用Golang和PHP生成mongodb的24位的id
mongodb id的用途
- 在分布式存储上作为全局唯一id使用；
- mogodb转为其他数据库，比如pgsql时，沿用原先的id规则；
- 需要隐藏真实数量的地方，比如用mysql存储用户，其自增id很容易看出用户数量；
- 防止某种形式的机器攻击，比如根据mysql、pgsql等自增id很容易通过机器生成url，在做采集时很方便。
mongodb的生成规则
mongodb根据版本不同，生成规则有部分调整，不同的地方在中间的10位（5 byte）。根据mongodb的文档，在mongodb3.2以下的ObjectId生成规则：8位的时间戳 + 6位的机器标志 + 4位的进程id + 6位的自增计数
a 4-byte value representing the seconds since the Unix epoch,
a 3-byte machine identifier,
a 2-byte process id, and
a 3-byte counter, starting with a random value.
mongodb3.4及以上的版本的ObjectId生成规则：8位的时间戳 + 10位的随机码 + 6位的自增计数
a 4-byte timestamp value, representing the ObjectId’s creation, measured in seconds since the Unix epoch
a 5-byte random value
a 3-byte incrementing counter, initialized to a random value
PHP生成mongodb id
下列算法是mongodb3.2之前的ObjectId生成算法，来自于网上，参考注释部分
/**
* 生成mongodb3.2级以下版本的mongo ObjectId，用于获得某个数据表的字符串自增id（全局唯一），每个数据表的起始id都是1。id的组成结构参考下列信息：
*
* Generate an ID, constructed using:
* a 4-byte value representing the seconds since the Unix epoch,
* a 3-byte machine identifier,
* a 2-byte process id, and
* a 3-byte counter, starting with a random value.
* Just like a MongoId string.
*
* @link http://docs.mongodb.org/manual/reference/object-id/
* @author http://luokr.com/p/16
* @param int $lastId 上一个id，当不提供（值为null时，系统自动从1开始）
* @return string 24 hexidecimal characters
*/
function uniqId($lastId = 0) {
return sprintf(
"%08x%06x%04x%06x",
/* 4-byte value representing the seconds since the Unix epoch. */
time() & 0xFFFFFFFF,
/* 3-byte machine identifier.
*
* On windows, the max length is 256. Linux doesn't have a limit, but it
* will fill in the first 256 chars of hostname even if the actual
* hostname is longer.
*
* From the GNU manual:
* gethostname stores the beginning of the host name in name even if the
* host name won't entirely fit. For some purposes, a truncated host name
* is good enough. If it is, you can ignore the error code.
*
* crc32 will be better than Times33. */
crc32(substr((string)gethostname(), 0, 256)) >> 8 & 0xFFFFFF,
/* 2-byte process id. */
getmypid() & 0xFFFF,
/* 3-byte counter, starting with a random value. */
$lastId = $lastId > 0xFFFFFE ? 1 : $lastId + 1
);
}下列php代码用于生成mongodb3.4级以上版本的ObjectId
/**
* 生成mongodb3.4及以上版本的mongo ObjectId.
* 用于获得某个数据表的字符串自增id（全局唯一），每个数据表的起始id都是1。id的组成结构参考下列信息：
*
* @author https://insuns.com
* @param int $lastId
*
* @return string
*/
function uniqId4($lastId = 0) {
return sprintf(
"%08x%010x%06x",
// a 4-byte timestamp value, representing the ObjectId’s creation, measured in seconds since the Unix epoch
time() & 0xFFFFFFFF,
//a 5-byte random value
// ！！！这个值应该从存储到缓存，每次从缓存获取！！！
mt_rand(0, 0xFFFFFFFFFF) ,
//a 3-byte incrementing counter, initialized to a random value
$lastId = $lastId > 0xFFFFFE ? 1 : $lastId + 1
);
}golang生成mongodb ObjectId
测试地址：https://play.golang.org/p/zS8-r8kikbm
注意：go playground中生成mongodb3.4以上版本的id每次都一样，经观察应该是随机数生成一致的原因，本人本机测试没问题。
/**
* 生成全局唯一的24位id
* File: uuid.go
* Package: uuid
* Author: /blog/YongGOLANGHePHPShengChengMONGODBDe24WeiDeID/5.html
* Date: 2021-03-03 09:52:04
*/
package uuid
import (
"fmt"
"hash/crc32"
"math/rand"
"os"
"time"
)
//GetUniqueId 生成mongodb3.2以下版本的mongo ObjectId.
