go.net/html/charset: new package
Implement retrieving encodings by name, according to the names listed
at http://encoding.spec.whatwg.org/#encodings
This is the first step toward implementing the encoding detection
algorithm.
R=nigeltao
CC=golang-dev
https://golang.org/cl/27110043
diff --git a/html/charset/encoding.go b/html/charset/encoding.go
new file mode 100644
index 0000000..8c2b5a9
--- /dev/null
+++ b/html/charset/encoding.go
@@ -0,0 +1,51 @@
+// Package charset provides common text encodings for HTML documents.
+//
+// The mapping from encoding labels to encodings is defined at
+// http://encoding.spec.whatwg.org.
+package charset
+
+import (
+ "errors"
+ "strings"
+
+ "code.google.com/p/go.text/encoding"
+ "code.google.com/p/go.text/transform"
+)
+
+// Encoding returns the encoding with the specified label, or nil if label is
+// not one of the standard encodings for HTML. Matching is case-insensitive
+// and ignores leading and trailing whitespace.
+func Encoding(label string) encoding.Encoding {
+ label = strings.ToLower(strings.Trim(label, "\t\n\r\f "))
+ return encodings[label]
+}
+
+type utf8Encoding struct{}
+
+func (utf8Encoding) NewDecoder() transform.Transformer {
+ return transform.Nop
+}
+
+func (utf8Encoding) NewEncoder() transform.Transformer {
+ return transform.Nop
+}
+
+var ErrReplacementEncoding = errors.New("charset: ISO-2022-CN and ISO-2022-KR are obsolete encodings for HTML")
+
+type errorTransformer struct {
+ err error
+}
+
+func (t errorTransformer) Transform(dst, src []byte, atEOF bool) (nDst, nSrc int, err error) {
+ return 0, 0, t.err
+}
+
+type replacementEncoding struct{}
+
+func (replacementEncoding) NewDecoder() transform.Transformer {
+ return errorTransformer{ErrReplacementEncoding}
+}
+
+func (replacementEncoding) NewEncoder() transform.Transformer {
+ return transform.Nop
+}
diff --git a/html/charset/encoding_test.go b/html/charset/encoding_test.go
new file mode 100644
index 0000000..1105ba8
--- /dev/null
+++ b/html/charset/encoding_test.go
@@ -0,0 +1,103 @@
+package charset
+
+import (
+ "io/ioutil"
+ "strings"
+ "testing"
+
+ "code.google.com/p/go.text/transform"
+)
+
+func transformString(t transform.Transformer, s string) (string, error) {
+ r := transform.NewReader(strings.NewReader(s), t)
+ b, err := ioutil.ReadAll(r)
+ return string(b), err
+}
+
+var testCases = []struct {
+ utf8, other, otherEncoding string
+}{
+ {"Résumé", "Résumé", "utf8"},
+ {"Résumé", "R\xe9sum\xe9", "latin1"},
+ {"これは漢字です。", "S0\x8c0o0\"oW[g0Y0\x020", "UTF-16LE"},
+ {"これは漢字です。", "0S0\x8c0oo\"[W0g0Y0\x02", "UTF-16BE"},
+ {"Hello, world", "Hello, world", "ASCII"},
+ {"Gdańsk", "Gda\xf1sk", "ISO-8859-2"},
+ {"Ââ Čč Đđ Ŋŋ Õõ Šš Žž Åå Ää", "\xc2\xe2 \xc8\xe8 \xa9\xb9 \xaf\xbf \xd5\xf5 \xaa\xba \xac\xbc \xc5\xe5 \xc4\xe4", "ISO-8859-10"},
+ {"สำหรับ", "\xca\xd3\xcb\xc3\u047a", "ISO-8859-11"},
+ {"latviešu", "latvie\xf0u", "ISO-8859-13"},
+ {"Seònaid", "Se\xf2naid", "ISO-8859-14"},
+ {"€1 is cheap", "\xa41 is cheap", "ISO-8859-15"},
+ {"românește", "rom\xe2ne\xbate", "ISO-8859-16"},
+ {"nutraĵo", "nutra\xbco", "ISO-8859-3"},
