2 #ifndef _ATALK_UNICODE_H
3 #define _ATALK_UNICODE_H 1
6 #include <netatalk/endian.h>
10 #define ucs2_t u_int16_t
13 #define MIN(a,b) ((a)<(b)?(a):(b))
17 #define MAX(a,b) ((a)>(b)?(a):(b))
20 #define SAFE_FREE(x) do { if ((x) != NULL) {free(x); x=NULL;} } while(0)
23 #define EILSEQ 84 /* Illegal byte sequence. */
26 /* generic iconv conversion structure */
28 size_t (*direct)(void *cd, char **inbuf, size_t *inbytesleft,
29 char **outbuf, size_t *outbytesleft);
30 size_t (*pull)(void *cd, char **inbuf, size_t *inbytesleft,
31 char **outbuf, size_t *outbytesleft);
32 size_t (*push)(void *cd, char **inbuf, size_t *inbytesleft,
33 char **outbuf, size_t *outbytesleft);
34 void *cd_direct, *cd_pull, *cd_push;
35 char *from_name, *to_name;
38 #define CHARSET_CLIENT 1
39 #define CHARSET_VOLUME 2
40 #define CHARSET_PRECOMPOSED 4
41 #define CHARSET_DECOMPOSED 8
42 #define CHARSET_MULTIBYTE 16
43 #define CHARSET_WIDECHAR 32
44 #define CHARSET_ICONV 64
46 #define IGNORE_CHAR '_'
48 /* conversion flags */
49 #define CONV_IGNORE (1<<0) /* return the first convertable characters. */
50 #define CONV_ESCAPEHEX (1<<1) /* escape unconvertable chars with :[UCS2HEX] */
51 #define CONV_ESCAPEDOTS (1<<2) /* escape leading dots with :2600 */
52 #define CONV_UNESCAPEHEX (1<<3)
53 #define CONV_TOUPPER (1<<4) /* convert to UPPERcase */
54 #define CONV_TOLOWER (1<<5) /* convert to lowercase */
55 #define CONV_PRECOMPOSE (1<<6) /* precompose */
56 #define CONV_DECOMPOSE (1<<7) /* precompose */
57 #define CONV_FORCE (1<<8) /* force convertion */
58 #define CONV__EILSEQ (1<<9) /* ignore EILSEQ, replace with IGNORE_CHAR (try USC2) */
60 /* conversion return flags */
61 #define CONV_REQMANGLE (1<<14) /* mangling of returned name is required */
62 #define CONV_REQESCAPE (1<<15) /* espace unconvertable chars with :[UCS2HEX] */
64 /* this defines the charset types used in samba */
65 typedef enum {CH_UCS2=0, CH_UTF8=1, CH_MAC=2, CH_UNIX=3, CH_UTF8_MAC=4} charset_t;
67 #define NUM_CHARSETS 5
70 * for each charset we have a function that pulls from that charset to
71 * a ucs2 buffer, and a function that pushes to a ucs2 buffer
74 struct charset_functions {
76 const long kTextEncoding;
77 size_t (*pull)(void *, char **inbuf, size_t *inbytesleft,
78 char **outbuf, size_t *outbytesleft);
79 size_t (*push)(void *, char **inbuf, size_t *inbytesleft,
80 char **outbuf, size_t *outbytesleft);
83 struct charset_functions *prev, *next;
87 extern atalk_iconv_t atalk_iconv_open (const char *, const char *);
88 extern size_t atalk_iconv (atalk_iconv_t, const char **, size_t *, char **, size_t *);
89 extern int atalk_iconv_close (atalk_iconv_t);
90 extern struct charset_functions *find_charset_functions (const char *);
91 extern int atalk_register_charset (struct charset_functions *);
93 /* from util_unistr.c */
94 extern ucs2_t toupper_w (ucs2_t);
95 extern ucs2_t tolower_w (ucs2_t);
96 extern int strupper_w (ucs2_t *);
97 extern int strlower_w (ucs2_t *);
98 extern int islower_w (ucs2_t);
99 extern int isupper_w (ucs2_t);
100 extern size_t strlen_w (const ucs2_t *);
101 extern size_t strnlen_w (const ucs2_t *, size_t);
102 extern ucs2_t* strchr_w (const ucs2_t *, ucs2_t);
103 extern ucs2_t *strcasechr_w (const ucs2_t *s, ucs2_t c);
104 extern int strcmp_w (const ucs2_t *, const ucs2_t *);
105 extern int strncmp_w (const ucs2_t *, const ucs2_t *, size_t);
106 extern int strcasecmp_w (const ucs2_t *, const ucs2_t *);
107 extern int strncasecmp_w (const ucs2_t *, const ucs2_t *, size_t);
108 extern ucs2_t *strstr_w (const ucs2_t *s, const ucs2_t *ins);
109 extern ucs2_t *strcasestr_w (const ucs2_t *, const ucs2_t *);
110 extern ucs2_t *strndup_w (const ucs2_t *, size_t);
111 extern ucs2_t *strdup_w (const ucs2_t *);
112 extern ucs2_t *strncpy_w (ucs2_t *, const ucs2_t *, const size_t);
113 extern ucs2_t *strncat_w (ucs2_t *, const ucs2_t *, const size_t);
114 extern ucs2_t *strcat_w (ucs2_t *, const ucs2_t *);
115 extern size_t precompose_w (ucs2_t *, size_t, ucs2_t *,size_t *);
116 extern size_t decompose_w (ucs2_t *, size_t, ucs2_t *,size_t *);
117 extern size_t utf8_charlen ( char* );
118 extern size_t utf8_strlen_validate ( char *);
121 extern void init_iconv (void);
122 extern size_t convert_string (charset_t, charset_t, void const *, size_t, void *, size_t);
123 extern size_t convert_string_allocate (charset_t, charset_t, void const *, size_t, char **);
124 extern size_t utf8_strupper (const char *, size_t, char *, size_t);
125 extern size_t utf8_strlower (const char *, size_t, char *, size_t);
126 extern size_t unix_strupper (const char *, size_t, char *, size_t);
127 extern size_t unix_strlower (const char *, size_t, char *, size_t);
128 extern size_t charset_strupper (charset_t, const char *, size_t, char *, size_t);
129 extern size_t charset_strlower (charset_t, const char *, size_t, char *, size_t);
131 extern size_t charset_to_ucs2_allocate (charset_t, ucs2_t **dest, const char *src);
132 extern size_t charset_to_utf8_allocate (charset_t, char **dest, const char *src);
133 extern size_t ucs2_to_charset_allocate (charset_t, char **dest, const ucs2_t *src);
134 extern size_t utf8_to_charset_allocate (charset_t, char **dest, const char *src);
135 extern size_t ucs2_to_charset (charset_t, const ucs2_t *src, char *dest, size_t);
137 extern size_t convert_charset (charset_t, charset_t, charset_t, const char *, size_t, char *, size_t, u_int16_t *);
139 extern size_t charset_precompose ( charset_t, char *, size_t, char *, size_t);
140 extern size_t charset_decompose ( charset_t, char *, size_t, char *, size_t);
141 extern size_t utf8_precompose ( char *, size_t, char *, size_t);
142 extern size_t utf8_decompose ( char *, size_t, char *, size_t);
144 extern charset_t add_charset (char* name);