ferret 0.1.0

Sign up to get free protection for your applications and to get access to all the features.
Files changed (202) hide show
  1. data/MIT-LICENSE +20 -0
  2. data/README +109 -0
  3. data/Rakefile +275 -0
  4. data/TODO +9 -0
  5. data/TUTORIAL +197 -0
  6. data/ext/extconf.rb +3 -0
  7. data/ext/ferret.c +23 -0
  8. data/ext/ferret.h +85 -0
  9. data/ext/index_io.c +543 -0
  10. data/ext/priority_queue.c +227 -0
  11. data/ext/ram_directory.c +316 -0
  12. data/ext/segment_merge_queue.c +41 -0
  13. data/ext/string_helper.c +42 -0
  14. data/ext/tags +240 -0
  15. data/ext/term.c +261 -0
  16. data/ext/term_buffer.c +299 -0
  17. data/ext/util.c +12 -0
  18. data/lib/ferret.rb +41 -0
  19. data/lib/ferret/analysis.rb +11 -0
  20. data/lib/ferret/analysis/analyzers.rb +93 -0
  21. data/lib/ferret/analysis/standard_tokenizer.rb +65 -0
  22. data/lib/ferret/analysis/token.rb +79 -0
  23. data/lib/ferret/analysis/token_filters.rb +86 -0
  24. data/lib/ferret/analysis/token_stream.rb +26 -0
  25. data/lib/ferret/analysis/tokenizers.rb +107 -0
  26. data/lib/ferret/analysis/word_list_loader.rb +27 -0
  27. data/lib/ferret/document.rb +2 -0
  28. data/lib/ferret/document/document.rb +152 -0
  29. data/lib/ferret/document/field.rb +304 -0
  30. data/lib/ferret/index.rb +26 -0
  31. data/lib/ferret/index/compound_file_io.rb +343 -0
  32. data/lib/ferret/index/document_writer.rb +288 -0
  33. data/lib/ferret/index/field_infos.rb +259 -0
  34. data/lib/ferret/index/fields_io.rb +175 -0
  35. data/lib/ferret/index/index.rb +228 -0
  36. data/lib/ferret/index/index_file_names.rb +33 -0
  37. data/lib/ferret/index/index_reader.rb +462 -0
  38. data/lib/ferret/index/index_writer.rb +488 -0
  39. data/lib/ferret/index/multi_reader.rb +363 -0
  40. data/lib/ferret/index/multiple_term_doc_pos_enum.rb +105 -0
  41. data/lib/ferret/index/segment_infos.rb +130 -0
  42. data/lib/ferret/index/segment_merge_info.rb +47 -0
  43. data/lib/ferret/index/segment_merge_queue.rb +16 -0
  44. data/lib/ferret/index/segment_merger.rb +337 -0
  45. data/lib/ferret/index/segment_reader.rb +380 -0
  46. data/lib/ferret/index/segment_term_enum.rb +178 -0
  47. data/lib/ferret/index/segment_term_vector.rb +58 -0
  48. data/lib/ferret/index/term.rb +49 -0
  49. data/lib/ferret/index/term_buffer.rb +88 -0
  50. data/lib/ferret/index/term_doc_enum.rb +283 -0
  51. data/lib/ferret/index/term_enum.rb +52 -0
  52. data/lib/ferret/index/term_info.rb +41 -0
  53. data/lib/ferret/index/term_infos_io.rb +312 -0
  54. data/lib/ferret/index/term_vector_offset_info.rb +20 -0
  55. data/lib/ferret/index/term_vectors_io.rb +552 -0
  56. data/lib/ferret/query_parser.rb +274 -0
  57. data/lib/ferret/query_parser/query_parser.tab.rb +819 -0
  58. data/lib/ferret/search.rb +49 -0
  59. data/lib/ferret/search/boolean_clause.rb +100 -0
  60. data/lib/ferret/search/boolean_query.rb +303 -0
  61. data/lib/ferret/search/boolean_scorer.rb +294 -0
  62. data/lib/ferret/search/caching_wrapper_filter.rb +40 -0
  63. data/lib/ferret/search/conjunction_scorer.rb +99 -0
  64. data/lib/ferret/search/disjunction_sum_scorer.rb +203 -0
  65. data/lib/ferret/search/exact_phrase_scorer.rb +32 -0
  66. data/lib/ferret/search/explanation.rb +41 -0
  67. data/lib/ferret/search/field_cache.rb +216 -0
  68. data/lib/ferret/search/field_doc.rb +31 -0
  69. data/lib/ferret/search/field_sorted_hit_queue.rb +184 -0
  70. data/lib/ferret/search/filter.rb +11 -0
  71. data/lib/ferret/search/filtered_query.rb +130 -0
  72. data/lib/ferret/search/filtered_term_enum.rb +79 -0
  73. data/lib/ferret/search/fuzzy_query.rb +153 -0
  74. data/lib/ferret/search/fuzzy_term_enum.rb +244 -0
  75. data/lib/ferret/search/hit_collector.rb +34 -0
  76. data/lib/ferret/search/hit_queue.rb +11 -0
  77. data/lib/ferret/search/index_searcher.rb +173 -0
  78. data/lib/ferret/search/match_all_docs_query.rb +104 -0
  79. data/lib/ferret/search/multi_phrase_query.rb +204 -0
  80. data/lib/ferret/search/multi_term_query.rb +65 -0
  81. data/lib/ferret/search/non_matching_scorer.rb +22 -0
  82. data/lib/ferret/search/phrase_positions.rb +55 -0
  83. data/lib/ferret/search/phrase_query.rb +217 -0
  84. data/lib/ferret/search/phrase_scorer.rb +153 -0
  85. data/lib/ferret/search/prefix_query.rb +47 -0
  86. data/lib/ferret/search/query.rb +111 -0
  87. data/lib/ferret/search/query_filter.rb +51 -0
  88. data/lib/ferret/search/range_filter.rb +103 -0
  89. data/lib/ferret/search/range_query.rb +139 -0
  90. data/lib/ferret/search/req_excl_scorer.rb +125 -0
  91. data/lib/ferret/search/req_opt_sum_scorer.rb +70 -0
  92. data/lib/ferret/search/score_doc.rb +38 -0
  93. data/lib/ferret/search/score_doc_comparator.rb +114 -0
  94. data/lib/ferret/search/scorer.rb +91 -0
  95. data/lib/ferret/search/similarity.rb +278 -0
  96. data/lib/ferret/search/sloppy_phrase_scorer.rb +47 -0
  97. data/lib/ferret/search/sort.rb +105 -0
  98. data/lib/ferret/search/sort_comparator.rb +60 -0
  99. data/lib/ferret/search/sort_field.rb +87 -0
  100. data/lib/ferret/search/spans.rb +12 -0
  101. data/lib/ferret/search/spans/near_spans_enum.rb +304 -0
  102. data/lib/ferret/search/spans/span_first_query.rb +79 -0
  103. data/lib/ferret/search/spans/span_near_query.rb +108 -0
  104. data/lib/ferret/search/spans/span_not_query.rb +130 -0
  105. data/lib/ferret/search/spans/span_or_query.rb +176 -0
  106. data/lib/ferret/search/spans/span_query.rb +25 -0
  107. data/lib/ferret/search/spans/span_scorer.rb +74 -0
  108. data/lib/ferret/search/spans/span_term_query.rb +105 -0
  109. data/lib/ferret/search/spans/span_weight.rb +84 -0
  110. data/lib/ferret/search/spans/spans_enum.rb +44 -0
  111. data/lib/ferret/search/term_query.rb +128 -0
  112. data/lib/ferret/search/term_scorer.rb +181 -0
  113. data/lib/ferret/search/top_docs.rb +24 -0
  114. data/lib/ferret/search/top_field_docs.rb +17 -0
  115. data/lib/ferret/search/weight.rb +54 -0
  116. data/lib/ferret/search/wildcard_query.rb +26 -0
  117. data/lib/ferret/search/wildcard_term_enum.rb +61 -0
  118. data/lib/ferret/stemmers.rb +1 -0
  119. data/lib/ferret/stemmers/porter_stemmer.rb +218 -0
  120. data/lib/ferret/store.rb +5 -0
  121. data/lib/ferret/store/buffered_index_io.rb +191 -0
  122. data/lib/ferret/store/directory.rb +139 -0
  123. data/lib/ferret/store/fs_store.rb +338 -0
  124. data/lib/ferret/store/index_io.rb +259 -0
  125. data/lib/ferret/store/ram_store.rb +282 -0
  126. data/lib/ferret/utils.rb +7 -0
  127. data/lib/ferret/utils/bit_vector.rb +105 -0
  128. data/lib/ferret/utils/date_tools.rb +138 -0
  129. data/lib/ferret/utils/number_tools.rb +91 -0
  130. data/lib/ferret/utils/parameter.rb +41 -0
  131. data/lib/ferret/utils/priority_queue.rb +120 -0
  132. data/lib/ferret/utils/string_helper.rb +47 -0
  133. data/lib/ferret/utils/weak_key_hash.rb +51 -0
  134. data/rake_utils/code_statistics.rb +106 -0
  135. data/setup.rb +1551 -0
  136. data/test/benchmark/tb_ram_store.rb +76 -0
  137. data/test/benchmark/tb_rw_vint.rb +26 -0
  138. data/test/longrunning/tc_numbertools.rb +60 -0
  139. data/test/longrunning/tm_store.rb +19 -0
