simple_text_extract 1.0.1 → 1.3.0

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: 28beca26a3231ec93af472f0aafdf46c2fcadf33ab79a0925f980f9d8ebfcde3
-  data.tar.gz: 7c1e424163c080ac59bf1414911b10a1dffbdc6d1e34deac4e7a5488f93d09fa
+  metadata.gz: 3d5ee7883d1447c45d4293ff8ac500334f195d3c9e6f88451490787cbf59e728
+  data.tar.gz: 42a88c4c258eedc9c382d80c4b72e8c5deacc46b4490dc7bc1f1d029b8dba2f1
 SHA512:
-  metadata.gz: 41d850e3f186c323757964593028fd46efbfe8cae2031cf0c86785ee0395640f21205b053ff6f36bce5df68e711dbb6cd2565a5f0e4e3c5a2f8256c3648b4215
-  data.tar.gz: ecd4b2d7bb87d4e4aab0b36b6bcc06e1e9b04bccfe6caad90d69145a7810f912524e1a2c7fecc6aad8f36ca8b5558f1817d4d18eec4e2fd24e5e8410256399b0
+  metadata.gz: 1a050e414a45fc766dbd89b3d468c1e67d687185c009caf1a41cd80f4ca8476a82aafdce29461bb8d11c367275a1de0955c39911f12d8760f10cb9fc6f1634f8
+  data.tar.gz: e4c49c9fc926a39d9db0cd6bbdd014e70ef480816a19d242ae541505534a3224ab960e9374459fff884b2f6b4690cf3f21cca85f2c6ff03ff9c5126ba1eb829d

data/.ruby-version

@@ -1 +1 @@
-2.6.5
+3.0.1

data/Gemfile.lock

@@ -1,26 +1,29 @@
 PATH
   remote: .
   specs:
-    simple_text_extract (1.0.0)
-      roo (~> 2.8.2)
-      spreadsheet (~> 1.1.8)
+    simple_text_extract (1.3.0)
+      roo (~> 2.8.3)
+      rubyzip (~> 2.3.2)
+      spreadsheet (~> 1.3.0)
 
 GEM
   remote: https://rubygems.org/
   specs:
-    mini_portile2 (2.4.0)
-    minitest (5.14.0)
-    mocha (1.11.2)
-    nokogiri (1.10.9)
-      mini_portile2 (~> 2.4.0)
-    rake (13.0.1)
+    mini_portile2 (2.7.1)
+    minitest (5.15.0)
+    mocha (1.13.0)
+    nokogiri (1.13.0)
+      mini_portile2 (~> 2.7.0)
+      racc (~> 1.4)
+    racc (1.6.0)
+    rake (13.0.6)
     roo (2.8.3)
       nokogiri (~> 1)
       rubyzip (>= 1.3.0, < 3.0.0)
     ruby-ole (1.2.12.2)
-    rubyzip (2.3.0)
-    spreadsheet (1.1.9)
-      ruby-ole (>= 1.0)
+    rubyzip (2.3.2)
+    spreadsheet (1.3.0)
+      ruby-ole
 
 PLATFORMS
   ruby
@@ -32,4 +35,4 @@ DEPENDENCIES
   simple_text_extract!
 
 BUNDLED WITH
-   2.0.2
+   2.2.15

data/README.md

@@ -9,6 +9,7 @@ SimpleTextExtract handles parsing text from:
 - `.doc`
 - `.xlsx`
 - `.xls`
+- `.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) 💪.
@@ -50,7 +51,7 @@ You can choose to use SimpleTextExtract without the following dependencies, but
 `pdf` parsing requires `poppler-utils`
 - `brew install poppler`
 
-`doc` parsing requires `antiword`
+`doc` parsing requires `antiword` and `unzip`
 - `brew install antiword`
 
 `xlsx` and `xls` parsing requires `ssconvert` which is part of `gnumeric`
@@ -75,6 +76,7 @@ In your `Aptfile`, add:
 ```
 antiword
 gnumeric
+unzip
 ```
 
 * 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.

