ferret 0.1.1 → 0.1.2

data/lib/ferret/search/range_query.rb

@@ -96,7 +96,7 @@ module Ferret::Search
         buffer << (@include_lower ? "[" : "{")
         buffer << @lower_term
       else
-        buffer << "|"
+        buffer << "<"
       end
 
       buffer << " " if @upper_term and @lower_term
@@ -105,7 +105,7 @@ module Ferret::Search
         buffer << @upper_term
         buffer << (@include_upper ? "]" : "}")
       else
-        buffer << "|"
+        buffer << ">"
       end
 
       if boost() != 1.0

data/test/test_helper.rb

@@ -4,3 +4,10 @@ $:.unshift File.join(File.dirname(__FILE__), '../ext')
 require 'test/unit'
 require 'ferret'
 require 'test/unit/index/th_doc'
+
+def load_test_dir(dir)
+  dir = File.join(File.dirname(__FILE__), dir)
+  Dir.foreach(dir) do |file|
+    require File.join(dir, file) if file =~ /^t[mcs]_.*\.rb$/
+  end
+end

data/test/unit/index/tc_index.rb

@@ -72,14 +72,14 @@ class IndexTest < Test::Unit::TestCase
 
   def do_test_index_with_doc_array(index)
     data = [
-      {"def_field" => "one two", :id => "me"},
-      {"def_field" => "one", :field2 => "three"},
+      {"def_field" => "one two multi", :id => "me"},
+      {"def_field" => "one", :field2 => "three multi"},
       {"def_field" => "two"},
       {"def_field" => "one", :field2 => "four"},
       {"def_field" => "one two"},
       {"def_field" => "two", :field2 => "three", "field3" => "four"},
-      {"def_field" => "one"},
-      {"def_field" => "two", :field2 => "three", "field3" => "five"}
+      {"def_field" => "one multi2"},
+      {"def_field" => "two", :field2 => "three multi2", "field3" => "five multi"}
     ]
     data.each {|doc| index << doc }
     q = "one AND two"
@@ -90,6 +90,10 @@ class IndexTest < Test::Unit::TestCase
     check_results(index, q, [0, 1, 3, 4, 6, 7])
     q = "two AND (field3:f*)"
     check_results(index, q, [5, 7])
+    q = "*:(multi OR multi2)"
+    check_results(index, q, [0, 1, 6, 7])
+    q = "field2|field3:(multi OR multi2)"
+    check_results(index, q, [1, 7])
     doc = index[5]
     assert_equal("three", index[5]["field2"])
     assert(!index.has_deletions?)
@@ -99,6 +103,7 @@ class IndexTest < Test::Unit::TestCase
     assert(index.has_deletions?)
     assert(index.deleted?(5))
     assert_equal(7, index.size)
+    q = "two AND (field3:f*)"
     check_results(index, q, [7])
     doc["field2"] = "dave"
     index << doc
@@ -114,7 +119,7 @@ class IndexTest < Test::Unit::TestCase
     assert(! index.deleted?(7))
     t = Term.new("field2", "four")
     assert_equal("one", index[t]["def_field"])
-    assert_equal("one two", index["me"]["def_field"])
+    assert_equal("one two multi", index["me"]["def_field"])
     index.delete("me")
     assert(index.deleted?(0))
   end

data/test/unit/index/tc_multiple_term_doc_pos_enum.rb

@@ -1,12 +1,15 @@
 require File.dirname(__FILE__) + "/../../test_helper"
 
 class MultipleTermDocPosEnumTest < Test::Unit::TestCase
+  include Ferret::Index
   include Ferret::Search
   include Ferret::Analysis
 
   def setup()
     @dir = Ferret::Store::RAMDirectory.new()
-    iw = IndexWriter.new(@dir, WhiteSpaceAnalyzer.new(), true, false)
+    iw = IndexWriter.new(@dir,
+                         :analyzer => WhiteSpaceAnalyzer.new(),
+                         :create_if_missing => true)
     @documents = IndexTestHelper.prepare_search_docs()
     @documents.each { |doc| iw << doc }
     iw.close()

data/test/unit/query_parser/tc_query_parser.rb

@@ -2,12 +2,8 @@ require File.dirname(__FILE__) + "/../../test_helper"
 
