From: Rob Pike <r@golang.org>
Date: Fri, 5 Mar 2010 19:34:53 +0000 (-0800)
Subject: Add ReadRune and WriteRune to bytes.Buffer
X-Git-Tag: weekly.2010-03-15~52
X-Git-Url: http://www.git.cypherpunks.su/?a=commitdiff_plain;h=0ac5ef70db410a219eeb46fd9c45205df6a3e2f6;p=gostls13.git

Add ReadRune and WriteRune to bytes.Buffer

The comments mention bufio's WriteRune, which should come next.

R=rsc
CC=golang-dev
https://golang.org/cl/245041
---

diff --git a/src/pkg/bytes/buffer.go b/src/pkg/bytes/buffer.go
index 76126959fe..acd4523ada 100644
--- a/src/pkg/bytes/buffer.go
+++ b/src/pkg/bytes/buffer.go
@@ -9,6 +9,7 @@ package bytes
 import (
 	"io"
 	"os"
+	"utf8"
 )
 
 // Copy from string to byte array at offset doff.  Assume there's room.
@@ -22,10 +23,10 @@ func copyString(dst []byte, doff int, str string) {
 // A Buffer is a variable-sized buffer of bytes with Read and Write methods.
 // The zero value for Buffer is an empty buffer ready to use.
 type Buffer struct {
-	buf       []byte   // contents are the bytes buf[off : len(buf)]
-	off       int      // read at &buf[off], write at &buf[len(buf)]
-	oneByte   [1]byte  // avoid allocation of slice on each WriteByte
-	bootstrap [64]byte // memory to hold first slice; helps small buffers (Printf) avoid allocation.
+	buf       []byte            // contents are the bytes buf[off : len(buf)]
+	off       int               // read at &buf[off], write at &buf[len(buf)]
+	runeBytes [utf8.UTFMax]byte // avoid allocation of slice on each WriteByte or Rune
+	bootstrap [64]byte          // memory to hold first slice; helps small buffers (Printf) avoid allocation.
 }
 
 // Bytes returns a slice of the contents of the unread portion of the buffer;
@@ -176,11 +177,25 @@ func (b *Buffer) WriteTo(w io.Writer) (n int64, err os.Error) {
 // The returned error is always nil, but is included
 // to match bufio.Writer's WriteByte.
 func (b *Buffer) WriteByte(c byte) os.Error {
-	b.oneByte[0] = c
-	b.Write(&b.oneByte)
+	b.runeBytes[0] = c
+	b.Write(b.runeBytes[0:1])
 	return nil
 }
 
+// WriteRune appends the UTF-8 encoding of Unicode
+// code point r to the buffer, returning its length and
+// an error, which is always nil but is included
+// to match bufio.Writer's WriteRune.
+func (b *Buffer) WriteRune(r int) (n int, err os.Error) {
+	if r < utf8.RuneSelf {
+		b.WriteByte(byte(r))
+		return 1, nil
+	}
+	n = utf8.EncodeRune(r, &b.runeBytes)
+	b.Write(b.runeBytes[0:n])
+	return n, nil
+}
+
 // Read reads the next len(p) bytes from the buffer or until the buffer
 // is drained.  The return value n is the number of bytes read.  If the
 // buffer has no data to return, err is os.EOF even if len(p) is zero;
@@ -217,6 +232,27 @@ func (b *Buffer) ReadByte() (c byte, err os.Error) {
 	return c, nil
 }
 
+// ReadRune reads and returns the next UTF-8-encoded
+// Unicode code point from the buffer.
+// If no bytes are available, the error returned is os.EOF.
+// If the bytes are an erroneous UTF-8 encoding, it
+// consumes one byte and returns U+FFFD, 1.
+func (b *Buffer) ReadRune() (r int, size int, err os.Error) {
+	if b.off >= len(b.buf) {
+		// Buffer is empty, reset to recover space.
+		b.Truncate(0)
+		return 0, 0, os.EOF
+	}
+	c := b.buf[b.off]
+	if c < utf8.RuneSelf {
+		b.off++
+		return int(c), 1, nil
+	}
+	r, n := utf8.DecodeRune(b.buf[b.off:])
+	b.off += n
+	return r, n, nil
+}
+
 // NewBuffer creates and initializes a new Buffer using buf as its initial
 // contents.  It is intended to prepare a Buffer to read existing data.  It
 // can also be used to to size the internal buffer for writing.  To do that,
diff --git a/src/pkg/bytes/buffer_test.go b/src/pkg/bytes/buffer_test.go
index af637cf63c..17acd72184 100644
--- a/src/pkg/bytes/buffer_test.go
+++ b/src/pkg/bytes/buffer_test.go
@@ -8,6 +8,7 @@ import (
 	. "bytes"
 	"rand"
 	"testing"
+	"utf8"
 )
 
 
@@ -262,3 +263,37 @@ func TestWriteTo(t *testing.T) {
 		empty(t, "TestReadFrom (2)", &b, s, make([]byte, len(data)))
 	}
 }
+
+func TestRuneIO(t *testing.T) {
+	const NRune = 1000
+	// Built a test array while we write the data
+	b := make([]byte, utf8.UTFMax*NRune)
+	var buf Buffer
+	n := 0
+	for r := 0; r < NRune; r++ {
+		size := utf8.EncodeRune(r, b[n:])
+		nbytes, err := buf.WriteRune(r)
+		if err != nil {
+			t.Fatalf("WriteRune(0x%x) error: %s", r, err)
+		}
+		if nbytes != size {
+			t.Fatalf("WriteRune(0x%x) expected %d, got %d", size, nbytes)
+		}
+		n += size
+	}
+	b = b[0:n]
+
+	// Check the resulting bytes
+	if !Equal(buf.Bytes(), b) {
+		t.Fatalf("incorrect result from WriteRune: %q not %q", buf.Bytes(), b)
+	}
+
+	// Read it back with ReadRune
+	for r := 0; r < NRune; r++ {
+		size := utf8.EncodeRune(r, b)
+		nr, nbytes, err := buf.ReadRune()
+		if nr != r || nbytes != size || err != nil {
+			t.Fatalf("ReadRune(0x%x) got 0x%x,%d not 0x%x,%d (err=%s)", r, nr, nbytes, r, size, err)
+		}
+	}
+}