32 #ifndef _QORE_ENCODING_H
34 #define _QORE_ENCODING_H
42 #include <qore/QoreThreadLock.h>
69 struct qore_encoding_private;
84 friend struct qore_encoding_private;
96 unsigned char maxwidth;
98 qore_encoding_private* priv;
200 typedef std::map<const char*, QoreEncoding*, ltcstrcase> encoding_map_t;
201 typedef std::map<const char*, const QoreEncoding*, ltcstrcase> const_encoding_map_t;
210 DLLLOCAL
static encoding_map_t emap;
211 DLLLOCAL
static const_encoding_map_t amap;
215 DLLLOCAL
static const QoreEncoding* findUnlocked(
const char* name);
236 DLLLOCAL
static void init(
const char* def);
DLLEXPORT const QoreEncoding * QCS_UTF16
UTF-16 (only UTF-8 and UTF-16* are multi-byte encodings)
Definition: QoreEncoding.h:251
qore_size_t(* mbcs_length_t)(const char *str, const char *end, bool &invalid)
for multi-byte character set encodings: gives the length of the string in characters
Definition: QoreEncoding.h:50
DLLEXPORT const QoreEncoding * QCS_KOI7
Russian: Kod Obmena Informatsiey, 7 bit characters.
Definition: QoreEncoding.h:271
DLLEXPORT const QoreEncoding * QCS_KOI8_R
Russian: Kod Obmena Informatsiey, 8 bit.
Definition: QoreEncoding.h:269
DLLEXPORT const QoreEncoding * QCS_KOI8_U
Ukrainian: Kod Obmena Informatsiey, 8 bit.
Definition: QoreEncoding.h:270
DLLEXPORT const QoreEncoding * QCS_ISO_8859_4
latin-4, Northern European character set
Definition: QoreEncoding.h:257
DLLEXPORT const QoreEncoding * QCS_ISO_8859_11
Thai character set.
Definition: QoreEncoding.h:264
qore_size_t(* mbcs_end_t)(const char *str, const char *end, qore_size_t num_chars, bool &invalid)
for multi-byte character set encodings: gives the number of bytes for the number of chars
Definition: QoreEncoding.h:53
DLLEXPORT const QoreEncoding * QCS_DEFAULT
the default encoding for the Qore library
DLLEXPORT const QoreEncoding * QCS_ISO_8859_15
latin-9, Western European with euro symbol
Definition: QoreEncoding.h:267
DLLEXPORT const QoreEncoding * QCS_UTF16LE
UTF-16LE (only UTF-8 and UTF-16* are multi-byte encodings)
Definition: QoreEncoding.h:253
DLLEXPORT const QoreEncoding * QCS_ISO_8859_6
Arabic character set.
Definition: QoreEncoding.h:259
DLLEXPORT const QoreEncoding * QCS_ISO_8859_8
Hebrew character set.
Definition: QoreEncoding.h:261
DLLEXPORT const QoreEncoding * QCS_UTF16BE
UTF-16BE (only UTF-8 and UTF-16* are multi-byte encodings)
Definition: QoreEncoding.h:252
DLLEXPORT const QoreEncoding * QCS_ISO_8859_9
latin-5, Turkish character set
Definition: QoreEncoding.h:262
DLLEXPORT const QoreEncoding * QCS_ISO_8859_7
Greek character set.
Definition: QoreEncoding.h:260
DLLEXPORT const QoreEncoding * QCS_ISO_8859_16
latin-10, Southeast European character set
Definition: QoreEncoding.h:268
qore_offset_t(* mbcs_charlen_t)(const char *str, qore_size_t valid_len)
for multi-byte encodings: gives the number of total bytes for the character given one or more charact...
