forked from django-haystack/django-haystack
/
elasticsearch2_backend.py
1045 lines (863 loc) · 39.5 KB
/
elasticsearch2_backend.py
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
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
587
588
589
590
591
592
593
594
595
596
597
598
599
600
601
602
603
604
605
606
607
608
609
610
611
612
613
614
615
616
617
618
619
620
621
622
623
624
625
626
627
628
629
630
631
632
633
634
635
636
637
638
639
640
641
642
643
644
645
646
647
648
649
650
651
652
653
654
655
656
657
658
659
660
661
662
663
664
665
666
667
668
669
670
671
672
673
674
675
676
677
678
679
680
681
682
683
684
685
686
687
688
689
690
691
692
693
694
695
696
697
698
699
700
701
702
703
704
705
706
707
708
709
710
711
712
713
714
715
716
717
718
719
720
721
722
723
724
725
726
727
728
729
730
731
732
733
734
735
736
737
738
739
740
741
742
743
744
745
746
747
748
749
750
751
752
753
754
755
756
757
758
759
760
761
762
763
764
765
766
767
768
769
770
771
772
773
774
775
776
777
778
779
780
781
782
783
784
785
786
787
788
789
790
791
792
793
794
795
796
797
798
799
800
801
802
803
804
805
806
807
808
809
810
811
812
813
814
815
816
817
818
819
820
821
822
823
824
825
826
827
828
829
830
831
832
833
834
835
836
837
838
839
840
841
842
843
844
845
846
847
848
849
850
851
852
853
854
855
856
857
858
859
860
861
862
863
864
865
866
867
868
869
870
871
872
873
874
875
876
877
878
879
880
881
882
883
884
885
886
887
888
889
890
891
892
893
894
895
896
897
898
899
900
901
902
903
904
905
906
907
908
909
910
911
912
913
914
915
916
917
918
919
920
921
922
923
924
925
926
927
928
929
930
931
932
933
934
935
936
937
938
939
940
941
942
943
944
945
946
947
948
949
950
951
952
953
954
955
956
957
958
959
960
961
962
963
964
965
966
967
968
969
970
971
972
973
974
975
976
977
978
979
980
981
982
983
984
985
986
987
988
989
990
991
992
993
994
995
996
997
998
999
1000
# -*- coding: utf-8 -*-
from __future__ import absolute_import, division, print_function, unicode_literals
import datetime
import re
import warnings
from django.conf import settings
from django.core.exceptions import ImproperlyConfigured
from django.utils import six
import haystack
from haystack.backends import BaseEngine, BaseSearchBackend, BaseSearchQuery, log_query
from haystack.constants import DEFAULT_OPERATOR, DJANGO_CT, DJANGO_ID, FUZZY_MAX_EXPANSIONS, FUZZY_MIN_SIM, ID
from haystack.exceptions import MissingDependency, MoreLikeThisError, SkipDocument
from haystack.inputs import Clean, Exact, PythonData, Raw
from haystack.models import SearchResult
from haystack.utils import get_identifier, get_model_ct
from haystack.utils import log as logging
from haystack.utils.app_loading import haystack_get_model
try:
import elasticsearch
if not ((2, 0, 0) <= elasticsearch.__version__ < (3, 0, 0)):
raise ImportError
from elasticsearch.helpers import bulk, scan
from elasticsearch.exceptions import NotFoundError
except ImportError:
raise MissingDependency("The 'elasticsearch2' backend requires the installation of 'elasticsearch>=2.0.0,<3.0.0'. Please refer to the documentation.")
