simple_text_extract 1.1.0 → 1.2.0

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: 35eee7886cc545693f85facc69bbe8b99ea141f0af3ad520f6f75d2bc61eddd7
-  data.tar.gz: 5a4b8e4a4dfe54535805f56e986fe36b5470889a96960b2bf8acd1ee4c94b084
+  metadata.gz: 93414a5f260468367e16054bfcbcebbd93962c90a2d6903622a622aa567f754d
+  data.tar.gz: af3fc14fcc1b3c532f5f54c7dfebdb8d4fd4da5de691fe4561b5e39bd6c04fe0
 SHA512:
-  metadata.gz: 9ace8965b9567c8d9e85f2d52912c8081da83a2dc0ff9c463f6ac28450e39ca874125e501196f546930615b4d6271abad88dc3fe8b91f0ade1253c0468652eca
-  data.tar.gz: 05d9819fd5835b8307ae6ece9b0f4efa8b00d615eaf6fcc054dc38959780761ed4cf40711d7b91de38a9e3390904dead968c0a4a0ccc9221a8ec5122a6f9f0b8
+  metadata.gz: 1219e1404ea893772da0905b7bd808f703240cdc9e7f875a287c4e7886e67ea8fbc4c07a2a55a95a8db3f828d7f7ad87a67832e7834618c62537df3d42e013da
+  data.tar.gz: c052e8f2640f8aa9ac452b9cfcad32695add2c1b374daf4dee712f34592a9d1decaae453dbeff1f473fdcd12df01f1a1f9e7751a03925514e91976bb9d654f10

data/.ruby-version

@@ -1 +1 @@
-2.6.5
+3.0.0

data/Gemfile.lock

@@ -1,19 +1,22 @@
 PATH
   remote: .
   specs:
-    simple_text_extract (1.0.0)
+    simple_text_extract (1.2.0)
       roo (~> 2.8.2)
+      rubyzip (>= 1.0.0)
       spreadsheet (~> 1.1.8)
 
 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 (2.5.1)
+    minitest (5.14.4)
+    mocha (1.12.0)
+    nokogiri (1.11.6)
+      mini_portile2 (~> 2.5.0)
+      racc (~> 1.4)
+    racc (1.5.2)
+    rake (13.0.3)
     roo (2.8.3)
       nokogiri (~> 1)
       rubyzip (>= 1.3.0, < 3.0.0)
@@ -32,4 +35,4 @@ DEPENDENCIES
   simple_text_extract!
 
 BUNDLED WITH
-   2.0.2
+   2.2.3

data/README.md

@@ -51,7 +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`
@@ -76,6 +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.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", "csv"].freeze
+  SUPPORTED_FILETYPES = ["xls", "xlsx", "doc", "docx", "txt", "pdf", "csv", "zip"].freeze
 
   class Error < StandardError; 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

@@ -7,11 +7,14 @@ 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 /.zip$/i
+        FormatExtractor::ZipExtract.new(file)
       when /(.txt$|.csv$)/i
         FormatExtractor::PlainText.new(file)
       when /.pdf$/i

data/lib/simple_text_extract/text_extractor.rb

@@ -26,7 +26,6 @@ module SimpleTextExtract
 
       def extract
         return unless file
-        return unless file
 
         begin
           FormatExtractorFactory.call(file).extract
@@ -38,7 +37,7 @@ module SimpleTextExtract
       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 = "1.1.0"
+  VERSION = "1.2.0"
 end

data/simple_text_extract.gemspec

@@ -30,6 +30,7 @@ Gem::Specification.new do |spec|
 
   spec.add_runtime_dependency "roo", "~> 2.8.2"
   spec.add_runtime_dependency "spreadsheet", "~> 1.1.8"
+  spec.add_runtime_dependency "rubyzip", ">= 1.0.0"
 
   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: 1.1.0
+  version: 1.2.0
 platform: ruby
 authors:
 - Nick Weiland
-autorequire: 
+autorequire:
 bindir: exe
 cert_chain: []
-date: 2020-07-29 00:00:00.000000000 Z
+date: 2021-05-26 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: roo
@@ -38,6 +38,20 @@ dependencies:
     - - "~>"
       - !ruby/object:Gem::Version
         version: 1.1.8
+- !ruby/object:Gem::Dependency
+  name: rubyzip
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - ">="
+      - !ruby/object:Gem::Version
+        version: 1.0.0
+  type: :runtime
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - ">="
+      - !ruby/object:Gem::Version
+        version: 1.0.0
 - !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
@@ -117,7 +132,7 @@ homepage: https://github.com/weilandia/simple_text_extract
 licenses:
 - MIT
 metadata: {}
-post_install_message: 
+post_install_message:
 rdoc_options: []
 require_paths:
 - lib
@@ -134,8 +149,8 @@ required_rubygems_version: !ruby/object:Gem::Requirement
 requirements:
 - antiword
 - pdftotext/poppler
-rubygems_version: 3.0.3
-signing_key: 
+rubygems_version: 3.2.3
+signing_key:
 specification_version: 4
 summary: Attempts to quickly extract text from various file types before resorting
   to something more extreme like Apache Tika.