-
Notifications
You must be signed in to change notification settings - Fork 2
Expand file tree
/
Copy pathsearch.py
More file actions
223 lines (207 loc) · 7.27 KB
/
search.py
File metadata and controls
223 lines (207 loc) · 7.27 KB
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
from elasticsearch import Elasticsearch
import hug
import re
@hug.response_middleware()
def CORS(request, response, resource):
response.set_header('Access-Control-Allow-Origin', '*')
response.set_header('Access-Control-Allow-Methods', 'GET')
@hug.get('/autocomplete')
def pref(q, fuzzy=False, limit=10, factor=50):
'''
This provides autocomplete suggestions for given query string
parameters :
q: accepts UTF-8 characters. The query string to search against the elasticsearch index.
limit: The number of results to be returned by the API.
factor: A parameter to modify the search sorting based on
the formula factor => Nominatim importance * factor + elasticsearch_score.
fuzzy: Provides results with typo tolerence.
returns :
results: The autocompletion results have the following format
{
"0": {
"addr": "",
...
"place_id": ,
"postcode": ,
"importance": ,
"country_code": ,
"calculated_score":
},
"1": {
...
},
...
}
'''
if q == '':
return
es = Elasticsearch()
# For fuzzy query - For typo tolerence support
if fuzzy == 'True':
print("Fuzzy query")
res = es.search(index="nominatim_sugg", body={
"query": {
"fuzzy": {
"addr": {
"value": q
}
}
},
"sort": {
"_script": {
"type": "number",
"script": {
"source": "doc[\"importance\"].value * params.factor + _score",
"params": {
"factor": 50
}
},
"order": "desc"
}
},
"size": limit
})
hits = res['hits']['hits']
results = {}
for i, hit in enumerate(hits):
hit['_source'].update({"calculated_score": hit['sort'][0]})
results[i] = hit['_source']
return results
terms = []
if type(q) is not list:
q = [q]
for i, term in enumerate(q):
terms += term.strip().split(" ")
# If the query string is a single word, do simple prefix match
if len(terms) == 1:
res = es.search(index="nominatim_sugg", body={
"query": {
"multi_match": {
"query": terms[-1],
"type": "phrase_prefix"
}
},
"sort": {
"_script": {
"type": "number",
"script": {
"lang": "painless",
"source": "doc[\"importance\"].value * " + str(factor) + " + _score",
"params": {
"factor": factor
}
},
"order": "desc"
}
},
"size": limit
})
# If the query string has more than one word, we use tokenization.
# first n-1 words are used to get terms_set matching
# the last word is used to get prefix matching
else:
res = es.search(index="nominatim_sugg", body={
"query": {
"bool": {
"must": [
{
"multi_match": {
"query": terms[-1],
"type": "phrase_prefix"
}
},
{
"terms_set": {
"addr": {
"terms": terms[:-1],
"minimum_should_match_script": {
"source": "params.num_terms"
}
}
}
}
]
}
},
"sort": {
"_script": {
"type": "number",
"script": {
"lang": "painless",
"source": "doc[\"importance\"].value * " + str(factor) + " + _score",
"params": {
"factor": factor
}
},
"order": "desc"
}
},
"size": limit
})
# We modify the results appropriately to return in required format
hits = res['hits']['hits']
results = {}
for i, hit in enumerate(hits):
hit['_source'].update({"calculated_score": hit['sort'][0]})
results[i] = hit['_source']
return results
@hug.get('/prefix_match')
def prefix_match(q, limit=10, factor=50):
'''
This provides prefix match autocomplete suggestions for given query string
parameters :
q: accepts UTF-8 characters. The query string to search against the elasticsearch index.
limit: The number of results to be returned by the API.
factor: A parameter to modify the search sorting based on
the formula factor => Nominatim importance * factor + elasticsearch_score.
returns :
results: The autocompletion results have the following format
{
"0": {
"addr": "",
...
"place_id": ,
"postcode": ,
"importance": ,
"country_code": ,
"calculated_score":
},
"1": {
...
},
...
}
'''
if q == '':
return
es = Elasticsearch()
# Do simple prefix match to fetch suggestions
res = es.search(index="nominatim_sugg", body={
"query": {
"multi_match": {
"query": q,
"type": "phrase_prefix"
}
},
"sort": {
"_script": {
"type": "number",
"script": {
"lang": "painless",
"source": "doc[\"importance\"].value * " + str(factor) + " + _score",
"params": {
"factor": factor
}
},
"order": "desc"
}
},
"size": limit
})
# We modify the results appropriately to return in required format
hits = res['hits']['hits']
results = {}
for i, hit in enumerate(hits):
hit['_source'].update({"calculated_score": hit['sort'][0]})
results[i] = hit['_source']
return results