/src/poco/Foundation/include/Poco/UTF32Encoding.h
Line | Count | Source (jump to first uncovered line) |
1 | | // |
2 | | // UTF32Encoding.h |
3 | | // |
4 | | // Library: Foundation |
5 | | // Package: Text |
6 | | // Module: UTF32Encoding |
7 | | // |
8 | | // Definition of the UTF32Encoding class. |
9 | | // |
10 | | // Copyright (c) 2004-2007, Applied Informatics Software Engineering GmbH. |
11 | | // and Contributors. |
12 | | // |
13 | | // SPDX-License-Identifier: BSL-1.0 |
14 | | // |
15 | | |
16 | | |
17 | | #ifndef Foundation_UTF32Encoding_INCLUDED |
18 | | #define Foundation_UTF32Encoding_INCLUDED |
19 | | |
20 | | |
21 | | #include "Poco/Foundation.h" |
22 | | #include "Poco/TextEncoding.h" |
23 | | |
24 | | |
25 | | namespace Poco { |
26 | | |
27 | | |
28 | | class Foundation_API UTF32Encoding: public TextEncoding |
29 | | /// UTF-32 text encoding, as defined in RFC 2781. |
30 | | /// |
31 | | /// When converting from UTF-32 to Unicode, surrogates are |
32 | | /// reported as they are - in other words, surrogate pairs |
33 | | /// are not combined into one Unicode character. |
34 | | { |
35 | | public: |
36 | | enum ByteOrderType |
37 | | { |
38 | | BIG_ENDIAN_BYTE_ORDER, |
39 | | LITTLE_ENDIAN_BYTE_ORDER, |
40 | | NATIVE_BYTE_ORDER |
41 | | }; |
42 | | |
43 | | UTF32Encoding(ByteOrderType byteOrder = NATIVE_BYTE_ORDER); |
44 | | /// Creates and initializes the encoding for the given byte order. |
45 | | |
46 | | UTF32Encoding(int byteOrderMark); |
47 | | /// Creates and initializes the encoding for the byte-order |
48 | | /// indicated by the given byte-order mark, which is the Unicode |
49 | | /// character 0xFEFF. |
50 | | |
51 | | ~UTF32Encoding(); |
52 | | |
53 | | ByteOrderType getByteOrder() const; |
54 | | /// Returns the byte-order currently in use. |
55 | | |
56 | | void setByteOrder(ByteOrderType byteOrder); |
57 | | /// Sets the byte order. |
58 | | |
59 | | void setByteOrder(int byteOrderMark); |
60 | | /// Sets the byte order according to the given |
61 | | /// byte order mark, which is the Unicode |
62 | | /// character 0xFEFF. |
63 | | |
64 | | const char* canonicalName() const; |
65 | | bool isA(const std::string& encodingName) const; |
66 | | const CharacterMap& characterMap() const; |
67 | | int convert(const unsigned char* bytes) const; |
68 | | int convert(int ch, unsigned char* bytes, int length) const; |
69 | | int queryConvert(const unsigned char* bytes, int length) const; |
70 | | int sequenceLength(const unsigned char* bytes, int length) const; |
71 | | |
72 | | protected: |
73 | | static int safeToInt(Poco::UInt32 value) |
74 | 0 | { |
75 | 0 | if (value <= 0x10FFFF) |
76 | 0 | return static_cast<int>(value); |
77 | 0 | else |
78 | 0 | return -1; |
79 | 0 | } |
80 | | |
81 | | private: |
82 | | bool _flipBytes; |
83 | | static const char* _names[]; |
84 | | static const CharacterMap _charMap; |
85 | | }; |
86 | | |
87 | | |
88 | | } // namespace Poco |
89 | | |
90 | | |
91 | | #endif // Foundation_UTF32Encoding_INCLUDED |