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 missing_dependency?('antiword')
+        return nil if missing_dependency?("antiword")
 
         `antiword #{Shellwords.escape(file.path)}`
       end

data/lib/simple_text_extract/format_extractor/zip_extract.rb

@@ -0,0 +1,24 @@
+# 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

@@ -7,12 +7,15 @@ 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) # rubocop:disable Metrics/MethodLength, Metrics/CyclomaticComplexity
+    def self.call(file)
       case file.path
-      when /.txt$/i
+      when /.zip$/i
+        FormatExtractor::ZipExtract.new(file)
+      when /(.txt$|.csv$)/i
         FormatExtractor::PlainText.new(file)
       when /.pdf$/i
         FormatExtractor::PDF.new(file)

data/lib/simple_text_extract/text_extractor.rb

@@ -29,13 +29,15 @@ module SimpleTextExtract
 
         begin
           FormatExtractorFactory.call(file).extract
+        rescue StandardError
+          nil
         ensure
           cleanup
         end
       end
 
       def cleanup
-        return unless file.class == Tempfile
+        return unless file.instance_of?(Tempfile)
 
         file.close
         file.unlink

data/lib/simple_text_extract/version.rb

@@ -1,5 +1,5 @@
 # frozen_string_literal: true
 
 module SimpleTextExtract
-  VERSION = "1.0.1"
+  VERSION = "1.3.0"
 end

data/lib/simple_text_extract.rb

@@ -5,7 +5,7 @@ require "simple_text_extract/text_extractor"
 require "simple_text_extract/format_extractor_factory"
 
 module SimpleTextExtract
-  SUPPORTED_FILETYPES = ["xls", "xlsx", "doc", "docx", "txt", "pdf"].freeze
+  SUPPORTED_FILETYPES = ["xls", "xlsx", "doc", "docx", "txt", "pdf", "csv", "zip"].freeze
 
   class Error < StandardError; end
 

data/simple_text_extract.gemspec

@@ -28,8 +28,9 @@ Gem::Specification.new do |spec|
   spec.requirements << "pdftotext/poppler"
   spec.required_ruby_version = ">= 2.5"
 
-  spec.add_runtime_dependency "roo", "~> 2.8.2"
-  spec.add_runtime_dependency "spreadsheet", "~> 1.1.8"
+  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"

metadata

@@ -1,14 +1,14 @@
 --- !ruby/object:Gem::Specification
 name: simple_text_extract
 version: !ruby/object:Gem::Version
-  version: 1.0.1
+  version: 1.3.0
 platform: ruby
 authors:
 - Nick Weiland
-autorequire: 
+autorequire:
 bindir: exe
 cert_chain: []
-date: 2020-03-31 00:00:00.000000000 Z
+date: 2022-01-07 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: roo
@@ -16,28 +16,42 @@ dependencies:
     requirements:
     - - "~>"
       - !ruby/object:Gem::Version
-        version: 2.8.2
+        version: 2.8.3
   type: :runtime
   prerelease: false
   version_requirements: !ruby/object:Gem::Requirement
     requirements:
     - - "~>"
       - !ruby/object:Gem::Version
-        version: 2.8.2
+        version: 2.8.3
 - !ruby/object:Gem::Dependency
   name: spreadsheet
   requirement: !ruby/object:Gem::Requirement
     requirements:
     - - "~>"
       - !ruby/object:Gem::Version
-        version: 1.1.8
+        version: 1.3.0
   type: :runtime
   prerelease: false
   version_requirements: !ruby/object:Gem::Requirement
     requirements:
     - - "~>"
       - !ruby/object:Gem::Version
-        version: 1.1.8
+        version: 1.3.0
+- !ruby/object:Gem::Dependency
+  name: rubyzip
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: 2.3.2
+  type: :runtime
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: 2.3.2
 - !ruby/object:Gem::Dependency
   name: rake
   requirement: !ruby/object:Gem::Requirement
@@ -107,6 +121,7 @@ files:
 - 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/version.rb
@@ -116,7 +131,7 @@ homepage: https://github.com/weilandia/simple_text_extract
 licenses:
 - MIT
 metadata: {}
-post_install_message: 
+post_install_message:
 rdoc_options: []
 require_paths:
 - lib
@@ -133,8 +148,8 @@ required_rubygems_version: !ruby/object:Gem::Requirement
 requirements:
 - antiword
 - pdftotext/poppler
-rubygems_version: 3.0.6
-signing_key: 
+rubygems_version: 3.2.15
+signing_key:
 specification_version: 4
 summary: Attempts to quickly extract text from various file types before resorting
   to something more extreme like Apache Tika.