Chore/sincronizar fork con version relajada de rubyzip

.github/workflows/test.yml

@@ -0,0 +1,31 @@
+name: Test
+
+on:
+  push:
+    branches: [ master ]
+  pull_request:
+    branches: [ master ]
+
+jobs:
+  test:
+    runs-on: ubuntu-latest
+    strategy:
+      matrix:
+        ruby-version: ['2.7', '3.0', '3.1', '3.2', '3.3', '3.4']
+
+    steps:
+    - uses: actions/checkout@v4
+
+    - name: Install system dependencies
+      run: |
+        sudo apt-get update -qq
+        sudo apt-get install -y catdoc unrtf poppler-utils tesseract-ocr
+
+    - name: Set up Ruby
+      uses: ruby/setup-ruby@v1
+      with:
+        ruby-version: ${{ matrix.ruby-version }}
+        bundler-cache: true
+
+    - name: Run tests
+      run: bundle exec rake spec

CHANGELOG

@@ -4,7 +4,31 @@ All notable changes to this project will be documented in this file.
 The format is based on [Keep a Changelog](https://keepachangelog.com/en/1.0.0/),
 and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0.html).
 
-## [Unreleased]
+## [0.3.7] - 2025-11-25
+
+### Added
+- Support for text/markdown content type in plaintext handler
+
+## [0.3.6] - 2025-10-16
+
+### Fixed
+- Resolver returns nil if the handler returns nil
+
+## [0.3.5] - 2025-10-14
+
+### Changed
+- Migrated CI from Travis to GitHub Actions
+
+### Fixed
+- Fix FrozenError when handler returns a frozen string
+- Fix Object#present? not being available in tests by requiring active_support before core_exts
+- Suppress tesseract extra output to reduce noise in OCR results
+
+## [0.3.4] - 2021-04-21
+- Further relax the rubyzip version requirement to allow 2.x versions
+- Fix: Removed --quiet from unrtf arguments. In newer versions this seems to
+  suppress the header line which we used as a marker to strip unrtf comments and
+  meta data from the command output.
 
 ## [0.3.3] - 2019-10-01
 - Relax rubyzip dependency. Our usage of rubyzip does not require adressing

README.md

@@ -1,4 +1,4 @@
-# plaintext [![Build Status](https://travis-ci.org/planio-gmbh/plaintext.svg?branch=master)](https://travis-ci.org/planio-gmbh/plaintext)
+# plaintext [![Test](https://github.com/planio-gmbh/plaintext/actions/workflows/test.yml/badge.svg)](https://github.com/planio-gmbh/plaintext/actions/workflows/test.yml)
 
 This gem wraps command line tools to extract plain text from typical files such as
 

lib/plaintext.rb

@@ -1,5 +1,7 @@
 # frozen_string_literal: true
 
+require 'active_support'
+require 'active_support/core_ext/object/blank'
 require 'active_support/core_ext/string'
 
 require 'plaintext/version'

lib/plaintext/file_handler/external_command_handler/image_handler.rb

@@ -8,7 +8,7 @@ class ImageHandler < ExternalCommandHandler
         'image/tiff'
     ]
     DEFAULT = [
-        '/usr/bin/tesseract', '__FILE__', 'stdout'
+        '/usr/bin/tesseract', '__FILE__', 'stdout', 'quiet'
     ].freeze
     def initialize
       @content_types = CONTENT_TYPES

lib/plaintext/file_handler/external_command_handler/rtf_handler.rb

@@ -3,7 +3,7 @@
 module Plaintext
   class RtfHandler < ExternalCommandHandler
     DEFAULT = [
-        '/usr/bin/unrtf', '--nopict', '--quiet', '--text', '__FILE__'
+        '/usr/bin/unrtf', '--nopict', '--text', '__FILE__'
     ].freeze
     def initialize
       @content_type = 'application/rtf'

lib/plaintext/file_handler/plaintext_handler.rb

@@ -3,7 +3,7 @@
 module Plaintext
 
   class PlaintextHandler < FileHandler
-    CONTENT_TYPES = %w(text/csv text/plain)
+    CONTENT_TYPES = %w(text/csv text/plain text/markdown)
     def initialize
       @content_types = CONTENT_TYPES
     end

lib/plaintext/version.rb

@@ -1,5 +1,5 @@
 # frozen_string_literal: true
 
 module Plaintext
-  VERSION = "0.3.4"
+  VERSION = "0.3.7"
 end

plaintext.gemspec

@@ -21,9 +21,9 @@ Gem::Specification.new do |spec|
 
   spec.add_dependency 'activesupport', '>2.2.1 '
   spec.add_dependency 'nokogiri', '~> 1.10', '>= 1.10.4'
-  spec.add_dependency 'rubyzip', '~> 2.0'
+  spec.add_dependency 'rubyzip', '>= 1.2.0'
 
-  spec.add_development_dependency 'bundler', '1.17.2'
+  spec.add_development_dependency 'bundler', '>= 2.0'
   spec.add_development_dependency 'rake', '~> 12.0'
   spec.add_development_dependency 'rspec'
 end

spec/lib/file_handler/external_command_handler/image_handler_spec.rb

@@ -23,6 +23,12 @@
       expect(subject.text(file)).to match /Enable two-factor authentication/
       expect(Plaintext::Resolver.new(file, 'image/tiff').text).to match /zeee spbp 7uhp hc7s/
     end
+    it 'Should extract empty text from images without text' do
+      file = File.new('spec/fixtures/files/image-without-text.jpg', 'r')
+
+      expect(subject.text(file)).to be_empty
+      expect(Plaintext::Resolver.new(file, 'image/jpeg').text).to be_empty
+    end
   else
     warn "#{described_class.name} could not be tested as external program is not available."
   end

spec/lib/file_handler/resolver_spec.rb

@@ -0,0 +1,34 @@
+# frozen_string_literal: true
+
+require 'spec_helper'
+
+describe Plaintext::Resolver do
+  subject(:resolver) do
+    file = File.new('spec/fixtures/files/text.txt', 'r')
+    described_class.new(file, 'text/plain')
+  end
+  let(:handler) { resolver.send(:find_handler) }
+
+
+  # NOTA: Este test viene del upstream pero nosotros modificamos el resolver
+  # por lo que no tiene sentido que lo pasemos. Modificamos su contenido con una
+  # versión compatible al código actual.
+  it 'squishes and strips the text returned by the handler' do
+    allow(handler).to receive(:text).and_return("  hello \n \n world! ")
+
+    expect(resolver.text).to eq("  hello \n \n world! ")
+  end
+
+  it 'returns nil if the handler returns nil' do
+    allow(handler).to receive(:text).and_return(nil)
+
+    expect(resolver.text).to be_nil
+  end
+
+  it 'can deal with frozen string returned by the handler' do
+    # make the handler return a frozen string
+    allow(handler).to receive(:text).and_wrap_original { |m, *args| m.call(*args).freeze }
+
+    expect(resolver.text).to include(/lorem ipsum/)
+  end
+end

spec/lib/file_handler/zipped_xml_handler/office_document_handler/docx_handler_spec.rb

@@ -9,11 +9,10 @@
   it 'Should extract text from .docx files' do
     file = File.new('spec/fixtures/files/text.docx', 'r')
 
-    expect(subject.text(file)).to(
-      match /lorem ipsum/
-    )
+    expect(subject.text(file)).to include('lorem ipsum')
+
     expect(Plaintext::Resolver.new(file, 'application/vnd.openxmlformats-officedocument.wordprocessingml.document').text).to(
-      match /lorem ipsum fulltext find me!/
+      include('lorem ipsum')
     )
   end
 

spec/lib/file_handler/zipped_xml_handler/office_document_handler/pptx_handler_spec.rb

@@ -3,37 +3,34 @@
 require 'spec_helper'
 
 describe Plaintext::PptxHandler do
-
   subject { described_class.new }
 
   it 'Should extract text from .pptx files' do
     file = File.new('spec/fixtures/files/presentation.pptx', 'r')
 
+    expect(subject.text(file).split.join(' ')).to include('Slide two')
+
+    resolver_presentation = Plaintext::Resolver.new(file, 'application/vnd.openxmlformats-officedocument.presentationml.presentation')
+    expect(resolver_presentation.text.split.join(' ')).to include('The Title find me Slide two')
 
