bcp data slurper

qwe.go

package main

import (
	"bufio"
	"encoding/csv"
	"os"
)

func main() {
	bufSize := 2 ^ 15
	filename := os.Args[1]
	f, err := os.Open(filename)
	if err != nil {
		panic(err)
	}

	rdr := bufio.NewReaderSize(f, bufSize)
	w := csv.NewWriter(bufio.NewWriter(os.Stdout))
	scanner := bufio.NewScanner(rdr)
	scanner.Split(scanTok)

	var record []string
	append := func(v string) {
		if len(v) == 0 {
			record = append(record, "\\N")
			return
		}
		if v == "\000" {
			record = append(record, "")
		} else {
			record = append(record, v)
		}
	}
	for scanner.Scan() {
		text := scanner.Text()

		l := len(text)
		if l == 0 {
			continue
		}
		sig := text[l-1]
		text = text[:l-1]

		switch sig {
		case '\001':
			append(text)
		case '\002':
			append(text)
			w.Write(record)
			record = record[:0]
		case '\000':
			append("\000")
		}
	}
	w.Flush()

}

func scanTok(data []byte, atEOF bool) (advance int, token []byte, err error) {
	for i := 0; i < len(data); i++ {
		switch data[i] {
		case '\000', '\001', '\002':
			return i + 1, data[:i+1], nil
		}
	}
	if !atEOF {
		return 0, nil, nil
	}
	// There is one final token to be delivered, which may be the empty string.
	// Returning bufio.ErrFinalToken here tells Scan there are no more tokens after this
	// but does not trigger an error to be returned from Scan itself.
	return 0, data, bufio.ErrFinalToken

}