xtractor 0.0.1 → 0.1.0

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA1:
-  metadata.gz: 6d3cd5007bf97796771406720cbb0ee70dfb202c
-  data.tar.gz: 04c5b121c7ec50cadec23798c81343922e9389e1
+  metadata.gz: e360ba9ddac0bd8b589bbfa0cdda7c344408b029
+  data.tar.gz: 9ffe93ad99b50e40d8fc018b71dc2cdb78bd4273
 SHA512:
-  metadata.gz: d3573e93e365cbcf8beb8d0e50bf3a57c40ab881f366b5851e4b1ff900424ce41df30522eaf4f03abd28a8eae5e222a24ec4a41203cd5cdd2dffe90b587bd532
-  data.tar.gz: 41e3abf3c28d2bd54acae446176f84a43ba17040bacba6e9ebc646a9bd0840a293d7d2c6ec1662e041a0802a22103e1a1afe88af0b670cb1c3145c24381942f8
+  metadata.gz: ec2936bc8117b54e570d30cbb871555d0853da8e5e5a27778e84274df085d03c5c079293ed30e21de86f8c5e71367bde511d20cf148c9f7ce714ff376d84175f
+  data.tar.gz: 3f917c1372895e6a3db1cd6ecfea2a56afe141299c07a2a362a89f7036d6346a65c83b243275be4062f1779e1f5ec11e4efcd7d33d6cfc4b1b5d9b7aaaa5b6ec

data/.travis.yml

@@ -1,4 +1,4 @@
-sudo: false
+sudo:  false
 language: ruby
 rvm:
   - 2.3.1

data/README.md

@@ -1,6 +1,8 @@
 # Xtractor
+<img src="https://badge.fury.io/rb/xtractor.svg" alt="Gem Version" /> <img src="https://travis-ci.org/Kamalpaneru/Xtractor.svg?branch=master" alt="Build" />
 
-Xtractor was developed as a need to my own problem of inserting handwritten data from an excelsheet image to excel.And it does the same as described.
+
+Xtractor was developed as a need to the problem of inserting data from an excelsheet image to excel.And it does the same as described.
 
 ## Installation
 
@@ -20,7 +22,22 @@ Or install it yourself as:
 
