#!/usr/bin/env ruby
# encoding: UTF-8

require "fileutils"
# resolve bin path, ignoring symlinks
require "pathname"
bin_file = Pathname.new(__FILE__).realpath

# add self to libpath
$:.unshift File.expand_path("../../lib", bin_file)

require "bundler/setup"
require_relative "../lib/stepmod/utils/terms_extractor"
require "optparse"

def log(message)
  puts "[stepmod-utils] #{message}"
end

options = {}
OptionParser.new do |opts|
  opts.banner = "Usage: #{$0} [options]"

  opts.on(
    "-p",
    "--path STEPMOD_DATA_PATH",
    String,
    "Path to STEPmod data directory",
  ) do |path|
    options[:stepmod_dir] = path
  end

  opts.on(
    "-i",
    "--index INDEX_PATH",
    String,
    "Path to repository_index.xml",
  ) do |path|
    unless path.nil?
      options[:index_path] = Pathname.new(path).to_s
    end
  end

  opts.on(
    "-o",
    "--output INDEX_PATH",
    String,
    "Path to output directory",
  ) do |path|
    unless path.nil?
      options[:output_dir] = Pathname.new(path).to_s
    end
  end

  opts.on_tail("-h", "--help", "Show this message") do
    puts opts
    exit
  end
end.parse!

stepmod_dir = options[:stepmod_dir]
if stepmod_dir.nil?
  raise StandardError.new(
    "STEPmod data path not set, set with the `-p` option.",
  )
else
  log "STEPmod data path: `#{stepmod_dir}`"
end

default_index_path = File.join(stepmod_dir, "repository_index.xml")
index_path = options[:index_path] || default_index_path
if File.exist?(index_path)
  log "Repository index path: `#{index_path}`"
else
  raise StandardError.new(
    "Index file not present at #{index_path}, set with the `-i` option.",
  )
end

default_output_dir = File.join(File.expand_path("..", stepmod_dir),
                               "output_yaml")
output_dir = options[:output_dir] || default_output_dir
unless File.directory?(output_dir)
  FileUtils.mkdir_p(output_dir)
end
log "Output directory path: `#{output_dir}`"

_general_concepts,
resource_concepts,
_parsed_bibliography,
_part_concepts,
part_resources,
part_modules = Stepmod::Utils::TermsExtractor.call(stepmod_dir, index_path)

def part_to_title(bibdata)
  {
    41 => "Fundamentals of product description and support",
    42 => "Geometric and topological representation",
    43 => "Foundation representation",
    44 => "Product structure, concept and configuration",
    45 => "Material and other engineering properties",
    46 => "Visual presentation",
    47 => "Shape tolerance",
    51 => "Mathematical representation",
  }[bibdata.part.to_i] || bibdata.title_en
end

# rubocop:disable Layout/LineLength
IMAGE_REPLACEMENTS = {
  "image::eq01.gif[]" => "stem:[H(A,B) = max {h(A, B), h(B,A)}]",
  "image::eq02.gif[]" => "stem:[max_{a in A} { min_{b in B} d(a,b) }]",
  "image::vector_z_c.gif[]" => "stem:[bar z_{c}]",
  "image::one_direction_repeat_factor_expression.gif[]" => "stem:[I + k cdot R; k = -1, 1]",
  "image::two_direction_repeat_factor_expression.gif[]" => "stem:[I + k_1 cdot R_1 + k_2 cdot R_2; k_1, k_2 = -1, 0, 1, k^2_1 + k^2_2 != 0]",
}.freeze

TEXT_REPLACEMENTS = {
  ' (see <module_ref linkend="ply_orientation_specification:4_entities:figure:f2"> Figure 2</module_ref>)' => "",
  ' (see <module_ref linkend="ply_orientation_specification:4_entities:figure:f3"> Figure 3</module_ref>)' => "",
}.freeze
# rubocop:enable Layout/LineLength

def replace_content(content)
  IMAGE_REPLACEMENTS.each_pair do |k, v|
    content.gsub!(k, v)
  end
  TEXT_REPLACEMENTS.each_pair do |k, v|
    content.gsub!(k, v)
  end

  content
end

def extract_bibliographies(concepts, bibliographies)
  concepts.each do |concept|
    sources = concept.default_lang.sources

    sources.each do |source|
      next if bibliographies[source.origin.text]

      bibliographies[source.origin.text] = {
        "type" => source.type,
        "origin" => {
          "ref" => source.origin.text,
          # "link" => source.origin.link,
        },
      }
    end
  end
end

def extract_sections(concepts, container)
  concepts.each do |concept|
    domain = concept.default_lang.domain

    next if container[domain]

    container[domain] = {
      "domain" => domain,
      "title" => domain.split(":").last.strip,
    }
  end
end

yaml_outputs = {
  clause_4_sections: {},
  clause_5_sections: {},
  bibliographies: {},
}

part_resources.each do |(_bibdata, current_part_resources)|
  current_part_resources.save_to_files(output_dir)
  extract_sections(current_part_resources, yaml_outputs[:clause_4_sections])
  extract_bibliographies(current_part_resources, yaml_outputs[:bibliographies])
end
log "INFO: part_resources written to YAML files in #{output_dir}"

part_modules.sort_by do |(bibdata, _part_modules_arm, _part_modules_mim)|
  bibdata.part.to_i
end.each do |(_bibdata, part_modules_arm, part_modules_mim)|
  unless part_modules_arm.empty?
    part_modules_arm.values.map do |managed_concept|
      managed_concept.save_to_files(output_dir)
      extract_sections(managed_concept, yaml_outputs[:clause_5_sections])
      extract_bibliographies(managed_concept, yaml_outputs[:bibliographies])
    end
  end

  unless part_modules_mim.empty?
    part_modules_mim.values.map do |managed_concept|
      managed_concept.save_to_files(output_dir)
      extract_sections(managed_concept, yaml_outputs[:clause_5_sections])
      extract_bibliographies(managed_concept, yaml_outputs[:bibliographies])
    end
  end
end
log "INFO: part_modules written to YAML files in #{output_dir}"

resource_concepts.save_to_files(output_dir)
log "INFO: resource_concepts written to YAML files in #{output_dir}"

extract_sections(resource_concepts, yaml_outputs[:clause_4_sections])
extract_bibliographies(resource_concepts, yaml_outputs[:bibliographies])

{
  clause_4_sections: "resource_sections.yaml",
  clause_5_sections: "module_sections.yaml",
  bibliographies: "bib.yaml",
}.each_pair do |var, filename|
  path = File.join(output_dir, filename)
  File.write(path, yaml_outputs[var].values.to_yaml)
  log "INFO: #{var} written to #{path}."
end