ferret 0.11.3 → 0.11.4

data/lib/ferret/browser/views/term/termdocs.rhtml

@@ -0,0 +1 @@
+<%= @reader.term_positions_for(@field, @term).to_json(:fast) %>

data/lib/ferret/browser/webrick.rb

@@ -0,0 +1,14 @@
+module WEBrick
+  class FerretBrowserHandler < WEBrick::HTTPServlet::AbstractServlet
+    # Creates a FerretBrowserHandler, which answers for the application
+    # within +klass+.
+    def initialize(server, reader, path)
+        super(server)
+        @delegator = Ferret::Browser::Delegator.new(reader, path)
+    end
+    # Handler for WEBrick requests (also aliased as do_POST).
+    def do_GET(req, res)
+      res.status, res.content_type, res.body = @delegator.run(req.meta_vars)
+    end
+  end
+end

data/lib/ferret/index.rb

@@ -387,40 +387,54 @@ module Ferret::Index
       end
     end
 
-    # Retrieve the document referenced by the document number +id+, if id is
-    # an integer or the first document with term +id+ if +id+ is a term.
+    # Retrieves a document/documents from the index. The method for retrieval
+    # depends on the type of the argument passed.
     #
-    # id:: The number of the document to retrieve, or the term used as the :id
-    #      for the document we wish to retrieve
-    def doc(*args)
+    # If +arg+ is an Integer then return the document based on the internal
+    # document number.
+    #
+    # If +arg+ is a Range, then return the documents within the range based on
+    # internal document number.
+    #
+    # If +arg+ is a String then search for the first document with +arg+ in
+    # the +id+ field. The +id+ field is either :id or whatever you set
+    # :id_field parameter to when you create the Index object.
+    def doc(*arg)
       @dir.synchronize do
-        ensure_reader_open()
-        id = args[0]
+        id = arg[0]
         if id.kind_of?(String) or id.kind_of?(Symbol)
+          ensure_reader_open()
           term_doc_enum = @reader.term_docs_for(@id_field, id.to_s)
           return term_doc_enum.next? ? @reader[term_doc_enum.doc] : nil
+        else
+          ensure_reader_open(false)
+          return @reader[*arg]
         end
-        return @reader[*args]
       end
     end
     alias :[] :doc
 
-    # Delete the document referenced by the document number +id+ if +id+ is an
-    # integer or all of the documents which have the term +id+ if +id+ is a
-    # term..
+    # Deletes a document/documents from the index. The method for determining
+    # the document to delete depends on the type of the argument passed.
+    #
+    # If +arg+ is an Integer then delete the document based on the internal
+    # document number. Will raise an error if the document does not exist.
     #
-    # id:: The number of the document to delete
-    def delete(id)
+    # If +arg+ is a String then search for the documents with +arg+ in the
+    # +id+ field. The +id+ field is either :id or whatever you set :id_field
+    # parameter to when you create the Index object. Will fail quietly if the
+    # no document exists.
+    def delete(arg)
       @dir.synchrolock do
         ensure_writer_open()
-        if id.is_a?(String) or id.is_a?(Symbol)
+        if arg.is_a?(String) or arg.is_a?(Symbol)
           ensure_writer_open()
-          @writer.delete(@id_field, id.to_s)
-        elsif id.is_a?(Integer)
+          @writer.delete(@id_field, arg.to_s)
+        elsif arg.is_a?(Integer)
           ensure_reader_open()
-          cnt = @reader.delete(id)
+          cnt = @reader.delete(arg)
         else
-          raise ArgumentError, "Cannot delete for id of type #{id.class}"
+          raise ArgumentError, "Cannot delete for arg of type #{arg.class}"
         end
         flush() if @auto_flush
       end
@@ -537,12 +551,15 @@ module Ferret::Index
     # index.
     def flush()
       @dir.synchronize do
-        @searcher.close if @searcher
-        @reader.close if @reader
-        @writer.close if @writer
-        @reader = nil
-        @writer = nil
-        @searcher = nil
+        if @reader
+          if @searcher
+            @searcher.close
+            @searcher = nil
+          end
+          @reader.commit
+        elsif @writer
+          @writer.commit
+        end
       end
     end
     alias :commit :flush
@@ -614,7 +631,7 @@ module Ferret::Index
     #             false.
     def persist(directory, create = true)
       synchronize do
-        flush()
+        close_all()
         old_dir = @dir
         if directory.is_a?(String)
           @dir = FSDirectory.new(directory, create)
@@ -684,19 +701,22 @@ module Ferret::Index
       end
 