Definition: QoreEncoding.h:63
DLLEXPORT const QoreEncoding * QCS_UTF8
UTF-8 multi-byte encoding (only UTF-8 and UTF-16 are multi-byte encodings)
Definition: QoreEncoding.h:250
DLLEXPORT const QoreEncoding * QCS_ISO_8859_2
latin-2, Central European encoding
Definition: QoreEncoding.h:255
DLLEXPORT const QoreEncoding * QCS_ISO_8859_10
latin-6, Nordic character set
Definition: QoreEncoding.h:263
DLLEXPORT const QoreEncoding * QCS_ISO_8859_1
latin-1, Western European encoding
Definition: QoreEncoding.h:254
qore_size_t(* mbcs_pos_t)(const char *str, const char *ptr, bool &invalid)
for multi-byte character set encodings: gives the character position of the ptr
Definition: QoreEncoding.h:56
DLLEXPORT const QoreEncoding * QCS_ISO_8859_5
Cyrillic character set.
Definition: QoreEncoding.h:258
DLLEXPORT QoreEncodingManager QEM
the QoreEncodingManager object
DLLEXPORT const QoreEncoding * QCS_ISO_8859_3
latin-3, Southern European character set
Definition: QoreEncoding.h:256
DLLEXPORT const QoreEncoding * QCS_USASCII
ascii encoding
Definition: QoreEncoding.h:249
unsigned(* mbcs_get_unicode_t)(const char *p)
returns the unicode code point for the given character, assumes there is enough data for the characte...
Definition: QoreEncoding.h:66
DLLEXPORT const QoreEncoding * QCS_ISO_8859_14
latin-8, Celtic character set
Definition: QoreEncoding.h:266
DLLEXPORT const QoreEncoding * QCS_ISO_8859_13
latin-7, Baltic rim character set
Definition: QoreEncoding.h:265
container for holding Qore-language exception information and also for registering a "thread_exit" ca...
Definition: ExceptionSink.h:48
defines string encoding functions in Qore
Definition: QoreEncoding.h:83
DLLEXPORT bool isMultiByte() const
returns true if the encoding is a multi-byte encoding
DLLEXPORT qore_size_t getByteLen(const char *p, const char *end, qore_size_t c, bool &invalid) const
gives the number of bytes for the number of chars in the string or up to the end of the string
DLLEXPORT int getUnicode(const char *p, const char *end, unsigned &clen, ExceptionSink *xsink) const
returns the unicode code point for the given character; if there are any errors (invalid character,...
DLLEXPORT qore_size_t getLength(const char *p, const char *end, bool &invalid) const
gives the length of the string in characters
DLLEXPORT int getMaxCharWidth() const
returns the maximum character width in bytes for the encoding
DLLEXPORT unsigned getMinCharWidth() const
returns the minimum character width in bytes for the encoding
DLLEXPORT qore_offset_t getCharLen(const char *p, qore_size_t valid_len) const
gives the number of total bytes for the next character at the given pointer
DLLEXPORT const char * getCode() const
returns the string code (ex: "UTF-8") for the encoding
DLLEXPORT const char * getDesc() const
returns the description for the encoding
DLLEXPORT qore_size_t getCharPos(const char *p, const char *end, bool &invalid) const
gives the character position (number of characters) starting from the first pointer to the second
DLLEXPORT bool isAsciiCompat() const
returns true if the character encoding is backwards-compatible with ASCII
manages encodings in Qore
Definition: QoreEncoding.h:208
static DLLEXPORT const QoreEncoding * add(const char *code, const char *desc=0, unsigned char maxwidth=1, mbcs_length_t l=0, mbcs_end_t e=0, mbcs_pos_t p=0, mbcs_charlen_t=0)
adds a new encoding to the list
static DLLEXPORT void showAliases()
prints out all aliases to stdout
static DLLEXPORT const QoreEncoding * findCreate(const char *name)
finds an encoding if it exists (also looks up against alias names) and creates a new one if it doesn'...
static DLLEXPORT void showEncodings()
prints out all valid encodings to stdout
static DLLEXPORT void addAlias(const QoreEncoding *qcs, const char *alias)
adds an alias for an encoding
Qore's string type supported by the QoreEncoding class.
Definition: QoreString.h:81
provides a mutually-exclusive thread lock
Definition: QoreThreadLock.h:49
intptr_t qore_offset_t
used for offsets that could be negative
Definition: common.h:76
size_t qore_size_t
used for sizes (same range as a pointer)
Definition: common.h:73