/usr/lib/python3/dist-packages/mongoengine/queryset/base.py is in python3-mongoengine 0.10.6-1.
This file is owned by root:root, with mode 0o644.
The actual contents of the file can be viewed below.
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 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477 1478 1479 1480 1481 1482 1483 1484 1485 1486 1487 1488 1489 1490 1491 1492 1493 1494 1495 1496 1497 1498 1499 1500 1501 1502 1503 1504 1505 1506 1507 1508 1509 1510 1511 1512 1513 1514 1515 1516 1517 1518 1519 1520 1521 1522 1523 1524 1525 1526 1527 1528 1529 1530 1531 1532 1533 1534 1535 1536 1537 1538 1539 1540 1541 1542 1543 1544 1545 1546 1547 1548 1549 1550 1551 1552 1553 1554 1555 1556 1557 1558 1559 1560 1561 1562 1563 1564 1565 1566 1567 1568 1569 1570 1571 1572 1573 1574 1575 1576 1577 1578 1579 1580 1581 1582 1583 1584 1585 1586 1587 1588 1589 1590 1591 1592 1593 1594 1595 1596 1597 1598 1599 1600 1601 1602 1603 1604 1605 1606 1607 1608 1609 1610 1611 1612 1613 1614 1615 1616 1617 1618 1619 1620 1621 1622 1623 1624 1625 1626 1627 1628 1629 1630 1631 1632 1633 1634 1635 1636 1637 1638 1639 1640 1641 1642 1643 1644 1645 1646 1647 1648 1649 1650 1651 1652 1653 1654 1655 1656 1657 1658 1659 1660 1661 1662 1663 1664 1665 1666 1667 1668 1669 1670 1671 1672 1673 1674 1675 1676 1677 1678 1679 1680 1681 1682 1683 1684 1685 1686 1687 1688 1689 1690 1691 1692 1693 1694 1695 1696 1697 1698 1699 1700 1701 1702 1703 1704 1705 1706 1707 1708 1709 1710 1711 1712 1713 1714 1715 1716 1717 1718 1719 1720 1721 1722 1723 1724 1725 1726 1727 1728 1729 1730 1731 1732 1733 1734 1735 1736 1737 1738 1739 1740 1741 1742 1743 1744 1745 1746 1747 1748 1749 1750 1751 1752 1753 1754 1755 1756 1757 1758 1759 1760 1761 1762 1763 1764 1765 1766 1767 1768 1769 1770 1771 1772 1773 1774 1775 1776 1777 1778 1779 1780 1781 1782 1783 1784 1785 1786 1787 1788 1789 1790 1791 1792 1793 1794 1795 1796 1797 1798 1799 1800 1801 1802 1803 1804 1805 1806 1807 1808 1809 1810 1811 1812 1813 1814 1815 1816 1817 1818 1819 1820 | import copy
import itertools
import operator
import pprint
import re
import warnings
from bson import SON
from bson.code import Code
from bson import json_util
import pymongo
import pymongo.errors
from pymongo.common import validate_read_preference
from mongoengine import signals
from mongoengine.connection import get_db
from mongoengine.context_managers import switch_db
from mongoengine.common import _import_class
from mongoengine.base.common import get_document
from mongoengine.errors import (OperationError, NotUniqueError,
InvalidQueryError, LookUpError)
from mongoengine.python_support import IS_PYMONGO_3
from mongoengine.queryset import transform
from mongoengine.queryset.field_list import QueryFieldList
from mongoengine.queryset.visitor import Q, QNode
if IS_PYMONGO_3:
from pymongo.collection import ReturnDocument
__all__ = ('BaseQuerySet', 'DO_NOTHING', 'NULLIFY', 'CASCADE', 'DENY', 'PULL')
# Delete rules
DO_NOTHING = 0
NULLIFY = 1
CASCADE = 2
DENY = 3
PULL = 4
RE_TYPE = type(re.compile(''))
class BaseQuerySet(object):
"""A set of results returned from a query. Wraps a MongoDB cursor,
providing :class:`~mongoengine.Document` objects as the results.
"""
__dereference = False
_auto_dereference = True
def __init__(self, document, collection):
self._document = document
self._collection_obj = collection
self._mongo_query = None
self._query_obj = Q()
self._initial_query = {}
self._where_clause = None
self._loaded_fields = QueryFieldList()
self._ordering = None
self._snapshot = False
self._timeout = True
self._class_check = True
self._slave_okay = False
self._read_preference = None
self._iter = False
self._scalar = []
self._none = False
self._as_pymongo = False
self._as_pymongo_coerce = False
self._search_text = None
# If inheritance is allowed, only return instances and instances of
# subclasses of the class being used
if document._meta.get('allow_inheritance') is True:
if len(self._document._subclasses) == 1:
self._initial_query = {"_cls": self._document._subclasses[0]}
else:
self._initial_query = {
"_cls": {"$in": self._document._subclasses}}
self._loaded_fields = QueryFieldList(always_include=['_cls'])
self._cursor_obj = None
self._limit = None
self._skip = None
self._hint = -1 # Using -1 as None is a valid value for hint
self.only_fields = []
self._max_time_ms = None
def __call__(self, q_obj=None, class_check=True, read_preference=None,
**query):
"""Filter the selected documents by calling the
:class:`~mongoengine.queryset.QuerySet` with a query.
:param q_obj: a :class:`~mongoengine.queryset.Q` object to be used in
the query; the :class:`~mongoengine.queryset.QuerySet` is filtered
multiple times with different :class:`~mongoengine.queryset.Q`
objects, only the last one will be used
:param class_check: If set to False bypass class name check when
querying collection
:param read_preference: if set, overrides connection-level
read_preference from `ReplicaSetConnection`.
:param query: Django-style query keyword arguments
"""
query = Q(**query)
if q_obj:
# make sure proper query object is passed
if not isinstance(q_obj, QNode):
msg = ("Not a query object: %s. "
"Did you intend to use key=value?" % q_obj)
raise InvalidQueryError(msg)
query &= q_obj
if read_preference is None:
queryset = self.clone()
else:
# Use the clone provided when setting read_preference
queryset = self.read_preference(read_preference)
queryset._query_obj &= query
queryset._mongo_query = None
queryset._cursor_obj = None
queryset._class_check = class_check
return queryset
def __getitem__(self, key):
"""Support skip and limit using getitem and slicing syntax.
