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
@@ -0,0 +1,168 @@
|
|
1
|
+
|
2
|
+
| A French stop word list. Comments begin with vertical bar. Each stop
|
3
|
+
| word is at the start of a line.
|
4
|
+
|
5
|
+
au | a + le
|
6
|
+
aux | a + les
|
7
|
+
avec | with
|
8
|
+
ce | this
|
9
|
+
ces | these
|
10
|
+
dans | with
|
11
|
+
de | of
|
12
|
+
des | de + les
|
13
|
+
du | de + le
|
14
|
+
elle | she
|
15
|
+
en | `of them' etc
|
16
|
+
et | and
|
17
|
+
eux | them
|
18
|
+
il | he
|
19
|
+
je | I
|
20
|
+
la | the
|
21
|
+
le | the
|
22
|
+
leur | their
|
23
|
+
lui | him
|
24
|
+
ma | my (fem)
|
25
|
+
mais | but
|
26
|
+
me | me
|
27
|
+
même | same; as in moi-même (myself) etc
|
28
|
+
mes | me (pl)
|
29
|
+
moi | me
|
30
|
+
mon | my (masc)
|
31
|
+
ne | not
|
32
|
+
nos | our (pl)
|
33
|
+
notre | our
|
34
|
+
nous | we
|
35
|
+
on | one
|
36
|
+
ou | where
|
37
|
+
par | by
|
38
|
+
pas | not
|
39
|
+
pour | for
|
40
|
+
qu | que before vowel
|
41
|
+
que | that
|
42
|
+
qui | who
|
43
|
+
sa | his, her (fem)
|
44
|
+
se | oneself
|
45
|
+
ses | his (pl)
|
46
|
+
son | his, her (masc)
|
47
|
+
sur | on
|
48
|
+
ta | thy (fem)
|
49
|
+
te | thee
|
50
|
+
tes | thy (pl)
|
51
|
+
toi | thee
|
52
|
+
ton | thy (masc)
|
53
|
+
tu | thou
|
54
|
+
un | a
|
55
|
+
une | a
|
56
|
+
vos | your (pl)
|
57
|
+
votre | your
|
58
|
+
vous | you
|
59
|
+
|
60
|
+
| single letter forms
|
61
|
+
|
62
|
+
c | c'
|
63
|
+
d | d'
|
64
|
+
j | j'
|
65
|
+
l | l'
|
66
|
+
à | to, at
|
67
|
+
m | m'
|
68
|
+
n | n'
|
69
|
+
s | s'
|
70
|
+
t | t'
|
71
|
+
y | there
|
72
|
+
|
73
|
+
| forms of être (not including the infinitive):
|
74
|
+
été
|
75
|
+
étée
|
76
|
+
étées
|
77
|
+
étés
|
78
|
+
étant
|
79
|
+
étante
|
80
|
+
étants
|
81
|
+
étantes
|
82
|
+
suis
|
83
|
+
es
|
84
|
+
est
|
85
|
+
sommes
|
86
|
+
êtes
|
87
|
+
sont
|
88
|
+
serai
|
89
|
+
seras
|
90
|
+
sera
|
91
|
+
serons
|
92
|
+
serez
|
93
|
+
seront
|
94
|
+
serais
|
95
|
+
serait
|
96
|
+
serions
|
97
|
+
seriez
|
98
|
+
seraient
|
99
|
+
étais
|
100
|
+
était
|
101
|
+
étions
|
102
|
+
étiez
|
103
|
+
étaient
|
104
|
+
fus
|
105
|
+
fut
|
106
|
+
fûmes
|
107
|
+
fûtes
|
108
|
+
furent
|
109
|
+
sois
|
110
|
+
soit
|
111
|
+
soyons
|
112
|
+
soyez
|
113
|
+
soient
|
114
|
+
fusse
|
115
|
+
fusses
|
116
|
+
fût
|
117
|
+
fussions
|
118
|
+
fussiez
|
119
|
+
fussent
|
120
|
+
|
121
|
+
| forms of avoir (not including the infinitive):
|
122
|
+
ayant
|
123
|
+
ayante
|
124
|
+
