simple-ocr 1.0.0

checksums.yaml

@@ -0,0 +1,7 @@
+---
+SHA1:
+  metadata.gz: 1f3b37c06436ef5f307e64c4033e5116b531f55c
+  data.tar.gz: 55a206753bfaec92711f8e42f2e5516dcde68ed6
+SHA512:
+  metadata.gz: 8336d1620e4982e00961862ce62f11db12344cb671712988c8258a34ddd2a64b021e36116fe541d9d81c26211e154cbff41e30c7d2f2f07d168a8f4b43ea3f54
+  data.tar.gz: 23957867d8bba43086ee2cb9f76a331f9a9da4b68c7811cbc37bd227ca78a2b6e9acce9dab58404242b4e9da41df6eb4e3aa9813912d3d743a6c5b4623079039

data/lib/simple-ocr.rb

@@ -0,0 +1,8 @@
+require 'simple-ocr/scan'
+require 'simple-ocr/zonal_ocr'
+require 'simple-ocr/image'
+require 'simple-ocr/path'
+
+module OCR
+	MIN_DENSITY = "300x300"
+end

data/lib/simple-ocr/image.rb

@@ -0,0 +1,20 @@
+module OCR
+
+	class Image
+
+		# Initialize your Input File.
+		#
+		# @params [String] path to input file.
+		def initialize(path)
+			@image = path
+		end
+
+		# OCR of input file (Main Function)
+		#
+		# @params [String, String, String] path to output file, options of conversion (e.g. Language), output format of file.
+		def scan(output_file, options, type)
+	      Scan.new(@image, output_file, options, type).scan_img
+	    end
+
+	end
+end

data/lib/simple-ocr/path.rb

@@ -0,0 +1,52 @@
+module OCR
+	class Path
+
+		EXTENS = {:pdf => "pdf", :png => "png"}
+
+		# Initialize your Input File.
+		#
+		# @params [String] path to input file.
+		def initialize(input_file)
+			@input_file = input_file
+		end
+
+		# Split the Realname
+		#
+		# @return [Array] name and extension
+		def name_exten
+			File.basename(@input_file).split(".")
+		end
+
+		# Duplicate the input file path
+		#
+		# @return [String] input file path
+		def duplicate_path
+			return @input_file.dup
+		end
+
+		# From PDF to Image conversion
+		#
+		# @return [String] Converted Image Path
+		def image_path
+			duppath = duplicate_path
+			duppath[name_exten[1]] = Path::EXTENS[:png]
+			return duppath
+		end
+
+		# Clean your Input File
+		#
+		# @return [String] Cleaned Image Path
+		def clean_image_path
+			duppath = duplicate_path
+			duppath[get_filename] = "cleaned_"+name_exten[0]+".png"
+			return duppath
+		end
+
+		# Get the FileName
+		#
+		# @return [String] Filename
+		def get_filename
+			File.basename(@input_file).split("/")[0]
+		end
+	end
+end

data/lib/simple-ocr/scan.rb

@@ -0,0 +1,54 @@
+require 'open3'
+
+module OCR
+	class Scan
+
+		EXTENS = %w{pdf}
+
+		# Initialize your Input File, Output File, Options, Type.
+		#
+		# @params [String, String, String, String] path to input file, path to output file, options of conversion (e.g. Language), output format of file.
+		def initialize(input_file, output_file, options, type)
+			@output_file = output_file
+			@options = options
+			@type = type
+			@input_file = input_file
+			if OCR::Path.new(input_file).name_exten[1] == OCR::Path::EXTENS[:pdf]
+				@image = OCR::Path.new(input_file).image_path
+				convert_to_img
+			else
+				@image = input_file
+			end
+			@clean_image = OCR::Path.new(input_file).clean_image_path
+		end
+
+		# Conversion of PDF to Image
+		def convert_to_img
+			`gs -sDEVICE=png16m '-r#{OCR::MIN_DENSITY}' -o '#{@image}' '#{@input_file}'`
+		end                                               
+
+		# OCR of Input
+		def scan_img
+			clean_img
+			`tesseract '#{@clean_image}' #{@options} '#{@output_file}' #{@type}`
+			delete_files
+		end
+
+		# Execute Command
+		def exec_command(command)
+			Open3.popen3(command)
+		end
+
+		# Shell Script for cleaning the Image.
+		def clean_img
+			`sh ./textcleaner -g -e stretch -f 25 -o 20 -t 30 -u -s 1 -T -p 20 '#{@image}' '#{@clean_image}'`
+		end
+
+		# Deleting unnecessary file after processing.
+		def delete_files
+			FileUtils.rm_rf(@clean_image)
+			FileUtils.rm_rf(@image) if OCR::Path.new(@input_file).name_exten[1] == "pdf"
+		end
+
+	end
+end

data/lib/simple-ocr/zonal_ocr.rb

@@ -0,0 +1,5 @@
+module OCR
+	class ZonalOcr
+		
+	end
+end

metadata

@@ -0,0 +1,50 @@
+--- !ruby/object:Gem::Specification
+name: simple-ocr
+version: !ruby/object:Gem::Version
+  version: 1.0.0
+platform: ruby
+authors:
+- Swaathi Kakarla
+- Shilpi Agrawal
+autorequire: 
+bindir: bin
+cert_chain: []
+date: 2015-10-28 00:00:00.000000000 Z
+dependencies: []
+description: Provides smart conversion of all scanned Images.
+email: shilpi@skcript.com
+executables: []
+extensions: []
+extra_rdoc_files: []
+files:
+- lib/simple-ocr.rb
+- lib/simple-ocr/image.rb
+- lib/simple-ocr/path.rb
+- lib/simple-ocr/scan.rb
+- lib/simple-ocr/zonal_ocr.rb
+homepage: http://www.skcript.com
+licenses:
+- Closed
+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: []
+rubyforge_project: 
+rubygems_version: 2.4.5
+signing_key: 
+specification_version: 4
+summary: OCR Engine by Skcript
+test_files: []
+has_rdoc: