simple_text_extract 1.3.0 → 3.0.0

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: 3d5ee7883d1447c45d4293ff8ac500334f195d3c9e6f88451490787cbf59e728
-  data.tar.gz: 42a88c4c258eedc9c382d80c4b72e8c5deacc46b4490dc7bc1f1d029b8dba2f1
+  metadata.gz: 411c821b9a0f6ab4f5b95d0104786fbca88c42ab97fa4bd41e8443baae7c80a3
+  data.tar.gz: e6034b96a08ed5bea7abc61e0fb0c762e4c16c44a1e4d54adbc7eff2d9a8bcab
 SHA512:
-  metadata.gz: 1a050e414a45fc766dbd89b3d468c1e67d687185c009caf1a41cd80f4ca8476a82aafdce29461bb8d11c367275a1de0955c39911f12d8760f10cb9fc6f1634f8
-  data.tar.gz: e4c49c9fc926a39d9db0cd6bbdd014e70ef480816a19d242ae541505534a3224ab960e9374459fff884b2f6b4690cf3f21cca85f2c6ff03ff9c5126ba1eb829d
+  metadata.gz: 87d96e6217062b72e104ac1165475d3af497937532fe7f03364128086f6ab61d490d650d60030813783ba32c418bbab564455dc0659882724e6711d9a612cc4d
+  data.tar.gz: 645af90b82616a06805603d2417498890f6fbb53c0d2661934b9ec40d686550c97a42b5bbcc9cf8fe90c049367e45a2e8dd76af8f29d375d8f501beed5be4b16

data/.github/workflows/build.yml

@@ -0,0 +1,30 @@
+name: build
+on: [push, pull_request]
+jobs:
+  build:
+    strategy:
+      fail-fast: false
+      matrix:
+        include:
+          - ruby: 3.2
+            gemfile: Gemfile
+          - ruby: 3.1
+            gemfile: Gemfile
+    runs-on: ubuntu-latest
+    env:
+      BUNDLE_GEMFILE: ${{ matrix.gemfile }}
+    steps:
+      - uses: actions/checkout@v3
+
+      - name: Install poppler-utils
+        run: sudo apt-get install -y poppler-utils
+
+      - name: Install antiword
+        run: sudo apt-get install -y antiword
+
+      - uses: ruby/setup-ruby@v1
+        with:
+          ruby-version: ${{ matrix.ruby }}
+          bundler-cache: true
+
+      - run: bundle exec rake test

data/.rubocop.yml

@@ -0,0 +1,115 @@
+AllCops:
+  NewCops: enable
+  TargetRubyVersion: 3.1
+  DisabledByDefault: true
+
+Security:
+  Enabled: true
+
+Bundler:
+  Enabled: true
+
+Lint:
+  Enabled: true
+
+Naming:
+  Enabled: true
+
+Style:
+  Enabled: true
+
+Layout:
+  Enabled: true
+
+Metrics:
+  Enabled: true
+
+Metrics/AbcSize:
+  Max: 26
+
+Metrics/CyclomaticComplexity:
+  Max: 13
+
+Metrics/PerceivedComplexity:
+  Max: 13
+
+Metrics/MethodLength:
+  Enabled: false
+
+Metrics/ClassLength:
+  Max: 125
+  Enabled: true
+  Exclude:
+    - 'test/**/*'
+
+Metrics/BlockLength:
+  Max: 30
+  Exclude:
+    - 'test/**/*'
+
+Style/ConditionalAssignment:
+  Enabled: false
+
+Style/NumericLiterals:
+  Enabled: false
+
+Style/SymbolProc:
+  Enabled: false
+
+Style/DoubleNegation:
+  Enabled: false
+
+Style/SymbolArray:
+  EnforcedStyle: brackets
+
+Style/WordArray:
+  EnforcedStyle: brackets
+
+Style/EmptyMethod:
+  EnforcedStyle: expanded
+
+Style/ClassAndModuleChildren:
+  Enabled: false
+
+Style/Documentation:
+  Enabled: false
+
+Style/FrozenStringLiteralComment:
+  EnforcedStyle: always
+
+Style/StringLiterals:
+  EnforcedStyle: double_quotes
+
+Style/RedundantReturn:
+  AllowMultipleReturnValues: true
+
+Style/Semicolon:
+  AllowAsExpressionSeparator: true
+
+Style/ExponentialNotation:
+  Enabled: false
+
+Style/RegexpLiteral:
+  Enabled: false
+
+Layout/LineLength:
+  Enabled: false
+
+Layout/EndAlignment:
+  EnforcedStyleAlignWith: variable
+  AutoCorrect: true
+
+Layout/IndentationConsistency:
+  EnforcedStyle: indented_internal_methods
+
+Layout/SpaceInsideBlockBraces:
+  EnforcedStyleForEmptyBraces: space
+
+Lint/MissingSuper:
+  Enabled: false
+
+Lint/ConstantDefinitionInBlock:
+  Enabled: false
+
+Style/SingleArgumentDig:
+  Enabled: false

data/.ruby-version

@@ -1 +1 @@
-3.0.1
+3.1.2

data/CHANGELOG.md

@@ -0,0 +1,6 @@
+## 2.0.0 (2023-04-14)
+
+- [BREAKING CHANGE] Improves format of text extracts to better support post processing into sentences/rows. This will only cause issues if you have tests/code that relies on the specific format of whitespace characters in the resulting extracts. For example, the docx extract will now preserve newline characters.
+- Improves memory allocation for xlsx files using `Roo#each_row_streaming`
+- Adds github actions as ci
+- Simplifies private api away from individual "format extractors"

data/Gemfile

@@ -5,3 +5,10 @@ source "https://rubygems.org"
 git_source(:github) { |repo_name| "https://github.com/#{repo_name}" }
 
 gemspec
+
+gem "memory_profiler"
+gem "minitest"
+gem "mocha"
+gem "pry"
+gem "rake"
+gem "rubocop"

data/Gemfile.lock

@@ -1,38 +1,72 @@
 PATH
   remote: .
   specs:
-    simple_text_extract (1.3.0)
-      roo (~> 2.8.3)
+    simple_text_extract (3.0.0)
+      roo (~> 2.10.0)
       rubyzip (~> 2.3.2)
       spreadsheet (~> 1.3.0)
 
 GEM
   remote: https://rubygems.org/
   specs:
-    mini_portile2 (2.7.1)
-    minitest (5.15.0)
-    mocha (1.13.0)
-    nokogiri (1.13.0)
-      mini_portile2 (~> 2.7.0)
+    ast (2.4.2)
+    coderay (1.1.3)
+    json (2.6.3)
+    memory_profiler (1.0.1)
+    method_source (1.0.0)
+    minitest (5.18.0)
+    mocha (2.0.2)
+      ruby2_keywords (>= 0.0.5)
+    nokogiri (1.14.3-arm64-darwin)
       racc (~> 1.4)
-    racc (1.6.0)
+    nokogiri (1.14.3-x86_64-linux)
+      racc (~> 1.4)
+    parallel (1.22.1)
+    parser (3.2.2.0)
+      ast (~> 2.4.1)
+    pry (0.14.2)
+      coderay (~> 1.1)
+      method_source (~> 1.0)
+    racc (1.6.2)
+    rainbow (3.1.1)
     rake (13.0.6)
-    roo (2.8.3)
+    regexp_parser (2.7.0)
+    rexml (3.2.5)
+    roo (2.10.0)
       nokogiri (~> 1)
       rubyzip (>= 1.3.0, < 3.0.0)
+    rubocop (1.50.1)
+      json (~> 2.3)
+      parallel (~> 1.10)
+      parser (>= 3.2.0.0)
+      rainbow (>= 2.2.2, < 4.0)
+      regexp_parser (>= 1.8, < 3.0)
+      rexml (>= 3.2.5, < 4.0)
+      rubocop-ast (>= 1.28.0, < 2.0)
+      ruby-progressbar (~> 1.7)
+      unicode-display_width (>= 2.4.0, < 3.0)
+    rubocop-ast (1.28.0)
+      parser (>= 3.2.1.0)
     ruby-ole (1.2.12.2)
+    ruby-progressbar (1.13.0)
+    ruby2_keywords (0.0.5)
     rubyzip (2.3.2)
     spreadsheet (1.3.0)
       ruby-ole
+    unicode-display_width (2.4.2)
 
 PLATFORMS
-  ruby
+  arm64-darwin-21
+  x86_64-linux
 
 DEPENDENCIES
-  minitest (~> 5.0)
+  memory_profiler
+  minitest
   mocha
-  rake (~> 13.0)
+  pry
+  rake
+  rubocop
   simple_text_extract!
 
 BUNDLED WITH
-   2.2.15
+   2.4.12

data/LICENSE.txt

@@ -1,7 +1,5 @@
 The MIT License (MIT)
 
-Copyright (c) 2019 Nick Weiland
-
 Permission is hereby granted, free of charge, to any person obtaining a copy
 of this software and associated documentation files (the "Software"), to deal
 in the Software without restriction, including without limitation the rights

data/README.md

@@ -1,8 +1,8 @@
 # 📄 SimpleTextExtract
 
-SimpleTextExtract attempts extract text from various file types and is recommended as a guard before resorting to something more extreme like Apache Tika. It is built specifically with ActiveStorage in mind and originally built for the purpose of extracting text from attachments in order to index the text in ElasticSearch using [SearchKick](https://github.com/ankane/searchkick).
+SimpleTextExtract attempts extract text from various file types and is recommended as a guard before resorting to something more extreme like Apache Tika. It is built specifically with ActiveStorage in mind and originally built for the purpose of extracting text from attachments in order to index the text in ElasticSearch.
 
