1// Copyright 2015 The Go Authors. All rights reserved.
2// Use of this source code is governed by a BSD-style
3// license that can be found in the LICENSE file.
4
5//go:generate go run gen.go
6
7// Package ianaindex maps names to Encodings as specified by the IANA registry.
8// This includes both the MIME and IANA names.
9//
10// See http://www.iana.org/assignments/character-sets/character-sets.xhtml for
11// more details.
12package ianaindex
13
14import (
15	"errors"
16	"sort"
17	"strings"
18
19	"golang.org/x/text/encoding"
20	"golang.org/x/text/encoding/charmap"
21	"golang.org/x/text/encoding/internal/identifier"
22	"golang.org/x/text/encoding/japanese"
23	"golang.org/x/text/encoding/korean"
24	"golang.org/x/text/encoding/simplifiedchinese"
25	"golang.org/x/text/encoding/traditionalchinese"
26	"golang.org/x/text/encoding/unicode"
27)
28
29// TODO: remove the "Status... incomplete" in the package doc comment.
30// TODO: allow users to specify their own aliases?
31// TODO: allow users to specify their own indexes?
32// TODO: allow canonicalizing names
33
34// NOTE: only use these top-level variables if we can get the linker to drop
35// the indexes when they are not used. Make them a function or perhaps only
36// support MIME otherwise.
37
38var (
39	// MIME is an index to map MIME names.
40	MIME *Index = mime
41
42	// IANA is an index that supports all names and aliases using IANA names as
43	// the canonical identifier.
44	IANA *Index = iana
45
46	// MIB is an index that associates the MIB display name with an Encoding.
47	MIB *Index = mib
48
49	mime = &Index{mimeName, ianaToMIB, ianaAliases, encodings[:]}
50	iana = &Index{ianaName, ianaToMIB, ianaAliases, encodings[:]}
51	mib  = &Index{mibName, ianaToMIB, ianaAliases, encodings[:]}
52)
53
54// Index maps names registered by IANA to Encodings.
55// Currently different Indexes only differ in the names they return for
56// encodings. In the future they may also differ in supported aliases.
57type Index struct {
58	names func(i int) string
59	toMIB []identifier.MIB // Sorted slice of supported MIBs
60	alias map[string]int
61	enc   []encoding.Encoding
62}
63
64var (
65	errInvalidName = errors.New("ianaindex: invalid encoding name")
66	errUnknown     = errors.New("ianaindex: unknown Encoding")
67	errUnsupported = errors.New("ianaindex: unsupported Encoding")
68)
69
70// Encoding returns an Encoding for IANA-registered names. Matching is
71// case-insensitive.
72func (x *Index) Encoding(name string) (encoding.Encoding, error) {
73	name = strings.TrimSpace(name)
74	// First try without lowercasing (possibly creating an allocation).
75	i, ok := x.alias[name]
76	if !ok {
77		i, ok = x.alias[strings.ToLower(name)]
78		if !ok {
79			return nil, errInvalidName
80		}
81	}
82	return x.enc[i], nil
83}
84
85// Name reports the canonical name of the given Encoding. It will return an
86// error if the e is not associated with a known encoding scheme.
87func (x *Index) Name(e encoding.Encoding) (string, error) {
88	id, ok := e.(identifier.Interface)
89	if !ok {
90		return "", errUnknown
91	}
92	mib, _ := id.ID()
93	if mib == 0 {
94		return "", errUnknown
95	}
96	v := findMIB(x.toMIB, mib)
97	if v == -1 {
98		return "", errUnsupported
99	}
100	return x.names(v), nil
101}
102
103// TODO: the coverage of this index is rather spotty. Allowing users to set
104// encodings would allow:
105// - users to increase coverage
106// - allow a partially loaded set of encodings in case the user doesn't need to
107//   them all.
108// - write an OS-specific wrapper for supported encodings and set them.
109// The exact definition of Set depends a bit on if and how we want to let users
110// write their own Encoding implementations. Also, it is not possible yet to
111// only partially load the encodings without doing some refactoring. Until this
112// is solved, we might as well not support Set.