"""
queryset = self.clone()
# Slice provided
if isinstance(key, slice):
try:
queryset._cursor_obj = queryset._cursor[key]
queryset._skip, queryset._limit = key.start, key.stop
if key.start and key.stop:
queryset._limit = key.stop - key.start
except IndexError as err:
# PyMongo raises an error if key.start == key.stop, catch it,
# bin it, kill it.
start = key.start or 0
if start >= 0 and key.stop >= 0 and key.step is None:
if start == key.stop:
queryset.limit(0)
queryset._skip = key.start
queryset._limit = key.stop - start
return queryset
raise err
# Allow further QuerySet modifications to be performed
return queryset
# Integer index provided
elif isinstance(key, int):
if queryset._scalar:
return queryset._get_scalar(
queryset._document._from_son(queryset._cursor[key],
_auto_dereference=self._auto_dereference,
only_fields=self.only_fields))
if queryset._as_pymongo:
return queryset._get_as_pymongo(queryset._cursor[key])
return queryset._document._from_son(queryset._cursor[key],
_auto_dereference=self._auto_dereference,
only_fields=self.only_fields)
raise AttributeError
def __iter__(self):
raise NotImplementedError
def _has_data(self):
""" Retrieves whether cursor has any data. """
queryset = self.order_by()
return False if queryset.first() is None else True
def __bool__(self):
""" Avoid to open all records in an if stmt in Py2. """
return self._has_data()
def __bool__(self):
""" Avoid to open all records in an if stmt in Py3. """
return self._has_data()
# Core functions
def all(self):
"""Returns all documents."""
return self.__call__()
def filter(self, *q_objs, **query):
"""An alias of :meth:`~mongoengine.queryset.QuerySet.__call__`
"""
return self.__call__(*q_objs, **query)
def search_text(self, text, language=None):
"""
Start a text search, using text indexes.
Require: MongoDB server version 2.6+.
:param language: The language that determines the list of stop words
for the search and the rules for the stemmer and tokenizer.
If not specified, the search uses the default language of the index.
For supported languages, see
`Text Search Languages <http://docs.mongodb.org/manual/reference/text-search-languages/#text-search-languages>`.
"""
queryset = self.clone()
if queryset._search_text:
raise OperationError(
"It is not possible to use search_text two times.")
query_kwargs = SON({'$search': text})
if language:
query_kwargs['$language'] = language
queryset._query_obj &= Q(__raw__={'$text': query_kwargs})
queryset._mongo_query = None
queryset._cursor_obj = None
queryset._search_text = text
return queryset
def get(self, *q_objs, **query):
"""Retrieve the the matching object raising
:class:`~mongoengine.queryset.MultipleObjectsReturned` or
`DocumentName.MultipleObjectsReturned` exception if multiple results
and :class:`~mongoengine.queryset.DoesNotExist` or
`DocumentName.DoesNotExist` if no results are found.
.. versionadded:: 0.3
"""
queryset = self.clone()
queryset = queryset.order_by().limit(2)
queryset = queryset.filter(*q_objs, **query)
try:
result = next(queryset)
except StopIteration:
msg = ("%s matching query does not exist."
% queryset._document._class_name)
raise queryset._document.DoesNotExist(msg)
try:
next(queryset)
except StopIteration:
return result
queryset.rewind()
message = '%d items returned, instead of 1' % queryset.count()
raise queryset._document.MultipleObjectsReturned(message)
def create(self, **kwargs):
"""Create new object. Returns the saved object instance.
.. versionadded:: 0.4
"""
return self._document(**kwargs).save()
def first(self):
"""Retrieve the first object matching the query.
"""
queryset = self.clone()
try:
result = queryset[0]
except IndexError:
result = None
return result
def insert(self, doc_or_docs, load_bulk=True, write_concern=None):
"""bulk insert documents
:param doc_or_docs: a document or list of documents to be inserted
:param load_bulk (optional): If True returns the list of document
instances
:param write_concern: Extra keyword arguments are passed down to
:meth:`~pymongo.collection.Collection.insert`
which will be used as options for the resultant
``getLastError`` command. For example,
``insert(..., {w: 2, fsync: True})`` will wait until at least
two servers have recorded the write and will force an fsync on
each server being written to.
By default returns document instances, set ``load_bulk`` to False to
return just ``ObjectIds``
.. versionadded:: 0.5
"""
Document = _import_class('Document')
if write_concern is None:
write_concern = {}
docs = doc_or_docs
return_one = False
if isinstance(docs, Document) or issubclass(docs.__class__, Document):
return_one = True
docs = [docs]
raw = []
for doc in docs:
if not isinstance(doc, self._document):
msg = ("Some documents inserted aren't instances of %s"
% str(self._document))
raise OperationError(msg)
if doc.pk and not doc._created:
msg = "Some documents have ObjectIds use doc.update() instead"
raise OperationError(msg)
raw.append(doc.to_mongo())
signals.pre_bulk_insert.send(self._document, documents=docs)
try:
ids = self._collection.insert(raw, **write_concern)
except pymongo.errors.DuplicateKeyError as err:
message = 'Could not save document (%s)'
raise NotUniqueError(message % str(err))
except pymongo.errors.OperationFailure as err:
message = 'Could not save document (%s)'
if re.match('^E1100[01] duplicate key', str(err)):
# E11000 - duplicate key error index
# E11001 - duplicate key on update
message = 'Tried to save duplicate unique keys (%s)'
raise NotUniqueError(message % str(err))
raise OperationError(message % str(err))
if not load_bulk:
signals.post_bulk_insert.send(
self._document, documents=docs, loaded=False)
return return_one and ids[0] or ids
documents = self.in_bulk(ids)
results = []
for obj_id in ids:
results.append(documents.get(obj_id))
signals.post_bulk_insert.send(
self._document, documents=results, loaded=True)
return return_one and results[0] or results
def count(self, with_limit_and_skip=False):
"""Count the selected elements in the query.
:param with_limit_and_skip (optional): take any :meth:`limit` or
:meth:`skip` that has been applied to this cursor into account when
getting the count
"""
if self._limit == 0 and with_limit_and_skip or self._none:
return 0
return self._cursor.count(with_limit_and_skip=with_limit_and_skip)
def delete(self, write_concern=None, _from_doc_delete=False, cascade_refs=None):
"""Delete the documents matched by the query.
:param write_concern: Extra keyword arguments are passed down which
will be used as options for the resultant
``getLastError`` command. For example,
``save(..., write_concern={w: 2, fsync: True}, ...)`` will
wait until at least two servers have recorded the write and
will force an fsync on the primary server.
:param _from_doc_delete: True when called from document delete therefore
signals will have been triggered so don't loop.
