#!/usr/bin/perl -w
-# Copyright © 2005-2012 Jamie Zawinski <jwz@jwz.org>
+# Copyright © 2005-2013 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
use bytes;
my $progname = $0; $progname =~ s@.*/@@g;
-my $version = q{ $Revision: 1.27 $ }; $version =~ s/^[^0-9]+([0-9.]+).*$/$1/;
+my $version = q{ $Revision: 1.31 $ }; $version =~ s/^[^0-9]+([0-9.]+).*$/$1/;
my $verbose = 0;
my $http_proxy = undef;
my $text_literal = '';
my $text_file = '';
my $text_program = '';
-my $text_url = 'http://twitter.com/statuses/public_timeline.atom';
+my $text_url = 'http://en.wikipedia.org/w/index.php?title=Special:NewPages&feed=rss';
# Default URL needs to be set and match what's in OSX/XScreenSaverView.m
my $wrap_columns = undef;
# Maps HTML character entities to the corresponding Latin1 characters.
#
my %entity_table = (
- "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',
- "apos" => '\'',
+ "quot" => '"', "amp" => '&', "lt" => '<',
+ "gt" => '>', "nbsp" => " ", "iexcl" => "\xA1",
+ "cent" => "\xA2", "pound" => "\xA3", "curren" => "\xA4",
+ "yen" => "\xA5", "brvbar" => "\xA6", "sect" => "\xA7",
+ "uml" => "\xA8", "copy" => "\xA9", "ordf" => "\xAA",
+ "laquo" => "\xAB", "not" => "\xAC", "shy" => "\xAD",
+ "reg" => "\xAE", "macr" => "\xAF", "deg" => "\xB0",
+ "plusmn" => "\xB1", "sup2" => "\xB2", "sup3" => "\xB3",
+ "acute" => "\xB4", "micro" => "\xB5", "para" => "\xB6",
+ "middot" => "\xB7", "cedil" => "\xB8", "sup1" => "\xB9",
+ "ordm" => "\xBA", "raquo" => "\xBB", "frac14" => "\xBC",
+ "frac12" => "\xBD", "frac34" => "\xBE", "iquest" => "\xBF",
+ "Agrave" => "\xC0", "Aacute" => "\xC1", "Acirc" => "\xC2",
+ "Atilde" => "\xC3", "Auml" => "\xC4", "Aring" => "\xC5",
+ "AElig" => "\xC6", "Ccedil" => "\xC7", "Egrave" => "\xC8",
+ "Eacute" => "\xC9", "Ecirc" => "\xCA", "Euml" => "\xCB",
+ "Igrave" => "\xCC", "Iacute" => "\xCD", "Icirc" => "\xCE",
+ "Iuml" => "\xCF", "ETH" => "\xD0", "Ntilde" => "\xD1",
+ "Ograve" => "\xD2", "Oacute" => "\xD3", "Ocirc" => "\xD4",
+ "Otilde" => "\xD5", "Ouml" => "\xD6", "times" => "\xD7",
+ "Oslash" => "\xD8", "Ugrave" => "\xD9", "Uacute" => "\xDA",
+ "Ucirc" => "\xDB", "Uuml" => "\xDC", "Yacute" => "\xDD",
+ "THORN" => "\xDE", "szlig" => "\xDF", "agrave" => "\xE0",
+ "aacute" => "\xE1", "acirc" => "\xE2", "atilde" => "\xE3",
+ "auml" => "\xE4", "aring" => "\xE5", "aelig" => "\xE6",
+ "ccedil" => "\xE7", "egrave" => "\xE8", "eacute" => "\xE9",
+ "ecirc" => "\xEA", "euml" => "\xEB", "igrave" => "\xEC",
+ "iacute" => "\xED", "icirc" => "\xEE", "iuml" => "\xEF",
+ "eth" => "\xF0", "ntilde" => "\xF1", "ograve" => "\xF2",
+ "oacute" => "\xF3", "ocirc" => "\xF4", "otilde" => "\xF5",