//用于获得某个数据表的字符串自增id（全局唯一），每个数据表的起始id都是1。id的组成结构参考下列信息：
//
// Generate an ID, constructed using:
// a 4-byte value representing the seconds since the Unix epoch,
// a 3-byte machine identifier,
// a 2-byte process id, and
// a 3-byte counter, starting with a random value.
// Just like a MongoId string.
func GetUniqueId(lastID ...int64) string {
var currentId int64 = 1
if len(lastID) > 0 && lastID[0] < 0xFFFFFF {
currentId = lastID[0] + 1
}
host, err := os.Hostname()
if err != nil {
host = "localhost"
}
return fmt.Sprintf(
"%08x%06x%04x%06x",
time.Now().Unix()&0xFFFFFFFF,
crc32.ChecksumIEEE([]byte(host))>>8&0xFFFFFF,
os.Getpid()&0xFFFF,
currentId)
}
var rd *rand.Rand = rand.New(rand.NewSource(time.Now().UnixNano()))
var midRand int64 = rd.Int63n(0xFFFFFFFF)
//GetUniqueId4 生成mongodb3.4及以上版本的mongo ObjectId.
//用于获得某个数据表的字符串自增id（全局唯一），每个数据表的起始id都是1。id的组成结构参考下列信息：
// a 4-byte timestamp value, representing the ObjectId’s creation, measured in seconds since the Unix epoch
// a 5-byte random value
// a 3-byte incrementing counter, initialized to a random value
func GetUniqueId4(lastID ...int64) string {
var currentId int64 = 1
if len(lastID) > 0 && lastID[0] < 0xFFFFFF {
currentId = lastID[0] + 1
}
return fmt.Sprintf(
"%08x%010x%06x",
time.Now().Unix()&0xFFFFFFFF,
midRand,
currentId)
}基准测试结果
cpu: Intel(R) Core(TM) i5-6267U CPU @ 2.90GHz
BenchmarkGetUniqueId-4 1000000000 0.0000186 ns/op 0 B/op 0 allocs/op
BenchmarkGetUniqueId4-4 1000000000 0.0000155 ns/op 0 B/op 0 allocs/op小结
实际上我自己使用时，传入的参数是用到这个id的表的名称，而lastId则通过内存缓存存储，每次要用的时候从缓存获取并加一。
下列是我生产用的代码
/**
* 生成全局唯一的24位id
* File: uuid.go
* Package: uuid
* Author: Lee
* Date: 2021-03-03 09:52:04
*/
package uuid
import (
"fmt"
"math/rand"
"sync"
"time"
)
var rd *rand.Rand = rand.New(rand.NewSource(time.Now().UnixNano()))
var midRand int64 = rd.Int63n(0xFFFFFFFF)
var cache *Cache = &Cache{}
//缓存
type Cache struct {
mu sync.Mutex //读写锁
data map[string]int64 //缓存
}
func (c *Cache) Get(k string) int64 {
c.mu.Lock()
defer c.mu.Unlock()
id, ok := c.data[k]
if !ok {
id = rd.Int63n(0xFFF000)
}
if id > 0xFFFFFE {
id = rd.Int63n(0xFFF000)
}
if c.data == nil {
c.data = map[string]int64{}
}
id++
c.data[k] = id
return id
}
// GetMongoID 生成mongodb3.4及以上版本的mongo ObjectId.
//用于获得某个数据表的字符串自增id（全局唯一），每个数据表的起始id都是1。id的组成结构参考下列信息：
// a 4-byte timestamp value, representing the ObjectId’s creation, measured in seconds since the Unix epoch
// a 5-byte random value
// a 3-byte incrementing counter, initialized to a random value
func GetMongoID(table string) string {
currentID := cache.Get(table)
return fmt.Sprintf(
"%08x%010x%06x",
time.Now().Unix()&0xFFFFFFFF,
midRand,
currentID)
}
基准测试
cpu: Intel(R) Core(TM) i5-6267U CPU @ 2.90GHz
BenchmarkGetMongoID-4 1000000000 0.0000064 ns/op 0 B/op 0 allocs/op
说点什么
博主