ferret 0.9.0 → 0.9.1
Sign up to get free protection for your applications and to get access to all the features.
- data/Rakefile +23 -5
- data/TODO +2 -1
- data/ext/analysis.c +838 -177
- data/ext/analysis.h +55 -7
- data/ext/api.c +69 -0
- data/ext/api.h +27 -0
- data/ext/array.c +8 -5
- data/ext/compound_io.c +132 -96
- data/ext/document.c +58 -28
- data/ext/except.c +59 -0
- data/ext/except.h +88 -0
- data/ext/ferret.c +47 -3
- data/ext/ferret.h +3 -0
- data/ext/field.c +15 -9
- data/ext/filter.c +1 -1
- data/ext/fs_store.c +215 -34
- data/ext/global.c +72 -3
- data/ext/global.h +4 -3
- data/ext/hash.c +44 -3
- data/ext/hash.h +9 -0
- data/ext/header.h +58 -0
- data/ext/inc/except.h +88 -0
- data/ext/inc/lang.h +23 -13
- data/ext/ind.c +16 -10
- data/ext/index.h +2 -22
- data/ext/index_io.c +3 -11
- data/ext/index_rw.c +245 -193
- data/ext/lang.h +23 -13
- data/ext/libstemmer.c +92 -0
- data/ext/libstemmer.h +79 -0
- data/ext/modules.h +162 -0
- data/ext/q_boolean.c +34 -21
- data/ext/q_const_score.c +6 -12
- data/ext/q_filtered_query.c +206 -0
- data/ext/q_fuzzy.c +18 -15
- data/ext/q_match_all.c +3 -7
- data/ext/q_multi_phrase.c +10 -14
- data/ext/q_parser.c +29 -2
- data/ext/q_phrase.c +14 -21
- data/ext/q_prefix.c +15 -12
- data/ext/q_range.c +30 -28
- data/ext/q_span.c +13 -21
- data/ext/q_term.c +17 -26
- data/ext/r_analysis.c +693 -21
- data/ext/r_doc.c +11 -12
- data/ext/r_index_io.c +4 -1
- data/ext/r_qparser.c +21 -2
- data/ext/r_search.c +285 -18
- data/ext/ram_store.c +5 -2
- data/ext/search.c +11 -17
- data/ext/search.h +21 -45
- data/ext/similarity.h +67 -0
- data/ext/sort.c +30 -25
- 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 +325 -0
- data/ext/store.c +34 -2
- data/ext/tags +2953 -0
- data/ext/term.c +21 -15
- data/ext/termdocs.c +5 -3
- data/ext/utilities.c +446 -0
- data/ext/vector.c +27 -13
- data/lib/ferret/document/document.rb +1 -1
- data/lib/ferret/index/index.rb +44 -6
- data/lib/ferret/query_parser/query_parser.tab.rb +7 -3
- data/lib/rferret.rb +2 -1
- data/test/test_helper.rb +2 -2
- data/test/unit/analysis/ctc_analyzer.rb +401 -0
- data/test/unit/analysis/ctc_tokenstream.rb +423 -0
- data/test/unit/analysis/{tc_letter_tokenizer.rb → rtc_letter_tokenizer.rb} +0 -0
- data/test/unit/analysis/{tc_lower_case_filter.rb → rtc_lower_case_filter.rb} +0 -0
- data/test/unit/analysis/{tc_lower_case_tokenizer.rb → rtc_lower_case_tokenizer.rb} +0 -0
- data/test/unit/analysis/{tc_per_field_analyzer_wrapper.rb → rtc_per_field_analyzer_wrapper.rb} +0 -0
- data/test/unit/analysis/{tc_porter_stem_filter.rb → rtc_porter_stem_filter.rb} +0 -0
- data/test/unit/analysis/{tc_standard_analyzer.rb → rtc_standard_analyzer.rb} +0 -0
- data/test/unit/analysis/{tc_standard_tokenizer.rb → rtc_standard_tokenizer.rb} +0 -0
- data/test/unit/analysis/{tc_stop_analyzer.rb → rtc_stop_analyzer.rb} +0 -0
- data/test/unit/analysis/{tc_stop_filter.rb → rtc_stop_filter.rb} +0 -0
- data/test/unit/analysis/{tc_white_space_analyzer.rb → rtc_white_space_analyzer.rb} +0 -0
- data/test/unit/analysis/{tc_white_space_tokenizer.rb → rtc_white_space_tokenizer.rb} +0 -0
- data/test/unit/analysis/{tc_word_list_loader.rb → rtc_word_list_loader.rb} +0 -0
- data/test/unit/analysis/tc_analyzer.rb +1 -2
