onlyoffice_pdf_parser 0.1.0

checksums.yaml

@@ -0,0 +1,7 @@
+---
+SHA256:
+  metadata.gz: 661dfba5483c4463abeac412e29aef2c7813ac31edf78e17ca3593ed879e10aa
+  data.tar.gz: 5bcabaa8c35ecf07a814f555693c64720234bffd1e9ee2e82b831e8c65f72a09
+SHA512:
+  metadata.gz: a91f4477b8d9a32de8459856a6e3e965380f5143be90cea0c67b1b94367ecfc1e4961f34be916dc5ae9bfbdf634d0f331d3a45f0b7c34261cf6d7ad9ddc392eb
+  data.tar.gz: b0960da736c0e12c99f02c7dc8c8dc3c08569b25f81b5995b858fd060322e77ab7c3145c4aeca9670be3ef12e8247d8550b410335c3b407bdc5a5a0b7aaf8f55

data/README.md

@@ -0,0 +1,12 @@
+# Onlyoffice PDF Parser
+
+It is gem for parsing pdf files.
+
+### Example
+
+```
+require 'onlyoffice_pdf_parser'
+
+OnlyofficePdfParser::PdfParser.parse('Text.pdf')
+
+```

data/lib/onlyoffice_pdf_parser/bmp_image.rb

@@ -0,0 +1,110 @@
+# frozen_string_literal: true
+
+require 'image_size'
+require 'rmagick'
+require_relative 'helpers/array_helper'
+require_relative 'helpers/cursor_point'
+
+module OnlyofficePdfParser
+  # class for storing bmp image pixels data
+  class BmpImage
+    include Magick
+    attr_accessor :path_to_image, :pixels, :width, :height
+    # @return [String] binary dat of file
+    attr_reader :data
+
+    def initialize(param = nil)
+      return unless param
+
+      init_data(param)
+      image_size = ImageSize.new(data).size
+
+      @width = image_size.first
+      @height = image_size.last
+      fetch_pixels
+    end
+
+    def to_s
+      path_to_image
+    end
+
+    def ==(other)
+      return false unless other.width == width && other.height == height
+
+      pixels.each_with_index do |row, row_index|
+        row.each_with_index do |pixel, pixel_index|
+          other_pixel = other.pixels[row_index][pixel_index]
+          result = (pixel == other_pixel)
+          return false unless result
+        end
+      end
+      true
+    end
+
+    def get_sub_image(start_point = CursorPoint.new(0, 0), width = 0, height = 0)
+      sub_image = BmpImage.new
+      pixels_array = []
+      height.times do |current_height|
+        line_array = []
+        width.times do |current_width|
+          pixel_line = pixels[start_point.top + current_height]
+          # If pixels match to near to the edge of right border of image, then end
+          return nil unless pixel_line
+
+          line_array << pixel_line[start_point.left + current_width]
+        end
+        pixels_array << line_array
+      end
+      sub_image.pixels = pixels_array
+      sub_image.width = width
+      sub_image.height = height
+      sub_image
+    end
+
+    def get_sub_image_array(path_to_sub_image)
+      coordinates_array = []
+      sub_image = BmpImage.new(path_to_sub_image)
+      first_sub_image_line = sub_image.pixels.first
+      pixels.each_with_index do |current_line, image_line_index|
+        included_indexes = ArrayHelper.get_array_inclusion_indexes(current_line, first_sub_image_line)
+        included_indexes.each do |current_included_index|
+          coordinates = image_location_start_find(current_included_index, image_line_index)
+          got_sub_image = get_sub_image(coordinates,
+                                        sub_image.width,
+                                        sub_image.height)
+          coordinates_array << coordinates if got_sub_image == sub_image
+        end
+      end
+      coordinates_array
+    end
+
+    private
+
+    # @param param [String] file path of file binaryt
+    # @return [Void] init class data
+    def init_data(param)
+      if OnlyofficePdfParser::FileHelper.file_path?(param)
+        @data = File.read(param)
+        @path_to_image = param
+      else
+        @data = param
+        @path_to_image = '[Binary Steam]'
+      end
+    end
+
+    # @return [Void] Fill @pixel with data
+    def fetch_pixels
+      tmp_file = Tempfile.new('onlyoffice_pdf_parser')
+      File.open(tmp_file, 'wb') { |file| file.write(data) }
+      @pixels = ImageList.new(tmp_file.path).get_pixels(0, 0, width, height).each_slice(width).to_a
+      tmp_file.unlink
+    end
+
+    # @param x_coordinate [Integer] x of start search
+    # @param y_coordinate [Integer] y of start search
+    # @return [CursorPoint] point to start
+    def image_location_start_find(x_coordinate, y_coordinate)
+      CursorPoint.new(x_coordinate % width, y_coordinate)
+    end
+  end
+end

