Skip to content

Commit 4aad7e7

Browse files
rykovrykov
committed
encoding: publicly expose identifier.{MIB,Interface}
1 parent 18b340f commit 4aad7e7

File tree

4 files changed

+112
-70
lines changed

4 files changed

+112
-70
lines changed

‎encoding/ianaindex/ianaindex.go‎

Lines changed: 9 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -104,6 +104,15 @@ func (x *Index) Name(e encoding.Encoding) (string, error) {
104104
return x.names(v), nil
105105
}
106106

107+
// FindMIB searches encoding by MIBenum identifier
108+
func (x *Index) FindMIB(mib identifier.MIB) (encoding.Encoding, error) {
109+
v := findMIB(x.toMIB, mib)
110+
if v == -1 {
111+
return nil, errUnsupported
112+
}
113+
return x.enc[v], nil
114+
}
115+
107116
// TODO: the coverage of this index is rather spotty. Allowing users to set
108117
// encodings would allow:
109118
// - users to increase coverage

‎encoding/ianaindex/ianaindex_test.go‎

Lines changed: 15 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -105,6 +105,21 @@ func TestEncoding(t *testing.T) {
105105
if got, err := tc.index.Name(enc); got != tc.canonical {
106106
t.Errorf("%d: Name(Encoding(%q)) = %q; want %q (%v)", i, tc.name, got, tc.canonical, err)
107107
}
108+
109+
id, ok := enc.(identifier.Interface)
110+
if !ok {
111+
t.Errorf("%d: encoding %q has no ID", i, tc.name)
112+
}
113+
mib, _ := id.ID()
114+
if mib == 0 {
115+
t.Errorf("%d: encoding %q returned 0 MIB enum", i, tc.name)
116+
}
117+
mibEnc, err := tc.index.FindMIB(mib)
118+
if err != nil {
119+
t.Errorf("%d: FindMIB error %q", i, err)
120+
} else if mibEnc != enc {
121+
t.Errorf("%d: FindMIB did not match encoding", i)
122+
}
108123
}
109124
}
110125

‎encoding/identifier/identifier.go‎

Lines changed: 79 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,79 @@
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+
// Package identifier defines the contract between implementations of Encoding
6+
// and Index by defining identifiers that uniquely identify standardized coded
7+
// character sets (CCS) and character encoding schemes (CES), which we will
8+
// together refer to as encodings, for which Encoding implementations provide
9+
// converters to and from UTF-8. This package is typically only of concern to
10+
// implementers of Indexes and Encodings.
11+
//
12+
// One part of the identifier is the MIB code, which is defined by IANA and
13+
// uniquely identifies a CCS or CES. Each code is associated with data that
14+
// references authorities, official documentation as well as aliases and MIME
15+
// names.
16+
//
17+
// Not all CESs are covered by the IANA registry. The "other" string that is
18+
// returned by ID can be used to identify other character sets or versions of
19+
// existing ones.
20+
//
21+
// It is recommended that each package that provides a set of Encodings provide
22+
// the All and Common variables to reference all supported encodings and
23+
// commonly used subset. This allows Index implementations to include all
24+
// available encodings without explicitly referencing or knowing about them.
25+
package identifier
26+
27+
// Note: this package is internal, but could be made public if there is a need
28+
// for writing third-party Indexes and Encodings.
29+
30+
// References:
31+
// - http://source.icu-project.org/repos/icu/icu/trunk/source/data/mappings/convrtrs.txt
32+
// - http://www.iana.org/assignments/character-sets/character-sets.xhtml
33+
// - http://www.iana.org/assignments/ianacharset-mib/ianacharset-mib
34+
// - http://www.ietf.org/rfc/rfc2978.txt
35+
// - https://www.unicode.org/reports/tr22/
36+
// - http://www.w3.org/TR/encoding/
37+
// - https://encoding.spec.whatwg.org/
38+
// - https://encoding.spec.whatwg.org/encodings.json
39+
// - https://tools.ietf.org/html/rfc6657#section-5
40+
41+
// Interface can be implemented by Encodings to define the CCS or CES for which
42+
// it implements conversions.
43+
type Interface interface {
44+
// ID returns an encoding identifier. Exactly one of the mib and other
45+
// values should be non-zero.
46+
//
47+
// In the usual case it is only necessary to indicate the MIB code. The
48+
// other string can be used to specify encodings for which there is no MIB,
49+
// such as "x-mac-dingbat".
50+
//
51+
// The other string may only contain the characters a-z, A-Z, 0-9, - and _.
52+
ID() (mib MIB, other string)
53+
54+
// NOTE: the restrictions on the encoding are to allow extending the syntax
55+
// with additional information such as versions, vendors and other variants.
56+
}
57+
58+
// A MIB identifies an encoding. It is derived from the IANA MIB codes and adds
59+
// some identifiers for some encodings that are not covered by the IANA
60+
// standard.
61+
//
62+
// See http://www.iana.org/assignments/ianacharset-mib.
63+
type MIB uint16
64+
65+
// These additional MIB types are not defined in IANA. They are added because
66+
// they are common and defined within the text repo.
67+
const (
68+
// Unofficial marks the start of encodings not registered by IANA.
69+
Unofficial MIB = 10000 + iota
70+
71+
// Replacement is the WhatWG replacement encoding.
72+
Replacement
73+
74+
// XUserDefined is the code for x-user-defined.
75+
XUserDefined
76+
77+
// MacintoshCyrillic is the code for x-mac-cyrillic.
78+
MacintoshCyrillic
79+
)

