boilerpipe-ruby 0.3.0 → 0.4.4

checksums.yaml

@@ -1,7 +1,7 @@
 ---
-SHA1:
-  metadata.gz: 64511e224c1ec186c5c7cde62568dd0ba8cf1005
-  data.tar.gz: 455a8bac8eaadda62706d8f507854c6f6ccb6dba
+SHA256:
+  metadata.gz: 835e5122c287082ef39874ee0a3365f08910a7a3f70b76c45dc264e8e1301edc
+  data.tar.gz: edff0860c01277adfc703e453e22b1d24c2db1817cfd4ad6800dfc1a6c0f339f
 SHA512:
-  metadata.gz: 8f2f769627e15ca0b8293122143304ef397ed789567cff61ceb48f45a657336442711c17d29d25fa8cfdf0dbcfd557030063e7b2a132550921ce601e2573e71f
-  data.tar.gz: 630f46c4d3a6e71933be0ba5f3bc98dc97fd34d10fb05d9e656e8f5f2f20fb4c28197122ef349398c79de7e57c795721307a5dadc7b4a796f907b2904d4816d0
+  metadata.gz: 7cbeb85f9dd74c930e9999e850d2abca6fd3e9470971461a978295de640195192f633a71a19a20b96824fb5becec2e7841e7f3e257b83b90550c935b6d16ff7b
+  data.tar.gz: 393803c95416f77a467724cd0b451961dcbb9c6e544c6d22a4f71853a041e5f2c32513ffd3f43e9733de43624fce31dad18b9cb7d0c37bd3cd722a6fdf223481

data/.circleci/config.yml

@@ -6,48 +6,30 @@ version: 2
 jobs:
   build:
     docker:
-      # specify the version you desire here
-       - image: circleci/ruby:2.4.1-node-browsers
-      
+       - image: circleci/ruby:2.5.5-node-browsers
+
       # Specify service dependencies here if necessary
       # CircleCI maintains a library of pre-built images
       # documented at https://circleci.com/docs/2.0/circleci-images/
-      # - image: circleci/postgres:9.4
 
     working_directory: ~/repo
 
     steps:
       - checkout
 
-      # Download and cache dependencies
-      - restore_cache:
-          keys:
-          - v1-dependencies-{{ checksum "Gemfile.lock" }}
-          # fallback to using the latest cache if no exact match is found
-          - v1-dependencies-
-
+      - run: gem install bundler
       - run:
           name: install dependencies
           command: |
-            bundle install --jobs=4 --retry=3 --path vendor/bundle
+            bundle install --jobs=4 --retry=3
 
-      - save_cache:
-          paths:
-            - ./vendor/bundle
-          key: v1-dependencies-{{ checksum "Gemfile.lock" }}
-        
-      # Database setup
-      #- run: bundle exec rake db:create
-      #- run: bundle exec rake db:schema:load
-
-      # run tests!
       - run:
           name: run tests
           command: |
             mkdir /tmp/test-results
             TEST_FILES="$(circleci tests glob "spec/**/*_spec.rb")"
-            
-            rspec --format progress "spec"
+
+            bundle exec rspec --format progress "spec"
 
       # collect reports
       - store_test_results:

data/.dockerignore

@@ -0,0 +1,7 @@
+.git
+.gitignore
+ log/*
+ tmp/*
+ *.swp
+ *.swo
+ Gemfile.lock

data/CHANGELOG.md

@@ -1,3 +1,32 @@
+# 0.4.4 / 2021-02-13
+* Do a better job of stripping out script tags
+
+# 0.4.3 / 2020-07-18
+
+* update deps
+
+# 0.4.2 / 2020-03-11
+
+* update deps
+
+# 0.4.1 / 2019-07-04
+
+* Fix bug in min_clause_words_filter ( used in article_sentence_extractor )
+* Allow tests to run in Docker
+* Update circle to continue to work
+* Add architecture flow
+* Code formatting
+* Add min words filter specs
+* Add label action specs
+* Add missing test case to ignorable element spec
+* Add merge_next case to text block spec
+* Dry up includes
+
+# 0.4.0 / 2017-09-15
+
+* Add KeepEverythingWithMinKWords Extractor
+* Add ArticleSentence Extractor
+
 # 0.3.0 / 2017-09-12
 
