xapian-fu 0.2 → 1.0.1
Sign up to get free protection for your applications and to get access to all the features.
- data/README.rdoc +152 -13
- data/examples/query.rb +34 -6
- data/examples/spider.rb +44 -15
- data/lib/xapian_fu/query_parser.rb +179 -0
- data/lib/xapian_fu/result_set.rb +52 -0
- data/lib/xapian_fu/stopper_factory.rb +40 -0
- data/lib/xapian_fu/stopwords/README +7 -0
- data/lib/xapian_fu/stopwords/danish.txt +102 -0
- data/lib/xapian_fu/stopwords/dutch.txt +113 -0
- data/lib/xapian_fu/stopwords/english.txt +312 -0
- data/lib/xapian_fu/stopwords/finnish.txt +89 -0
- data/lib/xapian_fu/stopwords/french.txt +168 -0
- data/lib/xapian_fu/stopwords/german.txt +286 -0
- data/lib/xapian_fu/stopwords/hungarian.txt +203 -0
- data/lib/xapian_fu/stopwords/italian.txt +295 -0
- data/lib/xapian_fu/stopwords/norwegian.txt +186 -0
- data/lib/xapian_fu/stopwords/portuguese.txt +245 -0
- data/lib/xapian_fu/stopwords/russian.txt +236 -0
- data/lib/xapian_fu/stopwords/spanish.txt +348 -0
- data/lib/xapian_fu/stopwords/swedish.txt +125 -0
- data/lib/xapian_fu/stopwords/update.rb +7 -0
- data/lib/xapian_fu/xapian_db.rb +215 -99
- data/lib/xapian_fu/xapian_doc.rb +229 -47
- data/lib/xapian_fu/xapian_doc_value_accessor.rb +125 -0
- data/lib/xapian_fu/xapian_documents_accessor.rb +82 -0
- data/lib/xapian_fu.rb +1 -0
- data/spec/query_parser_spec.rb +43 -0
- data/spec/stopper_factory_spec.rb +57 -0
- data/spec/xapian_db_spec.rb +458 -215
- data/spec/xapian_doc_spec.rb +180 -0
- data/spec/xapian_doc_value_accessor_spec.rb +92 -0
- metadata +29 -5
data/spec/xapian_doc_spec.rb
CHANGED
@@ -13,4 +13,184 @@ describe XapianDoc do
|
|
13
13
|
XapianDoc.new(:id => 666).should_not == XapianDoc.new(:id => 667)
|
14
14
|
end
|
15
15
|
|
16
|
+
describe "to_xapian_document" do
|
17
|
+
it "should tokenize strings" do
|
18
|
+
xdb = XapianDb.new
|
19
|
+
xdoc = xdb.documents.new("once upon a time").to_xapian_document
|
20
|
+
xdoc.terms.should be_a_kind_of Array
|
21
|
+
xdoc.terms.last.should be_a_kind_of Xapian::Term
|
22
|
+
xdoc.terms.last.term.should == "upon"
|
23
|
+
end
|
24
|
+
|
25
|
+
it "should store positions by default when tokenizing" do
|
26
|
+
xdb = XapianDb.new
|
27
|
+
doc = xdb.documents.new("once upon a time")
|
28
|
+
doc.save
|
29
|
+
xdb.ro.positionlist(doc.id, "time").first.should_not == nil
|
30
|
+
end
|
31
|
+
|
32
|
+
it "should not store positions when tokenizing when :index_positions is set to false" do
|
33
|
+
xdb = XapianDb.new(:index_positions => false)
|
34
|
+
doc = xdb.documents.new("once upon a time")
|
35
|
+
doc.save
|
36
|
+
xdb.ro.positionlist(doc.id, "once").first.should == nil
|
37
|
+
end
|
38
|
+
|
39
|
+
it "should tokenize a hash" do
|
40
|
+
xdb = XapianDb.new
|
41
|
+
xdoc = xdb.documents.new(:title => 'once upon a time').to_xapian_document
|
42
|
+
xdoc.terms.should be_a_kind_of Array
|
43
|
+
xdoc.terms.last.should be_a_kind_of Xapian::Term
|
44
|
+
xdoc.terms.last.term.should == "upon"
|
45
|
+
end
|
46
|
+
|
47
|
+
it "should tokenize the fields of a hash separately" do
|
48
|
+
xdb = XapianDb.new
|
49
|
+
xdoc = xdb.documents.new({ :text => "once upon a time", :title => "A story" }).to_xapian_document
|
50
|
+
terms = xdoc.terms.collect { |t| t.term }
|
51
|
+
terms.should include "XTEXTonce"
|
52
|
+
terms.should include "XTITLEstory"
|
53
|
+
terms.should_not include "XTEXTstory"
|
54
|
+
end
|
55
|
+
|
56
|
+
it "should not tokenize fields declared as not to be indexed" do
|
57
|
+
xdb = XapianDb.new(:fields => { :name => { :index => false } })
|
58
|
+
xdoc = xdb.documents.new({ :name => 'John Leach', :quote => 'Xapian Rocks' }).to_xapian_document
|
59
|
+
terms = xdoc.terms.collect { |t| t.term }
|
60
|
+
terms.should_not include 'XNAMEjohn'
|
61
|
+
terms.should_not include 'XNAMEleach'
|
62
|
+
terms.should_not include 'Zjohn'
|
63
|
+
terms.should_not include 'Zleach'
|
64
|
+
terms.should_not include 'john'
|
65
|
+
terms.should_not include 'leach'
|
66
|
+
end
|
67
|
+
|
68
|
+
it "should convert Time instances to a useful format when tokenizing" do
|
69
|
+
time = Time.now
|
70
|
+
xdb = XapianDb.new
|
71
|
+
xdoc = xdb.documents.new(:created_at => time).to_xapian_document
|
72
|
+
terms = xdoc.terms.collect { |t| t.term }
|
73
|
+
terms.should include time.utc.strftime("%Y%m%d%H%M%S")
|
74
|
+
end
|
75
|
+
|
76
|
+
it "should convert DateTime instances to a useful format when tokenizing" do
|
77
|
+
datetime = DateTime.now
|
78
|
+
xdb = XapianDb.new
|
79
|
+
xdoc = xdb.documents.new(:created_at => datetime).to_xapian_document
|
80
|
+
terms = xdoc.terms.collect { |t| t.term }
|
81
|
+
terms.should include datetime.strftime("%Y%m%d%H%M%S")
|
82
|
+
end
|
83
|
+
|
84
|
+
it "should convert Time instances to a useful format when tokenizing" do
|
85
|
+
date = Date.today
|
86
|
+
xdb = XapianDb.new
|
87
|
+
xdoc = xdb.documents.new(:created_on => date).to_xapian_document
|
88
|
+
terms = xdoc.terms.collect { |t| t.term }
|
89
|
+
terms.should include date.strftime("%Y%m%d")
|
90
|
+
end
|
91
|
+
|
92
|
+
it "should stem English words by default" do
|
93
|
+
xdb = XapianDb.new
|
94
|
+
xdoc = xdb.documents.new("She fished for fish").to_xapian_document
|
95
|
+
terms = xdoc.terms.collect { |t| t.term }
|
96
|
+
terms.should_not include "Zfished"
|
97
|
+
terms.should include "Zfish"
|
98
|
+
end
|
99
|
+
|
100
|
+
it "should inherit the databases stemmer by default" do
|
101
|
+
xdb = XapianDb.new(:stemmer => :french)
|
102
|
+
xdoc = xdb.documents.new("majestueusement").to_xapian_document
|
103
|
+
terms = xdoc.terms.collect { |t| t.term }
|
104
|
+
terms.should include 'Zmajestu'
|
105
|
+
end
|
106
|
+
|
107
|
+
stems = {
|
108
|
+
:german => { "aufeinander" => "aufeinand" },
|
109
|
+
:french => { "majestueusement" => "majestu" },
|
110
|
+
:swedish => { "kloekornas" => "kloek" },
|
111
|
+
:danish => { "indvendingerne" => "indvending" },
|
112
|
+
:russian => { "падшую", "падш" },
|
113
|
+
:italian => { "propagamento" => "propag" }
|
114
|
+
}
|
115
|
+
stems.keys.each do |lang|
|
116
|
+
stems[lang].each do |word, stem|
|
117
|
+
it "should stem #{lang.to_s.capitalize} words when the :stemmer option is set to :#{lang}" do
|
118
|
+
xdb = XapianDb.new
|
119
|
+
xdoc = xdb.documents.new(word, :stemmer => lang).to_xapian_document
|
120
|
+
terms = xdoc.terms.collect { |t| t.term }
|
121
|
+
terms.should include 'Z'+stem
|
122
|
+
end
|
123
|
+
end
|
124
|
+
end
|
125
|
+
|
126
|
+
it "should not stem words when stemmer is set to false" do
|
127
|
+
xdb = XapianDb.new
|
128
|
+
xdoc = xdb.documents.new("She fished for fish", :stemmer => false).to_xapian_document
|
129
|
+
terms = xdoc.terms.collect { |t| t.term if t.term =~ /^Z/ }.compact
|
130
|
+
