pdfbox_text_extraction 1.0.1 → 1.0.2

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA1:
-  metadata.gz: 037d71d25f199a1239bc1af7baff641840ab9f4a
-  data.tar.gz: 51ba95d37d5aac68439a348f0c139ab648759760
+  metadata.gz: 68496b6265347fcbd44fca03f10d0f5f45565b83
+  data.tar.gz: be3723f8439ef4c6a461cf148dda26c7c32e5a4d
 SHA512:
-  metadata.gz: 10fb9b69f45e7568d2508de9f21987d51d2fd0476a1acc2e4799f588fc16d396a374730db43e2e01734d9b2d4edc44efca502043ec2e71dd88bfc4497b084555
-  data.tar.gz: fde63fedb74600ec80978af3c81f63f135304ff284e75772f953bd6a1e6f2030b0d9668a421647b5497823558100cb6e7e04badacae284f78e61ef1aa972a3ca
+  metadata.gz: 31acd912221c54f20fbab2a7ec657b18fa2f60264b0227d130433294f3b3365f20a80b5c9cc38758d20a19667dbdc8570d2478980f9e107c153a6239f2e0277d
+  data.tar.gz: badd9068e8d424c2b0b055968c734cc70828b0114b94d65b2e5b13d72748c50ff7fdf3e377843139c8685b7ce3a3b4ff3cb03573bb5243e549ff8304b48c7bad

data/CHANGELOG.md

@@ -1,3 +1,8 @@
+### 1.0.2
+
+* Added specs
+* Refactorings and bug fixes
+
 ### 1.0.1
 
 * Fixed file name

data/lib/pdfbox_text_extraction.rb

@@ -31,18 +31,12 @@ class PdfboxTextExtraction
   # @param option [Float] crop_width crop area width
   # @param option [Float] crop_height crop area height
   # @return [String] the extracted text
-  def self.run(path_to_pdf, options)
-    extract_text(path_to_pdf, options)
-  end
-
-  # Extracts text
-  # @see #run
-  def self.extract_text(pdf_filepath, options)
-    file = File.new(pdf_filepath)
+  def self.run(path_to_pdf, options={})
+    file = File.new(path_to_pdf)
     pd_doc = PDDocument.load(file)
     text_stripper = nil
     all_text = ''
-    if %i[crop_x crop_y crop_width crop_height].any? { |e| options[e] }
+    if [:crop_x, :crop_y, :crop_width, :crop_height].any? { |e| options[e] }
       # crop options given, extract from crop area only
       res = 72
       body_text_rect = Rectangle2D::Float.new(
@@ -74,7 +68,7 @@ class PdfboxTextExtraction
 
   # Sets params on text_stripper.
   # @param text_stripper [PDFTextStripper]
-  def configure_text_extraction_params(text_stripper)
+  def self.configure_text_extraction_params(text_stripper)
 
     # *****************************************************
     # Extraction thresholds and tolerances

data/lib/pdfbox_text_extraction/version.rb

@@ -1,3 +1,3 @@
 class PdfboxTextExtraction
-  VERSION = "1.0.1"
+  VERSION = "1.0.2"
 end

data/spec/pdfbox_text_extraction_spec.rb

@@ -0,0 +1,39 @@
+# -*- coding: utf-8 -*-
+
+require_relative './spec_helper'
+
+describe PdfboxTextExtraction do
+
+  describe ".run" do
+
+    let(:pdf_file_path) { File.expand_path("../test_file.pdf", __FILE__) }
+
+    it "extracts full page text" do
+      extracted_text = PdfboxTextExtraction.run(pdf_file_path)
+      extracted_text.must_equal(
+        [
+          'This is a test pdf for the pdfbox_text_extraction Ruby gem.',
+          'Text at the top of the page.',
+          'Text in the middle of the page.',
+          'Text at the bottom of the page.',
+          '',
+        ].join("\n")
+      )
+    end
+
+    it "extracts crop area text" do
+      extracted_text = PdfboxTextExtraction.run(
+        pdf_file_path,
+        {
+          crop_x: 0,
+          crop_y: 3.0,
+          crop_width: 8.5,
+          crop_height: 6.0,
+        }
+      )
+      extracted_text.must_equal("Text in the middle of the page.\n\n")
+    end
+
+  end
+
+end

data/spec/spec_helper.rb

@@ -0,0 +1,5 @@
+# -*- coding: utf-8 -*-
+
+require 'bundler/setup'
+require 'minitest/autorun'
+require 'pdfbox_text_extraction'

metadata

@@ -1,7 +1,7 @@
 --- !ruby/object:Gem::Specification
 name: pdfbox_text_extraction
 version: !ruby/object:Gem::Version
-  version: 1.0.1
+  version: 1.0.2
 platform: ruby
 authors:
 - Jo Hund
@@ -69,6 +69,10 @@ files:
 - lib/pdfbox_text_extraction.rb
 - lib/pdfbox_text_extraction/version.rb
 - pdfbox_text_extraction.gemspec
+- spec/pdfbox_text_extraction_spec.rb
+- spec/spec_helper.rb
+- spec/test_file.odt
+- spec/test_file.pdf
 - vendor/pdfbox/commons-logging-1.2/LICENSE.txt
 - vendor/pdfbox/commons-logging-1.2/NOTICE.txt
 - vendor/pdfbox/commons-logging-1.2/RELEASE-NOTES.txt
@@ -100,4 +104,8 @@ rubygems_version: 2.4.8
 signing_key:
 specification_version: 4
 summary: Extract plain text from PDF documents.
-test_files: []
+test_files:
+- spec/pdfbox_text_extraction_spec.rb
+- spec/spec_helper.rb
+- spec/test_file.odt
+- spec/test_file.pdf