feat(db): 添加对达梦数据库的支持

- 在应用程序中新增对达梦数据库（DM）的配置和连接支持
- 实现 SetDmDB 函数以配置达梦数据库连接
- 更新数据库操作逻辑，支持达梦特有的 SQL 语法和功能
- 在相关文件中添加达梦数据库的处理逻辑，包括表创建、数据插入和查询
- 更新 go.mod 和 go.sum 文件以引入达梦数据库驱动
- 增强文档，详细说明达梦数据库的配置和使用方法

vendor/golang.org/x/text/encoding/charmap/charmap.go

@@ -0,0 +1,249 @@
+// Copyright 2013 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.
+
+//go:generate go run maketables.go
+
+// Package charmap provides simple character encodings such as IBM Code Page 437
+// and Windows 1252.
+package charmap // import "golang.org/x/text/encoding/charmap"
+
+import (
+	"unicode/utf8"
+
+	"golang.org/x/text/encoding"
+	"golang.org/x/text/encoding/internal"
+	"golang.org/x/text/encoding/internal/identifier"
+	"golang.org/x/text/transform"
+)
+
+// These encodings vary only in the way clients should interpret them. Their
+// coded character set is identical and a single implementation can be shared.
+var (
+	// ISO8859_6E is the ISO 8859-6E encoding.
+	ISO8859_6E encoding.Encoding = &iso8859_6E
+
+	// ISO8859_6I is the ISO 8859-6I encoding.
+	ISO8859_6I encoding.Encoding = &iso8859_6I
+
+	// ISO8859_8E is the ISO 8859-8E encoding.
+	ISO8859_8E encoding.Encoding = &iso8859_8E
+
+	// ISO8859_8I is the ISO 8859-8I encoding.
+	ISO8859_8I encoding.Encoding = &iso8859_8I
+
+	iso8859_6E = internal.Encoding{
+		Encoding: ISO8859_6,
+		Name:     "ISO-8859-6E",
+		MIB:      identifier.ISO88596E,
+	}
+
+	iso8859_6I = internal.Encoding{
+		Encoding: ISO8859_6,
+		Name:     "ISO-8859-6I",
+		MIB:      identifier.ISO88596I,
+	}
+
+	iso8859_8E = internal.Encoding{
+		Encoding: ISO8859_8,
+		Name:     "ISO-8859-8E",
+		MIB:      identifier.ISO88598E,
+	}
+
+	iso8859_8I = internal.Encoding{
+		Encoding: ISO8859_8,
+		Name:     "ISO-8859-8I",
+		MIB:      identifier.ISO88598I,
+	}
+)
+
+// All is a list of all defined encodings in this package.
+var All []encoding.Encoding = listAll
+
+// TODO: implement these encodings, in order of importance.
+// ASCII, ISO8859_1:       Rather common. Close to Windows 1252.
+// ISO8859_9:              Close to Windows 1254.
+
+// utf8Enc holds a rune's UTF-8 encoding in data[:len].
+type utf8Enc struct {
+	len  uint8
+	data [3]byte
+}
+
+// Charmap is an 8-bit character set encoding.
+type Charmap struct {
+	// name is the encoding's name.
+	name string
+	// mib is the encoding type of this encoder.
+	mib identifier.MIB
+	// asciiSuperset states whether the encoding is a superset of ASCII.
+	asciiSuperset bool
+	// low is the lower bound of the encoded byte for a non-ASCII rune. If
+	// Charmap.asciiSuperset is true then this will be 0x80, otherwise 0x00.
+	low uint8
+	// replacement is the encoded replacement character.
+	replacement byte
+	// decode is the map from encoded byte to UTF-8.
+	decode [256]utf8Enc
+	// encoding is the map from runes to encoded bytes. Each entry is a
+	// uint32: the high 8 bits are the encoded byte and the low 24 bits are
+	// the rune. The table entries are sorted by ascending rune.
+	encode [256]uint32
+}
+
+// NewDecoder implements the encoding.Encoding interface.
+func (m *Charmap) NewDecoder() *encoding.Decoder {
+	return &encoding.Decoder{Transformer: charmapDecoder{charmap: m}}
+}
+
+// NewEncoder implements the encoding.Encoding interface.
+func (m *Charmap) NewEncoder() *encoding.Encoder {
+	return &encoding.Encoder{Transformer: charmapEncoder{charmap: m}}
+}
+
+// String returns the Charmap's name.
+func (m *Charmap) String() string {
+	return m.name
+}
+
+// ID implements an internal interface.
+func (m *Charmap) ID() (mib identifier.MIB, other string) {
+	return m.mib, ""
+}
+
+// charmapDecoder implements transform.Transformer by decoding to UTF-8.
+type charmapDecoder struct {
+	transform.NopResetter
+	charmap *Charmap
+}
+
+func (m charmapDecoder) Transform(dst, src []byte, atEOF bool) (nDst, nSrc int, err error) {
+	for i, c := range src {
+		if m.charmap.asciiSuperset && c < utf8.RuneSelf {
+			if nDst >= len(dst) {
+				err = transform.ErrShortDst
+				break
+			}
+			dst[nDst] = c
+			nDst++
+			nSrc = i + 1
+			continue
+		}
+
+		decode := &m.charmap.decode[c]
+		n := int(decode.len)
+		if nDst+n > len(dst) {
+			err = transform.ErrShortDst
+			break
+		}
+		// It's 15% faster to avoid calling copy for these tiny slices.
+		for j := 0; j < n; j++ {
+			dst[nDst] = decode.data[j]
+			nDst++
+		}
+		nSrc = i + 1
+	}
+	return nDst, nSrc, err
+}
+
+// DecodeByte returns the Charmap's rune decoding of the byte b.
+func (m *Charmap) DecodeByte(b byte) rune {
+	switch x := &m.decode[b]; x.len {
+	case 1:
+		return rune(x.data[0])
+	case 2:
+		return rune(x.data[0]&0x1f)<<6 | rune(x.data[1]&0x3f)
+	default:
+		return rune(x.data[0]&0x0f)<<12 | rune(x.data[1]&0x3f)<<6 | rune(x.data[2]&0x3f)
+	}
+}
+
+// charmapEncoder implements transform.Transformer by encoding from UTF-8.
+type charmapEncoder struct {
+	transform.NopResetter
+	charmap *Charmap
+}
+
+func (m charmapEncoder) Transform(dst, src []byte, atEOF bool) (nDst, nSrc int, err error) {
+	r, size := rune(0), 0
+loop:
+	for nSrc < len(src) {
+		if nDst >= len(dst) {
+			err = transform.ErrShortDst
+			break
+		}
+		r = rune(src[nSrc])
+
+		// Decode a 1-byte rune.
+		if r < utf8.RuneSelf {
+			if m.charmap.asciiSuperset {
+				nSrc++
+				dst[nDst] = uint8(r)
+				nDst++
+				continue
+			}
+			size = 1
+
+		} else {
+			// Decode a multi-byte rune.
+			r, size = utf8.DecodeRune(src[nSrc:])
+			if size == 1 {
+				// All valid runes of size 1 (those below utf8.RuneSelf) were
+				// handled above. We have invalid UTF-8 or we haven't seen the
+				// full character yet.
+				if !atEOF && !utf8.FullRune(src[nSrc:]) {
+					err = transform.ErrShortSrc
+				} else {
+					err = internal.RepertoireError(m.charmap.replacement)
+				}
+				break
+			}
+		}
+
+		// Binary search in [low, high) for that rune in the m.charmap.encode table.
+		for low, high := int(m.charmap.low), 0x100; ; {
+			if low >= high {
+				err = internal.RepertoireError(m.charmap.replacement)
+				break loop
+			}
+			mid := (low + high) / 2
+			got := m.charmap.encode[mid]
+			gotRune := rune(got & (1<<24 - 1))
+			if gotRune < r {
+				low = mid + 1
+			} else if gotRune > r {
+				high = mid
+			} else {
+				dst[nDst] = byte(got >> 24)
+				nDst++
+				break
+			}
+		}
+		nSrc += size
+	}
+	return nDst, nSrc, err
+}
+
+// EncodeRune returns the Charmap's byte encoding of the rune r. ok is whether
+// r is in the Charmap's repertoire. If not, b is set to the Charmap's
+// replacement byte. This is often the ASCII substitute character '\x1a'.
+func (m *Charmap) EncodeRune(r rune) (b byte, ok bool) {
+	if r < utf8.RuneSelf && m.asciiSuperset {
+		return byte(r), true
+	}
+	for low, high := int(m.low), 0x100; ; {
+		if low >= high {
+			return m.replacement, false
+		}
+		mid := (low + high) / 2
+		got := m.encode[mid]
+		gotRune := rune(got & (1<<24 - 1))
+		if gotRune < r {
+			low = mid + 1
+		} else if gotRune > r {
+			high = mid
+		} else {
+			return byte(got >> 24), true
+		}
+	}
+}