:returns number of deleted documents
"""
queryset = self.clone()
doc = queryset._document
if write_concern is None:
write_concern = {}
# Handle deletes where skips or limits have been applied or
# there is an untriggered delete signal
has_delete_signal = signals.signals_available and (
signals.pre_delete.has_receivers_for(self._document) or
signals.post_delete.has_receivers_for(self._document))
call_document_delete = (queryset._skip or queryset._limit or
has_delete_signal) and not _from_doc_delete
if call_document_delete:
cnt = 0
for doc in queryset:
doc.delete(**write_concern)
cnt += 1
return cnt
delete_rules = doc._meta.get('delete_rules') or {}
# Check for DENY rules before actually deleting/nullifying any other
# references
for rule_entry in delete_rules:
document_cls, field_name = rule_entry
if document_cls._meta.get('abstract'):
continue
rule = doc._meta['delete_rules'][rule_entry]
if rule == DENY and document_cls.objects(
**{field_name + '__in': self}).count() > 0:
msg = ("Could not delete document (%s.%s refers to it)"
% (document_cls.__name__, field_name))
raise OperationError(msg)
for rule_entry in delete_rules:
document_cls, field_name = rule_entry
if document_cls._meta.get('abstract'):
continue
rule = doc._meta['delete_rules'][rule_entry]
if rule == CASCADE:
cascade_refs = set() if cascade_refs is None else cascade_refs
for ref in queryset:
cascade_refs.add(ref.id)
ref_q = document_cls.objects(**{field_name + '__in': self, 'id__nin': cascade_refs})
ref_q_count = ref_q.count()
if ref_q_count > 0:
ref_q.delete(write_concern=write_concern, cascade_refs=cascade_refs)
elif rule == NULLIFY:
document_cls.objects(**{field_name + '__in': self}).update(
write_concern=write_concern, **{'unset__%s' % field_name: 1})
elif rule == PULL:
document_cls.objects(**{field_name + '__in': self}).update(
write_concern=write_concern,
**{'pull_all__%s' % field_name: self})
result = queryset._collection.remove(queryset._query, **write_concern)
if result:
return result.get("n")
def update(self, upsert=False, multi=True, write_concern=None,
full_result=False, **update):
"""Perform an atomic update on the fields matched by the query.
:param upsert: Any existing document with that "_id" is overwritten.
:param multi: Update multiple documents.
:param write_concern: Extra keyword arguments are passed down which
will be used as options for the resultant
``getLastError`` command. For example,
``save(..., write_concern={w: 2, fsync: True}, ...)`` will
wait until at least two servers have recorded the write and
will force an fsync on the primary server.
:param full_result: Return the full result rather than just the number
updated.
:param update: Django-style update keyword arguments
.. versionadded:: 0.2
"""
if not update and not upsert:
raise OperationError("No update parameters, would remove data")
if write_concern is None:
write_concern = {}
queryset = self.clone()
query = queryset._query
update = transform.update(queryset._document, **update)
# If doing an atomic upsert on an inheritable class
# then ensure we add _cls to the update operation
if upsert and '_cls' in query:
if '$set' in update:
update["$set"]["_cls"] = queryset._document._class_name
else:
update["$set"] = {"_cls": queryset._document._class_name}
try:
result = queryset._collection.update(query, update, multi=multi,
upsert=upsert, **write_concern)
if full_result:
return result
elif result:
return result['n']
except pymongo.errors.DuplicateKeyError as err:
raise NotUniqueError('Update failed (%s)' % str(err))
except pymongo.errors.OperationFailure as err:
if str(err) == 'multi not coded yet':
message = 'update() method requires MongoDB 1.1.3+'
raise OperationError(message)
raise OperationError('Update failed (%s)' % str(err))
def upsert_one(self, write_concern=None, **update):
"""Overwrite or add the first document matched by the query.
:param write_concern: Extra keyword arguments are passed down which
will be used as options for the resultant
``getLastError`` command. For example,
``save(..., write_concern={w: 2, fsync: True}, ...)`` will
wait until at least two servers have recorded the write and
will force an fsync on the primary server.
:param update: Django-style update keyword arguments
:returns the new or overwritten document
.. versionadded:: 0.10.2
"""
atomic_update = self.update(multi=False, upsert=True, write_concern=write_concern,
full_result=True,**update)
if atomic_update['updatedExisting']:
document = self.get()
else:
document = self._document.objects.with_id(atomic_update['upserted'])
return document
def update_one(self, upsert=False, write_concern=None, **update):
"""Perform an atomic update on the fields of the first document
matched by the query.
:param upsert: Any existing document with that "_id" is overwritten.
:param write_concern: Extra keyword arguments are passed down which
will be used as options for the resultant
``getLastError`` command. For example,
``save(..., write_concern={w: 2, fsync: True}, ...)`` will
wait until at least two servers have recorded the write and
will force an fsync on the primary server.
:param update: Django-style update keyword arguments
.. versionadded:: 0.2
"""
return self.update(
upsert=upsert, multi=False, write_concern=write_concern, **update)
def modify(self, upsert=False, full_response=False, remove=False, new=False, **update):
"""Update and return the updated document.
Returns either the document before or after modification based on `new`
parameter. If no documents match the query and `upsert` is false,
returns ``None``. If upserting and `new` is false, returns ``None``.
If the full_response parameter is ``True``, the return value will be
the entire response object from the server, including the 'ok' and
'lastErrorObject' fields, rather than just the modified document.
This is useful mainly because the 'lastErrorObject' document holds
information about the command's execution.
:param upsert: insert if document doesn't exist (default ``False``)
:param full_response: return the entire response object from the
server (default ``False``, not available for PyMongo 3+)
:param remove: remove rather than updating (default ``False``)
:param new: return updated rather than original document
(default ``False``)
:param update: Django-style update keyword arguments
.. versionadded:: 0.9
"""
if remove and new:
raise OperationError("Conflicting parameters: remove and new")
if not update and not upsert and not remove:
raise OperationError(
"No update parameters, must either update or remove")
queryset = self.clone()
query = queryset._query
if not IS_PYMONGO_3 or not remove:
update = transform.update(queryset._document, **update)
sort = queryset._ordering
try:
if IS_PYMONGO_3:
if full_response:
msg = "With PyMongo 3+, it is not possible anymore to get the full response."
warnings.warn(msg, DeprecationWarning)
if remove:
result = queryset._collection.find_one_and_delete(
query, sort=sort, **self._cursor_args)
else:
if new:
return_doc = ReturnDocument.AFTER
else:
return_doc = ReturnDocument.BEFORE
result = queryset._collection.find_one_and_update(
query, update, upsert=upsert, sort=sort, return_document=return_doc,
**self._cursor_args)
else:
result = queryset._collection.find_and_modify(
query, update, upsert=upsert, sort=sort, remove=remove, new=new,
full_response=full_response, **self._cursor_args)
except pymongo.errors.DuplicateKeyError as err:
raise NotUniqueError("Update failed (%s)" % err)
except pymongo.errors.OperationFailure as err:
raise OperationError("Update failed (%s)" % err)
if full_response:
if result["value"] is not None:
result["value"] = self._document._from_son(result["value"], only_fields=self.only_fields)
else:
if result is not None:
result = self._document._from_son(result, only_fields=self.only_fields)
return result
def with_id(self, object_id):
"""Retrieve the object matching the id provided. Uses `object_id` only
and raises InvalidQueryError if a filter has been applied. Returns
`None` if no document exists with that id.
