module Tabula
  class Page < ZoneEntity
    include Tabula::HasCells

    attr_reader :rotation, :number_one_indexed, :file_path
    attr_writer :min_char_width, :min_char_height
    attr_accessor :cells

    def initialize(file_path, width, height, rotation, number, texts=[], ruling_lines=[], min_char_width=nil, min_char_height=nil, spatial_index=nil)
      super(0, 0, width, height)
      @rotation = rotation
      if number < 1
        raise ArgumentError, "Tabula::Page numbers are one-indexed; numbers < 1 are invalid."
      end
      @ruling_lines = ruling_lines
      @file_path = file_path
      @number_one_indexed = number
      @cells = []
      @spreadsheets = nil
      @min_char_width = min_char_width
      @min_char_height = min_char_height

      self.texts = texts

      @ruling_lines += minimal_bounding_box_of_ruling_lines.to_lines.map{|l| Ruling.new(l.getY1, l.getX1, l.getX2 - l.getX1, l.getY2 - l.getY1)}.select &:finite?

      if spatial_index.nil?
        @spatial_index = TextElementIndex.new
        self.texts.each { |te| @spatial_index << te }
      else
        @spatial_index = spatial_index
      end

    end

    def minimal_bounding_box_of_ruling_lines
      max_x = 0
      max_y = 0
      min_x = ::Float::INFINITY
      min_y = ::Float::INFINITY
      horizontal_ruling_lines.each do |t|
        min_x = t.left if t.left < min_x
        max_x = t.right if t.right > max_x
      end
      vertical_ruling_lines.each do |t|
        min_y = t.top if t.top < min_y
        max_y = t.bottom if t.bottom > max_y
      end
      java.awt.geom.Rectangle2D::Float.new(min_x, min_y, max_x - min_x, max_y - min_y)
    end

    # is there a scenario under which we'd prefer to use this over `minimal_bounding_box_of_ruling_lines`?
    # if so, what is it? If there are no ruling lines on the page _at all_, then adding this bounding box is
    # useless.
    def minimal_bounding_box_of_text_elements
      max_x = 0
      max_y = 0
      min_x = ::Float::INFINITY
      min_y = ::Float::INFINITY
      @texts.each do |t|
        min_x = t.x if t.x < min_x
        min_y = t.y if t.y < min_y
        max_x = t.x if t.x > max_x
        max_y = t.y if t.y > max_y       
      end
      java.awt.geom.Rectangle2D::Float.new(min_x, min_y, max_x - min_x, max_y - min_y)
    end

    def get_min_char_width
      @min_char_width ||= texts.map(&:width).min
    end

    def get_min_char_height
      @min_char_height ||= texts.map(&:height).min
    end

    def get_area(area)
      if area.is_a?(Array)
        top, left, bottom, right = area
        area = Tabula::ZoneEntity.new(top, left,
                                      right - left, bottom - top)
      end

      texts = self.get_text(area)
      page_area = PageArea.new(file_path,
                               area.width,
                               area.height,
                               rotation,
                               number,
                               texts,
                               Ruling.crop_rulings_to_area(@ruling_lines, area),
                               texts.map(&:width).min,
                               texts.map(&:height).min,
                               @spatial_index)
      return page_area
    end

    #returns a Table object
    def get_table(options={})
      options = {:vertical_rulings => []}.merge(options)
      if texts.empty?
        return Tabula::Table.new(0, [])
      end

      texts = self.texts.sort
      text_chunks = TextElement.merge_words(texts, options)

      lines = TextChunk.group_by_lines(text_chunks.sort).sort_by(&:top)

      columns = unless options[:vertical_rulings].empty?
                  options[:vertical_rulings].map(&:left).sort #pixel locations, not entities
                else
                  TextChunk.column_positions(lines).sort
                end

      table = Table.new(lines.count, columns)
      lines.each_with_index do |line, i|
        line.text_elements.select { |te| te.text !~ ONLY_SPACES_RE }.each do |te|
          j = columns.find_index { |s| te.left <= s } || columns.count
          table.add_text_element(te, i, j)
        end
      end

      # fixes up the table a little bit, replacing nils with empty TextElements
      # and sorting the lines.
      # table.rows.each do |l|
      #   l.text_elements = l.text_elements.map do |te|
      #     te || TextElement.new(nil, nil, nil, nil, nil, nil, '', nil)
      #   end
      # end
      # table.rows.sort_by!(&:top)
      table
    end

    #for API backwards-compatibility reasons, this returns an array of arrays.
    def make_table(options={})
      get_table(options).rows
    end

    # returns the Spreadsheets; creating them if they're not memoized
    def spreadsheets(options={})
      unless @spreadsheets.nil?
        return @spreadsheets
      end

      @spreadsheets = spreadsheet_areas(options).map do |rect|
        spr = Spreadsheet.new(rect.y, rect.x,
                        rect.width, rect.height,
                        self,
                        #TODO: keep track of the cells, instead of getting them again inefficiently.
                        [],
                        vertical_ruling_lines.select{|vl| rect.intersectsLine(vl) },
                        horizontal_ruling_lines.select{|hl| rect.intersectsLine(hl) }
                        )
        spr.cells = @cells.select{|c| spr.overlaps?(c) }
        spr.add_spanning_cells!
        spr
      end
      if options[:fill_in_cells]
        fill_in_cells!
      end
      spreadsheets
    end

    def spreadsheet_areas (options={})
      get_ruling_lines!(options)
      self.find_cells!(self.horizontal_ruling_lines, self.vertical_ruling_lines, options)

      spreadsheet_java_areas = find_spreadsheets_from_cells #literally, java.awt.geom.Area objects. lol sorry. polygons.