  140. data/test/test_all.rb +9 -0
  141. data/test/test_helper.rb +6 -0
  142. data/test/unit/analysis/tc_analyzer.rb +21 -0
  143. data/test/unit/analysis/tc_letter_tokenizer.rb +20 -0
  144. data/test/unit/analysis/tc_lower_case_filter.rb +20 -0
  145. data/test/unit/analysis/tc_lower_case_tokenizer.rb +27 -0
  146. data/test/unit/analysis/tc_per_field_analyzer_wrapper.rb +39 -0
  147. data/test/unit/analysis/tc_porter_stem_filter.rb +16 -0
  148. data/test/unit/analysis/tc_standard_analyzer.rb +20 -0
  149. data/test/unit/analysis/tc_standard_tokenizer.rb +20 -0
  150. data/test/unit/analysis/tc_stop_analyzer.rb +20 -0
  151. data/test/unit/analysis/tc_stop_filter.rb +14 -0
  152. data/test/unit/analysis/tc_white_space_analyzer.rb +21 -0
  153. data/test/unit/analysis/tc_white_space_tokenizer.rb +20 -0
  154. data/test/unit/analysis/tc_word_list_loader.rb +32 -0
  155. data/test/unit/document/tc_document.rb +47 -0
  156. data/test/unit/document/tc_field.rb +80 -0
  157. data/test/unit/index/tc_compound_file_io.rb +107 -0
  158. data/test/unit/index/tc_field_infos.rb +119 -0
  159. data/test/unit/index/tc_fields_io.rb +167 -0
  160. data/test/unit/index/tc_index.rb +140 -0
  161. data/test/unit/index/tc_index_reader.rb +622 -0
  162. data/test/unit/index/tc_index_writer.rb +57 -0
  163. data/test/unit/index/tc_multiple_term_doc_pos_enum.rb +80 -0
  164. data/test/unit/index/tc_segment_infos.rb +74 -0
  165. data/test/unit/index/tc_segment_term_docs.rb +17 -0
  166. data/test/unit/index/tc_segment_term_enum.rb +60 -0
  167. data/test/unit/index/tc_segment_term_vector.rb +71 -0
  168. data/test/unit/index/tc_term.rb +22 -0
  169. data/test/unit/index/tc_term_buffer.rb +57 -0
  170. data/test/unit/index/tc_term_info.rb +19 -0
  171. data/test/unit/index/tc_term_infos_io.rb +192 -0
  172. data/test/unit/index/tc_term_vector_offset_info.rb +18 -0
  173. data/test/unit/index/tc_term_vectors_io.rb +108 -0
  174. data/test/unit/index/th_doc.rb +244 -0
  175. data/test/unit/query_parser/tc_query_parser.rb +84 -0
  176. data/test/unit/search/tc_filter.rb +113 -0
  177. data/test/unit/search/tc_fuzzy_query.rb +136 -0
  178. data/test/unit/search/tc_index_searcher.rb +188 -0
  179. data/test/unit/search/tc_search_and_sort.rb +98 -0
  180. data/test/unit/search/tc_similarity.rb +37 -0
  181. data/test/unit/search/tc_sort.rb +48 -0
  182. data/test/unit/search/tc_sort_field.rb +27 -0
  183. data/test/unit/search/tc_spans.rb +153 -0
  184. data/test/unit/store/tc_fs_store.rb +84 -0
  185. data/test/unit/store/tc_ram_store.rb +35 -0
  186. data/test/unit/store/tm_store.rb +180 -0
  187. data/test/unit/store/tm_store_lock.rb +68 -0
  188. data/test/unit/ts_analysis.rb +16 -0
  189. data/test/unit/ts_document.rb +4 -0
  190. data/test/unit/ts_index.rb +18 -0
  191. data/test/unit/ts_query_parser.rb +3 -0
  192. data/test/unit/ts_search.rb +10 -0
  193. data/test/unit/ts_store.rb +6 -0
  194. data/test/unit/ts_utils.rb +10 -0
  195. data/test/unit/utils/tc_bit_vector.rb +65 -0
  196. data/test/unit/utils/tc_date_tools.rb +50 -0
  197. data/test/unit/utils/tc_number_tools.rb +59 -0
  198. data/test/unit/utils/tc_parameter.rb +40 -0
  199. data/test/unit/utils/tc_priority_queue.rb +62 -0
  200. data/test/unit/utils/tc_string_helper.rb +21 -0
  201. data/test/unit/utils/tc_weak_key_hash.rb +25 -0
  202. metadata +251 -0
@@ -0,0 +1,98 @@
1
+ require File.dirname(__FILE__) + "/../../test_helper"
2
+
3
+ class SearchAndSortTest < Test::Unit::TestCase
4
+ include Ferret::Document
5
+ include Ferret::Search
6