:param object_id: the value for the id of the document to look up
.. versionchanged:: 0.6 Raises InvalidQueryError if filter has been set
"""
queryset = self.clone()
if not queryset._query_obj.empty:
msg = "Cannot use a filter whilst using `with_id`"
raise InvalidQueryError(msg)
return queryset.filter(pk=object_id).first()
def in_bulk(self, object_ids):
"""Retrieve a set of documents by their ids.
:param object_ids: a list or tuple of ``ObjectId``\ s
:rtype: dict of ObjectIds as keys and collection-specific
Document subclasses as values.
.. versionadded:: 0.3
"""
doc_map = {}
docs = self._collection.find({'_id': {'$in': object_ids}},
**self._cursor_args)
if self._scalar:
for doc in docs:
doc_map[doc['_id']] = self._get_scalar(
self._document._from_son(doc, only_fields=self.only_fields))
elif self._as_pymongo:
for doc in docs:
doc_map[doc['_id']] = self._get_as_pymongo(doc)
else:
for doc in docs:
doc_map[doc['_id']] = self._document._from_son(
doc,
only_fields=self.only_fields,
_auto_dereference=self._auto_dereference)
return doc_map
def none(self):
"""Helper that just returns a list"""
queryset = self.clone()
queryset._none = True
return queryset
def no_sub_classes(self):
"""
Only return instances of this document and not any inherited documents
"""
if self._document._meta.get('allow_inheritance') is True:
self._initial_query = {"_cls": self._document._class_name}
return self
def using(self, alias):
"""This method is for controlling which database the QuerySet will be
evaluated against if you are using more than one database.
:param alias: The database alias
.. versionadded:: 0.9
"""
with switch_db(self._document, alias) as cls:
collection = cls._get_collection()
return self.clone_into(self.__class__(self._document, collection))
def clone(self):
"""Creates a copy of the current
:class:`~mongoengine.queryset.QuerySet`
.. versionadded:: 0.5
"""
return self.clone_into(self.__class__(self._document, self._collection_obj))
def clone_into(self, cls):
"""Creates a copy of the current
:class:`~mongoengine.queryset.base.BaseQuerySet` into another child class
"""
if not isinstance(cls, BaseQuerySet):
raise OperationError(
'%s is not a subclass of BaseQuerySet' % cls.__name__)
copy_props = ('_mongo_query', '_initial_query', '_none', '_query_obj',
'_where_clause', '_loaded_fields', '_ordering', '_snapshot',
'_timeout', '_class_check', '_slave_okay', '_read_preference',
'_iter', '_scalar', '_as_pymongo', '_as_pymongo_coerce',
'_limit', '_skip', '_hint', '_auto_dereference',
'_search_text', 'only_fields', '_max_time_ms')
for prop in copy_props:
val = getattr(self, prop)
setattr(cls, prop, copy.copy(val))
if self._cursor_obj:
cls._cursor_obj = self._cursor_obj.clone()
return cls
def select_related(self, max_depth=1):
"""Handles dereferencing of :class:`~bson.dbref.DBRef` objects or
:class:`~bson.object_id.ObjectId` a maximum depth in order to cut down
the number queries to mongodb.
.. versionadded:: 0.5
"""
# Make select related work the same for querysets
max_depth += 1
queryset = self.clone()
return queryset._dereference(queryset, max_depth=max_depth)
def limit(self, n):
"""Limit the number of returned documents to `n`. This may also be
achieved using array-slicing syntax (e.g. ``User.objects[:5]``).
:param n: the maximum number of objects to return
"""
queryset = self.clone()
queryset._limit = n if n != 0 else 1
# Return self to allow chaining
return queryset
def skip(self, n):
"""Skip `n` documents before returning the results. This may also be
achieved using array-slicing syntax (e.g. ``User.objects[5:]``).
:param n: the number of objects to skip before returning results
"""
queryset = self.clone()
queryset._skip = n
return queryset
def hint(self, index=None):
"""Added 'hint' support, telling Mongo the proper index to use for the
query.
Judicious use of hints can greatly improve query performance. When
doing a query on multiple fields (at least one of which is indexed)
pass the indexed field as a hint to the query.
Hinting will not do anything if the corresponding index does not exist.
The last hint applied to this cursor takes precedence over all others.
.. versionadded:: 0.5
"""
queryset = self.clone()
queryset._hint = index
return queryset
def distinct(self, field):
"""Return a list of distinct values for a given field.
:param field: the field to select distinct values from
.. note:: This is a command and won't take ordering or limit into
account.
.. versionadded:: 0.4
.. versionchanged:: 0.5 - Fixed handling references
.. versionchanged:: 0.6 - Improved db_field refrence handling
"""
queryset = self.clone()
try:
field = self._fields_to_dbfields([field]).pop()
finally:
distinct = self._dereference(queryset._cursor.distinct(field), 1,
name=field, instance=self._document)
doc_field = self._document._fields.get(field.split('.', 1)[0])
instance = False
# We may need to cast to the correct type eg. ListField(EmbeddedDocumentField)
EmbeddedDocumentField = _import_class('EmbeddedDocumentField')
ListField = _import_class('ListField')
GenericEmbeddedDocumentField = _import_class('GenericEmbeddedDocumentField')
if isinstance(doc_field, ListField):
doc_field = getattr(doc_field, "field", doc_field)
if isinstance(doc_field, (EmbeddedDocumentField, GenericEmbeddedDocumentField)):
instance = getattr(doc_field, "document_type", False)
# handle distinct on subdocuments
if '.' in field:
for field_part in field.split('.')[1:]:
# if looping on embedded document, get the document type instance
if instance and isinstance(doc_field, (EmbeddedDocumentField, GenericEmbeddedDocumentField)):
doc_field = instance
# now get the subdocument
doc_field = getattr(doc_field, field_part, doc_field)
# We may need to cast to the correct type eg. ListField(EmbeddedDocumentField)
if isinstance(doc_field, ListField):
doc_field = getattr(doc_field, "field", doc_field)
if isinstance(doc_field, (EmbeddedDocumentField, GenericEmbeddedDocumentField)):
instance = getattr(doc_field, "document_type", False)
if instance and isinstance(doc_field, (EmbeddedDocumentField,
GenericEmbeddedDocumentField)):
distinct = [instance(**doc) for doc in distinct]
return distinct
def only(self, *fields):
"""Load only a subset of this document's fields. ::
post = BlogPost.objects(...).only("title", "author.name")
.. note :: `only()` is chainable and will perform a union ::
So with the following it will fetch both: `title` and `author.name`::
post = BlogPost.objects.only("title").only("author.name")
:func:`~mongoengine.queryset.QuerySet.all_fields` will reset any
field filters.
