sdsykes-ferret 0.11.6.19
Sign up to get free protection for your applications and to get access to all the features.
- data/CHANGELOG +24 -0
- data/MIT-LICENSE +20 -0
- data/README +102 -0
- data/Rakefile +338 -0
- data/TODO +17 -0
- data/TUTORIAL +231 -0
- data/bin/ferret-browser +79 -0
- data/ext/analysis.c +1555 -0
- data/ext/analysis.h +219 -0
- data/ext/api.c +69 -0
- data/ext/api.h +27 -0
- data/ext/array.c +123 -0
- data/ext/array.h +53 -0
- data/ext/bitvector.c +540 -0
- data/ext/bitvector.h +272 -0
- data/ext/compound_io.c +383 -0
- data/ext/config.h +42 -0
- data/ext/document.c +156 -0
- data/ext/document.h +53 -0
- data/ext/except.c +120 -0
- data/ext/except.h +168 -0
- data/ext/extconf.rb +14 -0
- data/ext/ferret.c +402 -0
- data/ext/ferret.h +91 -0
- data/ext/filter.c +156 -0
- data/ext/fs_store.c +483 -0
- data/ext/global.c +418 -0
- data/ext/global.h +117 -0
- data/ext/hash.c +567 -0
- data/ext/hash.h +473 -0
- data/ext/hashset.c +170 -0
- data/ext/hashset.h +187 -0
- data/ext/header.h +58 -0
- data/ext/helper.c +62 -0
- data/ext/helper.h +13 -0
- data/ext/inc/lang.h +48 -0
- data/ext/inc/threading.h +31 -0
- data/ext/index.c +6425 -0
- data/ext/index.h +961 -0
- data/ext/lang.h +66 -0
- data/ext/libstemmer.c +92 -0
- data/ext/libstemmer.h +79 -0
- data/ext/mempool.c +87 -0
- data/ext/mempool.h +35 -0
- data/ext/modules.h +162 -0
- data/ext/multimapper.c +310 -0
- data/ext/multimapper.h +51 -0
- data/ext/posh.c +1006 -0
- data/ext/posh.h +1007 -0
- data/ext/priorityqueue.c +151 -0
- data/ext/priorityqueue.h +143 -0
- data/ext/q_boolean.c +1608 -0
- data/ext/q_const_score.c +161 -0
- data/ext/q_filtered_query.c +209 -0
- data/ext/q_fuzzy.c +268 -0
- data/ext/q_match_all.c +148 -0
- data/ext/q_multi_term.c +677 -0
- data/ext/q_parser.c +2825 -0
- data/ext/q_phrase.c +1126 -0
- data/ext/q_prefix.c +100 -0
- data/ext/q_range.c +350 -0
- data/ext/q_span.c +2402 -0
- data/ext/q_term.c +337 -0
- data/ext/q_wildcard.c +171 -0
- data/ext/r_analysis.c +2575 -0
- data/ext/r_index.c +3472 -0
- data/ext/r_qparser.c +585 -0
- data/ext/r_search.c +4105 -0
- data/ext/r_store.c +513 -0
- data/ext/r_utils.c +963 -0
- data/ext/ram_store.c +471 -0
- data/ext/search.c +1741 -0
- data/ext/search.h +885 -0
- data/ext/similarity.c +150 -0
- data/ext/similarity.h +82 -0
- data/ext/sort.c +983 -0
- data/ext/stem_ISO_8859_1_danish.c +338 -0
- data/ext/stem_ISO_8859_1_danish.h +16 -0
- data/ext/stem_ISO_8859_1_dutch.c +635 -0
- data/ext/stem_ISO_8859_1_dutch.h +16 -0
- data/ext/stem_ISO_8859_1_english.c +1156 -0
- data/ext/stem_ISO_8859_1_english.h +16 -0
- data/ext/stem_ISO_8859_1_finnish.c +792 -0
- data/ext/stem_ISO_8859_1_finnish.h +16 -0
- data/ext/stem_ISO_8859_1_french.c +1276 -0
- data/ext/stem_ISO_8859_1_french.h +16 -0
- data/ext/stem_ISO_8859_1_german.c +512 -0
- data/ext/stem_ISO_8859_1_german.h +16 -0
- data/ext/stem_ISO_8859_1_italian.c +1091 -0
- data/ext/stem_ISO_8859_1_italian.h +16 -0
- data/ext/stem_ISO_8859_1_norwegian.c +296 -0
- data/ext/stem_ISO_8859_1_norwegian.h +16 -0
- data/ext/stem_ISO_8859_1_porter.c +776 -0
- data/ext/stem_ISO_8859_1_porter.h +16 -0
- data/ext/stem_ISO_8859_1_portuguese.c +1035 -0
- data/ext/stem_ISO_8859_1_portuguese.h +16 -0
- data/ext/stem_ISO_8859_1_spanish.c +1119 -0
- data/ext/stem_ISO_8859_1_spanish.h +16 -0
- data/ext/stem_ISO_8859_1_swedish.c +307 -0
- data/ext/stem_ISO_8859_1_swedish.h +16 -0
- data/ext/stem_KOI8_R_russian.c +701 -0
- data/ext/stem_KOI8_R_russian.h +16 -0
- data/ext/stem_UTF_8_danish.c +344 -0
- data/ext/stem_UTF_8_danish.h +16 -0
- data/ext/stem_UTF_8_dutch.c +653 -0
- data/ext/stem_UTF_8_dutch.h +16 -0
- data/ext/stem_UTF_8_english.c +1176 -0
- data/ext/stem_UTF_8_english.h +16 -0
- data/ext/stem_UTF_8_finnish.c +808 -0
- data/ext/stem_UTF_8_finnish.h +16 -0
- data/ext/stem_UTF_8_french.c +1296 -0
- data/ext/stem_UTF_8_french.h +16 -0
- data/ext/stem_UTF_8_german.c +526 -0
- data/ext/stem_UTF_8_german.h +16 -0
- data/ext/stem_UTF_8_italian.c +1113 -0
- data/ext/stem_UTF_8_italian.h +16 -0
- data/ext/stem_UTF_8_norwegian.c +302 -0
- data/ext/stem_UTF_8_norwegian.h +16 -0
- data/ext/stem_UTF_8_porter.c +794 -0
- data/ext/stem_UTF_8_porter.h +16 -0
- data/ext/stem_UTF_8_portuguese.c +1055 -0
- data/ext/stem_UTF_8_portuguese.h +16 -0
- data/ext/stem_UTF_8_russian.c +709 -0
- data/ext/stem_UTF_8_russian.h +16 -0
- data/ext/stem_UTF_8_spanish.c +1137 -0
- data/ext/stem_UTF_8_spanish.h +16 -0
- data/ext/stem_UTF_8_swedish.c +313 -0
- data/ext/stem_UTF_8_swedish.h +16 -0
- data/ext/stopwords.c +401 -0
- data/ext/store.c +692 -0
- data/ext/store.h +777 -0
- data/ext/term_vectors.c +352 -0
- data/ext/threading.h +31 -0
- data/ext/utilities.c +446 -0