- data/test/unit/analysis/{c_token.rb → tc_token.rb} +0 -0
- data/test/unit/document/rtc_field.rb +28 -0
- data/test/unit/document/{c_document.rb → tc_document.rb} +0 -0
- data/test/unit/document/tc_field.rb +82 -12
- data/test/unit/index/{tc_compound_file_io.rb → rtc_compound_file_io.rb} +0 -0
- data/test/unit/index/{tc_field_infos.rb → rtc_field_infos.rb} +0 -0
- data/test/unit/index/{tc_fields_io.rb → rtc_fields_io.rb} +0 -0
- data/test/unit/index/{tc_multiple_term_doc_pos_enum.rb → rtc_multiple_term_doc_pos_enum.rb} +0 -0
- data/test/unit/index/{tc_segment_infos.rb → rtc_segment_infos.rb} +0 -0
- data/test/unit/index/{tc_segment_term_docs.rb → rtc_segment_term_docs.rb} +0 -0
- data/test/unit/index/{tc_segment_term_enum.rb → rtc_segment_term_enum.rb} +0 -0
- data/test/unit/index/{tc_segment_term_vector.rb → rtc_segment_term_vector.rb} +0 -0
- data/test/unit/index/{tc_term_buffer.rb → rtc_term_buffer.rb} +0 -0
- data/test/unit/index/{tc_term_info.rb → rtc_term_info.rb} +0 -0
- data/test/unit/index/{tc_term_infos_io.rb → rtc_term_infos_io.rb} +0 -0
- data/test/unit/index/{tc_term_vectors_io.rb → rtc_term_vectors_io.rb} +0 -0
- data/test/unit/index/{c_index.rb → tc_index.rb} +26 -6
- data/test/unit/index/{c_index_reader.rb → tc_index_reader.rb} +0 -0
- data/test/unit/index/{c_index_writer.rb → tc_index_writer.rb} +0 -0
- data/test/unit/index/{c_term.rb → tc_term.rb} +0 -0
- data/test/unit/index/{c_term_voi.rb → tc_term_voi.rb} +0 -0
- data/test/unit/query_parser/{c_query_parser.rb → rtc_query_parser.rb} +14 -14
- data/test/unit/query_parser/tc_query_parser.rb +24 -16
- data/test/unit/search/{tc_similarity.rb → rtc_similarity.rb} +0 -0
- data/test/unit/search/rtc_sort_field.rb +14 -0
- data/test/unit/search/{c_filter.rb → tc_filter.rb} +11 -11
- data/test/unit/search/{c_fuzzy_query.rb → tc_fuzzy_query.rb} +0 -0
- data/test/unit/search/{c_index_searcher.rb → tc_index_searcher.rb} +0 -0
- data/test/unit/search/{c_search_and_sort.rb → tc_search_and_sort.rb} +0 -0
- data/test/unit/search/{c_sort.rb → tc_sort.rb} +0 -0
- data/test/unit/search/tc_sort_field.rb +20 -7
- data/test/unit/search/{c_spans.rb → tc_spans.rb} +0 -0
- data/test/unit/store/rtc_fs_store.rb +62 -0
- data/test/unit/store/rtc_ram_store.rb +15 -0
- data/test/unit/store/rtm_store.rb +150 -0
- data/test/unit/store/rtm_store_lock.rb +2 -0
- data/test/unit/store/tc_fs_store.rb +54 -40
- data/test/unit/store/tc_ram_store.rb +20 -0
- data/test/unit/store/tm_store.rb +30 -146
- data/test/unit/store/tm_store_lock.rb +66 -0
- data/test/unit/utils/{tc_bit_vector.rb → rtc_bit_vector.rb} +0 -0
- data/test/unit/utils/{tc_date_tools.rb → rtc_date_tools.rb} +0 -0
- data/test/unit/utils/{tc_number_tools.rb → rtc_number_tools.rb} +0 -0
- data/test/unit/utils/{tc_parameter.rb → rtc_parameter.rb} +0 -0
- data/test/unit/utils/{tc_priority_queue.rb → rtc_priority_queue.rb} +0 -0
- data/test/unit/utils/{tc_string_helper.rb → rtc_string_helper.rb} +0 -0
- data/test/unit/utils/{tc_thread.rb → rtc_thread.rb} +0 -0
- data/test/unit/utils/{tc_weak_key_hash.rb → rtc_weak_key_hash.rb} +0 -0
- metadata +360 -289
- data/test/unit/document/c_field.rb +0 -98
- data/test/unit/search/c_sort_field.rb +0 -27
- data/test/unit/store/c_fs_store.rb +0 -76
- data/test/unit/store/c_ram_store.rb +0 -35
