string

사용하다:

• reader.ReadString('\n')
  • 라인이 매우 길 수 있다고 생각하지 않으면 (즉, 많은 RAM을 사용) \n반환 된 문자열의 끝에를 유지합니다 .
• reader.ReadLine()
  • RAM 소비 제한에 관심이 있고 행이 리더의 버퍼 크기보다 큰 경우를 처리하는 추가 작업을 신경 쓰지 않아도됩니다.

다른 답변에서 문제로 식별되는 시나리오를 테스트하는 프로그램을 작성하여 제안 된 다양한 솔루션을 테스트했습니다.

• 4MB 줄의 파일.
• 줄 바꿈으로 끝나지 않는 파일.

나는 그것을 발견했다 :

• Scanner솔루션은 긴 줄을 처리하지 않습니다.
• ReadLine솔루션은 구현하기가 복잡하다.
• ReadString솔루션은 간단하고 긴 줄을 작동합니다.

각 솔루션을 보여주는 코드는 다음과 같습니다 go run main.go.

package main

import (
    "bufio"
    "bytes"
    "fmt"
    "io"
    "os"
)

func readFileWithReadString(fn string) (err error) {
    fmt.Println("readFileWithReadString")

    file, err := os.Open(fn)
    defer file.Close()

    if err != nil {
        return err
    }

    // Start reading from the file with a reader.
    reader := bufio.NewReader(file)

    var line string
    for {
        line, err = reader.ReadString('\n')

        fmt.Printf(" > Read %d characters\n", len(line))

        // Process the line here.
        fmt.Println(" > > " + limitLength(line, 50))

        if err != nil {
            break
        }
    }

    if err != io.EOF {
        fmt.Printf(" > Failed!: %v\n", err)
    }

    return
}

func readFileWithScanner(fn string) (err error) {
    fmt.Println("readFileWithScanner - this will fail!")

    // Don't use this, it doesn't work with long lines...

    file, err := os.Open(fn)
    defer file.Close()

    if err != nil {
        return err
    }

    // Start reading from the file using a scanner.
    scanner := bufio.NewScanner(file)

    for scanner.Scan() {
        line := scanner.Text()

        fmt.Printf(" > Read %d characters\n", len(line))

        // Process the line here.
        fmt.Println(" > > " + limitLength(line, 50))
    }

    if scanner.Err() != nil {
        fmt.Printf(" > Failed!: %v\n", scanner.Err())
    }

    return
}

func readFileWithReadLine(fn string) (err error) {
    fmt.Println("readFileWithReadLine")

    file, err := os.Open(fn)
    defer file.Close()

    if err != nil {
        return err
    }

    // Start reading from the file with a reader.
    reader := bufio.NewReader(file)

    for {
        var buffer bytes.Buffer

        var l []byte
        var isPrefix bool
        for {
            l, isPrefix, err = reader.ReadLine()
            buffer.Write(l)

            // If we've reached the end of the line, stop reading.
            if !isPrefix {
                break
            }

            // If we're just at the EOF, break
            if err != nil {
                break
            }
        }

        if err == io.EOF {
            break
        }

        line := buffer.String()

        fmt.Printf(" > Read %d characters\n", len(line))

        // Process the line here.
        fmt.Println(" > > " + limitLength(line, 50))
    }

    if err != io.EOF {
        fmt.Printf(" > Failed!: %v\n", err)
    }

    return
}

func main() {
    testLongLines()
    testLinesThatDoNotFinishWithALinebreak()
}

func testLongLines() {
    fmt.Println("Long lines")
    fmt.Println()

    createFileWithLongLine("longline.txt")
    readFileWithReadString("longline.txt")
    fmt.Println()
    readFileWithScanner("longline.txt")
    fmt.Println()
    readFileWithReadLine("longline.txt")
    fmt.Println()
}

func testLinesThatDoNotFinishWithALinebreak() {
    fmt.Println("No linebreak")
    fmt.Println()

    createFileThatDoesNotEndWithALineBreak("nolinebreak.txt")
    readFileWithReadString("nolinebreak.txt")
    fmt.Println()
    readFileWithScanner("nolinebreak.txt")
    fmt.Println()
    readFileWithReadLine("nolinebreak.txt")
    fmt.Println()
}

func createFileThatDoesNotEndWithALineBreak(fn string) (err error) {
    file, err := os.Create(fn)
    defer file.Close()

    if err != nil {
        return err
    }

    w := bufio.NewWriter(file)
    w.WriteString("Does not end with linebreak.")
    w.Flush()

    return
}

func createFileWithLongLine(fn string) (err error) {
    file, err := os.Create(fn)
    defer file.Close()

    if err != nil {
        return err
    }

    w := bufio.NewWriter(file)

    fs := 1024 * 1024 * 4 // 4MB

    // Create a 4MB long line consisting of the letter a.
    for i := 0; i < fs; i++ {
        w.WriteRune('a')
    }

    // Terminate the line with a break.
    w.WriteRune('\n')

    // Put in a second line, which doesn't have a linebreak.
    w.WriteString("Second line.")

    w.Flush()

    return
}

func limitLength(s string, length int) string {
    if len(s) < length {
        return s
    }

    return s[:length]
}

나는 테스트했다 :

• 버전 이동 1.7 / amd64
• 버전 go1.6.3 linux / amd64로 이동
• Go 버전 go1.7.4 darwin / amd64

테스트 프로그램은 다음을 출력합니다.

Long lines

readFileWithReadString
 > Read 4194305 characters
 > > aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa
 > Read 12 characters
 > > Second line.

readFileWithScanner - this will fail!
 > Failed!: bufio.Scanner: token too long

readFileWithReadLine
 > Read 4194304 characters
 > > aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa
 > Read 12 characters
 > > Second line.

No linebreak

readFileWithReadString
 > Read 28 characters
 > > Does not end with linebreak.

readFileWithScanner - this will fail!
 > Read 28 characters
 > > Does not end with linebreak.

readFileWithReadLine
 > Read 28 characters
 > > Does not end with linebreak.

답변

// Readln returns a single line (without the ending \n)
// from the input buffered reader.
// An error is returned iff there is an error with the
// buffered reader.
func Readln(r *bufio.Reader) (string, error) {
  var (isPrefix bool = true
       err error = nil
       line, ln []byte
      )
  for isPrefix && err == nil {
      line, isPrefix, err = r.ReadLine()
      ln = append(ln, line...)
  }
  return string(ln),err
}

f, err := os.Open(fi)
if err != nil {
    fmt.Printf("error opening file: %v\n",err)
    os.Exit(1)
}
r := bufio.NewReader(f)
s, e := Readln(r)
for e == nil {
    fmt.Println(s)
    s,e = Readln(r)
}

func scanFile() {
    f, err := os.OpenFile(logfile, os.O_RDONLY, os.ModePerm)
    if err != nil {
        log.Fatalf("open file error: %v", err)
        return
    }
    defer f.Close()

    sc := bufio.NewScanner(f)
    for sc.Scan() {
        _ = sc.Text()  // GET the line string
    }
    if err := sc.Err(); err != nil {
        log.Fatalf("scan file error: %v", err)
        return
    }
}

func readFileLines() {
    f, err := os.OpenFile(logfile, os.O_RDONLY, os.ModePerm)
    if err != nil {
        log.Fatalf("open file error: %v", err)
        return
    }
    defer f.Close()

    rd := bufio.NewReader(f)
    for {
        line, err := rd.ReadString('\n')
        if err != nil {
            if err == io.EOF {
                break
            }

            log.Fatalf("read file line error: %v", err)
            return
        }
        _ = line  // GET the line string
    }
}

func readLine(path string) {
  inFile, err := os.Open(path)
  if err != nil {
     fmt.Println(err.Error() + `: ` + path)
     return
  }
  defer inFile.Close()

  scanner := bufio.NewScanner(inFile)
  for scanner.Scan() {
    fmt.Println(scanner.Text()) // the line
  }
}

func readLines() []string {
  r := bufio.NewReader(os.Stdin)
  bytes := []byte{}
  lines := []string{}
  for {
    line, isPrefix, err := r.ReadLine()
    if err != nil {
      break
    }
    bytes = append(bytes, line...)
    if !isPrefix {
      str := strings.TrimSpace(string(bytes))
      if len(str) > 0 {
        lines = append(lines, str)
        bytes = []byte{}
      }
    }
  }
  if len(bytes) > 0 {
    lines = append(lines, string(bytes))
  }
  return lines
}

  f, err := os.Open(filename)
  if err != nil {
    fmt.Println("error opening file ", err)
    os.Exit(1)
  }
  defer f.Close()
  r := bufio.NewReader(f)
  for {
    path, err := r.ReadString(10) // 0x0A separator = newline
    if err == io.EOF {
      // do something here
      break
    } else if err != nil {
      return err // if you return error
    }
  }