- data/ext/win32.h +54 -0
- data/lib/ferret.rb +29 -0
- data/lib/ferret/browser.rb +246 -0
- data/lib/ferret/browser/s/global.js +192 -0
- data/lib/ferret/browser/s/style.css +148 -0
- data/lib/ferret/browser/views/document/list.rhtml +49 -0
- data/lib/ferret/browser/views/document/show.rhtml +27 -0
- data/lib/ferret/browser/views/error/index.rhtml +7 -0
- data/lib/ferret/browser/views/help/index.rhtml +8 -0
- data/lib/ferret/browser/views/home/index.rhtml +29 -0
- data/lib/ferret/browser/views/layout.rhtml +22 -0
- data/lib/ferret/browser/views/term-vector/index.rhtml +4 -0
- data/lib/ferret/browser/views/term/index.rhtml +199 -0
- data/lib/ferret/browser/views/term/termdocs.rhtml +1 -0
- data/lib/ferret/browser/webrick.rb +14 -0
- data/lib/ferret/document.rb +130 -0
- data/lib/ferret/field_infos.rb +44 -0
- data/lib/ferret/index.rb +786 -0
- data/lib/ferret/number_tools.rb +157 -0
- data/lib/ferret_version.rb +3 -0
- data/setup.rb +1555 -0
- data/test/test_all.rb +5 -0
- data/test/test_helper.rb +24 -0
- data/test/threading/number_to_spoken.rb +132 -0
- data/test/threading/thread_safety_index_test.rb +79 -0
- data/test/threading/thread_safety_read_write_test.rb +76 -0
- data/test/threading/thread_safety_test.rb +133 -0
- data/test/unit/analysis/tc_analyzer.rb +548 -0
- data/test/unit/analysis/tc_token_stream.rb +646 -0
- data/test/unit/index/tc_index.rb +762 -0
- data/test/unit/index/tc_index_reader.rb +699 -0
- data/test/unit/index/tc_index_writer.rb +437 -0
- data/test/unit/index/th_doc.rb +315 -0
- data/test/unit/largefile/tc_largefile.rb +46 -0
- data/test/unit/query_parser/tc_query_parser.rb +238 -0
- data/test/unit/search/tc_filter.rb +135 -0
- data/test/unit/search/tc_fuzzy_query.rb +147 -0
- data/test/unit/search/tc_index_searcher.rb +61 -0
- data/test/unit/search/tc_multi_searcher.rb +128 -0
- data/test/unit/search/tc_multiple_search_requests.rb +58 -0
- data/test/unit/search/tc_search_and_sort.rb +179 -0
- data/test/unit/search/tc_sort.rb +49 -0
- data/test/unit/search/tc_sort_field.rb +27 -0
- data/test/unit/search/tc_spans.rb +190 -0
- data/test/unit/search/tm_searcher.rb +384 -0
- data/test/unit/store/tc_fs_store.rb +77 -0
- data/test/unit/store/tc_ram_store.rb +35 -0
- data/test/unit/store/tm_store.rb +34 -0
- data/test/unit/store/tm_store_lock.rb +68 -0
- data/test/unit/tc_document.rb +81 -0
- data/test/unit/ts_analysis.rb +2 -0
- data/test/unit/ts_index.rb +2 -0
- data/test/unit/ts_largefile.rb +4 -0
- data/test/unit/ts_query_parser.rb +2 -0
- data/test/unit/ts_search.rb +2 -0
- data/test/unit/ts_store.rb +2 -0
- data/test/unit/ts_utils.rb +2 -0
- data/test/unit/utils/tc_bit_vector.rb +295 -0
- data/test/unit/utils/tc_number_tools.rb +117 -0
- data/test/unit/utils/tc_priority_queue.rb +106 -0
- metadata +285 -0
@@ -0,0 +1,548 @@
|
|
1
|
+
require File.dirname(__FILE__) + "/../../test_helper"
|
2
|
+
|
3
|
+
class AnalyzerTest < Test::Unit::TestCase
|
4
|
+
include Ferret::Analysis
|
5
|
+
|
6
|
+
def test_analyzer()
|
7
|
+
input = 'DBalmain@gmail.com is My E-Mail 523@#$ ADDRESS. 23#@$'
|
8
|
+
a = Analyzer.new()
|
9
|
+
t = a.token_stream("fieldname", input)
|
10
|
+
t2 = a.token_stream("fieldname", input)
|
11
|
+
assert_equal(Token.new("dbalmain", 0, 8), t.next())
|
12
|
+
assert_equal(Token.new("gmail", 9, 14), t.next())
|
13
|
+
assert_equal(Token.new("com", 15, 18), t.next())
|
14
|
+
assert_equal(Token.new("is", 19, 21), t.next())
|
15
|
+
assert_equal(Token.new("my", 22, 24), t.next())
|
16
|
+
assert_equal(Token.new("e", 25, 26), t.next())
|
17
|
+
assert_equal(Token.new("mail", 27, 31), t.next())
|
18
|
+
assert_equal(Token.new("address", 39, 46), t.next())
|
19
|
+
assert(! t.next())
|
20
|
+
assert_equal(Token.new("dbalmain", 0, 8), t2.next())
|
21
|
+
assert_equal(Token.new("gmail", 9, 14), t2.next())
|
22
|
+
assert_equal(Token.new("com", 15, 18), t2.next())
|
23
|
+
assert_equal(Token.new("is", 19, 21), t2.next())
|
24
|
+
assert_equal(Token.new("my", 22, 24), t2.next())
|
25
|
+
assert_equal(Token.new("e", 25, 26), t2.next())
|
26
|
+
assert_equal(Token.new("mail", 27, 31), t2.next())
|
27
|
+
assert_equal(Token.new("address", 39, 46), t2.next())
|
28
|
+
assert(! t2.next())
|
29
|
+
a = Analyzer.new(false)
|
30
|
+
t = a.token_stream("fieldname", input)
|
31
|
+
assert_equal(Token.new("DBalmain", 0, 8), t.next())
|
32
|
+
assert_equal(Token.new("gmail", 9, 14), t.next())
|
33
|
+
assert_equal(Token.new("com", 15, 18), t.next())
|
34
|
+
assert_equal(Token.new("is", 19, 21), t.next())
|
35
|
+
assert_equal(Token.new("My", 22, 24), t.next())
|
36
|
+
assert_equal(Token.new("E", 25, 26), t.next())
|
37
|
+
assert_equal(Token.new("Mail", 27, 31), t.next())
|
38
|
+