- data/test/unit/store/m_store.rb +0 -34
- data/test/unit/store/m_store_lock.rb +0 -68
File without changes
|
@@ -0,0 +1,28 @@
|
|
1
|
+
require File.dirname(__FILE__) + "/../../test_helper"
|
2
|
+
|
3
|
+
|
4
|
+
class FieldTest < Test::Unit::TestCase
|
5
|
+
include Ferret::Document
|
6
|
+
include Ferret::Utils
|
7
|
+
|
8
|
+
def test_store()
|
9
|
+
assert_equal("COMPRESS", Field::Store::COMPRESS.to_s)
|
10
|
+
assert_equal("YES", Field::Store::YES.to_s)
|
11
|
+
assert_equal("NO", Field::Store::NO.to_s)
|
12
|
+
end
|
13
|
+
|
14
|
+
def test_index()
|
15
|
+
assert_equal("TOKENIZED", Field::Index::TOKENIZED.to_s)
|
16
|
+
assert_equal("UNTOKENIZED", Field::Index::UNTOKENIZED.to_s)
|
17
|
+
assert_equal("NO", Field::Index::NO.to_s)
|
18
|
+
assert_equal("NO_NORMS", Field::Index::NO_NORMS.to_s)
|
19
|
+
end
|
20
|
+
|
21
|
+
def test_term_vector()
|
22
|
+
assert_equal("YES", Field::TermVector::YES.to_s)
|
23
|
+
assert_equal("NO", Field::TermVector::NO.to_s)
|
24
|
+
assert_equal("WITH_POSITIONS", Field::TermVector::WITH_POSITIONS.to_s)
|
25
|
+
assert_equal("WITH_OFFSETS", Field::TermVector::WITH_OFFSETS.to_s)
|
26
|
+
assert_equal("WITH_POSITIONS_OFFSETS", Field::TermVector::WITH_POSITIONS_OFFSETS.to_s)
|
27
|
+
end
|
28
|
+
end
|
File without changes
|
@@ -6,23 +6,93 @@ class FieldTest < Test::Unit::TestCase
|
|
6
6
|
include Ferret::Utils
|
7
7
|
|
8
8
|
def test_store()
|
9
|
-
|
10
|
-
|
11
|
-
|
9
|
+
assert_not_nil(Field::Store::COMPRESS)
|
10
|
+
assert_not_nil(Field::Store::YES)
|
11
|
+
assert_not_nil(Field::Store::NO)
|
12
12
|
end
|
13
13
|
|
14
14
|
def test_index()
|
15
|
-
|
16
|
-
|
17
|
-
|
18
|
-
|
15
|
+
assert_not_nil(Field::Index::TOKENIZED)
|
16
|
+
assert_not_nil(Field::Index::UNTOKENIZED)
|
17
|
+
assert_not_nil(Field::Index::NO)
|
18
|
+
assert_not_nil(Field::Index::NO_NORMS)
|
19
19
|
end
|
20
20
|
|
21
21
|
def test_term_vector()
|
22
|
-
|
23
|
-
|
24
|
-
|
25
|
-
|
26
|
-
|
22
|
+
assert_not_nil(Field::TermVector::YES)
|
23
|
+
assert_not_nil(Field::TermVector::NO)
|
24
|
+
assert_not_nil(Field::TermVector::WITH_POSITIONS)
|
25
|
+
assert_not_nil(Field::TermVector::WITH_OFFSETS)
|
26
|
+
assert_not_nil(Field::TermVector::WITH_POSITIONS_OFFSETS)
|
27
|
+
end
|
28
|
+
|
29
|
+
def test_standard_field()
|
30
|
+
f = Field.new("name", "value", Field::Store::COMPRESS, Field::Index::TOKENIZED)
|
31
|
+
assert_equal("name", f.name)
|
32
|
+
assert_equal("value", f.data)
|
33
|
+
assert_equal(true, f.stored?)
|
34
|
+
assert_equal(true, f.compressed?)
|
35
|
+
assert_equal(true, f.indexed?)
|
36
|
+
assert_equal(true, f.tokenized?)
|
37
|
+
assert_equal(false, f.store_term_vector?)
|
38
|
+
assert_equal(false, f.store_offsets?)
|
39
|
+
assert_equal(false, f.store_positions?)
|
40
|
+
assert_equal(false, f.omit_norms?)
|
41
|
+
assert_equal(false, f.binary?)
|
42
|
+
assert_equal("stored/compressed,indexed,tokenized,<name:value>", f.to_s)
|
43
|
+
f.data = "183"
|
44
|
+
f.boost = 0.001
|
45
|
+
assert_equal("183", f.data)
|
46
|
+
assert(0.001 =~ f.boost)
|
47
|
+
end
|
48
|
+
|
49
|
+
def test_set_store()
|
50
|
+
f = Field.new("name", "", Field::Store::COMPRESS, Field::Index::TOKENIZED)
|
51
|
+
f.store = Field::Store::NO
|
52
|
+
assert_equal(false, f.stored?)