:param fields: fields to include
.. versionadded:: 0.3
.. versionchanged:: 0.5 - Added subfield support
"""
fields = dict([(f, QueryFieldList.ONLY) for f in fields])
self.only_fields = list(fields.keys())
return self.fields(True, **fields)
def exclude(self, *fields):
"""Opposite to .only(), exclude some document's fields. ::
post = BlogPost.objects(...).exclude("comments")
.. note :: `exclude()` is chainable and will perform a union ::
So with the following it will exclude both: `title` and `author.name`::
post = BlogPost.objects.exclude("title").exclude("author.name")
:func:`~mongoengine.queryset.QuerySet.all_fields` will reset any
field filters.
:param fields: fields to exclude
.. versionadded:: 0.5
"""
fields = dict([(f, QueryFieldList.EXCLUDE) for f in fields])
return self.fields(**fields)
def fields(self, _only_called=False, **kwargs):
"""Manipulate how you load this document's fields. Used by `.only()`
and `.exclude()` to manipulate which fields to retrieve. Fields also
allows for a greater level of control for example:
Retrieving a Subrange of Array Elements:
You can use the $slice operator to retrieve a subrange of elements in
an array. For example to get the first 5 comments::
post = BlogPost.objects(...).fields(slice__comments=5)
:param kwargs: A dictionary identifying what to include
.. versionadded:: 0.5
"""
# Check for an operator and transform to mongo-style if there is
operators = ["slice"]
cleaned_fields = []
for key, value in list(kwargs.items()):
parts = key.split('__')
if parts[0] in operators:
op = parts.pop(0)
value = {'$' + op: value}
key = '.'.join(parts)
cleaned_fields.append((key, value))
fields = sorted(cleaned_fields, key=operator.itemgetter(1))
queryset = self.clone()
for value, group in itertools.groupby(fields, lambda x: x[1]):
fields = [field for field, value in group]
fields = queryset._fields_to_dbfields(fields)
queryset._loaded_fields += QueryFieldList(
fields, value=value, _only_called=_only_called)
return queryset
def all_fields(self):
"""Include all fields. Reset all previously calls of .only() or
.exclude(). ::
post = BlogPost.objects.exclude("comments").all_fields()
.. versionadded:: 0.5
"""
queryset = self.clone()
queryset._loaded_fields = QueryFieldList(
always_include=queryset._loaded_fields.always_include)
return queryset
def order_by(self, *keys):
"""Order the :class:`~mongoengine.queryset.QuerySet` by the keys. The
order may be specified by prepending each of the keys by a + or a -.
Ascending order is assumed.
:param keys: fields to order the query results by; keys may be
prefixed with **+** or **-** to determine the ordering direction
"""
queryset = self.clone()
queryset._ordering = queryset._get_order_by(keys)
return queryset
def explain(self, format=False):
"""Return an explain plan record for the
:class:`~mongoengine.queryset.QuerySet`\ 's cursor.
:param format: format the plan before returning it
"""
plan = self._cursor.explain()
if format:
plan = pprint.pformat(plan)
return plan
# DEPRECATED. Has no more impact on PyMongo 3+
def snapshot(self, enabled):
"""Enable or disable snapshot mode when querying.
:param enabled: whether or not snapshot mode is enabled
..versionchanged:: 0.5 - made chainable
.. deprecated:: Ignored with PyMongo 3+
"""
if IS_PYMONGO_3:
msg = "snapshot is deprecated as it has no impact when using PyMongo 3+."
warnings.warn(msg, DeprecationWarning)
queryset = self.clone()
queryset._snapshot = enabled
return queryset
def timeout(self, enabled):
"""Enable or disable the default mongod timeout when querying.
:param enabled: whether or not the timeout is used
..versionchanged:: 0.5 - made chainable
"""
queryset = self.clone()
queryset._timeout = enabled
return queryset
# DEPRECATED. Has no more impact on PyMongo 3+
def slave_okay(self, enabled):
"""Enable or disable the slave_okay when querying.
:param enabled: whether or not the slave_okay is enabled
.. deprecated:: Ignored with PyMongo 3+
"""
if IS_PYMONGO_3:
msg = "slave_okay is deprecated as it has no impact when using PyMongo 3+."
warnings.warn(msg, DeprecationWarning)
queryset = self.clone()
queryset._slave_okay = enabled
return queryset
def read_preference(self, read_preference):
"""Change the read_preference when querying.
:param read_preference: override ReplicaSetConnection-level
preference.
"""
validate_read_preference('read_preference', read_preference)
queryset = self.clone()
queryset._read_preference = read_preference
queryset._cursor_obj = None # we need to re-create the cursor object whenever we apply read_preference
return queryset
def scalar(self, *fields):
"""Instead of returning Document instances, return either a specific
value or a tuple of values in order.
Can be used along with
:func:`~mongoengine.queryset.QuerySet.no_dereference` to turn off
dereferencing.
.. note:: This effects all results and can be unset by calling
``scalar`` without arguments. Calls ``only`` automatically.
:param fields: One or more fields to return instead of a Document.
"""
queryset = self.clone()
queryset._scalar = list(fields)
if fields:
queryset = queryset.only(*fields)
else:
queryset = queryset.all_fields()
return queryset
def values_list(self, *fields):
"""An alias for scalar"""
return self.scalar(*fields)
def as_pymongo(self, coerce_types=False):
"""Instead of returning Document instances, return raw values from
pymongo.
:param coerce_types: Field types (if applicable) would be use to
coerce types.
"""
queryset = self.clone()
queryset._as_pymongo = True
queryset._as_pymongo_coerce = coerce_types
return queryset
def max_time_ms(self, ms):
"""Wait `ms` milliseconds before killing the query on the server
:param ms: the number of milliseconds before killing the query on the server
"""
return self._chainable_method("max_time_ms", ms)
# JSON Helpers
def to_json(self, *args, **kwargs):
"""Converts a queryset to JSON"""
return json_util.dumps(self.as_pymongo(), *args, **kwargs)
def from_json(self, json_data):
"""Converts json data to unsaved objects"""
son_data = json_util.loads(json_data)
return [self._document._from_son(data, only_fields=self.only_fields) for data in son_data]
def aggregate(self, *pipeline, **kwargs):
"""
Perform a aggregate function based in your queryset params
:param pipeline: list of aggregation commands,\
see: http://docs.mongodb.org/manual/core/aggregation-pipeline/
.. versionadded:: 0.9
"""
initial_pipeline = []
if self._query:
initial_pipeline.append({'$match': self._query})
if self._ordering:
initial_pipeline.append({'$sort': dict(self._ordering)})
if self._limit is not None:
initial_pipeline.append({'$limit': self._limit})
if self._skip is not None:
initial_pipeline.append({'$skip': self._skip})
pipeline = initial_pipeline + list(pipeline)
return self._collection.aggregate(pipeline, cursor={}, **kwargs)
# JS functionality
def map_reduce(self, map_f, reduce_f, output, finalize_f=None, limit=None,
scope=None):
"""Perform a map/reduce query using the current query spec
and ordering. While ``map_reduce`` respects ``QuerySet`` chaining,
it must be the last call made, as it does not return a maleable
``QuerySet``.