vendor/golang.org/x/text/encoding/encoding.go

@@ -0,0 +1,335 @@
+// Copyright 2013 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 encoding defines an interface for character encodings, such as Shift
+// JIS and Windows 1252, that can convert to and from UTF-8.
+//
+// Encoding implementations are provided in other packages, such as
+// golang.org/x/text/encoding/charmap and
+// golang.org/x/text/encoding/japanese.
+package encoding // import "golang.org/x/text/encoding"
+
+import (
+	"errors"
+	"io"
+	"strconv"
+	"unicode/utf8"
+
+	"golang.org/x/text/encoding/internal/identifier"
+	"golang.org/x/text/transform"
+)
+
+// TODO:
+// - There seems to be some inconsistency in when decoders return errors
+//   and when not. Also documentation seems to suggest they shouldn't return
+//   errors at all (except for UTF-16).
+// - Encoders seem to rely on or at least benefit from the input being in NFC
+//   normal form. Perhaps add an example how users could prepare their output.
+
+// Encoding is a character set encoding that can be transformed to and from
+// UTF-8.
+type Encoding interface {
+	// NewDecoder returns a Decoder.
+	NewDecoder() *Decoder
+
+	// NewEncoder returns an Encoder.
+	NewEncoder() *Encoder
+}
+
+// A Decoder converts bytes to UTF-8. It implements transform.Transformer.
+//
+// Transforming source bytes that are not of that encoding will not result in an
+// error per se. Each byte that cannot be transcoded will be represented in the
+// output by the UTF-8 encoding of '\uFFFD', the replacement rune.
+type Decoder struct {
+	transform.Transformer
+
+	// This forces external creators of Decoders to use names in struct
+	// initializers, allowing for future extendibility without having to break
+	// code.
+	_ struct{}
+}
+
+// Bytes converts the given encoded bytes to UTF-8. It returns the converted
+// bytes or nil, err if any error occurred.
+func (d *Decoder) Bytes(b []byte) ([]byte, error) {
+	b, _, err := transform.Bytes(d, b)
+	if err != nil {
+		return nil, err
+	}
+	return b, nil
+}
+
+// String converts the given encoded string to UTF-8. It returns the converted
+// string or "", err if any error occurred.
+func (d *Decoder) String(s string) (string, error) {
+	s, _, err := transform.String(d, s)
+	if err != nil {
+		return "", err
+	}
+	return s, nil
+}
+
+// Reader wraps another Reader to decode its bytes.
+//
+// The Decoder may not be used for any other operation as long as the returned
+// Reader is in use.
+func (d *Decoder) Reader(r io.Reader) io.Reader {
+	return transform.NewReader(r, d)
+}
+
+// An Encoder converts bytes from UTF-8. It implements transform.Transformer.
+//
+// Each rune that cannot be transcoded will result in an error. In this case,
+// the transform will consume all source byte up to, not including the offending
+// rune. Transforming source bytes that are not valid UTF-8 will be replaced by
+// `\uFFFD`. To return early with an error instead, use transform.Chain to
+// preprocess the data with a UTF8Validator.
+type Encoder struct {
+	transform.Transformer
+
+	// This forces external creators of Encoders to use names in struct
+	// initializers, allowing for future extendibility without having to break
+	// code.
+	_ struct{}
+}
+
+// Bytes converts bytes from UTF-8. It returns the converted bytes or nil, err if
+// any error occurred.
+func (e *Encoder) Bytes(b []byte) ([]byte, error) {
+	b, _, err := transform.Bytes(e, b)
+	if err != nil {
+		return nil, err
+	}
+	return b, nil
+}
+
+// String converts a string from UTF-8. It returns the converted string or
+// "", err if any error occurred.
+func (e *Encoder) String(s string) (string, error) {
+	s, _, err := transform.String(e, s)
+	if err != nil {
+		return "", err
+	}
+	return s, nil
+}
+
+// Writer wraps another Writer to encode its UTF-8 output.
+//
+// The Encoder may not be used for any other operation as long as the returned
+// Writer is in use.
+func (e *Encoder) Writer(w io.Writer) io.Writer {
+	return transform.NewWriter(w, e)
+}
+
+// ASCIISub is the ASCII substitute character, as recommended by
+// https://unicode.org/reports/tr36/#Text_Comparison
+const ASCIISub = '\x1a'
+
+// Nop is the nop encoding. Its transformed bytes are the same as the source
+// bytes; it does not replace invalid UTF-8 sequences.
+var Nop Encoding = nop{}
+
+type nop struct{}
+
+func (nop) NewDecoder() *Decoder {
+	return &Decoder{Transformer: transform.Nop}
+}
+func (nop) NewEncoder() *Encoder {
+	return &Encoder{Transformer: transform.Nop}
+}
+
+// Replacement is the replacement encoding. Decoding from the replacement
+// encoding yields a single '\uFFFD' replacement rune. Encoding from UTF-8 to
+// the replacement encoding yields the same as the source bytes except that
+// invalid UTF-8 is converted to '\uFFFD'.
+//
+// It is defined at http://encoding.spec.whatwg.org/#replacement
+var Replacement Encoding = replacement{}
+
+type replacement struct{}
+
+func (replacement) NewDecoder() *Decoder {
+	return &Decoder{Transformer: replacementDecoder{}}
+}
+
+func (replacement) NewEncoder() *Encoder {
+	return &Encoder{Transformer: replacementEncoder{}}
+}
+
+func (replacement) ID() (mib identifier.MIB, other string) {
+	return identifier.Replacement, ""
+}
+
+type replacementDecoder struct{ transform.NopResetter }
+
+func (replacementDecoder) Transform(dst, src []byte, atEOF bool) (nDst, nSrc int, err error) {
+	if len(dst) < 3 {
+		return 0, 0, transform.ErrShortDst
+	}
+	if atEOF {
+		const fffd = "\ufffd"
+		dst[0] = fffd[0]
+		dst[1] = fffd[1]
+		dst[2] = fffd[2]
+		nDst = 3
+	}
+	return nDst, len(src), nil
+}
+
+type replacementEncoder struct{ transform.NopResetter }
+
+func (replacementEncoder) Transform(dst, src []byte, atEOF bool) (nDst, nSrc int, err error) {
+	r, size := rune(0), 0
+
+	for ; nSrc < len(src); nSrc += size {
+		r = rune(src[nSrc])
+
+		// Decode a 1-byte rune.
+		if r < utf8.RuneSelf {
+			size = 1
+
+		} else {
+			// Decode a multi-byte rune.
+			r, size = utf8.DecodeRune(src[nSrc:])
+			if size == 1 {
+				// All valid runes of size 1 (those below utf8.RuneSelf) were
+				// handled above. We have invalid UTF-8 or we haven't seen the
+				// full character yet.
+				if !atEOF && !utf8.FullRune(src[nSrc:]) {
+					err = transform.ErrShortSrc
+					break
+				}
+				r = '\ufffd'
+			}
+		}
+
+		if nDst+utf8.RuneLen(r) > len(dst) {
+			err = transform.ErrShortDst
+			break
+		}
+		nDst += utf8.EncodeRune(dst[nDst:], r)
+	}
+	return nDst, nSrc, err
+}
+
+// HTMLEscapeUnsupported wraps encoders to replace source runes outside the
+// repertoire of the destination encoding with HTML escape sequences.
+//
+// This wrapper exists to comply to URL and HTML forms requiring a
+// non-terminating legacy encoder. The produced sequences may lead to data
+// loss as they are indistinguishable from legitimate input. To avoid this
+// issue, use UTF-8 encodings whenever possible.
+func HTMLEscapeUnsupported(e *Encoder) *Encoder {
+	return &Encoder{Transformer: &errorHandler{e, errorToHTML}}
+}
+
+// ReplaceUnsupported wraps encoders to replace source runes outside the
+// repertoire of the destination encoding with an encoding-specific
+// replacement.
+//
+// This wrapper is only provided for backwards compatibility and legacy
+// handling. Its use is strongly discouraged. Use UTF-8 whenever possible.
+func ReplaceUnsupported(e *Encoder) *Encoder {
+	return &Encoder{Transformer: &errorHandler{e, errorToReplacement}}
+}
+
+type errorHandler struct {
+	*Encoder
+	handler func(dst []byte, r rune, err repertoireError) (n int, ok bool)
+}
+
+// TODO: consider making this error public in some form.
+type repertoireError interface {
+	Replacement() byte
+}
+
+func (h errorHandler) Transform(dst, src []byte, atEOF bool) (nDst, nSrc int, err error) {
+	nDst, nSrc, err = h.Transformer.Transform(dst, src, atEOF)
+	for err != nil {
+		rerr, ok := err.(repertoireError)
+		if !ok {
+			return nDst, nSrc, err
+		}
+		r, sz := utf8.DecodeRune(src[nSrc:])
+		n, ok := h.handler(dst[nDst:], r, rerr)
+		if !ok {
+			return nDst, nSrc, transform.ErrShortDst
+		}
+		err = nil
+		nDst += n
+		if nSrc += sz; nSrc < len(src) {
+			var dn, sn int
+			dn, sn, err = h.Transformer.Transform(dst[nDst:], src[nSrc:], atEOF)
+			nDst += dn
+			nSrc += sn
+		}
+	}
+	return nDst, nSrc, err
+}
+
+func errorToHTML(dst []byte, r rune, err repertoireError) (n int, ok bool) {
+	buf := [8]byte{}
+	b := strconv.AppendUint(buf[:0], uint64(r), 10)
+	if n = len(b) + len("&#;"); n >= len(dst) {
+		return 0, false
+	}
+	dst[0] = '&'
+	dst[1] = '#'
+	dst[copy(dst[2:], b)+2] = ';'
+	return n, true
+}
+
+func errorToReplacement(dst []byte, r rune, err repertoireError) (n int, ok bool) {
+	if len(dst) == 0 {
+		return 0, false
+	}
+	dst[0] = err.Replacement()
+	return 1, true
+}
+
+// ErrInvalidUTF8 means that a transformer encountered invalid UTF-8.
+var ErrInvalidUTF8 = errors.New("encoding: invalid UTF-8")
+
+// UTF8Validator is a transformer that returns ErrInvalidUTF8 on the first
+// input byte that is not valid UTF-8.
+var UTF8Validator transform.Transformer = utf8Validator{}
+
+type utf8Validator struct{ transform.NopResetter }
+
+func (utf8Validator) Transform(dst, src []byte, atEOF bool) (nDst, nSrc int, err error) {
+	n := len(src)
+	if n > len(dst) {
+		n = len(dst)
+	}
+	for i := 0; i < n; {
+		if c := src[i]; c < utf8.RuneSelf {
+			dst[i] = c
+			i++
+			continue
+		}
+		_, size := utf8.DecodeRune(src[i:])
+		if size == 1 {
+			// All valid runes of size 1 (those below utf8.RuneSelf) were
+			// handled above. We have invalid UTF-8 or we haven't seen the
+			// full character yet.
+			err = ErrInvalidUTF8
+			if !atEOF && !utf8.FullRune(src[i:]) {
+				err = transform.ErrShortSrc
+			}
+			return i, i, err
+		}
+		if i+size > len(dst) {
+			return i, i, transform.ErrShortDst
+		}
+		for ; size > 0; size-- {
+			dst[i] = src[i]
+			i++
+		}
+	}
+	if len(src) > len(dst) {
+		err = transform.ErrShortDst
+	}
+	return n, n, err
+}

vendor/golang.org/x/text/encoding/ianaindex/ascii.go

@@ -0,0 +1,74 @@
+// Copyright 2019 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 ianaindex
+
+import (
+	"unicode"
+	"unicode/utf8"
+
+	"golang.org/x/text/encoding"
+	"golang.org/x/text/encoding/internal"
+	"golang.org/x/text/encoding/internal/identifier"
+	"golang.org/x/text/transform"
+)
+
+type asciiDecoder struct {
+	transform.NopResetter
+}
+
+func (d asciiDecoder) Transform(dst, src []byte, atEOF bool) (nDst, nSrc int, err error) {
+	for _, c := range src {
+		if c > unicode.MaxASCII {
+			r := unicode.ReplacementChar
+			if nDst+utf8.RuneLen(r) > len(dst) {
+				err = transform.ErrShortDst
+				break
+			}
+			nDst += utf8.EncodeRune(dst[nDst:], r)
+			nSrc++
+			continue
+		}
+
+		if nDst >= len(dst) {
+			err = transform.ErrShortDst
+			break
+		}
+		dst[nDst] = c
+		nDst++
+		nSrc++
+	}
+	return nDst, nSrc, err
+}
+
+type asciiEncoder struct {
+	transform.NopResetter
+}
+
+func (d asciiEncoder) Transform(dst, src []byte, atEOF bool) (nDst, nSrc int, err error) {
+	for _, c := range src {
+		if c > unicode.MaxASCII {
+			err = internal.RepertoireError(encoding.ASCIISub)
+			break
+		}
+
+		if nDst >= len(dst) {
+			err = transform.ErrShortDst
+			break
+		}
+		dst[nDst] = c
+		nDst++
+		nSrc++
+	}
+	return nDst, nSrc, err
+}
+
+var asciiEnc = &internal.Encoding{
+	Encoding: &internal.SimpleEncoding{
+		asciiDecoder{},
+		asciiEncoder{},
+	},
+	Name: "US-ASCII",
+	MIB:  identifier.ASCII,
+}

vendor/golang.org/x/text/encoding/ianaindex/ianaindex.go

@@ -0,0 +1,214 @@
+// Copyright 2015 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.
+
+//go:generate go run gen.go
+
+// Package ianaindex maps names to Encodings as specified by the IANA registry.
+// This includes both the MIME and IANA names.
+//
+// See http://www.iana.org/assignments/character-sets/character-sets.xhtml for
+// more details.
+package ianaindex
+
+import (
+	"errors"
+	"sort"
+	"strings"
+
+	"golang.org/x/text/encoding"
+	"golang.org/x/text/encoding/charmap"
+	"golang.org/x/text/encoding/internal/identifier"
+	"golang.org/x/text/encoding/japanese"
+	"golang.org/x/text/encoding/korean"
+	"golang.org/x/text/encoding/simplifiedchinese"
+	"golang.org/x/text/encoding/traditionalchinese"
+	"golang.org/x/text/encoding/unicode"
+)
+
+// TODO: remove the "Status... incomplete" in the package doc comment.
+// TODO: allow users to specify their own aliases?
+// TODO: allow users to specify their own indexes?
+// TODO: allow canonicalizing names
+
+// NOTE: only use these top-level variables if we can get the linker to drop
+// the indexes when they are not used. Make them a function or perhaps only
+// support MIME otherwise.
+
+var (
+	// MIME is an index to map MIME names.
+	MIME *Index = mime
+
+	// IANA is an index that supports all names and aliases using IANA names as
+	// the canonical identifier.
+	IANA *Index = iana
+
+	// MIB is an index that associates the MIB display name with an Encoding.
+	MIB *Index = mib
+
+	mime = &Index{mimeName, ianaToMIB, ianaAliases, encodings[:]}
+	iana = &Index{ianaName, ianaToMIB, ianaAliases, encodings[:]}
+	mib  = &Index{mibName, ianaToMIB, ianaAliases, encodings[:]}
+)
+
+// Index maps names registered by IANA to Encodings.
+// Currently different Indexes only differ in the names they return for
+// encodings. In the future they may also differ in supported aliases.
+type Index struct {
+	names func(i int) string
+	toMIB []identifier.MIB // Sorted slice of supported MIBs
+	alias map[string]int
+	enc   []encoding.Encoding
+}
+
+var (
+	errInvalidName = errors.New("ianaindex: invalid encoding name")
+	errUnknown     = errors.New("ianaindex: unknown Encoding")
+	errUnsupported = errors.New("ianaindex: unsupported Encoding")
+)
+
+// Encoding returns an Encoding for IANA-registered names. Matching is
+// case-insensitive.
+//
+// If the provided name doesn't match a IANA-registered charset, an error is
+// returned. If the name matches a IANA-registered charset but isn't supported,
+// a nil encoding and a nil error are returned.
+func (x *Index) Encoding(name string) (encoding.Encoding, error) {
+	name = strings.TrimSpace(name)
+	// First try without lowercasing (possibly creating an allocation).
+	i, ok := x.alias[name]
+	if !ok {
+		i, ok = x.alias[strings.ToLower(name)]
+		if !ok {
+			return nil, errInvalidName
+		}
+	}
+	return x.enc[i], nil
+}
+
+// Name reports the canonical name of the given Encoding. It will return an
+// error if the e is not associated with a known encoding scheme.
+func (x *Index) Name(e encoding.Encoding) (string, error) {
+	id, ok := e.(identifier.Interface)
+	if !ok {
+		return "", errUnknown
+	}
+	mib, _ := id.ID()
+	if mib == 0 {
+		return "", errUnknown
+	}
+	v := findMIB(x.toMIB, mib)
+	if v == -1 {
+		return "", errUnsupported
+	}
+	return x.names(v), nil
+}
+
+// TODO: the coverage of this index is rather spotty. Allowing users to set
+// encodings would allow:
+// - users to increase coverage
+// - allow a partially loaded set of encodings in case the user doesn't need to
+//   them all.
+// - write an OS-specific wrapper for supported encodings and set them.
+// The exact definition of Set depends a bit on if and how we want to let users
+// write their own Encoding implementations. Also, it is not possible yet to
+// only partially load the encodings without doing some refactoring. Until this
+// is solved, we might as well not support Set.
+// // Set sets the e to be used for the encoding scheme identified by name. Only
+// // canonical names may be used. An empty name assigns e to its internally
+// // associated encoding scheme.
+// func (x *Index) Set(name string, e encoding.Encoding) error {
+// 	panic("TODO: implement")
+// }
+
+func findMIB(x []identifier.MIB, mib identifier.MIB) int {
+	i := sort.Search(len(x), func(i int) bool { return x[i] >= mib })
+	if i < len(x) && x[i] == mib {
+		return i
+	}
+	return -1
+}
+
+const maxMIMENameLen = '0' - 1 // officially 40, but we leave some buffer.
+
+func mimeName(x int) string {
+	n := ianaNames[x]
+	// See gen.go for a description of the encoding.
+	if n[0] <= maxMIMENameLen {
+		return n[1:n[0]]
+	}
+	return n
+}
+
+func ianaName(x int) string {
+	n := ianaNames[x]
+	// See gen.go for a description of the encoding.
+	if n[0] <= maxMIMENameLen {
+		return n[n[0]:]
+	}
+	return n
+}
+
+func mibName(x int) string {
+	return mibNames[x]
+}
+
+var encodings = [numIANA]encoding.Encoding{
+	enc3:    asciiEnc,
+	enc106:  unicode.UTF8,
+	enc1015: unicode.UTF16(unicode.BigEndian, unicode.UseBOM),
+	enc1013: unicode.UTF16(unicode.BigEndian, unicode.IgnoreBOM),
+	enc1014: unicode.UTF16(unicode.LittleEndian, unicode.IgnoreBOM),
+	enc2028: charmap.CodePage037,
+	enc2011: charmap.CodePage437,
+	enc2009: charmap.CodePage850,
+	enc2010: charmap.CodePage852,
+	enc2046: charmap.CodePage855,
+	enc2089: charmap.CodePage858,
+	enc2048: charmap.CodePage860,
+	enc2013: charmap.CodePage862,
+	enc2050: charmap.CodePage863,
+	enc2052: charmap.CodePage865,
+	enc2086: charmap.CodePage866,
+	enc2102: charmap.CodePage1047,
+	enc2091: charmap.CodePage1140,
+	enc4:    charmap.ISO8859_1,
+	enc5:    charmap.ISO8859_2,
+	enc6:    charmap.ISO8859_3,
+	enc7:    charmap.ISO8859_4,
+	enc8:    charmap.ISO8859_5,
+	enc9:    charmap.ISO8859_6,
+	enc81:   charmap.ISO8859_6E,
+	enc82:   charmap.ISO8859_6I,
+	enc10:   charmap.ISO8859_7,
+	enc11:   charmap.ISO8859_8,
+	enc84:   charmap.ISO8859_8E,
+	enc85:   charmap.ISO8859_8I,
+	enc12:   charmap.ISO8859_9,
+	enc13:   charmap.ISO8859_10,
+	enc109:  charmap.ISO8859_13,
+	enc110:  charmap.ISO8859_14,
+	enc111:  charmap.ISO8859_15,
+	enc112:  charmap.ISO8859_16,
+	enc2084: charmap.KOI8R,
+	enc2088: charmap.KOI8U,
+	enc2027: charmap.Macintosh,
+	enc2109: charmap.Windows874,
+	enc2250: charmap.Windows1250,
+	enc2251: charmap.Windows1251,
+	enc2252: charmap.Windows1252,
+	enc2253: charmap.Windows1253,
+	enc2254: charmap.Windows1254,
+	enc2255: charmap.Windows1255,
+	enc2256: charmap.Windows1256,
+	enc2257: charmap.Windows1257,
+	enc2258: charmap.Windows1258,
+	enc18:   japanese.EUCJP,
+	enc39:   japanese.ISO2022JP,
+	enc17:   japanese.ShiftJIS,
+	enc38:   korean.EUCKR,
+	enc114:  simplifiedchinese.GB18030,
+	enc113:  simplifiedchinese.GBK,
+	enc2085: simplifiedchinese.HZGB2312,
+	enc2026: traditionalchinese.Big5,
+}

