boilerpipe-ruby 0.3.0 → 0.4.0

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA1:
-  metadata.gz: 64511e224c1ec186c5c7cde62568dd0ba8cf1005
-  data.tar.gz: 455a8bac8eaadda62706d8f507854c6f6ccb6dba
+  metadata.gz: 68c2ea4ee42a6e1d76e85f7eaa3de9ca95f3a8d3
+  data.tar.gz: 42199704467cb7f20a8fff7c616be67bae1966e1
 SHA512:
-  metadata.gz: 8f2f769627e15ca0b8293122143304ef397ed789567cff61ceb48f45a657336442711c17d29d25fa8cfdf0dbcfd557030063e7b2a132550921ce601e2573e71f
-  data.tar.gz: 630f46c4d3a6e71933be0ba5f3bc98dc97fd34d10fb05d9e656e8f5f2f20fb4c28197122ef349398c79de7e57c795721307a5dadc7b4a796f907b2904d4816d0
+  metadata.gz: 875da6a2ddfdf517509e3ebb7b9c804fadf4a372b812df42bce92fccb82eb8ca31283f11e764c6796c15997bcb8fddf24301d821f4e24a962f40ba6f973f6f17
+  data.tar.gz: 5dfec7323587057c64b931725df2aa5b53dc5a2fadaef52374619fe5798826c98c4e7ae8bb1ea9267b5db9f40249d5822752700e57a145b058231088249d1ac6

data/CHANGELOG.md

@@ -1,3 +1,8 @@
+# 0.4.0 / 2017-09-15
+
+* Add KeepEverythingWithMinKWords Extractor
+* Add ArticleSentence Extractor
+
 # 0.3.0 / 2017-09-12
 
 * Add LargestContent Extractor

data/README.md

@@ -16,16 +16,18 @@ Just use either ArticleExtractor, DefaultExtractor or KeepEverythingExtractor -
 
 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)
 
+[![Gem Version](https://badge.fury.io/rb/boilerpipe-ruby.svg)](https://badge.fury.io/rb/boilerpipe-ruby)
+
 ## Installation
 
 Add this line to your application's Gemfile:

data/lib/boilerpipe.rb

@@ -6,9 +6,11 @@ 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'
 
@@ -24,8 +26,11 @@ 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'
 

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/keep_everything_with_k_min_words_extractor.rb

@@ -0,0 +1,21 @@
+
+# A full-text extractor which extracts the largest text component of a page.
+# For news articles, it may perform better than the DefaultExtractor, but
+# usually worse than ArticleExtractor.
+
+module Boilerpipe::Extractors
+  class KeepEverythingWithKMinWordsExtractor
+    def self.text(min, contents)
+      doc = ::Boilerpipe::SAX::BoilerpipeHTMLParser.parse(contents)
+      ::Boilerpipe::Extractors::KeepEverythingWithKMinWordsExtractor.process min, doc
+      doc.content
+    end
+
+    def self.process(min, doc)
+      ::Boilerpipe::Filters::SimpleBlockFusionProcessor.process doc
+      ::Boilerpipe::Filters::MarkEverythingContentFilter.process doc
+      ::Boilerpipe::Filters::MinWordsFilter.process min, doc
+      doc
+    end
+  end
+end

data/lib/boilerpipe/filters/min_clause_words_filter.rb

@@ -0,0 +1,37 @@
+#
+# Keeps only blocks that have at least one segment fragment ("clause") with at least k
+# words (default: 5).
+#
+# NOTE: You might consider using the SplitParagraphBlocksFilter upstream.
+#
+# SplitParagraphBlocksFilter
+
+module Boilerpipe::Filters
+  class MinClauseWordsFilter
+
+    def self.process(doc, min_words=5)
+
+      doc.text_blocks.each do |tb|
+        next if tb.is_not_content?
+
+        clause_delimiter = /[\p{L}\d \u00a0]+[\,.:;!?]+(?:[ \n\r]+|$)/
+        tb.text.scan(clause_delimiter).each do |possible_clause|
+          if is_clause? possible_clause
+            break
+          else
+            tb.content = false
+          end
+        end
+      end
+
+      doc
+    end
+
+    def self.is_clause?(text, min_words=5)
+     return false if text.nil?
+      whitespace = /[ \n\r]+/
+      text.scan(whitespace).size >= min_words
+    end
+
+  end
+end

data/lib/boilerpipe/filters/min_words_filter.rb

@@ -0,0 +1,16 @@
+
+# Keeps only those content blocks which contain at least k words.
+
+module Boilerpipe::Filters
+  class MinWordsFilter
+
+    def self.process(min_words, doc)
+      doc.text_blocks.each do |tb|
+        next if tb.is_not_content?
+        tb.content = false if tb.num_words < min_words
+      end
+      doc
+    end
+
+  end
+end

data/lib/boilerpipe/filters/split_paragraph_blocks_filter.rb

@@ -0,0 +1,40 @@
+
+# Splits TextBlocks at paragraph boundaries.
+#
+# NOTE: This is not fully supported (i.e., it will break highlighting support via
+# #getContainedTextElements()), but this one probably is necessary for some other filters.
+#
+# see MinClauseWordsFilter
+
+module Boilerpipe::Filters
+  class SplitParagraphBlocksFilter
+
+    def self.process(doc)
+      tbs = doc.text_blocks
+      new_blocks = []
+      changes = false
+      tbs.each do |tb|
+        paragraphs = tb.text.split(/[\n\r]+/)
+
+        if paragraphs.size < 2
+          new_blocks << tb
+          next
+        end
+
+        is_content = tb.is_content?
+        labels = tb.labels
+        paragraphs.each do |paragraph|
+          tbP = ::Boilerpipe::Document::TextBlock.new(paragraph)
+          tbP.content = is_content
+          tbP.add_labels(labels)
+          new_blocks << tbP
+          changes = true
+        end
+      end
+
+      doc.replace_text_blocks!(new_blocks) if changes
+      doc
+    end
+
+  end
+end

data/lib/boilerpipe/sax/boilerpipe_html_parser.rb

@@ -4,11 +4,11 @@ module Boilerpipe::SAX
     def self.parse(text)
 
       #script bug - delete script tags
-      text  = text.gsub(/\<script>.+?<\/script>/i, '')
+      text.gsub!(/\<script>.+?<\/script>/i, '')
 
       # nokogiri uses libxml for mri and nekohtml for jruby
       # mri doesn't remove &nbsp; when missing the semicolon
-      text = text.gsub(/(&nbsp) /, '\1; ')
+      text.gsub!(/(&nbsp) /, '\1; ')
 
 
       # use nokogiri to fix any bad tags, errors - keep experimenting with this

data/lib/boilerpipe/version.rb

@@ -1,3 +1,3 @@
 module Boilerpipe
-  VERSION = '0.3.0'
+  VERSION = '0.4.0'
 end

metadata

@@ -1,14 +1,14 @@
 --- !ruby/object:Gem::Specification
 name: boilerpipe-ruby
 version: !ruby/object:Gem::Version
-  version: 0.3.0
+  version: 0.4.0
 platform: ruby
 authors:
 - Gregory Ostermayr
 autorequire: 
 bindir: exe
 cert_chain: []
-date: 2017-09-12 00:00:00.000000000 Z
+date: 2017-09-15 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: bundler
@@ -103,9 +103,11 @@ files:
 - lib/boilerpipe/document/text_document.rb
 - lib/boilerpipe/errors.rb
 - lib/boilerpipe/extractors/article_extractor.rb
+- lib/boilerpipe/extractors/article_sentence_extractor.rb
 - lib/boilerpipe/extractors/canola_extractor.rb
 - lib/boilerpipe/extractors/default_extractor.rb
 - lib/boilerpipe/extractors/keep_everything_extractor.rb
+- lib/boilerpipe/extractors/keep_everything_with_k_min_words_extractor.rb
 - lib/boilerpipe/extractors/largest_content_extractor.rb
 - lib/boilerpipe/extractors/num_words_rules_extractor.rb
 - lib/boilerpipe/filters/block_proximity_fusion.rb
@@ -120,8 +122,11 @@ files:
 - lib/boilerpipe/filters/large_block_same_tag_level_to_content_filter.rb
 - lib/boilerpipe/filters/list_at_end_filter.rb
 - lib/boilerpipe/filters/mark_everything_content_filter.rb
+- lib/boilerpipe/filters/min_clause_words_filter.rb
+- lib/boilerpipe/filters/min_words_filter.rb
 - lib/boilerpipe/filters/num_words_rules_classifier.rb
 - lib/boilerpipe/filters/simple_block_fusion_processor.rb
+- lib/boilerpipe/filters/split_paragraph_blocks_filter.rb
 - lib/boilerpipe/filters/terminating_blocks_finder.rb
 - lib/boilerpipe/filters/trailing_headline_to_boilerplate_filter.rb
 - lib/boilerpipe/labels/default.rb