MongoDB中单对象大小超16M的存储方案

from pymongo import MongoClient
from gridfs import GridFS
 
client = MongoClient("mongodb://localhost:27017")
db = client.myDatabase
fs = GridFS(db)
 
# 存储文件
with open("large_file.bin", "rb") as f:
    fs.put(f, filename="large_file.bin")

# 读取文件
file_data = fs.get_last_version(filename="large_file.bin")
with open("output.bin", "wb") as f:
    f.write(file_data.read())

{ "_id": "user1", "logs": [ { "timestamp": "2025-01-01", "action": "login" }, ... ] }

// 主文档

{ "_id": "user1", "type": "userMetadata" }

// 子文档

{ "parentId": "user1", "logs": [ { "timestamp": "2025-01-01", "action": "login" }, ... ] }

db.metadata.find({ _id: "user1" });

db.logs.find({ parentId: "user1" });

{ "_id": "project1", "name": "Big Project", "tasks": [ /* 超大量任务数据 */ ] }

// 主文档 
{ "_id": "project1", "name": "Big Project" } 
// 任务文档 
{ "projectId": "project1", "taskId": 1, "taskName": "Task 1", ... }

db.projects.find({ _id: "project1" }); db.tasks.find({ projectId: "project1" });

import zlib
from pymongo import MongoClient
 
client = MongoClient("mongodb://localhost:27017")
db = client.myDatabase
collection = db.myCollection
 
# 压缩存储
data = {"key": "value" * 10000}
compressed_data = zlib.compress(str(data).encode("utf-8"))
collection.insert_one({"_id": "compressed_doc", "data": compressed_data})
 
# 解压读取
doc = collection.find_one({"_id": "compressed_doc"})
decompressed_data = zlib.decompress(doc["data"]).decode("utf-8")

{ "_id": "order1", "customer": { "id": 1, "name": "John Doe" }, "items": [ { "productId": "p1", "productName": "Product 1", "quantity": 2 } ] }

{ "_id": "order1", "customerId": 1, "items": [ { "p": "p1", "q": 2 } ] }