rdig 0.3.1 → 0.3.2

data/CHANGES

@@ -1,3 +1,10 @@
+0.3.2
+- make RDig compatible with Ferret 0.10.x
+- won't work any more with Ferret 0.9.x and before
+
+0.3.1
+- Bug fix release: fixed handling of unparseable URLs
+
 0.3.0
 - file system crawling
 - optional url rewriting before indexing, e.g. for linking to results 

data/README

@@ -5,7 +5,7 @@ to help building a site search for web sites or intranets. Internally,
 Ferret is used for the full text indexing. After creating a config file 
 for your site, the index can be built with a single call to rdig.
 
-RDig depends on Ferret (>= 0.3.2) and the RubyfulSoup library (>= 1.0.4).
+RDig depends on Ferret (>= 0.10.0) and the RubyfulSoup library (>= 1.0.4).
 
 == basic usage
 

data/lib/rdig.rb

@@ -24,7 +24,7 @@
 #++
 #
 
-RDIGVERSION = '0.3.1'
+RDIGVERSION = '0.3.2'
 
 
 require 'thread'
@@ -142,7 +142,7 @@ module RDig
             :create              => true,
             :handle_parse_errors => true,
             :analyzer            => Ferret::Analysis::StandardAnalyzer.new,
-            :occur_default       => Ferret::Search::BooleanClause::Occur::MUST
+            :occur_default       => :must
           )
         )
       end

data/lib/rdig/index.rb

@@ -3,27 +3,26 @@ module RDig
   
     # used by the crawler to build the ferret index
     class Indexer
-      include MonitorMixin, Ferret::Index, Ferret::Document
+      include MonitorMixin
       
       def initialize(settings)
         @config = settings
-        @index_writer = IndexWriter.new(settings.path,
-                                        :create   => settings.create,
-                                        :analyzer => settings.analyzer)
+        @index_writer = Ferret::Index::IndexWriter.new(
+                          :path     => settings.path,
+                          :create   => settings.create,
+                          :analyzer => settings.analyzer)
         super() # scary, MonitorMixin won't initialize if we don't call super() here (parens matter)
       end
       
       def add_to_index(document)
         puts "add to index: #{document.uri.to_s}" if RDig::config.verbose
-        doc = Ferret::Document::Document.new
         @config.rewrite_uri.call(document.uri) if @config.rewrite_uri
-        
-        doc << Field.new("url", document.uri.to_s, 
-                        Field::Store::YES, Field::Index::TOKENIZED)
-        doc << Field.new("title", document.title, 
-                        Field::Store::YES, Field::Index::TOKENIZED)
-        doc << Field.new("data",  document.body, 
-                        Field::Store::YES, Field::Index::TOKENIZED)
+        # all stored and tokenized, should be ferret defaults
+        doc = { 
+          :url   => document.uri.to_s,
+          :title => document.title,
+          :data  => document.body
+        }
         synchronize do
           @index_writer << doc
         end

data/rakefile

@@ -129,7 +129,7 @@ else
 
     #### Dependencies and requirements.
 
-    s.add_dependency('ferret', '>= 0.3.2')
+    s.add_dependency('ferret', '>= 0.10.0')
     s.add_dependency('rubyful_soup', '>= 1.0.4')
     #s.requirements << ""
 

metadata

@@ -1,10 +1,10 @@
 --- !ruby/object:Gem::Specification 
-rubygems_version: 0.8.11
+rubygems_version: 0.9.0
 specification_version: 1
 name: rdig
 version: !ruby/object:Gem::Version 
-  version: 0.3.1
-date: 2006-07-26 00:00:00 +02:00
+  version: 0.3.2
+date: 2006-10-09 00:00:00 +02:00
 summary: Ruby based web site indexing and searching library.
 require_paths: 
 - lib
@@ -25,49 +25,50 @@ required_ruby_version: !ruby/object:Gem::Version::Requirement
 platform: ruby
 signing_key: 
 cert_chain: 
+post_install_message: 
 authors: 
 - Jens Kraemer
 files: 
 - bin/rdig
 - lib/rdig
-- lib/rdig.rb
 - lib/htmlentities
-- lib/rdig/documents.rb
-- lib/rdig/file.rb
-- lib/rdig/content_extractors.rb
+- lib/rdig.rb
+- lib/rdig/crawler.rb
 - lib/rdig/search.rb
 - lib/rdig/highlight.rb
 - lib/rdig/index.rb
 - lib/rdig/url_filters.rb
-- lib/rdig/crawler.rb
-- lib/htmlentities/htmlentities.rb
-- lib/htmlentities/README
+- lib/rdig/content_extractors.rb
+- lib/rdig/documents.rb
+- lib/rdig/file.rb
 - lib/htmlentities/CHANGES
 - lib/htmlentities/COPYING
+- lib/htmlentities/README
+- lib/htmlentities/htmlentities.rb
 - test/unit
 - test/fixtures
 - test/test_helper.rb
-- test/unit/html_content_extractor_test.rb
-- test/unit/url_filters_test.rb
-- test/unit/word_content_extractor_test.rb
-- test/unit/crawler_fs_test.rb
 - test/unit/etag_filter_test.rb
+- test/unit/url_filters_test.rb
+- test/unit/html_content_extractor_test.rb
 - test/unit/pdf_content_extractor_test.rb
+- test/unit/word_content_extractor_test.rb
 - test/unit/file_document_test.rb
-- test/fixtures/pdf
+- test/unit/crawler_fs_test.rb
 - test/fixtures/html
+- test/fixtures/pdf
 - test/fixtures/word
-- test/fixtures/pdf/simple.pdf
 - test/fixtures/html/entities.html
-- test/fixtures/html/custom_tag_selectors.html
 - test/fixtures/html/simple.html
+- test/fixtures/html/custom_tag_selectors.html
+- test/fixtures/pdf/simple.pdf
 - test/fixtures/word/simple.doc
 - doc/examples
 - doc/examples/config.rb
-- TODO
 - LICENSE
-- README
+- TODO
 - CHANGES
+- README
 - install.rb
 - rakefile
 test_files: []
@@ -97,7 +98,7 @@ dependencies:
     requirements: 
     - - ">="
       - !ruby/object:Gem::Version 
-        version: 0.3.2
+        version: 0.10.0
     version: 
 - !ruby/object:Gem::Dependency 
   name: rubyful_soup