simple_text_extract 0.1.1 → 0.1.2

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: 6bfb9a91dc36259a45033d005b1b5a4bc37c941b153235708ca6755d77cce66e
-  data.tar.gz: dad58cb4b7f039d258196a1ce8568e8169214b12d8ff1c024e1fd9f8412fdf5b
+  metadata.gz: 0c6b024db3cda3f2d163a321e838e37a61e95c4531afc8cc540f7ef0e49ca6d6
+  data.tar.gz: 017e1d1942669d66c74b43872e174d848e2909907f991b7802052edc7021aa43
 SHA512:
-  metadata.gz: 0c5923028e2ff87feecddfcc2f6b340d4ffeb20d92bde686d607a1f498a2fe94326cd5f2df514f392641bbea988776955c76c4a12651178c2a32f885fda39c3d
-  data.tar.gz: acfb70f0bc6746011111a39c5fb730e378372e21b7b5f9eafda1f072c0ead5801ac2425d00070e1b2cc6cb78f6df3a93a0d313ae4627af1e3a7de3339baab882
+  metadata.gz: 76a36c16f31adf9360ccc55b8f1da78b9afd3d5f1d7c89d4139518bd0070f1d3b250eeb11d43af4127057622036086c0dad34970788fbce36088a6b282835b6d
+  data.tar.gz: b0691f0e9a1f0cc3efbfa0aa8a8a2fb7d8370e5cbd40b2c3dd9cb1998f1b67bb3e7a5ce8851e11756f6db957ae8b039b838f4a845dc6358c10db1e8984bab964

data/Gemfile.lock

@@ -1,14 +1,17 @@
 PATH
   remote: .
   specs:
-    simple_text_extract (0.1.0)
+    simple_text_extract (0.1.1)
 
 GEM
   remote: https://rubygems.org/
   specs:
     coderay (1.1.2)
+    metaclass (0.0.4)
     method_source (0.9.2)
     minitest (5.11.3)
+    mocha (1.8.0)
+      metaclass (~> 0.0.1)
     pry (0.12.2)
       coderay (~> 1.1.0)
       method_source (~> 0.9.0)
@@ -20,6 +23,7 @@ PLATFORMS
 DEPENDENCIES
   bundler (~> 1.17)
   minitest (~> 5.0)
+  mocha
   pry
   rake (~> 10.0)
   simple_text_extract!

data/README.md

@@ -75,6 +75,20 @@ antiword
 gnumeric
 ```
 
+## Benchmarks
+
+*Benchmarks test extracting text from the same file 50 times (Macbook pro)*
+
+| File format | SimpleTextExtract | Henkei (i.e. Yomu/Apache Tika) |
+|-------------|-------------------|--------------------------------|
+| .doc        | 1.40s             | 74.27s                         |
+| .docx       | 0.78s             | 71.44s                         |
+| .pdf*       | 1.73s             | 82.86s                         |
+| .xlsx       | 21.99s            | 51.89s                         |
+| .txt        | 0.036s            | 39.25s                         |
+
+* SimpleTextExtract is limited in its text extraction from pdfs, as Tika can also perform OCR on pdfs with Tesseract
+
 ## Development
 
 After checking out the repo, run `bin/setup` to install dependencies. Then, run `rake test` to run the tests. You can also run `bin/console` for an interactive prompt that will allow you to experiment.

data/lib/simple_text_extract/format_extractor/base.rb

@@ -13,6 +13,11 @@ module SimpleTextExtract
 
       def extract
       end
+
+      def missing_dependency?(command)
+        dependency = `command -v #{command}`
+        dependency.nil? || dependency.empty?
+      end
     end
   end
 end

data/lib/simple_text_extract/format_extractor/doc.rb

@@ -4,7 +4,7 @@ module SimpleTextExtract
   module FormatExtractor
     class Doc < Base
       def extract
-        return nil if `command -v antiword`.empty?
+        return nil if missing_dependency?('antiword')
 
         `antiword #{Shellwords.escape(file.path)}`
       end

data/lib/simple_text_extract/format_extractor/doc_x.rb

@@ -4,7 +4,7 @@ module SimpleTextExtract
   module FormatExtractor
     class DocX < Base
       def extract
-        return nil if `command -v unzip`.empty?
+        return nil if missing_dependency?("unzip")
 
         `unzip -p #{Shellwords.escape(file.path)} | grep '<w:t' | sed 's/<[^<]*>//g' | grep -v '^[[:space:]]*$'`
       end

data/lib/simple_text_extract/format_extractor/pdf.rb

@@ -4,7 +4,7 @@ module SimpleTextExtract
   module FormatExtractor
     class PDF < Base
       def extract
-        return nil if `command -v pdftotext`.empty?
+        return nil if missing_dependency?("pdftotext")
 
         `pdftotext #{Shellwords.escape(file.path)} -`
       end

data/lib/simple_text_extract/format_extractor/xls_x.rb

@@ -4,7 +4,7 @@ module SimpleTextExtract
   module FormatExtractor
     class XlsX < Base
       def extract
-        return nil if `command -v ssconvert`.empty?
+        return nil if missing_dependency?("ssconvert")
 
         extract_filepath = "#{file.path.split(".")[0]}.txt"
 

data/lib/simple_text_extract/version.rb

@@ -1,5 +1,5 @@
 # frozen_string_literal: true
 
 module SimpleTextExtract
-  VERSION = "0.1.1"
+  VERSION = "0.1.2"
 end

data/simple_text_extract.gemspec

@@ -31,4 +31,5 @@ Gem::Specification.new do |spec|
   spec.add_development_dependency "bundler", "~> 1.17"
   spec.add_development_dependency "rake", "~> 10.0"
   spec.add_development_dependency "minitest", "~> 5.0"
+  spec.add_development_dependency "mocha"
 end

metadata

@@ -1,7 +1,7 @@
 --- !ruby/object:Gem::Specification
 name: simple_text_extract
 version: !ruby/object:Gem::Version
-  version: 0.1.1
+  version: 0.1.2
 platform: ruby
 authors:
 - Nick Weiland
@@ -52,6 +52,20 @@ dependencies:
     - - "~>"
       - !ruby/object:Gem::Version
         version: '5.0'
+- !ruby/object:Gem::Dependency
+  name: mocha
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - ">="
+      - !ruby/object:Gem::Version
+        version: '0'
+  type: :development
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - ">="
+      - !ruby/object:Gem::Version
+        version: '0'
 description: Attempts to quickly extract text from various file types before resorting
   to something more extreme like Apache Tika. Built with ActiveStorage in mind.
 email: