#!/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_off, "Output XML (without converting to plain text)", :default => false
  opt :list_off,    "Exclude list items from output", :default => false
  opt :heading_off, "Exclude section titles from output", :default => false, :short => "-d"
  opt :title_off,   "Exclude page titles from output", :default => false
  opt :table_off,   "Exclude page titles from output", :default => true
  opt :template_off, "Remove template notations from output", :default => true
  opt :redirect_off, "Not show redirect destination", :default => false
  opt :strip_marker, "Remove symbols prefixed to list items, definitions, etc.", :default => false
  opt :category_off, "Not show article category information", :default => false
  opt :file_size,   "Approximate size (in MB) of each output file", :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])

input_file = ARGV[0]
output_dir = opts[:output_dir]
tfile_size = opts[:file_size]
convert_off = opts[:convert_off]
strip_tmarker = opts[:strip_marker]
opt_array = [:title_off, :list_off, :heading_off, :table_off, :template_off, :redirect_off]
config = {}
opt_array.each do |opt|
  config[opt] = opts[opt]
end

# a "parent" is either commandline progress bar or 
# a gui window (not available for now)
parent = Wp2txt::CmdProgbar.new
wpconv = Wp2txt::Runner.new(parent, input_file, output_dir, tfile_size, convert_off, strip_tmarker)

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

  if !opts[:category_off] && !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_off]
      line = format_wiki(e.last)
      line += "+HEADING+" if $DEBUG_MODE
    when :mw_paragraph
      next if config[:paragraph_off]
      line = format_wiki(e.last)
      line += "+PARAGRAPH+" if $DEBUG_MODE
    when :mw_table, :mw_htable
      next if config[:table_off]
      line = format_wiki(e.last)
      line += "+TABLE+" if $DEBUG_MODE
    when :mw_pre
      next if config[:pre_off]
      line = e.last
      line += "+PRE+" if $DEBUG_MODE
    when :mw_quote
      next if config[:quote_off]
      line = format_wiki(e.last)
      line += "+QUOTE+" if $DEBUG_MODE
    when :mw_unordered, :mw_ordered, :mw_definition
      next if config[:list_off]
      line = format_wiki(e.last)
      line += "+LIST+" if $DEBUG_MODE
    when :mw_redirect
      next if config[:redirect_off]
      line = format_wiki(e.last)
      line += "+REDIRECT+" if $DEBUG_MODE
      line += "\n\n"
    else
      if $DEBUG_MODE
        line = format_wiki(e.last)
        line += "+OTHER+"
      else
        next
      end
    end
    contents += line
    contents = remove_templates(contents) if config[:template_off]
  end
    
  ##### cleanup #####
  if /\A\s*\z/m =~ contents
    result = ""
  else
    result = config[:title_off] ? contents : title + "\n" + contents
  end
  result = result.gsub(/\[ref\]\s*\[\/ref\]/m){""}
  result = result.gsub(/\n\n\n+/m){"\n\n"} + "\n"  
end