-SimpleTextExtract handles parsing text from:
+SimpleTextExtract andlhes parsing text from:
 
 - `.pdf`
 - `.docx`
@@ -12,7 +12,7 @@ SimpleTextExtract handles parsing text from:
 - `.csv`
 - `.txt` 😜
 
-If no text is parsed (for `pdf`), or a file format is not supported (like images), then `nil` is returned and you can move on to the heavy-duty tools like [Henkei](https://github.com/abrom/henkei) 💪.
+If no text is parsed (for `pdf`), or a file format is not supported (like images), then `""` is returned and you can move on to try an OCR solution. For example, at [Govly](www.govly.com) use SimpleTextExtract before sending files to [AWS Textract](https://aws.amazon.com/textract/).
 
 ## Installation
 
@@ -35,66 +35,34 @@ Or install it yourself as:
 Text can be parsed from raw file content or files in the filesystem t by calling `SimpleTextExtract.extract`:
 
 ```ruby
-# using ActiveStorage >= 6
-extract = attachment.open { |tmp| SimpleTextExtract.extract(tempfile: tmp) }
-# raw file content or when ActiveStorage < 6
-extract = SimpleTextExtract.extract(filename: attachment.blob.filename, raw: attachment.download)
-
 # filesystem
 extract = SimpleTextExtract.extract(filepath: "path_to_file.pdf")
-```
-
-### Usage Dependencies
-
-You can choose to use SimpleTextExtract without the following dependencies, but it won't work for specific file types:
-
-`pdf` parsing requires `poppler-utils`
-- `brew install poppler`
-
-`doc` parsing requires `antiword` and `unzip`
-- `brew install antiword`
 
-`xlsx` and `xls` parsing requires `ssconvert` which is part of `gnumeric`
-- `brew install gnumeric`
+# raw
+extract = SimpleTextExtract.extract(filename: "some_file.raw", raw: "raw contents")
 
-### Usage on Heroku
+# tempfile
+extract = SimpleTextExtract.extract(tempfile: temp_file)
 
-To use on Heroku you'll have to add some custom buildpacks.
 
 
-##### heroku-buildpack-activestorage-preview
-
-If you're using ActiveStorage, you might already have the [heroku-buildpack-activestorage-preview](https://github.com/heroku/heroku-buildpack-activestorage-preview) added, which means you already have `poppler-utils` installed 🎉
-
-If not, you can either add that buildpack, or add `poppler-utils` to your `Aptfile` (see below).
-
-##### heroku-buildpack-apt
-
-To add `antiword` and/or `gnumeric`* as a dependency on Heroku, install the [heroku-buildpack-apt](https://elements.heroku.com/buildpacks/heroku/heroku-buildpack-apt) buildpack and follow the install instructions.
+# using ActiveStorage >= 6
+extract = attachment.open { |tmp| SimpleTextExtract.extract(tempfile: tmp) }
 
-In your `Aptfile`, add:
-```
-antiword
-gnumeric
-unzip
+# raw file content or when ActiveStorage < 6
+extract = SimpleTextExtract.extract(filename: attachment.blob.filename, raw: attachment.download)
 ```
 
-* There is currently an [issue](https://github.com/heroku/heroku-buildpack-google-chrome/issues/59) with the heroku-18 stack that requires additional dependencies added to the Aptfile to get `gnumeric` to work properly.  You can reference the linked issue above to figure out those dependencies, or downgrade to heroku-16 until it is fixed.
-
-## Benchmarks
+### Usage Dependencies
 
-*Benchmarks test extracting text from the same file 50 times (Macbook pro)*
+You can choose to use SimpleTextExtract without the following dependencies, but it won't work for specific file types:
 
-| 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       | 1.16s             | 51.89s                         |
-| .xls        | 0.80s             | 67.88s                         |
-| .txt        | 0.04s             | 39.25s                         |
+`pdf` parsing requires `poppler-utils`
+`doc` parsing requires `antiword`
 
-* SimpleTextExtract is limited in its text extraction from pdfs, as Tika can also perform OCR on pdfs with Tesseract
+#### Install deps on MacOS
+- `brew install poppler`
+- `brew install antiword`
 
 ## Development
 

data/bin/console

@@ -3,8 +3,5 @@
 require "bundler/setup"
 require "simple_text_extract"
 
-# You can add fixtures and/or initialization code here to make experimenting
-# with your gem easier. You can also use a different console, if you like.
-
-require "irb"
-IRB.start(__FILE__)
+require "pry"
+Pry.start

data/lib/simple_text_extract/extract.rb

@@ -0,0 +1,154 @@
+# frozen_string_literal: true
+
+class SimpleTextExtract::Extract
+  def self.formatter(path)
+    case path
+    when /.zip$/i
+      :zip
+    when /(.txt$|.csv$)/i
+      :plain
+    when /.pdf$/i
+      :pdf
+    when /.docx$/i
+      :docx
+    when /.doc$/i
+      :doc
+    when /.xlsx$/i
+      :xlsx
+    when /.xls$/i
+      :xls
+    end
+  end
+
+  attr_reader :file, :formatter
+
+  def initialize(filename: nil, raw: nil, filepath: nil, tempfile: nil)
+    @file = get_file(filename:, raw:, filepath:, tempfile:)
+    @formatter = self.class.formatter(File.extname(file)) if file
+  end
+
+  def to_s
+    @to_s ||= extract.to_s.gsub(/[^\S\n]+/, " ").gsub(/\s?\n\s+/, "\n").strip
+  end
+
+  private
+
+    def get_file(filename:, raw:, filepath:, tempfile:)
+      if tempfile&.class == Tempfile
+        tempfile
+      elsif !filename.nil? && !raw.nil?
+        write_tempfile(filename: filename.to_s, raw:)
+      elsif !filepath.nil? && File.exist?(filepath)
+        File.new(filepath)
+      end
+    end
+
+    def extract
+      return unless file
+
+      begin
+        send("#{formatter}_extract") if formatter
+      rescue StandardError
+        nil
+      ensure
+        cleanup
+      end
+    end
+
+    def cleanup
+      return unless file.instance_of?(Tempfile)
+
+      file.close
+      file.unlink
+    end
+
+    def write_tempfile(filename:, raw:)
+      filename = filename.split(".").then { |parts| [parts[0], ".#{parts[1]}"] }
+      file = Tempfile.new(filename)
+      raw = String.new(raw, encoding: Encoding::UTF_8)
+
+      file.write(raw)
+      file.tap(&:rewind)
+    end
+
+    def plain_extract
+      file.read
+    end
+
+    def pdf_extract
+      return nil if SimpleTextExtract.missing_dependency?("pdftotext")
+
+      `pdftotext #{Shellwords.escape(file.path)} -`
+    end
+
+    def xlsx_extract
+      require "roo"
+
+      spreadsheet = Roo::Spreadsheet.open(file, only_visible_sheets: true)
+
+      text = []
+
+      spreadsheet.sheets.each do |name|
+        text << name
+
+        spreadsheet.sheet(name)&.each_row_streaming { |row| text << row.join(" ") }
+      end
+
+      text.join("\n")
+    end
+
+    def xls_extract
+      require "spreadsheet"
+
+      spreadsheet = Spreadsheet.open(file)
+      text = []
+      spreadsheet.worksheets.each do |sheet|
+        text << sheet.name
+        sheet.rows.each { |row| text << row.join(" ") }
+      end
+
+      text.join("\n")
+    end
+
+    def doc_extract
+      return nil if SimpleTextExtract.missing_dependency?("antiword")
+
+      `antiword #{Shellwords.escape(file.path)}`
+    end
+
+    def docx_extract
+      require "zip"
+      require "nokogiri"
+
+      result = []
+      Zip::File.open(file) do |zip_file|
+        document = zip_file.glob("word/document*.xml").first
+        return "" if document.nil?
+
+        document_xml = document.get_input_stream.read
+        doc = Nokogiri::XML(document_xml)
+        doc.xpath("//w:document//w:body/w:p").each do |node|
+          result << node.text
+        end
+      end
+
+      result.join("\n")
+    end
+
+    def zip_extract
+      require "zip"
+
+      result = []
+      Zip::File.open(file) do |zip_file|
+        zip_file.each do |entry|
+          result << entry.name
+          result << SimpleTextExtract.extract(
+            raw: entry.get_input_stream.read,
+            filename: entry.name
+          )
+        end
+      end
+
+      result.join("\n")
+    end
+end

data/lib/simple_text_extract/version.rb

@@ -1,5 +1,5 @@
 # frozen_string_literal: true
 
 module SimpleTextExtract
-  VERSION = "1.3.0"
+  VERSION = "3.0.0"
 end

data/lib/simple_text_extract.rb

@@ -1,8 +1,7 @@
 # frozen_string_literal: true
 
 require "simple_text_extract/version"
-require "simple_text_extract/text_extractor"
-require "simple_text_extract/format_extractor_factory"
+require "simple_text_extract/extract"
 
 module SimpleTextExtract
   SUPPORTED_FILETYPES = ["xls", "xlsx", "doc", "docx", "txt", "pdf", "csv", "zip"].freeze
@@ -10,10 +9,15 @@ module SimpleTextExtract
   class Error < StandardError; end
 
