Gem name changed from ‚text_extractor‘ to ‚plaintext‘

.gitignore

@@ -90,5 +90,5 @@ npm-debug.log*
 /frontend/dist/
 /frontend/tests/*.gif
 node_modules/
-text_extractor.yml
+plaintext.yml
 structure.sql

Gemfile

@@ -163,8 +163,7 @@ gem 'aws-sdk', '~> 2.10.1'
 
 gem 'openproject-token', '~> 1.0.1'
 
-gem 'text-extractor', '0.1.0'
-
+gem 'plaintext', '0.1.0'
 
 group :test do
   gem 'rack-test', '~> 0.6.3'

Gemfile.lock

@@ -383,6 +383,10 @@ GEM
       rake (>= 0.8.1)
     pdf-core (0.7.0)
     pg (0.21.0)
+    plaintext (0.1.0)
+      activesupport (> 2.2.1)
+      nokogiri (~> 1.8.1)
+      rubyzip (~> 1.2.1)
     powerpack (0.1.1)
     prawn (2.2.2)
       pdf-core (~> 0.7.0)
@@ -559,10 +563,6 @@ GEM
     sys-filesystem (1.1.8)
       ffi
     test-prof (0.1.0)
-    text-extractor (0.1.0)
-      activesupport (> 2.2.1)
-      nokogiri (~> 1.8.1)
-      rubyzip (~> 1.2.1)
     thin (1.7.2)
       daemons (~> 1.0, >= 1.0.9)
       eventmachine (~> 1.0, >= 1.0.4)
@@ -674,6 +674,7 @@ DEPENDENCIES
   parallel_tests (~> 2.14.0)
   passenger
   pg (~> 0.21.0)
+  plaintext (= 0.1.0)
   prawn (~> 2.2)
   prawn-table (~> 0.2.2)
   pry-byebug (~> 3.4.2)
@@ -720,7 +721,6 @@ DEPENDENCIES
   syck (~> 1.3.0)
   sys-filesystem (~> 1.1.4)
   test-prof
-  text-extractor (= 0.1.0)
   thin (~> 1.7.2)
   timecop (~> 0.9.0)
   transactional_lock!

app/controllers/admin_controller.rb

@@ -77,12 +77,12 @@ class AdminController < ApplicationController
     @checklist = [
       [:text_default_administrator_account_changed, User.default_admin_account_changed?],
       [:text_file_repository_writable, repository_writable],
-      [:'extraction.available.pdftotext', TextExtractor::PdfHandler.available?],
-      [:'extraction.available.unrtf',     TextExtractor::RtfHandler.available?],
-      [:'extraction.available.catdoc',    TextExtractor::DocHandler.available?],
-      [:'extraction.available.xls2csv',   TextExtractor::XlsHandler.available?],
-      [:'extraction.available.catppt',    TextExtractor::PptHandler.available?],
-      [:'extraction.available.tesseract', TextExtractor::ImageHandler.available?]
+      [:'extraction.available.pdftotext', Plaintext::PdfHandler.available?],
+      [:'extraction.available.unrtf',     Plaintext::RtfHandler.available?],
+      [:'extraction.available.catdoc',    Plaintext::DocHandler.available?],
+      [:'extraction.available.xls2csv',   Plaintext::XlsHandler.available?],
+      [:'extraction.available.catppt',    Plaintext::PptHandler.available?],
+      [:'extraction.available.tesseract', Plaintext::ImageHandler.available?]
     ]
 
     @storage_information = OpenProject::Storage.mount_information

app/workers/extract_fulltext_job.rb

@@ -55,7 +55,7 @@ class ExtractFulltextJob < ApplicationJob
 
     begin
       if @attachment.readable?
-        resolver = TextExtractor::Resolver.new(@file, @attachment.content_type)
+        resolver = Plaintext::Resolver.new(@file, @attachment.content_type)
         @text = resolver.text
       end
     rescue => e

config/initializers/plaintext.rb

@@ -27,8 +27,8 @@
 # See doc/COPYRIGHT.rdoc for more details.
 #++
 
-file_name = File.join([Rails.root.to_s, 'config', 'text_extractor.yml'])
+file_name = File.join([Rails.root.to_s, 'config', 'plaintext.yml'])
 if File.file?(file_name)
   config_file = File.read(file_name)
-  TextExtractor::Configuration.load(config_file)
+  Plaintext::Configuration.load(config_file)
 end

config/plaintext.yml

@@ -0,0 +1,38 @@
+# Text extraction helper programs.
+#
+# commands should write the resulting plain text to STDOUT. Use __FILE__ as
+# placeholder for the file path. The values below are the defaults.
+# apt install poppler-utils
+pdftotext:
+ - /usr/local/bin/pdftotext
+ - -enc
+ - UTF-8
+ - __FILE__
+ - '-'
+
+# apt install unrtf
+unrtf:
+  - /usr/local/bin/unrtf
+  - --text
+  - __FILE__
+
+tesseract:
+  - /usr/local/bin/tesseract
+  - __FILE__
+  - stdout
+
+# apt install catdoc
+catdoc:
+  - /usr/bin/textutil
+  - -convert
+  - txt
+  - -stdout
+  - __FILE__
+# xls2csv:
+#   - /usr/bin/xls2csv
+#   - -dutf-8
+#   - __FILE__
+# catppt:
+#   - /usr/bin/catppt
+#   - -dutf-8
+#   - __FILE__

spec/features/work_packages/table/queries/filter_spec.rb

@@ -263,10 +263,10 @@ describe 'filter work packages', js: true do
       allow(EnterpriseToken).to receive(:allows_to?).and_return(false)
       allow(EnterpriseToken).to receive(:allows_to?).with(:attachment_filters).and_return(true)
 
-      allow_any_instance_of(TextExtractor::Resolver).to receive(:text).and_return('I am the first text $1.99.')
+      allow_any_instance_of(Plaintext::Resolver).to receive(:text).and_return('I am the first text $1.99.')
       wp_with_attachment_a
       ExtractFulltextJob.new(attachment_a.id).perform
-      allow_any_instance_of(TextExtractor::Resolver).to receive(:text).and_return('I am the second text.')
+      allow_any_instance_of(Plaintext::Resolver).to receive(:text).and_return('I am the second text.')
       wp_with_attachment_b
       ExtractFulltextJob.new(attachment_b.id).perform
       wp_without_attachment

spec/workers/extract_fulltext_job_spec.rb

@@ -38,7 +38,7 @@ describe ExtractFulltextJob, type: :job do
 
     context "with successful text extraction" do
       before do
-        allow_any_instance_of(TextExtractor::Resolver).to receive(:text).and_return(text)
+        allow_any_instance_of(Plaintext::Resolver).to receive(:text).and_return(text)
       end
 
       context 'attachment is readable' do
@@ -91,7 +91,7 @@ describe ExtractFulltextJob, type: :job do
       let(:logger) { Rails.logger }
 
       before do
-        allow_any_instance_of(TextExtractor::Resolver).to receive(:text).and_raise(exception_message)
+        allow_any_instance_of(Plaintext::Resolver).to receive(:text).and_raise(exception_message)
 
         # This line is actually part of the test. `expect` call needs to go so far up here, as we want to verify that a message gets logged.
         expect(logger).to receive(:error).with(exception_message)