vendor/golang.org/x/text/encoding/internal/identifier/identifier.go

@@ -0,0 +1,81 @@
+// Copyright 2015 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.
+
+//go:generate go run gen.go
+
+// Package identifier defines the contract between implementations of Encoding
+// and Index by defining identifiers that uniquely identify standardized coded
+// character sets (CCS) and character encoding schemes (CES), which we will
+// together refer to as encodings, for which Encoding implementations provide
+// converters to and from UTF-8. This package is typically only of concern to
+// implementers of Indexes and Encodings.
+//
+// One part of the identifier is the MIB code, which is defined by IANA and
+// uniquely identifies a CCS or CES. Each code is associated with data that
+// references authorities, official documentation as well as aliases and MIME
+// names.
+//
+// Not all CESs are covered by the IANA registry. The "other" string that is
+// returned by ID can be used to identify other character sets or versions of
+// existing ones.
+//
+// It is recommended that each package that provides a set of Encodings provide
+// the All and Common variables to reference all supported encodings and
+// commonly used subset. This allows Index implementations to include all
+// available encodings without explicitly referencing or knowing about them.
+package identifier
+
+// Note: this package is internal, but could be made public if there is a need
+// for writing third-party Indexes and Encodings.
+
+// References:
+// - http://source.icu-project.org/repos/icu/icu/trunk/source/data/mappings/convrtrs.txt
+// - http://www.iana.org/assignments/character-sets/character-sets.xhtml
+// - http://www.iana.org/assignments/ianacharset-mib/ianacharset-mib
+// - http://www.ietf.org/rfc/rfc2978.txt
+// - https://www.unicode.org/reports/tr22/
+// - http://www.w3.org/TR/encoding/
+// - https://encoding.spec.whatwg.org/
+// - https://encoding.spec.whatwg.org/encodings.json
+// - https://tools.ietf.org/html/rfc6657#section-5
+
+// Interface can be implemented by Encodings to define the CCS or CES for which
+// it implements conversions.
+type Interface interface {
+	// ID returns an encoding identifier. Exactly one of the mib and other
+	// values should be non-zero.
+	//
+	// In the usual case it is only necessary to indicate the MIB code. The
+	// other string can be used to specify encodings for which there is no MIB,
+	// such as "x-mac-dingbat".
+	//
+	// The other string may only contain the characters a-z, A-Z, 0-9, - and _.
+	ID() (mib MIB, other string)
+
+	// NOTE: the restrictions on the encoding are to allow extending the syntax
+	// with additional information such as versions, vendors and other variants.
+}
+
+// A MIB identifies an encoding. It is derived from the IANA MIB codes and adds
+// some identifiers for some encodings that are not covered by the IANA
+// standard.
+//
+// See http://www.iana.org/assignments/ianacharset-mib.
+type MIB uint16
+
+// These additional MIB types are not defined in IANA. They are added because
+// they are common and defined within the text repo.
+const (
+	// Unofficial marks the start of encodings not registered by IANA.
+	Unofficial MIB = 10000 + iota
+
+	// Replacement is the WhatWG replacement encoding.
+	Replacement
+
+	// XUserDefined is the code for x-user-defined.
+	XUserDefined
+
+	// MacintoshCyrillic is the code for x-mac-cyrillic.
+	MacintoshCyrillic
+)

vendor/golang.org/x/text/encoding/internal/internal.go

@@ -0,0 +1,75 @@
+// Copyright 2015 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 internal contains code that is shared among encoding implementations.
+package internal
+
+import (
+	"golang.org/x/text/encoding"
+	"golang.org/x/text/encoding/internal/identifier"
+	"golang.org/x/text/transform"
+)
+
+// Encoding is an implementation of the Encoding interface that adds the String
+// and ID methods to an existing encoding.
+type Encoding struct {
+	encoding.Encoding
+	Name string
+	MIB  identifier.MIB
+}
+
+// _ verifies that Encoding implements identifier.Interface.
+var _ identifier.Interface = (*Encoding)(nil)
+
+func (e *Encoding) String() string {
+	return e.Name
+}
+
+func (e *Encoding) ID() (mib identifier.MIB, other string) {
+	return e.MIB, ""
+}
+
+// SimpleEncoding is an Encoding that combines two Transformers.
+type SimpleEncoding struct {
+	Decoder transform.Transformer
+	Encoder transform.Transformer
+}
+
+func (e *SimpleEncoding) NewDecoder() *encoding.Decoder {
+	return &encoding.Decoder{Transformer: e.Decoder}
+}
+
+func (e *SimpleEncoding) NewEncoder() *encoding.Encoder {
+	return &encoding.Encoder{Transformer: e.Encoder}
+}
+
+// FuncEncoding is an Encoding that combines two functions returning a new
+// Transformer.
+type FuncEncoding struct {
+	Decoder func() transform.Transformer
+	Encoder func() transform.Transformer
+}
+
+func (e FuncEncoding) NewDecoder() *encoding.Decoder {
+	return &encoding.Decoder{Transformer: e.Decoder()}
+}
+
+func (e FuncEncoding) NewEncoder() *encoding.Encoder {
+	return &encoding.Encoder{Transformer: e.Encoder()}
+}
+
+// A RepertoireError indicates a rune is not in the repertoire of a destination
+// encoding. It is associated with an encoding-specific suggested replacement
+// byte.
+type RepertoireError byte
+
+// Error implements the error interrface.
+func (r RepertoireError) Error() string {
+	return "encoding: rune not supported by encoding."
+}
+
+// Replacement returns the replacement string associated with this error.
+func (r RepertoireError) Replacement() byte { return byte(r) }
+
+var ErrASCIIReplacement = RepertoireError(encoding.ASCIISub)

vendor/golang.org/x/text/encoding/japanese/all.go

@@ -0,0 +1,12 @@
+// Copyright 2015 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 japanese
+
+import (
+	"golang.org/x/text/encoding"
+)
+
+// All is a list of all defined encodings in this package.
+var All = []encoding.Encoding{EUCJP, ISO2022JP, ShiftJIS}

vendor/golang.org/x/text/encoding/japanese/eucjp.go

@@ -0,0 +1,225 @@
+// Copyright 2013 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 japanese
+
+import (
+	"unicode/utf8"
+
+	"golang.org/x/text/encoding"
+	"golang.org/x/text/encoding/internal"
+	"golang.org/x/text/encoding/internal/identifier"
+	"golang.org/x/text/transform"
+)
+
+// EUCJP is the EUC-JP encoding.
+var EUCJP encoding.Encoding = &eucJP
+
+var eucJP = internal.Encoding{
+	&internal.SimpleEncoding{eucJPDecoder{}, eucJPEncoder{}},
+	"EUC-JP",
+	identifier.EUCPkdFmtJapanese,
+}
+
+type eucJPDecoder struct{ transform.NopResetter }
+
+// See https://encoding.spec.whatwg.org/#euc-jp-decoder.
+func (eucJPDecoder) Transform(dst, src []byte, atEOF bool) (nDst, nSrc int, err error) {
+	r, size := rune(0), 0
+loop:
+	for ; nSrc < len(src); nSrc += size {
+		switch c0 := src[nSrc]; {
+		case c0 < utf8.RuneSelf:
+			r, size = rune(c0), 1
+
+		case c0 == 0x8e:
+			if nSrc+1 >= len(src) {
+				if !atEOF {
+					err = transform.ErrShortSrc
+					break loop
+				}
+				r, size = utf8.RuneError, 1
+				break
+			}
+			c1 := src[nSrc+1]
+			switch {
+			case c1 < 0xa1:
+				r, size = utf8.RuneError, 1
+			case c1 > 0xdf:
+				r, size = utf8.RuneError, 2
+				if c1 == 0xff {
+					size = 1
+				}
+			default:
+				r, size = rune(c1)+(0xff61-0xa1), 2
+			}
+		case c0 == 0x8f:
+			if nSrc+2 >= len(src) {
+				if !atEOF {
+					err = transform.ErrShortSrc
+					break loop
+				}
+				r, size = utf8.RuneError, 1
+				if p := nSrc + 1; p < len(src) && 0xa1 <= src[p] && src[p] < 0xfe {
+					size = 2
+				}
+				break
+			}
+			c1 := src[nSrc+1]
+			if c1 < 0xa1 || 0xfe < c1 {
+				r, size = utf8.RuneError, 1
+				break
+			}
+			c2 := src[nSrc+2]
+			if c2 < 0xa1 || 0xfe < c2 {
+				r, size = utf8.RuneError, 2
+				break
+			}
+			r, size = utf8.RuneError, 3
+			if i := int(c1-0xa1)*94 + int(c2-0xa1); i < len(jis0212Decode) {
+				r = rune(jis0212Decode[i])
+				if r == 0 {
+					r = utf8.RuneError
+				}
+			}
+
+		case 0xa1 <= c0 && c0 <= 0xfe:
+			if nSrc+1 >= len(src) {
+				if !atEOF {
+					err = transform.ErrShortSrc
+					break loop
+				}
+				r, size = utf8.RuneError, 1
+				break
+			}
+			c1 := src[nSrc+1]
+			if c1 < 0xa1 || 0xfe < c1 {
+				r, size = utf8.RuneError, 1
+				break
+			}
+			r, size = utf8.RuneError, 2
+			if i := int(c0-0xa1)*94 + int(c1-0xa1); i < len(jis0208Decode) {
+				r = rune(jis0208Decode[i])
+				if r == 0 {
+					r = utf8.RuneError
+				}
+			}
+
+		default:
+			r, size = utf8.RuneError, 1
+		}
+
+		if nDst+utf8.RuneLen(r) > len(dst) {
+			err = transform.ErrShortDst
+			break loop
+		}
+		nDst += utf8.EncodeRune(dst[nDst:], r)
+	}
+	return nDst, nSrc, err
+}
+
+type eucJPEncoder struct{ transform.NopResetter }
+
+func (eucJPEncoder) Transform(dst, src []byte, atEOF bool) (nDst, nSrc int, err error) {
+	r, size := rune(0), 0
+	for ; nSrc < len(src); nSrc += size {
+		r = rune(src[nSrc])
+
+		// Decode a 1-byte rune.
+		if r < utf8.RuneSelf {
+			size = 1
+
+		} else {
+			// Decode a multi-byte rune.
+			r, size = utf8.DecodeRune(src[nSrc:])
+			if size == 1 {
+				// All valid runes of size 1 (those below utf8.RuneSelf) were
+				// handled above. We have invalid UTF-8 or we haven't seen the
+				// full character yet.
+				if !atEOF && !utf8.FullRune(src[nSrc:]) {
+					err = transform.ErrShortSrc
+					break
+				}
+			}
+
+			// func init checks that the switch covers all tables.
+			switch {
+			case encode0Low <= r && r < encode0High:
+				if r = rune(encode0[r-encode0Low]); r != 0 {
+					goto write2or3
+				}
+			case encode1Low <= r && r < encode1High:
+				if r = rune(encode1[r-encode1Low]); r != 0 {
+					goto write2or3
+				}
+			case encode2Low <= r && r < encode2High:
+				if r = rune(encode2[r-encode2Low]); r != 0 {
+					goto write2or3
+				}
+			case encode3Low <= r && r < encode3High:
+				if r = rune(encode3[r-encode3Low]); r != 0 {
+					goto write2or3
+				}
+			case encode4Low <= r && r < encode4High:
+				if r = rune(encode4[r-encode4Low]); r != 0 {
+					goto write2or3
+				}
+			case encode5Low <= r && r < encode5High:
+				if 0xff61 <= r && r < 0xffa0 {
+					goto write2
+				}
+				if r = rune(encode5[r-encode5Low]); r != 0 {
+					goto write2or3
+				}
+			}
+			err = internal.ErrASCIIReplacement
+			break
+		}
+
+		if nDst >= len(dst) {
+			err = transform.ErrShortDst
+			break
+		}
+		dst[nDst] = uint8(r)
+		nDst++
+		continue
+
+	write2or3:
+		if r>>tableShift == jis0208 {
+			if nDst+2 > len(dst) {
+				err = transform.ErrShortDst
+				break
+			}
+		} else {
+			if nDst+3 > len(dst) {
+				err = transform.ErrShortDst
+				break
+			}
+			dst[nDst] = 0x8f
+			nDst++
+		}
+		dst[nDst+0] = 0xa1 + uint8(r>>codeShift)&codeMask
+		dst[nDst+1] = 0xa1 + uint8(r)&codeMask
+		nDst += 2
+		continue
+
+	write2:
+		if nDst+2 > len(dst) {
+			err = transform.ErrShortDst
+			break
+		}
+		dst[nDst+0] = 0x8e
+		dst[nDst+1] = uint8(r - (0xff61 - 0xa1))
+		nDst += 2
+		continue
+	}
+	return nDst, nSrc, err
+}
+
+func init() {
+	// Check that the hard-coded encode switch covers all tables.
+	if numEncodeTables != 6 {
+		panic("bad numEncodeTables")
+	}
+}