|
53
|
+
assert_equal(false, f.compressed?)
|
54
|
+
assert_equal("indexed,tokenized,<name:>", f.to_s)
|
55
|
+
end
|
56
|
+
|
57
|
+
def test_set_index()
|
58
|
+
f = Field.new("name", "value", Field::Store::COMPRESS, Field::Index::TOKENIZED)
|
59
|
+
f.index = Field::Index::NO
|
60
|
+
assert_equal(false, f.indexed?)
|
61
|
+
assert_equal(false, f.tokenized?)
|
62
|
+
assert_equal(false, f.omit_norms?)
|
63
|
+
assert_equal("stored/compressed,<name:value>", f.to_s)
|
64
|
+
f.index = Field::Index::NO_NORMS
|
65
|
+
assert_equal(true, f.indexed?)
|
66
|
+
assert_equal(false, f.tokenized?)
|
67
|
+
assert_equal(true, f.omit_norms?)
|
68
|
+
assert_equal("stored/compressed,indexed,omit_norms,<name:value>", f.to_s)
|
69
|
+
end
|
70
|
+
|
71
|
+
def test_set_term_vector()
|
72
|
+
f = Field.new("name", "value", Field::Store::COMPRESS, Field::Index::TOKENIZED)
|
73
|
+
f.term_vector = Field::TermVector::WITH_POSITIONS_OFFSETS
|
74
|
+
assert_equal(true, f.store_term_vector?)
|
75
|
+
assert_equal(true, f.store_offsets?)
|
76
|
+
assert_equal(true, f.store_positions?)
|
77
|
+
assert_equal("stored/compressed,indexed,tokenized,store_term_vector,store_offsets,store_positions,<name:value>", f.to_s)
|
78
|
+
end
|
79
|
+
|
80
|
+
def test_new_binary_field()
|
81
|
+
tmp = []
|
82
|
+
256.times {|i| tmp[i] = i}
|
83
|
+
bin = tmp.pack("c*")
|
84
|
+
f = Field.new_binary_field("name", bin, Field::Store::YES)
|
85
|
+
assert_equal("name", f.name)
|
86
|
+
assert_equal(bin, f.data)
|
87
|
+
assert_equal(true, f.stored?)
|
88
|
+
assert_equal(false, f.compressed?)
|
89
|
+
assert_equal(false, f.indexed?)
|
90
|
+
assert_equal(false, f.tokenized?)
|
91
|
+
assert_equal(false, f.store_term_vector?)
|
92
|
+
assert_equal(false, f.store_offsets?)
|
93
|
+
assert_equal(false, f.store_positions?)
|
94
|
+
assert_equal(false, f.omit_norms?)
|
95
|
+
assert_equal(true, f.binary?)
|
96
|
+
assert_equal("stored/uncompressed,binary,<name:=bin_data=>", f.to_s)
|
27
97
|
end
|
28
98
|
end
|
File without changes
|
File without changes
|
File without changes
|
File without changes
|
File without changes
|
File without changes
|
File without changes
|
File without changes
|
File without changes
|
File without changes
|
File without changes
|
File without changes
|
@@ -77,7 +77,7 @@ class IndexTest < Test::Unit::TestCase
|
|
77
77
|
|
78
78
|
def do_test_index_with_doc_array(index)
|
79
79
|
data = [
|
80
|
-
{"def_field" => "one two multi", :id => "
|
80
|
+
{"def_field" => "one two multi", :id => "myid"},
|
81
81
|
{"def_field" => "one", :field2 => "three multi"},
|
82
82
|
{"def_field" => "two"},
|
83
83
|
{"def_field" => "one", :field2 => "four"},
|
@@ -125,8 +125,8 @@ class IndexTest < Test::Unit::TestCase
|
|
125
125
|
assert(! index.deleted?(7))
|
126
126
|
t = Term.new("field2", "four")
|
127
127
|
assert_equal("one", index[t]["def_field"])
|
128
|
-
assert_equal("one two multi", index["
|
129
|
-
index.delete("
|
128
|
+
assert_equal("one two multi", index["myid"]["def_field"])
|
129
|
+
index.delete("myid")
|
130
130
|
assert(index.deleted?(0))
