#!/usr/bin/env ruby
# -*- coding: utf-8 -*-

$: << File.join(File.dirname(__FILE__))
$: << File.join(File.dirname(__FILE__), '..', 'lib')

$DEBUG_MODE = false
SHAREDIR = File.join(File.dirname(__FILE__), '..', 'share')
DOCDIR = File.join(File.dirname(__FILE__), '..', 'doc')

require 'wp2txt'
require 'wp2txt/utils'
require 'wp2txt/version'
require 'trollop'

include Wp2txt

opts = Trollop::options do
	version Wp2txt::VERSION
	banner <<-EOS
WP2TXT extracts plain text data from Wikipedia dump file (encoded in XML/compressed with Bzip2) stripping all the MediaWiki markups and other metadata.

Usage: wp2txt [options]
where [options] are:
EOS

  opt :input_file,  "Wikipedia dump file with .bz2 (compressed) or .txt (uncompressed) format", :required => true
  opt :output_dir,  "Output directory", :default => Dir::pwd, :type => String
  opt :convert,     "Output in plain text (converting from XML)", :default => true
  opt :list,    "Show list items in output", :default => true
  opt :heading, "Show section titles in output", :default => true, :short => "-d"
  opt :title,   "Show page titles in output", :default => true
  opt :table,   "Show table source code in output", :default => false
  opt :template, "leave inline template notations unmodified", :default => false
  opt :redirect, "Show redirect destination", :default => false
  opt :marker, "Show symbols prefixed to list items, definitions, etc.", :default => true
  opt :category, "Show article category information", :default => false
  opt :file_size,   "Approximate size (in MB) of each output file", :default => 10
  opt :limit_recur, "Max number of recursive call (0 to 10)", :default => 10
end
Trollop::die :size, "must be larger than 0" unless opts[:file_size] >= 0
Trollop::die :output_dir, "must exist" unless File.exist?(opts[:output_dir])
Trollop::die :limit_recur, "must be 10 or smaller" if opts[:limit_recur] > 10

input_file = ARGV[0]
output_dir = opts[:output_dir]
tfile_size = opts[:file_size]
limit_recur = opts[:limit_recur]
convert = opts[:convert]
strip_tmarker = opts[:marker] ? false : true
opt_array = [:title, :list, :heading, :table, :redirect]
$leave_template = true if opts[:template]
config = {}
opt_array.each do |opt|
  config[opt] = opts[opt]
end

parent = Wp2txt::CmdProgbar.new
wpconv = Wp2txt::Runner.new(parent, input_file, output_dir, tfile_size, convert, strip_tmarker, limit_recur)

wpconv.extract_text do |article|
  format_wiki!(article.title)
  title = "[[#{article.title}]]\n"

  if opts[:category] && !article.categories.empty?
    contents = "\nCATEGORIES: "
    contents << article.categories.join(", ")
    contents << "\n\n"
  else
    contents = ""
  end

  article.elements.each do |e|
    case e.first
    when :mw_heading
      next if !config[:heading]
      format_wiki!(e.last)
      line = e.last
      line << "+HEADING+" if $DEBUG_MODE
    when :mw_paragraph
      # next if !config[:paragraph]
      format_wiki!(e.last)
      line = e.last
      line << "+PARAGRAPH+" if $DEBUG_MODE
    when :mw_table, :mw_htable
      next if !config[:table]
      format_wiki!(e.last)
      line = e.last
      line << "+TABLE+" if $DEBUG_MODE
    when :mw_pre
      next if !config[:pre]
      line = e.last
      line << "+PRE+" if $DEBUG_MODE
    when :mw_quote
      # next if !config[:quote]
      format_wiki!(e.last)
      line = e.last
      line << "+QUOTE+" if $DEBUG_MODE
    when :mw_unordered, :mw_ordered, :mw_definition
      next if !config[:list]
      format_wiki!(e.last)
      line = e.last
      line << "+LIST+" if $DEBUG_MODE
    when :mw_redirect
      next if !config[:redirect]
      format_wiki!(e.last)
      line = e.last
      line << "+REDIRECT+" if $DEBUG_MODE
      line << "\n\n"
    else
      if $DEBUG_MODE
        format_wiki!(e.last)
        line = e.last
        line << "+OTHER+"
      else
        next
      end
    end
    contents << line    
  end

  remove_directive!(contents)
  remove_emphasis!(contents)
  mndash!(contents)
  make_reference!(contents)
  format_ref!(contents)
  remove_hr!(contents)
  remove_tag!(contents)
  special_chr!(contents)

  correct_inline_template!(contents) unless $leave_template
  remove_templates!(contents) unless $leave_template
    
  ##### cleanup #####
  if /\A\s*\z/m =~ contents
    result = ""
  else
    result = config[:title] ? title + "\n" + contents : contents
  end
  result = result.gsub(/\[ref\]\s*\[\/ref\]/m){""}
  result = result.gsub(/\n\n\n+/m){"\n\n"} + "\n"  
end