‎encoding/internal/identifier/identifier.go‎

Lines changed: 9 additions & 70 deletions
Original file line numberDiff line numberDiff line change
@@ -4,78 +4,17 @@
44

55
//go:generate go run gen.go
66

7-
// Package identifier defines the contract between implementations of Encoding
8-
// and Index by defining identifiers that uniquely identify standardized coded
9-
// character sets (CCS) and character encoding schemes (CES), which we will
10-
// together refer to as encodings, for which Encoding implementations provide
11-
// converters to and from UTF-8. This package is typically only of concern to
12-
// implementers of Indexes and Encodings.
13-
//
14-
// One part of the identifier is the MIB code, which is defined by IANA and
15-
// uniquely identifies a CCS or CES. Each code is associated with data that
16-
// references authorities, official documentation as well as aliases and MIME
17-
// names.
18-
//
19-
// Not all CESs are covered by the IANA registry. The "other" string that is
20-
// returned by ID can be used to identify other character sets or versions of
21-
// existing ones.
22-
//
23-
// It is recommended that each package that provides a set of Encodings provide
24-
// the All and Common variables to reference all supported encodings and
25-
// commonly used subset. This allows Index implementations to include all
26-
// available encodings without explicitly referencing or knowing about them.
277
package identifier
288

29-
// Note: this package is internal, but could be made public if there is a need
30-
// for writing third-party Indexes and Encodings.
31-
32-
// References:
33-
// - http://source.icu-project.org/repos/icu/icu/trunk/source/data/mappings/convrtrs.txt
34-
// - http://www.iana.org/assignments/character-sets/character-sets.xhtml
35-
// - http://www.iana.org/assignments/ianacharset-mib/ianacharset-mib
36-
// - http://www.ietf.org/rfc/rfc2978.txt
37-
// - https://www.unicode.org/reports/tr22/
38-
// - http://www.w3.org/TR/encoding/
39-
// - https://encoding.spec.whatwg.org/
40-
// - https://encoding.spec.whatwg.org/encodings.json
41-
// - https://tools.ietf.org/html/rfc6657#section-5
42-
43-
// Interface can be implemented by Encodings to define the CCS or CES for which
44-
// it implements conversions.
45-
type Interface interface {
46-
// ID returns an encoding identifier. Exactly one of the mib and other
47-
// values should be non-zero.
48-
//
49-
// In the usual case it is only necessary to indicate the MIB code. The
50-
// other string can be used to specify encodings for which there is no MIB,
51-
// such as "x-mac-dingbat".
52-
//
53-
// The other string may only contain the characters a-z, A-Z, 0-9, - and _.
54-
ID() (mib MIB, other string)
55-
56-
// NOTE: the restrictions on the encoding are to allow extending the syntax
57-
// with additional information such as versions, vendors and other variants.
58-
}
59-
60-
// A MIB identifies an encoding. It is derived from the IANA MIB codes and adds
61-
// some identifiers for some encodings that are not covered by the IANA
62-
// standard.
63-
//
64-
// See http://www.iana.org/assignments/ianacharset-mib.
65-
type MIB uint16
66-
67-
// These additional MIB types are not defined in IANA. They are added because
68-
// they are common and defined within the text repo.
69-
const (
70-
// Unofficial marks the start of encodings not registered by IANA.
71-
Unofficial MIB = 10000 + iota
9+
import (
10+
"golang.org/x/text/encoding/identifier"
11+
)
7212

73-
// Replacement is the WhatWG replacement encoding.
74-
Replacement
13+
var Replacement = identifier.Replacement
7514

76-
// XUserDefined is the code for x-user-defined.
77-
XUserDefined
15+
type Interface = identifier.Interface
16+
type MIB = identifier.MIB
7817

79-
// MacintoshCyrillic is the code for x-mac-cyrillic.
80-
MacintoshCyrillic
81-
)
18+
var Unofficial = identifier.Unofficial
19+
var MacintoshCyrillic = identifier.MacintoshCyrillic
20+
var XUserDefined = identifier.XUserDefined

0 commit comments

Comments
 (0)