Source

whoosh / tests / test_writing.py

Full commit
  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
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
from __future__ import with_statement
import random, time, threading

import pytest

from whoosh import analysis, fields, query, writing
from whoosh.compat import b, u, xrange, text_type
from whoosh.filedb.filestore import RamStorage
from whoosh.util.testing import TempIndex


def test_no_stored():
    schema = fields.Schema(id=fields.ID, text=fields.TEXT)
    with TempIndex(schema, "nostored") as ix:
        domain = (u("alfa"), u("bravo"), u("charlie"), u("delta"), u("echo"),
                  u("foxtrot"), u("golf"), u("hotel"), u("india"))

        w = ix.writer()
        for i in xrange(20):
            w.add_document(id=text_type(i),
                           text=u(" ").join(random.sample(domain, 5)))
        w.commit()

        with ix.reader() as r:
            assert sorted([int(id) for id in r.lexicon("id")]) == list(range(20))


def test_asyncwriter():
    schema = fields.Schema(id=fields.ID(stored=True), text=fields.TEXT)
    with TempIndex(schema, "asyncwriter") as ix:
        domain = (u("alfa"), u("bravo"), u("charlie"), u("delta"), u("echo"),
                  u("foxtrot"), u("golf"), u("hotel"), u("india"))

        writers = []
        # Simulate doing 20 (near-)simultaneous commits. If we weren't using
        # AsyncWriter, at least some of these would fail because the first
        # writer wouldn't be finished yet.
        for i in xrange(20):
            w = writing.AsyncWriter(ix)
            writers.append(w)
            w.add_document(id=text_type(i),
                           text=u(" ").join(random.sample(domain, 5)))
            w.commit()

        # Wait for all writers to finish before checking the results
        for w in writers:
            if w.running:
                w.join()

        # Check whether all documents made it into the index.
        with ix.reader() as r:
            assert sorted([int(id) for id in r.lexicon("id")]) == list(range(20))


def test_asyncwriter_no_stored():
    schema = fields.Schema(id=fields.ID, text=fields.TEXT)
    with TempIndex(schema, "asyncnostored") as ix:
        domain = (u("alfa"), u("bravo"), u("charlie"), u("delta"), u("echo"),
                  u("foxtrot"), u("golf"), u("hotel"), u("india"))

        writers = []
        # Simulate doing 20 (near-)simultaneous commits. If we weren't using
        # AsyncWriter, at least some of these would fail because the first
        # writer wouldn't be finished yet.
        for i in xrange(20):
            w = writing.AsyncWriter(ix)
            writers.append(w)
            w.add_document(id=text_type(i),
                           text=u(" ").join(random.sample(domain, 5)))
            w.commit()

        # Wait for all writers to finish before checking the results
        for w in writers:
            if w.running:
                w.join()

        # Check whether all documents made it into the index.
        with ix.reader() as r:
            assert sorted([int(id) for id in r.lexicon("id")]) == list(range(20))


def test_updates():
    schema = fields.Schema(id=fields.ID(unique=True, stored=True))
    ix = RamStorage().create_index(schema)
    for _ in xrange(10):
        with ix.writer() as w:
            w.update_document(id=u("a"))
    assert ix.doc_count() == 1


def test_buffered():
    schema = fields.Schema(id=fields.ID, text=fields.TEXT)
    with TempIndex(schema, "buffered") as ix:
        domain = u("alfa bravo charlie delta echo foxtrot golf hotel india")
        domain = domain.split()

        w = writing.BufferedWriter(ix, period=None, limit=10,
                                   commitargs={"merge": False})
        for i in xrange(20):
            w.add_document(id=text_type(i),
                           text=u(" ").join(random.sample(domain, 5)))
        time.sleep(0.1)
        w.close()

