versadac  1
versadac - Scalable Recorder Firmware
ldap_pvt_uc.h
1 /* $OpenLDAP: pkg/ldap/include/ldap_pvt_uc.h,v 1.31.2.3 2008/02/11 23:26:40 kurt Exp $ */
2 /* This work is part of OpenLDAP Software <http://www.openldap.org/>.
3  *
4  * Copyright 1998-2008 The OpenLDAP Foundation.
5  * All rights reserved.
6  *
7  * Redistribution and use in source and binary forms, with or without
8  * modification, are permitted only as authorized by the OpenLDAP
9  * Public License.
10  *
11  * A copy of this license is available in file LICENSE in the
12  * top-level directory of the distribution or, alternatively, at
13  * <http://www.OpenLDAP.org/license.html>.
14  */
15 
16 /*
17  * ldap_pvt_uc.h - Header for Unicode functions.
18  * These are meant to be used by the OpenLDAP distribution only.
19  * These should be named ldap_pvt_....()
20  */
21 
22 #ifndef _LDAP_PVT_UC_H
23 #define _LDAP_PVT_UC_H 1
24 
25 #include <lber.h> /* get ber_slen_t */
26 
27 #include <ac/bytes.h>
28 #ifdef VXWORKS_BUILD
29 #include "liblunicode/ucdata/ucdata.h"
30 #else
31 #include "../libraries/liblunicode/ucdata/ucdata.h"
32 #endif
33 
34 LDAP_BEGIN_DECL
35 
36 /*
37  * UTF-8 (in utf-8.c)
38  */
39 
40 /* UCDATA uses UCS-2 passed in a 4 byte unsigned int */
41 typedef ac_uint4 ldap_unicode_t;
42 
43 /* Convert a string with csize octets per character to UTF-8 */
44 LDAP_F( int ) ldap_ucs_to_utf8s LDAP_P((
45  struct berval *ucs, int csize, struct berval *utf8s ));
46 
47 
48 /* returns the number of bytes in the UTF-8 string */
49 LDAP_F (ber_len_t) ldap_utf8_bytes( const char * );
50 /* returns the number of UTF-8 characters in the string */
51 LDAP_F (ber_len_t) ldap_utf8_chars( const char * );
52 /* returns the length (in bytes) of the UTF-8 character */
53 LDAP_F (int) ldap_utf8_offset( const char * );
54 /* returns the length (in bytes) indicated by the UTF-8 character */
55 LDAP_F (int) ldap_utf8_charlen( const char * );
56 
57 /* returns the length (in bytes) indicated by the UTF-8 character
58  * also checks that shortest possible encoding was used
59  */
60 LDAP_F (int) ldap_utf8_charlen2( const char * );
61 
62 /* copies a UTF-8 character and returning number of bytes copied */
63 LDAP_F (int) ldap_utf8_copy( char *, const char *);
64 
65 /* returns pointer of next UTF-8 character in string */
66 LDAP_F (char*) ldap_utf8_next( const char * );
67 /* returns pointer of previous UTF-8 character in string */
68 LDAP_F (char*) ldap_utf8_prev( const char * );
69 
70 /* primitive ctype routines -- not aware of non-ascii characters */
71 LDAP_F (int) ldap_utf8_isascii( const char * );
72 LDAP_F (int) ldap_utf8_isalpha( const char * );
73 LDAP_F (int) ldap_utf8_isalnum( const char * );
74 LDAP_F (int) ldap_utf8_isdigit( const char * );
75 LDAP_F (int) ldap_utf8_isxdigit( const char * );
76 LDAP_F (int) ldap_utf8_isspace( const char * );
77 
78 /* span characters not in set, return bytes spanned */
79 LDAP_F (ber_len_t) ldap_utf8_strcspn( const char* str, const char *set);
80 /* span characters in set, return bytes spanned */
81 LDAP_F (ber_len_t) ldap_utf8_strspn( const char* str, const char *set);
82 /* return first occurance of character in string */
83 LDAP_F (char *) ldap_utf8_strchr( const char* str, const char *chr);
84 /* return first character of set in string */
85 LDAP_F (char *) ldap_utf8_strpbrk( const char* str, const char *set);
86 /* reentrant tokenizer */
87 LDAP_F (char*) ldap_utf8_strtok( char* sp, const char* sep, char **last);
88 
89 /* Optimizations */
90 LDAP_V (const char) ldap_utf8_lentab[128];
91 LDAP_V (const char) ldap_utf8_mintab[32];
92 
93 #define LDAP_UTF8_ISASCII(p) ( !(*(const unsigned char *)(p) & 0x80 ) )
94 #define LDAP_UTF8_CHARLEN(p) ( LDAP_UTF8_ISASCII(p) \
95  ? 1 : ldap_utf8_lentab[*(const unsigned char *)(p) ^ 0x80] )
96 
97 /* This is like CHARLEN but additionally validates to make sure
98  * the char used the shortest possible encoding.
