jruby-boilerpipe 0.0.2 → 0.0.3

checksums.yaml

@@ -1,7 +1,7 @@
 ---
-SHA1:
-  metadata.gz: 7e5ce4c67c60120978ee89b3f1f12fd78004ea7d
-  data.tar.gz: 4f0e3c53f036054f2063a72ff5cfc704c3d8d15b
+SHA256:
+  metadata.gz: 8a36efcb938933662d44ad33cd1887e99c34edf1376d36fc383a5a0424b4b797
+  data.tar.gz: ccdab7fda06435dfc91effb80f1edae0d810c6ef44b728a3e60710275a08d3da
 SHA512:
-  metadata.gz: cfd82a4cdf0feec6f052694ba1fb0bdf63aa80973c48fee3a22f74d9aff1c8c39c2fc75310cb255fc2f6d2c0166571323e37382ec782e8b2ec38c2fb8ecd40be
-  data.tar.gz: 02f2d69c4c36055e3728fc23bba42da998a6891496e442905d75d8f0c818238f9eb1f469cd3442f4dd4c18e0fe26087f70d1e4b6c545323bf8a20654ddb153a2
+  metadata.gz: cda5bbaf4fb99bfa863bcc718d66145481c23c7ded8ccfc57b6a8e6a7280d9e89f67c00c388719f3652727c027158dc19f92f84646bfdc89320f1f05f3e5f74c
+  data.tar.gz: e5bfef4c89ebbe6ba8658fcb653d6605f9a6253eaaa14ff9f13b23840a273c6ba4f495c6099d33852d4c68d655c9da2324606ed4c349412abafda3292f4e8608

data/lib/boilerpipe/extractors/article_extractor.rb

@@ -0,0 +1,23 @@
+module Boilerpipe
+  java_import 'com.kohlschutter.boilerpipe.extractors.ArticleExtractor'
+  java_import 'com.kohlschutter.boilerpipe.util.UnicodeTokenizer'
+  java_import java.net.URL
+
+  class ArticleExtractor
+    def  self.get_text(s)
+      url = nil
+
+      begin
+        url = Java::JavaNet::URL.new(s)
+      rescue Java::JavaNet::MalformedURLException => e
+        # not a URL
+      end
+      input = url ? url : s
+      ArticleExtractor::INSTANCE.get_text(input)
+    end
+
+    class <<self  
+      alias_method :text, :get_text
+    end 
+  end
+end

data/lib/boilerpipe/sax/boilerpipe_html_parser.rb

@@ -0,0 +1,17 @@
+module Boilerpipe
+  module SAX
+    java_import 'com.kohlschutter.boilerpipe.sax.BoilerpipeHTMLParser'
+    java_import 'org.xml.sax.InputSource'
+    java_import java.io.StringReader
+
+    class BoilerpipeHTMLParser
+      def self.parse(text)
+        parser = BoilerpipeHTMLParser.new
+        string_reader = StringReader.new(text)
+        is = InputSource.new(string_reader)
+        parser.parse(is)
+        parser.to_text_document
+      end
+    end
+  end
+end

data/lib/boilerpipe/version.rb

@@ -1,3 +1,3 @@
 module Boilerpipe
-  VERSION = '0.0.2'
+  VERSION = '0.0.3'
 end

data/lib/boilerpipe.rb

@@ -1,26 +1,4 @@
-require 'boilerpipe/version'
 require_relative 'boilerpipe-common-2.0-SNAPSHOT-jar-with-dependencies.jar'
-
-module Boilerpipe
-  java_import 'com.kohlschutter.boilerpipe.extractors.ArticleExtractor'
-  java_import 'com.kohlschutter.boilerpipe.util.UnicodeTokenizer'
-  java_import java.net.URL
-
-  class ArticleExtractor
-    def  self.get_text(s)
-      url = nil
-
-      begin
-        url = Java::JavaNet::URL.new(s)
-      rescue Java::JavaNet::MalformedURLException => e
-        # not a URL
-      end
-      input = url ? url : s
-      ArticleExtractor::INSTANCE.get_text(input)
-    end
-
-    class <<self  
-      alias_method :text, :get_text
-    end 
-  end
-end
+require 'boilerpipe/version'
+require 'boilerpipe/sax/boilerpipe_html_parser'
+require 'boilerpipe/extractors/article_extractor'

metadata

@@ -1,52 +1,52 @@
 --- !ruby/object:Gem::Specification
 name: jruby-boilerpipe
 version: !ruby/object:Gem::Version
-  version: 0.0.2
+  version: 0.0.3
 platform: ruby
 authors:
 - Gregory Ostermayr
-autorequire: 
+autorequire:
 bindir: exe
 cert_chain: []
-date: 2017-08-30 00:00:00.000000000 Z
+date: 2017-09-02 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
-  name: bundler
   requirement: !ruby/object:Gem::Requirement
     requirements:
     - - "~>"
       - !ruby/object:Gem::Version
         version: '1.10'
-  type: :development
+  name: bundler
   prerelease: false
+  type: :development
   version_requirements: !ruby/object:Gem::Requirement
     requirements:
     - - "~>"
       - !ruby/object:Gem::Version
         version: '1.10'
 - !ruby/object:Gem::Dependency
-  name: rake
   requirement: !ruby/object:Gem::Requirement
     requirements:
     - - "~>"
       - !ruby/object:Gem::Version
         version: '10.0'
-  type: :development
+  name: rake
   prerelease: false
+  type: :development
   version_requirements: !ruby/object:Gem::Requirement
     requirements:
     - - "~>"
       - !ruby/object:Gem::Version
         version: '10.0'
 - !ruby/object:Gem::Dependency
-  name: rspec
   requirement: !ruby/object:Gem::Requirement
     requirements:
     - - ">="
       - !ruby/object:Gem::Version
         version: '0'
-  type: :development
+  name: rspec
   prerelease: false
+  type: :development
   version_requirements: !ruby/object:Gem::Requirement
     requirements:
     - - ">="
@@ -69,11 +69,13 @@ files:
 - jruby-boilerpipe.gemspec
 - lib/boilerpipe-common-2.0-SNAPSHOT-jar-with-dependencies.jar
 - lib/boilerpipe.rb
+- lib/boilerpipe/extractors/article_extractor.rb
+- lib/boilerpipe/sax/boilerpipe_html_parser.rb
 - lib/boilerpipe/version.rb
 homepage: https://github.com/gregors/jruby-boilerpipe
 licenses: []
 metadata: {}
-post_install_message: 
+post_install_message:
 rdoc_options: []
 require_paths:
 - lib
@@ -88,9 +90,9 @@ required_rubygems_version: !ruby/object:Gem::Requirement
     - !ruby/object:Gem::Version
       version: '0'
 requirements: []
-rubyforge_project: 
-rubygems_version: 2.4.5
-signing_key: 
+rubyforge_project:
+rubygems_version: 2.6.11
+signing_key:
 specification_version: 4
 summary: Ruby wrapper around boilerpipe java library
 test_files: []