       # returns the new reader if one is opened
-      def ensure_reader_open()
+      def ensure_reader_open(get_latest = true)
         raise "tried to use a closed index" if not @open
         if @reader
-          latest = false
-          begin
-            latest = @reader.latest?
-          rescue Lock::LockError => le
-            sleep(@options[:lock_retry_time]) # sleep for 2 seconds and try again
-            latest = @reader.latest?
-          end
-          if not latest
-            @reader.close
-            return @reader = IndexReader.new(@dir)
+          if get_latest
+            latest = false
+            begin
+              latest = @reader.latest?
+            rescue Lock::LockError => le
+              sleep(@options[:lock_retry_time]) # sleep for 2 seconds and try again
+              latest = @reader.latest?
+            end
+            if not latest
+              @searcher.close if @searcher
+              @reader.close
+              return @reader = IndexReader.new(@dir)
+            end
           end
         else
           if @writer
@@ -737,6 +757,17 @@ module Ferret::Index
 
         return @searcher.search(query, options)
       end
+
+      def close_all()
+        @dir.synchronize do
+          @searcher.close if @searcher
+          @reader.close if @reader
+          @writer.close if @writer
+          @reader = nil
+          @searcher = nil
+          @writer = nil
+        end
+      end
   end
 end
 

data/lib/ferret_version.rb

@@ -1,3 +1,3 @@
 module Ferret
-  VERSION = '0.11.3'
+  VERSION = '0.11.4'
 end

data/test/unit/analysis/tc_analyzer.rb

@@ -38,7 +38,7 @@ class AnalyzerTest < Test::Unit::TestCase
     assert_equal(Token.new("ADDRESS", 39, 46), t.next())
     assert(! t.next())
   end
-end if (/utf-8/i !~ Ferret.locale)
+end if (/utf-8/i =~ Ferret.locale)
 
 class AsciiLetterAnalyzerTest < Test::Unit::TestCase
   include Ferret::Analysis
@@ -131,7 +131,7 @@ class LetterAnalyzerTest < Test::Unit::TestCase
     assert_equal(Token.new("öîí", 80, 86), t.next)
     assert(! t.next())
   end
-end if (/utf-8/i !~ Ferret.locale)
+end if (/utf-8/i =~ Ferret.locale)
 
 class AsciiWhiteSpaceAnalyzerTest < Test::Unit::TestCase
   include Ferret::Analysis
@@ -214,7 +214,7 @@ class WhiteSpaceAnalyzerTest < Test::Unit::TestCase
     assert_equal(Token.new('áägç®êëì¯úøã¬öîí', 55, 86), t.next)
     assert(! t.next())
   end
-end if (/utf-8/i !~ Ferret.locale)
+end if (/utf-8/i =~ Ferret.locale)
 
 class AsciiStandardAnalyzerTest < Test::Unit::TestCase
   include Ferret::Analysis
@@ -350,7 +350,7 @@ class StandardAnalyzerTest < Test::Unit::TestCase
     assert_equal(Token.new('öîí', 142, 148), t2.next)
     assert(! t2.next())
   end
-end if (/utf-8/i !~ Ferret.locale)
+end if (/utf-8/i =~ Ferret.locale)
 
 class PerFieldAnalyzerTest < Test::Unit::TestCase
   include Ferret::Analysis
@@ -545,4 +545,4 @@ class CustomAnalyzerTest < Test::Unit::TestCase
     assert_equal(Token.new("dêbater", 36, 44), t.next)
     assert(! t.next())
   end
-end if (/utf-8/i !~ Ferret.locale)
+end if (/utf-8/i =~ Ferret.locale)

data/test/unit/analysis/tc_token_stream.rb

@@ -109,7 +109,7 @@ class LetterTokenizerTest < Test::Unit::TestCase
     assert_equal(Token.new('öîí', 80, 86), t.next)
     assert(! t.next())
   end
-end if (/utf-8/i !~ Ferret.locale)
+end if (/utf-8/i =~ Ferret.locale)
 
