我正在try 根据时间间隔从Kafka
个事件中拆分一些事件.基本上,目标是读取datetime
列中的值,运行一个简单的公式来判断当前事件是否落在当前的interval
中.如果是,则将该事件附加到RecordBuilder
,否则flush
将事件组(A segment
)附加到parquet
文件.
以下是我到目前为止拥有的代码:
type Segment struct {
mu sync.Mutex
schema *arrow.Schema
evtStruct *arrow.StructType
builder *array.RecordBuilder
writer *pqarrow.FileWriter
timestampIndex int
}
func NewSegment(dir string, datetimeFieldName string, schema *arrow.Schema) (*Segment, error) {
// other inits here
// ...
// create a parquet file
pFile, err := os.Create(fileName)
if err != nil {
return nil, err
}
w, err := pqarrow.NewFileWriter(schema, pFile, props, pqarrow.DefaultWriterProps())
if err != nil {
panic(err)
}
// create the new record builder for inserting data to arrow
mem := memory.NewCheckedAllocator(memory.NewGoAllocator())
b := array.NewRecordBuilder(mem, schema)
evtStruct := arrow.StructOf(schema.Fields()...)
idx, ok := evtStruct.FieldIdx(datetimeFieldName)
if !ok {
return nil, fmt.Errorf("couldn't find datetime column")
}
return &Segment{
schema: schema,
evtStruct: evtStruct,
mu: sync.Mutex{},
builder: b,
writer: w,
timestampIndex: idx,
}, nil
}
// data comes from Kafka and it represent a single event
func (s *Segment) InsertData(data []byte) error {
s.mu.Lock()
defer s.mu.Unlock()
// TODO: do partition by interval here
// extract the datetime value --> dtVal (unix epoch)
// assume for now an interval of 5 minutes
// dtPartition = math.floor(dtVal, 5*60)
/* if dtPartition > oldDtPartition {
return s.Flush()
}
*/
// append the data to the current builder
if err := s.builder.UnmarshalJSON(data); err != nil {
return err
}
return nil
}
// Flush persist the segment on disk
func (s *Segment) Flush() error {
s.mu.Lock()
defer s.mu.Unlock()
rec := s.builder.NewRecord()
// closable
defer s.builder.Release()
defer s.writer.Close()
defer rec.Release()
// write parquet file
if err := s.writer.WriteBuffered(rec); err != nil {
return err
}
return nil
}
问题是,我无法对InsertData
函数的data
输入参数执行"Unmarshal"
操作,因为没有可以将其解组到的"struct"
.我能够创建arrow.Schema
和arrow.StructType
是因为我正在创建的服务允许用户定义事件的模式.因此,我正在try 找到一种方法来读取事件中的datetime
值,并决定哪一个值属于interval
.
在函数InsertData
中,我添加了一些我想要实现的愚蠢的伪代码.也许ApacheArrow有一些功能可以帮助我完成我想要做的事情.提前谢谢您.