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 +1,76 @@
1
+ require File.dirname(__FILE__) + "/../test_helper"
2
+ require 'benchmark'
3
+
4
+ class RAMStoreTest < Test::Unit::TestCase
5
+ def setup
6
+ @dir = Ferret::Store::RAMDirectory.new
7
+ end
8
+
9
+ def teardown
10
+ @dir.close()
11
+ end
12
+
13
+ def test_rw_bytes
14
+ bytes = [0x34, 0x87, 0xF9, 0xEA, 0x00, 0xFF]
15
+ rw_test(bytes, "byte")
16
+ end
17
+
18
+ def test_rw_ints
19
+ ints = [-2147483648, 2147483647, -1, 0]
20
+ rw_test(ints, "int")
21
+ end
22
+
23
+ def test_rw_longs
24
+ longs = [-9223372036854775808, 9223372036854775807, -1, 0]
25
+ rw_test(longs, "long")
26
+ end
27
+
28
+ def test_rw_uints
29
+ uints = [0xffffffff, 100000, 0]
30
+ rw_test(uints, "uint")
31
+ end
32
+
33
+ def test_rw_ulongs
34
+ ulongs = [0xffffffffffffffff, 100000000000000, 0]
35
+ rw_test(ulongs, "ulong")
36
+ end
37
+
38
+ def test_rw_vints
39
+ vints = [ 0xF8DC843342FE3484234987FE98AB987C897D214D123D123458EFBE2E238BACDEB9878790ABCDEF123DEF23988B89C,
40
+ 0x0000000000000000000000000000000000000000,
41
+ 0xFFFFFFFFFFFFFFFFFFFFFFFFFFFFFF]
42
+ rw_test(vints, "vint")
43
+ end
44
+
45
+ def test_rw_vlongs
46
+ vlongs = [ 0xF8DC843342FE3484234987FE98AB987C897D214D123D123458EFBE2E238BACDEB9878790ABCDEF123DEF23988B89C,
47
+ 0x0000000000000000000000000000000000000000,
48
+ 0xFFFFFFFFFFFFFFFFFFFFFFFFFFFFFF]
49
+ rw_test(vlongs, "vlong")
50
+ end
51
+
52
+ def test_rw_strings
53
+ strings = ['This is a ruby ferret test string ~!@#$%^&*()`123456790-=\)_+|', 'This is another string. I\'ll make this one a little longer than the last one. But I guess we need a few shorter ones too.', 'one', 'two', 'three', 'four', 'five', 'six', 'seven', 'eight', 'nine', 'ten']
54
+ rw_test(strings, "string")
55
+ end
56
+
57
+ # this test fills up the output stream so that the buffer will have to be
58
+ # written a few times. It then uses seek to make sure that it works
59
+ # correctly
60
+
61
+ def rw_test(values, type)
62
+ puts "\nrw_#{type} test"
63
+ Benchmark.bmbm do |x|
64
+ x.report("write") do
65
+ ostream = @dir.create_output("rw_#{type}.test")
66
+ 1000.times {values.each { |b| ostream.__send__("write_" + type, b) }}
67
+ ostream.close
68
+ end
69
+ x.report("read") do
70
+ istream = @dir.open_input("rw_#{type}.test")
71
+ 1000.times {values.each { |b| assert_equal(b, istream.__send__("read_" + type), "#{type} should be equal") }}
72
+ istream.close
73
+ end
74
+ end
75
+ end
76
+ end
@@ -0,0 +1,26 @@
1
+ $:.unshift File.join(File.dirname(__FILE__), '../../lib')
2
+
3
+ require 'ferret'
4
+
5
+ vints = [ 9223372036854775807,
6
+ 0x00,
7
+ 0xFFFFFFFFFFFFFFFF]
8
+ t = Time.new
9
+ 10.times do
10
+ dpath = File.join(File.dirname(__FILE__),
11
+ 'fsdir')
12
+ dir = Ferret::Store::FSDirectory.get_directory(dpath, true)
13
+
14
+ 100.times do
15
+ ostream = dir.create_output("rw_vint.test")
16
+ 300.times { |i| ostream.write_vint(vints[i%3]) }
17
+ ostream.close
18
+ istream = dir.open_input("rw_vint.test")
19
+ 300.times { istream.read_vint }
20
+ istream.close
21
+ end
22
+
23
+ dir.close
24
+ end
25
+
26