+ {"Kalâdlit", "Kal\xe2dlit", "ISO-8859-4"},
+ {"русский", "\xe0\xe3\xe1\xe1\xda\xd8\xd9", "ISO-8859-5"},
+ {"ελληνικά", "\xe5\xeb\xeb\xe7\xed\xe9\xea\xdc", "ISO-8859-7"},
+ {"Kağan", "Ka\xf0an", "ISO-8859-9"},
+ {"Résumé", "R\x8esum\x8e", "macintosh"},
+ {"Gdańsk", "Gda\xf1sk", "windows-1250"},
+ {"русский", "\xf0\xf3\xf1\xf1\xea\xe8\xe9", "windows-1251"},
+ {"Résumé", "R\xe9sum\xe9", "windows-1252"},
+ {"ελληνικά", "\xe5\xeb\xeb\xe7\xed\xe9\xea\xdc", "windows-1253"},
+ {"Kağan", "Ka\xf0an", "windows-1254"},
+ {"עִבְרִית", "\xf2\xc4\xe1\xc0\xf8\xc4\xe9\xfa", "windows-1255"},
+ {"العربية", "\xc7\xe1\xda\xd1\xc8\xed\xc9", "windows-1256"},
+ {"latviešu", "latvie\xf0u", "windows-1257"},
+ {"Việt", "Vi\xea\xf2t", "windows-1258"},
+ {"สำหรับ", "\xca\xd3\xcb\xc3\u047a", "windows-874"},
+ {"русский", "\xd2\xd5\xd3\xd3\xcb\xc9\xca", "KOI8-R"},
+ {"українська", "\xd5\xcb\xd2\xc1\xa7\xce\xd3\xd8\xcb\xc1", "KOI8-U"},
+ {"Hello 常用國字標準字體表", "Hello \xb1`\xa5\u03b0\xea\xa6r\xbc\u0437\u01e6r\xc5\xe9\xaa\xed", "big5"},
+ {"Hello 常用國字標準字體表", "Hello \xb3\xa3\xd3\xc3\x87\xf8\xd7\xd6\x98\xcb\x9c\xca\xd7\xd6\xf3\x77\xb1\xed", "gbk"},
+ {"Hello 常用國字標準字體表", "Hello \xb3\xa3\xd3\xc3\x87\xf8\xd7\xd6\x98\xcb\x9c\xca\xd7\xd6\xf3\x77\xb1\xed", "gb18030"},
+ {"עִבְרִית", "\x81\x30\xfb\x30\x81\x30\xf6\x34\x81\x30\xf9\x33\x81\x30\xf6\x30\x81\x30\xfb\x36\x81\x30\xf6\x34\x81\x30\xfa\x31\x81\x30\xfb\x38", "gb18030"},
+ {"㧯", "\x82\x31\x89\x38", "gb18030"},
+ {"これは漢字です。", "\x82\xb1\x82\xea\x82\xcd\x8a\xbf\x8e\x9a\x82\xc5\x82\xb7\x81B", "SJIS"},
+ {"Hello, 世界!", "Hello, \x90\xa2\x8aE!", "SJIS"},
+ {"ｲｳｴｵｶ", "\xb2\xb3\xb4\xb5\xb6", "SJIS"},
+ {"これは漢字です。", "\xa4\xb3\xa4\xec\xa4\u03f4\xc1\xbb\xfa\xa4\u01e4\xb9\xa1\xa3", "EUC-JP"},
+ {"Hello, 世界!", "Hello, \x1b$B@$3&\x1b(B!", "ISO-2022-JP"},
+ {"네이트 | 즐거움의 시작, 슈파스(Spaβ) NATE", "\xb3\xd7\xc0\xcc\xc6\xae | \xc1\xf1\xb0\xc5\xbf\xf2\xc0\xc7 \xbd\xc3\xc0\xdb, \xbd\xb4\xc6\xc4\xbd\xba(Spa\xa5\xe2) NATE", "EUC-KR"},
+}
+
+func TestDecode(t *testing.T) {
+ for _, tc := range testCases {
+ e := Encoding(tc.otherEncoding)
+ if e == nil {
+ t.Errorf("%s: not found", tc.otherEncoding)
+ continue
+ }
+
+ s, err := transformString(e.NewDecoder(), tc.other)
+
+ if err != nil {
+ t.Errorf("%s: decode %q: %v", tc.otherEncoding, tc.other, err)
+ continue
+ }
+
+ if s != tc.utf8 {
+ t.Errorf("%s: got %q, want %q", tc.otherEncoding, s, tc.utf8)
+ }
+ }
+}
+
+func TestEncode(t *testing.T) {
+ for _, tc := range testCases {
+ e := Encoding(tc.otherEncoding)
+ if e == nil {
+ t.Errorf("%s: not found", tc.otherEncoding)
+ continue
+ }
+
+ s, err := transformString(e.NewEncoder(), tc.utf8)
+
+ if err != nil {
+ t.Errorf("%s: encode %q: %s", tc.otherEncoding, tc.utf8, err)
+ continue
+ }
+
+ if s != tc.other {
+ t.Errorf("%s: got %q, want %q", tc.otherEncoding, s, tc.other)
+ }
+ }
+}
diff --git a/html/charset/gen.go b/html/charset/gen.go
new file mode 100644
index 0000000..633afd9
--- /dev/null
+++ b/html/charset/gen.go
@@ -0,0 +1,107 @@
+// +build ignore
+
+package main
+
+// Download http://encoding.spec.whatwg.org/encodings.json and use it to
+// generate table.go.
