my $progname = $0; $progname =~ s@.*/@@g;
-my $version = q{ $Revision: 1.125 $ }; $version =~ s/^[^0-9]+([0-9.]+).*$/$1/;
+my $version = q{ $Revision: 1.127 $ }; $version =~ s/^[^0-9]+([0-9.]+).*$/$1/;
my $copyright = "WebCollage $version, Copyright (c) 1999-2005" .
" Jamie Zawinski <jwz\@jwz.org>\n" .
" http://www.jwz.org/webcollage/\n";
);
+# For decoding HTML-encoded character entities to URLs.
+#
+my %entity_table = (
+ "apos" => '\'',
+ "quot" => '"', "amp" => '&', "lt" => '<', "gt" => '>',
+ "nbsp" => ' ', "iexcl" => '¡', "cent" => '¢', "pound" => '£',
+ "curren" => '¤', "yen" => '¥', "brvbar" => '¦', "sect" => '§',
+ "uml" => '¨', "copy" => '©', "ordf" => 'ª', "laquo" => '«',
+ "not" => '¬', "shy" => '', "reg" => '®', "macr" => '¯',
+ "deg" => '°', "plusmn" => '±', "sup2" => '²', "sup3" => '³',
+ "acute" => '´', "micro" => 'µ', "para" => '¶', "middot" => '·',
+ "cedil" => '¸', "sup1" => '¹', "ordm" => 'º', "raquo" => '»',
+ "frac14" => '¼', "frac12" => '½', "frac34" => '¾', "iquest" => '¿',
+ "Agrave" => 'À', "Aacute" => 'Á', "Acirc" => 'Â', "Atilde" => 'Ã',
+ "Auml" => 'Ä', "Aring" => 'Å', "AElig" => 'Æ', "Ccedil" => 'Ç',
+ "Egrave" => 'È', "Eacute" => 'É', "Ecirc" => 'Ê', "Euml" => 'Ë',
+ "Igrave" => 'Ì', "Iacute" => 'Í', "Icirc" => 'Î', "Iuml" => 'Ï',
+ "ETH" => 'Ð', "Ntilde" => 'Ñ', "Ograve" => 'Ò', "Oacute" => 'Ó',
+ "Ocirc" => 'Ô', "Otilde" => 'Õ', "Ouml" => 'Ö', "times" => '×',
+ "Oslash" => 'Ø', "Ugrave" => 'Ù', "Uacute" => 'Ú', "Ucirc" => 'Û',
+ "Uuml" => 'Ü', "Yacute" => 'Ý', "THORN" => 'Þ', "szlig" => 'ß',
+ "agrave" => 'à', "aacute" => 'á', "acirc" => 'â', "atilde" => 'ã',
+ "auml" => 'ä', "aring" => 'å', "aelig" => 'æ', "ccedil" => 'ç',
+ "egrave" => 'è', "eacute" => 'é', "ecirc" => 'ê', "euml" => 'ë',
+ "igrave" => 'ì', "iacute" => 'í', "icirc" => 'î', "iuml" => 'ï',
+ "eth" => 'ð', "ntilde" => 'ñ', "ograve" => 'ò', "oacute" => 'ó',
+ "ocirc" => 'ô', "otilde" => 'õ', "ouml" => 'ö', "divide" => '÷',
+ "oslash" => 'ø', "ugrave" => 'ù', "uacute" => 'ú', "ucirc" => 'û',
+ "uuml" => 'ü', "yacute" => 'ý', "thorn" => 'þ', "yuml" => 'ÿ',
+ "ndash" => '-', "mdash" => "--"
+);
+
+
##############################################################################
#
# Various global flags set by command line parameters, or computed
# returns three values: the HTTP response line; the document headers;
# and the document body.
#
-sub get_document_1 {
- my ( $url, $referer, $timeout ) = @_;
+sub get_document_1($$$) {
+ my ($url, $referer, $timeout) = @_;
if (!defined($timeout)) { $timeout = $http_timeout; }
if ($timeout > $http_timeout) { $timeout = $http_timeout; }
# returns two values: the document headers; and the document body.
# if the given URL did a redirect, returns the redirected-to document.
#
-sub get_document {
- my ( $url, $referer, $timeout ) = @_;
+sub get_document($$;$) {
+ my ($url, $referer, $timeout) = @_;
my $start = time;