See the :meth:`~mongoengine.tests.QuerySetTest.test_map_reduce`
and :meth:`~mongoengine.tests.QuerySetTest.test_map_advanced`
tests in ``tests.queryset.QuerySetTest`` for usage examples.
:param map_f: map function, as :class:`~bson.code.Code` or string
:param reduce_f: reduce function, as
:class:`~bson.code.Code` or string
:param output: output collection name, if set to 'inline' will try to
use :class:`~pymongo.collection.Collection.inline_map_reduce`
This can also be a dictionary containing output options
see: http://docs.mongodb.org/manual/reference/command/mapReduce/#dbcmd.mapReduce
:param finalize_f: finalize function, an optional function that
performs any post-reduction processing.
:param scope: values to insert into map/reduce global scope. Optional.
:param limit: number of objects from current query to provide
to map/reduce method
Returns an iterator yielding
:class:`~mongoengine.document.MapReduceDocument`.
.. note::
Map/Reduce changed in server version **>= 1.7.4**. The PyMongo
:meth:`~pymongo.collection.Collection.map_reduce` helper requires
PyMongo version **>= 1.11**.
.. versionchanged:: 0.5
- removed ``keep_temp`` keyword argument, which was only relevant
for MongoDB server versions older than 1.7.4
.. versionadded:: 0.3
"""
queryset = self.clone()
MapReduceDocument = _import_class('MapReduceDocument')
if not hasattr(self._collection, "map_reduce"):
raise NotImplementedError("Requires MongoDB >= 1.7.1")
map_f_scope = {}
if isinstance(map_f, Code):
map_f_scope = map_f.scope
map_f = str(map_f)
map_f = Code(queryset._sub_js_fields(map_f), map_f_scope)
reduce_f_scope = {}
if isinstance(reduce_f, Code):
reduce_f_scope = reduce_f.scope
reduce_f = str(reduce_f)
reduce_f_code = queryset._sub_js_fields(reduce_f)
reduce_f = Code(reduce_f_code, reduce_f_scope)
mr_args = {'query': queryset._query}
if finalize_f:
finalize_f_scope = {}
if isinstance(finalize_f, Code):
finalize_f_scope = finalize_f.scope
finalize_f = str(finalize_f)
finalize_f_code = queryset._sub_js_fields(finalize_f)
finalize_f = Code(finalize_f_code, finalize_f_scope)
mr_args['finalize'] = finalize_f
if scope:
mr_args['scope'] = scope
if limit:
mr_args['limit'] = limit
if output == 'inline' and not queryset._ordering:
map_reduce_function = 'inline_map_reduce'
else:
map_reduce_function = 'map_reduce'
if isinstance(output, str):
mr_args['out'] = output
elif isinstance(output, dict):
ordered_output = []
for part in ('replace', 'merge', 'reduce'):
value = output.get(part)
if value:
ordered_output.append((part, value))
break
else:
raise OperationError("actionData not specified for output")
db_alias = output.get('db_alias')
remaing_args = ['db', 'sharded', 'nonAtomic']
if db_alias:
ordered_output.append(('db', get_db(db_alias).name))
del remaing_args[0]
for part in remaing_args:
value = output.get(part)
if value:
ordered_output.append((part, value))
mr_args['out'] = SON(ordered_output)
results = getattr(queryset._collection, map_reduce_function)(
map_f, reduce_f, **mr_args)
if map_reduce_function == 'map_reduce':
results = results.find()
if queryset._ordering:
results = results.sort(queryset._ordering)
for doc in results:
yield MapReduceDocument(queryset._document, queryset._collection,
doc['_id'], doc['value'])
def exec_js(self, code, *fields, **options):
"""Execute a Javascript function on the server. A list of fields may be
provided, which will be translated to their correct names and supplied
as the arguments to the function. A few extra variables are added to
the function's scope: ``collection``, which is the name of the
collection in use; ``query``, which is an object representing the
current query; and ``options``, which is an object containing any
options specified as keyword arguments.
As fields in MongoEngine may use different names in the database (set
using the :attr:`db_field` keyword argument to a :class:`Field`
constructor), a mechanism exists for replacing MongoEngine field names
with the database field names in Javascript code. When accessing a
field, use square-bracket notation, and prefix the MongoEngine field
name with a tilde (~).
:param code: a string of Javascript code to execute
:param fields: fields that you will be using in your function, which
will be passed in to your function as arguments
:param options: options that you want available to the function
(accessed in Javascript through the ``options`` object)
"""
queryset = self.clone()
code = queryset._sub_js_fields(code)
fields = [queryset._document._translate_field_name(f) for f in fields]
collection = queryset._document._get_collection_name()
scope = {
'collection': collection,
'options': options or {},
}
query = queryset._query
if queryset._where_clause:
query['$where'] = queryset._where_clause
scope['query'] = query
code = Code(code, scope=scope)
db = queryset._document._get_db()
return db.eval(code, *fields)
def where(self, where_clause):
"""Filter ``QuerySet`` results with a ``$where`` clause (a Javascript
expression). Performs automatic field name substitution like
:meth:`mongoengine.queryset.Queryset.exec_js`.
.. note:: When using this mode of query, the database will call your
function, or evaluate your predicate clause, for each object
in the collection.
.. versionadded:: 0.5
"""
queryset = self.clone()
where_clause = queryset._sub_js_fields(where_clause)
queryset._where_clause = where_clause
return queryset
def sum(self, field):
"""Sum over the values of the specified field.
:param field: the field to sum over; use dot-notation to refer to
embedded document fields
.. versionchanged:: 0.5 - updated to map_reduce as db.eval doesnt work
with sharding.
"""
map_func = """
function() {
var path = '{{~%(field)s}}'.split('.'),
field = this;
for (p in path) {
if (typeof field != 'undefined')
field = field[path[p]];
else
break;
}
if (field && field.constructor == Array) {
field.forEach(function(item) {
emit(1, item||0);
});
} else if (typeof field != 'undefined') {
emit(1, field||0);
}
}
""" % dict(field=field)
reduce_func = Code("""
function(key, values) {
var sum = 0;
for (var i in values) {
sum += values[i];
}
return sum;
}
""")
for result in self.map_reduce(map_func, reduce_func, output='inline'):
return result.value
else:
return 0
def aggregate_sum(self, field):
"""Sum over the values of the specified field.
:param field: the field to sum over; use dot-notation to refer to
embedded document fields
This method is more performant than the regular `sum`, because it uses
the aggregation framework instead of map-reduce.
