diff options
Diffstat (limited to 'src/encoding/binary/varint.go')
-rw-r--r-- | src/encoding/binary/varint.go | 166 |
1 files changed, 166 insertions, 0 deletions
diff --git a/src/encoding/binary/varint.go b/src/encoding/binary/varint.go new file mode 100644 index 0000000..18e1ff1 --- /dev/null +++ b/src/encoding/binary/varint.go @@ -0,0 +1,166 @@ +// Copyright 2011 The Go Authors. All rights reserved. +// Use of this source code is governed by a BSD-style +// license that can be found in the LICENSE file. + +package binary + +// This file implements "varint" encoding of 64-bit integers. +// The encoding is: +// - unsigned integers are serialized 7 bits at a time, starting with the +// least significant bits +// - the most significant bit (msb) in each output byte indicates if there +// is a continuation byte (msb = 1) +// - signed integers are mapped to unsigned integers using "zig-zag" +// encoding: Positive values x are written as 2*x + 0, negative values +// are written as 2*(^x) + 1; that is, negative numbers are complemented +// and whether to complement is encoded in bit 0. +// +// Design note: +// At most 10 bytes are needed for 64-bit values. The encoding could +// be more dense: a full 64-bit value needs an extra byte just to hold bit 63. +// Instead, the msb of the previous byte could be used to hold bit 63 since we +// know there can't be more than 64 bits. This is a trivial improvement and +// would reduce the maximum encoding length to 9 bytes. However, it breaks the +// invariant that the msb is always the "continuation bit" and thus makes the +// format incompatible with a varint encoding for larger numbers (say 128-bit). + +import ( + "errors" + "io" +) + +// MaxVarintLenN is the maximum length of a varint-encoded N-bit integer. +const ( + MaxVarintLen16 = 3 + MaxVarintLen32 = 5 + MaxVarintLen64 = 10 +) + +// AppendUvarint appends the varint-encoded form of x, +// as generated by PutUvarint, to buf and returns the extended buffer. +func AppendUvarint(buf []byte, x uint64) []byte { + for x >= 0x80 { + buf = append(buf, byte(x)|0x80) + x >>= 7 + } + return append(buf, byte(x)) +} + +// PutUvarint encodes a uint64 into buf and returns the number of bytes written. +// If the buffer is too small, PutUvarint will panic. +func PutUvarint(buf []byte, x uint64) int { + i := 0 + for x >= 0x80 { + buf[i] = byte(x) | 0x80 + x >>= 7 + i++ + } + buf[i] = byte(x) + return i + 1 +} + +// Uvarint decodes a uint64 from buf and returns that value and the +// number of bytes read (> 0). If an error occurred, the value is 0 +// and the number of bytes n is <= 0 meaning: +// +// n == 0: buf too small +// n < 0: value larger than 64 bits (overflow) +// and -n is the number of bytes read +func Uvarint(buf []byte) (uint64, int) { + var x uint64 + var s uint + for i, b := range buf { + if i == MaxVarintLen64 { + // Catch byte reads past MaxVarintLen64. + // See issue https://golang.org/issues/41185 + return 0, -(i + 1) // overflow + } + if b < 0x80 { + if i == MaxVarintLen64-1 && b > 1 { + return 0, -(i + 1) // overflow + } + return x | uint64(b)<<s, i + 1 + } + x |= uint64(b&0x7f) << s + s += 7 + } + return 0, 0 +} + +// AppendVarint appends the varint-encoded form of x, +// as generated by PutVarint, to buf and returns the extended buffer. +func AppendVarint(buf []byte, x int64) []byte { + ux := uint64(x) << 1 + if x < 0 { + ux = ^ux + } + return AppendUvarint(buf, ux) +} + +// PutVarint encodes an int64 into buf and returns the number of bytes written. +// If the buffer is too small, PutVarint will panic. +func PutVarint(buf []byte, x int64) int { + ux := uint64(x) << 1 + if x < 0 { + ux = ^ux + } + return PutUvarint(buf, ux) +} + +// Varint decodes an int64 from buf and returns that value and the +// number of bytes read (> 0). If an error occurred, the value is 0 +// and the number of bytes n is <= 0 with the following meaning: +// +// n == 0: buf too small +// n < 0: value larger than 64 bits (overflow) +// and -n is the number of bytes read +func Varint(buf []byte) (int64, int) { + ux, n := Uvarint(buf) // ok to continue in presence of error + x := int64(ux >> 1) + if ux&1 != 0 { + x = ^x + } + return x, n +} + +var overflow = errors.New("binary: varint overflows a 64-bit integer") + +// ReadUvarint reads an encoded unsigned integer from r and returns it as a uint64. +// The error is EOF only if no bytes were read. +// If an EOF happens after reading some but not all the bytes, +// ReadUvarint returns io.ErrUnexpectedEOF. +func ReadUvarint(r io.ByteReader) (uint64, error) { + var x uint64 + var s uint + for i := 0; i < MaxVarintLen64; i++ { + b, err := r.ReadByte() + if err != nil { + if i > 0 && err == io.EOF { + err = io.ErrUnexpectedEOF + } + return x, err + } + if b < 0x80 { + if i == MaxVarintLen64-1 && b > 1 { + return x, overflow + } + return x | uint64(b)<<s, nil + } + x |= uint64(b&0x7f) << s + s += 7 + } + return x, overflow +} + +// ReadVarint reads an encoded signed integer from r and returns it as an int64. +// The error is EOF only if no bytes were read. +// If an EOF happens after reading some but not all the bytes, +// ReadVarint returns io.ErrUnexpectedEOF. +func ReadVarint(r io.ByteReader) (int64, error) { + ux, err := ReadUvarint(r) // ok to continue in presence of error + x := int64(ux >> 1) + if ux&1 != 0 { + x = ^x + } + return x, err +} |