+
+import (
+ "encoding/json"
+ "fmt"
+ "log"
+ "net/http"
+ "strings"
+)
+
+type enc struct {
+ Name string
+ Labels []string
+}
+
+type group struct {
+ Encodings []enc
+ Heading string
+}
+
+const specURL = "http://encoding.spec.whatwg.org/encodings.json"
+
+func main() {
+ resp, err := http.Get(specURL)
+ if err != nil {
+ log.Fatalf("error fetching %s: %s", specURL, err)
+ }
+ if resp.StatusCode != 200 {
+ log.Fatalf("error fetching %s: HTTP status %s", specURL, resp.Status)
+ }
+ defer resp.Body.Close()
+
+ var groups []group
+ d := json.NewDecoder(resp.Body)
+ err = d.Decode(&groups)
+ if err != nil {
+ log.Fatalf("error reading encodings.json: %s", err)
+ }
+
+ fmt.Println("// generated by go run gen.go; DO NOT EDIT")
+ fmt.Println()
+ fmt.Println("package charset")
+ fmt.Println()
+
+ fmt.Println("import (")
+ fmt.Println(`"code.google.com/p/go.text/encoding"`)
+ for _, pkg := range []string{"charmap", "japanese", "korean", "simplifiedchinese", "traditionalchinese", "unicode"} {
+ fmt.Printf("\"code.google.com/p/go.text/encoding/%s\"\n", pkg)
+ }
+ fmt.Println(")")
+ fmt.Println()
+
+ fmt.Println("var encodings = map[string]encoding.Encoding{")
+ for _, g := range groups {
+ for _, e := range g.Encodings {
+ goName, ok := miscNames[e.Name]
+ if !ok {
+ for k, v := range prefixes {
+ if strings.HasPrefix(e.Name, k) {
+ goName = v + e.Name[len(k):]
+ break
+ }
+ }
+ if goName == "" {
+ log.Fatalf("unrecognized encoding name: %s", e.Name)
+ }
+ }
+
+ for _, label := range e.Labels {
+ fmt.Printf("%q: %s,\n", label, goName)
+ }
+ }
+ }
+ fmt.Println("}")
+}
+
+var prefixes = map[string]string{
+ "iso-8859-": "charmap.ISO8859_",
+ "windows-": "charmap.Windows",
+}
+
+var miscNames = map[string]string{
+ "utf-8": "utf8Encoding{}",
+ "ibm866": "charmap.CodePage866",
+ "iso-8859-8-i": "charmap.ISO8859_8",
+ "koi8-r": "charmap.KOI8R",
+ "koi8-u": "charmap.KOI8U",
+ "macintosh": "charmap.Macintosh",
+ "x-mac-cyrillic": "charmap.MacintoshCyrillic",
+ "gbk": "simplifiedchinese.GBK",
+ "gb18030": "simplifiedchinese.GB18030",
+ "hz-gb-2312": "simplifiedchinese.HZGB2312",
+ "big5": "traditionalchinese.Big5",
+ "euc-jp": "japanese.EUCJP",
+ "iso-2022-jp": "japanese.ISO2022JP",
+ "shift_jis": "japanese.ShiftJIS",
+ "euc-kr": "korean.EUCKR",
+ "replacement": "replacementEncoding{}",
+ "utf-16be": "unicode.UTF16(unicode.BigEndian, unicode.IgnoreBOM)",
+ "utf-16le": "unicode.UTF16(unicode.LittleEndian, unicode.IgnoreBOM)",
+ "x-user-defined": "charmap.XUserDefined",
+}
diff --git a/html/charset/table.go b/html/charset/table.go
new file mode 100644
index 0000000..ae9a4e0
--- /dev/null
+++ b/html/charset/table.go
@@ -0,0 +1,232 @@
+// generated by go run gen.go; DO NOT EDIT