assert_equal(Token.new("ADDRESS", 39, 46), t.next())
|
39
|
+
assert(! t.next())
|
40
|
+
end
|
41
|
+
end if (/utf-8/i =~ Ferret.locale)
|
42
|
+
|
43
|
+
class AsciiLetterAnalyzerTest < Test::Unit::TestCase
|
44
|
+
include Ferret::Analysis
|
45
|
+
|
46
|
+
def test_letter_analyzer()
|
47
|
+
input = 'DBalmain@gmail.com is My E-Mail 523@#$ ADDRESS. 23#@$'
|
48
|
+
a = AsciiLetterAnalyzer.new()
|
49
|
+
t = a.token_stream("fieldname", input)
|
50
|
+
t2 = a.token_stream("fieldname", input)
|
51
|
+
assert_equal(Token.new("dbalmain", 0, 8), t.next())
|
52
|
+
assert_equal(Token.new("gmail", 9, 14), t.next())
|
53
|
+
assert_equal(Token.new("com", 15, 18), t.next())
|
54
|
+
assert_equal(Token.new("is", 19, 21), t.next())
|
55
|
+
assert_equal(Token.new("my", 22, 24), t.next())
|
56
|
+
assert_equal(Token.new("e", 25, 26), t.next())
|
57
|
+
assert_equal(Token.new("mail", 27, 31), t.next())
|
58
|
+
assert_equal(Token.new("address", 39, 46), t.next())
|
59
|
+
assert(! t.next())
|
60
|
+
assert_equal(Token.new("dbalmain", 0, 8), t2.next())
|
61
|
+
assert_equal(Token.new("gmail", 9, 14), t2.next())
|
62
|
+
assert_equal(Token.new("com", 15, 18), t2.next())
|
63
|
+
assert_equal(Token.new("is", 19, 21), t2.next())
|
64
|
+
assert_equal(Token.new("my", 22, 24), t2.next())
|
65
|
+
assert_equal(Token.new("e", 25, 26), t2.next())
|
66
|
+
assert_equal(Token.new("mail", 27, 31), t2.next())
|
67
|
+
assert_equal(Token.new("address", 39, 46), t2.next())
|
68
|
+
assert(! t2.next())
|
69
|
+
a = AsciiLetterAnalyzer.new(false)
|
70
|
+
t = a.token_stream("fieldname", input)
|
71
|
+
assert_equal(Token.new("DBalmain", 0, 8), t.next())
|
72
|
+
assert_equal(Token.new("gmail", 9, 14), t.next())
|
73
|
+
assert_equal(Token.new("com", 15, 18), t.next())
|
74
|
+
assert_equal(Token.new("is", 19, 21), t.next())
|
75
|
+
assert_equal(Token.new("My", 22, 24), t.next())
|
76
|
+
assert_equal(Token.new("E", 25, 26), t.next())
|
77
|
+
assert_equal(Token.new("Mail", 27, 31), t.next())
|
78
|
+
assert_equal(Token.new("ADDRESS", 39, 46), t.next())
|
79
|
+
assert(! t.next())
|
80
|
+
end
|
81
|
+
end
|
82
|
+
|
83
|
+
class LetterAnalyzerTest < Test::Unit::TestCase
|
84
|
+
include Ferret::Analysis
|
85
|
+
|
86
|
+
def test_letter_analyzer()
|
87
|
+
Ferret.locale = ""
|
88
|
+
input = 'DBalmän@gmail.com is My e-mail 52 #$ address. 23#@$ ÁÄGÇ®ÊË̯ÚØìÖÎÍ'
|
89
|
+
a = LetterAnalyzer.new(false)
|
90
|
+
t = a.token_stream("fieldname", input)
|
91
|
+
t2 = a.token_stream("fieldname", input)
|
92
|
+
assert_equal(Token.new("DBalmän", 0, 8), t.next)
|
93
|
+
assert_equal(Token.new("gmail", 9, 14), t.next)
|
94
|
+
assert_equal(Token.new("com", 15, 18), t.next)
|
95
|
+
assert_equal(Token.new("is", 19, 21), t.next)
|
96
|
+
assert_equal(Token.new("My", 22, 24), t.next)
|
97
|
+
assert_equal(Token.new("e", 25, 26), t.next)
|
98
|
+
assert_equal(Token.new("mail", 27, 31), t.next)
|
99
|
+
assert_equal(Token.new("address", 40, 47), t.next)
|
100
|
+
assert_equal(Token.new("ÁÄGÇ", 55, 62), t.next)
|
101
|
+
assert_equal(Token.new("ÊËÌ", 64, 70), t.next)
|
102
|
+
assert_equal(Token.new("ÚØÃ", 72, 78), t.next)
|
103
|
+
assert_equal(Token.new("ÖÎÍ", 80, 86), t.next)
|
104
|
+
assert(! t.next())
|
105
|
+
assert_equal(Token.new("DBalmän", 0, 8), t2.next)
|
106
|
+
assert_equal(Token.new("gmail", 9, 14), t2.next)
|
107
|
+
assert_equal(Token.new("com", 15, 18), t2.next)
|
108
|
+
assert_equal(Token.new("is", 19, 21), t2.next)
|
109
|
+
assert_equal(Token.new("My", 22, 24), t2.next)
|
110
|
+
assert_equal(Token.new("e", 25, 26), t2.next)
|
111
|
+
assert_equal(Token.new("mail", 27, 31), t2.next)
|
112
|
+
assert_equal(Token.new("address", 40, 47), t2.next)
|
113
|
+
assert_equal(Token.new("ÁÄGÇ", 55, 62), t2.next)
|
114
|
+
assert_equal(Token.new("ÊËÌ", 64, 70), t2.next)
|
115
|
+
assert_equal(Token.new("ÚØÃ", 72, 78), t2.next)
|
116
|
+
assert_equal(Token.new("ÖÎÍ", 80, 86), t2.next)
|
117
|
+
assert(! t2.next())
|
118
|
+
a = LetterAnalyzer.new()
|
119
|
+
t = a.token_stream("fieldname", input)
|
120
|
+
assert_equal(Token.new("dbalmän", 0, 8), t.next)
|
121
|
+
assert_equal(Token.new("gmail", 9, 14), t.next)
|
122
|
+
assert_equal(Token.new("com", 15, 18), t.next)
|
123
|
+
assert_equal(Token.new("is", 19, 21), t.next)
|
124
|
+
assert_equal(Token.new("my", 22, 24), t.next)
|
125
|
+
assert_equal(Token.new("e", 25, 26), t.next)
|
126
|
+
assert_equal(Token.new("mail", 27, 31), t.next)
|
127
|
+
assert_equal(Token.new("address", 40, 47), t.next)
|
128
|
+
assert_equal(Token.new("áägç", 55, 62), t.next)
|
129
|
+
assert_equal(Token.new("êëì", 64, 70), t.next)
|
130
|
+
assert_equal(Token.new("úøã", 72, 78), t.next)
|
131
|
+