if (defined($referer) && $referer eq $driftnet_magic) {
# in again, but you have to present the old cookie to get the new cookie.
# So, by doing this, the built-in cypherpunks cookie will never go "stale".
#
-sub set_cookie {
+sub set_cookie($$) {
my ($host, $cookie) = @_;
my $oc = $cookies{$host};
return unless $oc;
# given a URL and the body text at that URL, selects and returns a random
# image from it. returns () if no suitable images found.
#
-sub pick_image_from_body {
- my ( $url, $body ) = @_;
+sub pick_image_from_body($$) {
+ my ($url, $body) = @_;
my $base = $url;
$_ = $url;
############################################################################
-sub pick_dictionary {
+sub pick_dictionary() {
my @dicts = ("/usr/dict/words",
"/usr/share/dict/words",
"/usr/share/lib/dict/words");
# returns a random word from the dictionary
#
-sub random_word {
+sub random_word() {
local *IN;
if (! open (IN, "<$wordlist")) {
}
-sub random_words {
+sub random_words($) {
my ($or_p) = @_;
my $sep = ($or_p ? "%20OR%20" : "%20");
return (random_word . $sep .
}
-sub url_quote {
+sub url_quote($) {
my ($s) = @_;
$s =~ s|([^-a-zA-Z0-9.\@/_\r\n])|sprintf("%%%02X", ord($1))|ge;
return $s;
}
-sub url_unquote {
+sub url_unquote($) {
my ($s) = @_;
$s =~ s/[+]/ /g;
$s =~ s/%([a-z0-9]{2})/chr(hex($1))/ige;
return $s;
}
-sub html_quote {
+sub html_quote($) {
my ($s) = @_;
$s =~ s/&/&/gi;
$s =~ s/</</gi;
return $s;
}
-sub html_unquote {
+sub html_unquote($) {
my ($s) = @_;
- $s =~ s/</</gi; # far from exhaustive...
- $s =~ s/>/</gi;
- $s =~ s/"/\"/gi;
- $s =~ s/&/&/gi;
+ $s =~ s/(&([a-z]+);)/{ $entity_table{$2} || $1; }/gexi; # e.g., '
+ $s =~ s/(&\#(\d+);)/{ chr($2) }/gexi; # e.g., '
return $s;
}
# Note that this list contains all kinds of internal search engine
# junk URLs too -- caller must prune them.
#
-sub pick_from_search_engine {
+sub pick_from_search_engine($$$) {
my ( $timeout, $search_url, $words ) = @_;
$_ = $words;
}
-sub depoison {
+sub depoison(@) {
my (@urls) = @_;
my @urls2 = ();
foreach (@urls) {
# random image from it.
# returns the url of the page loaded; the url of the image chosen.
#
-sub pick_image_from_pages {
+sub pick_image_from_pages($$$$@) {
my ($base, $total_hit_count, $unfiltered_link_count, $timeout, @pages) = @_;
$total_hit_count = "?" unless defined($total_hit_count);
# returns two URLs: the page containing the image, and the image.
# Returns () if nothing found this time.
#
-sub pick_from_yahoo_random_link {
- my ( $timeout ) = @_;
+sub pick_from_yahoo_random_link($) {
+ my ($timeout) = @_;
print STDERR "\n\n" if ($verbose_load);
LOG ($verbose_load, "URL: $yahoo_random_link");
# returns two URLs: the page containing the image, and the image.
# Returns () if nothing found this time.
#
-sub pick_from_alta_vista_random_link {
- my ( $timeout ) = @_;
+sub pick_from_alta_vista_random_link($) {
+ my ($timeout) = @_;
print STDERR "\n\n" if ($verbose_load);
LOG ($verbose_load, "URL: $alta_vista_random_link");
"&q=";
# avimages
-sub pick_from_alta_vista_images {
- my ( $timeout ) = @_;
+sub pick_from_alta_vista_images($) {
+ my ($timeout) = @_;
my $words = random_word();
my $page = (int(rand(9)) + 1);
"&q=";
# googleimgs
-sub pick_from_google_images {
- my ( $timeout, $words, $max_page ) = @_;
+sub pick_from_google_images($;$$) {
+ my ($timeout, $words, $max_page) = @_;
if (!defined($words)) {
$words = random_word; # only one word for Google
# googlenums
-sub pick_from_google_image_numbers {
- my ( $timeout ) = @_;
+sub pick_from_google_image_numbers($) {
+ my ($timeout) = @_;
my $max = 9999;
my $number = int(rand($max));
# googlephotos
-sub pick_from_google_image_photos {
- my ( $timeout ) = @_;
+sub pick_from_google_image_photos($) {
+ my ($timeout) = @_;
my $i = int(rand($#photomakers + 1));
my $fn = $photomakers[$i];
"&aqo=";
# avtext
-sub pick_from_alta_vista_text {
- my ( $timeout ) = @_;
+sub pick_from_alta_vista_text($) {
+ my ($timeout) = @_;
my $words = random_words(0);
my $page = (int(rand(9)) + 1);
"&cobrand=undefined" .