+
+package charset
+
+import (
+ "code.google.com/p/go.text/encoding"
+ "code.google.com/p/go.text/encoding/charmap"
+ "code.google.com/p/go.text/encoding/japanese"
+ "code.google.com/p/go.text/encoding/korean"
+ "code.google.com/p/go.text/encoding/simplifiedchinese"
+ "code.google.com/p/go.text/encoding/traditionalchinese"
+ "code.google.com/p/go.text/encoding/unicode"
+)
+
+var encodings = map[string]encoding.Encoding{
+ "unicode-1-1-utf-8": utf8Encoding{},
+ "utf-8": utf8Encoding{},
+ "utf8": utf8Encoding{},
+ "866": charmap.CodePage866,
+ "cp866": charmap.CodePage866,
+ "csibm866": charmap.CodePage866,
+ "ibm866": charmap.CodePage866,
+ "csisolatin2": charmap.ISO8859_2,
+ "iso-8859-2": charmap.ISO8859_2,
+ "iso-ir-101": charmap.ISO8859_2,
+ "iso8859-2": charmap.ISO8859_2,
+ "iso88592": charmap.ISO8859_2,
+ "iso_8859-2": charmap.ISO8859_2,
+ "iso_8859-2:1987": charmap.ISO8859_2,
+ "l2": charmap.ISO8859_2,
+ "latin2": charmap.ISO8859_2,
+ "csisolatin3": charmap.ISO8859_3,
+ "iso-8859-3": charmap.ISO8859_3,
+ "iso-ir-109": charmap.ISO8859_3,
+ "iso8859-3": charmap.ISO8859_3,
+ "iso88593": charmap.ISO8859_3,
+ "iso_8859-3": charmap.ISO8859_3,
+ "iso_8859-3:1988": charmap.ISO8859_3,
+ "l3": charmap.ISO8859_3,
+ "latin3": charmap.ISO8859_3,
+ "csisolatin4": charmap.ISO8859_4,
+ "iso-8859-4": charmap.ISO8859_4,
+ "iso-ir-110": charmap.ISO8859_4,
+ "iso8859-4": charmap.ISO8859_4,
+ "iso88594": charmap.ISO8859_4,
+ "iso_8859-4": charmap.ISO8859_4,
+ "iso_8859-4:1988": charmap.ISO8859_4,
+ "l4": charmap.ISO8859_4,
+ "latin4": charmap.ISO8859_4,
+ "csisolatincyrillic": charmap.ISO8859_5,
+ "cyrillic": charmap.ISO8859_5,
+ "iso-8859-5": charmap.ISO8859_5,
+ "iso-ir-144": charmap.ISO8859_5,
+ "iso8859-5": charmap.ISO8859_5,
+ "iso88595": charmap.ISO8859_5,
+ "iso_8859-5": charmap.ISO8859_5,
+ "iso_8859-5:1988": charmap.ISO8859_5,
+ "arabic": charmap.ISO8859_6,
+ "asmo-708": charmap.ISO8859_6,
+ "csiso88596e": charmap.ISO8859_6,
+ "csiso88596i": charmap.ISO8859_6,
+ "csisolatinarabic": charmap.ISO8859_6,
+ "ecma-114": charmap.ISO8859_6,
+ "iso-8859-6": charmap.ISO8859_6,
+ "iso-8859-6-e": charmap.ISO8859_6,
+ "iso-8859-6-i": charmap.ISO8859_6,
+ "iso-ir-127": charmap.ISO8859_6,
+ "iso8859-6": charmap.ISO8859_6,
+ "iso88596": charmap.ISO8859_6,
+ "iso_8859-6": charmap.ISO8859_6,
+ "iso_8859-6:1987": charmap.ISO8859_6,
+ "csisolatingreek": charmap.ISO8859_7,
+ "ecma-118": charmap.ISO8859_7,
+ "elot_928": charmap.ISO8859_7,
+ "greek": charmap.ISO8859_7,
+ "greek8": charmap.ISO8859_7,
+ "iso-8859-7": charmap.ISO8859_7,
+ "iso-ir-126": charmap.ISO8859_7,
+ "iso8859-7": charmap.ISO8859_7,
+ "iso88597": charmap.ISO8859_7,
+ "iso_8859-7": charmap.ISO8859_7,