vendor/golang.org/x/text/encoding/japanese/iso2022jp.go

@@ -0,0 +1,299 @@
+// Copyright 2013 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 japanese
+
+import (
+	"unicode/utf8"
+
+	"golang.org/x/text/encoding"
+	"golang.org/x/text/encoding/internal"
+	"golang.org/x/text/encoding/internal/identifier"
+	"golang.org/x/text/transform"
+)
+
+// ISO2022JP is the ISO-2022-JP encoding.
+var ISO2022JP encoding.Encoding = &iso2022JP
+
+var iso2022JP = internal.Encoding{
+	internal.FuncEncoding{iso2022JPNewDecoder, iso2022JPNewEncoder},
+	"ISO-2022-JP",
+	identifier.ISO2022JP,
+}
+
+func iso2022JPNewDecoder() transform.Transformer {
+	return new(iso2022JPDecoder)
+}
+
+func iso2022JPNewEncoder() transform.Transformer {
+	return new(iso2022JPEncoder)
+}
+
+const (
+	asciiState = iota
+	katakanaState
+	jis0208State
+	jis0212State
+)
+
+const asciiEsc = 0x1b
+
+type iso2022JPDecoder int
+
+func (d *iso2022JPDecoder) Reset() {
+	*d = asciiState
+}
+
+func (d *iso2022JPDecoder) Transform(dst, src []byte, atEOF bool) (nDst, nSrc int, err error) {
+	r, size := rune(0), 0
+	for ; nSrc < len(src); nSrc += size {
+		c0 := src[nSrc]
+		if c0 >= utf8.RuneSelf {
+			r, size = '\ufffd', 1
+			goto write
+		}
+
+		if c0 == asciiEsc {
+			if nSrc+2 >= len(src) {
+				if !atEOF {
+					return nDst, nSrc, transform.ErrShortSrc
+				}
+				// TODO: is it correct to only skip 1??
+				r, size = '\ufffd', 1
+				goto write
+			}
+			size = 3
+			c1 := src[nSrc+1]
+			c2 := src[nSrc+2]
+			switch {
+			case c1 == '$' && (c2 == '@' || c2 == 'B'): // 0x24 {0x40, 0x42}
+				*d = jis0208State
+				continue
+			case c1 == '$' && c2 == '(': // 0x24 0x28
+				if nSrc+3 >= len(src) {
+					if !atEOF {
+						return nDst, nSrc, transform.ErrShortSrc
+					}
+					r, size = '\ufffd', 1
+					goto write
+				}
+				size = 4
+				if src[nSrc+3] == 'D' {
+					*d = jis0212State
+					continue
+				}
+			case c1 == '(' && (c2 == 'B' || c2 == 'J'): // 0x28 {0x42, 0x4A}
+				*d = asciiState
+				continue
+			case c1 == '(' && c2 == 'I': // 0x28 0x49
+				*d = katakanaState
+				continue
+			}
+			r, size = '\ufffd', 1
+			goto write
+		}
+
+		switch *d {
+		case asciiState:
+			r, size = rune(c0), 1
+
+		case katakanaState:
+			if c0 < 0x21 || 0x60 <= c0 {
+				r, size = '\ufffd', 1
+				goto write
+			}
+			r, size = rune(c0)+(0xff61-0x21), 1
+
+		default:
+			if c0 == 0x0a {
+				*d = asciiState
+				r, size = rune(c0), 1
+				goto write
+			}
+			if nSrc+1 >= len(src) {
+				if !atEOF {
+					return nDst, nSrc, transform.ErrShortSrc
+				}
+				r, size = '\ufffd', 1
+				goto write
+			}
+			size = 2
+			c1 := src[nSrc+1]
+			i := int(c0-0x21)*94 + int(c1-0x21)
+			if *d == jis0208State && i < len(jis0208Decode) {
+				r = rune(jis0208Decode[i])
+			} else if *d == jis0212State && i < len(jis0212Decode) {
+				r = rune(jis0212Decode[i])
+			} else {
+				r = '\ufffd'
+				goto write
+			}
+			if r == 0 {
+				r = '\ufffd'
+			}
+		}
+
+	write:
+		if nDst+utf8.RuneLen(r) > len(dst) {
+			return nDst, nSrc, transform.ErrShortDst
+		}
+		nDst += utf8.EncodeRune(dst[nDst:], r)
+	}
+	return nDst, nSrc, err
+}
+
+type iso2022JPEncoder int
+
+func (e *iso2022JPEncoder) Reset() {
+	*e = asciiState
+}
+
+func (e *iso2022JPEncoder) Transform(dst, src []byte, atEOF bool) (nDst, nSrc int, err error) {
+	r, size := rune(0), 0
+	for ; nSrc < len(src); nSrc += size {
+		r = rune(src[nSrc])
+
+		// Decode a 1-byte rune.
+		if r < utf8.RuneSelf {
+			size = 1
+
+		} else {
+			// Decode a multi-byte rune.
+			r, size = utf8.DecodeRune(src[nSrc:])
+			if size == 1 {
+				// All valid runes of size 1 (those below utf8.RuneSelf) were
+				// handled above. We have invalid UTF-8 or we haven't seen the
+				// full character yet.
+				if !atEOF && !utf8.FullRune(src[nSrc:]) {
+					err = transform.ErrShortSrc
+					break
+				}
+			}
+
+			// func init checks that the switch covers all tables.
+			//
+			// http://encoding.spec.whatwg.org/#iso-2022-jp says that "the index jis0212
+			// is not used by the iso-2022-jp encoder due to lack of widespread support".
+			//
+			// TODO: do we have to special-case U+00A5 and U+203E, as per
+			// http://encoding.spec.whatwg.org/#iso-2022-jp
+			// Doing so would mean that "\u00a5" would not be preserved
+			// after an encode-decode round trip.
+			switch {
+			case encode0Low <= r && r < encode0High:
+				if r = rune(encode0[r-encode0Low]); r>>tableShift == jis0208 {
+					goto writeJIS
+				}
+			case encode1Low <= r && r < encode1High:
+				if r = rune(encode1[r-encode1Low]); r>>tableShift == jis0208 {
+					goto writeJIS
+				}
+			case encode2Low <= r && r < encode2High:
+				if r = rune(encode2[r-encode2Low]); r>>tableShift == jis0208 {
+					goto writeJIS
+				}
+			case encode3Low <= r && r < encode3High:
+				if r = rune(encode3[r-encode3Low]); r>>tableShift == jis0208 {
+					goto writeJIS
+				}
+			case encode4Low <= r && r < encode4High:
+				if r = rune(encode4[r-encode4Low]); r>>tableShift == jis0208 {
+					goto writeJIS
+				}
+			case encode5Low <= r && r < encode5High:
+				if 0xff61 <= r && r < 0xffa0 {
+					goto writeKatakana
+				}
+				if r = rune(encode5[r-encode5Low]); r>>tableShift == jis0208 {
+					goto writeJIS
+				}
+			}
+
+			// Switch back to ASCII state in case of error so that an ASCII
+			// replacement character can be written in the correct state.
+			if *e != asciiState {
+				if nDst+3 > len(dst) {
+					err = transform.ErrShortDst
+					break
+				}
+				*e = asciiState
+				dst[nDst+0] = asciiEsc
+				dst[nDst+1] = '('
+				dst[nDst+2] = 'B'
+				nDst += 3
+			}
+			err = internal.ErrASCIIReplacement
+			break
+		}
+
+		if *e != asciiState {
+			if nDst+4 > len(dst) {
+				err = transform.ErrShortDst
+				break
+			}
+			*e = asciiState
+			dst[nDst+0] = asciiEsc
+			dst[nDst+1] = '('
+			dst[nDst+2] = 'B'
+			nDst += 3
+		} else if nDst >= len(dst) {
+			err = transform.ErrShortDst
+			break
+		}
+		dst[nDst] = uint8(r)
+		nDst++
+		continue
+
+	writeJIS:
+		if *e != jis0208State {
+			if nDst+5 > len(dst) {
+				err = transform.ErrShortDst
+				break
+			}
+			*e = jis0208State
+			dst[nDst+0] = asciiEsc
+			dst[nDst+1] = '$'
+			dst[nDst+2] = 'B'
+			nDst += 3
+		} else if nDst+2 > len(dst) {
+			err = transform.ErrShortDst
+			break
+		}
+		dst[nDst+0] = 0x21 + uint8(r>>codeShift)&codeMask
+		dst[nDst+1] = 0x21 + uint8(r)&codeMask
+		nDst += 2
+		continue
+
+	writeKatakana:
+		if *e != katakanaState {
+			if nDst+4 > len(dst) {
+				err = transform.ErrShortDst
+				break
+			}
+			*e = katakanaState
+			dst[nDst+0] = asciiEsc
+			dst[nDst+1] = '('
+			dst[nDst+2] = 'I'
+			nDst += 3
+		} else if nDst >= len(dst) {
+			err = transform.ErrShortDst
+			break
+		}
+		dst[nDst] = uint8(r - (0xff61 - 0x21))
+		nDst++
+		continue
+	}
+	if atEOF && err == nil && *e != asciiState {
+		if nDst+3 > len(dst) {
+			err = transform.ErrShortDst
+		} else {
+			*e = asciiState
+			dst[nDst+0] = asciiEsc
+			dst[nDst+1] = '('
+			dst[nDst+2] = 'B'
+			nDst += 3
+		}
+	}
+	return nDst, nSrc, err
+}