"&query=");
-sub pick_from_hotbot_text {
- my ( $timeout ) = @_;
+sub pick_from_hotbot_text($) {
+ my ($timeout) = @_;
$last_search = $hotbot_search_url; # for warnings
"&tab=web" .
"&query=";
-sub pick_from_lycos_text {
- my ( $timeout ) = @_;
+sub pick_from_lycos_text($) {
+ my ($timeout) = @_;
$last_search = $lycos_search_url; # for warnings
"&p=";
# yahoonews
-sub pick_from_yahoo_news_text {
- my ( $timeout ) = @_;
+sub pick_from_yahoo_news_text($) {
+ my ($timeout) = @_;
$last_search = $yahoo_news_url; # for warnings
my %lj_cache = (); # hash, for detecting dups
# livejournal
-sub pick_from_livejournal_images {
- my ( $timeout ) = @_;
+sub pick_from_livejournal_images($) {
+ my ($timeout) = @_;
$last_search = $livejournal_img_url; # for warnings
my $ircimages_url = "http://ircimages.com/";
# ircimages
-sub pick_from_ircimages {
- my ( $timeout ) = @_;
+sub pick_from_ircimages($) {
+ my ($timeout) = @_;
$last_search = $ircimages_url; # for warnings
# flickr
-sub pick_from_flickr {
- my ( $timeout ) = @_;
+sub pick_from_flickr($) {
+ my ($timeout) = @_;
my $start = 16 * int(rand(100));
############################################################################
# driftnet
-sub pick_from_driftnet {
- my ( $timeout ) = @_;
+sub pick_from_driftnet($) {
+ my ($timeout) = @_;
my $id = $driftnet_magic;
my $dir = $driftnet_dir;
}
-sub get_driftnet_file {
+sub get_driftnet_file($) {
my ($file) = @_;
error ("\$driftnet_dir unset?") unless ($driftnet_dir);
}
-sub spawn_driftnet {
+sub spawn_driftnet($) {
my ($cmd) = @_;
# make a directory to use.
# Returns () if nothing found this time.
#
-sub pick_image {
- my ( $timeout ) = @_;
+sub pick_image(;$) {
+ my ($timeout) = @_;
$current_state = "select";
$load_method = "none";
#
############################################################################
-sub timestr {
+sub timestr() {
return strftime ("%H:%M:%S: ", localtime);
}
-sub blurb {
+sub blurb() {
return "$progname: " . timestr() . "$current_state: ";
}
-sub error {
+sub error($) {
my ($err) = @_;
print STDERR blurb() . "$err\n";
exit 1;
}
-sub stacktrace {
+sub stacktrace() {
my $i = 1;
print STDERR "$progname: stack trace:\n";
while (1) {
my $lastlog = "";
-sub clearlog {
+sub clearlog() {
$lastlog = "";
}
-sub showlog {
+sub showlog() {
my $head = "$progname: DEBUG: ";
foreach (split (/\n/, $lastlog)) {
print STDERR "$head$_\n";
$lastlog = "";
}
-sub LOG {
+sub LOG($$) {
my ($print, $msg) = @_;
my $blurb = timestr() . "$current_state: ";
$lastlog .= "$blurb$msg\n";
my %stats_elapsed;
my $last_state = undef;
-sub record_attempt {
+sub record_attempt($) {
my ($name) = @_;
if ($last_state) {
$suppress_audit = 0;
}
-sub record_success {
+sub record_success($$$) {
my ($name, $url, $base) = @_;
if (defined($stats_successes{$name})) {
$stats_successes{$name}++;
}
-sub record_failure {
+sub record_failure($) {
my ($name) = @_;
return if $image_succeeded;
-sub stats_of {
+sub stats_of($) {
my ($name) = @_;
my $i = $stats_successes{$name};
my $j = $stats_attempts{$name};
my $current_start_time = 0;
-sub start_timer {
+sub start_timer($) {
my ($name) = @_;
$current_start_time = time;
}
}
-sub stop_timer {
+sub stop_timer($$) {
my ($name, $success) = @_;
$stats_elapsed{$name} += time - $current_start_time;
}
my $last_report_time = 0;
-sub report_performance {
+sub report_performance() {
return unless $verbose_warnings;
my @recent_images = ();
my @recent_sites = ();
-sub save_recent_url {
+sub save_recent_url($$) {
my ($url, $base) = @_;
return unless ($verbose_warnings);
