#!/usr/bin/perl -w
#
# Since calibre conversion seems to ignore the perfectly valid .ncx file as
# far as splitting chapters properly, this script is designed to add markup
# to the html that mirrors the info in the .ncx file so I can tell the
# converter to recognize the new markup to auto generate the toc. (Sigh...)
#
# One argument is the .ncx file.
#
# This is a total hack - it does no xml parsing, but simply uses text
# matching and assumes the <text> tag always comes before the matching
# <content> tag (cheesy, but easy :-).
#
# When converting, use this XPath to match headers that are chapters,
# and Bob's 'yer Uncle!
#
# //*[(name()='h1' or name()='h2' or name()='h3') and @class = 'chapter']
#
# And to get multi-level chapters right, use these:
#
# //h:h1[re:test(@class, "chapter", "i")]
# //h:h2[re:test(@class, "chapter", "i")]
# //h:h3[re:test(@class, "chapter", "i")]

use strict;
use File::Basename;

my %files;
my %hdrs;

sub read_ncx {
   my $ncxfile = shift;
   my $fh;
   my $indent;
   my $text;
   my $file;
   my $marker;
   local $_;
   open($fh, '<', $ncxfile) || die "Cannot read $ncxfile : $!\n";
   while (<$fh>) {
      last if (/\<navMap\>/);
   }
   while (<$fh>) {
      if (/^(\s*)\<text\>(.*)\<\/text\>/) {
         if (defined($text)) {
            die "Apparently missed a matching content prior to text $2\n";
         }
         $indent = length($1);
         $text = $2;
      } elsif (/\<content\s*src\=\"(.*)\#(.*)\"/) {
         $file = $1;
         if (defined($marker)) {
            die "Apparently missed a matching text prior to marker $2\n";
         }
         $marker = $2;
         my $r;
         my $info;
         if (! exists($files{$file})) {
            $r = {};
            $files{$file} = $r;
         } else {
            $r = $files{$file};
         }
         $hdrs{$indent} = '';
         $info = {};
         $info->{'indent'} = $indent;
         $info->{'text'} = $text;
         $info->{'count'} = 0;
         $r->{$marker} = $info;
         undef($indent);
         undef($marker);
         undef($file);
         undef($text);
      } elsif (/\<\/navMap\>/) {
         last;
      }
   }
   $text = 1;
   foreach $indent (sort { $a <=> $b } (keys(%hdrs))) {
      print "indent $indent assigned header h$text\n";
      $hdrs{$indent} = "h$text";
      ++$text;
   }
}

sub fix_one_file {
   my $file = shift;
   my $newfile = "$file.new";
   my $r = shift;
   my $fh;
   my $oh;
   local $_;
   open($fh, '<', $file) || die "Cannot read $file : $!\n";
   open($oh, '>', $newfile) || die "Cannot write $newfile : $!\n";
   while (<$fh>) {
      if (/^(.*)\<a\s+id\=\"(.+)\"\>\s*\<\/a\>(.*)$/) {
         my $lead = $1;
         my $marker = $2;
         my $trail = $3;
         if (exists($r->{$marker})) {
            my $info = $r->{$marker};
            my $count = $info->{'count'};
            ++$count;
            $info->{'count'} = $count;
            if ($count > 1) {
               print "Hey! $marker is defined more than once!\n";
            } else {
               my $hdr = $hdrs{$info->{'indent'}};
               my $text = $info->{'text'};
               $_ = "${lead}<$hdr class=\"chapter\" title=\"$text\"><a id=\"$marker\"></a></$hdr>$trail\n";
            }
         }
      }
      print $oh $_;
   }
   close($fh);
   close($oh);
   unlink($file);
   rename($newfile, $file);
}

read_ncx($ARGV[0]);
my $file;
foreach $file (sort(keys(%files))) {
   fix_one_file(dirname($ARGV[0]) . "/" . $file, $files{$file});
}
foreach $file (sort(keys(%files))) {
   my $r = $files{$file};
   my $marker;
   foreach $marker (sort(keys(%$r))) {
      my $info = $r->{$marker};
      if ($info->{'count'} == 0) {
         print "Hey! marker $marker inf file $file was never defined!\n";
      }
   }
}