utf8impl.h File Reference

UTF-8 manipulation macros (implementation). More...

#include <stdbool.h>
#include <stdlib.h>
#include <string.h>

Go to the source code of this file.

Macros
#define	UTF8_TO_UCS4(s, len, ucs4, clen, error)
	Convert a UTF-8 multibyte sequence into a single UCS-4 character. More...
#define	UTF8_FROM_UCS4(ucs4, s, len, error)
	Convert a single UCS-4 character into a UTF-8 multibyte sequence. More...
#define	UTF8_LENGTH(s, max, len, error)
	Calculate the length (in characters) of a bounded UTF-8 string. More...
#define	UTF8_CHAR_BYTE_LENGTH(s, len, error)
	Calculate the length (in bytes) of a UTF-8 character. More...
#define	UTF8_PREV(s, off, prevoff, error)
	Find previous legal UTF-8 char in string. More...
#define	UTF8_NEXT(s, len, off, nextoff, error)
	Find next legal UTF-8 char in string. More...
#define	UTF8_NEXT_PARANOID(s, len, off, nextoff, error)
	Skip to start of next sequence in UTF-8 input. More...

Variables
const uint8_t	numContinuations [256]
	Number of continuation bytes for a given start byte. More...

Detailed Description

UTF-8 manipulation macros (implementation).

Definition in file utf8impl.h.

Macro Definition Documentation

UTF8_CHAR_BYTE_LENGTH

#define UTF8_CHAR_BYTE_LENGTH	(		s,
			len,
			error
	)

Value:

do {                                                                    \
        if (s == NULL || len == NULL) {                                 \
                error = PARSERUTILS_BADPARM;                            \
                break;                                                  \
        }                                                               \
                                                                        \
        *len = numContinuations[s[0]] + 1 /* Start byte */;             \
                                                                        \
        error = PARSERUTILS_OK;                                         \
} while(0)

Calculate the length (in bytes) of a UTF-8 character.

Parameters

s	Pointer to start of character
len	Pointer to location to receive length
error	Location to receive error code

Definition at line 228 of file utf8impl.h.

UTF8_FROM_UCS4

#define UTF8_FROM_UCS4	(		ucs4,
			s,
			len,
			error
	)

Convert a single UCS-4 character into a UTF-8 multibyte sequence.

Encoding of UCS values outside the UTF-16 plane has been removed from RFC3629. This macro conforms to RFC2279, however.

Parameters

ucs4	The character to process (0 <= c <= 0x7FFFFFFF) (host endian)
s	Pointer to pointer to output buffer, updated on exit
len	Pointer to length, in bytes, of output buffer, updated on exit
error	Location to receive error code

Definition at line 123 of file utf8impl.h.

UTF8_LENGTH

#define UTF8_LENGTH	(		s,
			max,
			len,
			error
	)

Calculate the length (in characters) of a bounded UTF-8 string.

Parameters

s	The string
max	Maximum length
len	Pointer to location to receive length of string
error	Location to receive error code

Definition at line 182 of file utf8impl.h.

UTF8_NEXT

#define UTF8_NEXT	(		s,
			len,
			off,
			nextoff,
			error
	)

Value:

do {                                                                    \
        if (s == NULL || off >= len || nextoff == NULL) {               \
                error = PARSERUTILS_BADPARM;                            \
                break;                                                  \
        }                                                               \
                                                                        \
        /* Skip current start byte (if present - may be mid-sequence) */\
        if (s[off] < 0x80 || (s[off] & 0xC0) == 0xC0)                   \
                off++;                                                  \
                                                                        \
        while (off < len && (s[off] & 0xC0) == 0x80)                    \
                off++;                                                  \
                                                                        \
        *nextoff = off;                                                 \
                                                                        \
        error = PARSERUTILS_OK;                                         \
} while(0)

Find next legal UTF-8 char in string.

Parameters

s	The string (assumed valid)
len	Maximum offset in string
off	Offset in the string to start at
nextoff	Pointer to location to receive offset of first byte of next legal character
error	Location to receive error code

Definition at line 274 of file utf8impl.h.

UTF8_NEXT_PARANOID

#define UTF8_NEXT_PARANOID	(		s,
			len,
			off,
			nextoff,
			error
	)

Skip to start of next sequence in UTF-8 input.

Parameters

s	The string (assumed to be of dubious validity)
len	Maximum offset in string
off	Offset in the string to start at
nextoff	Pointer to location to receive offset of first byte of next legal character
error	Location to receive error code

Definition at line 303 of file utf8impl.h.

UTF8_PREV

#define UTF8_PREV	(		s,
			off,
			prevoff,
			error
	)

Value:

do {                                                                    \
        if (s == NULL || prevoff == NULL) {                             \
                error = PARSERUTILS_BADPARM;                            \
                break;                                                  \
        }                                                               \
                                                                        \
        while (off != 0 && (s[--off] & 0xC0) == 0x80)                   \
                /* do nothing */;                                       \
                                                                        \
        *prevoff = off;                                                 \
                                                                        \
        error = PARSERUTILS_OK;                                         \
} while(0)

Find previous legal UTF-8 char in string.

Parameters

s	The string
off	Offset in the string to start at
prevoff	Pointer to location to receive offset of first byte of previous legal character
error	Location to receive error code

Definition at line 249 of file utf8impl.h.

UTF8_TO_UCS4

#define UTF8_TO_UCS4	(		s,
			len,
			ucs4,
			clen,
			error
	)

Convert a UTF-8 multibyte sequence into a single UCS-4 character.

Encoding of UCS values outside the UTF-16 plane has been removed from RFC3629. This macro conforms to RFC2279, however.

Parameters

s	The sequence to process
len	Length of sequence
ucs4	Pointer to location to receive UCS-4 character (host endian)
clen	Pointer to location to receive byte length of UTF-8 sequence
error	Location to receive error code

Definition at line 34 of file utf8impl.h.

Variable Documentation

numContinuations

const uint8_t numContinuations[256]

extern

Number of continuation bytes for a given start byte.

Definition at line 20 of file utf8.c.