assert_equal(Token.new("öîí", 80, 86), t.next)
|
132
|
+
assert(! t.next())
|
133
|
+
end
|
134
|
+
end if (/utf-8/i =~ Ferret.locale)
|
135
|
+
|
136
|
+
class AsciiWhiteSpaceAnalyzerTest < Test::Unit::TestCase
|
137
|
+
include Ferret::Analysis
|
138
|
+
|
139
|
+
def test_white_space_analyzer()
|
140
|
+
input = 'DBalmain@gmail.com is My E-Mail 52 #$ ADDRESS. 23#@$'
|
141
|
+
a = AsciiWhiteSpaceAnalyzer.new()
|
142
|
+
t = a.token_stream("fieldname", input)
|
143
|
+
t2 = a.token_stream("fieldname", input)
|
144
|
+
assert_equal(Token.new('DBalmain@gmail.com', 0, 18), t.next)
|
145
|
+
assert_equal(Token.new('is', 19, 21), t.next)
|
146
|
+
assert_equal(Token.new('My', 22, 24), t.next)
|
147
|
+
assert_equal(Token.new('E-Mail', 25, 31), t.next)
|
148
|
+
assert_equal(Token.new('52', 32, 34), t.next)
|
149
|
+
assert_equal(Token.new('#$', 37, 39), t.next)
|
150
|
+
assert_equal(Token.new('ADDRESS.', 40, 48), t.next)
|
151
|
+
assert_equal(Token.new('23#@$', 49, 54), t.next)
|
152
|
+
assert(! t.next())
|
153
|
+
assert_equal(Token.new('DBalmain@gmail.com', 0, 18), t2.next)
|
154
|
+
assert_equal(Token.new('is', 19, 21), t2.next)
|
155
|
+
assert_equal(Token.new('My', 22, 24), t2.next)
|
156
|
+
assert_equal(Token.new('E-Mail', 25, 31), t2.next)
|
157
|
+
assert_equal(Token.new('52', 32, 34), t2.next)
|
158
|
+
assert_equal(Token.new('#$', 37, 39), t2.next)
|
159
|
+
assert_equal(Token.new('ADDRESS.', 40, 48), t2.next)
|
160
|
+
assert_equal(Token.new('23#@$', 49, 54), t2.next)
|
161
|
+
assert(! t2.next())
|
162
|
+
a = AsciiWhiteSpaceAnalyzer.new(true)
|
163
|
+
t = a.token_stream("fieldname", input)
|
164
|
+
assert_equal(Token.new('dbalmain@gmail.com', 0, 18), t.next)
|
165
|
+
assert_equal(Token.new('is', 19, 21), t.next)
|
166
|
+
assert_equal(Token.new('my', 22, 24), t.next)
|
167
|
+
assert_equal(Token.new('e-mail', 25, 31), t.next)
|
168
|
+
assert_equal(Token.new('52', 32, 34), t.next)
|
169
|
+
assert_equal(Token.new('#$', 37, 39), t.next)
|
170
|
+
assert_equal(Token.new('address.', 40, 48), t.next)
|
171
|
+
assert_equal(Token.new('23#@$', 49, 54), t.next)
|
172
|
+
assert(! t.next())
|
173
|
+
end
|
174
|
+
end
|
175
|
+
|
176
|
+
class WhiteSpaceAnalyzerTest < Test::Unit::TestCase
|
177
|
+
include Ferret::Analysis
|
178
|
+
|
179
|
+
def test_white_space_analyzer()
|
180
|
+
input = 'DBalmän@gmail.com is My e-mail 52 #$ address. 23#@$ ÁÄGÇ®ÊË̯ÚØìÖÎÍ'
|
181
|
+
a = WhiteSpaceAnalyzer.new()
|
182
|
+
t = a.token_stream("fieldname", input)
|
183
|
+
t2 = a.token_stream("fieldname", input)
|
184
|
+
assert_equal(Token.new('DBalmän@gmail.com', 0, 18), t.next)
|
185
|
+
assert_equal(Token.new('is', 19, 21), t.next)
|
186
|
+
assert_equal(Token.new('My', 22, 24), t.next)
|
187
|
+
assert_equal(Token.new('e-mail', 25, 31), t.next)
|
188
|
+
assert_equal(Token.new('52', 32, 34), t.next)
|
189
|
+
assert_equal(Token.new('#$', 37, 39), t.next)
|
190
|
+
assert_equal(Token.new('address.', 40, 48), t.next)
|
191
|
+
assert_equal(Token.new('23#@$', 49, 54), t.next)
|
192
|
+
assert_equal(Token.new('ÁÄGÇ®ÊË̯ÚØìÖÎÍ', 55, 86), t.next)
|
193
|
+
assert(! t.next())
|
194
|
+
assert_equal(Token.new('DBalmän@gmail.com', 0, 18), t2.next)
|
195
|
+
assert_equal(Token.new('is', 19, 21), t2.next)
|
196
|
+
assert_equal(Token.new('My', 22, 24), t2.next)
|
197
|
+
assert_equal(Token.new('e-mail', 25, 31), t2.next)
|
198
|
+
assert_equal(Token.new('52', 32, 34), t2.next)
|
199
|
+
assert_equal(Token.new('#$', 37, 39), t2.next)
|
200
|
+
assert_equal(Token.new('address.', 40, 48), t2.next)
|
201
|
+
assert_equal(Token.new('23#@$', 49, 54), t2.next)
|
202
|
+
assert_equal(Token.new('ÁÄGÇ®ÊË̯ÚØìÖÎÍ', 55, 86), t2.next)
|
203
|
+
assert(! t2.next())
|
204
|
+
a = WhiteSpaceAnalyzer.new(true)
|
205
|
+
t = a.token_stream("fieldname", input)
|
206
|
+
assert_equal(Token.new('dbalmän@gmail.com', 0, 18), t.next)
|
207
|
+
assert_equal(Token.new('is', 19, 21), t.next)
|
208
|
+
assert_equal(Token.new('my', 22, 24), t.next)
|
209
|
+
assert_equal(Token.new('e-mail', 25, 31), t.next)
|
210
|
+
assert_equal(Token.new('52', 32, 34), t.next)
|
211
|
+
assert_equal(Token.new('#$', 37, 39), t.next)
|
212
|
+
assert_equal(Token.new('address.', 40, 48), t.next)
|
213
|
+
assert_equal(Token.new('23#@$', 49, 54), t.next)
|
214
|
+
assert_equal(Token.new('áägç®êëì¯úøã¬öîí', 55, 86), t.next)
|
215
|
+
assert(! t.next())
|
216
|
+
end
|
217
|
+
end if (/utf-8/i =~ Ferret.locale)
|
218
|
+
|
219
|
+
class AsciiStandardAnalyzerTest < Test::Unit::TestCase
|
220
|
+
include Ferret::Analysis
|
221
|
+
|
222
|
+
def test_standard_analyzer()
|
223
|
+
input = 'DBalmain@gmail.com is My e-mail 52 #$ Address. 23#@$ http://www.google.com/results/ T.N.T. 123-1235-ASD-1234'
