您需要循环光标并使用$set
更新运算符。当然,要做到这一点,您可以使用“批量”操作来实现最大效率。话虽这么说,该方法会根据您的 MongoDB 服务器版本和 PyMongo 版本而有所不同。
从 MongoDB 3.2 开始,您需要使用批量写操作 https://docs.mongodb.org/manual/core/bulk-write-operations/#bulk-write-operations和bulkWrite() https://docs.mongodb.org/manual/reference/method/db.collection.bulkWrite/#db.collection.bulkWrite method.
var requests = [];
var cursor = db.collection.find( { "field.1": { "$exists": true } }, { "field": 1 } );
cursor.forEach( document => {
requests.push({
"updateOne": {
"filter" : { "_id": document._id },
"update" : { "field": { "$set": document.field[0] } }
}
});
if (requests.length === 1000) {
db.collection.bulkWrite(requests);
requests = [];
}
});
if (requests.length > 0) {
db.collection.bulkWrite(requests);
}
此查询使用 PyMongo 3.0 驱动程序,它提供了您需要使用的bulk_write() https://api.mongodb.org/python/current/api/pymongo/collection.html#pymongo.collection.Collection.bulk_write方法给出以下内容:
from pymongo import UpdateOne
requests = [];
cursor = db.collection.find({"field.1": {"$exists": True}}, {"field": 1})
for document in cursor:
requests.append(UpdateOne({'_id': document['_id']}, {'$set': {'field': document['field'][0]}}))
if len(requests) == 1000:
# Execute per 1000 operations
db.collection.bulk_write(requests)
requests = []
if len(requests) > 0:
# clean up queues
db.collection.bulk_write(requests)
从 MongoDB 2.6 开始,您需要使用现已弃用的Bulk https://docs.mongodb.org/manual/reference/method/Bulk/#bulk API.
var bulk = db.collection.initializeUnorderedBulkOp();
var count = 0;
// cursor is the same as in the previous version using MongoDB 3.2
cursor.forEach(function(document) {
bulk.find( { "_id": document._id } ).updateOne( { "$set": { "field": document.field[0] } } );
count++;
if (count % 1000 === 0) {
bulk.execute();
bulk = db.collection.initializedUnorderedBulkOp();
}
});
// Again clean up queues
if (count > 0 ) {
bulk.execute();
}
翻译成Python给出以下内容。
bulk = db.collection.initialize_unordered_bulk_op()
count = 0
for doc in cursor:
bulk.find({'_id': doc['_id']}).update_one({'$set': {'field': doc['field'][0]}})
count = count + 1
if count == 1000:
bulk.execute()
bulk = db.collection.initialize_unordered_bulk_op()
if count > 0:
bulk.execute()