Go 使用ObjectID

ObjectID介绍

MongoDB中的ObjectId是一种特殊的12字节 BSON 类型数据，用于为主文档提供唯一的标识符，默认情况下作为 _id 字段的默认值出现在每一个MongoDB集合中的文档中。以下是ObjectId的具体组成：

1. 时间戳（Timestamp）：

• 前4个字节（32位）表示创建该ObjectId时的Unix时间戳，精确到秒，从1970年1月1日UTC时间零点开始计算，这使得ObjectId具有一定程度的时间有序性。

2. 机器标识符（Machine ID）：

• 接下来的3个字节（24位）代表了生成此ObjectId的机器主机的唯一标识符。这个标识符通常是基于主机的网络接口地址哈希得到的，目的是确保不同主机生成的ObjectId是不同的。

3. 进程标识符（PID）：

• （旧版描述中提到的是进程ID，但在MongoDB较新版本中已不再使用）在某些早期的描述中提及2个字节代表进程ID，不过实际上MongoDB并不使用进程ID来生成ObjectId，以避免因为PID重用导致的冲突。现在这部分数据通常用于其他目的以保证全局唯一性。

4. 计数器（Counter）：

• 最后的3个字节（24位）是一个自增计数器，在同一台机器同一秒内生成的ObjectId会通过这个计数器递增来确保唯一性。计数器在一个秒内是从一个随机数开始递增的，这样即使在同一秒内创建多个ObjectId也能保证在单机上的唯一性。

因此，ObjectId的设计可以确保在分布式的环境下，每个文档都能拥有一个全局唯一的标识符，同时也包含了时间信息，这对于很多应用场景来说非常有用，比如排序、索引和逻辑处理。

ObjectID使用

分布式系统需要全局唯一ID且有序的，可以考虑ObjectID。

UUID太长了，且是无序的。感觉不太好，ObjectID算是个还可以的选择。当然还有很多其它方案。

Go项目，在Mongodb的驱动包里，有一个文件是objectid.go，有写好ObjectID生成算法。如果项目只要一个算法没必要引入完整的包，可以直接把这个文件拷贝出来。