data/lib/onlyoffice_pdf_parser/helpers/array_helper.rb

@@ -0,0 +1,23 @@
+# frozen_string_literal: true
+
+module OnlyofficePdfParser
+  # Methods to help working with array
+  class ArrayHelper
+    # Get list of indexes in which one array is included to another
+    # @param array [Array] big array
+    # @param included_array [Array] array to search
+    # @return [Array, Integer] indexes
+    def self.get_array_inclusion_indexes(array,
+                                         included_array)
+      index_array = []
+      first_element = included_array.first
+      array.each_with_index do |array_element, array_element_index|
+        if array_element == first_element
+          array_part = array.slice(array_element_index, included_array.length)
+          index_array << array_element_index if array_part == included_array
+        end
+      end
+      index_array
+    end
+  end
+end

data/lib/onlyoffice_pdf_parser/helpers/cursor_point.rb

@@ -0,0 +1,47 @@
+# frozen_string_literal: true
+
+module OnlyofficePdfParser
+  # Class for working with cursor coordinates
+  class CursorPoint
+    attr_accessor :left, :top
+
+    def initialize(left, top)
+      @left = left
+      @top = top
+    end
+
+    alias width left
+    alias height top
+    alias x left
+    alias y top
+
+    def dup
+      CursorPoint.new(@left, @top)
+    end
+
+    def to_s
+      "[#{@left}, #{@top}]"
+    end
+
+    def ==(other)
+      if other.respond_to?(:left) && other.respond_to?(:top)
+        @left == other.left && @top == other.top
+      else
+        false
+      end
+    end
+
+    def [](name)
+      case name
+      when :width
+        left
+      when :height
+        top
+      else
+        'Unknown attribute'
+      end
+    end
+  end
+
+  Dimensions = CursorPoint
+end

data/lib/onlyoffice_pdf_parser/helpers/file_helper.rb

@@ -0,0 +1,23 @@
+# frozen_string_literal: true
+
+module OnlyofficePdfParser
+  # Class for working with files
+  class FileHelper
+    class << self
+      # @return [String] name for temp file
+      def generate_temp_name
+        file = Tempfile.new(%w[onlyoffice_bmp_parser .bmp])
+        path = file.path
+        file.unlink
+        path
+      end
+
+      # @return [True, False] if string is file path
+      def file_path?(string)
+        File.exist?(string)
+      rescue ArgumentError
+        false
+      end
+    end
+  end
+end

data/lib/onlyoffice_pdf_parser/pdf_structure/pdf_convert_to_bmp_helper.rb

@@ -0,0 +1,24 @@
+# frozen_string_literal: true
+
+# Helper methods to convert pdf to bmp
+module PdfConvertToBmpHelper
+  # Fill @pages_bmp with data
+  def fetch_bmp_binary
+    temp_path = OnlyofficePdfParser::FileHelper.generate_temp_name
+    `convert "#{@file_path}" #{temp_path}`
+    files = multipage_files(temp_path)
+    files.each do |file|
+      @pages_in_bmp << File.binread(file)
+    end
+  end
+
+  private
+
+  # @param path_pattern [String] pattern to find bmps
+  # @return [Array<String>] list of bmps
+  def multipage_files(path_pattern)
+    files_dir = File.dirname(path_pattern)
+    files_base = File.basename(path_pattern, '.*')
+    Dir["#{files_dir}/#{files_base}*"]
+  end
+end

