codec: added codecutils/bytescan package

codec/codecutils/bytescan/scanner.go

@@ -0,0 +1,94 @@
+/*
+NAME
+  scanner.go
+
+AUTHOR
+  Dan Kortschak <dan@ausocean.org>
+
+LICENSE
+  This is Copyright (C) 2017 the Australian Ocean Lab (AusOcean)
+
+  It is free software: you can redistribute it and/or modify them
+  under the terms of the GNU General Public License as published by the
+  Free Software Foundation, either version 3 of the License, or (at your
+  option) any later version.
+
+  It is distributed in the hope that it will be useful, but WITHOUT
+  ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
+  FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License
+  for more details.
+
+  You should have received a copy of the GNU General Public License
+  in gpl.txt. If not, see http://www.gnu.org/licenses.
+*/
+
+package bytescan
+
+import "io"
+
+// Scanner is a byte scanner.
+type Scanner struct {
+	buf []byte
+	off int
+
+	// r is the source of data for the scanner.
+	r io.Reader
+}
+
+// NewScanner returns a scanner initialised with an io.Reader and a read buffer.
+func NewScanner(r io.Reader, buf []byte) *Scanner {
+	return &Scanner{r: r, buf: buf[:0]}
+}
+
+// ScanUntil scans the scanner's underlying io.Reader until a delim byte
+// has been read, appending all read bytes to dst. The resulting appended data,
+// the last read byte and whether the last read byte was the delimiter.
+func (c *Scanner) ScanUntil(dst []byte, delim byte) (res []byte, b byte, err error) {
+outer:
+	for {
+		var i int
+		for i, b = range c.buf[c.off:] {
+			if b != delim {
+				continue
+			}
+			dst = append(dst, c.buf[c.off:c.off+i+1]...)
+			c.off += i + 1
+			break outer
+		}
+		dst = append(dst, c.buf[c.off:]...)
+		err = c.reload()
+		if err != nil {
+			break
+		}
+	}
+	return dst, b, err
+}
+
+// ReadByte is an unexported ReadByte.
+func (c *Scanner) ReadByte() (byte, error) {
+	if c.off >= len(c.buf) {
+		err := c.reload()
+		if err != nil {
+			return 0, err
+		}
+	}
+	b := c.buf[c.off]
+	c.off++
+	return b, nil
+}
+
+// reload re-fills the scanner's buffer.
+func (c *Scanner) reload() error {
+	n, err := c.r.Read(c.buf[:cap(c.buf)])
+	c.buf = c.buf[:n]
+	if err != nil {
+		if err != io.EOF {
+			return err
+		}
+		if n == 0 {
+			return io.EOF
+		}
+	}
+	c.off = 0
+	return nil
+}

codec/codecutils/bytescan/scanner_test.go

@@ -0,0 +1,82 @@
+/*
+NAME
+  scanner_test.go
+
+DESCRIPTION
+  See Readme.md
+
+AUTHOR
+  Dan Kortschak <dan@ausocean.org>
+
+LICENSE
+  This is Copyright (C) 2017 the Australian Ocean Lab (AusOcean)
+
+  It is free software: you can redistribute it and/or modify them
+  under the terms of the GNU General Public License as published by the
+  Free Software Foundation, either version 3 of the License, or (at your
+  option) any later version.
+
+  It is distributed in the hope that it will be useful, but WITHOUT
+  ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
+  FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License
+  for more details.
+
+  You should have received a copy of the GNU General Public License
+  in gpl.txt. If not, see http://www.gnu.org/licenses.
+*/
+
+package bytescan
+
+import (
+	"bytes"
+	"reflect"
+	"testing"
+)
+
+type chunkEncoder [][]byte
+
+func (e *chunkEncoder) Encode(b []byte) error {
+	*e = append(*e, b)
+	return nil
+}
+
+func (*chunkEncoder) Stream() <-chan []byte { panic("INVALID USE") }
+
+func TestScannerReadByte(t *testing.T) {
+	data := []byte("Lorem ipsum dolor sit amet, consectetur adipiscing elit, sed do eiusmod tempor incididunt ut labore et dolore magna aliqua.")
+
+	for _, size := range []int{1, 2, 8, 1 << 10} {
+		r := NewScanner(bytes.NewReader(data), make([]byte, size))
+		var got []byte
+		for {
+			b, err := r.ReadByte()
+			if err != nil {
+				break
+			}
+			got = append(got, b)
+		}
+		if !bytes.Equal(got, data) {
+			t.Errorf("unexpected result for buffer size %d:\ngot :%q\nwant:%q", size, got, data)
+		}
+	}
+}
+
+func TestScannerScanUntilZero(t *testing.T) {
+	data := []byte("Lorem ipsum dolor sit amet, consectetur adipiscing elit,\x00 sed do eiusmod tempor incididunt ut \x00labore et dolore magna aliqua.")
+
+	for _, size := range []int{1, 2, 8, 1 << 10} {
+		r := NewScanner(bytes.NewReader(data), make([]byte, size))
+		var got [][]byte
+		for {
+			buf, _, err := r.ScanUntil(nil, 0x0)
+			got = append(got, buf)
+			if err != nil {
+				break
+			}
+		}
+		want := bytes.SplitAfter(data, []byte{0})
+		if !reflect.DeepEqual(got, want) {
+			t.Errorf("unexpected result for buffer zie %d:\ngot :%q\nwant:%q", size, got, want)
+		}
+	}
+}