+ "ouml" => "\xF6", "divide" => "\xF7", "oslash" => "\xF8",
+ "ugrave" => "\xF9", "uacute" => "\xFA", "ucirc" => "\xFB",
+ "uuml" => "\xFC", "yacute" => "\xFD", "thorn" => "\xFE",
+ "yuml" => "\xFF", "apos" => "\'",
# HTML 4 entities that do not have 1:1 Latin1 mappings.
- "bull" => "*", "hellip"=> "...", "prime" => "'", "Prime" => "\"",
- "frasl" => "/", "trade" => "[tm]", "larr" => "<-", "rarr" => "->",
- "harr" => "<->", "lArr" => "<=", "rArr" => "=>", "hArr" => "<=>",
- "empty" => "Ø", "minus" => "-", "lowast"=> "*", "sim" => "~",
- "cong" => "=~", "asymp" => "~", "ne" => "!=", "equiv" => "==",
- "le" => "<=", "ge" => ">=", "lang" => "<", "rang" => ">",
- "loz" => "<>", "OElig" => "OE", "oelig" => "oe", "Yuml" => "Y",
- "circ" => "^", "tilde" => "~", "ensp" => " ", "emsp" => " ",
- "thinsp"=> " ", "ndash" => "-", "mdash" => "-", "lsquo" => "`",
- "rsquo" => "'", "sbquo" => "'", "ldquo" => "\"", "rdquo" => "\"",
- "bdquo" => "\"", "lsaquo"=> "<", "rsaquo"=> ">",
+ "bull" => "*", "hellip"=> "...", "prime" => "'", "Prime" => "\"",
+ "frasl" => "/", "trade" => "[tm]", "larr" => "<-", "rarr" => "->",
+ "harr" => "<->", "lArr" => "<=", "rArr" => "=>", "hArr" => "<=>",
+ "empty" => "\xD8", "minus" => "-", "lowast"=> "*", "sim" => "~",
+ "cong" => "=~", "asymp" => "~", "ne" => "!=", "equiv" => "==",
+ "le" => "<=", "ge" => ">=", "lang" => "<", "rang" => ">",
+ "loz" => "<>", "OElig" => "OE", "oelig" => "oe", "Yuml" => "Y",
+ "circ" => "^", "tilde" => "~", "ensp" => " ", "emsp" => " ",
+ "thinsp"=> " ", "ndash" => "-", "mdash" => "-", "lsquo" => "`",
+ "rsquo" => "'", "sbquo" => "'", "ldquo" => "\"", "rdquo" => "\"",
+ "bdquo" => "\"", "lsaquo"=> "<", "rsaquo"=> ">",
);
# Maps certain UTF8 characters (2 or 3 bytes) to the corresponding
# Latin1 characters.
#
my %unicode_latin1_table = (
- "\xC2\xA1" => '¡', "\xC2\xA2" => '¢', "\xC2\xA3" => '£', "\xC2\xA4" => '¤',
- "\xC2\xA5" => '¥', "\xC2\xA6" => '¦', "\xC2\xA7" => '§', "\xC2\xA8" => '¨',
- "\xC2\xA9" => '©', "\xC2\xAA" => 'ª', "\xC2\xAB" => '«', "\xC2\xAC" => '¬',
- "\xC2\xAD" => '', "\xC2\xAE" => '®', "\xC2\xAF" => '¯', "\xC2\xB0" => '°',
- "\xC2\xB1" => '±', "\xC2\xB2" => '²', "\xC2\xB3" => '³', "\xC2\xB4" => '´',
- "\xC2\xB5" => 'µ', "\xC2\xB6" => '¶', "\xC2\xB7" => '·', "\xC2\xB8" => '¸',
- "\xC2\xB9" => '¹', "\xC2\xBA" => 'º', "\xC2\xBB" => '»', "\xC2\xBC" => '¼',
- "\xC2\xBD" => '½', "\xC2\xBE" => '¾', "\xC2\xBF" => '¿', "\xC3\x80" => 'À',
- "\xC3\x81" => 'Á', "\xC3\x82" => 'Â', "\xC3\x83" => 'Ã', "\xC3\x84" => 'Ä',
- "\xC3\x85" => 'Å', "\xC3\x86" => 'Æ', "\xC3\x87" => 'Ç', "\xC3\x88" => 'È',
- "\xC3\x89" => 'É', "\xC3\x8A" => 'Ê', "\xC3\x8B" => 'Ë', "\xC3\x8C" => 'Ì',