+ include Ferret::Store
7
+ include Ferret::Analysis
8
+ include Ferret::Index
9
+
10
+ def add_doc(hash, writer)
11
+ doc = Document.new()
12
+ hash.each_pair do |field, text|
13
+ doc << Field.new(field, text, Field::Store::NO, Field::Index::UNTOKENIZED)
14
+ end
15
+ doc.boost = hash["float"].to_f
16
+ writer << doc
17
+ end
18
+
19
+ def setup()
20
+ @dir = RAMDirectory.new()
21
+ iw = IndexWriter.new(@dir, :analyzer => WhiteSpaceAnalyzer.new(), :create => true)
22
+ docs = [ # len mod
23
+ {"search"=>"findall","string"=>"a","int"=>"6","float"=>"0.01"}, # 4 0
24
+ {"search"=>"findall","string"=>"c","int"=>"5","float"=>"0.1"}, # 3 3
25
+ {"search"=>"findall","string"=>"e","int"=>"2","float"=>"0.001"}, # 5 1
26
+ {"search"=>"findall","string"=>"g","int"=>"1","float"=>"1.0"}, # 3 3
27
+ {"search"=>"findall","string"=>"i","int"=>"3","float"=>"0.0001"}, # 6 2
28
+ {"search"=>"findall","string"=>"j","int"=>"4","float"=>"10.0"}, # 4 0
29
+ {"search"=>"findall","string"=>"h","int"=>"5","float"=>"0.00001"}, # 7 3
30
+ {"search"=>"findall","string"=>"f","int"=>"2","float"=>"100.0"}, # 5 1
31
+ {"search"=>"findall","string"=>"d","int"=>"3","float"=>"1000.0"}, # 6 2
32
+ {"search"=>"findall","string"=>"b","int"=>"4","float"=>"0.000001"} # 8 0
33
+ ]
34
+ docs.each {|doc| add_doc(doc, iw)}
35
+ iw.close
36
+ end
37
+
38
+ def tear_down()
39
+ @dir.close()
40
+ end
41
+
42
+ def do_test_top_docs(is, query, expected, sort = nil)
43
+ top_docs = is.search(query, {:sort => sort})
44
+ top_docs.total_hits.times do |i|
45
+ assert_equal(expected[i], top_docs.score_docs[i].doc)
46
+ end
47
+ end
48
+
49
+ def test_sorts()
50
+ is = IndexSearcher.new(@dir)
51
+ q = TermQuery.new(Term.new("search", "findall"))
52
+ do_test_top_docs(is, q, [8,7,5,3,1,0,2,4,6,9])
53
+ do_test_top_docs(is, q, [8,7,5,3,1,0,2,4,6,9], Sort::RELEVANCE)
54
+ do_test_top_docs(is, q, [8,7,5,3,1,0,2,4,6,9], [SortField::FIELD_SCORE])
55
+ do_test_top_docs(is, q, [0,1,2,3,4,5,6,7,8,9], Sort::INDEX_ORDER)
56
+ do_test_top_docs(is, q, [0,1,2,3,4,5,6,7,8,9], [SortField::FIELD_DOC])
57
+
58
+ ## int
59
+ sf_int = SortField.new("int", {:sort_type => SortField::SortType::INT})
60
+ do_test_top_docs(is, q, [0,1,6,5,9,4,8,2,7,3], [sf_int])
61
+ do_test_top_docs(is, q, [0,1,6,5,9,8,4,7,2,3], [sf_int, SortField::FIELD_SCORE])
62
+ sf_int = SortField.new("int", {:sort_type => SortField::SortType::INT, :reverse => true})
63
+ do_test_top_docs(is, q, [3,2,7,4,8,5,9,1,6,0], [sf_int])
64
+
65
+ ## float
66
+ sf_float = SortField.new("float", {:sort_type => SortField::SortType::FLOAT})
67
+ do_test_top_docs(is, q, [8,7,5,3,1,0,2,4,6,9], Sort.new([sf_float, SortField::FIELD_SCORE]))
68
+ sf_float = SortField.new("float", {:sort_type => SortField::SortType::FLOAT, :reverse => true})
69
+ do_test_top_docs(is, q, [9,6,4,2,0,1,3,5,7,8], Sort.new([sf_float, SortField::FIELD_SCORE]))
70
+
71
+ ## str
72
+ sf_str = SortField.new("string", {:sort_type => SortField::SortType::STRING})
73
+ do_test_top_docs(is, q, [0,9,1,8,2,7,3,6,4,5], [sf_str, SortField::FIELD_SCORE])
74
+
75
+ ## auto
76
+ do_test_top_docs(is, q, [0,9,1,8,2,7,3,6,4,5], Sort.new("string"))
77
+ do_test_top_docs(is, q, [0,1,6,5,9,4,8,2,7,3], Sort.new(["int"]))
78
+ do_test_top_docs(is, q, [8,7,5,3,1,0,2,4,6,9], Sort.new("float"))
79
+ do_test_top_docs(is, q, [9,6,4,2,0,1,3,5,7,8], Sort.new("float", true))
80
+ do_test_top_docs(is, q, [0,1,6,9,5,8,4,2,7,3], Sort.new(["int", "string"]))
81
+ do_test_top_docs(is, q, [3,7,2,4,8,5,9,6,1,0], Sort.new(["int", "string"], true))
82
+ end
83
+
84