DATETIME_REGEX = re.compile(
r'^(?P<year>\d{4})-(?P<month>\d{2})-(?P<day>\d{2})T'
r'(?P<hour>\d{2}):(?P<minute>\d{2}):(?P<second>\d{2})(\.\d+)?$')
class Elasticsearch2SearchBackend(BaseSearchBackend):
# Word reserved by Elasticsearch for special use.
RESERVED_WORDS = (
'AND',
'NOT',
'OR',
'TO',
)
# Characters reserved by Elasticsearch for special use.
# The '\\' must come first, so as not to overwrite the other slash replacements.
RESERVED_CHARACTERS = (
'\\', '+', '-', '&&', '||', '!', '(', ')', '{', '}',
'[', ']', '^', '"', '~', '*', '?', ':', '/',
)
# Settings to add an n-gram & edge n-gram analyzer.
DEFAULT_SETTINGS = {
'settings': {
"analysis": {
"analyzer": {
"ngram_analyzer": {
"type": "custom",
"tokenizer": "standard",
"filter": ["haystack_ngram", "lowercase"]
},
"edgengram_analyzer": {
"type": "custom",
"tokenizer": "standard",
"filter": ["haystack_edgengram", "lowercase"]
}
},
"tokenizer": {
"haystack_ngram_tokenizer": {
"type": "nGram",
"min_gram": 3,
"max_gram": 15,
},
"haystack_edgengram_tokenizer": {
"type": "edgeNGram",
"min_gram": 2,
"max_gram": 15,
"side": "front"
}
},
"filter": {
"haystack_ngram": {
"type": "nGram",
"min_gram": 3,
"max_gram": 15
},
"haystack_edgengram": {
"type": "edgeNGram",
"min_gram": 2,
"max_gram": 15
}
}
}
}
}
def __init__(self, connection_alias, **connection_options):
super(Elasticsearch2SearchBackend, self).__init__(connection_alias, **connection_options)
if 'URL' not in connection_options:
raise ImproperlyConfigured("You must specify a 'URL' in your settings for connection '%s'." % connection_alias)
if 'INDEX_NAME' not in connection_options:
raise ImproperlyConfigured("You must specify a 'INDEX_NAME' in your settings for connection '%s'." % connection_alias)
self.conn = elasticsearch.Elasticsearch(connection_options['URL'], timeout=self.timeout, **connection_options.get('KWARGS', {}))
self.index_name = connection_options['INDEX_NAME']
self.log = logging.getLogger('haystack')
self.setup_complete = False
self.existing_mapping = {}
self.content_field_name = None
def setup(self):
"""
Defers loading until needed.
"""
# Get the existing mapping & cache it. We'll compare it
# during the ``update`` & if it doesn't match, we'll put the new
# mapping.
try:
self.existing_mapping = self.conn.indices.get_mapping(index=self.index_name)
except NotFoundError:
pass
except Exception:
if not self.silently_fail:
raise
unified_index = haystack.connections[self.connection_alias].get_unified_index()
self.content_field_name, field_mapping = self.build_schema(unified_index.all_searchfields())
current_mapping = {
'modelresult': {
'properties': field_mapping,
}
}
if current_mapping != self.existing_mapping:
try:
# Make sure the index is there first.
self.conn.indices.create(index=self.index_name, body=self.DEFAULT_SETTINGS, ignore=400)
self.conn.indices.put_mapping(index=self.index_name, doc_type='modelresult', body=current_mapping)
self.existing_mapping = current_mapping
except Exception:
if not self.silently_fail:
raise
self.setup_complete = True
def update(self, index, iterable, commit=True):
"""
Updates the backend when given a SearchIndex and a collection of
documents.
:param index: The SearchIndex to update.
:param iterable: The collection of documents.
:param commit: True to refresh the search index after the update.