 class QueryParserTest < Test::Unit::TestCase
 
-
-  def setup()
-    @parser = Ferret::QueryParser.new("xxx")
-  end
-
   def test_strings()
+    parser = Ferret::QueryParser.new("xxx", :fields => ["f1", "f2", "f3"])
     pairs = [
       ['word', 'word'],
       ['field:word', 'field:word'],
@@ -24,14 +20,14 @@ class QueryParserTest < Test::Unit::TestCase
       ['{aaa bbb]', '{aaa bbb]'],
       ['field:[aaa bbb}', 'field:[aaa bbb}'],
       ['{aaa bbb}', '{aaa bbb}'],
-      ['{aaa|', '{aaa|'],
-      ['[aaa|', '[aaa|'],
-      ['field:|aaa}', 'field:|aaa}'],
-      ['|aaa]', '|aaa]'],
-      ['>aaa', '{aaa|'],
-      ['>=aaa', '[aaa|'],
-      ['<aaa', '|aaa}'],
-      ['field:<=aaa', 'field:|aaa]'],
+      ['{aaa>', '{aaa>'],
+      ['[aaa>', '[aaa>'],
+      ['field:<aaa}', 'field:<aaa}'],
+      ['<aaa]', '<aaa]'],
+      ['>aaa', '{aaa>'],
+      ['>=aaa', '[aaa>'],
+      ['<aaa', '<aaa}'],
+      ['field:<=aaa', 'field:<aaa]'],
       ['REQ one REQ two', '+one +two'],
       ['REQ one two', '+one two'],
       ['one REQ two', 'one +two'],
@@ -73,12 +69,44 @@ class QueryParserTest < Test::Unit::TestCase
       ['asdf?*?asd*dsf?asfd*asdf?', 'asdf?*?asd*dsf?asfd*asdf?'],
       ['field:a* AND field:(b*)', '+field:a* +field:b*'],
       ['field:abc~ AND field:(b*)', '+field:abc~0.5 +field:b*'],
-      ['asdf?*?asd*dsf?asfd*asdf?^20.0', 'asdf?*?asd*dsf?asfd*asdf?^20.0']
+      ['asdf?*?asd*dsf?asfd*asdf?^20.0', 'asdf?*?asd*dsf?asfd*asdf?^20.0'],
+
+      ['*:xxx', 'f1:xxx f2:xxx f3:xxx'],
+      ['f1|f2:xxx', 'f1:xxx f2:xxx'],
+
+      ['*:asd~0.2', 'f1:asd~0.2 f2:asd~0.2 f3:asd~0.2'],
+      ['f1|f2:asd~0.2', 'f1:asd~0.2 f2:asd~0.2'],
+
+      ['*:a?d*^20.0', '(f1:a?d* f2:a?d* f3:a?d*)^20.0'],
+      ['f1|f2:a?d*^20.0', '(f1:a?d* f2:a?d*)^20.0'],
+
+      ['*:"asdf <> xxx|yyy"', 'f1:"asdf <> xxx|yyy" f2:"asdf <> xxx|yyy" f3:"asdf <> xxx|yyy"'],
+      ['f1|f2:"asdf <> xxx|yyy"', 'f1:"asdf <> xxx|yyy" f2:"asdf <> xxx|yyy"'],
+
+      ['*:[bbb xxx]', 'f1:[bbb xxx] f2:[bbb xxx] f3:[bbb xxx]'],
+      ['f1|f2:[bbb xxx]', 'f1:[bbb xxx] f2:[bbb xxx]'],
+
+      ['*:(xxx AND bbb)', '+(f1:xxx f2:xxx f3:xxx) +(f1:bbb f2:bbb f3:bbb)'],
+      ['f1|f2:(xxx AND bbb)', '+(f1:xxx f2:xxx) +(f1:bbb f2:bbb)'],
+      ['asdf?*?asd*dsf?asfd*asdf?^20.0', 'asdf?*?asd*dsf?asfd*asdf?^20.0'],
+      ['"onewordphrase"', 'onewordphrase']
     ]
+      
+    pairs.each do |pair|
+      assert_equal(pair[1], parser.parse(pair[0]).to_s(parser.default_field))
+    end
+  end
 
+  def test_qp_with_standard_analyzer()
+    parser = Ferret::QueryParser.new("xxx", :fields => ["f1", "f2", "f3"],
+                                     :analyzer => Ferret::Analysis::StandardAnalyzer.new)
+    pairs = [
+    ['key:1234', 'key:1234'],
+      ['key:(1234)', 'key:1234']
+    ]
       
     pairs.each do |pair|
-      assert_equal(pair[1], @parser.parse(pair[0]).to_s(@parser.default_field))
+      assert_equal(pair[1], parser.parse(pair[0]).to_s(parser.default_field))
     end
   end
 end

data/test/unit/store/tm_store.rb

@@ -95,13 +95,13 @@ module StoreTest
   end
 
   def test_rw_utf8_strings
-    text = '�� ������'
+    text = '³³ ÄÄÄÄÄÄ 道德經'
     ostream = @dir.create_output("rw_utf8_strings.test")
     ostream.write_string(text)
     ostream.write_string(text*100)
     ostream.close
     istream = @dir.open_input("rw_utf8_strings.test")
-    assert_equal(text, istream.read_string, "Short string test failed")
+    assert_equal(text, x = istream.read_string, "Short string test failed")
     assert_equal(text*100, istream.read_string, "Short string test failed")
     istream.close
   end

