xref: /illumos-gate/usr/src/man/man9f/u8_validate.9f (revision 3b3c8f601c5530d4928a71e238c573c623491c34) 
 te
 Copyright (c) 2007, Sun Microsystems Inc. All Rights Reserved.
 The contents of this file are subject to the terms of the Common Development and Distribution License (the "License"). You may not use this file except in compliance with the License.
 You can obtain a copy of the license at usr/src/OPENSOLARIS.LICENSE or http://www.opensolaris.org/os/licensing. See the License for the specific language governing permissions and limitations under the License.
 When distributing Covered Code, include this CDDL HEADER in each file and include the License file at usr/src/OPENSOLARIS.LICENSE. If applicable, add the following below this CDDL HEADER, with the fields enclosed by brackets "[]" replaced with your own identifying information: Portions Copyright [yyyy] [name of copyright owner]
 U8_VALIDATE 9F "Sep 18, 2007"
 NAME
u8_validate - validate UTF-8 characters and calculate the byte length

 SYNOPSIS
#include <sys/types.h>
#include <sys/errno.h>
#include <sys/sunddi.h>

int u8_validate(char *u8str, size_t n, char **list, int flag,
 int *errno);




 INTERFACE LEVEL
illumos DDI specific (illumos DDI)

 PARAMETERS
u8str


The UTF-8 string to be validated.



n


The maximum number of bytes in u8str that can be examined and validated.



list


A list of null-terminated character strings in UTF-8 that must be additionally
checked against as invalid characters. The last string in list must be
null to indicate there is no further string.



flag


Possible validation options constructed by a bitwise-inclusive-OR of the
following values:
U8_VALIDATE_ENTIRE


By default, u8_validate() looks at the first character or up to n
bytes, whichever is smaller in terms of the number of bytes to be consumed, and
returns with the result.
When this option is used, u8_validate() will check up to n bytes
from u8str and possibly more than a character before returning the
result.



U8_VALIDATE_CHECK_ADDITIONAL


By default, u8_validate() does not use list supplied.
When this option is supplied with a list of character strings,
u8_validate() additionally validates u8str against the character
strings supplied with list and returns EBADF in errno if
u8str has any one of the character strings in list.



U8_VALIDATE_UCS2_RANGE


By default, u8_validate() uses the entire Unicode coding space of U+0000
to U+10FFFF.
When this option is specified, the valid Unicode coding space is smaller to
U+0000 to U+FFFF.






errno


An error occurred during validation. The following values are supported:
EBADF


Validation failed because list-specified characters were found in the string
pointed to by u8str.



EILSEQ


Validation failed because an illegal byte was found in the string pointed to by
u8str.



EINVAL


Validation failed because an incomplete byte was found in the string pointed to
by u8str.



ERANGE


Validation failed because character bytes were encountered that are outside the
range of the Unicode coding space.







 DESCRIPTION
The u8_validate() function validates u8str in UTF-8 and determines
the number of bytes constituting the character(s) pointed to by u8str.

 RETURN VALUES
If u8str is a null pointer, u8_validate() returns 0. Otherwise,
u8_validate() returns either the number of bytes that constitute the
characters if the next n or fewer bytes form valid characters, or -1 if
there is an validation failure, in which case it may set errno to
indicate the error.

 EXAMPLES
Example 1 Determine the length of the first UTF-8 character.

#include <sys/types.h>
#include <sys/errno.h>
#include <sys/sunddi.h>

char u8[MAXPATHLEN];
int errno;
.
.
.
len = u8_validate(u8, 4, (char **)NULL, 0, &errno);
if (len == -1) {
 switch (errno) {
 case EILSEQ:
 case EINVAL:
 return (MYFS4_ERR_INVAL);
 case EBADF:
 return (MYFS4_ERR_BADNAME);
 case ERANGE:
 return (MYFS4_ERR_BADCHAR);
 default:
 return (-10);
 }
}





Example 2 Check if there are any invalid characters in the entire string.

#include <sys/types.h>
#include <sys/errno.h>
#include <sys/sunddi.h>

char u8[MAXPATHLEN];
int n;
int errno;
.
.
.
n = strlen(u8);
len = u8_validate(u8, n, (char **)NULL, U8_VALIDATE_ENTIRE, &errno);
if (len == -1) {
 switch (errno) {
 case EILSEQ:
 case EINVAL:
 return (MYFS4_ERR_INVAL);
 case EBADF:
 return (MYFS4_ERR_BADNAME);
 case ERANGE:
 return (MYFS4_ERR_BADCHAR);
 default:
 return (-10);
 }
}





Example 3 Check if there is any invalid character, including prohibited
characters, in the entire string.

#include <sys/types.h>
#include <sys/errno.h>
#include <sys/sunddi.h>

char u8[MAXPATHLEN];
int n;
int errno;
char *prohibited[4] = {
 ".", "..", "\e\e", NULL
};
.
.
.
n = strlen(u8);
len = u8_validate(u8, n, prohibited,
 (U8_VALIDATE_ENTIRE|U8_VALIDATE_CHECK_ADDITIONAL), &errno);
if (len == -1) {
 switch (errno) {
 case EILSEQ:
 case EINVAL:
 return (MYFS4_ERR_INVAL);
 case EBADF:
 return (MYFS4_ERR_BADNAME);
 case ERANGE:
 return (MYFS4_ERR_BADCHAR);
 default:
 return (-10);
 }
}




 ATTRIBUTES
See attributes(5) for descriptions of the following attributes:






ATTRIBUTE TYPE ATTRIBUTE VALUE
Interface Stability Committed



 SEE ALSO
u8_strcmp(3C), u8_textprep_str(3C), u8_validate(3C),
attributes(5), u8_strcmp(9F), u8_textprep_str(9F),
uconv_u16tou32(9F)


The Unicode Standard (http://www.unicode.org)