vendor/golang.org/x/text/encoding/japanese/shiftjis.go

@@ -0,0 +1,189 @@
+// Copyright 2013 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 japanese
+
+import (
+	"unicode/utf8"
+
+	"golang.org/x/text/encoding"
+	"golang.org/x/text/encoding/internal"
+	"golang.org/x/text/encoding/internal/identifier"
+	"golang.org/x/text/transform"
+)
+
+// ShiftJIS is the Shift JIS encoding, also known as Code Page 932 and
+// Windows-31J.
+var ShiftJIS encoding.Encoding = &shiftJIS
+
+var shiftJIS = internal.Encoding{
+	&internal.SimpleEncoding{shiftJISDecoder{}, shiftJISEncoder{}},
+	"Shift JIS",
+	identifier.ShiftJIS,
+}
+
+type shiftJISDecoder struct{ transform.NopResetter }
+
+func (shiftJISDecoder) Transform(dst, src []byte, atEOF bool) (nDst, nSrc int, err error) {
+	r, size := rune(0), 0
+loop:
+	for ; nSrc < len(src); nSrc += size {
+		switch c0 := src[nSrc]; {
+		case c0 < utf8.RuneSelf:
+			r, size = rune(c0), 1
+
+		case 0xa1 <= c0 && c0 < 0xe0:
+			r, size = rune(c0)+(0xff61-0xa1), 1
+
+		case (0x81 <= c0 && c0 < 0xa0) || (0xe0 <= c0 && c0 < 0xfd):
+			if c0 <= 0x9f {
+				c0 -= 0x70
+			} else {
+				c0 -= 0xb0
+			}
+			c0 = 2*c0 - 0x21
+
+			if nSrc+1 >= len(src) {
+				if !atEOF {
+					err = transform.ErrShortSrc
+					break loop
+				}
+				r, size = '\ufffd', 1
+				goto write
+			}
+			c1 := src[nSrc+1]
+			switch {
+			case c1 < 0x40:
+				r, size = '\ufffd', 1 // c1 is ASCII so output on next round
+				goto write
+			case c1 < 0x7f:
+				c0--
+				c1 -= 0x40
+			case c1 == 0x7f:
+				r, size = '\ufffd', 1 // c1 is ASCII so output on next round
+				goto write
+			case c1 < 0x9f:
+				c0--
+				c1 -= 0x41
+			case c1 < 0xfd:
+				c1 -= 0x9f
+			default:
+				r, size = '\ufffd', 2
+				goto write
+			}
+			r, size = '\ufffd', 2
+			if i := int(c0)*94 + int(c1); i < len(jis0208Decode) {
+				r = rune(jis0208Decode[i])
+				if r == 0 {
+					r = '\ufffd'
+				}
+			}
+
+		case c0 == 0x80:
+			r, size = 0x80, 1
+
+		default:
+			r, size = '\ufffd', 1
+		}
+	write:
+		if nDst+utf8.RuneLen(r) > len(dst) {
+			err = transform.ErrShortDst
+			break loop
+		}
+		nDst += utf8.EncodeRune(dst[nDst:], r)
+	}
+	return nDst, nSrc, err
+}
+
+type shiftJISEncoder struct{ transform.NopResetter }
+
+func (shiftJISEncoder) Transform(dst, src []byte, atEOF bool) (nDst, nSrc int, err error) {
+	r, size := rune(0), 0
+loop:
+	for ; nSrc < len(src); nSrc += size {
+		r = rune(src[nSrc])
+
+		// Decode a 1-byte rune.
+		if r < utf8.RuneSelf {
+			size = 1
+
+		} else {
+			// Decode a multi-byte rune.
+			r, size = utf8.DecodeRune(src[nSrc:])
+			if size == 1 {
+				// All valid runes of size 1 (those below utf8.RuneSelf) were
+				// handled above. We have invalid UTF-8 or we haven't seen the
+				// full character yet.
+				if !atEOF && !utf8.FullRune(src[nSrc:]) {
+					err = transform.ErrShortSrc
+					break loop
+				}
+			}
+
+			// func init checks that the switch covers all tables.
+			switch {
+			case encode0Low <= r && r < encode0High:
+				if r = rune(encode0[r-encode0Low]); r>>tableShift == jis0208 {
+					goto write2
+				}
+			case encode1Low <= r && r < encode1High:
+				if r = rune(encode1[r-encode1Low]); r>>tableShift == jis0208 {
+					goto write2
+				}
+			case encode2Low <= r && r < encode2High:
+				if r = rune(encode2[r-encode2Low]); r>>tableShift == jis0208 {
+					goto write2
+				}
+			case encode3Low <= r && r < encode3High:
+				if r = rune(encode3[r-encode3Low]); r>>tableShift == jis0208 {
+					goto write2
+				}
+			case encode4Low <= r && r < encode4High:
+				if r = rune(encode4[r-encode4Low]); r>>tableShift == jis0208 {
+					goto write2
+				}
+			case encode5Low <= r && r < encode5High:
+				if 0xff61 <= r && r < 0xffa0 {
+					r -= 0xff61 - 0xa1
+					goto write1
+				}
+				if r = rune(encode5[r-encode5Low]); r>>tableShift == jis0208 {
+					goto write2
+				}
+			}
+			err = internal.ErrASCIIReplacement
+			break
+		}
+
+	write1:
+		if nDst >= len(dst) {
+			err = transform.ErrShortDst
+			break
+		}
+		dst[nDst] = uint8(r)
+		nDst++
+		continue
+
+	write2:
+		j1 := uint8(r>>codeShift) & codeMask
+		j2 := uint8(r) & codeMask
+		if nDst+2 > len(dst) {
+			err = transform.ErrShortDst
+			break loop
+		}
+		if j1 <= 61 {
+			dst[nDst+0] = 129 + j1/2
+		} else {
+			dst[nDst+0] = 193 + j1/2
+		}
+		if j1&1 == 0 {
+			dst[nDst+1] = j2 + j2/63 + 64
+		} else {
+			dst[nDst+1] = j2 + 159
+		}
+		nDst += 2
+		continue
+	}
+	return nDst, nSrc, err
+}

vendor/golang.org/x/text/encoding/korean/euckr.go

@@ -0,0 +1,177 @@
+// Copyright 2013 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 korean
+
+import (
+	"unicode/utf8"
+
+	"golang.org/x/text/encoding"
+	"golang.org/x/text/encoding/internal"
+	"golang.org/x/text/encoding/internal/identifier"
+	"golang.org/x/text/transform"
+)
+
+// All is a list of all defined encodings in this package.
+var All = []encoding.Encoding{EUCKR}
+
+// EUCKR is the EUC-KR encoding, also known as Code Page 949.
+var EUCKR encoding.Encoding = &eucKR
+
+var eucKR = internal.Encoding{
+	&internal.SimpleEncoding{eucKRDecoder{}, eucKREncoder{}},
+	"EUC-KR",
+	identifier.EUCKR,
+}
+
+type eucKRDecoder struct{ transform.NopResetter }
+
+func (eucKRDecoder) Transform(dst, src []byte, atEOF bool) (nDst, nSrc int, err error) {
+	r, size := rune(0), 0
+loop:
+	for ; nSrc < len(src); nSrc += size {
+		switch c0 := src[nSrc]; {
+		case c0 < utf8.RuneSelf:
+			r, size = rune(c0), 1
+
+		case 0x81 <= c0 && c0 < 0xff:
+			if nSrc+1 >= len(src) {
+				if !atEOF {
+					err = transform.ErrShortSrc
+					break loop
+				}
+				r, size = utf8.RuneError, 1
+				break
+			}
+			c1 := src[nSrc+1]
+			size = 2
+			if c0 < 0xc7 {
+				r = 178 * rune(c0-0x81)
+				switch {
+				case 0x41 <= c1 && c1 < 0x5b:
+					r += rune(c1) - (0x41 - 0*26)
+				case 0x61 <= c1 && c1 < 0x7b:
+					r += rune(c1) - (0x61 - 1*26)
+				case 0x81 <= c1 && c1 < 0xff:
+					r += rune(c1) - (0x81 - 2*26)
+				default:
+					goto decError
+				}
+			} else if 0xa1 <= c1 && c1 < 0xff {
+				r = 178*(0xc7-0x81) + rune(c0-0xc7)*94 + rune(c1-0xa1)
+			} else {
+				goto decError
+			}
+			if int(r) < len(decode) {
+				r = rune(decode[r])
+				if r != 0 {
+					break
+				}
+			}
+		decError:
+			r = utf8.RuneError
+			if c1 < utf8.RuneSelf {
+				size = 1
+			}
+
+		default:
+			r, size = utf8.RuneError, 1
+			break
+		}
+
+		if nDst+utf8.RuneLen(r) > len(dst) {
+			err = transform.ErrShortDst
+			break
+		}
+		nDst += utf8.EncodeRune(dst[nDst:], r)
+	}
+	return nDst, nSrc, err
+}
+
+type eucKREncoder struct{ transform.NopResetter }
+
+func (eucKREncoder) Transform(dst, src []byte, atEOF bool) (nDst, nSrc int, err error) {
+	r, size := rune(0), 0
+	for ; nSrc < len(src); nSrc += size {
+		r = rune(src[nSrc])
+
+		// Decode a 1-byte rune.
+		if r < utf8.RuneSelf {
+			size = 1
+
+			if nDst >= len(dst) {
+				err = transform.ErrShortDst
+				break
+			}
+			dst[nDst] = uint8(r)
+			nDst++
+			continue
+
+		} else {
+			// Decode a multi-byte rune.
+			r, size = utf8.DecodeRune(src[nSrc:])
+			if size == 1 {
+				// All valid runes of size 1 (those below utf8.RuneSelf) were
+				// handled above. We have invalid UTF-8 or we haven't seen the
+				// full character yet.
+				if !atEOF && !utf8.FullRune(src[nSrc:]) {
+					err = transform.ErrShortSrc
+					break
+				}
+			}
+
+			// func init checks that the switch covers all tables.
+			switch {
+			case encode0Low <= r && r < encode0High:
+				if r = rune(encode0[r-encode0Low]); r != 0 {
+					goto write2
+				}
+			case encode1Low <= r && r < encode1High:
+				if r = rune(encode1[r-encode1Low]); r != 0 {
+					goto write2
+				}
+			case encode2Low <= r && r < encode2High:
+				if r = rune(encode2[r-encode2Low]); r != 0 {
+					goto write2
+				}
+			case encode3Low <= r && r < encode3High:
+				if r = rune(encode3[r-encode3Low]); r != 0 {
+					goto write2
+				}
+			case encode4Low <= r && r < encode4High:
+				if r = rune(encode4[r-encode4Low]); r != 0 {
+					goto write2
+				}
+			case encode5Low <= r && r < encode5High:
+				if r = rune(encode5[r-encode5Low]); r != 0 {
+					goto write2
+				}
+			case encode6Low <= r && r < encode6High:
+				if r = rune(encode6[r-encode6Low]); r != 0 {
+					goto write2
+				}
+			}
+			err = internal.ErrASCIIReplacement
+			break
+		}
+
+	write2:
+		if nDst+2 > len(dst) {
+			err = transform.ErrShortDst
+			break
+		}
+		dst[nDst+0] = uint8(r >> 8)
+		dst[nDst+1] = uint8(r)
+		nDst += 2
+		continue
+	}
+	return nDst, nSrc, err
+}
+
+func init() {
+	// Check that the hard-coded encode switch covers all tables.
+	if numEncodeTables != 7 {
+		panic("bad numEncodeTables")
+	}
+}

vendor/golang.org/x/text/encoding/simplifiedchinese/all.go

@@ -0,0 +1,12 @@
+// Copyright 2015 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 simplifiedchinese
+
+import (
+	"golang.org/x/text/encoding"
+)
+
+// All is a list of all defined encodings in this package.
+var All = []encoding.Encoding{GB18030, GBK, HZGB2312}