data/lib/onlyoffice_pdf_parser/pdf_structure/pdf_reader_helper.rb

@@ -0,0 +1,17 @@
+# frozen_string_literal: true
+
+module OnlyofficePdfParser
+  # Module for helper methods for `pdf-reader` gem
+  module PdfReaderHelper
+    # Return font name from page data
+    # @param page [PDF::Reader::Page] page to parse
+    # @return [String] font
+    def parse_font(page)
+      return :unknown if page.fonts[:F1].nil?
+
+      font_string = page.fonts[:F1][:BaseFont].to_s
+      font_string = /(?=\+)(.*)/.match(font_string).to_s # remove from "+" to ","
+      font_string.delete('+')
+    end
+  end
+end

data/lib/onlyoffice_pdf_parser/pdf_structure.rb

@@ -0,0 +1,97 @@
+# frozen_string_literal: true
+
+require 'pdf/reader'
+require 'tempfile'
+require_relative 'helpers/file_helper'
+require_relative 'pdf_structure/pdf_reader_helper'
+require_relative 'pdf_structure/pdf_convert_to_bmp_helper'
+
+module OnlyofficePdfParser
+  # Class for working and parsing PDF files
+  class PdfStructure
+    include PdfConvertToBmpHelper
+    include PdfReaderHelper
+    # @return [Array, Pages] array of pages
+    attr_accessor :pages
+    # @return [String] full path to file
+    attr_accessor :file_path
+    # @return [Array<String>] bin representation of bmps
+    attr_reader :pages_in_bmp
+
+    def initialize(pages: [], file_path: nil)
+      @file_path = file_path
+      @pages = pages
+      @pages_in_bmp = []
+    end
+
+    def [](parameter)
+      case parameter
+      when :pages
+        @pages
+      when :page_size
+        @page_size
+      else
+        raise "Unknown instance variable - #{parameter}."
+      end
+    end
+
+    # @return [True, false] Check if pdf file contains graphic pattern
+    def contain_pattern?(path_to_patter)
+      pages_in_bmp.each do |current_page|
+        bmp = BmpImage.new(current_page)
+        array = bmp.get_sub_image_array(path_to_patter)
+        return true unless array.empty?
+      end
+      false
+    end
+
+    # Parse file using `pdf-reader` gem
+    def pdf_reader_parse
+      PDF::Reader.open(file_path.to_s) do |reader|
+        reader.pages.each do |page|
+          @pages << { text: page.text,
+                      fonts: parse_font(page) }
+        end
+      end
+    end
+
+    # @return [Array <Integer>] page size of pdf in points
+    def page_size_points
+      return @page_size_points if @page_size_points
+
+      pdfinfo = `pdfinfo "#{@file_path}"`
+      page_size_fraction = pdfinfo.split('Page size:')[1].split('pts').first.strip.split(', ').first.split(' x ')
+      @page_size_points = page_size_fraction.map { |size| size.to_f.round }
+    end
+
+    # @return [String, nil] name of page size
+    def page_size
+      @page_size = PAGE_SIZE_FOR_PDF.key(page_size_points)
+      @page_size ||= "Landscape #{PAGE_SIZE_FOR_PDF.key(page_size_points.reverse)}"
+    end
+
+    PAGE_SIZE_FOR_PDF = { 'US Letter' => [612, 792],
+                          'US Legal' => [612, 1008],
+                          'A4' => [595, 842],
+                          'A5' => [420, 595],
+                          'B5' => [499, 709],
+                          'Envelope #10' => [297, 684],
+                          'Envelope DL' => [312, 624],
+                          'Tabloid' => [792, 1224],
+                          'A3' => [842, 1191],
+                          'Tabloid Oversize' => [864, 1296],
+                          'ROC 16K' => [558, 774],
+                          'Envelope Choukei 3' => [340, 666],
+                          'Super B/A3' => [936, 1368] }.freeze
+
+    def self.parse(filename)
+      file = PdfStructure.new(pages: [], file_path: filename)
+      file.pdf_reader_parse
+      file.fetch_bmp_binary
+      file.page_size
+      file
+    end
+  end
+
+  PdfParser = PdfStructure
+end

