1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
|
from __future__ import with_statement
from whoosh import analysis, fields, formats
from whoosh.compat import u, xrange, permutations
from whoosh.filedb.filestore import RamStorage
from whoosh.query import spans
from whoosh.query import And, Or, Term, Phrase
from whoosh.util.testing import TempIndex
domain = ("alfa", "bravo", "bravo", "charlie", "delta", "echo")
_ix = None
def get_index():
global _ix
if _ix is not None:
return _ix
charfield = fields.FieldType(formats.Characters(),
analysis.SimpleAnalyzer(),
scorable=True, stored=True)
schema = fields.Schema(text=charfield)
st = RamStorage()
_ix = st.create_index(schema)
w = _ix.writer()
for ls in permutations(domain, 4):
w.add_document(text=u(" ").join(ls), _stored_text=ls)
w.commit()
return _ix
def test_multimatcher():
schema = fields.Schema(content=fields.TEXT(stored=True))
ix = RamStorage().create_index(schema)
domain = ("alfa", "bravo", "charlie", "delta")
for _ in xrange(3):
w = ix.writer()
for ls in permutations(domain):
w.add_document(content=u(" ").join(ls))
w.commit(merge=False)
q = Term("content", "bravo")
with ix.searcher() as s:
m = q.matcher(s)
while m.is_active():
content = s.stored_fields(m.id())["content"].split()
spans = m.spans()
for span in spans:
assert content[span.start] == "bravo"
m.next()
def test_excludematcher():
schema = fields.Schema(content=fields.TEXT(stored=True))
ix = RamStorage().create_index(schema)
domain = ("alfa", "bravo", "charlie", "delta")
for _ in xrange(3):
w = ix.writer()
for ls in permutations(domain):
w.add_document(content=u(" ").join(ls))
w.commit(merge=False)
w = ix.writer()
w.delete_document(5)
w.delete_document(10)
w.delete_document(28)
w.commit(merge=False)
q = Term("content", "bravo")
with ix.searcher() as s:
m = q.matcher(s)
while m.is_active():
content = s.stored_fields(m.id())["content"].split()
spans = m.spans()
for span in spans:
assert content[span.start] == "bravo"
m.next()
def test_span_term():
ix = get_index()
with ix.searcher() as s:
alllists = [d["text"] for d in s.all_stored_fields()]
for word in domain:
q = Term("text", word)
m = q.matcher(s)
ids = set()
while m.is_active():
id = m.id()
sps = m.spans()
ids.add(id)
original = list(s.stored_fields(id)["text"])
assert word in original
if word != "bravo":
assert len(sps) == 1
assert original.index(word) == sps[0].start
assert original.index(word) == sps[0].end
m.next()
for i, ls in enumerate(alllists):
if word in ls:
assert i in ids
else:
assert i not in ids
def test_span_first():
ix = get_index()
with ix.searcher() as s:
for word in domain:
q = spans.SpanFirst(Term("text", word))
m = q.matcher(s)
while m.is_active():
sps = m.spans()
original = s.stored_fields(m.id())["text"]
assert original[0] == word
assert len(sps) == 1
assert sps[0].start == 0
assert sps[0].end == 0
m.next()
q = spans.SpanFirst(Term("text", "bravo"), limit=1)
m = q.matcher(s)
while m.is_active():
orig = s.stored_fields(m.id())["text"]
for sp in m.spans():
assert orig[sp.start] == "bravo"
m.next()
def test_span_near():
ix = get_index()
with ix.searcher() as s:
def test(q):
m = q.matcher(s)
while m.is_active():
yield s.stored_fields(m.id())["text"], m.spans()
m.next()
for orig, sps in test(spans.SpanNear(Term("text", "alfa"),
Term("text", "bravo"),
ordered=True)):
assert orig[sps[0].start] == "alfa"
assert orig[sps[0].end] == "bravo"
for orig, sps in test(spans.SpanNear(Term("text", "alfa"),
Term("text", "bravo"),
ordered=False)):
first = orig[sps[0].start]
second = orig[sps[0].end]
assert ((first == "alfa" and second == "bravo") or (first == "bravo" and second == "alfa"))
for orig, sps in test(spans.SpanNear(Term("text", "bravo"),
Term("text", "bravo"),
ordered=True)):
text = " ".join(orig)
assert text.find("bravo bravo") > -1
q = spans.SpanNear(spans.SpanNear(Term("text", "alfa"),
Term("text", "charlie")),
Term("text", "echo"))
for orig, sps in test(q):
text = " ".join(orig)
assert text.find("alfa charlie echo") > -1
q = spans.SpanNear(Or([Term("text", "alfa"), Term("text", "charlie")]),
Term("text", "echo"), ordered=True)
for orig, sps in test(q):
text = " ".join(orig)
assert (text.find("alfa echo") > -1
or text.find("charlie echo") > -1)
def test_near_unordered():
schema = fields.Schema(text=fields.TEXT(stored=True))
st = RamStorage()
ix = st.create_index(schema)
w = ix.writer()
w.add_document(text=u("alfa bravo charlie delta echo"))
w.add_document(text=u("alfa bravo delta echo charlie"))
w.add_document(text=u("alfa charlie bravo delta echo"))