- "\xC3\x8D" => 'Í', "\xC3\x8E" => 'Î', "\xC3\x8F" => 'Ï', "\xC3\x90" => 'Ð',
- "\xC3\x91" => 'Ñ', "\xC3\x92" => 'Ò', "\xC3\x93" => 'Ó', "\xC3\x94" => 'Ô',
- "\xC3\x95" => 'Õ', "\xC3\x96" => 'Ö', "\xC3\x97" => '×', "\xC3\x98" => 'Ø',
- "\xC3\x99" => 'Ù', "\xC3\x9A" => 'Ú', "\xC3\x9B" => 'Û', "\xC3\x9C" => 'Ü',
- "\xC3\x9D" => 'Ý', "\xC3\x9E" => 'Þ', "\xC3\x9F" => 'ß', "\xC3\xA0" => 'à',
- "\xC3\xA1" => 'á', "\xC3\xA2" => 'â', "\xC3\xA3" => 'ã', "\xC3\xA4" => 'ä',
- "\xC3\xA5" => 'å', "\xC3\xA6" => 'æ', "\xC3\xA7" => 'ç', "\xC3\xA8" => 'è',
- "\xC3\xA9" => 'é', "\xC3\xAA" => 'ê', "\xC3\xAB" => 'ë', "\xC3\xAC" => 'ì',
- "\xC3\xAD" => 'í', "\xC3\xAE" => 'î', "\xC3\xAF" => 'ï', "\xC3\xB0" => 'ð',
- "\xC3\xB1" => 'ñ', "\xC3\xB2" => 'ò', "\xC3\xB3" => 'ó', "\xC3\xB4" => 'ô',
- "\xC3\xB5" => 'õ', "\xC3\xB6" => 'ö', "\xC3\xB7" => '÷', "\xC3\xB8" => 'ø',
- "\xC3\xB9" => 'ù', "\xC3\xBA" => 'ú', "\xC3\xBB" => 'û', "\xC3\xBC" => 'ü',
- "\xC3\xBD" => 'ý', "\xC3\xBE" => 'þ', "\xC3\xBF" => 'ÿ',
-
- "\xE2\x80\x93" => '--', "\xE2\x80\x94" => '--',
- "\xE2\x80\x98" => '`', "\xE2\x80\x99" => '\'',
- "\xE2\x80\x9C" => "``", "\xE2\x80\x9D" => "''",
- "\xE2\x80\xA6" => '...',
-);
-
+ "\xC2\xA1" => "\xA1", "\xC2\xA2" => "\xA2", "\xC2\xA3" => "\xA3",
+ "\xC2\xA4" => "\xA4", "\xC2\xA5" => "\xA5", "\xC2\xA6" => "\xA6",
+ "\xC2\xA7" => "\xA7", "\xC2\xA8" => "\xA8", "\xC2\xA9" => "\xA9",
+ "\xC2\xAA" => "\xAA", "\xC2\xAB" => "\xAB", "\xC2\xAC" => "\xAC",
+ "\xC2\xAD" => "\xAD", "\xC2\xAE" => "\xAE", "\xC2\xAF" => "\xAF",
+ "\xC2\xB0" => "\xB0", "\xC2\xB1" => "\xB1", "\xC2\xB2" => "\xB2",
+ "\xC2\xB3" => "\xB3", "\xC2\xB4" => "\xB4", "\xC2\xB5" => "\xB5",
+ "\xC2\xB6" => "\xB6", "\xC2\xB7" => "\xB7", "\xC2\xB8" => "\xB8",
+ "\xC2\xB9" => "\xB9", "\xC2\xBA" => "\xBA", "\xC2\xBB" => "\xBB",
+ "\xC2\xBC" => "\xBC", "\xC2\xBD" => "\xBD", "\xC2\xBE" => "\xBE",
+ "\xC2\xBF" => "\xBF", "\xC3\x80" => "\xC0", "\xC3\x81" => "\xC1",
+ "\xC3\x82" => "\xC2", "\xC3\x83" => "\xC3", "\xC3\x84" => "\xC4",
+ "\xC3\x85" => "\xC5", "\xC3\x86" => "\xC6", "\xC3\x87" => "\xC7",
+ "\xC3\x88" => "\xC8", "\xC3\x89" => "\xC9", "\xC3\x8A" => "\xCA",
+ "\xC3\x8B" => "\xCB", "\xC3\x8C" => "\xCC", "\xC3\x8D" => "\xCD",
+ "\xC3\x8E" => "\xCE", "\xC3\x8F" => "\xCF", "\xC3\x90" => "\xD0",
+ "\xC3\x91" => "\xD1", "\xC3\x92" => "\xD2", "\xC3\x93" => "\xD3",
+ "\xC3\x94" => "\xD4", "\xC3\x95" => "\xD5", "\xC3\x96" => "\xD6",
+ "\xC3\x97" => "\xD7", "\xC3\x98" => "\xD8", "\xC3\x99" => "\xD9",
+ "\xC3\x9A" => "\xDA", "\xC3\x9B" => "\xDB", "\xC3\x9C" => "\xDC",
+ "\xC3\x9D" => "\xDD", "\xC3\x9E" => "\xDE", "\xC3\x9F" => "\xDF",
