#!/usr/bin/perl -w

# Blosxom
# Author: Rael Dornfest <rael@oreilly.com>
# Version: 0+5i
# Home/Docs/Licensing: http://www.oreillynet.com/~rael/lang/perl/blosxom/

# --- Configurable variables -----

# What's this blog's title?
my $blog_title = 'Sam Ruby';

# What's this blog's description (for outgoing RSS feed)?
my $blog_description = "It's just data";

# What's this blog's primary language (for outgoing RSS feed)?
my $blog_language = 'en';

# Where are this blog's entries kept?
my $datadir = "/home/rubys/web/intertwingly.net/blosxom/";
my $datadir_current = $datadir;

# Should I stick only to the datadir for items or travel down the
# directory hierarchy looking for items?  If so, to what depth?
# 0 = infinite depth (aka grab everything), 1 = datadir only, n = n levels down
my $depth = 0;

# What should be used as separator in directory paths (the $path variable)?
my $path_separator = '/';

# How many entries should I show on the home page?
my $num_entries = 20;

# --------------------------------

use strict;
use FileHandle;
use File::Find;
use File::stat;
use Lucene;
use CGI qw/:standard :netscape escape/;
use POSIX qw/strftime/;

# Escape <, >, and &, and to produce valid RSS
my %escape = ('<'=>'&lt;', '>'=>'&gt;', '&'=>'&amp;', '"'=>'&quot;');  
my $escape_re  = join '|' => keys %escape;

my $fh = new FileHandle;
my $flavour = "html";

# Bring in the templates
my %template = ();
while (<DATA>) {
	last if /^(__END__)?$/;
	my($ct, $comp, $txt) = /^(\S+)\s(\S+)\s(.*)$/;
	$txt =~ s/\\n/\n/mg;
	$template{$ct}{$comp} = $txt;
}

$template{'html'}{'content_type'}='application/xhtml+xml;charset=iso-8859-1'
  if $ENV{'HTTP_ACCEPT'} =~ /application\/xhtml\+xml/;
$blog_title .= ": Posts by Citation";

chomp(my $content_type = $fh->open("< $datadir_current/content_type.$flavour") || $fh->open("< $datadir/content_type.$flavour") ? <$fh> : ($template{$flavour}{'content_type'} || 'text/plain'));
print header($content_type);

# determine what dates to include
my @files = ();
my $ext = 'txt';
find({ wanted => sub { my $curr_depth = $File::Find::dir =~ tr[/][]; return if $depth and $curr_depth > $depth; /.$ext$/ and push @files, $File::Find::name; }, follow_fast => 1 }, $datadir_current);

# Header
my $head = join '', ($fh->open("< $datadir_current/head.$flavour") || $fh->open("< $datadir/head.$flavour") ? <$fh> : ($template{$flavour}{'head'} || $template{'error'}{'head'}));
$head =~ s/(\$\w+)/$1 . "||''"/gee;
print $head;

my %people;

print "<h2>
Posts by Citation</h2>\n";
foreach my $blog (@files) {
  open FILE, $blog;
  my $title = <FILE>;
  my $entry = join(' ', <FILE>);
  close FILE;

  $entry =~ s/<!--StartFragment -->//g;
  $entry =~ s/&nbsp;/ /msg;
  $entry =~ s/\s+/ /msg;
  $entry =~ s/^<p> ?(.*?) ?<\/p>/\1/;

  (my $cite) = ($entry =~ /^<a href="[^"]*?"> ?([^<]*?)<\/a>:? ?<em>/);
  next unless $cite;
  $cite =~ s/<.*?>//g;
  $cite =~ s/:? *$//;
  $cite =~ s/^ //;

  $cite = lc($cite);
  $cite =~ s/^jon$/jon udell/;
  $cite =~ s/^dave$/dave winer/;
  $cite =~ s/^diveintomark$/mark pilgrim/;
  $cite =~ s/^burningbird$/shelley powers/;
  $cite =~ s/^sanjiva$/sanjiva weerawarana/;
  $cite =~ s/.*decafbad/les orchard/;
  $cite =~ s/l.m.orchard/les orchard/;
  $cite =~ s/ernie.*/ernie svenson/;
  $cite =~ s/\.net guy/brad wilson/;
  $cite =~ s/dotnetguy/brad wilson/;
  $cite =~ s/[^\w\s]//g;

  $people{$cite}++;
}

my @order = sort {$people{$b} <=> $people{$a} or $a cmp $b} keys %people;

my $line = 1;
print "<div class=\"blogbody\">\n";
foreach (@order) {
  (my $url = escape($_)) =~ s/%20/_/g;
  print "<br /><a href=\"$url/\">$_</a> ($people{$_})\n";
  print "<br />\n" if $line++ % 5 == 0;
}
print "</div>\n";

# Foot
my $foot = join '', ($fh->open("< $datadir_current/foot.$flavour") || $fh->open("< $datadir/foot.$flavour") ? <$fh> : ($template{$flavour}{'foot'} || $template{'error'}{'foot'}));
$foot =~ s/(\$\w+)/$1 . "||''"/gee;
while ( $foot =~ s/^(#include "(.*?)")$/$fh->open("$datadir_current\/$2") ? join "",<$fh> : "$1"/gme ) {}
print $foot;

# Default HTML and RSS template bits
__DATA__
html content_type text/html
html head <html><head><link rel="alternate" type="type="application/rss+xml" title="RSS" href="$url/?flav=rss" /><title>$blog_title $pi_da $pi_mo $pi_yr</title></head><body><center><font size="+3">$blog_title</font><br />$pi_da $pi_mo $pi_yr</center><p />
html story <p class="blosxomEntry"><a name="$fn"><span class="blosxomTitle"><b>$title</b></span></a><br /><span class="blosxomBody">$body</span><br /><span class="blosxomTime">Posted at $ti</span> [$path] <a href="$url/$yr/$mo_num/$da#$fn">#</a> <a href="http://www.google.com/search?q=$title">G</a></p>\n
html foot <p /><center><h6>Powered -- for some narrow definition of powered -- by <a href="http://www.oreillynet.com/~rael/lang/perl/blosxom/">Blosxom</a></h6></body></html>
rss content_type text/xml
rss head <?xml version="1.0"?>\n<!-- name="generator" content="bloxsom/0+5i" -->\n<!DOCTYPE rss PUBLIC "-//Netscape Communications//DTD RSS 0.91//EN" "http://my.netscape.com/publish/formats/rss-0.91.dtd">\n\n<rss version="0.91">\n  <channel>\n    <title>$blog_title $pi_da $pi_mo $pi_yr</title>\n    <link>$url/</link>\n    <description>$blog_description</description>\n    <language>$blog_language</language>\n
rss story   <item>\n    <title>$title</title>\n    <link>$url/$yr/$mo_num/$da#$fn</link>\n    <description>$body</description>\n  </item>\n
rss foot   </channel>\n</rss>
error head Error: I'm afraid this is the first I've heard of a "$flavour" flavoured Blosxom.  Try dropping the "/+$flavour" bit from the end of the URL.\n\n
html content_type text/html