        assert len(ix._segments()) == 2


def test_buffered_search():
    schema = fields.Schema(id=fields.STORED, text=fields.TEXT)
    with TempIndex(schema, "bufferedsearch") as ix:
        w = writing.BufferedWriter(ix, period=None, limit=5)
        w.add_document(id=1, text=u("alfa bravo charlie"))
        w.add_document(id=2, text=u("bravo tango delta"))
        w.add_document(id=3, text=u("tango delta echo"))
        w.add_document(id=4, text=u("charlie delta echo"))

        with w.searcher() as s:
            r = s.search(query.Term("text", u("tango")))
            assert sorted([d["id"] for d in r]) == [2, 3]

        w.add_document(id=5, text=u("foxtrot golf hotel"))
        w.add_document(id=6, text=u("india tango juliet"))
        w.add_document(id=7, text=u("tango kilo lima"))
        w.add_document(id=8, text=u("mike november echo"))

        with w.searcher() as s:
            r = s.search(query.Term("text", u("tango")))
            assert sorted([d["id"] for d in r]) == [2, 3, 6, 7]

        w.close()


def test_buffered_update():
    schema = fields.Schema(id=fields.ID(stored=True, unique=True),
                           payload=fields.STORED)
    with TempIndex(schema, "bufferedupdate") as ix:
        w = writing.BufferedWriter(ix, period=None, limit=5)
        for i in xrange(10):
            for char in u("abc"):
                fs = dict(id=char, payload=text_type(i) + char)
                w.update_document(**fs)

        with w.reader() as r:
            sfs = [sf for _, sf in r.iter_docs()]
            sfs = sorted(sfs, key=lambda x: x["id"])
            assert sfs == [{'id': u('a'), 'payload': u('9a')},
                           {'id': u('b'), 'payload': u('9b')},
                           {'id': u('c'), 'payload': u('9c')}]
            assert r.doc_count() == 3

        w.close()


def test_buffered_threads():
    domain = u("alfa bravo charlie delta").split()
    schema = fields.Schema(name=fields.ID(unique=True, stored=True))
    with TempIndex(schema, "buffthreads") as ix:
        class SimWriter(threading.Thread):
            def run(self):
                for _ in xrange(5):
                    w.update_document(name=random.choice(domain))
                    time.sleep(random.uniform(0.01, 0.1))

        w = writing.BufferedWriter(ix, limit=10)
        threads = [SimWriter() for _ in xrange(5)]
        for thread in threads:
            thread.start()
        for thread in threads:
            thread.join()
        w.close()

        with ix.reader() as r:
            assert r.doc_count() == 4
            assert sorted([d["name"] for d in r.all_stored_fields()]) == domain


def test_fractional_weights():
    ana = analysis.RegexTokenizer(r"\S+") | analysis.DelimitedAttributeFilter()

    # With Positions format
    schema = fields.Schema(f=fields.TEXT(analyzer=ana))
    ix = RamStorage().create_index(schema)
    w = ix.writer()
    w.add_document(f=u("alfa^0.5 bravo^1.5 charlie^2.0 delta^1.5"))
    w.commit()

    with ix.searcher() as s:
        wts = []
        for word in s.lexicon("f"):
            p = s.postings("f", word)
            wts.append(p.weight())
        assert wts == [0.5, 1.5, 2.0, 1.5]

    # Try again with Frequency format
    schema = fields.Schema(f=fields.TEXT(analyzer=ana, phrase=False))
    ix = RamStorage().create_index(schema)
    w = ix.writer()
    w.add_document(f=u("alfa^0.5 bravo^1.5 charlie^2.0 delta^1.5"))
    w.commit()

    with ix.searcher() as s:
        wts = []
        for word in s.lexicon("f"):
            p = s.postings("f", word)
            wts.append(p.weight())
        assert wts == [0.5, 1.5, 2.0, 1.5]


def test_cancel_delete():
    schema = fields.Schema(id=fields.ID(stored=True))
    # Single segment
    with TempIndex(schema, "canceldelete1") as ix:
        w = ix.writer()
        for char in u("ABCD"):
            w.add_document(id=char)
        w.commit()

        with ix.reader() as r:
            assert not r.has_deletions()

        w = ix.writer()
        w.delete_document(2)
        w.delete_document(3)
        w.cancel()

        with ix.reader() as r:
            assert not r.has_deletions()
            assert not r.is_deleted(2)
            assert not r.is_deleted(3)