ayantes
|
125
|
+
ayants
|
126
|
+
eu
|
127
|
+
eue
|
128
|
+
eues
|
129
|
+
eus
|
130
|
+
ai
|
131
|
+
as
|
132
|
+
avons
|
133
|
+
avez
|
134
|
+
ont
|
135
|
+
aurai
|
136
|
+
auras
|
137
|
+
aura
|
138
|
+
aurons
|
139
|
+
aurez
|
140
|
+
auront
|
141
|
+
aurais
|
142
|
+
aurait
|
143
|
+
aurions
|
144
|
+
auriez
|
145
|
+
auraient
|
146
|
+
avais
|
147
|
+
avait
|
148
|
+
avions
|
149
|
+
aviez
|
150
|
+
avaient
|
151
|
+
eut
|
152
|
+
eûmes
|
153
|
+
eûtes
|
154
|
+
eurent
|
155
|
+
aie
|
156
|
+
aies
|
157
|
+
ait
|
158
|
+
ayons
|
159
|
+
ayez
|
160
|
+
aient
|
161
|
+
eusse
|
162
|
+
eusses
|
163
|
+
eût
|
164
|
+
eussions
|
165
|
+
eussiez
|
166
|
+
eussent
|
167
|
+
|
168
|
+
|
@@ -0,0 +1,286 @@
|
|
1
|
+
|
2
|
+
| A German stop word list. Comments begin with vertical bar. Each stop
|
3
|
+
| word is at the start of a line.
|
4
|
+
|
5
|
+
| The number of forms in this list is reduced significantly by passing it
|
6
|
+
| through the German stemmer.
|
7
|
+
|
8
|
+
|
9
|
+
aber | but
|
10
|
+
|
11
|
+
alle | all
|
12
|
+
allem
|
13
|
+
allen
|
14
|
+
aller
|
15
|
+
alles
|
16
|
+
|
17
|
+
als | than, as
|
18
|
+
also | so
|
19
|
+
am | an + dem
|
20
|
+
an | at
|
21
|
+
|
22
|
+
ander | other
|
23
|
+
andere
|
24
|
+
anderem
|
25
|
+
anderen
|
26
|
+
anderer
|
27
|
+
anderes
|
28
|
+
anderm
|
29
|
+
andern
|
30
|
+
anderr
|
31
|
+
anders
|
32
|
+
|
33
|
+
auch | also
|
34
|
+
auf | on
|
35
|
+
aus | out of
|
36
|
+
bei | by
|
37
|
+
bin | am
|
38
|
+
bis | until
|
39
|
+
bist | art
|
40
|
+
da | there
|
41
|
+
damit | with it
|
42
|
+
dann | then
|
43
|
+
|
44
|
+
der | the
|
45
|
+
den
|
46
|
+
des
|
47
|
+
dem
|
48
|
+
die
|
49
|
+
das
|
50
|
+
|
51
|
+
daß | that
|
52
|
+
|
53
|
+
derselbe | the same
|
54
|
+
derselben
|
55
|
+
denselben
|
56
|
+
desselben
|
57
|
+
demselben
|
58
|
+
dieselbe
|
59
|
+
dieselben
|
60
|
+
dasselbe
|
61
|
+
|
62
|
+
dazu | to that
|
63
|
+
|
64
|
+
dein | thy
|
65
|
+
deine
|
66
|
+
deinem
|
67
|
+
deinen
|
68
|
+
deiner
|
69
|
+
deines
|
70
|
+
|
71
|
+
denn | because
|
72
|
+
|
73
|
+
derer | of those
|
74
|
+
dessen | of him
|
75
|
+
|
76
|
+
dich | thee
|
77
|
+
dir | to thee
|
78
|
+
du | thou
|
79
|
+
|
80
|
+
dies | this
|
81
|
+
diese
|
82
|
+
diesem
|
83
|
+
diesen
|
84
|
+
dieser
|
85
|
+
dieses
|
86
|
+
|
87
|
+
|
88
|
+
doch | (several meanings)
|
89
|
+
dort | (over) there
|
90
|
+
|
91
|
+
|
92
|
+
durch | through
|
93
|
+
|
94
|
+
ein | a
|
95
|
+
eine
|
96
|
+
einem
|
97
|
+
einen
|
98