+ "iso_8859-7:1987": charmap.ISO8859_7,
+ "sun_eu_greek": charmap.ISO8859_7,
+ "csiso88598e": charmap.ISO8859_8,
+ "csisolatinhebrew": charmap.ISO8859_8,
+ "hebrew": charmap.ISO8859_8,
+ "iso-8859-8": charmap.ISO8859_8,
+ "iso-8859-8-e": charmap.ISO8859_8,
+ "iso-ir-138": charmap.ISO8859_8,
+ "iso8859-8": charmap.ISO8859_8,
+ "iso88598": charmap.ISO8859_8,
+ "iso_8859-8": charmap.ISO8859_8,
+ "iso_8859-8:1988": charmap.ISO8859_8,
+ "visual": charmap.ISO8859_8,
+ "csiso88598i": charmap.ISO8859_8,
+ "iso-8859-8-i": charmap.ISO8859_8,
+ "logical": charmap.ISO8859_8,
+ "csisolatin6": charmap.ISO8859_10,
+ "iso-8859-10": charmap.ISO8859_10,
+ "iso-ir-157": charmap.ISO8859_10,
+ "iso8859-10": charmap.ISO8859_10,
+ "iso885910": charmap.ISO8859_10,
+ "l6": charmap.ISO8859_10,
+ "latin6": charmap.ISO8859_10,
+ "iso-8859-13": charmap.ISO8859_13,
+ "iso8859-13": charmap.ISO8859_13,
+ "iso885913": charmap.ISO8859_13,
+ "iso-8859-14": charmap.ISO8859_14,
+ "iso8859-14": charmap.ISO8859_14,
+ "iso885914": charmap.ISO8859_14,
+ "csisolatin9": charmap.ISO8859_15,
+ "iso-8859-15": charmap.ISO8859_15,
+ "iso8859-15": charmap.ISO8859_15,
+ "iso885915": charmap.ISO8859_15,
+ "iso_8859-15": charmap.ISO8859_15,
+ "l9": charmap.ISO8859_15,
+ "iso-8859-16": charmap.ISO8859_16,
+ "cskoi8r": charmap.KOI8R,
+ "koi": charmap.KOI8R,
+ "koi8": charmap.KOI8R,
+ "koi8-r": charmap.KOI8R,
+ "koi8_r": charmap.KOI8R,
+ "koi8-u": charmap.KOI8U,
+ "csmacintosh": charmap.Macintosh,
+ "mac": charmap.Macintosh,
+ "macintosh": charmap.Macintosh,
+ "x-mac-roman": charmap.Macintosh,
+ "dos-874": charmap.Windows874,
+ "iso-8859-11": charmap.Windows874,
+ "iso8859-11": charmap.Windows874,
+ "iso885911": charmap.Windows874,
+ "tis-620": charmap.Windows874,
+ "windows-874": charmap.Windows874,
+ "cp1250": charmap.Windows1250,
+ "windows-1250": charmap.Windows1250,
+ "x-cp1250": charmap.Windows1250,
+ "cp1251": charmap.Windows1251,
+ "windows-1251": charmap.Windows1251,
+ "x-cp1251": charmap.Windows1251,
+ "ansi_x3.4-1968": charmap.Windows1252,
+ "ascii": charmap.Windows1252,
+ "cp1252": charmap.Windows1252,
+ "cp819": charmap.Windows1252,
+ "csisolatin1": charmap.Windows1252,
+ "ibm819": charmap.Windows1252,
+ "iso-8859-1": charmap.Windows1252,
+ "iso-ir-100": charmap.Windows1252,
+ "iso8859-1": charmap.Windows1252,
+ "iso88591": charmap.Windows1252,
+ "iso_8859-1": charmap.Windows1252,
+ "iso_8859-1:1987": charmap.Windows1252,
+ "l1": charmap.Windows1252,
+ "latin1": charmap.Windows1252,
+ "us-ascii": charmap.Windows1252,
+ "windows-1252": charmap.Windows1252,
+ "x-cp1252": charmap.Windows1252,
+ "cp1253": charmap.Windows1253,
+ "windows-1253": charmap.Windows1253,