terms.should be_empty
|
131
|
+
end
|
132
|
+
|
133
|
+
it "should not stem english stop words by default" do
|
134
|
+
xdb = XapianDb.new
|
135
|
+
xdoc = xdb.documents.new("And they made a cake", :stemmer => :english).to_xapian_document
|
136
|
+
terms = xdoc.terms.collect { |t| t.term }
|
137
|
+
terms.should_not include 'Zand'
|
138
|
+
terms.should_not include 'Za'
|
139
|
+
terms.should include 'Zcake'
|
140
|
+
end
|
141
|
+
|
142
|
+
it "should allow setting the stopper on initialisation" do
|
143
|
+
xdb = XapianDb.new(:stopper => :english)
|
144
|
+
xdoc = xdb.documents.new("And they made a cake", :stopper => :french)
|
145
|
+
xdoc.stopper.call("ayantes").should == true
|
146
|
+
xdoc.stopper.call("and").should == false
|
147
|
+
end
|
148
|
+
|
149
|
+
it "should support stop words encoded in utf8" do
|
150
|
+
xdb = XapianDb.new
|
151
|
+
xdoc = xdb.documents.new("и они made a cake", :stemmer => :russian, :stopper => :russian).to_xapian_document
|
152
|
+
terms = xdoc.terms.collect { |t| t.term }
|
153
|
+
terms.should_not include 'Zи'
|
154
|
+
terms.should_not include 'Zони'
|
155
|
+
terms.should include 'Zcake'
|
156
|
+
end
|
157
|
+
end
|
158
|
+
|
159
|
+
describe "stemmer" do
|
160
|
+
it "should return the same stemmer as the database by default" do
|
161
|
+
xdb = XapianDb.new(:language => :french)
|
162
|
+
xdoc = xdb.documents.new("stink and bones")
|
163
|
+
xdoc.stemmer.call("contournait").should == "contourn"
|
164
|
+
end
|
165
|
+
it "should return a stemmer for the document language, overriding the db" do
|
166
|
+
xdb = XapianDb.new(:language => :english)
|
167
|
+
xdoc = xdb.documents.new("stink and bones", :language => :french)
|
168
|
+
xdoc.stemmer.call("contournait").should == "contourn"
|
169
|
+
end
|
170
|
+
it "should return a stemmer set by the :stemmer option, overriding the :language option and the db stemmer" do
|
171
|
+
xdb = XapianDb.new(:language => :german)
|
172
|
+
xdoc = xdb.documents.new("stink and bones", :language => :english, :stemmer => :french)
|
173
|
+
xdoc.stemmer.call("contournait").should == "contourn"
|
174
|
+
end
|
175
|
+
|
176
|
+
end
|
177
|
+
|
178
|
+
describe "stopper" do
|
179
|
+
it "should return the same stopper as the database by default" do
|
180
|
+
xdb = XapianDb.new(:language => :french)
|
181
|
+
xdoc = xdb.documents.new("stink and bones")
|
182
|
+
xdoc.stopper.call("avec").should == true
|
183
|
+
end
|
184
|
+
it "should return a stopper for the document language, overriding the db" do
|
185
|
+
xdb = XapianDb.new(:language => :english)
|
186
|
+
xdoc = xdb.documents.new("stink and bones", :language => :french)
|
187
|
+
xdoc.stopper.call("avec").should == true
|
188
|
+
end
|
189
|
+
it "should return a stopper set by the :stopper option, overriding the :language option and the db stopper" do
|
190
|
+
xdb = XapianDb.new(:language => :german)
|
191
|
+
xdoc = xdb.documents.new("stink and bones", :language => :english, :stopper => :french)
|
192
|
+
xdoc.stopper.call("avec").should == true
|
193
|
+
end
|
194
|
+
end
|
195
|
+
|
16
196
|
end
|
@@ -0,0 +1,92 @@
|
|
1
|
+
require 'xapian'
|
2
|
+
require 'lib/xapian_fu.rb'
|
3
|
+
include XapianFu
|
4
|
+
require 'fileutils'
|
5
|
+
|
6
|
+
describe XapianDocValueAccessor do
|
7
|
+
|
8
|
+
it "should store and fetch values like a hash" do
|
9
|
+