+ LENGTH = SortField::SortType.new("length", lambda{|str| str.length})
85
+ LENGTH_MODULO = SortField::SortType.new("length_mod", lambda{|str| str.length},
86
+ lambda{|i, j| (i%4) <=> (j%4)})
87
+ def test_special_sorts
88
+ is = IndexSearcher.new(@dir)
89
+ q = TermQuery.new(Term.new("search", "findall"))
90
+ sf = SortField.new("float", {:sort_type => LENGTH})
91
+ do_test_top_docs(is, q, [9,6,4,8,2,7,0,5,1,3], [sf])
92
+ sf = SortField.new("float", {:sort_type => LENGTH_MODULO})
93
+ do_test_top_docs(is, q, [1,3,6,4,8,2,7,0,5,9], [sf])
94
+ sf = SortField.new("float", {:sort_type => LENGTH,
95
+ :comparator => lambda{|i,j| (j%4) <=> (i%4)}})
96
+ do_test_top_docs(is, q, [0,5,9,2,7,4,8,1,3,6], [sf])
97
+ end
98
+ end
@@ -0,0 +1,37 @@
1
+ require File.dirname(__FILE__) + "/../../test_helper"
2
+
3
+
4
+ class SimilarityTest < Test::Unit::TestCase
5
+ include Ferret::Search
6
+ include Ferret::Index
7
+
8
+ def test_byte_float_conversion()
9
+ 256.times do |i|
10
+ assert_equal(i, Similarity.float_to_byte(Similarity.byte_to_float(i)))
11
+ assert_equal(Similarity.byte_to_float(i), Similarity::NORM_TABLE[i])
12
+ assert_equal(i, Similarity.encode_norm(Similarity.decode_norm(i)))
13
+ end
14
+ end
15
+
16
+ def test_default_similarity
17
+ dsim = DefaultSimilarity.new()
18
+ assert_equal(1.0/4, dsim.length_norm("field", 16))
19
+ assert_equal(1.0/4, dsim.query_norm(16))
20
+ assert_equal(3.0, dsim.tf(9))
21
+ assert_equal(1.0/10, dsim.sloppy_freq(9))
22
+ assert_equal(1.0, dsim.idf(9, 10))
23
+ assert_equal(4.0, dsim.coord(12, 3))
24
+ searcher = Object.new
25
+ def searcher.doc_freq(term) 9 end
26
+ def searcher.max_doc() 10 end
27
+ term = Term.new("field", "text")
28
+ assert_equal(1.0, dsim.idf_term(term, searcher))
29
+ terms = [
30
+ Term.new("field1", "text1"),
31
+ Term.new("field1", "text2"),
32
+ Term.new("field2", "text3"),
33
+ Term.new("field2", "text4")
34
+ ]
35
+ assert_equal(4.0, dsim.idf_phrase(terms, searcher))
36
+ end
37
+ end
@@ -0,0 +1,48 @@
1
+ require File.dirname(__FILE__) + "/../../test_helper"
2
+
3
+ class SortTest < Test::Unit::TestCase
4
+ include Ferret::Search
5
+
6
+ def test_basic()
7
+ s = Sort::RELEVANCE
8
+ assert_equal(2, s.fields.size)
9
+ assert_equal(SortField::FIELD_SCORE, s.fields[0])
10
+ assert_equal(SortField::FIELD_DOC, s.fields[1])
11
+
12
+ s = Sort::INDEX_ORDER
13
+ assert_equal(1, s.fields.size)
14
+ assert_equal(SortField::FIELD_DOC, s.fields[0])
15
+ end
16
+
17
+ def test_string_init()
18
+ s = Sort.new("field")
19
+ assert_equal(2, s.fields.size)
20
+ assert_equal(SortField::SortType::AUTO, s.fields[0].sort_type)
21
+ assert_equal("field", s.fields[0].name)
22
+ assert_equal(SortField::FIELD_DOC, s.fields[1])
23
+
24
+ s = Sort.new(["field1", "field2", "field3"])
25
+ assert_equal(3, s.fields.size)
26
+ assert_equal(SortField::SortType::AUTO, s.fields[0].sort_type)
27
+ assert_equal("field1", s.fields[0].name)
28
+ assert_equal(SortField::SortType::AUTO, s.fields[1].sort_type)
29
+ assert_equal("field2", s.fields[1].name)
30
+ assert_equal(SortField::SortType::AUTO, s.fields[2].sort_type)
31
+ assert_equal("field3", s.fields[2].name)
32
+ end
33
+
34
+ def test_multi_fields()
35
+ sf1 = SortField.new("field", {:sort_type => SortField::SortType::INT,
36
+ :reverse => true})
37
+ sf2 = SortField::FIELD_SCORE
38
+ sf3 = SortField::FIELD_DOC
39
+ s = Sort.new([sf1, sf2, sf3])
40
+
41
+ assert_equal(3, s.fields.size)
42
+ assert_equal(SortField::SortType::INT, s.fields[0].sort_type)
43
+ assert_equal("field", s.fields[0].name)
44
+ assert(s.fields[0].reverse?)