|
131
131
|
end
|
132
132
|
|
@@ -193,6 +193,26 @@ class IndexTest < Test::Unit::TestCase
|
|
193
193
|
index.close
|
194
194
|
end
|
195
195
|
|
196
|
+
def test_key_used_for_id_field
|
197
|
+
fs_path = File.expand_path(File.join(File.dirname(__FILE__), '../../temp/fsdir'))
|
198
|
+
Dir[File.join(fs_path, "*")].each {|path| begin File.delete(path) rescue nil end}
|
199
|
+
data = [
|
200
|
+
{:my_id => "one two", :id => "me"},
|
201
|
+
{:my_id => "one", :field2 => "three"},
|
202
|
+
{:my_id => "two"},
|
203
|
+
{:my_id => "one", :field2 => "four"},
|
204
|
+
{:my_id => "one two"},
|
205
|
+
{:my_id => "two", :field2 => "three", "field3" => "four"},
|
206
|
+
{:my_id => "one"},
|
207
|
+
{:my_id => "two", :field2 => "three", "field3" => "five"}
|
208
|
+
]
|
209
|
+
index = Index.new(:path => fs_path, :key => :my_id)
|
210
|
+
data.each {|doc| index << doc }
|
211
|
+
assert_equal(3, index.size)
|
212
|
+
assert_equal("three", index[:two][:field2])
|
213
|
+
index.close
|
214
|
+
end
|
215
|
+
|
196
216
|
def test_merging_indexes
|
197
217
|
data = [
|
198
218
|
{"f" => "zero"},
|
@@ -432,7 +452,7 @@ class IndexTest < Test::Unit::TestCase
|
|
432
452
|
{:id => 1, :val => "four"},
|
433
453
|
]
|
434
454
|
index = Index.new(:analyzer => WhiteSpaceAnalyzer.new,
|
435
|
-
:key =>
|
455
|
+
:key => :id)
|
436
456
|
data.each { |doc| index << doc }
|
437
457
|
assert_equal(2, index.size)
|
438
458
|
assert_equal("two", index[0][:val])
|
@@ -453,7 +473,7 @@ class IndexTest < Test::Unit::TestCase
|
|
453
473
|
{:id => 1, :table => "product", :product => "backpack"}
|
454
474
|
]
|
455
475
|
index = Index.new(:analyzer => WhiteSpaceAnalyzer.new,
|
456
|
-
:key => [
|
476
|
+
:key => [:id, :table])
|
457
477
|
data.each { |doc| index << doc }
|
458
478
|
assert_equal(4, index.size)
|
459
479
|
assert_equal("super tent", index[0][:product])
|
@@ -476,7 +496,7 @@ class IndexTest < Test::Unit::TestCase
|
|
476
496
|
{:id => 1, :table => "Product", :product => "backpack"}
|
477
497
|
]
|
478
498
|
index = Index.new(:analyzer => Analyzer.new,
|
479
|
-
:key => [
|
499
|
+
:key => [:id, :table])
|
480
500
|
data.each do |dat|
|
481
501
|
doc = Document.new
|
482
502
|
dat.each_pair do |key, value|
|
File without changes
|
File without changes
|
File without changes
|
File without changes
|
@@ -3,7 +3,7 @@ require File.dirname(__FILE__) + "/../../test_helper"
|
|
3
3
|
class QueryParserTest < Test::Unit::TestCase
|
4
4
|
|
5
5
|
def test_strings()
|
6
|
-
parser = Ferret::QueryParser.new("xxx", :fields => ["
|
6
|
+
parser = Ferret::QueryParser.new("xxx", :fields => ["f1", "f2", "f3"])
|
7
7
|
pairs = [
|
8
8
|
['', ''],
|
9
9
|
['word', 'word'],
|
@@ -17,7 +17,7 @@ class QueryParserTest < Test::Unit::TestCase
|
|
17
17
|
['field:"one <> <> <> three <>"', 'field:"one <> <> <> three"'],
|
18
18
|
['field:"one <> <> <> three|four|five <>"', 'field:"one <> <> <> three|four|five"'],
|
19
19
|
['field:"one|two three|four|five six|seven"', 'field:"one|two three|four|five six|seven"'],
|
20
|
-
['
|
20
|
+
['contents:"testing|trucks"', 'contents:testing contents:trucks'],