"""
if not self.setup_complete:
try:
self.setup()
except elasticsearch.TransportError as e:
if not self.silently_fail:
raise
self.log.error("Failed to add documents to Elasticsearch: %s", e, exc_info=True)
return
prepped_docs = []
for obj in iterable:
try:
prepped_data = index.full_prepare(obj)
final_data = {}
# Convert the data to make sure it's happy.
for key, value in prepped_data.items():
final_data[key] = self._from_python(value)
final_data['_id'] = final_data[ID]
prepped_docs.append(final_data)
except SkipDocument:
self.log.debug(u"Indexing for object `%s` skipped", obj)
except elasticsearch.TransportError as e:
if not self.silently_fail:
raise
# We'll log the object identifier but won't include the actual object
# to avoid the possibility of that generating encoding errors while
# processing the log message:
self.log.error(u"%s while preparing object for update" % e.__class__.__name__, exc_info=True,
extra={"data": {"index": index,
"object": get_identifier(obj)}})
bulk(self.conn, prepped_docs, index=self.index_name, doc_type='modelresult')
if commit:
self.conn.indices.refresh(index=self.index_name)
def remove(self, obj_or_string, commit=True):
"""
Removes a document/object from the backend. Can be either a model
instance or the identifier (i.e. ``app_name.model_name.id``) in the
event the object no longer exists.
:param obj_or_string: The model instance or the identifier.
:param commit: True to refresh the search index after the remove.
"""
doc_id = get_identifier(obj_or_string)
if not self.setup_complete:
try:
self.setup()
except elasticsearch.TransportError as e:
if not self.silently_fail:
raise
self.log.error("Failed to remove document '%s' from Elasticsearch: %s", doc_id, e,
exc_info=True)
return
try:
self.conn.delete(index=self.index_name, doc_type='modelresult', id=doc_id, ignore=404)
if commit:
self.conn.indices.refresh(index=self.index_name)
except elasticsearch.TransportError as e:
if not self.silently_fail:
raise
self.log.error("Failed to remove document '%s' from Elasticsearch: %s", doc_id, e, exc_info=True)
def clear(self, models=None, commit=True):
"""
Clears the backend of all documents/objects for a collection of models.
:param models: List or tuple of models to clear.
:param commit: Not used.
"""
if models is not None:
assert isinstance(models, (list, tuple))
try:
if models is None:
self.conn.indices.delete(index=self.index_name, ignore=404)
self.setup_complete = False
self.existing_mapping = {}
self.content_field_name = None
else:
models_to_delete = []
for model in models:
models_to_delete.append("%s:%s" % (DJANGO_CT, get_model_ct(model)))
# Delete using scroll API
query = {'query': {'query_string': {'query': " OR ".join(models_to_delete)}}}
generator = scan(self.conn, query=query, index=self.index_name, doc_type='modelresult')
actions = ({
'_op_type': 'delete',
'_id': doc['_id'],
} for doc in generator)
bulk(self.conn, actions=actions, index=self.index_name, doc_type='modelresult')
self.conn.indices.refresh(index=self.index_name)
except elasticsearch.TransportError as e:
if not self.silently_fail:
raise
if models is not None:
self.log.error("Failed to clear Elasticsearch index of models '%s': %s",
','.join(models_to_delete), e, exc_info=True)
else:
self.log.error("Failed to clear Elasticsearch index: %s", e, exc_info=True)
def build_search_kwargs(self, query_string, sort_by=None, start_offset=0, end_offset=None,
fields='', highlight=False, facets=None,
date_facets=None, query_facets=None,
narrow_queries=None, spelling_query=None,
within=None, dwithin=None, distance_point=None,
models=None, limit_to_registered_models=None,
result_class=None):
index = haystack.connections[self.connection_alias].get_unified_index()
content_field = index.document_field
if query_string == '*:*':
kwargs = {
'query': {
"match_all": {}
},
}
else:
kwargs = {
'query': {
'query_string': {
'default_field': content_field,
'default_operator': DEFAULT_OPERATOR,
'query': query_string,
'analyze_wildcard': True,
'auto_generate_phrase_queries': True,
'fuzzy_min_sim': FUZZY_MIN_SIM,
'fuzzy_max_expansions': FUZZY_MAX_EXPANSIONS,
},
},
}
# so far, no filters
filters = []
if fields:
if isinstance(fields, (list, set)):
fields = " ".join(fields)
kwargs['fields'] = fields
if sort_by is not None:
order_list = []
for field, direction in sort_by:
if field == 'distance' and distance_point:
# Do the geo-enabled sort.
lng, lat = distance_point['point'].get_coords()
sort_kwargs = {
"_geo_distance": {
distance_point['field']: [lng, lat],
"order": direction,
"unit": "km"
}
}
else:
if field == 'distance':
warnings.warn("In order to sort by distance, you must call the '.distance(...)' method.")