|
+
einer
|
99
|
+
eines
|
100
|
+
|
101
|
+
einig | some
|
102
|
+
einige
|
103
|
+
einigem
|
104
|
+
einigen
|
105
|
+
einiger
|
106
|
+
einiges
|
107
|
+
|
108
|
+
einmal | once
|
109
|
+
|
110
|
+
er | he
|
111
|
+
ihn | him
|
112
|
+
ihm | to him
|
113
|
+
|
114
|
+
es | it
|
115
|
+
etwas | something
|
116
|
+
|
117
|
+
euer | your
|
118
|
+
eure
|
119
|
+
eurem
|
120
|
+
euren
|
121
|
+
eurer
|
122
|
+
eures
|
123
|
+
|
124
|
+
für | for
|
125
|
+
gegen | towards
|
126
|
+
gewesen | p.p. of sein
|
127
|
+
hab | have
|
128
|
+
habe | have
|
129
|
+
haben | have
|
130
|
+
hat | has
|
131
|
+
hatte | had
|
132
|
+
hatten | had
|
133
|
+
hier | here
|
134
|
+
hin | there
|
135
|
+
hinter | behind
|
136
|
+
|
137
|
+
ich | I
|
138
|
+
mich | me
|
139
|
+
mir | to me
|
140
|
+
|
141
|
+
|
142
|
+
ihr | you, to her
|
143
|
+
ihre
|
144
|
+
ihrem
|
145
|
+
ihren
|
146
|
+
ihrer
|
147
|
+
ihres
|
148
|
+
euch | to you
|
149
|
+
|
150
|
+
im | in + dem
|
151
|
+
in | in
|
152
|
+
indem | while
|
153
|
+
ins | in + das
|
154
|
+
ist | is
|
155
|
+
|
156
|
+
jede | each, every
|
157
|
+
jedem
|
158
|
+
jeden
|
159
|
+
jeder
|
160
|
+
jedes
|
161
|
+
|
162
|
+
jene | that
|
163
|
+
jenem
|
164
|
+
jenen
|
165
|
+
jener
|
166
|
+
jenes
|
167
|
+
|
168
|
+
jetzt | now
|
169
|
+
kann | can
|
170
|
+
|
171
|
+
kein | no
|
172
|
+
keine
|
173
|
+
keinem
|
174
|
+
keinen
|
175
|
+
keiner
|
176
|
+
keines
|
177
|
+
|
178
|
+
können | can
|
179
|
+
könnte | could
|
180
|
+
machen | do
|
181
|
+
man | one
|
182
|
+
|
183
|
+
manche | some, many a
|
184
|
+
manchem
|
185
|
+
manchen
|
186
|
+
mancher
|
187
|
+
manches
|
188
|
+
|
189
|
+
mein | my
|
190
|
+
meine
|
191
|
+
meinem
|
192
|
+
meinen
|
193
|
+
meiner
|
194
|
+
meines
|
195
|
+
|
196
|
+
mit | with
|
197
|
+
muss | must
|
198
|
+
musste | had to
|
199
|
+
nach | to(wards)
|
200
|
+
nicht | not
|
201
|
+
nichts | nothing
|
202
|
+
noch | still, yet
|
203
|
+
nun | now
|
204
|
+
nur | only
|
205
|
+
ob | whether
|
206
|
+
oder | or
|
207
|
+
ohne | without
|
208
|
+
sehr | very
|
209
|
+
|
210
|
+
sein | his
|
211
|
+
seine
|
212
|
+
seinem
|
213
|
+
seinen
|
214
|
+
seiner
|
215
|
+
seines
|
216
|
+
|
217
|
+
selbst | self
|
218
|
+
sich | herself
|
219
|
+
|
220
|
+
sie | they, she
|
221
|
+
ihnen | to them
|
222
|
+
|
223
|
+
sind | are
|
224
|
+
so | so
|
225
|
+
|
226
|
+
solche | such
|
227
|
+
solchem
|
228
|
+
solchen
|
229
|
+
solcher
|
230
|
+
solches
|
231
|
+
|
232
|
+
soll | shall
|
233
|
+
sollte | should
|
234
|
+
sondern | but
|
235
|
+
sonst | else
|
236
|
+
über | over
|
237
|
+
um | about, around
|
238
|
+
und | and
|
239
|
+
|
240
|
+
uns | us
|
241
|
+
unse
|
242
|
+
unsem
|
243
|
+
unsen
|
244
|
+
unser
|
245
|
+
unses
|
246
|
+
|
247
|
+
unter | under
|
248
|
+
viel | much
|
249
|
+
vom | von + dem
|
250
|
+
von | from
|
251
|
+
vor | before
|
252
|
+
während | while
|
253
|
+
war | was
|
254
|
+
waren | were
|
255
|
+
warst | wast
|
256
|
+
was | what
|
257
|
+
weg | away, off
|
258
|
+
weil | because
|
259
|
+
weiter | further
|
260
|
+
|
261
|
+
welche | which
|
262
|
+
welchem
|
263
|
+
welchen
|
264
|
+
welcher
|
265
|
+
welches
|
266
|
+
|
267
|
+
wenn | when
|
268
|
+
werde | will
|
269
|
+
werden | will
|
270
|
+
wie | how
|
271
|
+
wieder | again
|
272
|
+
will | want
|
273
|
+
wir | we
|
274
|
+
wird | will
|
275
|
+
wirst | willst
|
276
|
+
wo | where
|
277
|
+
wollen | want
|
278
|
+
wollte | wanted
|
279
|
+
würde | would
|
280
|
+
würden | would
|
281
|
+
zu | to
|
282
|
+
zum | zu + dem
|
283
|
+
zur | zu + der
|
284
|
+
zwar | indeed
|
285
|
+
zwischen | between
|
286
|
+
|
@@ -0,0 +1,203 @@
|
|
1
|
+
|
2
|
+
| Hungarian stop word list
|
3
|
+
| prepared by Anna Tordai
|
4
|
+
|
5
|
+
a
|
6
|
+
ahogy
|
7
|
+
ahol
|
8
|
+
aki
|
9
|
+
akik
|
10
|
+
akkor
|
11
|
+
alatt
|
12
|
+
által
|
13
|
+
általában
|
14
|
+
amely
|
15
|
+
amelyek
|
16
|
+
amelyekben
|
17
|
+
amelyeket
|
18
|
+
amelyet
|
19
|
+
amelynek
|
20
|
+
ami
|
21
|
+
amit
|
22
|
+
amolyan
|
23
|
+
amíg
|
24
|
+
amikor
|
25
|
+
át
|
26
|
+
abban
|
27
|
+
ahhoz
|
28
|
+
annak
|
29
|
+
arra
|
30
|
+
arról
|
31
|
+
az
|
32
|
+
azok
|
33
|
+
azon
|
34
|
+
azt
|
35
|
+
azzal
|
36
|
+
azért
|
37
|
+
aztán
|
38
|
+
azután
|
39
|
+
azonban
|
40
|
+
bár
|
41
|
+
be
|
42
|
+
belül
|
43
|
+
benne
|
44
|
+
cikk
|
45
|
+
cikkek
|
46
|
+
cikkeket
|
47
|
+
csak
|
48
|
+
de
|
49
|
+
e
|
50
|
+
eddig
|
51
|
+
egész
|
52
|
+
egy
|
53
|
+
egyes
|
54
|
+
egyetlen
|
55
|
+
egyéb
|
56
|
+
egyik
|
57
|
+
egyre
|
58
|
+
ekkor
|
59
|
+
el
|
60
|
+
elég
|
61
|
+
ellen
|
62
|
+
elõ
|
63
|
+
elõször
|
64
|
+
elõtt
|
65
|
+
elsõ
|
66
|
+
én
|
67
|
+
éppen
|
68
|
+
ebben
|
69
|
+
ehhez
|
70
|
+
emilyen
|
71
|
+
ennek
|
72
|
+
erre
|
73
|
+
ez
|
74
|
+
ezt
|
75
|
+
ezek
|
76
|
+
ezen
|
77
|
+
ezzel
|
78
|
+
ezért
|
79
|
+
és
|
80
|
+
fel
|
81
|
+
felé
|
82
|
+
hanem
|
83
|
+
hiszen
|
84
|
+
hogy
|
85
|
+
hogyan
|
86
|
+
igen
|
87
|
+
így
|
88
|
+
illetve
|
89
|
+
ill.