data/lib/onlyoffice_pdf_parser/version.rb

@@ -0,0 +1,7 @@
+# frozen_string_literal: true
+
+module OnlyofficePdfParser
+  module Version
+    STRING = '0.1.0'
+  end
+end

data/lib/onlyoffice_pdf_parser.rb

@@ -0,0 +1,4 @@
+# frozen_string_literal: true
+
+require_relative 'onlyoffice_pdf_parser/bmp_image.rb'
+require_relative 'onlyoffice_pdf_parser/pdf_structure.rb'

metadata

@@ -0,0 +1,103 @@
+--- !ruby/object:Gem::Specification
+name: onlyoffice_pdf_parser
+version: !ruby/object:Gem::Version
+  version: 0.1.0
+platform: ruby
+authors:
+- Pavel Lobashov
+- Dmitry Rotaty
+autorequire: 
+bindir: bin
+cert_chain: []
+date: 2020-03-13 00:00:00.000000000 Z
+dependencies:
+- !ruby/object:Gem::Dependency
+  name: image_size
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '2'
+  type: :runtime
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '2'
+- !ruby/object:Gem::Dependency
+  name: pdf-reader
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '2'
+  type: :runtime
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '2'
+- !ruby/object:Gem::Dependency
+  name: rmagick
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - ">="
+      - !ruby/object:Gem::Version
+        version: '2'
+    - - "<"
+      - !ruby/object:Gem::Version
+        version: '5'
+  type: :runtime
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - ">="
+      - !ruby/object:Gem::Version
+        version: '2'
+    - - "<"
+      - !ruby/object:Gem::Version
+        version: '5'
+description: Wrapper for Testrail by OnlyOffice
+email:
+- shockwavenn@gmail.com
+- kvazilife@gmail.com
+executables: []
+extensions: []
+extra_rdoc_files: []
+files:
+- README.md
+- lib/onlyoffice_pdf_parser.rb
+- lib/onlyoffice_pdf_parser/bmp_image.rb
+- lib/onlyoffice_pdf_parser/helpers/array_helper.rb
+- lib/onlyoffice_pdf_parser/helpers/cursor_point.rb
+- lib/onlyoffice_pdf_parser/helpers/file_helper.rb
+- lib/onlyoffice_pdf_parser/pdf_structure.rb
+- lib/onlyoffice_pdf_parser/pdf_structure/pdf_convert_to_bmp_helper.rb
+- lib/onlyoffice_pdf_parser/pdf_structure/pdf_reader_helper.rb
+- lib/onlyoffice_pdf_parser/version.rb
+homepage: https://github.com/onlyoffice-testing-robot/onlyoffice_pdf_parser
+licenses:
+- AGPL-3.0
+metadata: {}
+post_install_message: 
+rdoc_options: []
+require_paths:
+- lib
+required_ruby_version: !ruby/object:Gem::Requirement
+  requirements:
+  - - ">="
+    - !ruby/object:Gem::Version
+      version: '0'
+required_rubygems_version: !ruby/object:Gem::Requirement
+  requirements:
+  - - ">="
+    - !ruby/object:Gem::Version
+      version: '0'
+requirements: []
+rubygems_version: 3.0.6
+signing_key: 
+specification_version: 4
+summary: ONLYOFFICE Testrail Wrapper Gem
+test_files: []