vendor/golang.org/x/text/encoding/simplifiedchinese/gbk.go

@@ -0,0 +1,269 @@
+// Copyright 2013 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 simplifiedchinese
+
+import (
+	"unicode/utf8"
+
+	"golang.org/x/text/encoding"
+	"golang.org/x/text/encoding/internal"
+	"golang.org/x/text/encoding/internal/identifier"
+	"golang.org/x/text/transform"
+)
+
+var (
+	// GB18030 is the GB18030 encoding.
+	GB18030 encoding.Encoding = &gbk18030
+	// GBK is the GBK encoding. It encodes an extension of the GB2312 character set
+	// and is also known as Code Page 936.
+	GBK encoding.Encoding = &gbk
+)
+
+var gbk = internal.Encoding{
+	&internal.SimpleEncoding{
+		gbkDecoder{gb18030: false},
+		gbkEncoder{gb18030: false},
+	},
+	"GBK",
+	identifier.GBK,
+}
+
+var gbk18030 = internal.Encoding{
+	&internal.SimpleEncoding{
+		gbkDecoder{gb18030: true},
+		gbkEncoder{gb18030: true},
+	},
+	"GB18030",
+	identifier.GB18030,
+}
+
+type gbkDecoder struct {
+	transform.NopResetter
+	gb18030 bool
+}
+
+func (d gbkDecoder) Transform(dst, src []byte, atEOF bool) (nDst, nSrc int, err error) {
+	r, size := rune(0), 0
+loop:
+	for ; nSrc < len(src); nSrc += size {
+		switch c0 := src[nSrc]; {
+		case c0 < utf8.RuneSelf:
+			r, size = rune(c0), 1
+
+		// Microsoft's Code Page 936 extends GBK 1.0 to encode the euro sign U+20AC
+		// as 0x80. The HTML5 specification at http://encoding.spec.whatwg.org/#gbk
+		// says to treat "gbk" as Code Page 936.
+		case c0 == 0x80:
+			r, size = '€', 1
+
+		case c0 < 0xff:
+			if nSrc+1 >= len(src) {
+				if !atEOF {
+					err = transform.ErrShortSrc
+					break loop
+				}
+				r, size = utf8.RuneError, 1
+				goto write
+			}
+			c1 := src[nSrc+1]
+			switch {
+			case 0x40 <= c1 && c1 < 0x7f:
+				c1 -= 0x40
+			case 0x80 <= c1 && c1 < 0xff:
+				c1 -= 0x41
+			case d.gb18030 && 0x30 <= c1 && c1 < 0x40:
+				if nSrc+3 >= len(src) {
+					if !atEOF {
+						err = transform.ErrShortSrc
+						break loop
+					}
+					// The second byte here is always ASCII, so we can set size
+					// to 1 in all cases.
+					r, size = utf8.RuneError, 1
+					goto write
+				}
+				c2 := src[nSrc+2]
+				if c2 < 0x81 || 0xff <= c2 {
+					r, size = utf8.RuneError, 1
+					goto write
+				}
+				c3 := src[nSrc+3]
+				if c3 < 0x30 || 0x3a <= c3 {
+					r, size = utf8.RuneError, 1
+					goto write
+				}
+				size = 4
+				r = ((rune(c0-0x81)*10+rune(c1-0x30))*126+rune(c2-0x81))*10 + rune(c3-0x30)
+				if r < 39420 {
+					i, j := 0, len(gb18030)
+					for i < j {
+						h := i + (j-i)/2
+						if r >= rune(gb18030[h][0]) {
+							i = h + 1
+						} else {
+							j = h
+						}
+					}
+					dec := &gb18030[i-1]
+					r += rune(dec[1]) - rune(dec[0])
+					goto write
+				}
+				r -= 189000
+				if 0 <= r && r < 0x100000 {
+					r += 0x10000
+				} else {
+					r, size = utf8.RuneError, 1
+				}
+				goto write
+			default:
+				r, size = utf8.RuneError, 1
+				goto write
+			}
+			r, size = '\ufffd', 2
+			if i := int(c0-0x81)*190 + int(c1); i < len(decode) {
+				r = rune(decode[i])
+				if r == 0 {
+					r = '\ufffd'
+				}
+			}
+
+		default:
+			r, size = utf8.RuneError, 1
+		}
+
+	write:
+		if nDst+utf8.RuneLen(r) > len(dst) {
+			err = transform.ErrShortDst
+			break loop
+		}
+		nDst += utf8.EncodeRune(dst[nDst:], r)
+	}
+	return nDst, nSrc, err
+}
+
+type gbkEncoder struct {
+	transform.NopResetter
+	gb18030 bool
+}
+
+func (e gbkEncoder) Transform(dst, src []byte, atEOF bool) (nDst, nSrc int, err error) {
+	r, r2, size := rune(0), rune(0), 0
+	for ; nSrc < len(src); nSrc += size {
+		r = rune(src[nSrc])
+
+		// Decode a 1-byte rune.
+		if r < utf8.RuneSelf {
+			size = 1
+
+		} else {
+			// Decode a multi-byte rune.
+			r, size = utf8.DecodeRune(src[nSrc:])
+			if size == 1 {
+				// All valid runes of size 1 (those below utf8.RuneSelf) were
+				// handled above. We have invalid UTF-8 or we haven't seen the
+				// full character yet.
+				if !atEOF && !utf8.FullRune(src[nSrc:]) {
+					err = transform.ErrShortSrc
+					break
+				}
+			}
+
+			// func init checks that the switch covers all tables.
+			switch {
+			case encode0Low <= r && r < encode0High:
+				if r2 = rune(encode0[r-encode0Low]); r2 != 0 {
+					goto write2
+				}
+			case encode1Low <= r && r < encode1High:
+				// Microsoft's Code Page 936 extends GBK 1.0 to encode the euro sign U+20AC
+				// as 0x80. The HTML5 specification at http://encoding.spec.whatwg.org/#gbk
+				// says to treat "gbk" as Code Page 936.
+				if r == '€' {
+					r = 0x80
+					goto write1
+				}
+				if r2 = rune(encode1[r-encode1Low]); r2 != 0 {
+					goto write2
+				}
+			case encode2Low <= r && r < encode2High:
+				if r2 = rune(encode2[r-encode2Low]); r2 != 0 {
+					goto write2
+				}
+			case encode3Low <= r && r < encode3High:
+				if r2 = rune(encode3[r-encode3Low]); r2 != 0 {
+					goto write2
+				}
+			case encode4Low <= r && r < encode4High:
+				if r2 = rune(encode4[r-encode4Low]); r2 != 0 {
+					goto write2
+				}
+			}
+
+			if e.gb18030 {
+				if r < 0x10000 {
+					i, j := 0, len(gb18030)
+					for i < j {
+						h := i + (j-i)/2
+						if r >= rune(gb18030[h][1]) {
+							i = h + 1
+						} else {
+							j = h
+						}
+					}
+					dec := &gb18030[i-1]
+					r += rune(dec[0]) - rune(dec[1])
+					goto write4
+				} else if r < 0x110000 {
+					r += 189000 - 0x10000
+					goto write4
+				}
+			}
+			err = internal.ErrASCIIReplacement
+			break
+		}
+
+	write1:
+		if nDst >= len(dst) {
+			err = transform.ErrShortDst
+			break
+		}
+		dst[nDst] = uint8(r)
+		nDst++
+		continue
+
+	write2:
+		if nDst+2 > len(dst) {
+			err = transform.ErrShortDst
+			break
+		}
+		dst[nDst+0] = uint8(r2 >> 8)
+		dst[nDst+1] = uint8(r2)
+		nDst += 2
+		continue
+
+	write4:
+		if nDst+4 > len(dst) {
+			err = transform.ErrShortDst
+			break
+		}
+		dst[nDst+3] = uint8(r%10 + 0x30)
+		r /= 10
+		dst[nDst+2] = uint8(r%126 + 0x81)
+		r /= 126
+		dst[nDst+1] = uint8(r%10 + 0x30)
+		r /= 10
+		dst[nDst+0] = uint8(r + 0x81)
+		nDst += 4
+		continue
+	}
+	return nDst, nSrc, err
+}
+
+func init() {
+	// Check that the hard-coded encode switch covers all tables.
+	if numEncodeTables != 5 {
+		panic("bad numEncodeTables")
+	}
+}

vendor/golang.org/x/text/encoding/simplifiedchinese/hzgb2312.go

@@ -0,0 +1,245 @@
+// Copyright 2013 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 simplifiedchinese
+
+import (
+	"unicode/utf8"
+
+	"golang.org/x/text/encoding"
+	"golang.org/x/text/encoding/internal"
+	"golang.org/x/text/encoding/internal/identifier"
+	"golang.org/x/text/transform"
+)
+
+// HZGB2312 is the HZ-GB2312 encoding.
+var HZGB2312 encoding.Encoding = &hzGB2312
+
+var hzGB2312 = internal.Encoding{
+	internal.FuncEncoding{hzGB2312NewDecoder, hzGB2312NewEncoder},
+	"HZ-GB2312",
+	identifier.HZGB2312,
+}
+
+func hzGB2312NewDecoder() transform.Transformer {
+	return new(hzGB2312Decoder)
+}
+
+func hzGB2312NewEncoder() transform.Transformer {
+	return new(hzGB2312Encoder)
+}
+
+const (
+	asciiState = iota
+	gbState
+)
+
+type hzGB2312Decoder int
+
+func (d *hzGB2312Decoder) Reset() {
+	*d = asciiState
+}
+
+func (d *hzGB2312Decoder) Transform(dst, src []byte, atEOF bool) (nDst, nSrc int, err error) {
+	r, size := rune(0), 0
+loop:
+	for ; nSrc < len(src); nSrc += size {
+		c0 := src[nSrc]
+		if c0 >= utf8.RuneSelf {
+			r, size = utf8.RuneError, 1
+			goto write
+		}
+
+		if c0 == '~' {
+			if nSrc+1 >= len(src) {
+				if !atEOF {
+					err = transform.ErrShortSrc
+					break loop
+				}
+				r, size = utf8.RuneError, 1
+				goto write
+			}
+			size = 2
+			switch src[nSrc+1] {
+			case '{':
+				*d = gbState
+				continue
+			case '}':
+				*d = asciiState
+				continue
+			case '~':
+				if nDst >= len(dst) {
+					err = transform.ErrShortDst
+					break loop
+				}
+				dst[nDst] = '~'
+				nDst++
+				continue
+			case '\n':
+				continue
+			default:
+				r = utf8.RuneError
+				goto write
+			}
+		}
+
+		if *d == asciiState {
+			r, size = rune(c0), 1
+		} else {
+			if nSrc+1 >= len(src) {
+				if !atEOF {
+					err = transform.ErrShortSrc
+					break loop
+				}
+				r, size = utf8.RuneError, 1
+				goto write
+			}
+			size = 2
+			c1 := src[nSrc+1]
+			if c0 < 0x21 || 0x7e <= c0 || c1 < 0x21 || 0x7f <= c1 {
+				// error
+			} else if i := int(c0-0x01)*190 + int(c1+0x3f); i < len(decode) {
+				r = rune(decode[i])
+				if r != 0 {
+					goto write
+				}
+			}
+			if c1 > utf8.RuneSelf {
+				// Be consistent and always treat non-ASCII as a single error.
+				size = 1
+			}
+			r = utf8.RuneError
+		}
+
+	write:
+		if nDst+utf8.RuneLen(r) > len(dst) {
+			err = transform.ErrShortDst
+			break loop
+		}
+		nDst += utf8.EncodeRune(dst[nDst:], r)
+	}
+	return nDst, nSrc, err
+}
+
+type hzGB2312Encoder int
+
+func (d *hzGB2312Encoder) Reset() {
+	*d = asciiState
+}
+
+func (e *hzGB2312Encoder) Transform(dst, src []byte, atEOF bool) (nDst, nSrc int, err error) {
+	r, size := rune(0), 0
+	for ; nSrc < len(src); nSrc += size {
+		r = rune(src[nSrc])
+
+		// Decode a 1-byte rune.
+		if r < utf8.RuneSelf {
+			size = 1
+			if r == '~' {
+				if nDst+2 > len(dst) {
+					err = transform.ErrShortDst
+					break
+				}
+				dst[nDst+0] = '~'
+				dst[nDst+1] = '~'
+				nDst += 2
+				continue
+			} else if *e != asciiState {
+				if nDst+3 > len(dst) {
+					err = transform.ErrShortDst
+					break
+				}
+				*e = asciiState
+				dst[nDst+0] = '~'
+				dst[nDst+1] = '}'
+				nDst += 2
+			} else if nDst >= len(dst) {
+				err = transform.ErrShortDst
+				break
+			}
+			dst[nDst] = uint8(r)
+			nDst += 1
+			continue
+
+		}
+
+		// Decode a multi-byte rune.
+		r, size = utf8.DecodeRune(src[nSrc:])
+		if size == 1 {
+			// All valid runes of size 1 (those below utf8.RuneSelf) were
+			// handled above. We have invalid UTF-8 or we haven't seen the
+			// full character yet.
+			if !atEOF && !utf8.FullRune(src[nSrc:]) {
+				err = transform.ErrShortSrc
+				break
+			}
+		}
+
+		// func init checks that the switch covers all tables.
+		switch {
+		case encode0Low <= r && r < encode0High:
+			if r = rune(encode0[r-encode0Low]); r != 0 {
+				goto writeGB
+			}
+		case encode1Low <= r && r < encode1High:
+			if r = rune(encode1[r-encode1Low]); r != 0 {
+				goto writeGB
+			}
+		case encode2Low <= r && r < encode2High:
+			if r = rune(encode2[r-encode2Low]); r != 0 {
+				goto writeGB
+			}
+		case encode3Low <= r && r < encode3High:
+			if r = rune(encode3[r-encode3Low]); r != 0 {
+				goto writeGB
+			}
+		case encode4Low <= r && r < encode4High:
+			if r = rune(encode4[r-encode4Low]); r != 0 {
+				goto writeGB
+			}
+		}
+
+	terminateInASCIIState:
+		// Switch back to ASCII state in case of error so that an ASCII
+		// replacement character can be written in the correct state.
+		if *e != asciiState {
+			if nDst+2 > len(dst) {
+				err = transform.ErrShortDst
+				break
+			}
+			dst[nDst+0] = '~'
+			dst[nDst+1] = '}'
+			nDst += 2
+		}
+		err = internal.ErrASCIIReplacement
+		break
+
+	writeGB:
+		c0 := uint8(r>>8) - 0x80
+		c1 := uint8(r) - 0x80
+		if c0 < 0x21 || 0x7e <= c0 || c1 < 0x21 || 0x7f <= c1 {
+			goto terminateInASCIIState
+		}
+		if *e == asciiState {
+			if nDst+4 > len(dst) {
+				err = transform.ErrShortDst
+				break
+			}
+			*e = gbState
+			dst[nDst+0] = '~'
+			dst[nDst+1] = '{'
+			nDst += 2
+		} else if nDst+2 > len(dst) {
+			err = transform.ErrShortDst
+			break
+		}
+		dst[nDst+0] = c0
+		dst[nDst+1] = c1
+		nDst += 2
+		continue
+	}
+	// TODO: should one always terminate in ASCII state to make it safe to
+	// concatenate two HZ-GB2312-encoded strings?
+	return nDst, nSrc, err
+}