45
+ assert_equal(SortField::FIELD_SCORE, s.fields[1])
46
+ assert_equal(SortField::FIELD_DOC, s.fields[2])
47
+ end
48
+ end
@@ -0,0 +1,27 @@
1
+ require File.dirname(__FILE__) + "/../../test_helper"
2
+
3
+ class SortFieldTest < Test::Unit::TestCase
4
+ include Ferret::Search
5
+
6
+ def test_field_score()
7
+ fs = SortField::FIELD_SCORE
8
+ assert_equal(SortField::SortType::SCORE, fs.sort_type)
9
+ assert_nil(fs.name)
10
+ assert(!fs.reverse?, "FIELD_SCORE should not be reverse")
11
+ assert_nil(fs.comparator)
12
+ end
13
+
14
+ def test_field_doc()
15
+ fs = SortField::FIELD_DOC
16
+ assert_equal(SortField::SortType::DOC, fs.sort_type)
17
+ assert_nil(fs.name)
18
+ assert(!fs.reverse?, "FIELD_DOC should not be reverse")
19
+ assert_nil(fs.comparator)
20
+ end
21
+
22
+ def test_error_raised()
23
+ assert_raise(ArgumentError) {
24
+ fs = SortField.new(nil, {:sort_type => SortField::SortType::INT})
25
+ }
26
+ end
27
+ end
@@ -0,0 +1,153 @@
1
+ require File.dirname(__FILE__) + "/../../test_helper"
2
+
3
+
4
+ class SpansBasicTest < Test::Unit::TestCase
5
+ include Ferret::Document
6
+ include Ferret::Search
7
+ include Ferret::Store
8
+ include Ferret::Index
9
+ include Ferret::Search::Spans
10
+ include Ferret::Analysis
11
+
12
+ def setup()
13
+ data = [
14
+ "start finish one two three four five six seven",
15
+ "start one finish two three four five six seven",
16
+ "start one two finish three four five six seven",
17
+ "start one two three finish four five six seven",
18
+ "start one two three four finish five six seven",
19
+ "start one two three four five finish six seven",
20
+ "start one two three four five six finish seven eight",
21
+ "start one two three four five six seven finish eight nine",
22
+ "start one two three four five six finish seven eight",
23
+ "start one two three four five finish six seven",
24
+ "start one two three four finish five six seven",
25
+ "start one two three finish four five six seven",
26
+ "start one two finish three four five six seven",
27
+ "start one finish two three four five six seven",
28
+ "start finish one two three four five six seven",
29
+ "start start one two three four five six seven",
30
+ "finish start one two three four five six seven",
31
+ "finish one start two three four five six seven",
32
+ "finish one two start three four five six seven",
33
+ "finish one two three start four five six seven",
34
+ "finish one two three four start five six seven",
35
+ "finish one two three four five start six seven",
36
+ "finish one two three four five six start seven eight",
37
+ "finish one two three four five six seven start eight nine",
38
+ "finish one two three four five six start seven eight",
39
+ "finish one two three four five start six seven",
40
+ "finish one two three four start five six seven",
41
+ "finish one two three start four five six seven",
42
+ "finish one two start three four five six seven",
43
+ "finish one start two three four five six seven",
44
+ "finish start one two three four five six seven"
45
+ ]
46
+ @dir = RAMDirectory.new
47
+ iw = IndexWriter.new(@dir, :analyzer => WhiteSpaceAnalyzer.new(), :create => true)
48
+ data.each do |line|
49
+ doc = Document.new()
50
+ doc << Field.new("field", line, Field::Store::NO, Field::Index::TOKENIZED)
51
+ iw << doc