+ puts "took #{Time.new - t} seconds"
@@ -0,0 +1,60 @@
1
+ require File.dirname(__FILE__) + "/../../../test_helper"
2
+
3
+
4
+ class NumberToolsTest < Test::Unit::TestCase
5
+ include Lucene::Document
6
+ def test_near_zero()
7
+ 10.times() do |i|
8
+ 10.times() { |j| subtest_two_longs(i, j) }
9
+ end
10
+ end
11
+
12
+ def test_max()
13
+ # make sure the constants convert to their equivelents
14
+ assert_equal(NumberTools::LONG_MAX_VALUE, NumberTools.s_to_long(NumberTools::MAX_STRING_VALUE))
15
+ assert_equal(NumberTools::MAX_STRING_VALUE, NumberTools.long_to_s(NumberTools::LONG_MAX_VALUE))
16
+ # test near MAX, too
17
+
18
+ NumberTools::LONG_MAX_VALUE.downto(NumberTools::LONG_MAX_VALUE - 100) do |l|
19
+ subtest_two_longs(l, l - 1)
20
+ end
21
+ end
22
+
23
+ def test_min()
24
+ # make sure the constants convert to their equivelents
25
+ assert_equal(NumberTools::LONG_MIN_VALUE, NumberTools.s_to_long(NumberTools::MIN_STRING_VALUE))
26
+ assert_equal(NumberTools::MIN_STRING_VALUE, NumberTools.long_to_s(NumberTools::LONG_MIN_VALUE))
27
+
28
+ # test near MIN, too
29
+ NumberTools::LONG_MIN_VALUE.upto(NumberTools::LONG_MIN_VALUE + 100) do |l|
30
+ subtest_two_longs(l, l + 1)
31
+ end
32
+ end
33
+
34
+ def subtest_two_longs(i, j)
35
+ # convert to strings
36
+ a = NumberTools.long_to_s(i)
37
+ b = NumberTools.long_to_s(j)
38
+
39
+ # are they the right length?
40
+ assert_equal(NumberTools::STR_SIZE, a.length())
41
+ assert_equal(NumberTools::STR_SIZE, b.length())
42
+
43
+ # are they the right order?
44
+ if (i < j)
45
+ assert(a < b)
46
+ elsif (i > j)
47
+ assert(a > b)
48
+ else
49
+ assert_equal(a, b)
50
+ end
51
+
52
+ # can we convert them back to longs?
53
+ i2 = NumberTools.s_to_long(a)
54
+ j2 = NumberTools.s_to_long(b)
55
+
56
+ assert_equal(i, i2)
57
+ assert_equal(j, j2)
58
+ end
59
+
60
+ end
@@ -0,0 +1,19 @@
1
+ module StoreTest
2
+ # declare dir so inheritors can access it.
3
+ def test_modified_full
4
+ # difficult to test this one but as file mtime is only stored to the
5
+ # nearest second. We can assume this test will happen in less than one
6
+ # second. (I hope)
7
+ time = Time.new.to_i
8
+ @dir.touch('mtime_test')
9
+ time_before = @dir.modified('mtime_test').to_i
10
+ assert(time_before - time <= 2, "test that mtime is approximately equal to the system time when the file was touched")
11
+ # wait until the time ticks over one second.
12
+ time = Time.new while (time.to_i == time_before)
13
+ time_before_again = @dir.modified('mtime_test').to_i
14
+ assert_equal(time_before, time_before_again, "the modified time shouldn't change")
15
+ @dir.touch('mtime_test')
16
+ time_after = @dir.modified('mtime_test').to_i
17
+ assert(time_before < time_after, "the modified time should now be greater")
18
+ end
19
+ end
@@ -0,0 +1,9 @@
1
+ $:.unshift File.dirname(__FILE__)
2
+
3
+ require 'unit/ts_analysis.rb'
4
+ require 'unit/ts_document.rb'
5
+ require 'unit/ts_index.rb'
6
+ require 'unit/ts_query_parser.rb'
7
+ require 'unit/ts_search.rb'
8
+ require 'unit/ts_store.rb'
9
+ require 'unit/ts_utils.rb'
@@ -0,0 +1,6 @@
1