   def self.extract(filename: nil, raw: nil, filepath: nil, tempfile: nil)
-    TextExtractor.new(filename: filename, raw: raw, filepath: filepath, tempfile: tempfile).to_s
+    Extract.new(filename:, raw:, filepath:, tempfile:).to_s
   end
 
   def self.supports?(filename: nil)
     SUPPORTED_FILETYPES.include?(filename.split(".").last)
   end
+
+  def self.missing_dependency?(command)
+    dependency = `bash -c 'command -v #{command}'`
+    dependency.nil? || dependency.empty?
+  end
 end

data/simple_text_extract.gemspec

@@ -9,30 +9,24 @@ Gem::Specification.new do |spec|
   spec.version       = SimpleTextExtract::VERSION
   spec.authors       = ["Nick Weiland"]
   spec.email         = ["nickweiland@gmail.com"]
-
-  spec.summary       = "Attempts to quickly extract text from various file types before resorting to something more extreme like Apache Tika."
-  spec.description   = "Attempts to quickly extract text from various file types before resorting to something more extreme like Apache Tika. Built with ActiveStorage in mind."
+  spec.summary       = "Extract text from various file types before resorting to an OCR solution."
+  spec.description   = "Extract text from various file types before resorting to an OCR solution."
   spec.homepage      = "https://github.com/weilandia/simple_text_extract"
   spec.license       = "MIT"
+  spec.required_ruby_version = Gem::Requirement.new(">= 3.1")
 
-  # Specify which files should be added to the gem when it is released.
-  # The `git ls-files -z` loads the files in the RubyGem that have been added into git.
   spec.files = Dir.chdir(File.expand_path(__dir__)) do
     `git ls-files -z`.split("\x0").reject { |f| f.match(%r{^(test|spec|features)/}) }
   end
+
   spec.bindir        = "exe"
   spec.executables   = spec.files.grep(%r{^exe/}) { |f| File.basename(f) }
   spec.require_paths = ["lib"]
 
   spec.requirements << "antiword"
   spec.requirements << "pdftotext/poppler"
-  spec.required_ruby_version = ">= 2.5"
-
-  spec.add_runtime_dependency "roo", "~> 2.8.3"
-  spec.add_runtime_dependency "spreadsheet", "~> 1.3.0"
-  spec.add_runtime_dependency "rubyzip", "~> 2.3.2"
 
-  spec.add_development_dependency "rake", "~> 13.0"
-  spec.add_development_dependency "minitest", "~> 5.0"
-  spec.add_development_dependency "mocha"
+  spec.add_dependency "roo", "~> 2.10.0"
+  spec.add_dependency "spreadsheet", "~> 1.3.0"
+  spec.add_dependency "rubyzip", "~> 2.3.2"
 end