      #transform each spreadsheet area into a rectangle
      # and get the cells contained within it.
      # getBounds2D is theoretically better than getBounds, but it returns a Rectangle2D.Double, which doesn't have our Ruby sugar on it.
      spreadsheet_java_areas.map{|a| a.getBounds } 
    end

    def fill_in_cells!(options={})
      spreadsheets(options).each do |spreadsheet|
        spreadsheet.cells.each do |cell|
          cell.text_elements = page.get_cell_text(cell)
        end
        spreadsheet.cells_resolved = true
      end
    end

    def number(indexing_base=:one_indexed)
      if indexing_base == :zero_indexed
        return @number_one_indexed - 1
      else
        return @number_one_indexed
      end
    end

    # TODO no need for this, let's choose one name
    def ruling_lines
      get_ruling_lines!
    end

    def horizontal_ruling_lines
      get_ruling_lines!
      @horizontal_ruling_lines.nil? ? [] : @horizontal_ruling_lines
    end

    def vertical_ruling_lines
      get_ruling_lines!
      @vertical_ruling_lines.nil? ? [] : @vertical_ruling_lines
    end

    #returns ruling lines, memoizes them in
    def get_ruling_lines!(options={})
      if @ruling_lines.nil? || @ruling_lines.empty?
        return []
      end
      self.snap_points!

      @ruling_lines.select! { |l| !(l.width == 0 && l.height == 0) }

      @vertical_ruling_lines ||= Ruling.collapse_oriented_rulings(@ruling_lines.select(&:vertical?))
      @horizontal_ruling_lines ||= Ruling.collapse_oriented_rulings(@ruling_lines.select(&:horizontal?))

      @vertical_ruling_lines + @horizontal_ruling_lines

    end

    ##
    # get text insidea area
    # area can be an Array ([top, left, width, height])
    # or a Rectangle2D
    def get_text(area=nil)
      if area.instance_of?(Array)
        top, left, bottom, right = area
        area = Tabula::ZoneEntity.new(top, left,
                                      right - left, bottom - top)
      end
      if area.nil?
        texts
      else
        @spatial_index.contains(area)
      end
    end

    def fill_in_cell_texts!(areas)
      texts.each do |t|
        area = areas.find{|a| a.contains(t) }
        area.text_elements << t unless area.nil?
      end
      areas.each do |area|
        area.text_elements = TextElement.merge_words(area.text_elements)
      end
    end

    def get_cell_text(area=nil)
      TextElement.merge_words(self.get_text(area))
    end

    def to_json(options={})
      { :width => self.width,
        :height => self.height,
        :number => self.number,
        :rotation => self.rotation,
        :texts => self.texts
      }.to_json(options)
    end

    def snap_points!
      lines_to_points = {}
      points = []
      @ruling_lines.each do |line|
        point1 = line.p1 #comptooters are the wurst
        point2 = line.p2
        # for a given line, each call to #p1 and #p2 creates a new
        # Point2D::Float object, rather than returning the same one over and
        # over again.
        # so we have to get it, store it in memory as `point1` and `point2`
        # and then store those in various places (and now, modifying one will
        # modify the reference and thereby modify the other)
        lines_to_points[line] = [point1, point2]
        points += [point1, point2]
      end

      # lines are stored separately from their constituent points
      # so you can't modify the points and then modify the lines.
      # ah, but perhaps I can stick the points in a hash AND in an array
      # and then modify the lines by means of the points in the hash.

      [[:x, :x=, self.get_min_char_width], [:y, :y=, self.get_min_char_height]].each do |getter, setter, cell_size|
        sorted_points = points.sort_by(&getter)
        first_point = sorted_points.shift
        grouped_points = sorted_points.inject([[first_point]] ) do |memo, next_point|
          last = memo.last

          if (next_point.send(getter) - last.first.send(getter)).abs < cell_size
            memo[-1] << next_point
          else
            memo << [next_point]
          end
          memo
        end
        grouped_points.each do |group|
          uniq_locs = group.map(&getter).uniq
          avg_loc = uniq_locs.sum / uniq_locs.size
          group.each{|p| p.send(setter, avg_loc) }
        end
      end

      lines_to_points.each do |l, p1_p2|
        l.java_send :setLine, [java.awt.geom.Point2D, java.awt.geom.Point2D], p1_p2[0], p1_p2[1]
      end
    end
  end

end