|
224
|
+
a = AsciiStandardAnalyzer.new()
|
225
|
+
t = a.token_stream("fieldname", input)
|
226
|
+
t2 = a.token_stream("fieldname", input)
|
227
|
+
assert_equal(Token.new('dbalmain@gmail.com', 0, 18), t.next)
|
228
|
+
assert_equal(Token.new('email', 25, 31, 3), t.next)
|
229
|
+
assert_equal(Token.new('e', 25, 26, 0), t.next)
|
230
|
+
assert_equal(Token.new('mail', 27, 31), t.next)
|
231
|
+
assert_equal(Token.new('52', 32, 34), t.next)
|
232
|
+
assert_equal(Token.new('address', 40, 47), t.next)
|
233
|
+
assert_equal(Token.new('23', 49, 51), t.next)
|
234
|
+
assert_equal(Token.new('www.google.com/results', 55, 84), t.next)
|
235
|
+
assert_equal(Token.new('tnt', 86, 91), t.next)
|
236
|
+
assert_equal(Token.new('123-1235-asd-1234', 93, 110), t.next)
|
237
|
+
assert(! t.next())
|
238
|
+
assert_equal(Token.new('dbalmain@gmail.com', 0, 18), t2.next)
|
239
|
+
assert_equal(Token.new('email', 25, 31, 3), t2.next)
|
240
|
+
assert_equal(Token.new('e', 25, 26, 0), t2.next)
|
241
|
+
assert_equal(Token.new('mail', 27, 31), t2.next)
|
242
|
+
assert_equal(Token.new('52', 32, 34), t2.next)
|
243
|
+
assert_equal(Token.new('address', 40, 47), t2.next)
|
244
|
+
assert_equal(Token.new('23', 49, 51), t2.next)
|
245
|
+
assert_equal(Token.new('www.google.com/results', 55, 84), t2.next)
|
246
|
+
assert_equal(Token.new('tnt', 86, 91), t2.next)
|
247
|
+
assert_equal(Token.new('123-1235-asd-1234', 93, 110), t2.next)
|
248
|
+
assert(! t2.next())
|
249
|
+
a = AsciiStandardAnalyzer.new(ENGLISH_STOP_WORDS, false)
|
250
|
+
t = a.token_stream("fieldname", input)
|
251
|
+
t2 = a.token_stream("fieldname", input)
|
252
|
+
assert_equal(Token.new('DBalmain@gmail.com', 0, 18), t.next)
|
253
|
+
assert_equal(Token.new('My', 22, 24), t.next)
|
254
|
+
assert_equal(Token.new('email', 25, 31, 3), t.next)
|
255
|
+
assert_equal(Token.new('e', 25, 26, 0), t.next)
|
256
|
+
assert_equal(Token.new('mail', 27, 31), t.next)
|
257
|
+
assert_equal(Token.new('52', 32, 34), t.next)
|
258
|
+
assert_equal(Token.new('Address', 40, 47), t.next)
|
259
|
+
assert_equal(Token.new('23', 49, 51), t.next)
|
260
|
+
assert_equal(Token.new('www.google.com/results', 55, 84), t.next)
|
261
|
+
assert_equal(Token.new('TNT', 86, 91), t.next)
|
262
|
+
assert_equal(Token.new('123-1235-ASD-1234', 93, 110), t.next)
|
263
|
+
assert(! t.next())
|
264
|
+
end
|
265
|
+
end
|
266
|
+
|
267
|
+
class StandardAnalyzerTest < Test::Unit::TestCase
|
268
|
+
include Ferret::Analysis
|
269
|
+
|
270
|
+
def test_standard_analyzer()
|
271
|
+
input = 'DBalmán@gmail.com is My e-mail and the Address. 23#@$ http://www.google.com/results/ T.N.T. 123-1235-ASD-1234 23#@$ ÁÄGÇ®ÊË̯ÚØìÖÎÍ'
|
272
|
+
a = StandardAnalyzer.new()
|
273
|
+
t = a.token_stream("fieldname", input)
|
274
|
+
t2 = a.token_stream("fieldname", input)
|
275
|
+
assert_equal(Token.new('dbalmán@gmail.com', 0, 18), t.next)
|
276
|
+
assert_equal(Token.new('email', 25, 31, 3), t.next)
|
277
|
+
assert_equal(Token.new('e', 25, 26, 0), t.next)
|
278
|
+
assert_equal(Token.new('mail', 27, 31), t.next)
|
279
|
+
assert_equal(Token.new('address', 40, 47), t.next)
|
280
|
+
assert_equal(Token.new('23', 49, 51), t.next)
|
281
|
+
assert_equal(Token.new('www.google.com/results', 55, 84), t.next)
|
282
|
+
assert_equal(Token.new('tnt', 86, 91), t.next)
|
283
|
+
assert_equal(Token.new('123-1235-asd-1234', 93, 110), t.next)
|
284
|
+
assert_equal(Token.new('23', 111, 113), t.next)
|
285
|
+
assert_equal(Token.new('áägç', 117, 124), t.next)
|
286
|
+
assert_equal(Token.new('êëì', 126, 132), t.next)
|
287
|
+
assert_equal(Token.new('úøã', 134, 140), t.next)
|
288
|
+
assert_equal(Token.new('öîí', 142, 148), t.next)
|
289
|
+
assert(! t.next())
|
290
|
+
assert_equal(Token.new('dbalmán@gmail.com', 0, 18), t2.next)
|
291
|
+
assert_equal(Token.new('email', 25, 31, 3), t2.next)
|
292
|
+
assert_equal(Token.new('e', 25, 26, 0), t2.next)
|
293
|
+
assert_equal(Token.new('mail', 27, 31), t2.next)
|
294
|
+
assert_equal(Token.new('address', 40, 47), t2.next)
|
295
|
+
assert_equal(Token.new('23', 49, 51), t2.next)
|
296
|
+
assert_equal(Token.new('www.google.com/results', 55, 84), t2.next)
|
297
|
+
assert_equal(Token.new('tnt', 86, 91), t2.next)
|
298
|
+
assert_equal(Token.new('123-1235-asd-1234', 93, 110), t2.next)
|
299
|
+
assert_equal(Token.new('23', 111, 113), t2.next)
|
300
|
+
assert_equal(Token.new('áägç', 117, 124), t2.next)
|
301
|
+
assert_equal(Token.new('êëì', 126, 132), t2.next)
|
302
|
+
assert_equal(Token.new('úøã', 134, 140), t2.next)
|
303
|
+
assert_equal(Token.new('öîí', 142, 148), t2.next)
|
304
|
+
assert(! t2.next())
|
305
|
+
a = StandardAnalyzer.new(nil, false)
|
306
|
+