w.add_document(text=u("echo delta alfa foxtrot"))
w.commit()
with ix.searcher() as s:
q = spans.SpanNear(Term("text", "bravo"), Term("text", "charlie"),
ordered=False)
r = sorted(d["text"] for d in s.search(q))
assert r == [u('alfa bravo charlie delta echo'), u('alfa charlie bravo delta echo')]
def test_span_near_tree():
ana = analysis.SimpleAnalyzer()
schema = fields.Schema(text=fields.TEXT(analyzer=ana, stored=True))
st = RamStorage()
ix = st.create_index(schema)
w = ix.writer()
w.add_document(text=u("The Lucene library is by Doug Cutting and Whoosh " +
"was made by Matt Chaput"))
w.commit()
nq1 = spans.SpanNear(Term("text", "lucene"), Term("text", "doug"), slop=5)
nq2 = spans.SpanNear(nq1, Term("text", "whoosh"), slop=4)
with ix.searcher() as s:
m = nq2.matcher(s)
assert m.spans() == [spans.Span(1, 8)]
def test_spannear2():
schema = fields.Schema(id=fields.STORED, text=fields.TEXT)
with TempIndex(schema) as ix:
with ix.writer() as w:
w.add_document(id="a", text=u"alfa echo")
w.add_document(id="b", text=u"alfa bravo echo")
w.add_document(id="c", text=u"alfa bravo charlie echo")
w.add_document(id="d", text=u"alfa bravo charlie delta echo")
w.add_document(id="e", text=u"alfa bravo charlie fox delta echo")
w.add_document(id="f", text=u"charlie delta echo fox golf hotel")
with ix.searcher() as s:
q = spans.SpanNear2([Term("text", "bravo"), Term("text", "echo")],
slop=3)
assert q.estimate_size(s.reader()) == 4
ids = "".join(sorted(hit["id"] for hit in s.search(q)))
assert ids == "bcd"
def test_span_not():
ix = get_index()
with ix.searcher() as s:
nq = spans.SpanNear(Term("text", "alfa"), Term("text", "charlie"),
slop=2)
bq = Term("text", "bravo")
q = spans.SpanNot(nq, bq)
m = q.matcher(s)
while m.is_active():
orig = list(s.stored_fields(m.id())["text"])
i1 = orig.index("alfa")
i2 = orig.index("charlie")
dist = i2 - i1
assert 0 < dist < 3
if "bravo" in orig:
assert orig.index("bravo") != i1 + 1
m.next()
def test_span_or():
ix = get_index()
with ix.searcher() as s:
nq = spans.SpanNear(Term("text", "alfa"), Term("text", "charlie"),
slop=2)
bq = Term("text", "bravo")
q = spans.SpanOr([nq, bq])
m = q.matcher(s)
while m.is_active():
orig = s.stored_fields(m.id())["text"]
assert ("alfa" in orig and "charlie" in orig) or "bravo" in orig
m.next()
def test_span_contains():
ix = get_index()
with ix.searcher() as s:
nq = spans.SpanNear(Term("text", "alfa"), Term("text", "charlie"),
slop=3)
cq = spans.SpanContains(nq, Term("text", "echo"))
m = cq.matcher(s)
ls = []
while m.is_active():
orig = s.stored_fields(m.id())["text"]
ls.append(" ".join(orig))
m.next()
ls.sort()
assert ls == ['alfa bravo echo charlie', 'alfa bravo echo charlie',
'alfa delta echo charlie', 'alfa echo bravo charlie',
'alfa echo bravo charlie', 'alfa echo charlie bravo',
'alfa echo charlie bravo', 'alfa echo charlie delta',
'alfa echo delta charlie', 'bravo alfa echo charlie',
'bravo alfa echo charlie', 'delta alfa echo charlie',
]
def test_span_before():
ix = get_index()
with ix.searcher() as s:
bq = spans.SpanBefore(Term("text", "alfa"), Term("text", "charlie"))
m = bq.matcher(s)
while m.is_active():
orig = list(s.stored_fields(m.id())["text"])
assert "alfa" in orig
assert "charlie" in orig
assert orig.index("alfa") < orig.index("charlie")
m.next()
def test_span_condition():
ix = get_index()
with ix.searcher() as s:
sc = spans.SpanCondition(Term("text", "alfa"), Term("text", "charlie"))
m = sc.matcher(s)
while m.is_active():
orig = list(s.stored_fields(m.id())["text"])
assert "alfa" in orig
assert "charlie" in orig
for span in m.spans():
assert orig[span.start] == "alfa"
m.next()
def test_regular_or():
ix = get_index()
with ix.searcher() as s:
oq = Or([Term("text", "bravo"), Term("text", "alfa")])
m = oq.matcher(s)
while m.is_active():
orig = s.stored_fields(m.id())["text"]
for span in m.spans():
v = orig[span.start]
assert v == "bravo" or v == "alfa"
m.next()
def test_regular_and():
ix = get_index()
with ix.searcher() as s:
aq = And([Term("text", "bravo"), Term("text", "alfa")])
m = aq.matcher(s)
while m.is_active():
orig = s.stored_fields(m.id())["text"]
for span in m.spans():
v = orig[span.start]
assert v == "bravo" or v == "alfa"
m.next()
def test_span_characters():
ix = get_index()
with ix.searcher() as s:
pq = Phrase("text", ["bravo", "echo"])
m = pq.matcher(s)
while m.is_active():
orig = " ".join(s.stored_fields(m.id())["text"])
for span in m.spans():
startchar, endchar = span.startchar, span.endchar
assert orig[startchar:endchar] == "bravo echo"
m.next()
|
