214 lines
3.4 KiB
Plaintext
214 lines
3.4 KiB
Plaintext
.TH RUNE 2
|
|
.SH NAME
|
|
runetochar, chartorune, runelen, runenlen, fullrune, utfecpy, utflen, utfnlen, utfrune, utfrrune, utfutf \- rune/UTF conversion
|
|
.SH SYNOPSIS
|
|
.ta \w'\fLchar*xx'u
|
|
.B #include <u.h>
|
|
.br
|
|
.B #include <libc.h>
|
|
.PP
|
|
.B
|
|
int runetochar(char *s, Rune *r)
|
|
.PP
|
|
.B
|
|
int chartorune(Rune *r, char *s)
|
|
.PP
|
|
.B
|
|
int runelen(long r)
|
|
.PP
|
|
.B
|
|
int runenlen(Rune *r, int n)
|
|
.PP
|
|
.B
|
|
int fullrune(char *s, int n)
|
|
.PP
|
|
.B
|
|
char* utfecpy(char *s1, char *es1, char *s2)
|
|
.PP
|
|
.B
|
|
int utflen(char *s)
|
|
.PP
|
|
.B
|
|
int utfnlen(char *s, long n)
|
|
.PP
|
|
.B
|
|
char* utfrune(char *s, long c)
|
|
.PP
|
|
.B
|
|
char* utfrrune(char *s, long c)
|
|
.PP
|
|
.B
|
|
char* utfutf(char *s1, char *s2)
|
|
.SH DESCRIPTION
|
|
These routines convert to and from a
|
|
.SM UTF
|
|
byte stream and runes.
|
|
.PP
|
|
.I Runetochar
|
|
copies one rune at
|
|
.I r
|
|
to at most
|
|
.B UTFmax
|
|
bytes starting at
|
|
.I s
|
|
and returns the number of bytes copied.
|
|
.BR UTFmax ,
|
|
defined as
|
|
.B 4
|
|
in
|
|
.BR <libc.h> ,
|
|
is the maximum number of bytes required to represent a rune.
|
|
.PP
|
|
.I Chartorune
|
|
copies at most
|
|
.B UTFmax
|
|
bytes starting at
|
|
.I s
|
|
to one rune at
|
|
.I r
|
|
and returns the number of bytes copied.
|
|
If the input is not exactly in
|
|
.SM UTF
|
|
format,
|
|
.I chartorune
|
|
will convert to
|
|
.B Runeerror
|
|
(0xFFFD)
|
|
and return 1.
|
|
.PP
|
|
.I Runelen
|
|
returns the number of bytes
|
|
required to convert
|
|
.I r
|
|
into
|
|
.SM UTF.
|
|
.PP
|
|
.I Runenlen
|
|
returns the number of bytes
|
|
required to convert the
|
|
.I n
|
|
runes pointed to by
|
|
.I r
|
|
into
|
|
.SM UTF.
|
|
.PP
|
|
.I Fullrune
|
|
returns 1 if the string
|
|
.I s
|
|
of length
|
|
.I n
|
|
is long enough to be decoded by
|
|
.I chartorune
|
|
and 0 otherwise.
|
|
This does not guarantee that the string
|
|
contains a legal
|
|
.SM UTF
|
|
encoding.
|
|
This routine is used by programs that
|
|
obtain input a byte at
|
|
a time and need to know when a full rune
|
|
has arrived.
|
|
.PP
|
|
The following routines are analogous to the
|
|
corresponding string routines with
|
|
.B utf
|
|
substituted for
|
|
.B str
|
|
and
|
|
.B rune
|
|
substituted for
|
|
.BR chr .
|
|
.PP
|
|
.I Utfecpy
|
|
copies UTF sequences until a null sequence has been copied, but writes no
|
|
sequences beyond
|
|
.IR es1 .
|
|
If any sequences are copied,
|
|
.I s1
|
|
is terminated by a null sequence, and a pointer to that sequence is returned.
|
|
Otherwise, the original
|
|
.I s1
|
|
is returned.
|
|
.PP
|
|
.I Utflen
|
|
returns the number of runes that
|
|
are represented by the
|
|
.SM UTF
|
|
string
|
|
.IR s .
|
|
.PP
|
|
.I Utfnlen
|
|
returns the number of complete runes that
|
|
are represented by the first
|
|
.I n
|
|
bytes of
|
|
.SM UTF
|
|
string
|
|
.IR s .
|
|
If the last few bytes of the string contain an incompletely coded rune,
|
|
.I utfnlen
|
|
will not count them; in this way, it differs from
|
|
.IR utflen ,
|
|
which includes every byte of the string.
|
|
.PP
|
|
.I Utfrune
|
|
.RI ( utfrrune )
|
|
returns a pointer to the first (last)
|
|
occurrence of rune
|
|
.I c
|
|
in the
|
|
.SM UTF
|
|
string
|
|
.IR s ,
|
|
or 0 if
|
|
.I c
|
|
does not occur in the string.
|
|
The NUL byte terminating a string is considered to
|
|
be part of the string
|
|
.IR s .
|
|
.PP
|
|
.I Utfutf
|
|
returns a pointer to the first occurrence of
|
|
the
|
|
.SM UTF
|
|
string
|
|
.I s2
|
|
as a
|
|
.SM UTF
|
|
substring of
|
|
.IR s1 ,
|
|
or 0 if there is none.
|
|
If
|
|
.I s2
|
|
is the null string,
|
|
.I utfutf
|
|
returns
|
|
.IR s1 .
|
|
.SH SOURCE
|
|
.B /sys/src/libc/port/rune.c
|
|
.br
|
|
.B /sys/src/libc/port/utfecpy.c
|
|
.br
|
|
.B /sys/src/libc/port/utfrune.c
|
|
.br
|
|
.B /sys/src/libc/port/utfrrune.c
|
|
.br
|
|
.B /sys/src/libc/port/utflen.c
|
|
.br
|
|
.B /sys/src/libc/port/utfnlen.c
|
|
.br
|
|
.B /sys/src/libc/port/utfutf.c
|
|
.SH SEE ALSO
|
|
.IR utf (6),
|
|
.IR tcs (1)
|
|
.SH BUGS
|
|
When re-encoding UTF strings with
|
|
.I chartorune
|
|
and
|
|
.I runetochar
|
|
one has to consider that encoding a
|
|
.I Runeerror
|
|
(0xFFFD)
|
|
that resulted from invalid encoded input can yield
|
|
a longer UTF sequence on the output.
|