ch);
if (($marker >= 0xC0) &&
($marker <= 0xCF) &&
($marker != 0xC4) &&
($marker != 0xCC)) { # it's a SOFn marker
$i += 3;
return () if (length($body) <= $i);
my $s = substr($body, $i, 4); $i += 4;
my ($a,$b,$c,$d) = unpack("C"x4, $s);
return (($c<<8|$d), ($a<<8|$b));
} else {
# We must skip variables, since FFs in variable names aren't
# valid JPEG markers.
return () if (length($body) <= $i);
my $s = substr($body, $i, 2); $i += 2;
my ($c1, $c2) = unpack ("C"x2, $s);
my $length = ($c1 << 8) | $c2;
return () if ($length < 2);
$i += $length-2;
}
}
return ();
}
# Given the raw body of a PNG document, returns the dimensions of the image.
#
sub png_size($) {
my ($body) = @_;
return () unless ($body =~ m/^\211PNG\r/s);
my ($bits) = ($body =~ m/^.{12}(.{12})/s);
return () unless defined ($bits);
return () unless ($bits =~ /^IHDR/);
my ($ign, $w, $h) = unpack("a4N2", $bits);
return ($w, $h);
}
# Given the raw body of a GIF, JPEG, or PNG document, returns the dimensions
# of the image.
#
sub image_size($) {
my ($body) = @_;
return () if (length($body) < 10);
my ($w, $h) = gif_size ($body);
if ($w && $h) { return ($w, $h); }
($w, $h) = jpeg_size ($body);
if ($w && $h) { return ($w, $h); }
# #### TODO: need image parsers for TIFF, XPM, XBM.
return png_size ($body);
}
# Returns the dimensions of the image file.
#
sub image_file_size($) {
my ($file) = @_;
my $in;
if (! open ($in, '<:raw', $file)) {
print STDERR "$progname: $file: $!\n" if ($verbose);
return ();
}
my $body = '';
sysread ($in, $body, 1024 * 50); # The first 50k should be enough.
close $in; # (It's not for certain huge jpegs...
return image_size ($body); # but we know they're huge!)
}
sub error($) {
my ($err) = @_;
print STDERR "$progname: $err\n";
exit 1;
}
sub usage() {
print STDERR "usage: $progname [--verbose] directory-or-feed-url\n\n" .
" Prints the name of a randomly-selected image file. The directory\n" .
" is searched recursively. Images smaller than " .
"${min_image_width}x${min_image_height} are excluded.\n" .
"\n" .
" The directory may also be the URL of an RSS/Atom feed. Enclosed\n" .
" images will be downloaded and cached locally.\n" .
"\n";
exit 1;
}
sub main() {
my $dir = undef;
while ($_ = $ARGV[0]) {
shift @ARGV;
if (m/^--?verbose$/s) { $verbose++; }
elsif (m/^-v+$/s) { $verbose += length($_)-1; }
elsif (m/^--?name$/s) { } # ignored, for compatibility
elsif (m/^--?spotlight$/s) { $use_spotlight_p = 1; }
elsif (m/^--?no-spotlight$/s) { $use_spotlight_p = 0; }
elsif (m/^--?cache$/s) { $cache_p = 1; }
elsif (m/^--?no-?cache$/s) { $cache_p = 0; }
elsif (m/^-./) { usage; }
elsif (!defined($dir)) { $dir = $_; }
else { usage; }
}
usage unless (defined($dir));
$dir =~ s@^feed:@http:@si;
if ($dir =~ m/^https?:/si) {
# ok
} else {
$dir =~ s@^~/@$ENV{HOME}/@s; # allow literal "~/"
$dir =~ s@/+$@@s; # omit trailing /
if (! -d $dir) {
print STDERR "$progname: $dir: not a directory or URL\n";
usage;
}
}
my $file = find_random_file ($dir);
print STDOUT "$file\n";
}
main;
exit 0;
|