# Regular sorting.
sort_kwargs = {field: {'order': direction}}
order_list.append(sort_kwargs)
kwargs['sort'] = order_list
if start_offset is not None:
kwargs['from'] = start_offset
if end_offset is not None:
kwargs['size'] = end_offset - start_offset
if highlight is True:
kwargs['highlight'] = {
'fields': {
content_field: {'store': 'yes'},
}
}
if self.include_spelling:
kwargs['suggest'] = {
'suggest': {
'text': spelling_query or query_string,
'term': {
# Using content_field here will result in suggestions of stemmed words.
'field': '_all',
},
},
}
if narrow_queries is None:
narrow_queries = set()
if facets is not None:
kwargs.setdefault('aggs', {})
for facet_fieldname, extra_options in facets.items():
facet_options = {
'meta': {
'_type': 'terms',
},
'terms': {
'field': facet_fieldname,
}
}
if 'order' in extra_options:
facet_options['meta']['order'] = extra_options.pop('order')
# Special cases for options applied at the facet level (not the terms level).
if extra_options.pop('global_scope', False):
# Renamed "global_scope" since "global" is a python keyword.
facet_options['global'] = True
if 'facet_filter' in extra_options:
facet_options['facet_filter'] = extra_options.pop('facet_filter')
facet_options['terms'].update(extra_options)
kwargs['aggs'][facet_fieldname] = facet_options
if date_facets is not None:
kwargs.setdefault('aggs', {})
for facet_fieldname, value in date_facets.items():
# Need to detect on gap_by & only add amount if it's more than one.
interval = value.get('gap_by').lower()
# Need to detect on amount (can't be applied on months or years).
if value.get('gap_amount', 1) != 1 and interval not in ('month', 'year'):
# Just the first character is valid for use.
interval = "%s%s" % (value['gap_amount'], interval[:1])
kwargs['aggs'][facet_fieldname] = {
'meta': {
'_type': 'date_histogram',
},
'date_histogram': {
'field': facet_fieldname,
'interval': interval,
},
'aggs': {
facet_fieldname: {
'date_range': {
'field': facet_fieldname,
'ranges': [
{
'from': self._from_python(value.get('start_date')),
'to': self._from_python(value.get('end_date')),
}
]
}
}
}
}
if query_facets is not None:
kwargs.setdefault('aggs', {})
for facet_fieldname, value in query_facets:
kwargs['aggs'][facet_fieldname] = {
'meta': {
'_type': 'query',
},
'filter': {
'query_string': {
'query': value,
}
},
}
if limit_to_registered_models is None:
limit_to_registered_models = getattr(settings, 'HAYSTACK_LIMIT_TO_REGISTERED_MODELS', True)
if models and len(models):
model_choices = sorted(get_model_ct(model) for model in models)
elif limit_to_registered_models:
# Using narrow queries, limit the results to only models handled
# with the current routers.
model_choices = self.build_models_list()
else:
model_choices = []
if len(model_choices) > 0:
filters.append({"terms": {DJANGO_CT: model_choices}})
for q in narrow_queries:
filters.append({
'query_string': {
'query': q
}
})
if within is not None:
from haystack.utils.geo import generate_bounding_box
((south, west), (north, east)) = generate_bounding_box(within['point_1'], within['point_2'])
within_filter = {
"geo_bounding_box": {
within['field']: {
"top_left": {
"lat": north,
"lon": west
},
"bottom_right": {
"lat": south,
"lon": east
}
}
},
}
filters.append(within_filter)
if dwithin is not None:
lng, lat = dwithin['point'].get_coords()
# NB: the 1.0.0 release of elasticsearch introduce an
# incompatible change on the distance filter formating
if elasticsearch.VERSION >= (1, 0, 0):
distance = "%(dist).6f%(unit)s" % {
'dist': dwithin['distance'].km,
'unit': "km"
}
else:
distance = dwithin['distance'].km
dwithin_filter = {
"geo_distance": {
"distance": distance,
dwithin['field']: {
"lat": lat,
"lon": lng
}
}
}
filters.append(dwithin_filter)
# if we want to filter, change the query type to filteres
if filters:
kwargs["query"] = {"filtered": {"query": kwargs.pop("query")}}
if len(filters) == 1:
kwargs['query']['filtered']["filter"] = filters[0]
else:
kwargs['query']['filtered']["filter"] = {"bool": {"must": filters}}
return kwargs
@log_query
def search(self, query_string, **kwargs):
if len(query_string) == 0:
return {
'results': [],
'hits': 0,
}
if not self.setup_complete:
self.setup()
search_kwargs = self.build_search_kwargs(query_string, **kwargs)
search_kwargs['from'] = kwargs.get('start_offset', 0)
order_fields = set()
for order in search_kwargs.get('sort', []):
for key in order.keys():
order_fields.add(key)
geo_sort = '_geo_distance' in order_fields
end_offset = kwargs.get('end_offset')
start_offset = kwargs.get('start_offset', 0)
if end_offset is not None and end_offset > start_offset:
search_kwargs['size'] = end_offset - start_offset
try:
raw_results = self.conn.search(body=search_kwargs,
index=self.index_name,
doc_type='modelresult',
_source=True)
except elasticsearch.TransportError as e:
if not self.silently_fail:
raise
self.log.error("Failed to query Elasticsearch using '%s': %s", query_string, e, exc_info=True)
raw_results = {}
return self._process_results(raw_results,
highlight=kwargs.get('highlight'),
result_class=kwargs.get('result_class', SearchResult),
distance_point=kwargs.get('distance_point'),
geo_sort=geo_sort)
def more_like_this(self, model_instance, additional_query_string=None,
start_offset=0, end_offset=None, models=None,
limit_to_registered_models=None, result_class=None, **kwargs):
from haystack import connections
if not self.setup_complete:
self.setup()
# Deferred models will have a different class ("RealClass_Deferred_fieldname")
# which won't be in our registry:
model_klass = model_instance._meta.concrete_model
index = connections[self.connection_alias].get_unified_index().get_index(model_klass)
field_name = index.get_content_field()
params = {}
if start_offset is not None:
params['from_'] = start_offset
if end_offset is not None:
params['size'] = end_offset - start_offset
doc_id = get_identifier(model_instance)
try:
# More like this Query
# https://www.elastic.co/guide/en/elasticsearch/reference/2.2/query-dsl-mlt-query.html
mlt_query = {
'query': {
'more_like_this': {
'fields': [field_name],
'like': [{
"_id": doc_id
}]
}
}
}
narrow_queries = []
if additional_query_string and additional_query_string != '*:*':
additional_filter = {
"query": {
"query_string": {
"query": additional_query_string
}
}
}
narrow_queries.append(additional_filter)
if limit_to_registered_models is None:
limit_to_registered_models = getattr(settings, 'HAYSTACK_LIMIT_TO_REGISTERED_MODELS', True)
if models and len(models):
model_choices = sorted(get_model_ct(model) for model in models)
elif limit_to_registered_models:
# Using narrow queries, limit the results to only models handled
# with the current routers.
model_choices = self.build_models_list()
else:
model_choices = []
if len(model_choices) > 0:
model_filter = {"terms": {DJANGO_CT: model_choices}}
narrow_queries.append(model_filter)
if len(narrow_queries) > 0:
mlt_query = {
"query": {
"filtered": {
'query': mlt_query['query'],
'filter': {
'bool': {
'must': list(narrow_queries)
}
}
}
}
}
raw_results = self.conn.search(
body=mlt_query,
index=self.index_name,
doc_type='modelresult',
_source=True, **params)
except elasticsearch.TransportError as e:
if not self.silently_fail:
raise
self.log.error("Failed to fetch More Like This from Elasticsearch for document '%s': %s",
doc_id, e, exc_info=True)
raw_results = {}
return self._process_results(raw_results, result_class=result_class)
def _process_results(self, raw_results, highlight=False,
result_class=None, distance_point=None,
geo_sort=False):
from haystack import connections
results = []
hits = raw_results.get('hits', {}).get('total', 0)
facets = {}
spelling_suggestion = None
if result_class is None:
result_class = SearchResult
if self.include_spelling and 'suggest' in raw_results:
raw_suggest = raw_results['suggest'].get('suggest')
if raw_suggest:
spelling_suggestion = ' '.join([word['text'] if len(word['options']) == 0 else word['options'][0]['text'] for word in raw_suggest])
if 'aggregations' in raw_results:
facets = {
'fields': {},
'dates': {},
'queries': {},
}
for facet_fieldname, facet_info in raw_results['aggregations'].items():
facet_type = facet_info['meta']['_type']
if facet_type == 'terms':
facets['fields'][facet_fieldname] = [(individual['key'], individual['doc_count']) for individual in facet_info['buckets']]
if 'order' in facet_info['meta']:
if facet_info['meta']['order'] == 'reverse_count':
srt = sorted(facets['fields'][facet_fieldname], key=lambda x: x[1])
facets['fields'][facet_fieldname] = srt
elif facet_type == 'date_histogram':
# Elasticsearch provides UTC timestamps with an extra three
# decimals of precision, which datetime barfs on.
facets['dates'][facet_fieldname] = [(datetime.datetime.utcfromtimestamp(individual['key'] / 1000), individual['doc_count']) for individual in facet_info['buckets']]
elif facet_type == 'query':
facets['queries'][facet_fieldname] = facet_info['doc_count']
unified_index = connections[self.connection_alias].get_unified_index()
indexed_models = unified_index.get_indexed_models()
content_field = unified_index.document_field
for raw_result in raw_results.get('hits', {}).get('hits', []):
source = raw_result['_source']
app_label, model_name = source[DJANGO_CT].split('.')
additional_fields = {}
model = haystack_get_model(app_label, model_name)
if model and model in indexed_models:
for key, value in source.items():
index = unified_index.get_index(model)
string_key = str(key)
if string_key in index.fields and hasattr(index.fields[string_key], 'convert'):
additional_fields[string_key] = index.fields[string_key].convert(value)
else:
additional_fields[string_key] = self._to_python(value)
del(additional_fields[DJANGO_CT])
del(additional_fields[DJANGO_ID])
if 'highlight' in raw_result:
additional_fields['highlighted'] = raw_result['highlight'].get(content_field, '')
if distance_point:
additional_fields['_point_of_origin'] = distance_point
if geo_sort and raw_result.get('sort'):
from haystack.utils.geo import Distance
additional_fields['_distance'] = Distance(km=float(raw_result['sort'][0]))
else:
additional_fields['_distance'] = None
result = result_class(app_label, model_name, source[DJANGO_ID], raw_result['_score'], **additional_fields)
results.append(result)
else:
hits -= 1
return {
'results': results,
'hits': hits,
'facets': facets,
'spelling_suggestion': spelling_suggestion,
}
def build_schema(self, fields):
content_field_name = ''
mapping = {
DJANGO_CT: {'type': 'string', 'index': 'not_analyzed', 'include_in_all': False},
DJANGO_ID: {'type': 'string', 'index': 'not_analyzed', 'include_in_all': False},
}
for field_name, field_class in fields.items():
field_mapping = FIELD_MAPPINGS.get(field_class.field_type, DEFAULT_FIELD_MAPPING).copy()
if field_class.boost != 1.0:
field_mapping['boost'] = field_class.boost
if field_class.document is True:
content_field_name = field_class.index_fieldname
# Do this last to override `text` fields.
if field_mapping['type'] == 'string':
if field_class.indexed is False or hasattr(field_class, 'facet_for'):
field_mapping['index'] = 'not_analyzed'
del field_mapping['analyzer']
mapping[field_class.index_fieldname] = field_mapping
return content_field_name, mapping
def _iso_datetime(self, value):
"""
If value appears to be something datetime-like, return it in ISO format.
Otherwise, return None.
"""
if hasattr(value, 'strftime'):
if hasattr(value, 'hour'):
return value.isoformat()
else:
return '%sT00:00:00' % value.isoformat()
def _from_python(self, value):
"""Convert more Python data types to ES-understandable JSON."""
iso = self._iso_datetime(value)
if iso:
return iso
elif isinstance(value, six.binary_type):
# TODO: Be stricter.
return six.text_type(value, errors='replace')
elif isinstance(value, set):
return list(value)
return value
def _to_python(self, value):
"""Convert values from ElasticSearch to native Python values."""
if isinstance(value, (int, float, complex, list, tuple, bool)):
return value
if isinstance(value, six.string_types):
possible_datetime = DATETIME_REGEX.search(value)
if possible_datetime:
date_values = possible_datetime.groupdict()
for dk, dv in date_values.items():
date_values[dk] = int(dv)
return datetime.datetime(
date_values['year'], date_values['month'],
date_values['day'], date_values['hour'],
date_values['minute'], date_values['second'])
try:
# This is slightly gross but it's hard to tell otherwise what the
# string's original type might have been. Be careful who you trust.
converted_value = eval(value)
# Try to handle most built-in types.
if isinstance(
converted_value,
(int, list, tuple, set, dict, float, complex)):
return converted_value
except Exception:
# If it fails (SyntaxError or its ilk) or we don't trust it,
# continue on.
pass
return value
# DRL_FIXME: Perhaps move to something where, if none of these
# match, call a custom method on the form that returns, per-backend,
# the right type of storage?
DEFAULT_FIELD_MAPPING = {'type': 'string', 'analyzer': 'snowball'}
FIELD_MAPPINGS = {
'edge_ngram': {'type': 'string', 'analyzer': 'edgengram_analyzer'},
'ngram': {'type': 'string', 'analyzer': 'ngram_analyzer'},
'date': {'type': 'date'},
'datetime': {'type': 'date'},
'location': {'type': 'geo_point'},
'boolean': {'type': 'boolean'},
'float': {'type': 'float'},
'long': {'type': 'long'},
'integer': {'type': 'long'},
}
# Sucks that this is almost an exact copy of what's in the Solr backend,
# but we can't import due to dependencies.
class Elasticsearch2SearchQuery(BaseSearchQuery):
def matching_all_fragment(self):
return '*:*'
def build_query_fragment(self, field, filter_type, value):
from haystack import connections
query_frag = ''
if not hasattr(value, 'input_type_name'):
# Handle when we've got a ``ValuesListQuerySet``...
if hasattr(value, 'values_list'):
value = list(value)
if isinstance(value, six.string_types):
# It's not an ``InputType``. Assume ``Clean``.
value = Clean(value)
else:
value = PythonData(value)
# Prepare the query using the InputType.
prepared_value = value.prepare(self)
if not isinstance(prepared_value, (set, list, tuple)):
