ferret 0.9.1 → 0.9.2

data/test/unit/search/tc_search_and_sort.rb

@@ -44,8 +44,74 @@ class SearchAndSortTest < Test::Unit::TestCase
     top_docs.total_hits.times do |i|
       assert_equal(expected[i], top_docs.score_docs[i].doc)
     end
+
+    # test sorting works for smaller ranged query
+    first_doc = 3
+    num_docs = 3
+    top_docs = is.search(query, {:sort => sort,
+                                 :first_doc => first_doc,
+                                 :num_docs => num_docs})
+    num_docs.times do |i|
+      assert_equal(expected[first_doc + i], top_docs.score_docs[i].doc)
+    end
+  end
+
+  def test_sort_field_to_s()
+    assert_equal("<SCORE>", SortField::FIELD_SCORE.to_s);
+    sf = SortField.new("MyScore",
+                       {:sort_type => SortField::SortType::SCORE,
+                        :reverse => true})
+    assert_equal("MyScore:<SCORE>!", sf.to_s)
+    assert_equal("<DOC>", SortField::FIELD_DOC.to_s);
+    sf = SortField.new("MyDoc",
+                       {:sort_type => SortField::SortType::DOC,
+                        :reverse => true})
+    assert_equal("MyDoc:<DOC>!", sf.to_s)
+    sf = SortField.new("date",
+                       {:sort_type => SortField::SortType::INTEGER})
+    assert_equal("date:<integer>", sf.to_s)
+    sf = SortField.new("date",
+                       {:sort_type => SortField::SortType::INTEGER,
+                        :reverse => true})
+    assert_equal("date:<integer>!", sf.to_s)
+    sf = SortField.new("price",
+                       {:sort_type => SortField::SortType::FLOAT})
+    assert_equal("price:<float>", sf.to_s)
+    sf = SortField.new("price",
+                       {:sort_type => SortField::SortType::FLOAT,
+                        :reverse => true})
+    assert_equal("price:<float>!", sf.to_s)
+    sf = SortField.new("content",
+                       {:sort_type => SortField::SortType::STRING})
+    assert_equal("content:<string>", sf.to_s)
+    sf = SortField.new("content",
+                       {:sort_type => SortField::SortType::STRING,
+                        :reverse => true})
+    assert_equal("content:<string>!", sf.to_s)
+    sf = SortField.new("auto_field",
+                       {:sort_type => SortField::SortType::AUTO})
+    assert_equal("auto_field:<auto>", sf.to_s)
+    sf = SortField.new("auto_field",
+                       {:sort_type => SortField::SortType::AUTO,
+                        :reverse => true})
+    assert_equal("auto_field:<auto>!", sf.to_s)
+  end
+  
+  def test_sort_to_s()
+    sort = Sort.new
+    assert_equal("Sort[<SCORE>, <DOC>]", sort.to_s)
+    sf = SortField.new("auto_field",
+                       {:sort_type => SortField::SortType::AUTO,
+                        :reverse => true})
+    sort = Sort.new([sf, SortField::FIELD_SCORE, SortField::FIELD_DOC])
+    assert_equal("Sort[auto_field:<auto>!, <SCORE>, <DOC>]", sort.to_s)
+    sort = Sort.new(["one", "two", SortField::FIELD_DOC])
+    assert_equal("Sort[one:<auto>, two:<auto>, <DOC>]", sort.to_s)
+    sort = Sort.new(["one", "two"])
+    assert_equal("Sort[one:<auto>, two:<auto>, <DOC>]", sort.to_s)
   end
 
+
   def test_sorts()
     is = IndexSearcher.new(@dir)
     q = TermQuery.new(Term.new("search", "findall"))