data/test/unit/ts_analysis.rb

@@ -1,16 +1,2 @@
-$:.unshift File.dirname(__FILE__)
 require File.join(File.dirname(__FILE__), "../test_helper.rb")
-
-require 'analysis/tc_letter_tokenizer'
-require 'analysis/tc_white_space_tokenizer'
-require 'analysis/tc_lower_case_tokenizer'
-require 'analysis/tc_word_list_loader'
-require 'analysis/tc_lower_case_filter'
-require 'analysis/tc_stop_filter'
-require 'analysis/tc_porter_stem_filter'
-require 'analysis/tc_analyzer'
-require 'analysis/tc_stop_analyzer'
-require 'analysis/tc_white_space_analyzer'
-require 'analysis/tc_per_field_analyzer_wrapper'
-require 'analysis/tc_standard_tokenizer'
-require 'analysis/tc_standard_analyzer'
+load_test_dir('unit/analysis')

data/test/unit/ts_document.rb

@@ -1,4 +1,2 @@
-$:.unshift File.dirname(__FILE__)
-
-require 'document/tc_field.rb'
-require 'document/tc_document.rb'
+require File.join(File.dirname(__FILE__), "../test_helper.rb")
+load_test_dir('unit/document')

data/test/unit/ts_index.rb

@@ -1,18 +1,2 @@
-$:.unshift File.dirname(__FILE__)
-
-require 'index/tc_compound_file_io.rb'
-require 'index/tc_field_infos.rb'
-require 'index/tc_fields_io.rb'
-require 'index/tc_index_writer.rb'
-require 'index/tc_index_reader.rb'
-require 'index/tc_segment_infos.rb'
-require 'index/tc_segment_term_docs.rb'
-require 'index/tc_segment_term_enum.rb'
-require 'index/tc_segment_term_vector.rb'
-require 'index/tc_term.rb'
-require 'index/tc_term_buffer.rb'
-require 'index/tc_term_info.rb'
-require 'index/tc_term_infos_io.rb'
-require 'index/tc_term_vector_offset_info.rb'
-require 'index/tc_term_vectors_io.rb'
-require 'index/tc_index.rb'
+require File.join(File.dirname(__FILE__), "../test_helper.rb")
+load_test_dir('unit/index')

data/test/unit/ts_query_parser.rb

@@ -1,3 +1,2 @@
-$:.unshift File.dirname(__FILE__)
-
-require 'query_parser/tc_query_parser.rb'
+require File.join(File.dirname(__FILE__), "../test_helper.rb")
+load_test_dir('unit/query_parser')

data/test/unit/ts_search.rb

@@ -1,10 +1,2 @@
-$:.unshift File.dirname(__FILE__)
-
-require 'search/tc_similarity.rb'
-require 'search/tc_index_searcher.rb'
-require 'search/tc_fuzzy_query.rb'
-require 'search/tc_sort_field.rb'
-require 'search/tc_sort.rb'
-require 'search/tc_search_and_sort.rb'
-require 'search/tc_filter.rb'
-require 'search/tc_spans.rb'
+require File.join(File.dirname(__FILE__), "../test_helper.rb")
+load_test_dir('unit/search')

data/test/unit/ts_store.rb

@@ -1,6 +1,2 @@
-$:.unshift File.dirname(__FILE__)
 require File.join(File.dirname(__FILE__), "../test_helper.rb")
-
-
-require 'store/tc_fs_store'
-require 'store/tc_ram_store'
+load_test_dir('unit/store')

data/test/unit/ts_utils.rb

@@ -1,10 +1,2 @@
-$:.unshift File.dirname(__FILE__)
 require File.join(File.dirname(__FILE__), "../test_helper.rb")
-
-require 'utils/tc_string_helper'
-require 'utils/tc_priority_queue'
-require 'utils/tc_bit_vector'
-require 'utils/tc_date_tools.rb'
-require 'utils/tc_number_tools.rb'
-require 'utils/tc_parameter.rb'
-require 'utils/tc_weak_key_hash.rb'
+load_test_dir('unit/utils')

metadata

@@ -3,8 +3,8 @@ rubygems_version: 0.8.11
 specification_version: 1
 name: ferret
 version: !ruby/object:Gem::Version 
-  version: 0.1.1
-date: 2005-10-22 00:00:00 +09:00
+  version: 0.1.2
+date: 2005-10-25 00:00:00 +09:00
 summary: Ruby indexing library.
 require_paths: 
   - lib