ocr-file 0.0.8 → 0.0.10

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: 9ae0f4940b34df3280221cf8b26d86ba3498f8344ef5f0e27ea335ca651a8906
-  data.tar.gz: 5e790899721d25bb0f4dc0e8e276b39b62bbb2803549fdbc8ba148804885bec0
+  metadata.gz: e77eefa085a14282b42584bd4bf6796a99e10589552b52858cb8f5dd75c84b97
+  data.tar.gz: 9fde9adae0c252ecc56937a314c676903a6b2a6ababe51030cbcd9ab3ee1ba81
 SHA512:
-  metadata.gz: 6cd016ca7bba37866579cad59f01f41d190c0a191cd1ce27fa7037646da7bf4962923664c7b6295655936aed8714fac01b08301be65fdfef68403c8dd12c075b
-  data.tar.gz: f1581713a76e19f1b24d43f030cccbfb32b206bea8d1a5f07fed26fe4e0cfaa3f991c0c35b98bf1f222ca36b143e83700638ecf3b0520b9663d2fe4336cc5da2
+  metadata.gz: f6c9cf596d6a78ccea7e1fb45543826e1b95dab74449700eb0f0bed4bace802fbc15fba118a982fbf7daed9ebb188e417876f1e6a9cb6f620eb3630a4aaed7af
+  data.tar.gz: 9aab569d476170d8c7b405f65a1629d8ec789f008f734a7cc7f49c5716c89c7a7b5010ae3096ed7e4b3358fe650c221da658801a893cd76f6183f23b19696349

data/Gemfile.lock

@@ -1,7 +1,7 @@
 PATH
   remote: .
   specs:
-    ocr-file (0.0.8)
+    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
@@ -81,7 +82,8 @@ You will need to install `tesseract` with your desired language on your system,
   # The files can be images or other PDFs
   file_paths = []
   merged_document = ::HexaPDF::Document.new
-  documents = file_paths.map { |path| OcrFile::ImageEngines::PdfEngine.insert_image(merged_document, path) }
+  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

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

@@ -30,6 +30,10 @@ module OcrFile
       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

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

@@ -79,6 +79,8 @@ module OcrFile
 
         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 = "0.0.8"
+  VERSION = "0.0.10"
 end

metadata

@@ -1,14 +1,14 @@
 --- !ruby/object:Gem::Specification
 name: ocr-file
 version: !ruby/object:Gem::Version
-  version: 0.0.8
+  version: 0.0.10
 platform: ruby
 authors:
 - trex22
 autorequire:
 bindir: bin
 cert_chain: []
-date: 2022-07-23 00:00:00.000000000 Z
+date: 2023-07-23 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: console-style