"""
result = self._document._get_collection().aggregate([
{'$match': self._query},
{'$group': {'_id': 'sum', 'total': {'$sum': '$' + field}}}
])
if IS_PYMONGO_3:
result = list(result)
else:
result = result.get('result')
if result:
return result[0]['total']
return 0
def average(self, field):
"""Average over the values of the specified field.
:param field: the field to average over; use dot-notation to refer to
embedded document fields
.. versionchanged:: 0.5 - updated to map_reduce as db.eval doesnt work
with sharding.
"""
map_func = """
function() {
var path = '{{~%(field)s}}'.split('.'),
field = this;
for (p in path) {
if (typeof field != 'undefined')
field = field[path[p]];
else
break;
}
if (field && field.constructor == Array) {
field.forEach(function(item) {
emit(1, {t: item||0, c: 1});
});
} else if (typeof field != 'undefined') {
emit(1, {t: field||0, c: 1});
}
}
""" % dict(field=field)
reduce_func = Code("""
function(key, values) {
var out = {t: 0, c: 0};
for (var i in values) {
var value = values[i];
out.t += value.t;
out.c += value.c;
}
return out;
}
""")
finalize_func = Code("""
function(key, value) {
return value.t / value.c;
}
""")
for result in self.map_reduce(map_func, reduce_func,
finalize_f=finalize_func, output='inline'):
return result.value
else:
return 0
def aggregate_average(self, field):
"""Average over the values of the specified field.
:param field: the field to average over; use dot-notation to refer to
embedded document fields
This method is more performant than the regular `average`, because it
uses the aggregation framework instead of map-reduce.
"""
result = self._document._get_collection().aggregate([
{'$match': self._query},
{'$group': {'_id': 'avg', 'total': {'$avg': '$' + field}}}
])
if IS_PYMONGO_3:
result = list(result)
else:
result = result.get('result')
if result:
return result[0]['total']
return 0
def item_frequencies(self, field, normalize=False, map_reduce=True):
"""Returns a dictionary of all items present in a field across
the whole queried set of documents, and their corresponding frequency.
This is useful for generating tag clouds, or searching documents.
.. note::
Can only do direct simple mappings and cannot map across
:class:`~mongoengine.fields.ReferenceField` or
:class:`~mongoengine.fields.GenericReferenceField` for more complex
counting a manual map reduce call would is required.
If the field is a :class:`~mongoengine.fields.ListField`, the items within
each list will be counted individually.
:param field: the field to use
:param normalize: normalize the results so they add to 1.0
:param map_reduce: Use map_reduce over exec_js
.. versionchanged:: 0.5 defaults to map_reduce and can handle embedded
document lookups
"""
if map_reduce:
return self._item_frequencies_map_reduce(field,
normalize=normalize)
return self._item_frequencies_exec_js(field, normalize=normalize)
# Iterator helpers
def __next__(self):
"""Wrap the result in a :class:`~mongoengine.Document` object.
"""
if self._limit == 0 or self._none:
raise StopIteration
raw_doc = next(self._cursor)
if self._as_pymongo:
return self._get_as_pymongo(raw_doc)
doc = self._document._from_son(raw_doc,
_auto_dereference=self._auto_dereference, only_fields=self.only_fields)
if self._scalar:
return self._get_scalar(doc)
return doc
def rewind(self):
"""Rewind the cursor to its unevaluated state.
.. versionadded:: 0.3
"""
self._iter = False
self._cursor.rewind()
# Properties
@property
def _collection(self):
"""Property that returns the collection object. This allows us to
perform operations only if the collection is accessed.
"""
return self._collection_obj
@property
def _cursor_args(self):
if not IS_PYMONGO_3:
fields_name = 'fields'
cursor_args = {
'timeout': self._timeout,
'snapshot': self._snapshot
}
if self._read_preference is not None:
cursor_args['read_preference'] = self._read_preference
else:
cursor_args['slave_okay'] = self._slave_okay
else:
fields_name = 'projection'
# snapshot is not handled at all by PyMongo 3+
# TODO: evaluate similar possibilities using modifiers
if self._snapshot:
msg = "The snapshot option is not anymore available with PyMongo 3+"
warnings.warn(msg, DeprecationWarning)
cursor_args = {
'no_cursor_timeout': self._timeout
}
if self._loaded_fields:
cursor_args[fields_name] = self._loaded_fields.as_dict()
if self._search_text:
if fields_name not in cursor_args:
cursor_args[fields_name] = {}
cursor_args[fields_name]['_text_score'] = {'$meta': "textScore"}
return cursor_args
@property
def _cursor(self):
if self._cursor_obj is None:
# In PyMongo 3+, we define the read preference on a collection
# level, not a cursor level. Thus, we need to get a cloned
# collection object using `with_options` first.
if IS_PYMONGO_3 and self._read_preference is not None:
self._cursor_obj = self._collection\
.with_options(read_preference=self._read_preference)\
.find(self._query, **self._cursor_args)
else:
self._cursor_obj = self._collection.find(self._query,
**self._cursor_args)
# Apply where clauses to cursor
if self._where_clause:
where_clause = self._sub_js_fields(self._where_clause)
self._cursor_obj.where(where_clause)
if self._ordering:
# Apply query ordering
self._cursor_obj.sort(self._ordering)
elif self._ordering is None and self._document._meta['ordering']:
# Otherwise, apply the ordering from the document model, unless
# it's been explicitly cleared via order_by with no arguments
order = self._get_order_by(self._document._meta['ordering'])
self._cursor_obj.sort(order)
if self._limit is not None:
self._cursor_obj.limit(self._limit)
if self._skip is not None:
self._cursor_obj.skip(self._skip)
if self._hint != -1:
self._cursor_obj.hint(self._hint)
return self._cursor_obj
def __deepcopy__(self, memo):
"""Essential for chained queries with ReferenceFields involved"""
return self.clone()
@property
def _query(self):
if self._mongo_query is None:
self._mongo_query = self._query_obj.to_query(self._document)
if self._class_check and self._initial_query:
if "_cls" in self._mongo_query:
self._mongo_query = {"$and": [self._initial_query, self._mongo_query]}
else:
self._mongo_query.update(self._initial_query)
return self._mongo_query
@property
def _dereference(self):
if not self.__dereference:
self.__dereference = _import_class('DeReference')()
return self.__dereference
def no_dereference(self):
"""Turn off any dereferencing for the results of this queryset.
