ocr-file 0.0.7 → 0.0.10

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: 8b87806d21622a72c6166c35fe4367f5b07135e5e7fab4e8be8b8941f75439dc
-  data.tar.gz: d342a91e9b23f8677784553327ba1cc1c00e1599415512b28226f8e9f6bc55b4
+  metadata.gz: e77eefa085a14282b42584bd4bf6796a99e10589552b52858cb8f5dd75c84b97
+  data.tar.gz: 9fde9adae0c252ecc56937a314c676903a6b2a6ababe51030cbcd9ab3ee1ba81
 SHA512:
-  metadata.gz: ecadeeb21a358274bce4ed3d7fce66e53d31ff3abe940ff1b9d77893f12b73bfd41e9ac35324e3a98f004638f9d1906760ef962a3637fbaf48973faeec9a17cb
-  data.tar.gz: 5d4a149dd6d0da1feb723b08c327edab414b75f0b633cea53aaee00d43313d26b84659956957acec7550a822998b76a760b3888770a606d8b4a1f9bb14f807c2
+  metadata.gz: f6c9cf596d6a78ccea7e1fb45543826e1b95dab74449700eb0f0bed4bace802fbc15fba118a982fbf7daed9ebb188e417876f1e6a9cb6f620eb3630a4aaed7af
+  data.tar.gz: 9aab569d476170d8c7b405f65a1629d8ec789f008f734a7cc7f49c5716c89c7a7b5010ae3096ed7e4b3358fe650c221da658801a893cd76f6183f23b19696349

data/Gemfile.lock

@@ -1,7 +1,7 @@
 PATH
   remote: .
   specs:
-    ocr-file (0.0.6)
+    ocr-file (0.0.9)
       active_attr (~> 0.15.4)
       console-style (~> 0.0.1)
       hexapdf (~> 0.23.0)

data/README.md

@@ -45,6 +45,7 @@ You will need to install `tesseract` with your desired language on your system,
     image_preprocess: true,
     effects: ['despeckle', 'deskew', 'enhance', 'sharpen', 'remove_shadow', 'bw'], # Applies effects as listed. 'norm' is also available
     automatic_reprocess: true, # Will possibly do double + the operations but can produce better results automatically
+    dimensions: [width, height], # Can be nil but will lock the images
     # PDF to Image Processing
     optimise_pdf: true,
     extract_pdf_images: true, # if false will screenshot each PDF page
@@ -79,9 +80,10 @@ You will need to install `tesseract` with your desired language on your system,
 
   # How to merge files into a single PDF:
   # The files can be images or other PDFs
-  filepaths = []
-  documents = file_paths.map { |path| OcrFile::ImageEngines::PdfEngine.open_pdf(path, password: '') }
-  merged_document = OcrFile::ImageEngines::PdfEngine.merge(documents)
+  file_paths = []
+  merged_document = ::HexaPDF::Document.new
+  dimensions = [width, height] # or nil to maintain dimensions
+  documents = file_paths.map { |path| OcrFile::ImageEngines::PdfEngine.insert_image(merged_document, path, dimensions: dimensions) }
   OcrFile::ImageEngines::PdfEngine.save_pdf(merged_document, save_file_path, optimise: true)
 ```
 

data/lib/ocr-file/document.rb

@@ -25,6 +25,7 @@ module OcrFile
       image_preprocess: true,
       effects: ['despeckle', 'deskew', 'enhance', 'sharpen', 'remove_shadow', 'bw'],
       automatic_reprocess: true,
+      dimensions: nil, # width, height. Will lock images to these dimensions
       # PDF to Image Processing
       optimise_pdf: true,
       extract_pdf_images: true, # if false will screenshot each PDF page
@@ -66,7 +67,7 @@ module OcrFile
 
     def image?
       return false if pdf?
-      ACCEPTED_IMAGE_TYPES.any? { |type| @original_file_path.downcase.include?(".#{type}")}
+      ACCEPTED_IMAGE_TYPES.any? { |type| @original_file_path.downcase.include?(".#{type}") }
     end
 
     # Treat anything which isnt a PDF or image as text

data/lib/ocr-file/image_engines/image_magick.rb

@@ -5,7 +5,7 @@ module OcrFile
       # Conversion of image types
       # Rotation and detection of skew
 
-      attr_reader :image_path, :image, :temp_path, :save_file_path, :config
+      attr_reader :image_path, :image, :temp_path, :save_file_path, :config, :width, :height
 
       def initialize(image_path:, temp_path:, save_file_path:, config:)
         @image_path = image_path
@@ -22,11 +22,18 @@ module OcrFile
         # end
 
         @image = MiniMagick::Image.open(image_path)
+
+        @width = @image[:width]
+        @height = @image[:height]
       end
 
       def convert!
         return @image_path unless @config[:image_preprocess]
 
+        if @config[:dimensions].is_a?(Array) && @config[:dimensions].size == 2
+          resize(width, height)
+        end
+
         @config[:effects].each do |effect|
           self.send(effect.to_sym)
         end
@@ -39,6 +46,10 @@ module OcrFile
         @save_file_path
       end
 
+      def resize(width, height)
+        @image.resize("#{width}x#{height}")
+      end
+
       # Effects
       # http://www.imagemagick.org/script/command-line-options.php
       def bw

data/lib/ocr-file/image_engines/pdf_engine.rb

@@ -61,9 +61,26 @@ module OcrFile
         image_paths
       end
 
-      def insert_image(document, image_path)
-        canvas = document.pages.add.canvas
-        canvas.image(image_path, at: [0, 0], height: 700)
+      def insert_image(document, image_path, dimensions: nil)
+        image_processor = OcrFile::ImageEngines::ImageMagick.new(
+          image_path: image_path,
+          temp_path: @temp_folder_path,
+          save_file_path: '',
+          config: @config
+        )
+
+        if dimensions
+          width = dimensions[0]
+          height = dimensions[1]
+        else
+          width = image_processor.width
+          height = image_processor.height
+        end
+
+        page = document.pages.add([0, 0, width, height])
+        page.canvas.image(@image || image_path, at: [0, 0], width: width, height: height)
+
+        document
       end
 
       def combine(text, pdf_of_images)

data/lib/ocr-file/version.rb

@@ -1,3 +1,3 @@
 module OcrFile
-  VERSION = "0.0.7"
+  VERSION = "0.0.10"
 end

metadata

@@ -1,14 +1,14 @@
 --- !ruby/object:Gem::Specification
 name: ocr-file
 version: !ruby/object:Gem::Version
-  version: 0.0.7
+  version: 0.0.10
 platform: ruby
 authors:
 - trex22
 autorequire:
 bindir: bin
 cert_chain: []
-date: 2022-07-22 00:00:00.000000000 Z
+date: 2023-07-23 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: console-style