上代码
func NewScanner(r io.Reader) *Scanner {
return &Scanner{
r: r,
split: ScanLines,
maxTokenSize: MaxScanTokenSize,
}
}
函数NewScanner返回一个Scanner,这个返回值来自于函数参数r。他的类型是io.Reader。
type Scanner struct {
r io.Reader // The reader provided by the client.
split SplitFunc // The function to split the tokens.
maxTokenSize int // Maximum size of a token; modified by tests.
token []byte // Last token returned by split.
buf []byte // Buffer used as argument to split.
start int // First non-processed byte in buf.
end int // End of data in buf.
err error // Sticky error.
empties int // Count of successive empty tokens.
scanCalled bool // Scan has been called; buffer is in use.
done bool // Scan has finished.
}
Scanner是一个结构体,他包含了一些参数。当然他也有自己的方法。
func (s *Scanner) Scan() bool {
if s.done {
return false
}
s.scanCalled = true
// Loop until we have a token.
for {
// See if we can get a token with what we already have.
// If we've run out of data but have an error, give the split function
// a chance to recover any remaining, possibly empty token.
if s.end > s.start || s.err != nil {
advance, token, err := s.split(s.buf[s.start:s.end], s.err != nil)
if err != nil {
if err == ErrFinalToken {
s.token = token
s.done = true
return true
}
s.setErr(err)
return false
}
if !s.advance(advance) {
return false
}
s.token = token
if token != nil {
if s.err == nil || advance > 0 {
s.empties = 0
} else {
// Returning tokens not advancing input at EOF.
s.empties++
if s.empties > maxConsecutiveEmptyReads {
panic("bufio.Scan: too many empty tokens without progressing")
}
}
return true
}
}
// We cannot generate a token with what we are holding.
// If we've already hit EOF or an I/O error, we are done.
if s.err != nil {
// Shut it down.
s.start = 0
s.end = 0
return false
}
// Must read more data.
// First, shift data to beginning of buffer if there's lots of empty space
// or space is needed.
if s.start > 0 && (s.end == len(s.buf) || s.start > len(s.buf)/2) {
copy(s.buf, s.buf[s.start:s.end])
s.end -= s.start
s.start = 0
}
// Is the buffer full? If so, resize.
if s.end == len(s.buf) {
// Guarantee no overflow in the multiplication below.
const maxInt = int(^uint(0) >> 1)
if len(s.buf) >= s.maxTokenSize || len(s.buf) > maxInt/2 {
s.setErr(ErrTooLong)
return false
}
newSize := len(s.buf) * 2
if newSize == 0 {
newSize = startBufSize
}
if newSize > s.maxTokenSize {
newSize = s.maxTokenSize
}
newBuf := make([]byte, newSize)
copy(newBuf, s.buf[s.start:s.end])
s.buf = newBuf
s.end -= s.start
s.start = 0
}
// Finally we can read some input. Make sure we don't get stuck with
// a misbehaving Reader. Officially we don't need to do this, but let's
// be extra careful: Scanner is for safe, simple jobs.
for loop := 0; ; {
n, err := s.r.Read(s.buf[s.end:len(s.buf)])
s.end += n
if err != nil {
s.setErr(err)
break
}
if n > 0 {
s.empties = 0
break
}
loop++
if loop > maxConsecutiveEmptyReads {
s.setErr(io.ErrNoProgress)
break
}
}
}
有疑问加站长微信联系(非本文作者)