|
90
|
+
ill
|
91
|
+
ilyen
|
92
|
+
ilyenkor
|
93
|
+
ison
|
94
|
+
ismét
|
95
|
+
itt
|
96
|
+
jó
|
97
|
+
jól
|
98
|
+
jobban
|
99
|
+
kell
|
100
|
+
kellett
|
101
|
+
keresztül
|
102
|
+
keressünk
|
103
|
+
ki
|
104
|
+
kívül
|
105
|
+
között
|
106
|
+
közül
|
107
|
+
legalább
|
108
|
+
lehet
|
109
|
+
lehetett
|
110
|
+
legyen
|
111
|
+
lenne
|
112
|
+
lenni
|
113
|
+
lesz
|
114
|
+
lett
|
115
|
+
maga
|
116
|
+
magát
|
117
|
+
majd
|
118
|
+
majd
|
119
|
+
már
|
120
|
+
más
|
121
|
+
másik
|
122
|
+
meg
|
123
|
+
még
|
124
|
+
mellett
|
125
|
+
mert
|
126
|
+
mely
|
127
|
+
melyek
|
128
|
+
mi
|
129
|
+
mit
|
130
|
+
míg
|
131
|
+
miért
|
132
|
+
milyen
|
133
|
+
mikor
|
134
|
+
minden
|
135
|
+
mindent
|
136
|
+
mindenki
|
137
|
+
mindig
|
138
|
+
mint
|
139
|
+
mintha
|
140
|
+
mivel
|
141
|
+
most
|
142
|
+
nagy
|
143
|
+
nagyobb
|
144
|
+
nagyon
|
145
|
+
ne
|
146
|
+
néha
|
147
|
+
nekem
|
148
|
+
neki
|
149
|
+
nem
|
150
|
+
néhány
|
151
|
+
nélkül
|
152
|
+
nincs
|
153
|
+
olyan
|
154
|
+
ott
|
155
|
+
össze
|
156
|
+
õ
|
157
|
+
õk
|
158
|
+
õket
|
159
|
+
pedig
|
160
|
+
persze
|
161
|
+
rá
|
162
|
+
s
|
163
|
+
saját
|
164
|
+
sem
|
165
|
+
semmi
|
166
|
+
sok
|
167
|
+
sokat
|
168
|
+
sokkal
|
169
|
+
számára
|
170
|
+
szemben
|
171
|
+
szerint
|
172
|
+
szinte
|
173
|
+
talán
|
174
|
+
tehát
|
175
|
+
teljes
|
176
|
+
tovább
|
177
|
+
továbbá
|
178
|
+
több
|
179
|
+
úgy
|
180
|
+
ugyanis
|
181
|
+
új
|
182
|
+
újabb
|
183
|
+
újra
|
184
|
+
után
|
185
|
+
utána
|
186
|
+
utolsó
|
187
|
+
vagy
|
188
|
+
vagyis
|
189
|
+
valaki
|
190
|
+
valami
|
191
|
+
valamint
|
192
|
+
való
|
193
|
+
vagyok
|
194
|
+
van
|
195
|
+
vannak
|
196
|
+
volt
|
197
|
+
voltam
|
198
|
+
voltak
|
199
|
+
voltunk
|
200
|
+
vissza
|
201
|
+
vele
|
202
|
+
viszont
|
203
|
+
volna
|