# Does %-decoding.
#
-sub url_decode {
+sub url_decode($) {
($_) = @_;
tr/+/ /;
s/%([a-fA-F0-9][a-fA-F0-9])/pack("C", hex($1))/eg;
# Given the raw body of a GIF document, returns the dimensions of the image.
#
-sub gif_size {
+sub gif_size($) {
my ($body) = @_;
my $type = substr($body, 0, 6);
my $s;
# Given the raw body of a JPEG document, returns the dimensions of the image.
#
-sub jpeg_size {
+sub jpeg_size($) {
my ($body) = @_;
my $i = 0;
my $L = length($body);
# Given the raw body of a PNG document, returns the dimensions of the image.
#
-sub png_size {
+sub png_size($) {
my ($body) = @_;
return () unless ($body =~ m/^\211PNG\r/);
my ($bits) = ($body =~ m/^.{12}(.{12})/s);
# Given the raw body of a GIF, JPEG, or PNG document, returns the dimensions
# of the image.
#
-sub image_size {
+sub image_size($) {
my ($body) = @_;
my ($w, $h) = gif_size ($body);
if ($w && $h) { return ($w, $h); }
# returns the full path of the named program, or undef.
#
-sub which {
+sub which($) {
my ($prog) = @_;
foreach (split (/:/, $ENV{PATH})) {
if (-x "$_/$prog") {
# Like rand(), but chooses numbers with a bell curve distribution.
-sub bellrand {
+sub bellrand(;$) {
($_) = @_;
$_ = 1.0 unless defined($_);
$_ /= 3.0;
}
-sub exit_cleanup {
+sub exit_cleanup() {
x_cleanup();
print STDERR "$progname: exiting\n" if ($verbose_warnings);
if (@pids_to_kill) {
}
}
-sub signal_cleanup {
+sub signal_cleanup($) {
my ($sig) = @_;
print STDERR blurb() . (defined($sig)
? "caught signal $sig."
#
##############################################################################
-sub url_only_output {
+sub url_only_output() {
do {
my ($base, $img) = pick_image;
if ($img) {
my $delay = 2;
-sub x_cleanup {
+sub x_cleanup() {
unlink $image_ppm, $image_tmp1, $image_tmp2;
unlink $imagemap_html_tmp, $imagemap_jpg_tmp
if (defined ($imagemap_html_tmp));
# Like system, but prints status about exit codes, and kills this process
# with whatever signal killed the sub-process, if any.
#
-sub nontrapping_system {
+sub nontrapping_system(@) {
$! = 0;
$_ = join(" ", @_);
# writes a PPM to the given output file. Returns the width/height of the
# image if successful.
#
-sub image_to_pnm {
+sub image_to_pnm($$$) {
my ($url, $body, $output) = @_;
my ($cmd, $cmd2, $w, $h);
}
}
-sub pick_root_displayer {
+sub pick_root_displayer() {
my @names = ();
foreach my $cmd (@root_displayers) {
my $ppm_to_root_window_cmd = undef;
-sub x_or_pbm_output {
+sub x_or_pbm_output($) {
my ($window_id) = @_;
# Check for our helper program, to see whether we need to use PPM pipelines.
}
}
-sub paste_image {
+sub paste_image($$$$) {
my ($base, $img, $body, $source) = @_;
$current_state = "paste";
}
-sub update_imagemap {
+sub update_imagemap($$$$$$$$) {
my ($url, $x, $y, $w, $h, $image_ppm, $image_width, $image_height) = @_;
$current_state = "imagemap";
}
-sub init_signals {
+sub init_signals() {
$SIG{HUP} = \&signal_cleanup;
$SIG{INT} = \&signal_cleanup;
END { exit_cleanup(); }
-sub main {
+sub main() {
$| = 1;
srand(time ^ $$);
}
}
-main;
+main();
exit (0);