blob: 66e29d2d00e4d2b3cbade63d9abd9e2e4e297ee8 (
plain) (
blame)
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
|
//
// UTF8Encoding.h
//
// Library: Foundation
// Package: Text
// Module: UTF8Encoding
//
// Definition of the UTF8Encoding class.
//
// Copyright (c) 2004-2007, Applied Informatics Software Engineering GmbH.
// and Contributors.
//
// SPDX-License-Identifier: BSL-1.0
//
#ifndef Foundation_UTF8Encoding_INCLUDED
#define Foundation_UTF8Encoding_INCLUDED
#include "Poco/Foundation.h"
#include "Poco/TextEncoding.h"
namespace Poco {
class Foundation_API UTF8Encoding: public TextEncoding
/// UTF-8 text encoding, as defined in RFC 2279.
{
public:
UTF8Encoding();
~UTF8Encoding();
const char* canonicalName() const;
bool isA(const std::string& encodingName) const;
const CharacterMap& characterMap() const;
int convert(const unsigned char* bytes) const;
int convert(int ch, unsigned char* bytes, int length) const;
int queryConvert(const unsigned char* bytes, int length) const;
int sequenceLength(const unsigned char* bytes, int length) const;
static bool isLegal(const unsigned char *bytes, int length);
/// Utility routine to tell whether a sequence of bytes is legal UTF-8.
/// This must be called with the length pre-determined by the first byte.
/// The sequence is illegal right away if there aren't enough bytes
/// available. If presented with a length > 4, this function returns false.
/// The Unicode definition of UTF-8 goes up to 4-byte sequences.
///
/// Adapted from ftp://ftp.unicode.org/Public/PROGRAMS/CVTUTF/ConvertUTF.c
/// Copyright 2001-2004 Unicode, Inc.
private:
static const char* _names[];
static const CharacterMap _charMap;
};
} // namespace Poco
#endif // Foundation_UTF8Encoding_INCLUDED
|