t = a.token_stream("fieldname", input)
|
307
|
+
assert_equal(Token.new('DBalmán@gmail.com', 0, 18), t.next)
|
308
|
+
assert_equal(Token.new('My', 22, 24), t.next)
|
309
|
+
assert_equal(Token.new('email', 25, 31, 3), t.next)
|
310
|
+
assert_equal(Token.new('e', 25, 26, 0), t.next)
|
311
|
+
assert_equal(Token.new('mail', 27, 31), t.next)
|
312
|
+
assert_equal(Token.new('Address', 40, 47), t.next)
|
313
|
+
assert_equal(Token.new('23', 49, 51), t.next)
|
314
|
+
assert_equal(Token.new('www.google.com/results', 55, 84), t.next)
|
315
|
+
assert_equal(Token.new('TNT', 86, 91), t.next)
|
316
|
+
assert_equal(Token.new('123-1235-ASD-1234', 93, 110), t.next)
|
317
|
+
assert_equal(Token.new('23', 111, 113), t.next)
|
318
|
+
assert_equal(Token.new('ÁÄGÇ', 117, 124), t.next)
|
319
|
+
assert_equal(Token.new('ÊËÌ', 126, 132), t.next)
|
320
|
+
assert_equal(Token.new('ÚØÃ', 134, 140), t.next)
|
321
|
+
assert_equal(Token.new('ÖÎÍ', 142, 148), t.next)
|
322
|
+
assert(! t.next())
|
323
|
+
a = StandardAnalyzer.new(["e-mail", "23", "tnt"])
|
324
|
+
t = a.token_stream("fieldname", input)
|
325
|
+
t2 = a.token_stream("fieldname", input)
|
326
|
+
assert_equal(Token.new('dbalmán@gmail.com', 0, 18), t.next)
|
327
|
+
assert_equal(Token.new('is', 19, 21), t.next)
|
328
|
+
assert_equal(Token.new('my', 22, 24), t.next)
|
329
|
+
assert_equal(Token.new('and', 32, 35), t.next)
|
330
|
+
assert_equal(Token.new('the', 36, 39), t.next)
|
331
|
+
assert_equal(Token.new('address', 40, 47), t.next)
|
332
|
+
assert_equal(Token.new('www.google.com/results', 55, 84), t.next)
|
333
|
+
assert_equal(Token.new('123-1235-asd-1234', 93, 110), t.next)
|
334
|
+
assert_equal(Token.new('áägç', 117, 124), t.next)
|
335
|
+
assert_equal(Token.new('êëì', 126, 132), t.next)
|
336
|
+
assert_equal(Token.new('úøã', 134, 140), t.next)
|
337
|
+
assert_equal(Token.new('öîí', 142, 148), t.next)
|
338
|
+
assert(! t.next())
|
339
|
+
assert_equal(Token.new('dbalmán@gmail.com', 0, 18), t2.next)
|
340
|
+
assert_equal(Token.new('is', 19, 21), t2.next)
|
341
|
+
assert_equal(Token.new('my', 22, 24), t2.next)
|
342
|
+
assert_equal(Token.new('and', 32, 35), t2.next)
|
343
|
+
assert_equal(Token.new('the', 36, 39), t2.next)
|
344
|
+
assert_equal(Token.new('address', 40, 47), t2.next)
|
345
|
+
assert_equal(Token.new('www.google.com/results', 55, 84), t2.next)
|
346
|
+
assert_equal(Token.new('123-1235-asd-1234', 93, 110), t2.next)
|
347
|
+
assert_equal(Token.new('áägç', 117, 124), t2.next)
|
348
|
+
assert_equal(Token.new('êëì', 126, 132), t2.next)
|
349
|
+
assert_equal(Token.new('úøã', 134, 140), t2.next)
|
350
|
+
assert_equal(Token.new('öîí', 142, 148), t2.next)
|
351
|
+
assert(! t2.next())
|
352
|
+
end
|
353
|
+
end if (/utf-8/i =~ Ferret.locale)
|
354
|
+
|
355
|
+
class PerFieldAnalyzerTest < Test::Unit::TestCase
|
356
|
+
include Ferret::Analysis
|
357
|
+
def test_per_field_analyzer()
|
358
|
+
input = 'DBalmain@gmail.com is My e-mail 52 #$ address. 23#@$'
|
359
|
+
pfa = PerFieldAnalyzer.new(StandardAnalyzer.new())
|
360
|
+
pfa['white'] = WhiteSpaceAnalyzer.new(false)
|
361
|
+
pfa['white_l'] = WhiteSpaceAnalyzer.new(true)
|
362
|
+
pfa['letter'] = LetterAnalyzer.new(false)
|
363
|
+
pfa.add_field('letter', LetterAnalyzer.new(true))
|
364
|
+
pfa.add_field('letter_u', LetterAnalyzer.new(false))
|
365
|
+
t = pfa.token_stream('white', input)
|
366
|
+
assert_equal(Token.new('DBalmain@gmail.com', 0, 18), t.next)
|
367
|
+
assert_equal(Token.new('is', 19, 21), t.next)
|
368
|
+
assert_equal(Token.new('My', 22, 24), t.next)
|
369
|
+
assert_equal(Token.new('e-mail', 25, 31), t.next)
|
370
|
+
assert_equal(Token.new('52', 32, 34), t.next)
|
371
|
+
assert_equal(Token.new('#$', 37, 39), t.next)
|
372
|
+
assert_equal(Token.new('address.', 40, 48), t.next)
|
373
|
+
assert_equal(Token.new('23#@$', 49, 54), t.next)
|
374
|
+
assert(! t.next())
|
375
|
+
t = pfa.token_stream('white_l', input)
|
376
|
+
assert_equal(Token.new('dbalmain@gmail.com', 0, 18), t.next)
|
377
|
+
assert_equal(Token.new('is', 19, 21), t.next)
|
378
|
+
assert_equal(Token.new('my', 22, 24), t.next)
|
379
|
+
assert_equal(Token.new('e-mail', 25, 31), t.next)
|
380
|
+
assert_equal(Token.new('52', 32, 34), t.next)
|
381
|
+
assert_equal(Token.new('#$', 37, 39), t.next)
|
382
|
+
assert_equal(Token.new('address.', 40, 48), t.next)
|
383
|
+
assert_equal(Token.new('23#@$', 49, 54), t.next)
|
384
|
+
assert(! t.next())
|
385
|
+
t = pfa.token_stream('letter_u', input)
|
386
|
+
assert_equal(Token.new('DBalmain', 0, 8), t.next)
|
387
|
+
assert_equal(Token.new('gmail', 9, 14), t.next)
|
388
|
+
assert_equal(Token.new('com', 15, 18), t.next)
|
389
|
+
assert_equal(Token.new('is', 19, 21), t.next)
