simple-ocr 1.0.0 → 1.0.2

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA1:
-  metadata.gz: 1f3b37c06436ef5f307e64c4033e5116b531f55c
-  data.tar.gz: 55a206753bfaec92711f8e42f2e5516dcde68ed6
+  metadata.gz: 9709934460b8582dd2a2ddf24c9c46a6ea1fed9b
+  data.tar.gz: da7c6d2f038b5dade09dc8e18a51d1a83b2be5bb
 SHA512:
-  metadata.gz: 8336d1620e4982e00961862ce62f11db12344cb671712988c8258a34ddd2a64b021e36116fe541d9d81c26211e154cbff41e30c7d2f2f07d168a8f4b43ea3f54
-  data.tar.gz: 23957867d8bba43086ee2cb9f76a331f9a9da4b68c7811cbc37bd227ca78a2b6e9acce9dab58404242b4e9da41df6eb4e3aa9813912d3d743a6c5b4623079039
+  metadata.gz: a8b518651bc8d31ad658199302917d0b313d753d39128b4ceb67404ffbaed31bbc5343a03b90d43a50be60e529c4b2cce157f7e56bfce0007ea8d0a298e87401
+  data.tar.gz: 68a05698d7de9d6738d0a4f68aebfc2455ad75a2a6f7930a2e5db9fa9b8f2aac3885a0f01f83dec916c2c0217e1d31f4ec8963f13bad796c9fce299e071b7811

data/lib/simple-ocr/image.rb

@@ -13,8 +13,7 @@ module OCR
 		#
 		# @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
-
+      Scan.new(@image, output_file, options, type).scan_img
+    end
 	end
 end

data/lib/simple-ocr/path.rb

@@ -21,7 +21,7 @@ module OCR
 		#
 		# @return [String] input file path
 		def duplicate_path
-			return @input_file.dup
+			@input_file.dup
 		end
 
 		# From PDF to Image conversion
@@ -30,7 +30,7 @@ module OCR
 		def image_path
 			duppath = duplicate_path
 			duppath[name_exten[1]] = Path::EXTENS[:png]
-			return duppath
+			duppath
 		end
 
 		# Clean your Input File
@@ -38,15 +38,15 @@ module OCR
 		# @return [String] Cleaned Image Path
 		def clean_image_path
 			duppath = duplicate_path
-			duppath[get_filename] = "cleaned_"+name_exten[0]+".png"
-			return duppath
+			duppath[get_filename] = "cleaned_"+get_filename+".png"
+			duppath
 		end
 
 		# Get the FileName
 		#
 		# @return [String] Filename
 		def get_filename
-			File.basename(@input_file).split("/")[0]
+			File.basename(@input_file)
 		end
 	end
 end

data/lib/simple-ocr/scan.rb

@@ -1,4 +1,5 @@
 require 'open3'
+require 'fileutils'
 
 module OCR
 	class Scan
@@ -11,15 +12,25 @@ module OCR
 		def initialize(input_file, output_file, options, type)
 			@output_file = output_file
 			@options = options
-			@type = type
+			@type = handle_output_type(type)
 			@input_file = input_file
-			if OCR::Path.new(input_file).name_exten[1] == OCR::Path::EXTENS[:pdf]
+			if pdf?(input_file)
 				@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
+			@clean_image = OCR::Path.new(output_file).clean_image_path
+		end
+		
+		def handle_output_type(type)
+			if type == :pdf
+				'pdf'
+			elsif type == :hocr
+				'hocr'
+			else
+				nil.to_s
+			end
 		end
 
 		# Conversion of PDF to Image
@@ -41,14 +52,19 @@ module OCR
 
 		# 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}'`
+			name = 'simple-ocr'
+			g = Gem::Specification.find_by_name(name)
+			`sh #{File.join(g.full_gem_path, 'lib/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.
+		# Deleting unnecessary files after processing.
 		def delete_files
 			FileUtils.rm_rf(@clean_image)
-			FileUtils.rm_rf(@image) if OCR::Path.new(@input_file).name_exten[1] == "pdf"
+			FileUtils.rm_rf(@image) if pdf?
 		end
 
+		def pdf?(input_file = @input_file)
+			OCR::Path.new(input_file).name_exten[1] == OCR::Path::EXTENS[:pdf]
+		end
 	end
-end
+end

metadata

@@ -1,7 +1,7 @@
 --- !ruby/object:Gem::Specification
 name: simple-ocr
 version: !ruby/object:Gem::Version
-  version: 1.0.0
+  version: 1.0.2
 platform: ruby
 authors:
 - Swaathi Kakarla
@@ -42,9 +42,8 @@ required_rubygems_version: !ruby/object:Gem::Requirement
       version: '0'
 requirements: []
 rubyforge_project: 
-rubygems_version: 2.4.5
+rubygems_version: 2.4.8
 signing_key: 
 specification_version: 4
 summary: OCR Engine by Skcript
 test_files: []
-has_rdoc: