RubyGems - nddrylliog_pismo - Versions diffs - 0.7.3 - Mend

nddrylliog_pismo 0.7.3

This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.

Files changed (43) hide show

data/.document +5 -0
data/.gitignore +29 -0
data/Gemfile +4 -0
data/LICENSE +23 -0
data/NOTICE +4 -0
data/README.markdown +131 -0
data/Rakefile +72 -0
data/bin/pismo +45 -0
data/lib/pismo.rb +82 -0
data/lib/pismo/document.rb +67 -0
data/lib/pismo/external_attributes.rb +14 -0
data/lib/pismo/internal_attributes.rb +316 -0
data/lib/pismo/reader.rb +19 -0
data/lib/pismo/reader/base.rb +259 -0
data/lib/pismo/reader/cluster.rb +171 -0
data/lib/pismo/reader/tree.rb +154 -0
data/lib/pismo/stopwords.txt +1002 -0
data/lib/pismo/version.rb +3 -0
data/pismo.gemspec +30 -0
data/test/corpus/bbcnews.html +2131 -0
data/test/corpus/bbcnews2.html +1575 -0
data/test/corpus/briancray.html +269 -0
data/test/corpus/cant_read.html +426 -0
data/test/corpus/factor.html +1362 -0
data/test/corpus/gmane.html +138 -0
data/test/corpus/huffington.html +2932 -0
data/test/corpus/metadata_expected.yaml +72 -0
data/test/corpus/metadata_expected.yaml.old +122 -0
data/test/corpus/queness.html +919 -0
data/test/corpus/reader_expected.yaml +39 -0
data/test/corpus/readers/cluster_expected.yaml +45 -0
data/test/corpus/readers/tree_expected.yaml +55 -0
data/test/corpus/rubyinside.html +318 -0
data/test/corpus/rww.html +1351 -0
data/test/corpus/spolsky.html +298 -0
data/test/corpus/techcrunch.html +1285 -0
data/test/corpus/tweet.html +360 -0
data/test/corpus/youtube.html +2348 -0
data/test/corpus/zefrank.html +535 -0
data/test/helper.rb +15 -0
data/test/test_corpus.rb +54 -0
data/test/test_pismo_document.rb +34 -0
metadata +156 -0

data/test/helper.rb ADDED

@@ -0,0 +1,15 @@
+require 'rubygems'
+require 'test/unit'
+require 'shoulda'
+require 'open-uri'
+require 'yaml'
+begin; require 'turn'; rescue LoadError; end
+$LOAD_PATH.unshift(File.join(File.dirname(__FILE__), '..', 'lib'))
+$LOAD_PATH.unshift(File.dirname(__FILE__))
+require 'pismo'
+class Test::Unit::TestCase
+  include Pismo
+  HTML_DIRECTORY = File.dirname(__FILE__) + "/corpus"
+end

data/test/test_corpus.rb ADDED

@@ -0,0 +1,54 @@
+require 'helper'
+class TestCorpus < Test::Unit::TestCase
+  context "A corpus of HTML documents" do
+    setup do
+      # Load the corpus files' HTML content into a hash
+      @corpus = {}
+      Dir[HTML_DIRECTORY + "/*.html"].each { |filename| @corpus[File.basename(filename).sub(/\.html$/, '').to_sym] = File.read(filename) }
+      # Load the "expected metadata" ready for tests
+      @metadata = YAML.load(open(HTML_DIRECTORY + "/metadata_expected.yaml"))
+      @reader_metadata = YAML.load(open(HTML_DIRECTORY + "/reader_expected.yaml"))
+      @readers = {}
+      Dir[HTML_DIRECTORY + "/readers/*_expected.yaml"].each { |filename| @readers[File.basename(filename).sub(/_expected\.yaml$/, '').to_sym] = File.read(filename) }
+    end
+    should "pass basic sanitization and result in Nokogiri documents" do
+      @corpus.values.each do |html|
+        doc = Document.new(html)
+        assert doc.html.length > 1000
+        assert doc.doc.kind_of?(Nokogiri::HTML::Document)
+      end
+    end
+    should "pass metadata extraction tests" do
+      @metadata.each do |file, expected|
+        @doc = Document.new(@corpus[file])
+        expected.each do |k, v|
+          assert_equal v, @doc.send(k)
+        end
+      end
+    end
+    should "pass base reader content extraction tests" do
+      @reader_metadata.each do |file, expected|
+        @doc = Reader::Document.create(@corpus[file])
+        assert_equal expected, @doc.sentences(2)
+      end
+    end
+    should "pass reader content extraction tests" do
+      @readers.each do |reader, expected|
+        results = YAML.load(expected)
+        results.each_key do |file|
+          @doc = Document.new(@corpus[file], :reader => reader)
+          assert_equal results[file], @doc.body
+        end
+      end
+    end
+  end
+end

data/test/test_pismo_document.rb ADDED

@@ -0,0 +1,34 @@
+require 'helper'
+class TestPismoDocument < Test::Unit::TestCase
+  context "Pismo::Document" do
+    should "process an IO/File object" do
+      doc = Document.new(open(HTML_DIRECTORY + "/rubyinside.html"))
+      assert doc.doc.kind_of?(Nokogiri::HTML::Document)
+    end
+  end
+  context "A very basic Pismo document" do
+    setup do
+      @doc = Document.new(%{<html><body><h1>Hello</h1></body></html>})
+    end
+    should "pass sanitization" do
+      assert_equal %{<!DOCTYPE html PUBLIC "-//W3C//DTD HTML 4.0 Transitional//EN" "http://www.w3.org/TR/REC-html40/loose.dtd">\n<html><body><h1>Hello</h1></body></html>\n}, @doc.html
+    end
+    should "result in a Nokogiri document" do
+      assert @doc.doc.kind_of?(Nokogiri::HTML::Document)
+    end
+  end
+  context "A basic real world blog post" do
+    setup do
+      @doc = Document.new(open(HTML_DIRECTORY + "/rubyinside.html"))
+    end
+    should "provide a title" do
+      assert_equal  "CoffeeScript: A New Language With A Pure Ruby Compiler", @doc.title
+    end
+  end
+end

metadata ADDED

@@ -0,0 +1,156 @@
+--- !ruby/object:Gem::Specification
+name: nddrylliog_pismo
+version: !ruby/object:Gem::Version
+  version: 0.7.3
+  prerelease:
+platform: ruby
+authors:
+- Peter Cooper
+autorequire:
+bindir: bin
+cert_chain: []
+date: 2010-12-19 00:00:00.000000000 Z
+dependencies:
+- !ruby/object:Gem::Dependency
+  name: shoulda
+  requirement: &14086660 !ruby/object:Gem::Requirement
+    none: false
+    requirements:
+    - - ! '>='
+      - !ruby/object:Gem::Version
+        version: '0'
+  type: :development
+  prerelease: false
+  version_requirements: *14086660
+- !ruby/object:Gem::Dependency
+  name: awesome_print
+  requirement: &14085980 !ruby/object:Gem::Requirement
+    none: false
+    requirements:
+    - - ! '>='
+      - !ruby/object:Gem::Version
+        version: '0'
+  type: :runtime
+  prerelease: false
+  version_requirements: *14085980
+- !ruby/object:Gem::Dependency
+  name: nokogiri
+  requirement: &14085420 !ruby/object:Gem::Requirement
+    none: false
+    requirements:
+    - - ! '>='
+      - !ruby/object:Gem::Version
+        version: '0'
+  type: :runtime
+  prerelease: false
+  version_requirements: *14085420
+- !ruby/object:Gem::Dependency
+  name: sanitize
+  requirement: &14084820 !ruby/object:Gem::Requirement
+    none: false
+    requirements:
+    - - ! '>='
+      - !ruby/object:Gem::Version
+        version: '0'
+  type: :runtime
+  prerelease: false
+  version_requirements: *14084820
+- !ruby/object:Gem::Dependency
+  name: fast-stemmer
+  requirement: &14084200 !ruby/object:Gem::Requirement
+    none: false
+    requirements:
+    - - ! '>='
+      - !ruby/object:Gem::Version
+        version: '0'
+  type: :runtime
+  prerelease: false
+  version_requirements: *14084200
+- !ruby/object:Gem::Dependency
+  name: chronic
+  requirement: &14100720 !ruby/object:Gem::Requirement
+    none: false
+    requirements:
+    - - ! '>='
+      - !ruby/object:Gem::Version
+        version: '0'
+  type: :runtime
+  prerelease: false
+  version_requirements: *14100720
+description: Pismo extracts and retrieves content-related metadata from HTML pages
+  - you can use the resulting data in an organized way, such as a summary/first paragraph,
+  body text, keywords, RSS feed URL, favicon, etc.
+email:
+- git@peterc.org
+executables:
+- pismo
+extensions: []
+extra_rdoc_files: []
+files:
+- .document
+- .gitignore
+- Gemfile
+- LICENSE
+- NOTICE
+- README.markdown
+- Rakefile
+- bin/pismo
+- lib/pismo.rb
+- lib/pismo/document.rb
+- lib/pismo/external_attributes.rb
+- lib/pismo/internal_attributes.rb
+- lib/pismo/reader.rb
+- lib/pismo/reader/base.rb
+- lib/pismo/reader/cluster.rb
+- lib/pismo/reader/tree.rb
+- lib/pismo/stopwords.txt
+- lib/pismo/version.rb
+- pismo.gemspec
+- test/corpus/bbcnews.html
+- test/corpus/bbcnews2.html
+- test/corpus/briancray.html
+- test/corpus/cant_read.html
+- test/corpus/factor.html
+- test/corpus/gmane.html
+- test/corpus/huffington.html
+- test/corpus/metadata_expected.yaml
+- test/corpus/metadata_expected.yaml.old
+- test/corpus/queness.html
+- test/corpus/reader_expected.yaml
+- test/corpus/readers/cluster_expected.yaml
+- test/corpus/readers/tree_expected.yaml
+- test/corpus/rubyinside.html
+- test/corpus/rww.html
+- test/corpus/spolsky.html
+- test/corpus/techcrunch.html
+- test/corpus/tweet.html
+- test/corpus/youtube.html
+- test/corpus/zefrank.html
+- test/helper.rb
+- test/test_corpus.rb
+- test/test_pismo_document.rb
+homepage: http://github.com/peterc/pismo
+licenses: []
+post_install_message:
+rdoc_options: []
+require_paths:
+- lib
+required_ruby_version: !ruby/object:Gem::Requirement
+  none: false
+  requirements:
+  - - ! '>='
+    - !ruby/object:Gem::Version
+      version: '0'
+required_rubygems_version: !ruby/object:Gem::Requirement
+  none: false
+  requirements:
+  - - ! '>='
+    - !ruby/object:Gem::Version
+      version: '0'
+requirements: []
+rubyforge_project: nddrylliog_pismo
+rubygems_version: 1.8.17
+signing_key:
+specification_version: 3
+summary: Extracts or retrieves content-related metadata from HTML pages
+test_files: []