+ "\xC3\xA0" => "\xE0", "\xC3\xA1" => "\xE1", "\xC3\xA2" => "\xE2",
+ "\xC3\xA3" => "\xE3", "\xC3\xA4" => "\xE4", "\xC3\xA5" => "\xE5",
+ "\xC3\xA6" => "\xE6", "\xC3\xA7" => "\xE7", "\xC3\xA8" => "\xE8",
+ "\xC3\xA9" => "\xE9", "\xC3\xAA" => "\xEA", "\xC3\xAB" => "\xEB",
+ "\xC3\xAC" => "\xEC", "\xC3\xAD" => "\xED", "\xC3\xAE" => "\xEE",
+ "\xC3\xAF" => "\xEF", "\xC3\xB0" => "\xF0", "\xC3\xB1" => "\xF1",
+ "\xC3\xB2" => "\xF2", "\xC3\xB3" => "\xF3", "\xC3\xB4" => "\xF4",
+ "\xC3\xB5" => "\xF5", "\xC3\xB6" => "\xF6", "\xC3\xB7" => "\xF7",
+ "\xC3\xB8" => "\xF8", "\xC3\xB9" => "\xF9", "\xC3\xBA" => "\xFA",
+ "\xC3\xBB" => "\xFB", "\xC3\xBC" => "\xFC", "\xC3\xBD" => "\xFD",
+ "\xC3\xBE" => "\xFE", "\xC3\xBF" => "\xFF",
+
+ "\xE2\x80\x93" => '--', "\xE2\x80\x94" => '--',
+ "\xE2\x80\x98" => '`', "\xE2\x80\x99" => '\'',
+ "\xE2\x80\x9C" => "``", "\xE2\x80\x9D" => "''",
+ "\xE2\x80\xB2" => "'", "\xE2\x80\xA6" => '...',
+ "\xE2\x86\x90" => ' ← ', "\xE2\x84\xA2" => '™',
+ "\xE2\x80\xA2" => '•', "\xC2\xA0" => ' ', #
+ );
# Convert any HTML entities to Latin1 characters.
#
#
sub de_unicoddle($) {
my ($text) = @_;
- foreach my $key (keys (%unicode_latin1_table)) {
+ foreach my $key (sort { length($b) <=> length($a) }
+ keys (%unicode_latin1_table)) {
my $val = $unicode_latin1_table{$key};
$text =~ s/$key/$val/gs;
}
#
sub get_x11_prefs() {
my $got_any_p = 0;
- local *IN;
- if (open (IN, "<$config_file")) {
+ if (open (my $in, '<', $config_file)) {
print STDERR "$progname: reading $config_file\n" if ($verbose > 1);
- my $body = '';
- while (<IN>) { $body .= $_; }
- close IN;
+ local $/ = undef; # read entire file
+ my $body = <$in>;
+ close $in;
$got_any_p = get_x11_prefs_1 ($body);
} elsif ($verbose > 1) {
$text_file =~ s@^~/@$ENV{HOME}/@s; # allow literal "~/"
- local *IN;
- if (open (IN, "<$text_file")) {
+ if (open (my $in, '<', $text_file)) {
print STDERR "$progname: reading $text_file\n" if ($verbose);
if ($wrap_columns && $wrap_columns > 0) {
# read it, then reformat it.
- my $body = '';
- while (<IN>) { $body .= $_; }
+ local $/ = undef; # read entire file
+ my $body = <$in>;
reformat_text ($body);
} else {
- # stream it
- while (<IN>) {
+ # stream it by lines
+ while (<$in>) {
y/A-Za-z/N-ZA-Mn-za-m/ if ($nyarlathotep_p);
- print $_;
+ print STDOUT $_;
}
}
- close IN;
+ close $in;
} else {
error ("$text_file: $!");
}
s@<[^<>]*>?@@gs; # lose all other HTML tags
$_ = de_entify ($_); # convert HTML entities
+ # For Wikipedia: delete anything inside {{ }} and unwrap [[tags]],
+ # among other things.
+ #
+ if ($rss_p eq 'wiki') {
+
+ # Creation line is often truncated: screws up parsing with unbalanced {{.
