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
|
import six
class Query(object):
"""
Query is used to build complex queries that have more parameters than just the query string.
The query string is set in the constructor, and other options have setter functions.
The setter functions return the query object, so they can be chained,
i.e. `Query("foo").verbatim().filter(...)` etc.
"""
def __init__(self, query_string):
"""
Create a new query object.
The query string is set in the constructor, and other options have setter functions.
"""
self._query_string = query_string
self._offset = 0
self._num = 10
self._no_content = False
self._no_stopwords = False
self._fields = None
self._verbatim = False
self._with_payloads = False
self._with_scores = False
self._filters = list()
self._ids = None
self._slop = -1
self._in_order = False
self._sortby = None
self._return_fields = []
self._summarize_fields = []
self._highlight_fields = []
self._language = None
def query_string(self):
"""
Return the query string of this query only
"""
return self._query_string
def limit_ids(self, *ids):
"""
Limit the results to a specific set of pre-known document ids of any length
"""
self._ids = ids
return self
def return_fields(self, *fields):
"""
Only return values from these fields
"""
self._return_fields = fields
return self
def _mk_field_list(self, fields):
if not fields:
return []
return [fields] if isinstance(fields, six.string_types) else list(fields)
def summarize(self, fields=None, context_len=None, num_frags=None, sep=None):
"""
Return an abridged format of the field, containing only the segments of
the field which contain the matching term(s).
If `fields` is specified, then only the mentioned fields are
summarized; otherwise all results are summarized.
Server side defaults are used for each option (except `fields`) if not specified
- **fields** List of fields to summarize. All fields are summarized if not specified
- **context_len** Amount of context to include with each fragment
- **num_frags** Number of fragments per document
- **sep** Separator string to separate fragments
"""
args = ['SUMMARIZE']
fields = self._mk_field_list(fields)
if fields:
args += ['FIELDS', str(len(fields))] + fields
if context_len is not None:
args += ['LEN', str(context_len)]
if num_frags is not None:
args += ['FRAGS', str(num_frags)]
if sep is not None:
args += ['SEPARATOR', sep]
self._summarize_fields = args
return self
def highlight(self, fields=None, tags=None):
"""
Apply specified markup to matched term(s) within the returned field(s)
- **fields** If specified then only those mentioned fields are highlighted, otherwise all fields are highlighted
- **tags** A list of two strings to surround the match.
"""
args = ['HIGHLIGHT']
fields = self._mk_field_list(fields)
if fields:
args += ['FIELDS', str(len(fields))] + fields
if tags:
args += ['TAGS'] + list(tags)
self._highlight_fields = args
return self
def language(self, language):
"""
Analyze the query as being in the specified language
:param language: The language (e.g. `chinese` or `english`)
"""
self._language = language
return self
def slop(self, slop):
"""
Allow a masimum of N intervening non matched terms between phrase terms (0 means exact phrase)
"""
self._slop = slop
return self
def in_order(self):
"""
Match only documents where the query terms appear in the same order in the document.
i.e. for the query 'hello world', we do not match 'world hello'
"""
self._in_order = True
return self
def get_args(self):
"""
Format the redis arguments for this query and return them
"""
args = [self._query_string]
if self._no_content:
args.append('NOCONTENT')
if self._fields:
args.append('INFIELDS')
args.append(len(self._fields))
args += self._fields
if self._verbatim:
args.append('VERBATIM')
if self._no_stopwords:
args.append('NOSTOPWORDS')
if self._filters:
for flt in self._filters:
assert isinstance(flt, Filter)
args += flt.args
if self._with_payloads:
args.append('WITHPAYLOADS')
if self._with_scores:
args.append('WITHSCORES')
if self._ids:
args.append('INKEYS')
args.append(len(self._ids))
args += self._ids
if self._slop >= 0:
args += ['SLOP', self._slop]
if self._in_order:
args.append('INORDER')
if self._return_fields:
args.append('RETURN')
args.append(len(self._return_fields))
args += self._return_fields
if self._sortby:
assert isinstance(self._sortby, SortbyField)
args.append('SORTBY')
args += self._sortby.args
if self._language:
args += ['LANGUAGE', self._language]
args += self._summarize_fields + self._highlight_fields
args += ["LIMIT", self._offset, self._num]
return args
def paging(self, offset, num):
"""
Set the paging for the query (defaults to 0..10).
- **offset**: Paging offset for the results. Defaults to 0
- **num**: How many results do we want
"""
self._offset = offset
self._num = num
return self
def verbatim(self):
"""
Set the query to be verbatim, i.e. use no query expansion or stemming
"""
self._verbatim = True
return self
def no_content(self):
"""
Set the query to only return ids and not the document content
"""
self._no_content = True
return self
def no_stopwords(self):
"""
Prevent the query from being filtered for stopwords.
Only useful in very big queries that you are certain contain no stopwords.
"""
self._no_stopwords = True
return self
def with_payloads(self):
"""
Ask the engine to return document payloads
"""
self._with_payloads = True
return self
def with_scores(self):
"""
Ask the engine to return document search scores
"""
self._with_scores = True
return self
def limit_fields(self, *fields):
"""
Limit the search to specific TEXT fields only
- **fields**: A list of strings, case sensitive field names from the defined schema
"""
self._fields = fields
return self
def add_filter(self, flt):
"""
Add a numeric or geo filter to the query.
**Currently only one of each filter is supported by the engine**
- **flt**: A NumericFilter or GeoFilter object, used on a corresponding field
"""
self._filters.append(flt)
return self
def sort_by(self, field, asc=True):
"""
Add a sortby field to the query
- **field** - the name of the field to sort by
- **asc** - when `True`, sorting will be done in asceding order
"""
self._sortby = SortbyField(field, asc)
return self
class Filter(object):
def __init__(self, keyword, field, *args):
self.args = [keyword, field] + list(args)
class NumericFilter(Filter):
INF = '+inf'
NEG_INF = '-inf'
def __init__(self, field, minval, maxval, minExclusive = False, maxExclusive = False):
args = [
minval if not minExclusive else '({}'.format(minval),
maxval if not maxExclusive else '({}'.format(maxval),
]
Filter.__init__(self, 'FILTER', field, *args)
class GeoFilter(Filter):
METERS = 'm'
KILOMETERS = 'km'
FEET = 'ft'
MILES = 'mi'
def __init__(self, field, lon, lat, radius, unit = KILOMETERS):
Filter.__init__(self, 'GEOFILTER', field, lon, lat, radius, unit)
class SortbyField(object):
def __init__(self, field, asc=True):
self.args = [field, 'ASC' if asc else 'DESC']
|