metadata

@@ -1,14 +1,14 @@
 --- !ruby/object:Gem::Specification
 name: simple_text_extract
 version: !ruby/object:Gem::Version
-  version: 1.3.0
+  version: 3.0.0
 platform: ruby
 authors:
 - Nick Weiland
 autorequire:
 bindir: exe
 cert_chain: []
-date: 2022-01-07 00:00:00.000000000 Z
+date: 2023-04-14 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: roo
@@ -16,14 +16,14 @@ dependencies:
     requirements:
     - - "~>"
       - !ruby/object:Gem::Version
-        version: 2.8.3
+        version: 2.10.0
   type: :runtime
   prerelease: false
   version_requirements: !ruby/object:Gem::Requirement
     requirements:
     - - "~>"
       - !ruby/object:Gem::Version
-        version: 2.8.3
+        version: 2.10.0
 - !ruby/object:Gem::Dependency
   name: spreadsheet
   requirement: !ruby/object:Gem::Requirement
@@ -52,60 +52,18 @@ dependencies:
     - - "~>"
       - !ruby/object:Gem::Version
         version: 2.3.2
-- !ruby/object:Gem::Dependency
-  name: rake
-  requirement: !ruby/object:Gem::Requirement
-    requirements:
-    - - "~>"
-      - !ruby/object:Gem::Version
-        version: '13.0'
-  type: :development
-  prerelease: false
-  version_requirements: !ruby/object:Gem::Requirement
-    requirements:
-    - - "~>"
-      - !ruby/object:Gem::Version
-        version: '13.0'
-- !ruby/object:Gem::Dependency
-  name: minitest
-  requirement: !ruby/object:Gem::Requirement
-    requirements:
-    - - "~>"
-      - !ruby/object:Gem::Version
-        version: '5.0'
-  type: :development
-  prerelease: false
-  version_requirements: !ruby/object:Gem::Requirement
-    requirements:
-    - - "~>"
-      - !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.
+description: Extract text from various file types before resorting to an OCR solution.
 email:
 - nickweiland@gmail.com
 executables: []
 extensions: []
 extra_rdoc_files: []
 files:
+- ".github/workflows/build.yml"
 - ".gitignore"
+- ".rubocop.yml"
 - ".ruby-version"
-- ".travis.yml"
-- CODE_OF_CONDUCT.md
+- CHANGELOG.md
 - Gemfile
 - Gemfile.lock
 - LICENSE.txt
@@ -114,19 +72,9 @@ files:
 - bin/console
 - bin/setup
 - lib/simple_text_extract.rb
-- lib/simple_text_extract/format_extractor/base.rb
-- lib/simple_text_extract/format_extractor/doc.rb
-- lib/simple_text_extract/format_extractor/doc_x.rb
-- lib/simple_text_extract/format_extractor/pdf.rb
-- lib/simple_text_extract/format_extractor/plain_text.rb
-- lib/simple_text_extract/format_extractor/xls.rb
-- lib/simple_text_extract/format_extractor/xls_x.rb
-- lib/simple_text_extract/format_extractor/zip_extract.rb
-- lib/simple_text_extract/format_extractor_factory.rb
-- lib/simple_text_extract/text_extractor.rb
+- lib/simple_text_extract/extract.rb
 - lib/simple_text_extract/version.rb
 - simple_text_extract.gemspec
-- tags
 homepage: https://github.com/weilandia/simple_text_extract
 licenses:
 - MIT
@@ -139,7 +87,7 @@ required_ruby_version: !ruby/object:Gem::Requirement
   requirements:
   - - ">="
     - !ruby/object:Gem::Version
-      version: '2.5'
+      version: '3.1'
 required_rubygems_version: !ruby/object:Gem::Requirement
   requirements:
   - - ">="
@@ -148,9 +96,8 @@ required_rubygems_version: !ruby/object:Gem::Requirement
 requirements:
 - antiword
 - pdftotext/poppler
-rubygems_version: 3.2.15
+rubygems_version: 3.3.7
 signing_key:
 specification_version: 4
-summary: Attempts to quickly extract text from various file types before resorting
-  to something more extreme like Apache Tika.
+summary: Extract text from various file types before resorting to an OCR solution.
 test_files: []

data/.travis.yml

@@ -1,7 +0,0 @@
----
-sudo: false
-language: ruby
-cache: bundler
-rvm:
-  - 2.6.0
-before_install: gem install bundler -v 1.17.2

data/CODE_OF_CONDUCT.md

@@ -1,74 +0,0 @@
-# Contributor Covenant Code of Conduct
-
-## Our Pledge
-
-In the interest of fostering an open and welcoming environment, we as
-contributors and maintainers pledge to making participation in our project and
-our community a harassment-free experience for everyone, regardless of age, body
-size, disability, ethnicity, gender identity and expression, level of experience,
-nationality, personal appearance, race, religion, or sexual identity and
-orientation.
-
-## Our Standards
-
-Examples of behavior that contributes to creating a positive environment
-include:
-
-* Using welcoming and inclusive language
-* Being respectful of differing viewpoints and experiences
-* Gracefully accepting constructive criticism
-* Focusing on what is best for the community
-* Showing empathy towards other community members
-
-Examples of unacceptable behavior by participants include:
-
-* The use of sexualized language or imagery and unwelcome sexual attention or
-advances
-* Trolling, insulting/derogatory comments, and personal or political attacks
-* Public or private harassment
-* Publishing others' private information, such as a physical or electronic
-  address, without explicit permission
-* Other conduct which could reasonably be considered inappropriate in a
-  professional setting
-
-## Our Responsibilities
-
-Project maintainers are responsible for clarifying the standards of acceptable
-behavior and are expected to take appropriate and fair corrective action in
-response to any instances of unacceptable behavior.
-
-Project maintainers have the right and responsibility to remove, edit, or
-reject comments, commits, code, wiki edits, issues, and other contributions
-that are not aligned to this Code of Conduct, or to ban temporarily or
-permanently any contributor for other behaviors that they deem inappropriate,
-threatening, offensive, or harmful.
-
-## Scope
-
-This Code of Conduct applies both within project spaces and in public spaces
-when an individual is representing the project or its community. Examples of
-representing a project or community include using an official project e-mail
-address, posting via an official social media account, or acting as an appointed
-representative at an online or offline event. Representation of a project may be
-further defined and clarified by project maintainers.
-
-## Enforcement
-
-Instances of abusive, harassing, or otherwise unacceptable behavior may be
-reported by contacting the project team at nickweiland@gmail.com. All
-complaints will be reviewed and investigated and will result in a response that
-is deemed necessary and appropriate to the circumstances. The project team is
-obligated to maintain confidentiality with regard to the reporter of an incident.
-Further details of specific enforcement policies may be posted separately.
-
-Project maintainers who do not follow or enforce the Code of Conduct in good
-faith may face temporary or permanent repercussions as determined by other
-members of the project's leadership.
-
-## Attribution
-
-This Code of Conduct is adapted from the [Contributor Covenant][homepage], version 1.4,
-available at [http://contributor-covenant.org/version/1/4][version]
-
-[homepage]: http://contributor-covenant.org
-[version]: http://contributor-covenant.org/version/1/4/