 * Add LargestContent Extractor
@@ -17,4 +46,4 @@
 
 # 0.1.0 / 2017-09-08
 
-* Add Article Extractor 
+* Add Article Extractor

data/Dockerfile

@@ -0,0 +1,14 @@
+From ruby:2.5
+RUN gem install bundler
+COPY *gemspec /usr/src/app/
+COPY Gemfile /usr/src/app/
+COPY lib/boilerpipe/version.rb /usr/src/app/lib/boilerpipe/
+COPY bin /usr/src/app/
+COPY bin/* /usr/src/app/bin/
+
+WORKDIR /usr/src/app
+RUN bin/setup
+
+COPY . /usr/src/app/
+
+CMD ["bundle", "exec", "rspec", "--color", "--format", "doc"]

data/README.md

@@ -1,5 +1,8 @@
 # Boilerpipe
 
+[![CircleCI](https://circleci.com/gh/gregors/boilerpipe-ruby/tree/master.svg?style=shield)](https://circleci.com/gh/gregors/boilerpipe-ruby/tree/master)
+[![Gem Version](https://badge.fury.io/rb/boilerpipe-ruby.svg)](https://badge.fury.io/rb/boilerpipe-ruby)
+
 A pure ruby implemenation of the boilerpipe algorithm.
 
 This is a text extraction utility first written by Christian Kohlshutter - [presentation](http://videolectures.net/wsdm2010_kohlschutter_bdu/)
@@ -10,21 +13,22 @@ I saw other gems making use of boilerpipe via the [free api](http://boilerpipe-w
 
 This solution works great if you're using Jruby but I wanted a pure ruby solution to use on MRI. Open vim - start coding...
 
+Here's a high level [diagram](boilerpipe_flow.md) of how the system works.
+
 # TLDR
 
 Just use either ArticleExtractor, DefaultExtractor or KeepEverythingExtractor - try out the others when you feel like experimenting...
 
 Presently the follow Extractors are implemented
 * [x] ArticleExtractor
-* [ ] ArticleSentenceExtractor
+* [x] ArticleSentenceExtractor
 * [x] CanolaExtractor
 * [x] DefaultExtractor
 * [x] KeepEverythingExtractor
-* [ ] KeepEverythingWithMinKWordsExtractor
+* [x] KeepEverythingWithMinKWordsExtractor
 * [x] LargestContentExtractor
 * [x] NumWordsRulesExtractor
 
-[![CircleCI](https://circleci.com/gh/gregors/boilerpipe-ruby/tree/master.svg?style=shield)](https://circleci.com/gh/gregors/boilerpipe-ruby/tree/master)
 
 ## Installation
 
@@ -67,7 +71,14 @@ Or install it yourself as:
 
 After checking out the repo, run `bin/setup` to install dependencies. Then, run `rake spec` to run the tests. You can also run `bin/console` for an interactive prompt that will allow you to experiment.
 
-To install this gem onto your local machine, run `bundle exec rake install`. To release a new version, update the version number in `version.rb`, and then run `bundle exec rake release`, which will create a git tag for the version, push git commits and tags, and push the `.gem` file to [rubygems.org](https://rubygems.org).
+To install this gem onto your local machine, run `bundle exec rake install`.
+
+### Running Tests on Docker
+
+The default run command will run the tests
+
+    docker build -t boilerpipe .
+    docker run -it --rm boilerpipe
 
 ## Contributing
 

data/Rakefile

@@ -1,14 +1,13 @@
-require "bundler/gem_tasks"
-require "rspec/core/rake_task"
+require 'bundler/gem_tasks'
+require 'rspec/core/rake_task'
 
 RSpec::Core::RakeTask.new(:spec)
 
 task :default => :spec
 
-
 desc 'Downloads forked boilerpipe jar from Gregors github for sanity checks'
 task :download_boilerpipe_jar do
   FileUtils.mkdir_p 'spec/sanity_checks/jars/'
   Dir.chdir 'spec/sanity_checks/jars/'
- `wget 'https://github.com/gregors/jruby-boilerpipe/raw/master/lib/boilerpipe-common-2.0-SNAPSHOT-jar-with-dependencies.jar'`
+  `wget 'https://github.com/gregors/jruby-boilerpipe/raw/master/lib/boilerpipe-common-2.0-SNAPSHOT-jar-with-dependencies.jar'`
 end

data/bin/console

@@ -1,7 +1,7 @@
 #!/usr/bin/env ruby
 
-require "bundler/setup"
-require "boilerpipe"
+require 'bundler/setup'
+require 'boilerpipe'
 
 # You can add fixtures and/or initialization code here to make experimenting
 # with your gem easier. You can also use a different console, if you like.
@@ -10,5 +10,5 @@ require "boilerpipe"
 # require "pry"
 # Pry.start
 
-require "irb"
+require 'irb'
 IRB.start

data/boilerpipe-ruby.gemspec

@@ -10,18 +10,18 @@ Gem::Specification.new do |spec|
   spec.email         = ['<gregory.ostermayr@gmail.com>']
   spec.license       = 'Apache 2.0'
 