vendor/golang.org/x/text/encoding/traditionalchinese/big5.go

@@ -0,0 +1,199 @@
+// Copyright 2013 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 traditionalchinese
+
+import (
+	"unicode/utf8"
+
+	"golang.org/x/text/encoding"
+	"golang.org/x/text/encoding/internal"
+	"golang.org/x/text/encoding/internal/identifier"
+	"golang.org/x/text/transform"
+)
+
+// All is a list of all defined encodings in this package.
+var All = []encoding.Encoding{Big5}
+
+// Big5 is the Big5 encoding, also known as Code Page 950.
+var Big5 encoding.Encoding = &big5
+
+var big5 = internal.Encoding{
+	&internal.SimpleEncoding{big5Decoder{}, big5Encoder{}},
+	"Big5",
+	identifier.Big5,
+}
+
+type big5Decoder struct{ transform.NopResetter }
+
+func (big5Decoder) Transform(dst, src []byte, atEOF bool) (nDst, nSrc int, err error) {
+	r, size, s := rune(0), 0, ""
+loop:
+	for ; nSrc < len(src); nSrc += size {
+		switch c0 := src[nSrc]; {
+		case c0 < utf8.RuneSelf:
+			r, size = rune(c0), 1
+
+		case 0x81 <= c0 && c0 < 0xff:
+			if nSrc+1 >= len(src) {
+				if !atEOF {
+					err = transform.ErrShortSrc
+					break loop
+				}
+				r, size = utf8.RuneError, 1
+				goto write
+			}
+			c1 := src[nSrc+1]
+			switch {
+			case 0x40 <= c1 && c1 < 0x7f:
+				c1 -= 0x40
+			case 0xa1 <= c1 && c1 < 0xff:
+				c1 -= 0x62
+			case c1 < 0x40:
+				r, size = utf8.RuneError, 1
+				goto write
+			default:
+				r, size = utf8.RuneError, 2
+				goto write
+			}
+			r, size = '\ufffd', 2
+			if i := int(c0-0x81)*157 + int(c1); i < len(decode) {
+				if 1133 <= i && i < 1167 {
+					// The two-rune special cases for LATIN CAPITAL / SMALL E WITH CIRCUMFLEX
+					// AND MACRON / CARON are from http://encoding.spec.whatwg.org/#big5
+					switch i {
+					case 1133:
+						s = "\u00CA\u0304"
+						goto writeStr
+					case 1135:
+						s = "\u00CA\u030C"
+						goto writeStr
+					case 1164:
+						s = "\u00EA\u0304"
+						goto writeStr
+					case 1166:
+						s = "\u00EA\u030C"
+						goto writeStr
+					}
+				}
+				r = rune(decode[i])
+				if r == 0 {
+					r = '\ufffd'
+				}
+			}
+
+		default:
+			r, size = utf8.RuneError, 1
+		}
+
+	write:
+		if nDst+utf8.RuneLen(r) > len(dst) {
+			err = transform.ErrShortDst
+			break loop
+		}
+		nDst += utf8.EncodeRune(dst[nDst:], r)
+		continue loop
+
+	writeStr:
+		if nDst+len(s) > len(dst) {
+			err = transform.ErrShortDst
+			break loop
+		}
+		nDst += copy(dst[nDst:], s)
+		continue loop
+	}
+	return nDst, nSrc, err
+}
+
+type big5Encoder struct{ transform.NopResetter }
+
+func (big5Encoder) Transform(dst, src []byte, atEOF bool) (nDst, nSrc int, err error) {
+	r, size := rune(0), 0
+	for ; nSrc < len(src); nSrc += size {
+		r = rune(src[nSrc])
+
+		// Decode a 1-byte rune.
+		if r < utf8.RuneSelf {
+			size = 1
+			if nDst >= len(dst) {
+				err = transform.ErrShortDst
+				break
+			}
+			dst[nDst] = uint8(r)
+			nDst++
+			continue
+
+		} else {
+			// Decode a multi-byte rune.
+			r, size = utf8.DecodeRune(src[nSrc:])
+			if size == 1 {
+				// All valid runes of size 1 (those below utf8.RuneSelf) were
+				// handled above. We have invalid UTF-8 or we haven't seen the
+				// full character yet.
+				if !atEOF && !utf8.FullRune(src[nSrc:]) {
+					err = transform.ErrShortSrc
+					break
+				}
+			}
+		}
+
+		if r >= utf8.RuneSelf {
+			// func init checks that the switch covers all tables.
+			switch {
+			case encode0Low <= r && r < encode0High:
+				if r = rune(encode0[r-encode0Low]); r != 0 {
+					goto write2
+				}
+			case encode1Low <= r && r < encode1High:
+				if r = rune(encode1[r-encode1Low]); r != 0 {
+					goto write2
+				}
+			case encode2Low <= r && r < encode2High:
+				if r = rune(encode2[r-encode2Low]); r != 0 {
+					goto write2
+				}
+			case encode3Low <= r && r < encode3High:
+				if r = rune(encode3[r-encode3Low]); r != 0 {
+					goto write2
+				}
+			case encode4Low <= r && r < encode4High:
+				if r = rune(encode4[r-encode4Low]); r != 0 {
+					goto write2
+				}
+			case encode5Low <= r && r < encode5High:
+				if r = rune(encode5[r-encode5Low]); r != 0 {
+					goto write2
+				}
+			case encode6Low <= r && r < encode6High:
+				if r = rune(encode6[r-encode6Low]); r != 0 {
+					goto write2
+				}
+			case encode7Low <= r && r < encode7High:
+				if r = rune(encode7[r-encode7Low]); r != 0 {
+					goto write2
+				}
+			}
+			err = internal.ErrASCIIReplacement
+			break
+		}
+
+	write2:
+		if nDst+2 > len(dst) {
+			err = transform.ErrShortDst
+			break
+		}
+		dst[nDst+0] = uint8(r >> 8)
+		dst[nDst+1] = uint8(r)
+		nDst += 2
+		continue
+	}
+	return nDst, nSrc, err
+}
+
+func init() {
+	// Check that the hard-coded encode switch covers all tables.
+	if numEncodeTables != 8 {
+		panic("bad numEncodeTables")
+	}
+}

vendor/golang.org/x/text/encoding/unicode/override.go

@@ -0,0 +1,82 @@
+// Copyright 2015 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 unicode
+
+import (
+	"golang.org/x/text/transform"
+)
+
+// BOMOverride returns a new decoder transformer that is identical to fallback,
+// except that the presence of a Byte Order Mark at the start of the input
+// causes it to switch to the corresponding Unicode decoding. It will only
+// consider BOMs for UTF-8, UTF-16BE, and UTF-16LE.
+//
+// This differs from using ExpectBOM by allowing a BOM to switch to UTF-8, not
+// just UTF-16 variants, and allowing falling back to any encoding scheme.
+//
+// This technique is recommended by the W3C for use in HTML 5: "For
+// compatibility with deployed content, the byte order mark (also known as BOM)
+// is considered more authoritative than anything else."
+// http://www.w3.org/TR/encoding/#specification-hooks
+//
+// Using BOMOverride is mostly intended for use cases where the first characters
+// of a fallback encoding are known to not be a BOM, for example, for valid HTML
+// and most encodings.
+func BOMOverride(fallback transform.Transformer) transform.Transformer {
+	// TODO: possibly allow a variadic argument of unicode encodings to allow
+	// specifying details of which fallbacks are supported as well as
+	// specifying the details of the implementations. This would also allow for
+	// support for UTF-32, which should not be supported by default.
+	return &bomOverride{fallback: fallback}
+}
+
+type bomOverride struct {
+	fallback transform.Transformer
+	current  transform.Transformer
+}
+
+func (d *bomOverride) Reset() {
+	d.current = nil
+	d.fallback.Reset()
+}
+
+var (
+	// TODO: we could use decode functions here, instead of allocating a new
+	// decoder on every NewDecoder as IgnoreBOM decoders can be stateless.
+	utf16le = UTF16(LittleEndian, IgnoreBOM)
+	utf16be = UTF16(BigEndian, IgnoreBOM)
+)
+
+const utf8BOM = "\ufeff"
+
+func (d *bomOverride) Transform(dst, src []byte, atEOF bool) (nDst, nSrc int, err error) {
+	if d.current != nil {
+		return d.current.Transform(dst, src, atEOF)
+	}
+	if len(src) < 3 && !atEOF {
+		return 0, 0, transform.ErrShortSrc
+	}
+	d.current = d.fallback
+	bomSize := 0
+	if len(src) >= 2 {
+		if src[0] == 0xFF && src[1] == 0xFE {
+			d.current = utf16le.NewDecoder()
+			bomSize = 2
+		} else if src[0] == 0xFE && src[1] == 0xFF {
+			d.current = utf16be.NewDecoder()
+			bomSize = 2
+		} else if len(src) >= 3 &&
+			src[0] == utf8BOM[0] &&
+			src[1] == utf8BOM[1] &&
+			src[2] == utf8BOM[2] {
+			d.current = transform.Nop
+			bomSize = 3
+		}
+	}
+	if bomSize < len(src) {
+		nDst, nSrc, err = d.current.Transform(dst, src[bomSize:], atEOF)
+	}
+	return nDst, nSrc + bomSize, err
+}