 class AsciiWhiteSpaceTokenizerTest < Test::Unit::TestCase
   include Ferret::Analysis
@@ -186,7 +186,7 @@ class WhiteSpaceTokenizerTest < Test::Unit::TestCase
     assert_equal(Token.new('áägç®êëì¯úøã¬öîí', 55, 86), t.next)
     assert(! t.next())
   end
-end if (/utf-8/i !~ Ferret.locale)
+end if (/utf-8/i =~ Ferret.locale)
 
 class AsciiStandardTokenizerTest < Test::Unit::TestCase
   include Ferret::Analysis
@@ -275,7 +275,7 @@ class StandardTokenizerTest < Test::Unit::TestCase
     assert_equal(Token.new('www.davebalmain.com/trac-site', 25, 61), t.next)
     assert(! t.next())
   end
-end if (/utf-8/i !~ Ferret.locale)
+end if (/utf-8/i =~ Ferret.locale)
 
 class RegExpTokenizerTest < Test::Unit::TestCase
   include Ferret::Analysis
@@ -428,7 +428,7 @@ END
     assert_equal(Token.new('szzzt', 256, 264), t.next)
     assert(! t.next())
   end
-end if (/utf-8/i !~ Ferret.locale)
+end if (/utf-8/i =~ Ferret.locale)
 
 class StopFilterTest < Test::Unit::TestCase
   include Ferret::Analysis

data/test/unit/index/tc_index.rb

@@ -150,7 +150,7 @@ class IndexTest < Test::Unit::TestCase
     fs_path = File.expand_path(File.join(File.dirname(__FILE__), '../../temp/fsdir'))
 
     Dir[File.join(fs_path, "*")].each {|path| begin File.delete(path) rescue nil end}
-    assert_raise(FileNotFoundError) do
+    assert_raise(Ferret::FileNotFoundError) do
       Index.new(:path => fs_path,
                 :create_if_missing => false,
                 :default_field => :xxx)

data/test/unit/index/tc_index_reader.rb

@@ -31,6 +31,11 @@ module IndexReaderCommon
   def do_test_term_enum()
     te = @ir.terms(:author)
 
+    assert_equal('[{"term":"Leo","frequency":1},{"term":"Tolstoy","frequency":1}]', te.to_json);
+    te.field = :author
+    assert_equal('[["Leo",1],["Tolstoy",1]]', te.to_json(:fast));
+    te.field = :author
+
     assert(te.next?)
     assert_equal("Leo", te.term)
     assert_equal(1, te.doc_freq)
@@ -99,6 +104,11 @@ module IndexReaderCommon
     end
     assert(! tde.next?)
 
+    tde = @ir.term_docs_for(:body, "Wally")
+    assert_equal('[{"document":0,"frequency":1},{"document":5,"frequency":1},{"document":18,"frequency":3},{"document":20,"frequency":6}]', tde.to_json)
+    tde = @ir.term_docs_for(:body, "Wally")
+    assert_equal('[[0,1],[5,1],[18,3],[20,6]]', tde.to_json(:fast))
+
     do_test_term_docpos_enum_skip_to(tde)
 
     # test term positions
@@ -124,6 +134,33 @@ module IndexReaderCommon
     assert_nil(tde.next_position())
     assert(! tde.next?)
 
+    tde = @ir.term_positions_for(:body, "read")
+    assert_equal('[' +
+       '{"document":1,"frequency":1,"positions":[3]},' +
+       '{"document":2,"frequency":2,"positions":[1,4]},' +
+       '{"document":6,"frequency":4,"positions":[3,4,5,6]},' +
+       '{"document":9,"frequency":3,"positions":[0,4,13]},' +
+       '{"document":10,"frequency":1,"positions":[1]},' +
+       '{"document":16,"frequency":2,"positions":[2,3]},' +
+       '{"document":17,"frequency":1,"positions":[2]},' +
+       '{"document":20,"frequency":1,"positions":[21]},' +
+       '{"document":21,"frequency":6,"positions":[3,4,5,8,9,10]}]',
+       tde.to_json())
+    tde = @ir.term_positions_for(:body, "read")
+    assert_equal('[' +
+       '[1,1,[3]],' +
+       '[2,2,[1,4]],' +
+       '[6,4,[3,4,5,6]],' +
+       '[9,3,[0,4,13]],' +
+       '[10,1,[1]],' +
+       '[16,2,[2,3]],' +
+       '[17,1,[2]],' +
+       '[20,1,[21]],' +
+       '[21,6,[3,4,5,8,9,10]]]',
+       tde.to_json(:fast))
+
+    tde = @ir.term_positions_for(:body, "read")
+
     do_test_term_docpos_enum_skip_to(tde)
   end
 

