markdown2inao.pl

#!/usr/bin/env perl

use strict;
use warnings;
use Pod::Usage;

use Text::Markdown 'markdown';
use HTML::TreeBuilder;
use List::Util 'max';

my $infile  = $ARGV[0]
    or pod2usage(-1);

open my $fh, '<', $infile or die $!;
my $text = do { local $/; <$fh> };
close $fh;

my $html = markdown($text);

my $tree = HTML::TreeBuilder->new;
$tree->parse_content(\$html);

my $inao = q[];
my $body = $tree->find('body');
for my $elem ($body->content_list) {
    if ($elem->tag =~ /^h(\d+)/) {
        my $level = $1;

        $inao .= '■' x $level;
        $inao .= $elem->as_trimmed_text;
        $inao .= "\n";
    }
    elsif ($elem->tag eq 'p') {
        my $p = q[];
        for my $inline ($elem->content_list) {
            if (ref $inline eq '') {
                # (注:)は脚注としてあつかう
                $inline =~ s!\(注:(.+?)\)!◆注/◆$1◆/注◆!gs;
                $p .= $inline;
            }
            elsif ($inline->tag eq 'code') {
                $p .= '◆cmd/◆';
                $p .= $inline->as_trimmed_text;
                $p .= '◆/cmd◆';
            }
            elsif ($inline->tag eq 'strong') {
                $p .= '◆b/◆';
                $p .= $inline->as_trimmed_text;
                $p .= '◆/b◆';
            }
            elsif ($inline->tag eq 'em') {
                $p .= '◆i/◆';
                $p .= $inline->as_trimmed_text;
                $p .= '◆/i◆';
            }
        }

        if ($p !~ /^[\s　]+$/) {
            $inao .= "$p\n";
        }
    }
    elsif ($elem->tag eq 'pre') {
        my $code = $elem->find('code');
        my $text = $code->as_text;

        # asciiのみカウント。日本語は目視でがんばる
        my $max = max map { length } grep /^[\x00-\x7f]*$/, split /\r?\n/, $text;
        if ($text =~ /^●/) {
            # キャプション付きリスト63文字まで
            if ($max > 63) {
                warn "リストは63文字まで！(現在$max使用):\n$text\n\n";
            }
        }
        else {
            # 本文埋め込みは、特集の場合55文字まで、連載の場合58文字まで
            if ($max > 55) {
                warn "本文埋め込みリストは55文字まで！(現在$max使用):\n$text\n\n";
            }
        }

        $inao .= "◆list/◆\n";
        $inao .= $text;
        $inao .= "◆/list◆\n";
    }
    elsif ($elem->tag eq 'ul') {
        for my $list ($elem->find('li')) {
            $inao .= '・' . $list->as_trimmed_text . "\n";
        }
    }
    elsif ($elem->tag eq 'ol') {
        my $i = 0;
        for my $list ($elem->find('li')) {
            $inao .= '(' . ++$i .')' . $list->as_trimmed_text . "\n";
        }
    }
    elsif ($elem->tag eq 'table') {
	$inao .= "◆table/◆\n";
	if ($elem->find('caption')) {
	    $inao .= "●";
	    $inao .= $elem->find('caption')->as_trimmed_text;
	    $inao .= "\n"
	}
	for my $table ($elem->find('tr')) {
	    if ($table->find('th')) {
		$inao .= "◆table-title◆";
		for my $item ($table->find('th')){
		    $inao .= $item->as_trimmed_text;
		    $inao .= "\t";
		}
	    }
	    if ($table->find('td')) {
		for my $item ($table->find('td')){
		    $inao .= $item->as_trimmed_text;
		    $inao .= "\t";
		}
	    }
	    chop($inao);
	    $inao .= "\n"
	}
	$inao .= "◆/table◆\n";
    }
}

print $inao;

__END__

=head1 NAME

markdown2inao.pl - markdown to inao converter

=head1 SYNOPSIS

    markdown2inao.pl input.markdown.txt

=cut