 ## Usage
 
-Used to split cells from excel sheet images and extracts data.
+Used to split cells from excel sheet images and extracts data. <br>
+  NOTE: I've replaced Tesseract with Azure Computer Vision API(Not perfect but a significant improvement though).<br> <br>
+
+  ```ruby
+    require 'xtractor'
+
+    Xtractor::Execute.new('Image_Filename')
+
+  ```
+## Sample Image
+
+![image_f3](https://user-images.githubusercontent.com/13826932/31273813-03dde45a-aab0-11e7-942f-c77202f996d1.jpg)
+
+## Generate API key
+  Replace API_KEY in ```lib/xtractor/request.rb ``` with your Key.<br>
+    ```https://azure.microsoft.com/en-gb/try/cognitive-services/ ```
 
 ## Contributing
 

data/lib/xtractor.rb

@@ -1,4 +1,5 @@
 require "xtractor/version"
 require "xtractor/xtract"
+require_relative "xtractor/request"
 
 

data/lib/xtractor/request.rb

@@ -0,0 +1,46 @@
+require 'net/http'
+require 'json'
+
+class Azure_API
+
+  def request_API
+      uri = URI('https://westcentralus.api.cognitive.microsoft.com/vision/v1.0/ocr')
+      uri.query = URI.encode_www_form({
+
+        'language' => 'en',
+        'detectOrientation ' => 'true'
+      })
+
+      request = Net::HTTP::Post.new(uri.request_uri)
+
+      request['Ocp-Apim-Subscription-Key'] = "d0154961a66b4a0aa41d6f4fbb4b2105"
+
+      request['Content-Type'] = 'application/octet-stream'
+
+      collect = Hash.new
+
+      all_files = Dir.glob("cell-files/*.{jpg,png,gif}").sort
+
+      all_files.each do |crop_image|
+          request.body = File.binread("#{crop_image}")
+
+          response = Net::HTTP.start(uri.host, uri.port, :use_ssl => uri.scheme == 'https') do |http|
+          http.request(request)
+          end
+
+          collect[crop_image[0..-5]]= JSON.parse(response.body)
+
+          initial_res = collect[crop_image[0..-5]].dig("regions",0,"lines",0,"words",0,"text").to_s
+          mid_res = collect[crop_image[0..-5]].dig("regions",0,"lines",0,"words",1,"text").to_s
+          final_res = collect[crop_image[0..-5]].dig("regions",0,"lines",0,"words",2,"text").to_s
+
+          collect[crop_image[0..-5]] = initial_res + ' ' + mid_res + ' ' + final_res
+
+          puts collect[crop_image[0..-5]]
+
+          File.open("cell-files/#{crop_image[11..-5]}.txt", "w") do |data|
+              data.write(collect[crop_image[0..-5]])
+          end
+      end
+  end
+end

data/lib/xtractor/version.rb

@@ -1,3 +1,3 @@
 module Xtractor
-  VERSION = "0.0.1"
+  VERSION = "0.1.0"
 end

data/lib/xtractor/xtract.rb

@@ -1,11 +1,13 @@
 require "rubygems"
 require "rmagick"
+require_relative "request"
 
 module Xtractor
   class Execute
 
     def initialize(image)
       img = Magick::Image::read(image).first
+
       if %w(TIFF).include? img.format
         crop_throw(img)
       else
@@ -16,76 +18,97 @@ module Xtractor
     end
 
     def crop_throw(img)
-      img = img.resize_to_fit(2500,906)
-      box = img.bounding_box
-      img.crop!(box.x, box.y, box.width, box.height)
+       img = img.resize_to_fit(2500,906)
+       box = img.bounding_box
+       img.crop!(box.x, box.y, box.width, box.height)
       start(img)
     end
 
-    def start(img)
-      store_line_rows = (0..img.rows-1).inject([]) do |arr, line_index|
-      threshold = (img.columns*0.10).floor
-      arr << line_index if img.get_pixels(0, line_index, (threshold), 1).select{|pixel|
-      pixel.red < 63000 }.length >= threshold*0.95
-      arr
+    def store_line_rows(img)
+      (0...img.rows).inject([]) do |arr, line_index|
+        threshold = (img.columns*0.10).floor
+        arr << line_index if img.get_pixels(0, line_index, (threshold), 1).select{|pixel|
+          pixel.red < 63000 }.length >= threshold*0.95
+        arr
       end
+    end
 
-
-      store_line_columns = (0..img.columns-1).inject([])do |arr, line_index|
-      threshold = (img.rows*0.10).floor
-      arr << line_index if img.get_pixels(line_index, 0, 1, (threshold)).select{|pixel|
-      pixel.red < 63000 }.length >= threshold*0.95
-      arr
-     end
-
-
-
-      columns_filter = store_line_columns[1..-1].inject( [[ (store_line_columns[0]),(store_line_columns[0]) ]]) do |arr, line|
-      if line == arr.last[1]+1
-        arr.last[1] = line
-      else
-        arr << [line,line]
-      end
-      arr
+    def store_line_columns(img)
+      (0...img.columns).inject([])do |arr, line_index|
+        threshold = (img.rows*0.10).floor
+        arr << line_index if img.get_pixels(line_index, 0, 1, (threshold)).select{|pixel|
+          pixel.red < 63000 }.length >= threshold*0.95
+        arr
       end
+    end
 
-
-      rows_filter = store_line_rows[1..-1].inject( [[ (store_line_rows[0]), (store_line_rows[0] )]]) do |arr, line|
-      if line == arr.last[1]+1