|
21
21
|
['[aaa bbb]', '[aaa bbb]'],
|
22
22
|
['{aaa bbb]', '{aaa bbb]'],
|
23
23
|
['field:[aaa bbb}', 'field:[aaa bbb}'],
|
@@ -54,7 +54,7 @@ class QueryParserTest < Test::Unit::TestCase
|
|
54
54
|
['one AND (two OR three)', '+one +(two three)'],
|
55
55
|
['field:(one AND (two OR three))', '+field:one +(field:two field:three)'],
|
56
56
|
['one AND (two OR [aaa vvv})', '+one +(two [aaa vvv})'],
|
57
|
-
['one AND (
|
57
|
+
['one AND (one:two OR two:three) AND four', '+one +(one:two two:three) +four'],
|
58
58
|
['one^1.23', 'one^1.23'],
|
59
59
|
['(one AND two)^100.23', '(+one +two)^100.23'],
|
60
60
|
['field:(one AND two)^100.23', '(+field:one +field:two)^100.23'],
|
@@ -73,42 +73,42 @@ class QueryParserTest < Test::Unit::TestCase
|
|
73
73
|
['field:abc~ AND field:(b*)', '+field:abc~ +field:b*'],
|
74
74
|
['asdf?*?asd*dsf?asfd*asdf?^20.0', 'asdf?*?asd*dsf?asfd*asdf?^20.0'],
|
75
75
|
|
76
|
-
['*:xxx', '
|
76
|
+
['*:xxx', 'f1:xxx f2:xxx f3:xxx'],
|
77
77
|
['f1|f2:xxx', 'f1:xxx f2:xxx'],
|
78
78
|
|
79
|
-
['*:asd~0.2', '
|
79
|
+
['*:asd~0.2', 'f1:asd~0.2 f2:asd~0.2 f3:asd~0.2'],
|
80
80
|
['f1|f2:asd~0.2', 'f1:asd~0.2 f2:asd~0.2'],
|
81
81
|
|
82
|
-
['*:a?d*^20.0', '(
|
82
|
+
['*:a?d*^20.0', '(f1:a?d* f2:a?d* f3:a?d*)^20.0'],
|
83
83
|
['f1|f2:a?d*^20.0', '(f1:a?d* f2:a?d*)^20.0'],
|
84
84
|
|
85
|
-
['*:"asdf <> xxx|yyy"', '
|
85
|
+
['*:"asdf <> xxx|yyy"', 'f1:"asdf <> xxx|yyy" f2:"asdf <> xxx|yyy" f3:"asdf <> xxx|yyy"'],
|
86
86
|
['f1|f2:"asdf <> xxx|yyy"', 'f1:"asdf <> xxx|yyy" f2:"asdf <> xxx|yyy"'],
|
87
87
|
|
88
|
-
['*:[bbb xxx]', '
|
88
|
+
['*:[bbb xxx]', 'f1:[bbb xxx] f2:[bbb xxx] f3:[bbb xxx]'],
|
89
89
|
['f1|f2:[bbb xxx]', 'f1:[bbb xxx] f2:[bbb xxx]'],
|
90
90
|
|
91
|
-
['*:(xxx AND bbb)', '+(
|
91
|
+
['*:(xxx AND bbb)', '+(f1:xxx f2:xxx f3:xxx) +(f1:bbb f2:bbb f3:bbb)'],
|
92
92
|
['f1|f2:(xxx AND bbb)', '+(f1:xxx f2:xxx) +(f1:bbb f2:bbb)'],
|
93
93
|
['asdf?*?asd*dsf?asfd*asdf?^20.0', 'asdf?*?asd*dsf?asfd*asdf?^20.0'],
|
94
94
|
['"onewordphrase"', 'onewordphrase']
|
95
95
|
]
|
96
96
|
|
97
97
|
pairs.each do |query_str, expected|
|
98
|
-
assert_equal(expected, parser.parse(query_str).to_s(
|
98
|
+
assert_equal(expected, parser.parse(query_str).to_s(parser.default_field))
|
99
99
|
end
|
100
100
|
end
|
101
101
|
|
102
102
|
def test_qp_with_standard_analyzer()
|
103
|
-
parser = Ferret::QueryParser.new("xxx", :fields => ["
|
103
|
+
parser = Ferret::QueryParser.new("xxx", :fields => ["f1", "f2", "f3"],
|
104
104
|
:analyzer => Ferret::Analysis::StandardAnalyzer.new)
|
105
105
|
pairs = [
|
106
|
-
|
106
|
+
['key:1234', 'key:1234'],
|
107
107
|
['key:(1234)', 'key:1234']
|
108
108
|
]
|
109
109
|
|
110
110
|
pairs.each do |query_str, expected|
|
111
|
-
assert_equal(expected, parser.parse(query_str).to_s(
|
111
|
+
assert_equal(expected, parser.parse(query_str).to_s(parser.default_field))
|
112
112
|
end
|
113
113
|
end
|
114
114
|
|
@@ -132,7 +132,7 @@ class QueryParserTest < Test::Unit::TestCase
|
|
132
132
|
|
133
133
|
pairs.each do |query_str, expected|
