有没有办法将嵌套文档结构转换为数组？ 以下是一个例子：
输入
"experience" : { "0" : { "duration" : "3 months", "end" : "August 2012", "organization" : { "0" : { "name" : "Bank of China", "profile_url" : "http://www.linkedin.com/company/13801" } }, "start" : "June 2012", "title" : "Intern Analyst" } },预期产出：
"experience" : [ { "duration" : "3 months", "end" : "August 2012", "organization" : { "0" : { "name" : "Bank of China", "profile_url" : "http://www.linkedin.com/company/13801" } }, "start" : "June 2012", "title" : "Intern Analyst" } ],目前我正在使用脚本迭代每个元素，将它们转换为数组并最终更新文档。 但这需要花费很多时间，有没有更好的方法呢？
Is there a way to convert a nested document structure into an array? Below is an example:
Input
"experience" : { "0" : { "duration" : "3 months", "end" : "August 2012", "organization" : { "0" : { "name" : "Bank of China", "profile_url" : "http://www.linkedin.com/company/13801" } }, "start" : "June 2012", "title" : "Intern Analyst" } },Expected Output:
"experience" : [ { "duration" : "3 months", "end" : "August 2012", "organization" : { "0" : { "name" : "Bank of China", "profile_url" : "http://www.linkedin.com/company/13801" } }, "start" : "June 2012", "title" : "Intern Analyst" } ],Currently I am using a script to iterate over each element, convert them to an array & finally update the document. But it is taking a lot of time, is there a better way of doing this?
最满意答案
您仍然需要迭代内容，但您应该使用批量操作回写：
对于MongoDB 2.6及更高版本：
var bulk = db.collection.initializeUnorderedBulkOp(),
count = 0;
db.collection.find({
"$where": "return !Array.isArray(this.experience)"
}).forEach(function(doc) {
bulk.find({ "_id": doc._id }).updateOne({
"$set": { "experience": [doc.experience["0"]] }
});
count++;
// Write once in 1000 entries
if ( count % 1000 == 0 ) {
bulk.execute();
bulk = db.collection.initializeUnorderedBulkOp();
}
})
// Write the remaining
if ( count % 1000 != 0 )
bulk.execute();
或者在MongoDB 3.2及更高版本的现代版本中， bulkWrite()方法是首选：
var ops = [];
db.collection.find({
"$where": "return !Array.isArray(this.experience)"
}).forEach(function(doc) {
ops.push({
"updateOne": {
"filter": { "_id": doc._id },
"update": { "$set": { "experience": [doc.experience["0"]] } }
}
});
if ( ops.length == 1000 ) {
db.collection.bulkWrite(ops,{ "ordered": false })
ops = [];
}
})
if ( ops.length > 0 )
db.collection.bulkWrite(ops,{ "ordered": false });
因此，当通过游标写回数据库时，使用“无序”设置的批量写入操作是可行的方法。 每批1000个请求只有一个写入/响应，这减少了大量开销，“无序”意味着写入可以并行发生，而不是按顺序发生。 这一切都使它更快。
You still need to iterate over the content, but instead you should be writing back using bulk operations:
Either for MongoDB 2.6 and greater:
var bulk = db.collection.initializeUnorderedBulkOp(),
count = 0;
db.collection.find({
"$where": "return !Array.isArray(this.experience)"
}).forEach(function(doc) {
bulk.find({ "_id": doc._id }).updateOne({
"$set": { "experience": [doc.experience["0"]] }
});
count++;
// Write once in 1000 entries
if ( count % 1000 == 0 ) {
bulk.execute();
bulk = db.collection.initializeUnorderedBulkOp();
}
})
// Write the remaining
if ( count % 1000 != 0 )
bulk.execute();
Or in modern releases of MongoDB 3.2 and greater, the bulkWrite() method is preferred:
var ops = [];
db.collection.find({
"$where": "return !Array.isArray(this.experience)"
}).forEach(function(doc) {
ops.push({
"updateOne": {
"filter": { "_id": doc._id },
"update": { "$set": { "experience": [doc.experience["0"]] } }
}
});
if ( ops.length == 1000 ) {
db.collection.bulkWrite(ops,{ "ordered": false })
ops = [];
}
})
if ( ops.length > 0 )
db.collection.bulkWrite(ops,{ "ordered": false });
So when writing back to the database over a cursor, then bulk write operations with "unordered" set is the way to go. It's only one write/response per batch of 1000 requests, which reduces a lot of overhead, and "unordered" means that writes can happen in parallel rather than in a serial order. It all makes it faster.
更多推荐
发布评论