+ $:.unshift File.join(File.dirname(__FILE__), '../lib')
2
+ $:.unshift File.join(File.dirname(__FILE__), '../ext')
3
+
4
+ require 'test/unit'
5
+ require 'ferret'
6
+ require 'test/unit/index/th_doc'
@@ -0,0 +1,21 @@
1
+ require File.dirname(__FILE__) + "/../../test_helper"
2
+
3
+ class AnalyzerTest < Test::Unit::TestCase
4
+ include Ferret::Analysis
5
+ include Ferret::Utils::StringHelper
6
+
7
+ def test_analyzer()
8
+ input = StringReader.new('DBalmain@gmail.com is My E-Mail 523@#$ ADDRESS. 23#@$')
9
+ a = Analyzer.new()
10
+ t = a.token_stream("fieldname", input)
11
+ assert_equal(Token.new("dbalmain", 0, 8), t.next())
12
+ assert_equal(Token.new("gmail", 9, 14), t.next())
13
+ assert_equal(Token.new("com", 15, 18), t.next())
14
+ assert_equal(Token.new("is", 19, 21), t.next())
15
+ assert_equal(Token.new("my", 22, 24), t.next())
16
+ assert_equal(Token.new("e", 25, 26), t.next())
17
+ assert_equal(Token.new("mail", 27, 31), t.next())
18
+ assert_equal(Token.new("address", 39, 46), t.next())
19
+ assert(! t.next())
20
+ end
21
+ end
@@ -0,0 +1,20 @@
1
+ require File.dirname(__FILE__) + "/../../test_helper"
2
+
3
+ class LetterTokenizerTest < Test::Unit::TestCase
4
+ include Ferret::Analysis
5
+ include Ferret::Utils::StringHelper
6
+
7
+ def test_lettertokenizer()
8
+ input = StringReader.new('DBalmain@gmail.com is My e-mail 523@#$ address. 23#@$')
9
+ t = LetterTokenizer.new(input)
10
+ assert_equal(Token.new("DBalmain", 0, 8), t.next())
11
+ assert_equal(Token.new("gmail", 9, 14), t.next())
12
+ assert_equal(Token.new("com", 15, 18), t.next())
13
+ assert_equal(Token.new("is", 19, 21), t.next())
14
+ assert_equal(Token.new("My", 22, 24), t.next())
15
+ assert_equal(Token.new("e", 25, 26), t.next())
16
+ assert_equal(Token.new("mail", 27, 31), t.next())
17
+ assert_equal(Token.new("address", 39, 46), t.next())
18
+ assert(! t.next())
19
+ end
20
+ end
@@ -0,0 +1,20 @@
1
+ require File.dirname(__FILE__) + "/../../test_helper"
2
+
3
+ class LowerCaseFilterTest < Test::Unit::TestCase
4
+ include Ferret::Analysis
5
+ include Ferret::Utils::StringHelper
6
+
7
+ def test_lowercasefilter()
8
+ input = StringReader.new('DBalmain@gmail.com is My E-Mail 52 #$ ADDRESS. 23#@$')
9
+ t = LowerCaseFilter.new(WhiteSpaceTokenizer.new(input))
10
+ assert_equal(Token.new('dbalmain@gmail.com', 0, 18), t.next())
11
+ assert_equal(Token.new('is', 19, 21), t.next())
12
+ assert_equal(Token.new('my', 22, 24), t.next())
13
+ assert_equal(Token.new('e-mail', 25, 31), t.next())
14
+ assert_equal(Token.new('52', 32, 34), t.next())
15
+ assert_equal(Token.new('#$', 37, 39), t.next())
16
+ assert_equal(Token.new('address.', 40, 48), t.next())
17
+ assert_equal(Token.new('23#@$', 49, 54), t.next())
18
+ assert(! t.next())
19
+ end
20
+ end
@@ -0,0 +1,27 @@
1
+ require File.dirname(__FILE__) + "/../../test_helper"
2
+
3
+ class LowerCaseTokenizerTest < Test::Unit::TestCase
4
+ include Ferret::Analysis
5
+ include Ferret::Utils::StringHelper
6
+
7
+ def test_normalize()
8
+ lt = LowerCaseTokenizer.new(StringReader.new(""))
9
+ assert_equal('!', lt.__send__(:normalize,"!"))