|
134
134
|
do_test_query_parse_exception_raised(query_str)
|
135
|
-
assert_equal(expected, parser.parse(query_str).to_s(
|
135
|
+
assert_equal(expected, parser.parse(query_str).to_s(parser.default_field))
|
136
136
|
end
|
137
137
|
end
|
138
138
|
end
|
@@ -3,7 +3,7 @@ require File.dirname(__FILE__) + "/../../test_helper"
|
|
3
3
|
class QueryParserTest < Test::Unit::TestCase
|
4
4
|
|
5
5
|
def test_strings()
|
6
|
-
parser = Ferret::QueryParser.new("xxx", :fields => ["
|
6
|
+
parser = Ferret::QueryParser.new("xxx", :fields => ["xxx", "field", "f1", "f2"])
|
7
7
|
pairs = [
|
8
8
|
['', ''],
|
9
9
|
['word', 'word'],
|
@@ -17,7 +17,7 @@ class QueryParserTest < Test::Unit::TestCase
|
|
17
17
|
['field:"one <> <> <> three <>"', 'field:"one <> <> <> three"'],
|
18
18
|
['field:"one <> <> <> three|four|five <>"', 'field:"one <> <> <> three|four|five"'],
|
19
19
|
['field:"one|two three|four|five six|seven"', 'field:"one|two three|four|five six|seven"'],
|
20
|
-
['
|
20
|
+
['field:"testing|trucks"', 'field:testing field:trucks'],
|
21
21
|
['[aaa bbb]', '[aaa bbb]'],
|
22
22
|
['{aaa bbb]', '{aaa bbb]'],
|
23
23
|
['field:[aaa bbb}', 'field:[aaa bbb}'],
|
@@ -54,7 +54,7 @@ class QueryParserTest < Test::Unit::TestCase
|
|
54
54
|
['one AND (two OR three)', '+one +(two three)'],
|
55
55
|
['field:(one AND (two OR three))', '+field:one +(field:two field:three)'],
|
56
56
|
['one AND (two OR [aaa vvv})', '+one +(two [aaa vvv})'],
|
57
|
-
['one AND (
|
57
|
+
['one AND (f1:two OR f2:three) AND four', '+one +(f1:two f2:three) +four'],
|
58
58
|
['one^1.23', 'one^1.23'],
|
59
59
|
['(one AND two)^100.23', '(+one +two)^100.23'],
|
60
60
|
['field:(one AND two)^100.23', '(+field:one +field:two)^100.23'],
|
@@ -70,45 +70,45 @@ class QueryParserTest < Test::Unit::TestCase
|
|
70
70
|
['ab*de', 'ab*de'],
|
71
71
|
['asdf?*?asd*dsf?asfd*asdf?', 'asdf?*?asd*dsf?asfd*asdf?'],
|
72
72
|
['field:a* AND field:(b*)', '+field:a* +field:b*'],
|
73
|
-
['field:abc~ AND field:(b*)', '+field:abc~
|
73
|
+
['field:abc~ AND field:(b*)', '+field:abc~ +field:b*'],
|
74
74
|
['asdf?*?asd*dsf?asfd*asdf?^20.0', 'asdf?*?asd*dsf?asfd*asdf?^20.0'],
|
75
75
|
|
76
|
-
['*:xxx', '
|
76
|
+
['*:xxx', 'xxx field:xxx f1:xxx f2:xxx'],
|
77
77
|
['f1|f2:xxx', 'f1:xxx f2:xxx'],
|
78
78
|
|
79
|
-
['*:asd~0.2', '
|
79
|
+
['*:asd~0.2', 'asd~0.2 field:asd~0.2 f1:asd~0.2 f2:asd~0.2'],
|
80
80
|
['f1|f2:asd~0.2', 'f1:asd~0.2 f2:asd~0.2'],
|
81
81
|
|
82
|
-
['*:a?d*^20.0', '(
|
82
|
+
['*:a?d*^20.0', '(a?d* field:a?d* f1:a?d* f2:a?d*)^20.0'],
|
83
83
|
['f1|f2:a?d*^20.0', '(f1:a?d* f2:a?d*)^20.0'],
|
84
84
|
|
85
|
-
['*:"asdf <> xxx|yyy"', '
|
85
|
+
['*:"asdf <> xxx|yyy"', '"asdf <> xxx|yyy" field:"asdf <> xxx|yyy" f1:"asdf <> xxx|yyy" f2:"asdf <> xxx|yyy"'],
|
86
86
|
['f1|f2:"asdf <> xxx|yyy"', 'f1:"asdf <> xxx|yyy" f2:"asdf <> xxx|yyy"'],
|
87
87
|
|
88
|
-
['*:[bbb xxx]', '
|
88
|
+
['*:[bbb xxx]', '[bbb xxx] field:[bbb xxx] f1:[bbb xxx] f2:[bbb xxx]'],
|
89
89
|
['f1|f2:[bbb xxx]', 'f1:[bbb xxx] f2:[bbb xxx]'],
|
90
90
|
|
91
|
-
['*:(xxx AND bbb)', '+(
|
91
|