-    expect(subject.text(file)).to match /Slide two/
+    resolver_slideshow = Plaintext::Resolver.new(file, 'application/vnd.openxmlformats-officedocument.presentationml.slideshow')
+    expect(resolver_slideshow.text.split.join(' ')).to include('The Title find me Slide two')
 
-    expect(Plaintext::Resolver.new(file, 'application/vnd.openxmlformats-officedocument.presentationml.presentation').text).to(
-        match /The Title find me Slide two/
-    )
-    expect(Plaintext::Resolver.new(file, 'application/vnd.openxmlformats-officedocument.presentationml.slideshow').text).to(
-        match /The Title find me Slide two/
-    )
-    expect(Plaintext::Resolver.new(file, 'application/vnd.ms-powerpoint.template.macroEnabled.12').text).to(
-        match /The Title find me Slide two/
-    )
+    resolver_template = Plaintext::Resolver.new(file, 'application/vnd.ms-powerpoint.template.macroEnabled.12')
+    expect(resolver_template.text.split.join(' ')).to include('The Title find me Slide two')
   end
 
   it 'Should only extract text up to given size limit' do
     file = File.new('spec/fixtures/files/presentation.pptx', 'r')
-    expect(subject.text(file, max_size: 2)).to eq "Th"
+    expect(subject.text(file, max_size: 2)).to eq 'Th'
 
     r = Plaintext::Resolver.new(file, 'application/vnd.openxmlformats-officedocument.presentationml.presentation')
     r.max_plaintext_bytes = 3
-    expect(r.text).to eq "The"
+    expect(r.text).to eq 'The'
   end
 
   it 'Should return a utf8 encoded string' do
     file = File.new('spec/fixtures/files/presentation.pptx', 'r')
     expect(subject.text(file).encoding.name).to eq 'UTF-8'
   end
-end
+end

spec/lib/file_handler/zipped_xml_handler/office_document_handler/xlsx_handler_spec.rb

@@ -9,10 +9,10 @@
   it 'Should extract text from .xlsx files' do
     file = File.new('spec/fixtures/files/spreadsheet.xlsx', 'r')
 
-    expect(subject.text(file)).to match /lorem ipsum/
+    expect(subject.text(file).split.join(' ')).to include('lorem ipsum')
 
-    expect(Plaintext::Resolver.new(file, 'application/vnd.openxmlformats-officedocument.spreadsheetml.sheet').text).to(
-        match /lorem ipsum fulltext find me!/
+    expect(Plaintext::Resolver.new(file, 'application/vnd.openxmlformats-officedocument.spreadsheetml.sheet').text.split.join(' ')).to(
+      include('lorem ipsum fulltext find me!')
     )
   end
 end

spec/lib/file_handler/zipped_xml_handler/opendocument_handler_spec.rb

@@ -3,86 +3,83 @@
 require 'spec_helper'
 
 describe Plaintext::OpendocumentHandler do
-
   subject { described_class.new }
-  
+
   it 'Should accept a path string as input' do
     file = 'spec/fixtures/files/text.odt'
-    expect(subject.text(file)).to match /lorem ipsum/
+    expect(subject.text(file).split.join(' ')).to include('lorem ipsum')
   end
 
   it 'Should accept a pathname as input' do
     file = Pathname('spec/fixtures/files/text.odt')
-    expect(subject.text(file)).to match /lorem ipsum/
+    expect(subject.text(file).split.join(' ')).to include('lorem ipsum')
   end
 
   it 'Should extract text from .odt files' do
     file = File.new('spec/fixtures/files/text.odt', 'r')
 
-    expect(subject.text(file)).to match /lorem ipsum/
-    expect(Plaintext::Resolver.new(file, 'application/vnd.oasis.opendocument.text').text).to(
-        match /lorem ipsum fulltext find me!/
-    )
+    expect(subject.text(file).split.join(' ')).to include('lorem ipsum')
+
+    resolver = Plaintext::Resolver.new(file, 'application/vnd.oasis.opendocument.text')
+    expect(resolver.text.split.join(' ')).to include('lorem ipsum fulltext find me!')
   end
 
   it 'Should extract text from .ott files' do
     file = File.new('spec/fixtures/files/text.ott', 'r')
 