内容如下：

package hobjectidimport ("crypto/rand""encoding""encoding/binary""encoding/hex""encoding/json""errors""fmt""io""sync/atomic""time"
)// 代码来自  https://github.com/mongodb/mongo-go-driver/blob/v1/bson/primitive/objectid.go// ErrInvalidHex indicates that a hex string cannot be converted to an ObjectID.
var ErrInvalidHex = errors.New("the provided hex string is not a valid ObjectID")// ObjectID is the BSON ObjectID type.
type ObjectID [12]byte// NilObjectID is the zero value for ObjectID.
var NilObjectID ObjectIDvar objectIDCounter = readRandomUint32()
var processUnique = processUniqueBytes()var _ encoding.TextMarshaler = ObjectID{}
var _ encoding.TextUnmarshaler = &ObjectID{}// NewObjectID generates a new ObjectID.
func NewObjectID() ObjectID {return NewObjectIDFromTimestamp(time.Now())
}// NewObjectIDFromTimestamp generates a new ObjectID based on the given time.
func NewObjectIDFromTimestamp(timestamp time.Time) ObjectID {var b [12]bytebinary.BigEndian.PutUint32(b[0:4], uint32(timestamp.Unix()))copy(b[4:9], processUnique[:])putUint24(b[9:12], atomic.AddUint32(&objectIDCounter, 1))return b
}// Timestamp extracts the time part of the ObjectId.
func (id ObjectID) Timestamp() time.Time {unixSecs := binary.BigEndian.Uint32(id[0:4])return time.Unix(int64(unixSecs), 0).UTC()
}// Hex returns the hex encoding of the ObjectID as a string.
func (id ObjectID) Hex() string {var buf [24]bytehex.Encode(buf[:], id[:])return string(buf[:])
}func (id ObjectID) String() string {return fmt.Sprintf("ObjectID(%q)", id.Hex())
}// IsZero returns true if id is the empty ObjectID.
func (id ObjectID) IsZero() bool {return id == NilObjectID
}// ObjectIDFromHex creates a new ObjectID from a hex string. It returns an error if the hex string is not a
// valid ObjectID.
func ObjectIDFromHex(s string) (ObjectID, error) {if len(s) != 24 {return NilObjectID, ErrInvalidHex}var oid [12]byte_, err := hex.Decode(oid[:], []byte(s))if err != nil {return NilObjectID, err}return oid, nil
}// IsValidObjectID returns true if the provided hex string represents a valid ObjectID and false if not.
//
// Deprecated: Use ObjectIDFromHex and check the error instead.
func IsValidObjectID(s string) bool {_, err := ObjectIDFromHex(s)return err == nil
}// MarshalText returns the ObjectID as UTF-8-encoded text. Implementing this allows us to use ObjectID
// as a map key when marshalling JSON. See https://pkg.go.dev/encoding#TextMarshaler
func (id ObjectID) MarshalText() ([]byte, error) {return []byte(id.Hex()), nil
}// UnmarshalText populates the byte slice with the ObjectID. Implementing this allows us to use ObjectID
// as a map key when unmarshalling JSON. See https://pkg.go.dev/encoding#TextUnmarshaler
func (id *ObjectID) UnmarshalText(b []byte) error {oid, err := ObjectIDFromHex(string(b))if err != nil {return err}*id = oidreturn nil
}// MarshalJSON returns the ObjectID as a string
func (id ObjectID) MarshalJSON() ([]byte, error) {return json.Marshal(id.Hex())
}// UnmarshalJSON populates the byte slice with the ObjectID. If the byte slice is 24 bytes long, it
// will be populated with the hex representation of the ObjectID. If the byte slice is twelve bytes
// long, it will be populated with the BSON representation of the ObjectID. This method also accepts empty strings and
// decodes them as NilObjectID. For any other inputs, an error will be returned.
func (id *ObjectID) UnmarshalJSON(b []byte) error {// Ignore "null" to keep parity with the standard library. Decoding a JSON null into a non-pointer ObjectID field// will leave the field unchanged. For pointer values, encoding/json will set the pointer to nil and will not// enter the UnmarshalJSON hook.if string(b) == "null" {return nil}var err errorswitch len(b) {case 12:copy(id[:], b)default:// Extended JSONvar res interface{}err := json.Unmarshal(b, &res)if err != nil {return err}str, ok := res.(string)if !ok {m, ok := res.(map[string]interface{})if !ok {return errors.New("not an extended JSON ObjectID")}oid, ok := m["$oid"]if !ok {return errors.New("not an extended JSON ObjectID")}str, ok = oid.(string)if !ok {return errors.New("not an extended JSON ObjectID")}}// An empty string is not a valid ObjectID, but we treat it as a special value that decodes as NilObjectID.if len(str) == 0 {copy(id[:], NilObjectID[:])return nil}if len(str) != 24 {return fmt.Errorf("cannot unmarshal into an ObjectID, the length must be 24 but it is %d", len(str))}_, err = hex.Decode(id[:], []byte(str))if err != nil {return err}}return err
}func processUniqueBytes() [5]byte {var b [5]byte_, err := io.ReadFull(rand.Reader, b[:])if err != nil {panic(fmt.Errorf("cannot initialize objectid package with crypto.rand.Reader: %w", err))}return b
}func readRandomUint32() uint32 {var b [4]byte_, err := io.ReadFull(rand.Reader, b[:])if err != nil {panic(fmt.Errorf("cannot initialize objectid package with crypto.rand.Reader: %w", err))}return (uint32(b[0]) << 0) | (uint32(b[1]) << 8) | (uint32(b[2]) << 16) | (uint32(b[3]) << 24)
}func putUint24(b []byte, v uint32) {b[0] = byte(v >> 16)b[1] = byte(v >> 8)b[2] = byte(v)
}

使用生成算法，生成的ID 可以与环境无关、业务无关。通用性更好。