+
['*:(xxx AND bbb)', '+(xxx field:xxx f1:xxx f2:xxx) +(bbb field:bbb f1:bbb f2:bbb)'],
|
92
92
|
['f1|f2:(xxx AND bbb)', '+(f1:xxx f2:xxx) +(f1:bbb f2:bbb)'],
|
93
93
|
['asdf?*?asd*dsf?asfd*asdf?^20.0', 'asdf?*?asd*dsf?asfd*asdf?^20.0'],
|
94
94
|
['"onewordphrase"', 'onewordphrase']
|
95
95
|
]
|
96
96
|
|
97
97
|
pairs.each do |query_str, expected|
|
98
|
-
assert_equal(expected, parser.parse(query_str).to_s(
|
98
|
+
assert_equal(expected, parser.parse(query_str).to_s("xxx"))
|
99
99
|
end
|
100
100
|
end
|
101
101
|
|
102
102
|
def test_qp_with_standard_analyzer()
|
103
|
-
parser = Ferret::QueryParser.new("xxx", :fields => ["
|
103
|
+
parser = Ferret::QueryParser.new("xxx", :fields => ["xxx", "key"],
|
104
104
|
:analyzer => Ferret::Analysis::StandardAnalyzer.new)
|
105
105
|
pairs = [
|
106
|
-
|
106
|
+
['key:1234', 'key:1234'],
|
107
107
|
['key:(1234)', 'key:1234']
|
108
108
|
]
|
109
109
|
|
110
110
|
pairs.each do |query_str, expected|
|
111
|
-
assert_equal(expected, parser.parse(query_str).to_s(
|
111
|
+
assert_equal(expected, parser.parse(query_str).to_s("xxx"))
|
112
112
|
end
|
113
113
|
end
|
114
114
|
|
@@ -119,6 +119,14 @@ class QueryParserTest < Test::Unit::TestCase
|
|
119
119
|
end
|
120
120
|
end
|
121
121
|
|
122
|
+
def test_prefix_query
|
123
|
+
parser = Ferret::QueryParser.new("xxx", :fields => ["xxx"],
|
124
|
+
:analyzer => Ferret::Analysis::StandardAnalyzer.new)
|
125
|
+
assert_equal(Ferret::Search::PrefixQuery, parser.parse("asdg*").class)
|
126
|
+
assert_equal(Ferret::Search::WildcardQuery, parser.parse("a?dg*").class)
|
127
|
+
assert_equal(Ferret::Search::WildcardQuery, parser.parse("a*dg*").class)
|
128
|
+
assert_equal(Ferret::Search::WildcardQuery, parser.parse("adg*c").class)
|
129
|
+
end
|
122
130
|
|
123
131
|
def test_bad_queries
|
124
132
|
parser = Ferret::QueryParser.new("xxx", :fields => ["f1", "f2"],
|
@@ -127,12 +135,12 @@ class QueryParserTest < Test::Unit::TestCase
|
|
127
135
|
pairs = [
|
128
136
|
['::*word', 'word'],
|
129
137
|
['()*&)(*^&*(', ''],
|
130
|
-
['()*&one)(*two(*&"', 'one two']
|
138
|
+
['()*&one)(*two(*&"', '"one two"']
|
131
139
|
]
|
132
140
|
|
133
141
|
pairs.each do |query_str, expected|
|
134
142
|
do_test_query_parse_exception_raised(query_str)
|
135
|
-
assert_equal(expected, parser.parse(query_str).to_s(
|
143
|
+
assert_equal(expected, parser.parse(query_str).to_s("xxx"))
|
136
144
|
end
|
137
145
|
end
|
138
146
|
end
|
File without changes
|
@@ -0,0 +1,14 @@
|
|
1
|
+
require File.dirname(__FILE__) + "/../../test_helper"
|
2
|
+
|
3
|
+
class SortFieldTest < Test::Unit::TestCase
|
4
|
+
include Ferret::Search
|
5
|
+
|
6
|
+
def test_params()
|
7
|
+
assert_equal("score", SortField::SortType::SCORE.to_s)
|
8
|
+
assert_equal("doc", SortField::SortType::DOC.to_s)
|
9
|
+
assert_equal("auto", SortField::SortType::AUTO.to_s)
|
10
|
+
assert_equal("string", SortField::SortType::STRING.to_s)
|
11
|
+
assert_equal("int", SortField::SortType::INTEGER.to_s)
|
12
|
+
assert_equal("float", SortField::SortType::FLOAT.to_s)
|
13
|
+
end
|
14
|
+
end
|