99  * 'l' is used to temporarily hold the result of CHARLEN.
100  */
101 #define LDAP_UTF8_CHARLEN2(p, l) ( ( ( l = LDAP_UTF8_CHARLEN( p )) < 3 || \
102  ( ldap_utf8_mintab[*(const unsigned char *)(p) & 0x1f] & (p)[1] ) ) ? \
103  l : 0 )
104 
105 #define LDAP_UTF8_OFFSET(p) ( LDAP_UTF8_ISASCII(p) \
106  ? 1 : ldap_utf8_offset((p)) )
107 
108 #define LDAP_UTF8_COPY(d,s) ( LDAP_UTF8_ISASCII(s) \
109  ? (*(d) = *(s), 1) : ldap_utf8_copy((d),(s)) )
110 
111 #define LDAP_UTF8_NEXT(p) ( LDAP_UTF8_ISASCII(p) \
112  ? (char *)(p)+1 : ldap_utf8_next((p)) )
113 
114 #define LDAP_UTF8_INCR(p) ((p) = LDAP_UTF8_NEXT(p))
115 
116 /* For symmetry */
117 #define LDAP_UTF8_PREV(p) (ldap_utf8_prev((p)))
118 #define LDAP_UTF8_DECR(p) ((p)=LDAP_UTF8_PREV((p)))
119 
120 
121 /* these probably should be renamed */
122 LDAP_LUNICODE_F(int) ucstrncmp(
123  const ldap_unicode_t *,
124  const ldap_unicode_t *,
125  ber_len_t );
126 
127 LDAP_LUNICODE_F(int) ucstrncasecmp(
128  const ldap_unicode_t *,
129  const ldap_unicode_t *,
130  ber_len_t );
131 
132 LDAP_LUNICODE_F(ldap_unicode_t *) ucstrnchr(
133  const ldap_unicode_t *,
134  ber_len_t,
135  ldap_unicode_t );
136 
137 LDAP_LUNICODE_F(ldap_unicode_t *) ucstrncasechr(
138  const ldap_unicode_t *,
139  ber_len_t,
140  ldap_unicode_t );
141 
142 LDAP_LUNICODE_F(void) ucstr2upper(
143  ldap_unicode_t *,
144  ber_len_t );
145 
146 #define LDAP_UTF8_NOCASEFOLD 0x0U
147 #define LDAP_UTF8_CASEFOLD 0x1U
148 #define LDAP_UTF8_ARG1NFC 0x2U
149 #define LDAP_UTF8_ARG2NFC 0x4U
150 #define LDAP_UTF8_APPROX 0x8U
151 
152 LDAP_LUNICODE_F(struct berval *) UTF8bvnormalize(
153  struct berval *,
154  struct berval *,
155  unsigned,
156  void *memctx );
157 
158 LDAP_LUNICODE_F(int) UTF8bvnormcmp(
159  struct berval *,
160  struct berval *,
161  unsigned,
162  void *memctx );
163 
164 LDAP_END_DECL
165 
166 #endif
167 
Definition: lber.h:212