readrune.go

/*
Based on go1.16/src/fmt/scan.go.

Copyright (c) 2009 The Go Authors. All rights reserved.

Redistribution and use in source and binary forms, with or without
modification, are permitted provided that the following conditions are
met:

   * Redistributions of source code must retain the above copyright
notice, this list of conditions and the following disclaimer.
   * Redistributions in binary form must reproduce the above
copyright notice, this list of conditions and the following disclaimer
in the documentation and/or other materials provided with the
distribution.
   * Neither the name of Google Inc. nor the names of its
contributors may be used to endorse or promote products derived from
this software without specific prior written permission.

THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS
"AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR
A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT
OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL,
SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT
LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE,
DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY
THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
(INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
*/

package mt

import (
	"errors"
	"io"
	"unicode/utf8"
)

// readRune is a structure to enable reading UTF-8 encoded code points
// from an io.Reader. It is used if the Reader given to the scanner does
// not already implement io.RuneScanner.
type readRune struct {
	io.Reader
	buf      [utf8.UTFMax]byte // used only inside ReadRune
	pending  int               // number of bytes in pendBuf; only >0 for bad UTF-8
	pendBuf  [utf8.UTFMax]byte // bytes left over
	peekRune rune              // if >=0 next rune; when <0 is ^(previous Rune)
}

// readByte returns the next byte from the input, which may be
// left over from a previous read if the UTF-8 was ill-formed.
func (r *readRune) readByte() (b byte, err error) {
	if r.pending > 0 {
		b = r.pendBuf[0]
		copy(r.pendBuf[0:], r.pendBuf[1:])
		r.pending--
		return
	}
	n, err := io.ReadFull(r, r.pendBuf[:1])
	if n != 1 {
		return 0, err
	}
	return r.pendBuf[0], err
}

// ReadRune returns the next UTF-8 encoded code point from the
// io.Reader inside r.
func (r *readRune) ReadRune() (rr rune, size int, err error) {
	if r.peekRune >= 0 {
		rr = r.peekRune
		r.peekRune = ^r.peekRune
		size = utf8.RuneLen(rr)
		return
	}
	r.buf[0], err = r.readByte()
	if err != nil {
		return
	}
	if r.buf[0] < utf8.RuneSelf { // fast check for common ASCII case
		rr = rune(r.buf[0])
		size = 1 // Known to be 1.
		// Flip the bits of the rune so it's available to UnreadRune.
		r.peekRune = ^rr
		return
	}
	var n int
	for n = 1; !utf8.FullRune(r.buf[:n]); n++ {
		r.buf[n], err = r.readByte()
		if err != nil {
			if err == io.EOF {
				err = nil
				break
			}
			return
		}
	}
	rr, size = utf8.DecodeRune(r.buf[:n])
	if size < n { // an error, save the bytes for the next read
		copy(r.pendBuf[r.pending:], r.buf[size:n])
		r.pending += n - size
	}
	// Flip the bits of the rune so it's available to UnreadRune.
	r.peekRune = ^rr
	return
}

func (r *readRune) UnreadRune() error {
	if r.peekRune >= 0 {
		return errors.New("fmt: scanning called UnreadRune with no rune available")
	}
	// Reverse bit flip of previously read rune to obtain valid >=0 state.
	r.peekRune = ^r.peekRune
	return nil
}