-        arr.last[1] = line
-      else
-        arr << [line,line]
+    def columns_filter(img)
+      store_line_columns(img)[1..-1].inject( [[ (store_line_columns(img)[0]),(store_line_columns(img)[0]) ]]) do |arr, line|
+        if line == arr.last[1]+1
+          arr.last[1] = line
+        else
+          arr << [line,line]
+        end
+        arr
       end
-      arr
+    end
+
+    def rows_filter(img)
+      store_line_rows(img)[1..-1].inject( [[ (store_line_rows(img)[0]), (store_line_rows(img)[0] )]]) do |arr, line|
+        if line == arr.last[1]+1
+          arr.last[1] = line
+        else
+          arr << [line,line]
+        end
+        arr
       end
+    end
 
 
-      Dir.mkdir('cell-files') if !File.exists?('cell-files')
 
-      output_file = File.open('table.txt', 'w')
+    def start(img)
+      Dir.mkdir('cell-files') if !File.exist?('cell-files')
 
-      rows_filter[0..-2].each_with_index do |row, i|
-        text_row = []
-      columns_filter[0..-2].each_with_index do |column, j|
-        x,y= column[1], row[1]
-        w,h= columns_filter[j+1][0]-x, rows_filter[i+1][0]-y
+      rows_filter(img)[0..-2].each_with_index do |row, i|
+        columns_filter(img)[0..-2].each_with_index do |column, j|
+          x,y= column[1], row[1]
+          w,h= columns_filter(img)[j+1][0]-x, rows_filter(img)[i+1][0]-y
 
-      Magick::Image.constitute(w, h, "RGB", img.get_pixels(x,y,w,h).map{ |pixel|
-          [pixel.red, pixel.green, pixel.blue]}.flatten).write("cell-files/#{j}x#{i}.tif") do |out|
+          Magick::Image.constitute(w, h, "RGB", img.get_pixels(x,y,w,h).map{ |pixel|
+          [pixel.red, pixel.green, pixel.blue]}.flatten).write("cell-files/#{j}x#{i}.jpg") do |out|
               out.depth=8
           end
 
-      `tesseract cell-files/#{j}x#{i}.tif cell-files/#{j}x#{i} `
-
+           r_image = Magick::Image::read("cell-files/#{j}x#{i}.jpg").first
+           res_image = r_image.resize(r_image.columns,100)
 
-      text_row << File.open("cell-files/#{j}x#{i}.txt", 'r').readlines.map{|line| line.strip}.join(" ")
+           res_image.write("cell-files/#{j}x#{i}.jpg") do
+             self.quality = 100
+           end
 
+        end
       end
+      collect_hash(img)
+    end
+
+    def collect_hash(img)
+      api = Azure_API.new
+      api.request_API
+      out_final(img)
+    end
 
-      output_file.puts( text_row.join("\t"))
+    def  out_final(img)
+      output_file = File.open('table.tsv', 'w')
+      rows_filter(img)[0..-2].each_with_index do |_row, i|
+        text_row = []
+          columns_filter(img)[0..-2].each_with_index do |_column, j|
+              text_row << File.open("cell-files/#{j}x#{i}.txt", 'r').readlines.map{|line| line.strip}.join(" ")
+          end
+          output_file.puts( text_row.join("\t"))
       end
       output_file.close
     end
 
   end
 end
+

data/xtractor.gemspec

@@ -11,7 +11,7 @@ Gem::Specification.new do |spec|
   spec.files            = ["lib/xtract.rb"]
 
   spec.summary       = %q{Splits cells in an excelsheet images and extracts data.}
-  spec.description   = %q{Xtractor was developed as a need to my own problem of inserting handwritten data from an excelsheet printed paper to excel.And it does the same as described. }
+  spec.description   = %q{Xtractor was developed as a need to my own problem of inserting handwritten data from an excelsheet image to excel.And it does the same as described. }
   spec.homepage      = 'https://rubygems.org/gems/xtractor'
   spec.license       = "MIT"
 

metadata

@@ -1,14 +1,14 @@
 --- !ruby/object:Gem::Specification
 name: xtractor
 version: !ruby/object:Gem::Version
-  version: 0.0.1
+  version: 0.1.0
 platform: ruby
 authors:
 - kamalpaneru
 autorequire: 
 bindir: exe
 cert_chain: []
-date: 2017-06-10 00:00:00.000000000 Z
+date: 2017-10-16 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: bundler
@@ -67,7 +67,7 @@ dependencies:
       - !ruby/object:Gem::Version
         version: 2.16.0
 description: 'Xtractor was developed as a need to my own problem of inserting handwritten
-  data from an excelsheet printed paper to excel.And it does the same as described. '
+  data from an excelsheet image to excel.And it does the same as described. '
 email:
 - kamalpaneru.15@gmail.com
 executables: []
@@ -85,6 +85,7 @@ files:
 - bin/console
 - bin/setup
 - lib/xtractor.rb
+- lib/xtractor/request.rb
 - lib/xtractor/version.rb
 - lib/xtractor/xtract.rb
 - xtractor.gemspec
@@ -109,7 +110,7 @@ required_rubygems_version: !ruby/object:Gem::Requirement
       version: '0'
 requirements: []
 rubyforge_project: 
-rubygems_version: 2.5.1
+rubygems_version: 2.6.14
 signing_key: 
 specification_version: 4
 summary: Splits cells in an excelsheet images and extracts data.