    # Multiple segments
    with TempIndex(schema, "canceldelete2") as ix:
        for char in u("ABCD"):
            w = ix.writer()
            w.add_document(id=char)
            w.commit(merge=False)

        with ix.reader() as r:
            assert not r.has_deletions()

        w = ix.writer()
        w.delete_document(2)
        w.delete_document(3)
        w.cancel()

        with ix.reader() as r:
            assert not r.has_deletions()
            assert not r.is_deleted(2)
            assert not r.is_deleted(3)


def test_delete_nonexistant():
    from whoosh.writing import IndexingError

    schema = fields.Schema(id=fields.ID(stored=True))
    # Single segment
    with TempIndex(schema, "deletenon1") as ix:
        w = ix.writer()
        for char in u("ABC"):
            w.add_document(id=char)
        w.commit()

        try:
            w = ix.writer()
            with pytest.raises(IndexingError):
                w.delete_document(5)
        finally:
            w.cancel()

    # Multiple segments
    with TempIndex(schema, "deletenon1") as ix:
        for char in u("ABC"):
            w = ix.writer()
            w.add_document(id=char)
            w.commit(merge=False)

        try:
            w = ix.writer()
            with pytest.raises(IndexingError):
                w.delete_document(5)
        finally:
            w.cancel()


def test_add_field():
    schema = fields.Schema(a=fields.TEXT)
    with TempIndex(schema, "addfield") as ix:
        with ix.writer() as w:
            w.add_document(a=u("alfa bravo charlie"))
        with ix.writer() as w:
            w.add_field("b", fields.ID(stored=True))
            w.add_field("c*", fields.ID(stored=True), glob=True)
            w.add_document(a=u("delta echo foxtrot"), b=u("india"), cat=u("juliet"))

        with ix.searcher() as s:
            fs = s.document(b=u("india"))
            assert fs == {"b": "india", "cat": "juliet"}


def test_add_reader():
    schema = fields.Schema(i=fields.ID(stored=True, unique=True),
                           a=fields.TEXT(stored=True, spelling=True),
                           b=fields.TEXT(vector=True))
    with TempIndex(schema, "addreader") as ix:
        with ix.writer() as w:
            w.add_document(i=u("0"), a=u("alfa bravo charlie delta"),
                           b=u("able baker coxwell dog"))
            w.add_document(i=u("1"), a=u("bravo charlie delta echo"),
                           b=u("elf fabio gong hiker"))
            w.add_document(i=u("2"), a=u("charlie delta echo foxtrot"),
                           b=u("india joker king loopy"))
            w.add_document(i=u("3"), a=u("delta echo foxtrot golf"),
                           b=u("mister noogie oompah pancake"))

        with ix.writer() as w:
            w.delete_by_term("i", "1")
            w.delete_by_term("i", "3")

        with ix.writer() as w:
            w.add_document(i=u("4"), a=u("hotel india juliet kilo"),
                           b=u("quick rhubarb soggy trap"))
            w.add_document(i=u("5"), a=u("india juliet kilo lima"),
                           b=u("umber violet weird xray"))

        with ix.reader() as r:
            assert r.doc_count_all() == 4

            sfs = list(r.all_stored_fields())
            assert sfs == [{"i": u("4"),
                            "a": u("hotel india juliet kilo")},
                           {"i": u("5"), "a":
                            u("india juliet kilo lima")},
                           {"i": u("0"), "a":
                            u("alfa bravo charlie delta")},
                           {"i": u("2"), "a":
                            u("charlie delta echo foxtrot")},
                           ]