vendor/golang.org/x/text/encoding/unicode/unicode.go

@@ -0,0 +1,512 @@
+// Copyright 2013 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 unicode provides Unicode encodings such as UTF-16.
+package unicode // import "golang.org/x/text/encoding/unicode"
+
+import (
+	"bytes"
+	"errors"
+	"unicode/utf16"
+	"unicode/utf8"
+
+	"golang.org/x/text/encoding"
+	"golang.org/x/text/encoding/internal"
+	"golang.org/x/text/encoding/internal/identifier"
+	"golang.org/x/text/internal/utf8internal"
+	"golang.org/x/text/runes"
+	"golang.org/x/text/transform"
+)
+
+// TODO: I think the Transformers really should return errors on unmatched
+// surrogate pairs and odd numbers of bytes. This is not required by RFC 2781,
+// which leaves it open, but is suggested by WhatWG. It will allow for all error
+// modes as defined by WhatWG: fatal, HTML and Replacement. This would require
+// the introduction of some kind of error type for conveying the erroneous code
+// point.
+
+// UTF8 is the UTF-8 encoding. It neither removes nor adds byte order marks.
+var UTF8 encoding.Encoding = utf8enc
+
+// UTF8BOM is an UTF-8 encoding where the decoder strips a leading byte order
+// mark while the encoder adds one.
+//
+// Some editors add a byte order mark as a signature to UTF-8 files. Although
+// the byte order mark is not useful for detecting byte order in UTF-8, it is
+// sometimes used as a convention to mark UTF-8-encoded files. This relies on
+// the observation that the UTF-8 byte order mark is either an illegal or at
+// least very unlikely sequence in any other character encoding.
+var UTF8BOM encoding.Encoding = utf8bomEncoding{}
+
+type utf8bomEncoding struct{}
+
+func (utf8bomEncoding) String() string {
+	return "UTF-8-BOM"
+}
+
+func (utf8bomEncoding) ID() (identifier.MIB, string) {
+	return identifier.Unofficial, "x-utf8bom"
+}
+
+func (utf8bomEncoding) NewEncoder() *encoding.Encoder {
+	return &encoding.Encoder{
+		Transformer: &utf8bomEncoder{t: runes.ReplaceIllFormed()},
+	}
+}
+
+func (utf8bomEncoding) NewDecoder() *encoding.Decoder {
+	return &encoding.Decoder{Transformer: &utf8bomDecoder{}}
+}
+
+var utf8enc = &internal.Encoding{
+	&internal.SimpleEncoding{utf8Decoder{}, runes.ReplaceIllFormed()},
+	"UTF-8",
+	identifier.UTF8,
+}
+
+type utf8bomDecoder struct {
+	checked bool
+}
+
+func (t *utf8bomDecoder) Reset() {
+	t.checked = false
+}
+
+func (t *utf8bomDecoder) Transform(dst, src []byte, atEOF bool) (nDst, nSrc int, err error) {
+	if !t.checked {
+		if !atEOF && len(src) < len(utf8BOM) {
+			if len(src) == 0 {
+				return 0, 0, nil
+			}
+			return 0, 0, transform.ErrShortSrc
+		}
+		if bytes.HasPrefix(src, []byte(utf8BOM)) {
+			nSrc += len(utf8BOM)
+			src = src[len(utf8BOM):]
+		}
+		t.checked = true
+	}
+	nDst, n, err := utf8Decoder.Transform(utf8Decoder{}, dst[nDst:], src, atEOF)
+	nSrc += n
+	return nDst, nSrc, err
+}
+
+type utf8bomEncoder struct {
+	written bool
+	t       transform.Transformer
+}
+
+func (t *utf8bomEncoder) Reset() {
+	t.written = false
+	t.t.Reset()
+}
+
+func (t *utf8bomEncoder) Transform(dst, src []byte, atEOF bool) (nDst, nSrc int, err error) {
+	if !t.written {
+		if len(dst) < len(utf8BOM) {
+			return nDst, 0, transform.ErrShortDst
+		}
+		nDst = copy(dst, utf8BOM)
+		t.written = true
+	}
+	n, nSrc, err := utf8Decoder.Transform(utf8Decoder{}, dst[nDst:], src, atEOF)
+	nDst += n
+	return nDst, nSrc, err
+}
+
+type utf8Decoder struct{ transform.NopResetter }
+
+func (utf8Decoder) Transform(dst, src []byte, atEOF bool) (nDst, nSrc int, err error) {
+	var pSrc int // point from which to start copy in src
+	var accept utf8internal.AcceptRange
+
+	// The decoder can only make the input larger, not smaller.
+	n := len(src)
+	if len(dst) < n {
+		err = transform.ErrShortDst
+		n = len(dst)
+		atEOF = false
+	}
+	for nSrc < n {
+		c := src[nSrc]
+		if c < utf8.RuneSelf {
+			nSrc++
+			continue
+		}
+		first := utf8internal.First[c]
+		size := int(first & utf8internal.SizeMask)
+		if first == utf8internal.FirstInvalid {
+			goto handleInvalid // invalid starter byte
+		}
+		accept = utf8internal.AcceptRanges[first>>utf8internal.AcceptShift]
+		if nSrc+size > n {
+			if !atEOF {
+				// We may stop earlier than necessary here if the short sequence
+				// has invalid bytes. Not checking for this simplifies the code
+				// and may avoid duplicate computations in certain conditions.
+				if err == nil {
+					err = transform.ErrShortSrc
+				}
+				break
+			}
+			// Determine the maximal subpart of an ill-formed subsequence.
+			switch {
+			case nSrc+1 >= n || src[nSrc+1] < accept.Lo || accept.Hi < src[nSrc+1]:
+				size = 1
+			case nSrc+2 >= n || src[nSrc+2] < utf8internal.LoCB || utf8internal.HiCB < src[nSrc+2]:
+				size = 2
+			default:
+				size = 3 // As we are short, the maximum is 3.
+			}
+			goto handleInvalid
+		}
+		if c = src[nSrc+1]; c < accept.Lo || accept.Hi < c {
+			size = 1
+			goto handleInvalid // invalid continuation byte
+		} else if size == 2 {
+		} else if c = src[nSrc+2]; c < utf8internal.LoCB || utf8internal.HiCB < c {
+			size = 2
+			goto handleInvalid // invalid continuation byte
+		} else if size == 3 {
+		} else if c = src[nSrc+3]; c < utf8internal.LoCB || utf8internal.HiCB < c {
+			size = 3
+			goto handleInvalid // invalid continuation byte
+		}
+		nSrc += size
+		continue
+
+	handleInvalid:
+		// Copy the scanned input so far.
+		nDst += copy(dst[nDst:], src[pSrc:nSrc])
+
+		// Append RuneError to the destination.
+		const runeError = "\ufffd"
+		if nDst+len(runeError) > len(dst) {
+			return nDst, nSrc, transform.ErrShortDst
+		}
+		nDst += copy(dst[nDst:], runeError)
+
+		// Skip the maximal subpart of an ill-formed subsequence according to
+		// the W3C standard way instead of the Go way. This Transform is
+		// probably the only place in the text repo where it is warranted.
+		nSrc += size
+		pSrc = nSrc
+
+		// Recompute the maximum source length.
+		if sz := len(dst) - nDst; sz < len(src)-nSrc {
+			err = transform.ErrShortDst
+			n = nSrc + sz
+			atEOF = false
+		}
+	}
+	return nDst + copy(dst[nDst:], src[pSrc:nSrc]), nSrc, err
+}
+
+// UTF16 returns a UTF-16 Encoding for the given default endianness and byte
+// order mark (BOM) policy.
+//
+// When decoding from UTF-16 to UTF-8, if the BOMPolicy is IgnoreBOM then
+// neither BOMs U+FEFF nor noncharacters U+FFFE in the input stream will affect
+// the endianness used for decoding, and will instead be output as their
+// standard UTF-8 encodings: "\xef\xbb\xbf" and "\xef\xbf\xbe". If the BOMPolicy
+// is UseBOM or ExpectBOM a staring BOM is not written to the UTF-8 output.
+// Instead, it overrides the default endianness e for the remainder of the
+// transformation. Any subsequent BOMs U+FEFF or noncharacters U+FFFE will not
+// affect the endianness used, and will instead be output as their standard
+// UTF-8 encodings. For UseBOM, if there is no starting BOM, it will proceed
+// with the default Endianness. For ExpectBOM, in that case, the transformation
+// will return early with an ErrMissingBOM error.
+//
+// When encoding from UTF-8 to UTF-16, a BOM will be inserted at the start of
+// the output if the BOMPolicy is UseBOM or ExpectBOM. Otherwise, a BOM will not
+// be inserted. The UTF-8 input does not need to contain a BOM.
+//
+// There is no concept of a 'native' endianness. If the UTF-16 data is produced
+// and consumed in a greater context that implies a certain endianness, use
+// IgnoreBOM. Otherwise, use ExpectBOM and always produce and consume a BOM.
+//
+// In the language of https://www.unicode.org/faq/utf_bom.html#bom10, IgnoreBOM
+// corresponds to "Where the precise type of the data stream is known... the
+// BOM should not be used" and ExpectBOM corresponds to "A particular
+// protocol... may require use of the BOM".
+func UTF16(e Endianness, b BOMPolicy) encoding.Encoding {
+	return utf16Encoding{config{e, b}, mibValue[e][b&bomMask]}
+}
+
+// mibValue maps Endianness and BOMPolicy settings to MIB constants. Note that
+// some configurations map to the same MIB identifier. RFC 2781 has requirements
+// and recommendations. Some of the "configurations" are merely recommendations,
+// so multiple configurations could match.
+var mibValue = map[Endianness][numBOMValues]identifier.MIB{
+	BigEndian: [numBOMValues]identifier.MIB{
+		IgnoreBOM: identifier.UTF16BE,
+		UseBOM:    identifier.UTF16, // BigEnding default is preferred by RFC 2781.
+		// TODO: acceptBOM | strictBOM would map to UTF16BE as well.
+	},
+	LittleEndian: [numBOMValues]identifier.MIB{
+		IgnoreBOM: identifier.UTF16LE,
+		UseBOM:    identifier.UTF16, // LittleEndian default is allowed and preferred on Windows.
+		// TODO: acceptBOM | strictBOM would map to UTF16LE as well.
+	},
+	// ExpectBOM is not widely used and has no valid MIB identifier.
+}
+
+// All lists a configuration for each IANA-defined UTF-16 variant.
+var All = []encoding.Encoding{
+	UTF8,
+	UTF16(BigEndian, UseBOM),
+	UTF16(BigEndian, IgnoreBOM),
+	UTF16(LittleEndian, IgnoreBOM),
+}
+
+// BOMPolicy is a UTF-16 encoding's byte order mark policy.
+type BOMPolicy uint8
+
+const (
+	writeBOM   BOMPolicy = 0x01
+	acceptBOM  BOMPolicy = 0x02
+	requireBOM BOMPolicy = 0x04
+	bomMask    BOMPolicy = 0x07
+
+	// HACK: numBOMValues == 8 triggers a bug in the 1.4 compiler (cannot have a
+	// map of an array of length 8 of a type that is also used as a key or value
+	// in another map). See golang.org/issue/11354.
+	// TODO: consider changing this value back to 8 if the use of 1.4.* has
+	// been minimized.
+	numBOMValues = 8 + 1
+
+	// IgnoreBOM means to ignore any byte order marks.
+	IgnoreBOM BOMPolicy = 0
+	// Common and RFC 2781-compliant interpretation for UTF-16BE/LE.
+
+	// UseBOM means that the UTF-16 form may start with a byte order mark, which
+	// will be used to override the default encoding.
+	UseBOM BOMPolicy = writeBOM | acceptBOM
+	// Common and RFC 2781-compliant interpretation for UTF-16.
+
+	// ExpectBOM means that the UTF-16 form must start with a byte order mark,
+	// which will be used to override the default encoding.
+	ExpectBOM BOMPolicy = writeBOM | acceptBOM | requireBOM
+	// Used in Java as Unicode (not to be confused with Java's UTF-16) and
+	// ICU's UTF-16,version=1. Not compliant with RFC 2781.
+
+	// TODO (maybe): strictBOM: BOM must match Endianness. This would allow:
+	// - UTF-16(B|L)E,version=1: writeBOM | acceptBOM | requireBOM | strictBOM
+	//    (UnicodeBig and UnicodeLittle in Java)
+	// - RFC 2781-compliant, but less common interpretation for UTF-16(B|L)E:
+	//    acceptBOM | strictBOM (e.g. assigned to CheckBOM).
+	// This addition would be consistent with supporting ExpectBOM.
+)
+
+// Endianness is a UTF-16 encoding's default endianness.
+type Endianness bool
+
+const (
+	// BigEndian is UTF-16BE.
+	BigEndian Endianness = false
+	// LittleEndian is UTF-16LE.
+	LittleEndian Endianness = true
+)
+
+// ErrMissingBOM means that decoding UTF-16 input with ExpectBOM did not find a
+// starting byte order mark.
+var ErrMissingBOM = errors.New("encoding: missing byte order mark")
+
+type utf16Encoding struct {
+	config
+	mib identifier.MIB
+}
+
+type config struct {
+	endianness Endianness
+	bomPolicy  BOMPolicy
+}
+
+func (u utf16Encoding) NewDecoder() *encoding.Decoder {
+	return &encoding.Decoder{Transformer: &utf16Decoder{
+		initial: u.config,
+		current: u.config,
+	}}
+}
+
+func (u utf16Encoding) NewEncoder() *encoding.Encoder {
+	return &encoding.Encoder{Transformer: &utf16Encoder{
+		endianness:       u.endianness,
+		initialBOMPolicy: u.bomPolicy,
+		currentBOMPolicy: u.bomPolicy,
+	}}
+}
+
+func (u utf16Encoding) ID() (mib identifier.MIB, other string) {
+	return u.mib, ""
+}
+
+func (u utf16Encoding) String() string {
+	e, b := "B", ""
+	if u.endianness == LittleEndian {
+		e = "L"
+	}
+	switch u.bomPolicy {
+	case ExpectBOM:
+		b = "Expect"
+	case UseBOM:
+		b = "Use"
+	case IgnoreBOM:
+		b = "Ignore"
+	}
+	return "UTF-16" + e + "E (" + b + " BOM)"
+}
+
+type utf16Decoder struct {
+	initial config
+	current config
+}
+
+func (u *utf16Decoder) Reset() {
+	u.current = u.initial
+}
+
+func (u *utf16Decoder) Transform(dst, src []byte, atEOF bool) (nDst, nSrc int, err error) {
+	if len(src) < 2 && atEOF && u.current.bomPolicy&requireBOM != 0 {
+		return 0, 0, ErrMissingBOM
+	}
+	if len(src) == 0 {
+		return 0, 0, nil
+	}
+	if len(src) >= 2 && u.current.bomPolicy&acceptBOM != 0 {
+		switch {
+		case src[0] == 0xfe && src[1] == 0xff:
+			u.current.endianness = BigEndian
+			nSrc = 2
+		case src[0] == 0xff && src[1] == 0xfe:
+			u.current.endianness = LittleEndian
+			nSrc = 2
+		default:
+			if u.current.bomPolicy&requireBOM != 0 {
+				return 0, 0, ErrMissingBOM
+			}
+		}
+		u.current.bomPolicy = IgnoreBOM
+	}
+
+	var r rune
+	var dSize, sSize int
+	for nSrc < len(src) {
+		if nSrc+1 < len(src) {
+			x := uint16(src[nSrc+0])<<8 | uint16(src[nSrc+1])
+			if u.current.endianness == LittleEndian {
+				x = x>>8 | x<<8
+			}
+			r, sSize = rune(x), 2
+			if utf16.IsSurrogate(r) {
+				if nSrc+3 < len(src) {
+					x = uint16(src[nSrc+2])<<8 | uint16(src[nSrc+3])
+					if u.current.endianness == LittleEndian {
+						x = x>>8 | x<<8
+					}
+					// Save for next iteration if it is not a high surrogate.
+					if isHighSurrogate(rune(x)) {
+						r, sSize = utf16.DecodeRune(r, rune(x)), 4
+					}
+				} else if !atEOF {
+					err = transform.ErrShortSrc
+					break
+				}
+			}
+			if dSize = utf8.RuneLen(r); dSize < 0 {
+				r, dSize = utf8.RuneError, 3
+			}
+		} else if atEOF {
+			// Single trailing byte.
+			r, dSize, sSize = utf8.RuneError, 3, 1
+		} else {
+			err = transform.ErrShortSrc
+			break
+		}
+		if nDst+dSize > len(dst) {
+			err = transform.ErrShortDst
+			break
+		}
+		nDst += utf8.EncodeRune(dst[nDst:], r)
+		nSrc += sSize
+	}
+	return nDst, nSrc, err
+}
+
+func isHighSurrogate(r rune) bool {
+	return 0xDC00 <= r && r <= 0xDFFF
+}
+
+type utf16Encoder struct {
+	endianness       Endianness
+	initialBOMPolicy BOMPolicy
+	currentBOMPolicy BOMPolicy
+}
+
+func (u *utf16Encoder) Reset() {
+	u.currentBOMPolicy = u.initialBOMPolicy
+}
+
+func (u *utf16Encoder) Transform(dst, src []byte, atEOF bool) (nDst, nSrc int, err error) {
+	if u.currentBOMPolicy&writeBOM != 0 {
+		if len(dst) < 2 {
+			return 0, 0, transform.ErrShortDst
+		}
+		dst[0], dst[1] = 0xfe, 0xff
+		u.currentBOMPolicy = IgnoreBOM
+		nDst = 2
+	}
+
+	r, size := rune(0), 0
+	for nSrc < len(src) {
+		r = rune(src[nSrc])
+
+		// Decode a 1-byte rune.
+		if r < utf8.RuneSelf {
+			size = 1
+
+		} else {
+			// Decode a multi-byte rune.
+			r, size = utf8.DecodeRune(src[nSrc:])
+			if size == 1 {
+				// All valid runes of size 1 (those below utf8.RuneSelf) were
+				// handled above. We have invalid UTF-8 or we haven't seen the
+				// full character yet.
+				if !atEOF && !utf8.FullRune(src[nSrc:]) {
+					err = transform.ErrShortSrc
+					break
+				}
+			}
+		}
+
+		if r <= 0xffff {
+			if nDst+2 > len(dst) {
+				err = transform.ErrShortDst
+				break
+			}
+			dst[nDst+0] = uint8(r >> 8)
+			dst[nDst+1] = uint8(r)
+			nDst += 2
+		} else {
+			if nDst+4 > len(dst) {
+				err = transform.ErrShortDst
+				break
+			}
+			r1, r2 := utf16.EncodeRune(r)
+			dst[nDst+0] = uint8(r1 >> 8)
+			dst[nDst+1] = uint8(r1)
+			dst[nDst+2] = uint8(r2 >> 8)
+			dst[nDst+3] = uint8(r2)
+			nDst += 4
+		}
+		nSrc += size
+	}
+
+	if u.endianness == LittleEndian {
+		for i := 0; i < nDst; i += 2 {
+			dst[i], dst[i+1] = dst[i+1], dst[i]
+		}
+	}
+	return nDst, nSrc, err
+}