10
+ assert_equal('r', lt.__send__(:normalize,"r"))
11
+ assert_equal('r', lt.__send__(:normalize,"R"))
12
+ end
13
+
14
+ def test_lowercase_tokenizer()
15
+ input = StringReader.new('DBalmain@gmail.com is My E-Mail 523@#$ ADDRESS. 23#@$')
16
+ t = LowerCaseTokenizer.new(input)
17
+ assert_equal(Token.new("dbalmain", 0, 8), t.next())
18
+ assert_equal(Token.new("gmail", 9, 14), t.next())
19
+ assert_equal(Token.new("com", 15, 18), t.next())
20
+ assert_equal(Token.new("is", 19, 21), t.next())
21
+ assert_equal(Token.new("my", 22, 24), t.next())
22
+ assert_equal(Token.new("e", 25, 26), t.next())
23
+ assert_equal(Token.new("mail", 27, 31), t.next())
24
+ assert_equal(Token.new("address", 39, 46), t.next())
25
+ assert(! t.next())
26
+ end
27
+ end
@@ -0,0 +1,39 @@
1
+ require File.dirname(__FILE__) + "/../../test_helper"
2
+
3
+ class PerFieldAnalyzerWrapperTest < Test::Unit::TestCase
4
+ include Ferret::Analysis
5
+ include Ferret::Utils::StringHelper
6
+ def test_perfieldanalyzerwrapper()
7
+ aw = PerFieldAnalyzerWrapper.new(Analyzer.new())
8
+ aw.add_analyzer("abstract", WhiteSpaceAnalyzer.new())
9
+ aw.add_analyzer("body", StopAnalyzer.new(['is', 'my', 'address']))
10
+ input = StringReader.new('DBalmain@gmail.com is My e-mail ADDRESS')
11
+ t = aw.token_stream("title", input)
12
+ assert_equal(Token.new("dbalmain", 0, 8), t.next())
13
+ assert_equal(Token.new("gmail", 9, 14), t.next())
14
+ assert_equal(Token.new("com", 15, 18), t.next())
15
+ assert_equal(Token.new("is", 19, 21), t.next())
16
+ assert_equal(Token.new("my", 22, 24), t.next())
17
+ assert_equal(Token.new("e", 25, 26), t.next())
18
+ assert_equal(Token.new("mail", 27, 31), t.next())
19
+ assert_equal(Token.new("address", 32, 39), t.next())
20
+ assert(! t.next())
21
+ input.reset()
22
+ t = aw.token_stream("abstract", input)
23
+ assert_equal(Token.new('DBalmain@gmail.com', 0, 18), t.next())
24
+ assert_equal(Token.new('is', 19, 21), t.next())
25
+ assert_equal(Token.new('My', 22, 24), t.next())
26
+ assert_equal(Token.new('e-mail', 25, 31), t.next())
27
+ assert_equal(Token.new("ADDRESS", 32, 39), t.next())
28
+ if ( token = t.next()): puts token.term_text end
29
+ assert(! t.next())
30
+ input.reset()
31
+ t = aw.token_stream("body", input)
32
+ assert_equal(Token.new("dbalmain", 0, 8), t.next())
33
+ assert_equal(Token.new("gmail", 9, 14), t.next())
34
+ assert_equal(Token.new("com", 15, 18), t.next())
35
+ assert_equal(Token.new("e", 25, 26), t.next())
36
+ assert_equal(Token.new("mail", 27, 31), t.next())
37
+ assert(! t.next())
38
+ end
39
+ end
@@ -0,0 +1,16 @@
1
+ require File.dirname(__FILE__) + "/../../test_helper"
2
+
3
+ class PorterStemFilterTest < Test::Unit::TestCase
4
+ include Ferret::Analysis
5
+ include Ferret::Utils::StringHelper
6
+
7
+ def test_porterstempfilter()
8
+ input = StringReader.new('breath Breathes BreatHed BREATHING')
9
+ t = PorterStemFilter.new(LowerCaseFilter.new(WhiteSpaceTokenizer.new(input)))
10
+ assert_equal(Token.new('breath', 0, 6), t.next())
11
+ assert_equal(Token.new('breath', 7, 15), t.next())
12
+ assert_equal(Token.new('breath', 16, 24), t.next())
13
+ assert_equal(Token.new('breath', 25, 34), t.next())
14
+ assert(! t.next())
15
+ end
16
+ end
@@ -0,0 +1,20 @@
1
+ require File.dirname(__FILE__) + "/../../test_helper"
2
+
3
+ class StandardAnalyzerTest < Test::Unit::TestCase
4
+ include Ferret::Utils::StringHelper
5
+ include Ferret::Analysis
6
+
7
+ def test_lettertokenizer()
8
+ input = StringReader.new('D.Ba_l-n@gma-l.com AB&Sons Toys\'r\'us you\'re she\'s, #$%^$%*& job@dot I.B.M. the an AnD THEIR')