"""
queryset = self.clone()
queryset._auto_dereference = False
return queryset
# Helper Functions
def _item_frequencies_map_reduce(self, field, normalize=False):
map_func = """
function() {
var path = '{{~%(field)s}}'.split('.');
var field = this;
for (p in path) {
if (typeof field != 'undefined')
field = field[path[p]];
else
break;
}
if (field && field.constructor == Array) {
field.forEach(function(item) {
emit(item, 1);
});
} else if (typeof field != 'undefined') {
emit(field, 1);
} else {
emit(null, 1);
}
}
""" % dict(field=field)
reduce_func = """
function(key, values) {
var total = 0;
var valuesSize = values.length;
for (var i=0; i < valuesSize; i++) {
total += parseInt(values[i], 10);
}
return total;
}
"""
values = self.map_reduce(map_func, reduce_func, 'inline')
frequencies = {}
for f in values:
key = f.key
if isinstance(key, float):
if int(key) == key:
key = int(key)
frequencies[key] = int(f.value)
if normalize:
count = sum(frequencies.values())
frequencies = dict([(k, float(v) / count)
for k, v in list(frequencies.items())])
return frequencies
def _item_frequencies_exec_js(self, field, normalize=False):
"""Uses exec_js to execute"""
freq_func = """
function(path) {
var path = path.split('.');
var total = 0.0;
db[collection].find(query).forEach(function(doc) {
var field = doc;
for (p in path) {
if (field)
field = field[path[p]];
else
break;
}
if (field && field.constructor == Array) {
total += field.length;
} else {
total++;
}
});
var frequencies = {};
var types = {};
var inc = 1.0;
db[collection].find(query).forEach(function(doc) {
field = doc;
for (p in path) {
if (field)
field = field[path[p]];
else
break;
}
if (field && field.constructor == Array) {
field.forEach(function(item) {
frequencies[item] = inc + (isNaN(frequencies[item]) ? 0: frequencies[item]);
});
} else {
var item = field;
types[item] = item;
frequencies[item] = inc + (isNaN(frequencies[item]) ? 0: frequencies[item]);
}
});
return [total, frequencies, types];
}
"""
total, data, types = self.exec_js(freq_func, field)
values = dict([(types.get(k), int(v)) for k, v in data.items()])
if normalize:
values = dict([(k, float(v) / total) for k, v in list(values.items())])
frequencies = {}
for k, v in values.items():
if isinstance(k, float):
if int(k) == k:
k = int(k)
frequencies[k] = v
return frequencies
def _fields_to_dbfields(self, fields):
"""Translate fields paths to its db equivalents"""
ret = []
subclasses = []
document = self._document
if document._meta['allow_inheritance']:
subclasses = [get_document(x)
for x in document._subclasses][1:]
for field in fields:
try:
field = ".".join(f.db_field for f in
document._lookup_field(field.split('.')))
ret.append(field)
except LookUpError as err:
found = False
for subdoc in subclasses:
try:
subfield = ".".join(f.db_field for f in
subdoc._lookup_field(field.split('.')))
ret.append(subfield)
found = True
break
except LookUpError:
pass
if not found:
raise err
return ret
def _get_order_by(self, keys):
"""Creates a list of order by fields
"""
key_list = []
for key in keys:
if not key:
continue
if key == '$text_score':
key_list.append(('_text_score', {'$meta': "textScore"}))
continue
direction = pymongo.ASCENDING
if key[0] == '-':
direction = pymongo.DESCENDING
if key[0] in ('-', '+'):
key = key[1:]
key = key.replace('__', '.')
try:
key = self._document._translate_field_name(key)
except:
pass
key_list.append((key, direction))
if self._cursor_obj and key_list:
self._cursor_obj.sort(key_list)
return key_list
def _get_scalar(self, doc):
def lookup(obj, name):
chunks = name.split('__')
for chunk in chunks:
obj = getattr(obj, chunk)
return obj
data = [lookup(doc, n) for n in self._scalar]
if len(data) == 1:
return data[0]
return tuple(data)
def _get_as_pymongo(self, row):
# Extract which fields paths we should follow if .fields(...) was
# used. If not, handle all fields.
if not getattr(self, '__as_pymongo_fields', None):
self.__as_pymongo_fields = []
for field in self._loaded_fields.fields - set(['_cls']):
self.__as_pymongo_fields.append(field)
while '.' in field:
field, _ = field.rsplit('.', 1)
self.__as_pymongo_fields.append(field)
all_fields = not self.__as_pymongo_fields
def clean(data, path=None):
path = path or ''
if isinstance(data, dict):
new_data = {}
for key, value in data.items():
new_path = '%s.%s' % (path, key) if path else key
if all_fields:
include_field = True
elif self._loaded_fields.value == QueryFieldList.ONLY:
include_field = new_path in self.__as_pymongo_fields
else:
include_field = new_path not in self.__as_pymongo_fields
if include_field:
new_data[key] = clean(value, path=new_path)
data = new_data
elif isinstance(data, list):
data = [clean(d, path=path) for d in data]
else:
if self._as_pymongo_coerce:
# If we need to coerce types, we need to determine the
# type of this field and use the corresponding
# .to_python(...)
from mongoengine.fields import EmbeddedDocumentField
obj = self._document
for chunk in path.split('.'):
obj = getattr(obj, chunk, None)
if obj is None:
break
elif isinstance(obj, EmbeddedDocumentField):
obj = obj.document_type
if obj and data is not None:
data = obj.to_python(data)
return data
return clean(row)
def _sub_js_fields(self, code):
"""When fields are specified with [~fieldname] syntax, where
*fieldname* is the Python name of a field, *fieldname* will be
substituted for the MongoDB name of the field (specified using the
:attr:`name` keyword argument in a field's constructor).
"""
def field_sub(match):
# Extract just the field name, and look up the field objects
field_name = match.group(1).split('.')
fields = self._document._lookup_field(field_name)
# Substitute the correct name for the field into the javascript
return '["%s"]' % fields[-1].db_field
def field_path_sub(match):
# Extract just the field name, and look up the field objects
field_name = match.group(1).split('.')
fields = self._document._lookup_field(field_name)
# Substitute the correct name for the field into the javascript
return ".".join([f.db_field for f in fields])
code = re.sub('\[\s*~([A-z_][A-z_0-9.]+?)\s*\]', field_sub, code)
code = re.sub('\{\{\s*~([A-z_][A-z_0-9.]+?)\s*\}\}', field_path_sub,
code)
return code
def _chainable_method(self, method_name, val):
queryset = self.clone()
method = getattr(queryset._cursor, method_name)
method(val)
setattr(queryset, "_" + method_name, val)
return queryset
# Deprecated
def ensure_index(self, **kwargs):
"""Deprecated use :func:`Document.ensure_index`"""
msg = ("Doc.objects()._ensure_index() is deprecated. "
"Use Doc.ensure_index() instead.")
warnings.warn(msg, DeprecationWarning)
self._document.__class__.ensure_index(**kwargs)
return self
def _ensure_indexes(self):
"""Deprecated use :func:`~Document.ensure_indexes`"""
msg = ("Doc.objects()._ensure_indexes() is deprecated. "
"Use Doc.ensure_indexes() instead.")
warnings.warn(msg, DeprecationWarning)
self._document.__class__.ensure_indexes()
|