data/test/unit/search/tc_spans.rb

@@ -68,7 +68,7 @@ class SpansBasicTest < Test::Unit::TestCase
   end
 
   def check_hits(query, expected, test_explain = false, top=nil)
-    top_docs = @searcher.search(query, {:limit => expected.length})
+    top_docs = @searcher.search(query, {:limit => expected.length + 1})
     assert_equal(expected.length, top_docs.hits.size)
     assert_equal(top, top_docs.hits[0].doc) if top
     assert_equal(expected.length, top_docs.total_hits)
@@ -170,4 +170,21 @@ class SpansBasicTest < Test::Unit::TestCase
     q = SpanOrQuery.new([nearq1, nearq2])
     check_hits(q, [0,3,4,5,6,8,9,10,11,14,16,30], false)
   end
+
+  def test_span_prefix_query_max_terms
+    @dir = RAMDirectory.new
+    iw = IndexWriter.new(:dir => @dir,
+                         :analyzer => WhiteSpaceAnalyzer.new())
+    2000.times { |i| iw << {:field => "prefix#{i} term#{i}"} }
+    iw.close()
+    @searcher = Searcher.new(@dir)
+
+    pq = SpanPrefixQuery.new(:field, "prefix")
+    tq = SpanTermQuery.new(:field, "term1500")
+    q = SpanNearQuery.new(:clauses => [pq, tq], :in_order => true)
+    check_hits(q, [], false)
+    pq = SpanPrefixQuery.new(:field, "prefix", 2000)
+    q = SpanNearQuery.new(:clauses => [pq, tq], :in_order => true)
+    check_hits(q, [1500], false)
+  end
 end

metadata

@@ -3,8 +3,8 @@ rubygems_version: 0.9.0
 specification_version: 1
 name: ferret
 version: !ruby/object:Gem::Version 
-  version: 0.11.3
-date: 2007-03-03 00:00:00 +11:00
+  version: 0.11.4
+date: 2007-04-07 00:00:00 +10:00
 summary: Ruby indexing library.
 require_paths: 
 - lib
@@ -13,7 +13,7 @@ homepage: http://ferret.davebalmain.com/trac
 rubyforge_project: ferret
 description: Ferret is a port of the Java Lucene project. It is a powerful indexing and search library.
 autorequire: ferret
-default_executable: 
+default_executable: ferret-browser
 bindir: bin
 has_rdoc: true
 required_ruby_version: !ruby/object:Gem::Version::Requirement 
@@ -168,7 +168,20 @@ files:
 - lib/ferret/field_infos.rb
 - lib/ferret/document.rb
 - lib/ferret/index.rb
+- lib/ferret/browser.rb
 - lib/ferret/number_tools.rb
+- lib/ferret/browser/webrick.rb
+- lib/ferret/browser/views/layout.rhtml
+- lib/ferret/browser/views/term/index.rhtml
+- lib/ferret/browser/views/term/termdocs.rhtml
+- lib/ferret/browser/views/home/index.rhtml
+- lib/ferret/browser/views/help/index.rhtml
+- lib/ferret/browser/views/document/list.rhtml
+- lib/ferret/browser/views/document/show.rhtml
+- lib/ferret/browser/views/error/index.rhtml
+- lib/ferret/browser/views/term-vector/index.rhtml
+- lib/ferret/browser/s/style.css
+- lib/ferret/browser/s/global.js
 - test/test_helper.rb
 - test/test_all.rb
 - test/unit/tc_document.rb
@@ -227,8 +240,8 @@ extra_rdoc_files:
 - ext/r_index.c
 - ext/r_store.c
 - ext/ferret.c
-executables: []
-
+executables: 
+- ferret-browser
 extensions: 
 - ext/extconf.rb
 requirements: []