|
390
|
+
assert_equal(Token.new('My', 22, 24), t.next)
|
391
|
+
assert_equal(Token.new('e', 25, 26), t.next)
|
392
|
+
assert_equal(Token.new('mail', 27, 31), t.next)
|
393
|
+
assert_equal(Token.new('address', 40, 47), t.next)
|
394
|
+
assert(! t.next())
|
395
|
+
t = pfa.token_stream('letter', input)
|
396
|
+
assert_equal(Token.new('dbalmain', 0, 8), t.next)
|
397
|
+
assert_equal(Token.new('gmail', 9, 14), t.next)
|
398
|
+
assert_equal(Token.new('com', 15, 18), t.next)
|
399
|
+
assert_equal(Token.new('is', 19, 21), t.next)
|
400
|
+
assert_equal(Token.new('my', 22, 24), t.next)
|
401
|
+
assert_equal(Token.new('e', 25, 26), t.next)
|
402
|
+
assert_equal(Token.new('mail', 27, 31), t.next)
|
403
|
+
assert_equal(Token.new('address', 40, 47), t.next)
|
404
|
+
assert(! t.next())
|
405
|
+
t = pfa.token_stream('XXX', input) # should use default StandardAnalzyer
|
406
|
+
assert_equal(Token.new('dbalmain@gmail.com', 0, 18), t.next)
|
407
|
+
assert_equal(Token.new('email', 25, 31, 3), t.next)
|
408
|
+
assert_equal(Token.new('e', 25, 26, 0), t.next)
|
409
|
+
assert_equal(Token.new('mail', 27, 31), t.next)
|
410
|
+
assert_equal(Token.new('52', 32, 34), t.next)
|
411
|
+
assert_equal(Token.new('address', 40, 47), t.next)
|
412
|
+
assert_equal(Token.new('23', 49, 51), t.next)
|
413
|
+
assert(! t.next())
|
414
|
+
end
|
415
|
+
end
|
416
|
+
|
417
|
+
class RegExpAnalyzerTest < Test::Unit::TestCase
|
418
|
+
include Ferret::Analysis
|
419
|
+
|
420
|
+
def test_reg_exp_analyzer()
|
421
|
+
input = 'DBalmain@gmail.com is My e-mail 52 #$ Address. 23#@$ http://www.google.com/RESULT_3.html T.N.T. 123-1235-ASD-1234 23 Rob\'s'
|
422
|
+
a = RegExpAnalyzer.new()
|
423
|
+
t = a.token_stream('XXX', input)
|
424
|
+
t2 = a.token_stream('XXX', "one_Two three")
|
425
|
+
assert_equal(Token.new('dbalmain@gmail.com', 0, 18), t.next)
|
426
|
+
assert_equal(Token.new('is', 19, 21), t.next)
|
427
|
+
assert_equal(Token.new('my', 22, 24), t.next)
|
428
|
+
assert_equal(Token.new('e-mail', 25, 31), t.next)
|
429
|
+
assert_equal(Token.new('52', 32, 34), t.next)
|
430
|
+
assert_equal(Token.new('address', 40, 47), t.next)
|
431
|
+
assert_equal(Token.new('23', 49, 51), t.next)
|
432
|
+
assert_equal(Token.new('http://www.google.com/result_3.html', 55, 90), t.next)
|
433
|
+
assert_equal(Token.new('t.n.t.', 91, 97), t.next)
|
434
|
+
assert_equal(Token.new('123-1235-asd-1234', 98, 115), t.next)
|
435
|
+
assert_equal(Token.new('23', 116, 118), t.next)
|
436
|
+
assert_equal(Token.new('rob\'s', 119, 124), t.next)
|
437
|
+
assert(! t.next())
|
438
|
+
t = t2
|
439
|
+
assert_equal(Token.new("one_two", 0, 7), t.next())
|
440
|
+
assert_equal(Token.new("three", 8, 13), t.next())
|
441
|
+
assert(! t.next())
|
442
|
+
a = RegExpAnalyzer.new(/\w{2,}/, false)
|
443
|
+
t = a.token_stream('XXX', input)
|
444
|
+
t2 = a.token_stream('XXX', "one Two three")
|
445
|
+
assert_equal(Token.new('DBalmain', 0, 8), t.next)
|
446
|
+
assert_equal(Token.new('gmail', 9, 14), t.next)
|
447
|
+
assert_equal(Token.new('com', 15, 18), t.next)
|
448
|
+
assert_equal(Token.new('is', 19, 21), t.next)
|
449
|
+
assert_equal(Token.new('My', 22, 24), t.next)
|
450
|
+
assert_equal(Token.new('mail', 27, 31), t.next)
|
451
|
+
assert_equal(Token.new('52', 32, 34), t.next)
|
452
|
+
assert_equal(Token.new('Address', 40, 47), t.next)
|
453
|
+
assert_equal(Token.new('23', 49, 51), t.next)
|
454
|
+
assert_equal(Token.new('http', 55, 59), t.next)
|
455
|
+
assert_equal(Token.new('www', 62, 65), t.next)
|
456
|
+
assert_equal(Token.new('google', 66, 72), t.next)
|
457
|
+
assert_equal(Token.new('com', 73, 76), t.next)
|
458
|
+
assert_equal(Token.new('RESULT_3', 77, 85), t.next)
|
459
|
+
assert_equal(Token.new('html', 86, 90), t.next)
|
460
|
+
assert_equal(Token.new('123', 98, 101), t.next)
|
461
|
+
assert_equal(Token.new('1235', 102, 106), t.next)
|
462
|
+
assert_equal(Token.new('ASD', 107, 110), t.next)
|
463
|
+
assert_equal(Token.new('1234', 111, 115), t.next)
|
464
|
+
assert_equal(Token.new('23', 116, 118), t.next)
|
465
|
+
assert_equal(Token.new('Rob', 119, 122), t.next)
|
466
|
+
assert(! t.next())
|
467
|
+
assert_equal(Token.new("one", 0, 3), t2.next())
|
468
|
+
assert_equal(Token.new("Two", 4, 7), t2.next())
|
469
|
+
assert_equal(Token.new("three", 8, 13), t2.next())
|
470
|
+
assert(! t2.next())
|
471
|
+
a = RegExpAnalyzer.new() do |str|
|
472
|
+
if str =~ /^[[:alpha:]]\.([[:alpha:]]\.)+$/
|
473
|
+
str.gsub!(/\./, '')
|
474
|
+
elsif str =~ /'[sS]$/
|
475
|
+
str.gsub!(/'[sS]$/, '')
|
476
|
+
end
|
477
|
+
str
|
478
|
+
end
|
479
|
+
t = a.token_stream('XXX', input)
|
480
|
+
t2 = a.token_stream('XXX', "one's don't T.N.T.")