metadata

@@ -3,8 +3,8 @@ rubygems_version: 0.8.11
 specification_version: 1
 name: ferret
 version: !ruby/object:Gem::Version 
-  version: 0.9.1
-date: 2006-04-11 00:00:00 +09:00
+  version: 0.9.2
+date: 2006-05-11 00:00:00 +09:00
 summary: Ruby indexing library.
 require_paths: 
 - lib
@@ -30,9 +30,9 @@ authors:
 files: 
 - setup.rb
 - Rakefile
+- TODO
 - README
 - MIT-LICENSE
-- TODO
 - TUTORIAL
 - CHANGELOG
 - ext/ferret.c
@@ -51,7 +51,6 @@ files:
 - ext/document.c
 - ext/compound_io.c
 - ext/index_rw.c
-- ext/termdocs.c
 - ext/vector.c
 - ext/field.c
 - ext/term.c
@@ -60,20 +59,20 @@ files:
 - ext/q_boolean.c
 - ext/q_match_all.c
 - ext/q_phrase.c
-- ext/q_fuzzy.c
+- ext/q_filtered_query.c
 - ext/search.c
 - ext/dummy.exe
-- ext/q_multi_phrase.c
+- ext/q_fuzzy.c
 - ext/q_wildcard.c
 - ext/ind.c
 - ext/q_range.c
+- ext/q_multi_phrase.c
 - ext/q_prefix.c
 - ext/q_span.c
 - ext/filter.c
 - ext/similarity.c
-- ext/sort.c
 - ext/q_term.c
-- ext/q_filtered_query.c
+- ext/sort.c
 - ext/index_io.c
 - ext/fs_store.c
 - ext/ram_store.c
@@ -86,22 +85,6 @@ files:
 - ext/hash.c
 - ext/except.c
 - ext/priorityqueue.c
-- ext/document.h
-- ext/store.h
-- ext/array.h
-- ext/priorityqueue.h
-- ext/hashset.h
-- ext/helper.h
-- ext/global.h
-- ext/lang.h
-- ext/bitvector.h
-- ext/analysis.h
-- ext/hash.h
-- ext/search.h
-- ext/ferret.h
-- ext/index.h
-- ext/except.h
-- ext/similarity.h
 - ext/libstemmer.h
 - ext/libstemmer.c
 - ext/modules.h
@@ -112,6 +95,7 @@ files:
 - ext/stem_ISO_8859_1_italian.c
 - ext/stem_UTF_8_portuguese.c
 - ext/stem_UTF_8_portuguese.h
+- ext/ferret.h
 - ext/stem_UTF_8_french.c
 - ext/stem_UTF_8_spanish.c
 - ext/stem_UTF_8_dutch.c
@@ -130,7 +114,6 @@ files:
 - ext/stem_ISO_8859_1_portuguese.c
 - ext/stem_UTF_8_russian.c
 - ext/stem_ISO_8859_1_spanish.c
-- ext/tags
 - ext/stem_ISO_8859_1_french.c
 - ext/stem_ISO_8859_1_portuguese.h
 - ext/stem_ISO_8859_1_dutch.c
@@ -140,6 +123,7 @@ files:
 - ext/stem_ISO_8859_1_spanish.h
 - ext/stem_ISO_8859_1_french.h
 - ext/stem_ISO_8859_1_porter.c
+- ext/tags
 - ext/stem_ISO_8859_1_dutch.h
 - ext/stem_UTF_8_finnish.c
 - ext/stem_KOI8_R_russian.h
@@ -162,6 +146,24 @@ files:
 - ext/stem_ISO_8859_1_danish.h
 - ext/stem_UTF_8_english.h
 - ext/stem_UTF_8_norwegian.h
+- ext/document.h
+- ext/store.h
+- ext/array.h
+- ext/priorityqueue.h
+- ext/hashset.h
+- ext/helper.h
+- ext/global.h
+- ext/bitvector.h
+- ext/analysis.h
+- ext/hash.h
+- ext/search.h
+- ext/similarity.h
+- ext/index.h
+- ext/except.h
+- ext/lang.h
+- ext/frtio.h
+- ext/w32_io.c
+- ext/nix_io.c
 - ext/inc/lang.h
 - ext/inc/except.h
 - lib/ferret.rb
@@ -257,6 +259,7 @@ files:
 - lib/ferret/search/range_filter.rb
 - lib/ferret/search/field_cache.rb
 - lib/ferret/search/match_all_query.rb
+- lib/ferret/search/multi_searcher.rb
 - lib/ferret/search/spans/near_spans_enum.rb
 - lib/ferret/search/spans/span_first_query.rb
 - lib/ferret/search/spans/spans_enum.rb
@@ -345,13 +348,14 @@ files:
 - test/unit/document/rtc_field.rb
 - test/unit/document/tc_document.rb
 - test/unit/query_parser/tc_query_parser.rb
-- test/unit/query_parser/rtc_query_parser.rb
 - test/unit/search/tc_fuzzy_query.rb
+- test/unit/search/tc_multi_searcher2.rb
 - test/unit/search/tc_index_searcher.rb
 - test/unit/search/tc_spans.rb
 - test/unit/search/tc_filter.rb
 - test/unit/search/tc_sort.rb
 - test/unit/search/tc_sort_field.rb
+- test/unit/search/tc_multi_searcher.rb
 - test/unit/search/rtc_sort_field.rb
 - test/unit/search/rtc_similarity.rb
 - test/unit/search/tc_search_and_sort.rb
@@ -364,6 +368,7 @@ files:
 - test/utils/number_to_spoken.rb
 - test/unit/analysis/data/wordfile
 - rake_utils/code_statistics.rb
+- ext/termdocs.c
 test_files: []
 