52
+ end
53
+
54
+ iw.close()
55
+
56
+ @is = IndexSearcher.new(@dir)
57
+ end
58
+
59
+ def tear_down()
60
+ @iw.close
61
+ @dir.close
62
+ end
63
+
64
+ def number_split(i)
65
+ if (i < 10)
66
+ return "<#{i}>"
67
+ elsif (i < 100)
68
+ return "<#{((i/10)*10)}> <#{i%10}>"
69
+ else
70
+ return "<#{((i/100)*100)}> <#{(((i%100)/10)*10)}> <#{i%10}>"
71
+ end
72
+ end
73
+
74
+ def check_hits(query, expected, test_explain = false, top=nil)
75
+ top_docs = @is.search(query, {:num_docs => expected.length})
76
+ assert_equal(expected.length, top_docs.score_docs.size)
77
+ assert_equal(top, top_docs.score_docs[0].doc) if top
78
+ assert_equal(expected.length, top_docs.total_hits)
79
+ top_docs.score_docs.each do |score_doc|
80
+ assert(expected.include?(score_doc.doc),
81
+ "#{score_doc.doc} was found unexpectedly")
82
+ if test_explain
83
+ assert(score_doc.score =~ @is.explain(query, score_doc.doc).value,
84
+ "Scores(#{score_doc.score} != #{@is.explain(query, score_doc.doc).value})")
85
+ end
86
+ end
87
+ end
88
+
89
+ def test_span_term_query()
90
+ tq = SpanTermQuery.new(Term.new("field", "nine"))
91
+ check_hits(tq, [7,23], true)
92
+ tq = SpanTermQuery.new(Term.new("field", "eight"))
93
+ check_hits(tq, [6,7,8,22,23,24])
94
+ end
95
+
96
+ def test_span_near_query()
97
+ tq1 = SpanTermQuery.new(Term.new("field", "start"))
98
+ tq2 = SpanTermQuery.new(Term.new("field", "finish"))
99
+ q = SpanNearQuery.new([tq1, tq2], 0, true)
100
+ check_hits(q, [0,14], true)
101
+ q = SpanNearQuery.new([tq1, tq2], 0, false)
102
+ check_hits(q, [0,14,16,30], true)
103
+ q = SpanNearQuery.new([tq1, tq2], 1, true)
104
+ check_hits(q, [0,1,13,14])
105
+ q = SpanNearQuery.new([tq1, tq2], 1, false)
106
+ check_hits(q, [0,1,13,14,16,17,29,30])
107
+ q = SpanNearQuery.new([tq1, tq2], 4, true)
108
+ check_hits(q, [0,1,2,3,4,10,11,12,13,14])
109
+ q = SpanNearQuery.new([tq1, tq2], 4, false)
110
+ check_hits(q, [0,1,2,3,4,10,11,12,13,14,16,17,18,19,20,26,27,28,29,30])
111
+ end
112
+
113
+ def test_span_not_query()
114
+ tq1 = SpanTermQuery.new(Term.new("field", "start"))
115
+ tq2 = SpanTermQuery.new(Term.new("field", "finish"))
116
+ tq3 = SpanTermQuery.new(Term.new("field", "two"))
117
+ tq4 = SpanTermQuery.new(Term.new("field", "five"))
118
+ nearq1 = SpanNearQuery.new([tq1, tq2], 4, true)
119
+ nearq2 = SpanNearQuery.new([tq3, tq4], 4, true)
120
+ q = SpanNotQuery.new(nearq1, nearq2)
121
+ check_hits(q, [0,1,13,14], true)
122
+ nearq1 = SpanNearQuery.new([tq1, tq2], 4, false)
123
+ q = SpanNotQuery.new(nearq1, nearq2)
124
+ check_hits(q, [0,1,13,14,16,17,29,30])
125
+ nearq1 = SpanNearQuery.new([tq1, tq3], 4, true)
126
+ nearq2 = SpanNearQuery.new([tq2, tq4], 8, false)
127
+ q = SpanNotQuery.new(nearq1, nearq2)
128
+ check_hits(q, [2,3,4,5,6,7,8,9,10,11,12,15])
129
+ end
130
+
131
+ def test_span_first_query()
132
+ finish_first = [16,17,18,19,20,21,22,23,24,25,26,27,28,29,30]
133
+ tq = SpanTermQuery.new(Term.new("field", "finish"))
134
+ q = SpanFirstQuery.new(tq, 1)
135
+ check_hits(q, finish_first, true)
136
+ q = SpanFirstQuery.new(tq, 5)
137
+ check_hits(q, [0,1,2,3,11,12,13,14]+finish_first, false)
138
+ end
139
+
140
+ def test_span_or_query_query()
141
+ tq1 = SpanTermQuery.new(Term.new("field", "start"))
142
+ tq2 = SpanTermQuery.new(Term.new("field", "finish"))