113// // Set sets the e to be used for the encoding scheme identified by name. Only
114// // canonical names may be used. An empty name assigns e to its internally
115// // associated encoding scheme.
116// func (x *Index) Set(name string, e encoding.Encoding) error {
117// 	panic("TODO: implement")
118// }
119
120func findMIB(x []identifier.MIB, mib identifier.MIB) int {
121	i := sort.Search(len(x), func(i int) bool { return x[i] >= mib })
122	if i < len(x) && x[i] == mib {
123		return i
124	}
125	return -1
126}
127
128const maxMIMENameLen = '0' - 1 // officially 40, but we leave some buffer.
129
130func mimeName(x int) string {
131	n := ianaNames[x]
132	// See gen.go for a description of the encoding.
133	if n[0] <= maxMIMENameLen {
134		return n[1:n[0]]
135	}
136	return n
137}
138
139func ianaName(x int) string {
140	n := ianaNames[x]
141	// See gen.go for a description of the encoding.
142	if n[0] <= maxMIMENameLen {
143		return n[n[0]:]
144	}
145	return n
146}
147
148func mibName(x int) string {
149	return mibNames[x]
150}
151
152var encodings = [numIANA]encoding.Encoding{
153	enc106:  unicode.UTF8,
154	enc1015: unicode.UTF16(unicode.BigEndian, unicode.UseBOM),
155	enc1013: unicode.UTF16(unicode.BigEndian, unicode.IgnoreBOM),
156	enc1014: unicode.UTF16(unicode.LittleEndian, unicode.IgnoreBOM),
157	enc2028: charmap.CodePage037,
158	enc2011: charmap.CodePage437,
159	enc2009: charmap.CodePage850,
160	enc2010: charmap.CodePage852,
161	enc2046: charmap.CodePage855,
162	enc2089: charmap.CodePage858,
163	enc2048: charmap.CodePage860,
164	enc2013: charmap.CodePage862,
165	enc2050: charmap.CodePage863,
166	enc2052: charmap.CodePage865,
167	enc2086: charmap.CodePage866,
168	enc2102: charmap.CodePage1047,
169	enc2091: charmap.CodePage1140,
170	enc4:    charmap.ISO8859_1,
171	enc5:    charmap.ISO8859_2,
172	enc6:    charmap.ISO8859_3,
173	enc7:    charmap.ISO8859_4,
174	enc8:    charmap.ISO8859_5,
175	enc9:    charmap.ISO8859_6,
176	enc81:   charmap.ISO8859_6E,
177	enc82:   charmap.ISO8859_6I,
178	enc10:   charmap.ISO8859_7,
179	enc11:   charmap.ISO8859_8,
180	enc84:   charmap.ISO8859_8E,
181	enc85:   charmap.ISO8859_8I,
182	enc12:   charmap.ISO8859_9,
183	enc13:   charmap.ISO8859_10,
184	enc109:  charmap.ISO8859_13,
185	enc110:  charmap.ISO8859_14,
186	enc111:  charmap.ISO8859_15,
187	enc112:  charmap.ISO8859_16,
188	enc2084: charmap.KOI8R,
189	enc2088: charmap.KOI8U,
190	enc2027: charmap.Macintosh,
191	enc2109: charmap.Windows874,
192	enc2250: charmap.Windows1250,
193	enc2251: charmap.Windows1251,
194	enc2252: charmap.Windows1252,
195	enc2253: charmap.Windows1253,
196	enc2254: charmap.Windows1254,
197	enc2255: charmap.Windows1255,
198	enc2256: charmap.Windows1256,
199	enc2257: charmap.Windows1257,
200	enc2258: charmap.Windows1258,
201	enc18:   japanese.EUCJP,
202	enc39:   japanese.ISO2022JP,
203	enc17:   japanese.ShiftJIS,
204	enc38:   korean.EUCKR,
205	enc114:  simplifiedchinese.GB18030,
206	enc113:  simplifiedchinese.GBK,
207	enc2085: simplifiedchinese.HZGB2312,
208	enc2026: traditionalchinese.Big5,
209}
210