+ "x-cp1253": charmap.Windows1253,
+ "cp1254": charmap.Windows1254,
+ "csisolatin5": charmap.Windows1254,
+ "iso-8859-9": charmap.Windows1254,
+ "iso-ir-148": charmap.Windows1254,
+ "iso8859-9": charmap.Windows1254,
+ "iso88599": charmap.Windows1254,
+ "iso_8859-9": charmap.Windows1254,
+ "iso_8859-9:1989": charmap.Windows1254,
+ "l5": charmap.Windows1254,
+ "latin5": charmap.Windows1254,
+ "windows-1254": charmap.Windows1254,
+ "x-cp1254": charmap.Windows1254,
+ "cp1255": charmap.Windows1255,
+ "windows-1255": charmap.Windows1255,
+ "x-cp1255": charmap.Windows1255,
+ "cp1256": charmap.Windows1256,
+ "windows-1256": charmap.Windows1256,
+ "x-cp1256": charmap.Windows1256,
+ "cp1257": charmap.Windows1257,
+ "windows-1257": charmap.Windows1257,
+ "x-cp1257": charmap.Windows1257,
+ "cp1258": charmap.Windows1258,
+ "windows-1258": charmap.Windows1258,
+ "x-cp1258": charmap.Windows1258,
+ "x-mac-cyrillic": charmap.MacintoshCyrillic,
+ "x-mac-ukrainian": charmap.MacintoshCyrillic,
+ "chinese": simplifiedchinese.GBK,
+ "csgb2312": simplifiedchinese.GBK,
+ "csiso58gb231280": simplifiedchinese.GBK,
+ "gb2312": simplifiedchinese.GBK,
+ "gb_2312": simplifiedchinese.GBK,
+ "gb_2312-80": simplifiedchinese.GBK,
+ "gbk": simplifiedchinese.GBK,
+ "iso-ir-58": simplifiedchinese.GBK,
+ "x-gbk": simplifiedchinese.GBK,
+ "gb18030": simplifiedchinese.GB18030,
+ "hz-gb-2312": simplifiedchinese.HZGB2312,
+ "big5": traditionalchinese.Big5,
+ "big5-hkscs": traditionalchinese.Big5,
+ "cn-big5": traditionalchinese.Big5,
+ "csbig5": traditionalchinese.Big5,
+ "x-x-big5": traditionalchinese.Big5,
+ "cseucpkdfmtjapanese": japanese.EUCJP,
+ "euc-jp": japanese.EUCJP,
+ "x-euc-jp": japanese.EUCJP,
+ "csiso2022jp": japanese.ISO2022JP,
+ "iso-2022-jp": japanese.ISO2022JP,
+ "csshiftjis": japanese.ShiftJIS,
+ "ms_kanji": japanese.ShiftJIS,
+ "shift-jis": japanese.ShiftJIS,
+ "shift_jis": japanese.ShiftJIS,
+ "sjis": japanese.ShiftJIS,
+ "windows-31j": japanese.ShiftJIS,
+ "x-sjis": japanese.ShiftJIS,
+ "cseuckr": korean.EUCKR,
+ "csksc56011987": korean.EUCKR,
+ "euc-kr": korean.EUCKR,
+ "iso-ir-149": korean.EUCKR,
+ "korean": korean.EUCKR,
+ "ks_c_5601-1987": korean.EUCKR,
+ "ks_c_5601-1989": korean.EUCKR,
+ "ksc5601": korean.EUCKR,
+ "ksc_5601": korean.EUCKR,
+ "windows-949": korean.EUCKR,
+ "csiso2022kr": replacementEncoding{},
+ "iso-2022-kr": replacementEncoding{},
+ "iso-2022-cn": replacementEncoding{},
+ "iso-2022-cn-ext": replacementEncoding{},
+ "utf-16be": unicode.UTF16(unicode.BigEndian, unicode.IgnoreBOM),
+ "utf-16": unicode.UTF16(unicode.LittleEndian, unicode.IgnoreBOM),
+ "utf-16le": unicode.UTF16(unicode.LittleEndian, unicode.IgnoreBOM),
+ "x-user-defined": charmap.XUserDefined,
+}