-    expect(subject.text(file)).to match /lorem ipsum/
-    expect(Plaintext::Resolver.new(file, 'application/vnd.oasis.opendocument.text-template').text).to(
-        match /lorem ipsum fulltext find me!/
-    )
+    expect(subject.text(file).split.join(' ')).to include('lorem ipsum')
+
+    resolver = Plaintext::Resolver.new(file, 'application/vnd.oasis.opendocument.text-template')
+    expect(resolver.text.split.join(' ')).to include('lorem ipsum fulltext find me!')
   end
 
   it 'Should extract text from .odp files' do
     file = File.new('spec/fixtures/files/presentation.odp', 'r')
 
-    expect(subject.text(file)).to match /The Title find me Slide two Click To Add Text/
-    expect(Plaintext::Resolver.new(file, 'application/vnd.oasis.opendocument.presentation').text).to(
-        match /The Title find me Slide two/
-    )
+    expect(subject.text(file).split.join(' ')).to include('The Title find me Slide two Click To Add Text')
+
+    resolver = Plaintext::Resolver.new(file, 'application/vnd.oasis.opendocument.presentation')
+    expect(resolver.text.split.join(' ')).to include('The Title find me Slide two')
   end
 
   it 'Should extract text from .otp files' do
     file = File.new('spec/fixtures/files/presentation.otp', 'r')
 
-    expect(subject.text(file)).to match /The Title find me Slide two Click To Add Text/
-    expect(Plaintext::Resolver.new(file, 'application/vnd.oasis.opendocument.presentation-template').text).to(
-        match /The Title find me Slide two/
-    )
+    expect(subject.text(file).split.join(' ')).to include('The Title find me Slide two Click To Add Text')
+
+    resolver = Plaintext::Resolver.new(file, 'application/vnd.oasis.opendocument.presentation-template')
+    expect(resolver.text.split.join(' ')).to include('The Title find me Slide two')
   end
 
   it 'Should extract text from .ods files' do
     file = File.new('spec/fixtures/files/spreadsheet.ods', 'r')
 
-    expect(subject.text(file)).to match /lorem ipsum/
-    expect(Plaintext::Resolver.new(file, 'application/vnd.oasis.opendocument.spreadsheet').text).to(
-        match /lorem ipsum fulltext find me!/
-    )
+    expect(subject.text(file).split.join(' ')).to include('lorem ipsum')
+
+    resolver = Plaintext::Resolver.new(file, 'application/vnd.oasis.opendocument.spreadsheet')
+    expect(resolver.text.split.join(' ')).to include('lorem ipsum fulltext find me!')
   end
 
   it 'Should extract text from .ots files' do
     file = File.new('spec/fixtures/files/spreadsheet.ots', 'r')
 
-    expect(subject.text(file)).to match /lorem ipsum/
-    expect(Plaintext::Resolver.new(file, 'application/vnd.oasis.opendocument.spreadsheet-template').text).to(
-        match /lorem ipsum fulltext find me!/
-    )
+    expect(subject.text(file).split.join(' ')).to include('lorem ipsum')
+
+    resolver = Plaintext::Resolver.new(file, 'application/vnd.oasis.opendocument.spreadsheet-template')
+    expect(resolver.text.split.join(' ')).to include('lorem ipsum fulltext find me!')
   end
 
   it 'Should only extract text up to given size limit' do
     file = File.new('spec/fixtures/files/spreadsheet.ots', 'r')
     expect(subject.text(file, max_size: 2)).to eq 'lo'
 
-    r = Plaintext::Resolver.new(file,
-                                'application/vnd.oasis.opendocument.spreadsheet')
+    r = Plaintext::Resolver.new(file, 'application/vnd.oasis.opendocument.spreadsheet')
     r.max_plaintext_bytes = 3
-    expect(r.text).to eq "lor"
+    expect(r.text).to eq 'lor'
   end
 
   it 'Should return a utf8 encoded string' do
     file = File.new('spec/fixtures/files/spreadsheet.ots', 'r')
     expect(subject.text(file).encoding.name).to eq 'UTF-8'
   end
-
-end
+end