values = XapianDocValueAccessor.new(XapianDoc.new(nil))
|
10
|
+
values.store(:city, "Leeds").should == "Leeds"
|
11
|
+
values.fetch(:city).should == "Leeds"
|
12
|
+
values[:city] = "London"
|
13
|
+
values[:city].should == "London"
|
14
|
+
end
|
15
|
+
|
16
|
+
it "should add and retrieve values from the Xapian::Document" do
|
17
|
+
doc = XapianDoc.new(nil)
|
18
|
+
values = XapianDocValueAccessor.new(doc)
|
19
|
+
lambda { values[:city] = "London" }.should change(doc.xapian_document, :values_count).by(1)
|
20
|
+
end
|
21
|
+
|
22
|
+
it "should store fields defined as Fixnum as packed Long" do
|
23
|
+
xdb = XapianDb.new(:fields => { :number => { :type => Fixnum, :store => true } })
|
24
|
+
[-83883, 256532, 0, 0x3fffffff].each do |number|
|
25
|
+
doc = xdb.documents.new(:number => number)
|
26
|
+
doc.values.store(:number, number, Fixnum).should == number
|
27
|
+
doc.values.fetch(:number, Fixnum).should == number
|
28
|
+
doc.to_xapian_document.values.first.value.should == [number].pack("l")
|
29
|
+
end
|
30
|
+
end
|
31
|
+
|
32
|
+
it "should store fields defined as Bignum as packed Double-precision float, big-endian byte order" do
|
33
|
+
xdb = XapianDb.new(:fields => { :number => { :type => Bignum, :store => true } })
|
34
|
+
doc = xdb.documents.new(:number => 0x3fffffffffffff)
|
35
|
+
doc.values.store(:number, 0x3fffffffffffff).should == 0x3fffffffffffff
|
36
|
+
doc.values.fetch(:number).should == 0x3fffffffffffff
|
37
|
+
doc.to_xapian_document.values.first.value.should == [0x3fffffffffffff].pack("G")
|
38
|
+
end
|
39
|
+
|
40
|
+
it "should store fields defined as Float as packed Double-precision float, big-endian byte order" do
|
41
|
+
xdb = XapianDb.new(:fields => { :number => { :type => Float, :store => true } })
|
42
|
+
[-0.303393984588383833, 8.448488388488384, 1.0].each do |number|
|
43
|
+
doc = xdb.documents.new(:number => number)
|
44
|
+
doc.values.store(:number, number).should == number
|
45
|
+
doc.values.fetch(:number).should == number
|
46
|
+
doc.to_xapian_document.values.first.value.should == [number].pack("G")
|
47
|
+
end
|
48
|
+
end
|
49
|
+
|
50
|
+
it "should store fields defined as Time in UTC as packed Double-precision float, big-endian byte order" do
|
51
|
+
xdb = XapianDb.new(:fields => { :created_at => { :type => Time, :store => true }})
|
52
|
+
time = Time.now
|
53
|
+
doc = xdb.documents.new(:created_at => time)
|
54
|
+
doc.values.store(:created_at, time).should == time
|
55
|
+
doc.values.fetch(:created_at).should == time
|
56
|
+
doc.to_xapian_document.values.first.value.should == [time.utc.to_f].pack("G")
|
57
|
+
end
|
58
|
+
|
59
|
+
it "should store fields defined as DateTime as a string" do
|
60
|
+
xdb = XapianDb.new(:fields => { :created_at => { :type => DateTime, :store => true }})
|
61
|
+
datetime = DateTime.now
|
62
|
+
doc = xdb.documents.new(:created_at => datetime)
|
63
|
+
doc.values.store(:created_at, datetime).should == datetime
|
64
|
+
doc.values.fetch(:created_at).should be_close(datetime, 0.0001) # miliseconds are not stored
|
65
|
+
doc.to_xapian_document.values.first.value.should == datetime.to_s
|
66
|
+
end
|
67
|
+
|
68
|
+
it "should store fields defined as Date as a string" do
|
69
|
+
xdb = XapianDb.new(:fields => { :created_on => { :type => Date, :store => true }})
|
70
|
+
date = Date.today
|
71
|
+
doc = xdb.documents.new(:created_on => date)