data/lib/simple_text_extract/format_extractor/base.rb

@@ -1,23 +0,0 @@
-# frozen_string_literal: true
-
-require "shellwords"
-
-module SimpleTextExtract
-  module FormatExtractor
-    class Base
-      attr_reader :file
-
-      def initialize(file)
-        @file = file
-      end
-
-      def extract
-      end
-
-      def missing_dependency?(command)
-        dependency = `bash -c 'command -v #{command}'`
-        dependency.nil? || dependency.empty?
-      end
-    end
-  end
-end

data/lib/simple_text_extract/format_extractor/doc.rb

@@ -1,13 +0,0 @@
-# frozen_string_literal: true
-
-module SimpleTextExtract
-  module FormatExtractor
-    class Doc < Base
-      def extract
-        return nil if missing_dependency?("antiword")
-
-        `antiword #{Shellwords.escape(file.path)}`
-      end
-    end
-  end
-end

data/lib/simple_text_extract/format_extractor/doc_x.rb

@@ -1,13 +0,0 @@
-# frozen_string_literal: true
-
-module SimpleTextExtract
-  module FormatExtractor
-    class DocX < Base
-      def extract
-        return nil if missing_dependency?("unzip")
-
-        `unzip -p #{Shellwords.escape(file.path)} | grep '<w:t' | sed 's/<[^<]*>//g' | grep -v '^[[:space:]]*$'`
-      end
-    end
-  end
-end

data/lib/simple_text_extract/format_extractor/pdf.rb

@@ -1,13 +0,0 @@
-# frozen_string_literal: true
-
-module SimpleTextExtract
-  module FormatExtractor
-    class PDF < Base
-      def extract
-        return nil if missing_dependency?("pdftotext")
-
-        `pdftotext #{Shellwords.escape(file.path)} -`
-      end
-    end
-  end
-end

data/lib/simple_text_extract/format_extractor/plain_text.rb

@@ -1,11 +0,0 @@
-# frozen_string_literal: true
-
-module SimpleTextExtract
-  module FormatExtractor
-    class PlainText < Base
-      def extract
-        file.read
-      end
-    end
-  end
-end

data/lib/simple_text_extract/format_extractor/xls.rb

@@ -1,20 +0,0 @@
-# frozen_string_literal: true
-
-module SimpleTextExtract
-  module FormatExtractor
-    class Xls < Base
-      def extract
-        require "spreadsheet"
-
-        spreadsheet = Spreadsheet.open(file)
-        text = []
-        spreadsheet.worksheets.each do |sheet|
-          text << sheet.name
-          text << sheet.rows
-        end
-
-        text.flatten.join(" ")
-      end
-    end
-  end
-end

data/lib/simple_text_extract/format_extractor/xls_x.rb

@@ -1,22 +0,0 @@
-# frozen_string_literal: true
-
-module SimpleTextExtract
-  module FormatExtractor
-    class XlsX < Base
-      def extract
-        require "roo"
-
-        spreadsheet = Roo::Spreadsheet.open(file, only_visible_sheets: true)
-
-        text = []
-
-        spreadsheet.each_with_pagename do |name, sheet|
-          text << name
-          1.upto(sheet.last_row.to_i) { |row| text << sheet.row(row) }
-        end
-
-        text.flatten.join(" ")
-      end
-    end
-  end
-end

data/lib/simple_text_extract/format_extractor/zip_extract.rb

@@ -1,24 +0,0 @@
-# frozen_string_literal: true
-
-module SimpleTextExtract
-  module FormatExtractor
-    class ZipExtract < Base
-      def extract
-        require "zip"
-
-        result = []
-        Zip::File.open(file) do |zip_file|
-          zip_file.each do |entry|
-            result << entry.name
-            result << SimpleTextExtract.extract(
-              raw: entry.get_input_stream.read,
-              filename: entry.name
-            )
-          end
-        end
-
-        result.join(" ")
-      end
-    end
-  end
-end