 rdoc_options: 

data/test/unit/query_parser/rtc_query_parser.rb

@@ -1,138 +0,0 @@
-require File.dirname(__FILE__) + "/../../test_helper"
-
-class QueryParserTest < Test::Unit::TestCase
-
-  def test_strings()
-    parser = Ferret::QueryParser.new("xxx", :fields => ["f1", "f2", "f3"])
-    pairs = [
-      ['', ''],
-      ['word', 'word'],
-      ['field:word', 'field:word'],
-      ['"word1 word2 word3"', '"word word word"'],
-      ['"word1 2342 word3"', '"word word"'],
-      ['field:"one two three"', 'field:"one two three"'],
-      ['field:"one 222 three"', 'field:"one three"'],
-      ['field:"one <> three"', 'field:"one <> three"'],
-      ['field:"one <> three <>"', 'field:"one <> three"'],
-      ['field:"one <> <> <> three <>"', 'field:"one <> <> <> three"'],
-      ['field:"one <> <> <> three|four|five <>"', 'field:"one <> <> <> three|four|five"'],
-      ['field:"one|two three|four|five six|seven"', 'field:"one|two three|four|five six|seven"'],
-      ['contents:"testing|trucks"', 'contents:testing contents:trucks'],
-      ['[aaa bbb]', '[aaa bbb]'],
-      ['{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]'],
-      ['REQ one REQ two', '+one +two'],
-      ['REQ one two', '+one two'],
-      ['one REQ two', 'one +two'],
-      ['+one +two', '+one +two'],
-      ['+one two', '+one two'],
-      ['one +two', 'one +two'],
-      ['-one -two', '-one -two'],
-      ['-one two', '-one two'],
-      ['one -two', 'one -two'],
-      ['!one !two', '-one -two'],
-      ['!one two', '-one two'],
-      ['one !two', 'one -two'],
-      ['NOT one NOT two', '-one -two'],
-      ['NOT one two', '-one two'],
-      ['one NOT two', 'one -two'],
-      ['one two', 'one two'],
-      ['one OR two', 'one two'],
-      ['one AND two', '+one +two'],
-      ['one two AND three', 'one two +three'],
-      ['one two OR three', 'one two three'],
-      ['one (two AND three)', 'one (+two +three)'],
-      ['one AND (two OR three)', '+one +(two three)'],
-      ['field:(one AND (two OR three))', '+field:one +(field:two field:three)'],
-      ['one AND (two OR [aaa vvv})', '+one +(two [aaa vvv})'],
-      ['one AND (one:two OR two:three) AND four', '+one +(one:two two:three) +four'],
-      ['one^1.23', 'one^1.23'],
-      ['(one AND two)^100.23', '(+one +two)^100.23'],
-      ['field:(one AND two)^100.23', '(+field:one +field:two)^100.23'],
-      ['field:(one AND [aaa bbb]^23.3)^100.23', '(+field:one +field:[aaa bbb]^23.3)^100.23'],
-      ['(REQ field:"one two three")^23', 'field:"one two three"^23.0'],
-      ['asdf~0.2', 'asdf~0.2'],
-      ['field:asdf~0.2', 'field:asdf~0.2'],
-      ['asdf~0.2^100.0', 'asdf~0.2^100.0'],
-      ['field:asdf~0.2^0.1', 'field:asdf~0.2^0.1'],
-      ['field:"asdf <> asdf|asdf"~4', 'field:"asdf <> asdf|asdf"~4'],
-      ['"one two three four five"~5', '"one two three four five"~5'],
-      ['ab?de', 'ab?de'],
-      ['ab*de', 'ab*de'],
-      ['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~ +field:b*'],
-      ['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 |query_str, expected|
-      assert_equal(expected, parser.parse(query_str).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 |query_str, expected|
-      assert_equal(expected, parser.parse(query_str).to_s(parser.default_field))
-    end
-  end
-  
-  def do_test_query_parse_exception_raised(str)
-    parser = Ferret::QueryParser.new("xxx", :fields => ["f1", "f2", "f3"])
-    assert_raise(Ferret::QueryParser::QueryParseException) do
-      parser.parse(str)
-    end
-  end
-
-  
-  def test_bad_queries
-    parser = Ferret::QueryParser.new("xxx", :fields => ["f1", "f2"],
-                                            :handle_parse_errors => true)
-
-    pairs = [
-      ['::*word', 'word'],
-      ['()*&)(*^&*(', ''],
-      ['()*&one)(*two(*&"', '"one two"']
-    ]
-      
-    pairs.each do |query_str, expected|
-      do_test_query_parse_exception_raised(query_str)
-      assert_equal(expected, parser.parse(query_str).to_s(parser.default_field))
-    end
-  end
-end