UTF-8 text encoding, as defined in RFC 2279. More...
#include <UTF8Encoding.h>
Public Member Functions | |
const char * | canonicalName () const |
Destroys the encoding. | |
const CharacterMap & | characterMap () const |
int | convert (int ch, unsigned char *bytes, int length) const |
int | convert (const unsigned char *bytes) const |
bool | isA (const std::string &encodingName) const |
UTF8Encoding () | |
~UTF8Encoding () | |
Static Public Member Functions | |
static bool | isLegal (const unsigned char *bytes, int length) |
Static Private Attributes | |
static const CharacterMap | _charMap |
static const char * | _names [] |
UTF-8 text encoding, as defined in RFC 2279.
Definition at line 50 of file UTF8Encoding.h.
Poco::UTF8Encoding::UTF8Encoding | ( | ) |
Definition at line 73 of file UTF8Encoding.cpp.
Poco::UTF8Encoding::~UTF8Encoding | ( | ) |
Definition at line 78 of file UTF8Encoding.cpp.
const char * Poco::UTF8Encoding::canonicalName | ( | ) | const [virtual] |
Destroys the encoding.
Implements Poco::TextEncoding.
Definition at line 83 of file UTF8Encoding.cpp.
const TextEncoding::CharacterMap & Poco::UTF8Encoding::characterMap | ( | ) | const [virtual] |
Returns true if the given name is one of the names of this encoding. For example, the "ISO-8859-1" encoding is also known as "Latin-1".
Encoding name comparision are be case insensitive.
Implements Poco::TextEncoding.
Definition at line 100 of file UTF8Encoding.cpp.
int Poco::UTF8Encoding::convert | ( | int | ch, | |
unsigned char * | bytes, | |||
int | length | |||
) | const [virtual] |
The convert function is used to convert multibyte sequences; bytes will point to a byte sequence of n bytes where getCharacterMap()[*bytes] == -n.
The convert function must return the Unicode scalar value represented by this byte sequence or -1 if the byte sequence is malformed. The default implementation returns (int) bytes[0].
Reimplemented from Poco::TextEncoding.
Definition at line 181 of file UTF8Encoding.cpp.
int Poco::UTF8Encoding::convert | ( | const unsigned char * | bytes | ) | const [virtual] |
Returns the CharacterMap for the encoding. The CharacterMap should be kept in a static member. As characterMap() can be called frequently, it should be implemented in such a way that it just returns a static map. If the map is built at runtime, this should be done in the constructor.
Reimplemented from Poco::TextEncoding.
Definition at line 151 of file UTF8Encoding.cpp.
bool Poco::UTF8Encoding::isA | ( | const std::string & | encodingName | ) | const [virtual] |
Returns the canonical name of this encoding, e.g. "ISO-8859-1". Encoding name comparisons are case insensitive.
Implements Poco::TextEncoding.
Definition at line 89 of file UTF8Encoding.cpp.
bool Poco::UTF8Encoding::isLegal | ( | const unsigned char * | bytes, | |
int | length | |||
) | [static] |
Definition at line 106 of file UTF8Encoding.cpp.
const TextEncoding::CharacterMap Poco::UTF8Encoding::_charMap [static, private] |
{ 0x00, 0x01, 0x02, 0x03, 0x04, 0x05, 0x06, 0x07, 0x08, 0x09, 0x0a, 0x0b, 0x0c, 0x0d, 0x0e, 0x0f, 0x10, 0x11, 0x12, 0x13, 0x14, 0x15, 0x16, 0x17, 0x18, 0x19, 0x1a, 0x1b, 0x1c, 0x1d, 0x1e, 0x1f, 0x20, 0x21, 0x22, 0x23, 0x24, 0x25, 0x26, 0x27, 0x28, 0x29, 0x2a, 0x2b, 0x2c, 0x2d, 0x2e, 0x2f, 0x30, 0x31, 0x32, 0x33, 0x34, 0x35, 0x36, 0x37, 0x38, 0x39, 0x3a, 0x3b, 0x3c, 0x3d, 0x3e, 0x3f, 0x40, 0x41, 0x42, 0x43, 0x44, 0x45, 0x46, 0x47, 0x48, 0x49, 0x4a, 0x4b, 0x4c, 0x4d, 0x4e, 0x4f, 0x50, 0x51, 0x52, 0x53, 0x54, 0x55, 0x56, 0x57, 0x58, 0x59, 0x5a, 0x5b, 0x5c, 0x5d, 0x5e, 0x5f, 0x60, 0x61, 0x62, 0x63, 0x64, 0x65, 0x66, 0x67, 0x68, 0x69, 0x6a, 0x6b, 0x6c, 0x6d, 0x6e, 0x6f, 0x70, 0x71, 0x72, 0x73, 0x74, 0x75, 0x76, 0x77, 0x78, 0x79, 0x7a, 0x7b, 0x7c, 0x7d, 0x7e, 0x7f, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -2, -2, -2, -2, -2, -2, -2, -2, -2, -2, -2, -2, -2, -2, -2, -2, -2, -2, -2, -2, -2, -2, -2, -2, -2, -2, -2, -2, -2, -2, -2, -2, -3, -3, -3, -3, -3, -3, -3, -3, -3, -3, -3, -3, -3, -3, -3, -3, -4, -4, -4, -4, -4, -4, -4, -4, -5, -5, -5, -5, -6, -6, -1, -1, }
Definition at line 74 of file UTF8Encoding.h.
const char * Poco::UTF8Encoding::_names [static, private] |
{ "UTF-8", "UTF8", NULL }
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.
Definition at line 73 of file UTF8Encoding.h.