|
481
|
+
assert_equal(Token.new('dbalmain@gmail.com', 0, 18), t.next)
|
482
|
+
assert_equal(Token.new('is', 19, 21), t.next)
|
483
|
+
assert_equal(Token.new('my', 22, 24), t.next)
|
484
|
+
assert_equal(Token.new('e-mail', 25, 31), t.next)
|
485
|
+
assert_equal(Token.new('52', 32, 34), t.next)
|
486
|
+
assert_equal(Token.new('address', 40, 47), t.next)
|
487
|
+
assert_equal(Token.new('23', 49, 51), t.next)
|
488
|
+
assert_equal(Token.new('http://www.google.com/result_3.html', 55, 90), t.next)
|
489
|
+
assert_equal(Token.new('tnt', 91, 97), t.next)
|
490
|
+
assert_equal(Token.new('123-1235-asd-1234', 98, 115), t.next)
|
491
|
+
assert_equal(Token.new('23', 116, 118), t.next)
|
492
|
+
assert_equal(Token.new('rob', 119, 124), t.next)
|
493
|
+
assert(! t.next())
|
494
|
+
assert_equal(Token.new("one", 0, 5), t2.next())
|
495
|
+
assert_equal(Token.new("don't", 6, 11), t2.next())
|
496
|
+
assert_equal(Token.new("tnt", 12, 18), t2.next())
|
497
|
+
assert(! t2.next())
|
498
|
+
end
|
499
|
+
end
|
500
|
+
|
501
|
+
module Ferret::Analysis
|
502
|
+
class StemmingStandardAnalyzer < StandardAnalyzer
|
503
|
+
def token_stream(field, text)
|
504
|
+
StemFilter.new(super)
|
505
|
+
end
|
506
|
+
end
|
507
|
+
end
|
508
|
+
|
509
|
+
class CustomAnalyzerTest < Test::Unit::TestCase
|
510
|
+
include Ferret::Analysis
|
511
|
+
|
512
|
+
def test_custom_filter()
|
513
|
+
input = 'DBalmán@gmail.com is My e-mail and the Address. 23#@$ http://www.google.com/results/ T.N.T. 123-1235-ASD-1234 23#@$ ÁÄGÇ®ÊË̯ÚØìÖÎÍ'
|
514
|
+
a = StemmingStandardAnalyzer.new()
|
515
|
+
t = a.token_stream("fieldname", input)
|
516
|
+
assert_equal(Token.new('dbalmán@gmail.com', 0, 18), t.next)
|
517
|
+
assert_equal(Token.new('email', 25, 31, 3), t.next)
|
518
|
+
assert_equal(Token.new('e', 25, 26, 0), t.next)
|
519
|
+
assert_equal(Token.new('mail', 27, 31), t.next)
|
520
|
+
assert_equal(Token.new('address', 40, 47), t.next)
|
521
|
+
assert_equal(Token.new('23', 49, 51), t.next)
|
522
|
+
assert_equal(Token.new('www.google.com/result', 55, 84), t.next)
|
523
|
+
assert_equal(Token.new('tnt', 86, 91), t.next)
|
524
|
+
assert_equal(Token.new('123-1235-asd-1234', 93, 110), t.next)
|
525
|
+
assert_equal(Token.new('23', 111, 113), t.next)
|
526
|
+
assert_equal(Token.new('áägç', 117, 124), t.next)
|
527
|
+
assert_equal(Token.new('êëì', 126, 132), t.next)
|
528
|
+
assert_equal(Token.new('úøã', 134, 140), t.next)
|
529
|
+
assert_equal(Token.new('öîí', 142, 148), t.next)
|
530
|
+
assert(! t.next())
|
531
|
+
input = "Debate Debates DEBATED DEBating Debater";
|
532
|
+
t = a.token_stream("fieldname", input)
|
533
|
+
assert_equal(Token.new("debat", 0, 6), t.next)
|
534
|
+
assert_equal(Token.new("debat", 7, 14), t.next)
|
535
|
+
assert_equal(Token.new("debat", 15, 22), t.next)
|
536
|
+
assert_equal(Token.new("debat", 23, 31), t.next)
|
537
|
+
assert_equal(Token.new("debat", 32, 39), t.next)
|
538
|
+
assert(! t.next())
|
539
|
+
input = "Dêbate dêbates DÊBATED DÊBATing dêbater";
|
540
|
+
t = StemFilter.new(LowerCaseFilter.new(LetterTokenizer.new(input)), :english)
|
541
|
+
assert_equal(Token.new("dêbate", 0, 7), t.next)
|
542
|
+
assert_equal(Token.new("dêbate", 8, 16), t.next)
|
543
|
+
assert_equal(Token.new("dêbate", 17, 25), t.next)
|
544
|
+
assert_equal(Token.new("dêbate", 26, 35), t.next)
|
545
|
+
assert_equal(Token.new("dêbater", 36, 44), t.next)
|
546
|
+
assert(! t.next())
|
547
|
+
end
|
548
|
+
end if (/utf-8/i =~ Ferret.locale)
|