parquet-go的CSVWriter

shulu2024-07-15 23:56

parquet-go的CSVWriter

代码:

go 复制代码

package main

import (
	"github.com/xitongsys/parquet-go-source/local"
	"github.com/xitongsys/parquet-go/writer"
	"log"
)

func main() {
	var err error
	md := []string{
		"name=Name, type=BYTE_ARRAY, convertedtype=UTF8, encoding=PLAIN",
		"name=address, type=LIST, valuetype=BYTE_ARRAY, valueconvertedtype=UTF8",
	}

	//write
	fw, err := local.NewLocalFileWriter("csv.parquet")
	if err != nil {
		log.Println("Can't open file", err)
		return
	}
	pw, err := writer.NewCSVWriter(md, fw, 4)
	if err != nil {
		log.Println("Can't create csv writer", err)
		return
	}

	num := 10
	for i := 0; i < num; i++ {
		data2 := []interface{}{
			"Student Name",
			[]string{"string1", "string2", "string3"},
		}
		if err = pw.Write(data2); err != nil {
			log.Println("Write error", err)
		}

	}
	if err = pw.WriteStop(); err != nil {
		log.Println("WriteStop error", err)
	}
	log.Println("Write Finished")
	fw.Close()

}

执行这段代码会报错:

go 复制代码

pw, err := writer.NewCSVWriter(md, fw, 4)

报错如下:

shell 复制代码

failed to create schema from tag map: type LIST: not a valid Type string

分析原因后是CSVWriter不支持LIST。

具体报错在这里:

go 复制代码

if t, err := parquet.TypeFromString(info.Type); err == nil {
	schema.Type = &t

} else {
		return nil, fmt.Errorf("type " + info.Type + ": " + err.Error())
}

进入parquet.TypeFromString()

go 复制代码

func TypeFromString(s string) (Type, error) {
	switch s {
	case "BOOLEAN":
		return Type_BOOLEAN, nil
	case "INT32":
		return Type_INT32, nil
	case "INT64":
		return Type_INT64, nil
	case "INT96":
		return Type_INT96, nil
	case "FLOAT":
		return Type_FLOAT, nil
	case "DOUBLE":
		return Type_DOUBLE, nil
	case "BYTE_ARRAY":
		return Type_BYTE_ARRAY, nil
	case "FIXED_LEN_BYTE_ARRAY":
		return Type_FIXED_LEN_BYTE_ARRAY, nil
	}
	return Type(0), fmt.Errorf("not a valid Type string")
}

可以看到这里并没有LIST，也没有MAP。只支持如上一些类型。