data/lib/simple_text_extract/format_extractor_factory.rb

@@ -1,35 +0,0 @@
-# frozen_string_literal: true
-
-require "simple_text_extract/format_extractor/base"
-require "simple_text_extract/format_extractor/plain_text"
-require "simple_text_extract/format_extractor/pdf"
-require "simple_text_extract/format_extractor/xls_x"
-require "simple_text_extract/format_extractor/xls"
-require "simple_text_extract/format_extractor/doc_x"
-require "simple_text_extract/format_extractor/doc"
-require "simple_text_extract/format_extractor/zip_extract"
-
-module SimpleTextExtract
-  class FormatExtractorFactory
-    def self.call(file)
-      case file.path
-      when /.zip$/i
-        FormatExtractor::ZipExtract.new(file)
-      when /(.txt$|.csv$)/i
-        FormatExtractor::PlainText.new(file)
-      when /.pdf$/i
-        FormatExtractor::PDF.new(file)
-      when /.docx$/i
-        FormatExtractor::DocX.new(file)
-      when /.doc$/i
-        FormatExtractor::Doc.new(file)
-      when /.xlsx$/i
-        FormatExtractor::XlsX.new(file)
-      when /.xls$/i
-        FormatExtractor::Xls.new(file)
-      else
-        FormatExtractor::Base.new(file)
-      end
-    end
-  end
-end

data/lib/simple_text_extract/text_extractor.rb

@@ -1,55 +0,0 @@
-# frozen_string_literal: true
-
-module SimpleTextExtract
-  class TextExtractor
-    attr_reader :file
-
-    def initialize(filename: nil, raw: nil, filepath: nil, tempfile: nil)
-      @file = get_file(filename: filename, raw: raw, filepath: filepath, tempfile: tempfile)
-    end
-
-    def to_s
-      @to_s ||= extract.to_s
-    end
-
-    private
-
-      def get_file(filename:, raw:, filepath:, tempfile:)
-        if tempfile&.class == Tempfile
-          tempfile
-        elsif !filename.nil? && !raw.nil?
-          write_tempfile(filename: filename.to_s, raw: raw)
-        elsif !filepath.nil? && File.exist?(filepath)
-          File.new(filepath)
-        end
-      end
-
-      def extract
-        return unless file
-
-        begin
-          FormatExtractorFactory.call(file).extract
-        rescue StandardError
-          nil
-        ensure
-          cleanup
-        end
-      end
-
-      def cleanup
-        return unless file.instance_of?(Tempfile)
-
-        file.close
-        file.unlink
-      end
-
-      def write_tempfile(filename:, raw:)
-        filename = filename.split(".").yield_self { |parts| [parts[0], ".#{parts[1]}"] }
-        file = Tempfile.new(filename)
-        raw = String.new(raw, encoding: Encoding::UTF_8)
-
-        file.write(raw)
-        file.tap(&:rewind)
-      end
-  end
-end

data/tags

@@ -1,17 +0,0 @@
-!_TAG_FILE_FORMAT	2	/extended format; --format=1 will not append ;" to lines/
-!_TAG_FILE_SORTED	1	/0=unsorted, 1=sorted, 2=foldcase/
-!_TAG_OUTPUT_MODE	u-ctags	/u-ctags or e-ctags/
-!_TAG_PROGRAM_AUTHOR	Universal Ctags Team	//
-!_TAG_PROGRAM_NAME	Universal Ctags	/Derived from Exuberant Ctags/
-!_TAG_PROGRAM_URL	https://ctags.io/	/official site/
-!_TAG_PROGRAM_VERSION	0.0.0	/54afb0f/
-Error	lib/simple_text_extract.rb	/^  class Error < StandardError; end$/;"	c	module:SimpleTextExtract
-SimpleTextExtract	lib/simple_text_extract.rb	/^module SimpleTextExtract$/;"	m
-SimpleTextExtract	lib/simple_text_extract/version.rb	/^module SimpleTextExtract$/;"	m
-TextExtractor	lib/simple_text_extract/text_extractor.rb	/^class SimpleTextExtract::TextExtractor$/;"	c	module:SimpleTextExtract
-VERSION	lib/simple_text_extract/version.rb	/^  VERSION = "0.1.0"$/;"	c
-call	lib/simple_text_extract/text_extractor.rb	/^  def self.call(filename:, raw_content:, filepath:)$/;"	S	class:TextExtractor
-extract	lib/simple_text_extract.rb	/^  def self.extract(filename: nil, raw_content: nil, filepath: nil)$/;"	S	module:SimpleTextExtract
-extract	lib/simple_text_extract/text_extractor.rb	/^  def extract$/;"	f	class:TextExtractor
-filepath	lib/simple_text_extract/text_extractor.rb	/^  attr_reader :filename, :raw_content, :filepath$/;"	A
-initialize	lib/simple_text_extract/text_extractor.rb	/^  def initialize(filename:, raw_content:, filepath:)$/;"	f	class:TextExtractor