            assert " ".join(r.field_terms("a")) == "alfa bravo charlie delta echo foxtrot hotel india juliet kilo lima"

            vs = []
            for docnum in r.all_doc_ids():
                v = r.vector(docnum, "b")
                vs.append(list(v.all_ids()))
            assert vs == [["quick", "rhubarb", "soggy", "trap"],
                          ["umber", "violet", "weird", "xray"],
                          ["able", "baker", "coxwell", "dog"],
                          ["india", "joker", "king", "loopy"]
                          ]

            gr = r.word_graph("a")
            assert list(gr.flatten_strings()) == ["alfa", "bravo", "charlie",
                                                  "delta", "echo", "foxtrot",
                                                  "hotel", "india", "juliet",
                                                  "kilo", "lima"]


def test_add_reader_spelling():
    # Test whether add_spell_word() items get copied over in a merge

    # Because b is stemming and spelled, it will use add_spell_word()
    ana = analysis.StemmingAnalyzer()
    schema = fields.Schema(a=fields.TEXT(spelling=True),
                           b=fields.TEXT(analyzer=ana, spelling=True))
    with TempIndex(schema, "addreadersp") as ix:
        with ix.writer() as w:
            w.add_document(a=u("rendering modeling compositing enabling"),
                           b=u("rendering modeling compositing enabling"))
            w.add_document(a=u("flying rolling tying quitting polling"),
                           b=u("flying rolling tying quitting polling"))

        with ix.writer() as w:
            w.add_document(a=u("writing eyeing ripping timing yelling"),
                           b=u("writing eyeing ripping timing yelling"))
            w.add_document(a=u("undoing indicating opening pressing"),
                           b=u("undoing indicating opening pressing"))

        with ix.searcher() as s:
            gr = s.reader().word_graph("a")
            assert " ".join(gr.flatten_strings()) == ("compositing enabling eyeing flying indicating "
                                                      "modeling opening polling pressing quitting "
                                                      "rendering ripping rolling timing tying undoing "
                                                      "writing yelling")

            gr = s.reader().word_graph("b")
            assert " ".join(gr.flatten_strings()) == ("compositing enabling eyeing flying indicating "
                                                      "modeling opening polling pressing quitting "
                                                      "rendering ripping rolling timing tying undoing "
                                                      "writing yelling")

def test_clear():
    schema = fields.Schema(a=fields.KEYWORD)
    ix = RamStorage().create_index(schema)

    # Add some segments
    with ix.writer() as w:
        w.add_document(a=u("one two three"))
        w.merge = False
    with ix.writer() as w:
        w.add_document(a=u("two three four"))
        w.merge = False
    with ix.writer() as w:
        w.add_document(a=u("three four five"))
        w.merge = False

    # Clear
    with ix.writer() as w:
        w.add_document(a=u("foo bar baz"))
        w.mergetype = writing.CLEAR

    with ix.searcher() as s:
        assert s.doc_count_all() == 1
        assert list(s.reader().lexicon("a")) == [b("bar"), b("baz"), b("foo")]


def test_spellable_list():
    # Make sure a spellable field works with a list of pre-analyzed tokens

    ana = analysis.StemmingAnalyzer()
    schema = fields.Schema(Location=fields.STORED,Lang=fields.STORED,
                           Title=fields.TEXT(spelling=True, analyzer=ana))
    ix = RamStorage().create_index(schema)

    doc = {'Location': '1000/123', 'Lang': 'E',
           'Title': ['Introduction', 'Numerical', 'Analysis']}

    with ix.writer() as w:
        w.add_document(**doc)


def test_zero_procs():
    schema = fields.Schema(text=fields.TEXT)
    ix = RamStorage().create_index(schema)
    with ix.writer(procs=0) as w:
        assert isinstance(w, writing.IndexWriter)

    with ix.writer(procs=1) as w:
        assert isinstance(w, writing.IndexWriter)