simple_text_extract 0.1.3 → 0.2.0

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: bd06e0bd11dd74c71adb01918b474b714ebd3762785931d14d294052aa3301e5
-  data.tar.gz: 8fbfff63e6403e4abfc980abd03fce52a1653010c6d401c2507ae253d9391916
+  metadata.gz: fa34a31195f18156df695d2fb860a2beb9562f6a8ae76d6f2b6a7d4585e2e306
+  data.tar.gz: 3af31eaa54ed98bf8d0355cdf2bdf29f525a97e1ae66573b1c7317cbfcd3c951
 SHA512:
-  metadata.gz: 6d2cc814d3b419e9540800752f097b2f9d860e4756e7bd6b8e62f6178ad6cd7967c0f0dd9912a6f900564a686e78564c2c2acb7cee412c9e857ae6ed48cc906e
-  data.tar.gz: dbb00c6da2de38f9d254486adb98bbce2c607a2c54c8637e2b8c9e08efae746ff8bd2ef384a9b1f7ffc2d4edaabda7527498c63726525aa29ba005f24db03770
+  metadata.gz: 3d37e232dd959b4c0897439a29b46f64d598f024b61bba2edc2cdad1f0d14461db77b93a227326697d4913e83ab87b4393234943aef964285b253c652849436d
+  data.tar.gz: 44255a841598321a97559ef3a77c3db3e6f6a7d22cb78fc78819aaecef643b8b67c85484b4f10ac979923f28c8f727fcaca69ebec694b3df9fe5f6a9c37cc1f9

data/Gemfile.lock

@@ -1,7 +1,9 @@
 PATH
   remote: .
   specs:
-    simple_text_extract (0.1.1)
+    simple_text_extract (0.1.3)
+      roo (~> 2.8)
+      spreadsheet (~> 1.1.8)
 
 GEM
   remote: https://rubygems.org/
@@ -9,13 +11,23 @@ GEM
     coderay (1.1.2)
     metaclass (0.0.4)
     method_source (0.9.2)
+    mini_portile2 (2.4.0)
     minitest (5.11.3)
     mocha (1.8.0)
       metaclass (~> 0.0.1)
+    nokogiri (1.10.1)
+      mini_portile2 (~> 2.4.0)
     pry (0.12.2)
       coderay (~> 1.1.0)
       method_source (~> 0.9.0)
     rake (10.5.0)
+    roo (2.8.1)
+      nokogiri (~> 1)
+      rubyzip (>= 1.2.1, < 2.0.0)
+    ruby-ole (1.2.12.1)
+    rubyzip (1.2.2)
+    spreadsheet (1.1.8)
+      ruby-ole (>= 1.0)
 
 PLATFORMS
   ruby

data/README.md

@@ -51,9 +51,6 @@ You can choose to use SimpleTextExtract without the following dependencies, but
 `doc` parsing requires `antiword`
 - `brew install antiword`
 
-`xlsx` and `xls` parsing requires `ssconvert` which is part of `gnumeric`
-- `brew install gnumeric`
-
 ### Usage on Heroku
 
 To use on Heroku you'll have to add some custom buildpacks.
@@ -72,7 +69,6 @@ To add `antiword` as a dependency on Heroku, install the [heroku-buildpack-apt](
 In your `Aptfile`, add:
 ```
 antiword
-gnumeric
 ```
 
 ## Benchmarks

data/lib/simple_text_extract/format_extractor/xls.rb

@@ -0,0 +1,21 @@
+# 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

@@ -4,16 +4,18 @@ module SimpleTextExtract
   module FormatExtractor
     class XlsX < Base
       def extract
-        return nil if missing_dependency?("ssconvert")
+        require "roo"
 
-        extract_filepath = "#{file.path.split(".")[0]}.txt"
+        spreadsheet = Roo::Spreadsheet.open(file)
 
-        `ssconvert -O 'separator=" "' #{Shellwords.escape(file.path)} #{extract_filepath}`
+        text = []
 
-        text = File.read(extract_filepath)
-        File.unlink(extract_filepath)
+        spreadsheet.each_with_pagename do |name, sheet|
+          text << name
+          1.upto(sheet.last_row.to_i) { |row| text << sheet.row(row) }
+        end
 
-        text
+        text.flatten.join(" ")
       end
     end
   end

data/lib/simple_text_extract/format_extractor_factory.rb

@@ -4,6 +4,7 @@ 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"
 
@@ -19,8 +20,10 @@ module SimpleTextExtract
         FormatExtractor::DocX.new(file)
       when /.doc$/i
         FormatExtractor::Doc.new(file)
-      when /(.xlsx$|.xls$)/i
+      when /.xlsx$/i
         FormatExtractor::XlsX.new(file)
+      when /.xls$/i
+        FormatExtractor::Xls.new(file)
       else
         FormatExtractor::Base.new(file)
       end

data/lib/simple_text_extract/version.rb

@@ -1,5 +1,5 @@
 # frozen_string_literal: true
 
 module SimpleTextExtract
-  VERSION = "0.1.3"
+  VERSION = "0.2.0"
 end

data/simple_text_extract.gemspec

@@ -24,10 +24,13 @@ Gem::Specification.new do |spec|
   spec.executables   = spec.files.grep(%r{^exe/}) { |f| File.basename(f) }
   spec.require_paths = ["lib"]
 
-  spec.requirements << "Antiword"
+  spec.requirements << "antiword"
   spec.requirements << "pdftotext/poppler"
   spec.required_ruby_version = ">= 2.5"
 
+  spec.add_runtime_dependency "roo", "~> 2.8"
+  spec.add_runtime_dependency "spreadsheet", "~> 1.1.8"
+
   spec.add_development_dependency "bundler", "~> 1.17"
   spec.add_development_dependency "rake", "~> 10.0"
   spec.add_development_dependency "minitest", "~> 5.0"

metadata

@@ -1,15 +1,43 @@
 --- !ruby/object:Gem::Specification
 name: simple_text_extract
 version: !ruby/object:Gem::Version
-  version: 0.1.3
+  version: 0.2.0
 platform: ruby
 authors:
 - Nick Weiland
 autorequire: 
 bindir: exe
 cert_chain: []
-date: 2019-01-24 00:00:00.000000000 Z
+date: 2019-01-25 00:00:00.000000000 Z
 dependencies:
+- !ruby/object:Gem::Dependency
+  name: roo
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '2.8'
+  type: :runtime
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '2.8'
+- !ruby/object:Gem::Dependency
+  name: spreadsheet
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: 1.1.8
+  type: :runtime
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: 1.1.8
 - !ruby/object:Gem::Dependency
   name: bundler
   requirement: !ruby/object:Gem::Requirement
@@ -92,6 +120,7 @@ files:
 - 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_factory.rb
 - lib/simple_text_extract/tempfile_extractor.rb
@@ -118,7 +147,7 @@ required_rubygems_version: !ruby/object:Gem::Requirement
     - !ruby/object:Gem::Version
       version: '0'
 requirements:
-- Antiword
+- antiword
 - pdftotext/poppler
 rubyforge_project: 
 rubygems_version: 2.7.6