# Then convert whatever we get back to what pysolr wants if needed.
prepared_value = self.backend._from_python(prepared_value)
# 'content' is a special reserved word, much like 'pk' in
# Django's ORM layer. It indicates 'no special field'.
if field == 'content':
index_fieldname = ''
else:
index_fieldname = u'%s:' % connections[self._using].get_unified_index().get_index_fieldname(field)
filter_types = {
'contains': u'%s',
'startswith': u'%s*',
'exact': u'%s',
'gt': u'{%s TO *}',
'gte': u'[%s TO *]',
'lt': u'{* TO %s}',
'lte': u'[* TO %s]',
'fuzzy': u'%s~',
}
if value.post_process is False:
query_frag = prepared_value
else:
if filter_type in ['contains', 'startswith', 'fuzzy']:
if value.input_type_name == 'exact':
query_frag = prepared_value
else:
# Iterate over terms & incorportate the converted form of each into the query.
terms = []
if isinstance(prepared_value, six.string_types):
for possible_value in prepared_value.split(' '):
terms.append(filter_types[filter_type] % self.backend._from_python(possible_value))
else:
terms.append(filter_types[filter_type] % self.backend._from_python(prepared_value))
if len(terms) == 1:
query_frag = terms[0]
else:
query_frag = u"(%s)" % " AND ".join(terms)
elif filter_type == 'in':
in_options = []
for possible_value in prepared_value:
in_options.append(u'"%s"' % self.backend._from_python(possible_value))
query_frag = u"(%s)" % " OR ".join(in_options)
elif filter_type == 'range':
start = self.backend._from_python(prepared_value[0])
end = self.backend._from_python(prepared_value[1])
query_frag = u'["%s" TO "%s"]' % (start, end)
elif filter_type == 'exact':
if value.input_type_name == 'exact':
query_frag = prepared_value
else:
prepared_value = Exact(prepared_value).prepare(self)
query_frag = filter_types[filter_type] % prepared_value
else:
if value.input_type_name != 'exact':
prepared_value = Exact(prepared_value).prepare(self)
query_frag = filter_types[filter_type] % prepared_value
if len(query_frag) and not isinstance(value, Raw):
if not query_frag.startswith('(') and not query_frag.endswith(')'):
query_frag = "(%s)" % query_frag
return u"%s%s" % (index_fieldname, query_frag)
def build_alt_parser_query(self, parser_name, query_string='', **kwargs):
if query_string:
kwargs['v'] = query_string
kwarg_bits = []
for key in sorted(kwargs.keys()):
if isinstance(kwargs[key], six.string_types) and ' ' in kwargs[key]:
kwarg_bits.append(u"%s='%s'" % (key, kwargs[key]))
else:
kwarg_bits.append(u"%s=%s" % (key, kwargs[key]))
return u"{!%s %s}" % (parser_name, ' '.join(kwarg_bits))
def build_params(self, spelling_query=None, **kwargs):
search_kwargs = {
'start_offset': self.start_offset,
'result_class': self.result_class
}
order_by_list = None
if self.order_by:
if order_by_list is None:
order_by_list = []
for field in self.order_by:
direction = 'asc'
if field.startswith('-'):
direction = 'desc'
field = field[1:]
order_by_list.append((field, direction))
search_kwargs['sort_by'] = order_by_list
if self.date_facets:
search_kwargs['date_facets'] = self.date_facets
if self.distance_point:
search_kwargs['distance_point'] = self.distance_point
if self.dwithin:
search_kwargs['dwithin'] = self.dwithin
if self.end_offset is not None:
search_kwargs['end_offset'] = self.end_offset
if self.facets:
search_kwargs['facets'] = self.facets
if self.fields:
search_kwargs['fields'] = self.fields
if self.highlight:
search_kwargs['highlight'] = self.highlight
if self.models:
search_kwargs['models'] = self.models
if self.narrow_queries:
search_kwargs['narrow_queries'] = self.narrow_queries
if self.query_facets:
search_kwargs['query_facets'] = self.query_facets