9
+ sa = StandardAnalyzer.new()
10
+ t = sa.token_stream("field", input)
11
+ assert_equal(Token.new("d.ba_l-n@gma-l.com", 0, 18), t.next())
12
+ assert_equal(Token.new("ab&sons", 19, 26), t.next())
13
+ assert_equal(Token.new("toys'r'us", 27, 36), t.next())
14
+ assert_equal(Token.new("you're", 37, 43), t.next())
15
+ assert_equal(Token.new("she", 44, 49), t.next())
16
+ assert_equal(Token.new("job@dot", 60, 67), t.next())
17
+ assert_equal(Token.new("ibm", 68, 74), t.next())
18
+ assert(! t.next())
19
+ end
20
+ end
@@ -0,0 +1,20 @@
1
+ require File.dirname(__FILE__) + "/../../test_helper"
2
+
3
+ class StandardTokenizerTest < Test::Unit::TestCase
4
+ include Ferret::Analysis
5
+ include Ferret::Utils::StringHelper
6
+
7
+ def test_lettertokenizer()
8
+ input = StringReader.new('DBalmain@gmail.com is My e-mail 523@#$ address. 23#@$')
9
+ t = StandardTokenizer.new(input)
10
+ assert_equal(Token.new("DBalmain@gmail.com", 0, 18), t.next())
11
+ assert_equal(Token.new("is", 19, 21), t.next())
12
+ assert_equal(Token.new("My", 22, 24), t.next())
13
+ assert_equal(Token.new("e", 25, 26), t.next())
14
+ assert_equal(Token.new("mail", 27, 31), t.next())
15
+ assert_equal(Token.new("523", 32, 35), t.next())
16
+ assert_equal(Token.new("address", 39, 46), t.next())
17
+ assert_equal(Token.new("23", 48, 50), t.next())
18
+ assert(! t.next())
19
+ end
20
+ end
@@ -0,0 +1,20 @@
1
+ require File.dirname(__FILE__) + "/../../test_helper"
2
+
3
+ class StopAnalyzerTest < Test::Unit::TestCase
4
+ include Ferret::Analysis
5
+ include Ferret::Utils::StringHelper
6
+
7
+ def test_stopanalyzer()
8
+ input = StringReader.new('The Quick AND the DEAD the and to it there their')
9
+ a = StopAnalyzer.new()
10
+ t = a.token_stream("field name", input)
11
+ assert_equal(Token.new('quick', 4, 9), t.next())
12
+ assert_equal(Token.new('dead', 18, 22), t.next())
13
+ assert(! t.next())
14
+ input = StringReader.new("David Balmain")
15
+ a = StopAnalyzer.new(["david"])
16
+ t = a.token_stream("field name", input)
17
+ assert_equal(Token.new('balmain', 6, 13), t.next())
18
+ assert(! t.next())
19
+ end
20
+ end
@@ -0,0 +1,14 @@
1
+ require File.dirname(__FILE__) + "/../../test_helper"
2
+
3
+ class StopFilterTest < Test::Unit::TestCase
4
+ include Ferret::Analysis
5
+ include Ferret::Utils::StringHelper
6
+
7
+ def test_stopfilter()
8
+ input = StringReader.new('The Quick AND the DEAD the and to it there their')
9
+ t = StopFilter.new_with_file(LowerCaseTokenizer.new(input), File.dirname(__FILE__) + '/data/wordfile')
10
+ assert_equal(Token.new('quick', 4, 9), t.next())
11
+ assert_equal(Token.new('dead', 18, 22), t.next())
12
+ assert(! t.next())
13
+ end
14
+ end
@@ -0,0 +1,21 @@
1
+ require File.dirname(__FILE__) + "/../../test_helper"
2
+
3
+ class WhiteSpaceAnalyzerTest < Test::Unit::TestCase
4
+ include Ferret::Analysis
5
+ include Ferret::Utils::StringHelper
6
+
7
+ def test_whitespaceanalyzer()
8
+ input = StringReader.new('DBalmain@gmail.com is My e-mail 52 #$ address. 23#@$')
9
+ a = WhiteSpaceAnalyzer.new()
10
+ t = a.token_stream("field", input)
11
+ assert_equal(Token.new('DBalmain@gmail.com', 0, 18), t.next())
12
+ assert_equal(Token.new('is', 19, 21), t.next())
13
+ assert_equal(Token.new('My', 22, 24), t.next())
14
+ assert_equal(Token.new('e-mail', 25, 31), t.next())
15
+ assert_equal(Token.new('52', 32, 34), t.next())
16
+ assert_equal(Token.new('#$', 37, 39), t.next())
17
+ assert_equal(Token.new('address.', 40, 48), t.next())
18
+ assert_equal(Token.new('23#@$', 49, 54), t.next())
19
+ assert(! t.next())
20
+ end
21
+ end