-  spec.summary       = %q{A pure ruby implemenation of the boilerpipe algorithm}
-  spec.description   = %q{A pure ruby implementation of the boilerpipe algorithm}
+  spec.summary       = %q{A pure ruby implementation of the boilerpipe web content extraction algorithm}
+  spec.description   = %q{A pure ruby implementation of the boilerpipe web content extraction algorithm}
   spec.homepage      = 'https://github.com/gregors/boilerpipe-ruby'
 
   spec.files         = `git ls-files -z`.split("\x0").reject { |f| f.match(%r{^(test|spec|features)/}) }
-  spec.bindir        = "exe"
+  spec.bindir        = 'exe'
   spec.executables   = spec.files.grep(%r{^exe/}) { |f| File.basename(f) }
-  spec.require_paths = ["lib"]
+  spec.require_paths = ['lib']
 
-  spec.add_development_dependency 'bundler', '~> 1.11'
-  spec.add_development_dependency 'rake', '~> 10.0'
-  spec.add_development_dependency 'rspec', '~> 3.0'
-  spec.add_development_dependency 'rickshaw', '~> 0.4.0'
-  spec.add_runtime_dependency 'nokogiri', '>= 1.6.6.2'
+  spec.add_development_dependency 'bundler', '~> 2.0'
+  spec.add_development_dependency 'rake', '>= 12.3.3'
+  spec.add_development_dependency 'rickshaw', '~> 0.5.0'
+  spec.add_development_dependency 'rspec', '~> 3.10'
+  spec.add_runtime_dependency 'nokogiri', '~> 1.10'
 end

data/boilerpipe_flow.md

@@ -0,0 +1,40 @@
+```
+raw html
+   |
+   |
+  sax input -> sax parser(html parser) ->  HTML Content handler -> tokenizer ---------
+                                                                                     |
+    -------------------------------------<------------------------------------<------|
+    |              |            |
+text blocks    text blocks  text blocks
+    |              |            |
+    |              |            |
+    -----------------------------
+          |
+          |
+     text document
+          |
+          |
+        filter
+          |
+        filter
+          |
+        filter
+          |
+        filter
+          |
+        filter
+          |
+        filter
+          |
+        filter
+          |
+        filter
+          |
+        filter
+          |
+          |
+     text document
+          |
+  outputs extracted text
+  ```

data/lib/boilerpipe.rb

@@ -1,3 +1,6 @@
+require 'nokogiri'
+require 'set'
+
 require 'boilerpipe/version'
 
 require 'boilerpipe/util/unicode_tokenizer'
@@ -6,9 +9,11 @@ require 'boilerpipe/document/text_document'
 require 'boilerpipe/document/text_block'
 
 require 'boilerpipe/extractors/article_extractor'
+require 'boilerpipe/extractors/article_sentence_extractor'
 require 'boilerpipe/extractors/canola_extractor'
 require 'boilerpipe/extractors/default_extractor'
 require 'boilerpipe/extractors/keep_everything_extractor'
+require 'boilerpipe/extractors/keep_everything_with_k_min_words_extractor'
 require 'boilerpipe/extractors/largest_content_extractor'
 require 'boilerpipe/extractors/num_words_rules_extractor'
 
@@ -24,14 +29,18 @@ require 'boilerpipe/filters/keep_largest_block_filter'
 require 'boilerpipe/filters/large_block_same_tag_level_to_content_filter'
 require 'boilerpipe/filters/list_at_end_filter'
 require 'boilerpipe/filters/mark_everything_content_filter'
+require 'boilerpipe/filters/min_clause_words_filter'
+require 'boilerpipe/filters/min_words_filter'
 require 'boilerpipe/filters/num_words_rules_classifier'
 require 'boilerpipe/filters/simple_block_fusion_processor'
+require 'boilerpipe/filters/split_paragraph_blocks_filter'
 require 'boilerpipe/filters/terminating_blocks_finder'
 require 'boilerpipe/filters/trailing_headline_to_boilerplate_filter'
 
 require 'boilerpipe/labels/default'
 require 'boilerpipe/labels/label_action'
 
+require 'boilerpipe/sax/preprocessor'
 require 'boilerpipe/sax/html_content_handler'
 require 'boilerpipe/sax/boilerpipe_html_parser'
 require 'boilerpipe/sax/tag_action_map'

data/lib/boilerpipe/document/text_block.rb

@@ -1,10 +1,7 @@
-require 'set'
-
 module Boilerpipe
   module Document
     class TextBlock
-
-       #EMPTY_END = TextBlock.new('', 0, 0, 0, 0, 999999999999999999999999999)
+      # EMPTY_END = TextBlock.new('', 0, 0, 0, 0, 999999999999999999999999999)
 
       attr_reader :text, :num_words, :num_words_in_wrapped_lines, :num_words_in_anchor_text,
                   :num_wrapped_lines, :offset_blocks_start, :offset_blocks_end, :text_density,
@@ -12,7 +9,7 @@ module Boilerpipe
 
       attr_accessor :content
 
-      def initialize(text, num_words=0, num_words_in_anchor_text=0, num_words_in_wrapped_lines=0, num_wrapped_lines=1, offset_blocks=0)
+      def initialize(text, num_words = 0, num_words_in_anchor_text = 0, num_words_in_wrapped_lines = 0, num_wrapped_lines = 1, offset_blocks = 0)
         @labels = Set.new
         @text = text
         @num_words = num_words
@@ -32,9 +29,9 @@ module Boilerpipe
         new('', 0, 0, 0, 0, -1)
       end
 
-     def set_tag_level(level)
-       @tag_level = level
-     end
+      def set_tag_level(level)
+        @tag_level = level
+      end
 
       def is_content?
         @content
@@ -68,8 +65,8 @@ module Boilerpipe
         @num_words_in_anchor_text += other.num_words_in_anchor_text
         @num_words_in_wrapped_lines += other.num_words_in_wrapped_lines
         @num_wrapped_lines += other.num_wrapped_lines
-        @offset_blocks_start = [@offset_blocks_start , other.offset_blocks_start].min
-        @offset_blocks_end = [@offset_blocks_end , other.offset_blocks_end].max
+        @offset_blocks_start = [@offset_blocks_start, other.offset_blocks_start].min
+        @offset_blocks_end = [@offset_blocks_end, other.offset_blocks_end].max
         init_densities
         @content |= other.is_content?
 
@@ -87,10 +84,10 @@ module Boilerpipe
       end
 
       def to_s
-        #"[" + offsetBlocksStart + "-" + offsetBlocksEnd + ";tl=" + tagLevel + "; nw=" + numWords + ";nwl=" + numWrappedLines + ";ld=" + linkDensity + "]\t" + (isContent ? "CONTENT" : "boilerplate") + "," + labels + "\n" + getText();
+        # "[" + offsetBlocksStart + "-" + offsetBlocksEnd + ";tl=" + tagLevel + "; nw=" + numWords + ";nwl=" + numWrappedLines + ";ld=" + linkDensity + "]\t" + (isContent ? "CONTENT" : "boilerplate") + "," + labels + "\n" + getText();
         labels = 'null'
         if !@labels.empty?
-          labels ="[#{ @labels.to_a.join(',')}]"
+          labels = "[#{@labels.to_a.join(',')}]"
         end
         "[#{@offset_blocks_start}-#{@offset_blocks_end};tl=#{@tag_level}; nw=#{@num_words};nwl=#{@num_wrapped_lines};ld=#{@link_density}]\t#{is_content? ? 'CONTENT' : 'BOILERPLATE'},#{labels}\n#{text}"
       end
@@ -100,6 +97,7 @@ module Boilerpipe
       end
 
       private
+
       def init_densities
         if @num_words_in_wrapped_lines == 0
           @num_words_in_wrapped_lines = @num_words

data/lib/boilerpipe/document/text_document.rb

@@ -19,14 +19,14 @@ module Boilerpipe
           case text_block.is_content?
           when true
             next unless include_content
-            s << text_block.text
-            s << "\n"
           when false
             next unless include_noncontent
-           s << text_block.text
-           s << "\n"
           end
+
+          s << text_block.text
+          s << "\n"
         end
+
         s
       end
 
@@ -38,7 +38,6 @@ module Boilerpipe
         @text_blocks.map(&:to_s).join("\n")
       end
       alias_method :debug_string, :debug_s
-
     end
   end
 end

data/lib/boilerpipe/extractors/article_sentence_extractor.rb

@@ -0,0 +1,17 @@
+# A full-text extractor which is tuned towards extracting sentences from news articles.
+
+module Boilerpipe::Extractors
+  class ArticleSentenceExtractor
+    def self.text(contents)
+      doc = ::Boilerpipe::SAX::BoilerpipeHTMLParser.parse(contents)
+      ::Boilerpipe::Extractors::ArticleSentenceExtractor.process(doc)
+      doc.content
+    end
+
+    def self.process(doc)
+      ::Boilerpipe::Extractors::ArticleExtractor.process doc
+      ::Boilerpipe::Filters::SplitParagraphBlocksFilter.process doc
+      ::Boilerpipe::Filters::MinClauseWordsFilter.process doc
+    end
+  end
+end

data/lib/boilerpipe/extractors/canola_extractor.rb

@@ -1,6 +1,5 @@
 module Boilerpipe::Extractors
   class CanolaExtractor
-
     def self.text(contents)
       doc = ::Boilerpipe::SAX::BoilerpipeHTMLParser.parse(contents)
       ::Boilerpipe::Extractors::CanolaExtractor.process doc