143
+ tq3 = SpanTermQuery.new(Term.new("field", "five"))
144
+ nearq1 = SpanNearQuery.new([tq1, tq2], 1, true)
145
+ nearq2 = SpanNearQuery.new([tq2, tq3], 0, false)
146
+ q = SpanOrQuery.new([nearq1, nearq2])
147
+ check_hits(q, [0,1,4,5,9,10,13,14], false)
148
+ nearq1 = SpanNearQuery.new([tq1, tq2], 0, false)
149
+ nearq2 = SpanNearQuery.new([tq2, tq3], 1, false)
150
+ q = SpanOrQuery.new([nearq1, nearq2])
151
+ check_hits(q, [0,3,4,5,6,8,9,10,11,14,16,30], false)
152
+ end
153
+ end
@@ -0,0 +1,84 @@
1
+ require File.dirname(__FILE__) + "/../../test_helper"
2
+ require File.dirname(__FILE__) + "/tm_store"
3
+ require File.dirname(__FILE__) + "/tm_store_lock"
4
+
5
+ module Ferret::Store
6
+
7
+ class FSDirectory
8
+ def FSDirectory.directory_cache
9
+ @@Directories
10
+ end
11
+
12
+ def ref_count
13
+ @ref_count
14
+ end
15
+
16
+ def get_lock_prefix
17
+ lock_prefix
18
+ end
19
+ end
20
+ end
21
+
22
+ class FSStoreTest < Test::Unit::TestCase
23
+ include Ferret::Store
24
+ include StoreTest
25
+ include StoreLockTest
26
+ def setup
27
+ @dpath = File.join(File.dirname(__FILE__),
28
+ '../../temp/fsdir')
29
+ @dir = FSDirectory.get_directory(@dpath, true)
30
+ end
31
+
32
+ def teardown
33
+ @dir.refresh()
34
+ @dir.close()
35
+ end
36
+
37
+ def test_cache
38
+ dir_path = File.join(File.dirname(__FILE__),
39
+ '/../../temp/cachetest')
40
+ assert(! FSDirectory.directory_cache[dir_path],
41
+ "this directory should not be cached yet")
42
+ @dir1 = FSDirectory.get_directory(dir_path, true)
43
+ assert(FSDirectory.directory_cache[dir_path],
44
+ "this directory should now be cached")
45
+ assert_equal(@dir1.ref_count, 1,
46
+ "There is one reference so the refcount should now be 1")
47
+ @dir2 = FSDirectory.get_directory(dir_path, true)
48
+ assert(@dir1 === @dir2,
49
+ "The directory should be cached so the same directory object should have been returned")
50
+ assert_equal(@dir1.ref_count, 2,
51
+ "There are two references so the refcount should now be 2")
52
+ @dir1.close
53
+ assert(FSDirectory.directory_cache[dir_path],
54
+ "this directory shouldn't have been removed yet")
55
+ assert_equal(@dir2.ref_count, 1,
56
+ "There is one reference so the refcount should now be 1")
57
+ @dir2.close
58
+ assert(! FSDirectory.directory_cache[dir_path],
59
+ "this directory should have been removed from the cache")
60
+ end
61
+
62
+ def test_fslock
63
+ name = "lfile"
64
+ lock_file_path = @dpath + "/" + @dir.get_lock_prefix() + name
65
+ if File.exists?(lock_file_path) then
66
+ File.delete(lock_file_path)
67
+ end
68
+ assert(! File.exists?(lock_file_path),
69
+ "There should be no lock file")
70
+ lock = @dir.make_lock(name)
71
+ assert(! File.exists?(lock_file_path),
72
+ "There should still be no lock file")
73
+ assert(! @dir.exists?(lock_file_path),
74
+ "The lock should be hidden by the FSDirectories directory scan")
75
+ assert(! lock.locked?, "lock shouldn't be locked yet")
76
+ lock.obtain
77
+ assert(lock.locked?, "lock should now be locked")
78
+ assert(File.exists?(lock_file_path),
79
+ "A lock file should have been created")
80
+ lock.release
81
+ assert(! lock.locked?, "lock should be freed again")
82
+ assert(! File.exists?(lock_file_path), "The lock file should have been deleted")
83
+ end
84
+ end