|
72
|
+
doc.values.store(:created_on, date).should == date
|
73
|
+
doc.values.fetch(:created_on).should == date
|
74
|
+
doc.to_xapian_document.values.first.value.should == date.to_s
|
75
|
+
end
|
76
|
+
|
77
|
+
it "should count the stored values when size is called" do
|
78
|
+
doc = XapianDoc.new(nil)
|
79
|
+
lambda { doc.values[:city] = "London" }.should change(doc.values, :size).by(1)
|
80
|
+
end
|
81
|
+
|
82
|
+
it "should delete values from the Xapian::Document" do
|
83
|
+
doc = XapianDoc.new(nil)
|
84
|
+
doc.values[:city] = "Leeds"
|
85
|
+
lambda { doc.values.delete(:city) }.should change(doc.values, :size).by(-1)
|
86
|
+
doc.values[:city] = "London"
|
87
|
+
doc.values.delete(:city).should == "London"
|
88
|
+
end
|
89
|
+
|
90
|
+
end
|
91
|
+
|
92
|
+
|
metadata
CHANGED
@@ -1,7 +1,7 @@
|
|
1
1
|
--- !ruby/object:Gem::Specification
|
2
2
|
name: xapian-fu
|
3
3
|
version: !ruby/object:Gem::Version
|
4
|
-
version:
|
4
|
+
version: 1.0.1
|
5
5
|
platform: ruby
|
6
6
|
authors:
|
7
7
|
- John Leach
|
@@ -9,7 +9,7 @@ autorequire:
|
|
9
9
|
bindir: bin
|
10
10
|
cert_chain: []
|
11
11
|
|
12
|
-
date: 2009-
|
12
|
+
date: 2009-09-09 00:00:00 +01:00
|
13
13
|
default_executable:
|
14
14
|
dependencies: []
|
15
15
|
|
@@ -24,9 +24,28 @@ extra_rdoc_files:
|
|
24
24
|
- LICENSE
|
25
25
|
files:
|
26
26
|
- lib/xapian_fu.rb
|
27
|
-
- lib/xapian_fu
|
27
|
+
- lib/xapian_fu/result_set.rb
|
28
|
+
- lib/xapian_fu/stopper_factory.rb
|
29
|
+
- lib/xapian_fu/stopwords/swedish.txt
|
30
|
+
- lib/xapian_fu/stopwords/french.txt
|
31
|
+
- lib/xapian_fu/stopwords/english.txt
|
32
|
+
- lib/xapian_fu/stopwords/dutch.txt
|
33
|
+
- lib/xapian_fu/stopwords/italian.txt
|
34
|
+
- lib/xapian_fu/stopwords/norwegian.txt
|
35
|
+
- lib/xapian_fu/stopwords/finnish.txt
|
36
|
+
- lib/xapian_fu/stopwords/hungarian.txt
|
37
|
+
- lib/xapian_fu/stopwords/README
|
38
|
+
- lib/xapian_fu/stopwords/update.rb
|
39
|
+
- lib/xapian_fu/stopwords/portuguese.txt
|
40
|
+
- lib/xapian_fu/stopwords/german.txt
|
41
|
+
- lib/xapian_fu/stopwords/danish.txt
|
42
|
+
- lib/xapian_fu/stopwords/spanish.txt
|
43
|
+
- lib/xapian_fu/stopwords/russian.txt
|
28
44
|
- lib/xapian_fu/xapian_db.rb
|
29
45
|
- lib/xapian_fu/xapian_doc.rb
|
46
|
+
- lib/xapian_fu/xapian_documents_accessor.rb
|
47
|
+
- lib/xapian_fu/query_parser.rb
|
48
|
+
- lib/xapian_fu/xapian_doc_value_accessor.rb
|
30
49
|
- examples/ar_spider.rb
|
31
50
|
- examples/query.rb
|
32
51
|
- examples/spider.rb
|
@@ -35,6 +54,8 @@ files:
|
|
35
54
|
- LICENSE
|
36
55
|
has_rdoc: true
|
37
56
|
homepage: http://github.com/johnl/xapian-fu/tree/master
|
57
|
+
licenses: []
|
58
|
+
|
38
59
|
post_install_message:
|
39
60
|
rdoc_options:
|
40
61
|
- --title
|
@@ -59,11 +80,14 @@ required_rubygems_version: !ruby/object:Gem::Requirement
|
|
59
80
|
requirements: []
|
60
81
|
|
61
82
|
rubyforge_project: xapian-fu
|
62
|
-
rubygems_version: 1.3.
|
83
|
+
rubygems_version: 1.3.5
|
63
84
|
signing_key:
|
64
|
-
specification_version:
|
85
|
+
specification_version: 3
|
65
86
|
summary: A Ruby interface to the Xapian search engine
|
66
87
|
test_files:
|
88
|
+
- spec/stopper_factory_spec.rb
|
67
89
|
- spec/xapian_doc_spec.rb
|
68
90
|
- spec/xapian_db_spec.rb
|
91
|
+
- spec/query_parser_spec.rb
|
92
|
+
- spec/xapian_doc_value_accessor_spec.rb
|
69
93
|
- spec/spec.opts
|