+ s@(: +<- +Created page) with [^\n]+@$1@s;
+
+ s@/\*.*?\*/@@si; # /* ... */
+
+ # Try to omit all tables, since they're impossible to read as text.
+ #
+ 1 while (s/{{[^{}]*}}/ /gs); # {{ ... }}
+ 1 while (s/{\|.*?\|}/\n\n/gs); # {| ... |}
+ 1 while (s/\|-.*?\|/ /gs); # |- ... | (table cell)
+
+ # Convert anchors to something more readable.
+ #
+ s/\[\[([^\[\]\|]+)\|([^\[\]]+)\]\]/$2/gs; # [[link|anchor]]
+ s/\[\[([^:\[\]\|]+)\]\]/$1/gs; # [[anchor]]
+ s/\[https?:[^\[\]\s]+\s+([^\[\]]+)\]/$1/gs; # [url anchor]
+
+ # Convert all references to asterisks.
+ s@\s*<ref>\s*.*?</ref>@*@gs; # <ref> ... <ref> -> "*"
+ s@\n[ \t]*\d+\s*\^\s*http[^\s]+[ \t]*\n@\n@gs; # 1 ^ URL (a Reflist)
+
+ s@\[\[File:([^\|\]]+).*?\]\]@\n$1\n@gs; # [[File: X | ... ]]
+ s@\[\[Category:.*?\]\]@@gs; # omit categories
+
+ s/<[^<>]*>//gs; # Omit all remaining tags
+ s/\'{3,}//gs; # Omit ''' and ''''
+ s/\'\'/\"/gs; # '' -> "
+ s/\`\`/\"/gs; # `` -> "
+ s/\"\"+/\"/gs; # "" -> "
+
+ s/^[ \t]*[*#]+[ \t]*$//gm; # Omit lines with just * or # on them
+
+ # Omit trailing headlines with no text after them (e.g. == Notes ==)
+ 1 while (s/\n==+[ \t]*[^\n=]+[ \t]*==+\s*$/\n/s);
+ }
+
+
# elide any remaining non-Latin1 binary data...
- s/([\177-\377]+(\s*[\177-\377]+)[^a-z\d]*)/«...» /g;
- #s/([\177-\377]+(\s*[\177-\377]+)[^a-z\d]*)/«$1» /g;
+ s/([^\000-\176]+(\s*[^\000-\176]+)[^a-z\d]*)/\xAB...\xBB /g;
+# s/([^\000-\176]+(\s*[^\000-\176]+)[^a-z\d]*)/\xAB$1\xBB /g;
$_ .= "\n";
if (!defined($wrap_columns) || $wrap_columns > 0) {
$Text::Wrap::columns = ($wrap_columns || 72);
- $_ = wrap ("", " ", $_); # wrap the lines as a paragraph
- s/[ \t]+$//gm; # lose whitespace at end of line again
+ $Text::Wrap::break = '[\s/|]'; # wrap on slashes for URLs
+ $_ = wrap ("", " ", $_); # wrap the lines as a paragraph
+ s/[ \t]+$//gm; # lose whitespace at end of line again
}
s/^\n+//gs;
sub reformat_rss($) {
my ($body) = @_;
+ my $wiki_p = ($body =~ m@<generator>[^<>]*Wiki@si);
+
$body =~ s/(<(ITEM|ENTRY)\b)/\001\001$1/gsi;
my @items = split (/\001\001/, $body);
$title = '' if ($body1 eq $title); # Identical in Twitter's atom feed.
- reformat_html ("$title<P>$body1", 1);
+ reformat_html ("$title<P>$body1", $wiki_p ? 'wiki' : 'rss');
print "\n";
}
}
if ($wrap_columns && $wrap_columns > 0) {
print STDERR "$progname: wrapping at $wrap_columns...\n" if ($verbose > 2);
$Text::Wrap::columns = $wrap_columns;
+ $Text::Wrap::break = '[\s/]'; # wrap on slashes for URLs
$body = wrap ("", "", $body);
$body =~ s/[ \t]+$//gm;
}
# 3) Different behavior than MacOS 10.1 through 10.4; and 4)
# Different behavior than every other Unix in the world.
#
- # See http://jwz.livejournal.com/817438.html, and for those of
- # you inside Apple, "Problem ID 5606018".
+ # See http://jwz.org/b/DHke, and for those of you inside Apple,
+ # "Problem ID 5606018".
#
# One workaround would be to rewrite the savers to have an
# internal buffer, and always read as much data as possible as