1 | /*
|
---|
2 | Unix SMB/CIFS implementation.
|
---|
3 | charset defines
|
---|
4 | Copyright (C) Andrew Tridgell 2001
|
---|
5 | Copyright (C) Jelmer Vernooij 2002
|
---|
6 |
|
---|
7 | This program is free software; you can redistribute it and/or modify
|
---|
8 | it under the terms of the GNU General Public License as published by
|
---|
9 | the Free Software Foundation; either version 3 of the License, or
|
---|
10 | (at your option) any later version.
|
---|
11 |
|
---|
12 | This program is distributed in the hope that it will be useful,
|
---|
13 | but WITHOUT ANY WARRANTY; without even the implied warranty of
|
---|
14 | MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
|
---|
15 | GNU General Public License for more details.
|
---|
16 |
|
---|
17 | You should have received a copy of the GNU General Public License
|
---|
18 | along with this program. If not, see <http://www.gnu.org/licenses/>.
|
---|
19 | */
|
---|
20 |
|
---|
21 | /* This is a public header file that is installed as part of Samba.
|
---|
22 | * If you remove any functions or change their signature, update
|
---|
23 | * the so version number. */
|
---|
24 |
|
---|
25 | #ifndef __CHARSET_H__
|
---|
26 | #define __CHARSET_H__
|
---|
27 |
|
---|
28 | #include <talloc.h>
|
---|
29 |
|
---|
30 | /* this defines the charset types used in samba */
|
---|
31 | typedef enum {CH_UTF16LE=0, CH_UTF16=0, CH_UNIX, CH_DISPLAY, CH_DOS, CH_UTF8, CH_UTF16BE, CH_UTF16MUNGED} charset_t;
|
---|
32 |
|
---|
33 | #define NUM_CHARSETS 7
|
---|
34 |
|
---|
35 | /*
|
---|
36 | * SMB UCS2 (16-bit unicode) internal type.
|
---|
37 | * smb_ucs2_t is *always* in little endian format.
|
---|
38 | */
|
---|
39 |
|
---|
40 | typedef uint16_t smb_ucs2_t;
|
---|
41 |
|
---|
42 | #ifdef WORDS_BIGENDIAN
|
---|
43 | #define UCS2_SHIFT 8
|
---|
44 | #else
|
---|
45 | #define UCS2_SHIFT 0
|
---|
46 | #endif
|
---|
47 |
|
---|
48 | /* turn a 7 bit character into a ucs2 character */
|
---|
49 | #define UCS2_CHAR(c) ((c) << UCS2_SHIFT)
|
---|
50 |
|
---|
51 | /* return an ascii version of a ucs2 character */
|
---|
52 | #define UCS2_TO_CHAR(c) (((c) >> UCS2_SHIFT) & 0xff)
|
---|
53 |
|
---|
54 | /* Copy into a smb_ucs2_t from a possibly unaligned buffer. Return the copied smb_ucs2_t */
|
---|
55 | #define COPY_UCS2_CHAR(dest,src) (((unsigned char *)(dest))[0] = ((unsigned char *)(src))[0],\
|
---|
56 | ((unsigned char *)(dest))[1] = ((unsigned char *)(src))[1], (dest))
|
---|
57 |
|
---|
58 |
|
---|
59 |
|
---|
60 | /*
|
---|
61 | * for each charset we have a function that pulls from that charset to
|
---|
62 | * a ucs2 buffer, and a function that pushes to a ucs2 buffer
|
---|
63 | * */
|
---|
64 |
|
---|
65 | struct charset_functions {
|
---|
66 | const char *name;
|
---|
67 | size_t (*pull)(void *, const char **inbuf, size_t *inbytesleft,
|
---|
68 | char **outbuf, size_t *outbytesleft);
|
---|
69 | size_t (*push)(void *, const char **inbuf, size_t *inbytesleft,
|
---|
70 | char **outbuf, size_t *outbytesleft);
|
---|
71 | struct charset_functions *prev, *next;
|
---|
72 | };
|
---|
73 |
|
---|
74 | /* this type is used for manipulating unicode codepoints */
|
---|
75 | typedef uint32_t codepoint_t;
|
---|
76 |
|
---|
77 | #define INVALID_CODEPOINT ((codepoint_t)-1)
|
---|
78 |
|
---|
79 | /*
|
---|
80 | * This is auxiliary struct used by source/script/gen-8-bit-gap.sh script
|
---|
81 | * during generation of an encoding table for charset module
|
---|
82 | * */
|
---|
83 |
|
---|
84 | struct charset_gap_table {
|
---|
85 | uint16_t start;
|
---|
86 | uint16_t end;
|
---|
87 | int32_t idx;
|
---|
88 | };
|
---|
89 |
|
---|
90 |
|
---|
91 | /* generic iconv conversion structure */
|
---|
92 | typedef struct smb_iconv_s {
|
---|
93 | size_t (*direct)(void *cd, const char **inbuf, size_t *inbytesleft,
|
---|
94 | char **outbuf, size_t *outbytesleft);
|
---|
95 | size_t (*pull)(void *cd, const char **inbuf, size_t *inbytesleft,
|
---|
96 | char **outbuf, size_t *outbytesleft);
|
---|
97 | size_t (*push)(void *cd, const char **inbuf, size_t *inbytesleft,
|
---|
98 | char **outbuf, size_t *outbytesleft);
|
---|
99 | void *cd_direct, *cd_pull, *cd_push;
|
---|
100 | char *from_name, *to_name;
|
---|
101 | } *smb_iconv_t;
|
---|
102 |
|
---|
103 | /* string manipulation flags */
|
---|
104 | #define STR_TERMINATE 1
|
---|
105 | #define STR_UPPER 2
|
---|
106 | #define STR_ASCII 4
|
---|
107 | #define STR_UNICODE 8
|
---|
108 | #define STR_NOALIGN 16
|
---|
109 | #define STR_NO_RANGE_CHECK 32
|
---|
110 | #define STR_LEN8BIT 64
|
---|
111 | #define STR_TERMINATE_ASCII 128 /* only terminate if ascii */
|
---|
112 | #define STR_LEN_NOTERM 256 /* the length field is the unterminated length */
|
---|
113 |
|
---|
114 | struct loadparm_context;
|
---|
115 | struct smb_iconv_convenience;
|
---|
116 |
|
---|
117 | /* replace some string functions with multi-byte
|
---|
118 | versions */
|
---|
119 | #define strlower(s) strlower_m(s)
|
---|
120 | #define strupper(s) strupper_m(s)
|
---|
121 |
|
---|
122 | char *strchr_m(const char *s, char c);
|
---|
123 | size_t strlen_m_ext(const char *s, charset_t src_charset, charset_t dst_charset);
|
---|
124 | size_t strlen_m_ext_term(const char *s, charset_t src_charset,
|
---|
125 | charset_t dst_charset);
|
---|
126 | size_t strlen_m_term(const char *s);
|
---|
127 | size_t strlen_m_term_null(const char *s);
|
---|
128 | size_t strlen_m(const char *s);
|
---|
129 | char *alpha_strcpy(char *dest, const char *src, const char *other_safe_chars, size_t maxlength);
|
---|
130 | void string_replace_m(char *s, char oldc, char newc);
|
---|
131 | bool strcsequal_m(const char *s1,const char *s2);
|
---|
132 | bool strequal_m(const char *s1, const char *s2);
|
---|
133 | int strncasecmp_m(const char *s1, const char *s2, size_t n);
|
---|
134 | bool next_token(const char **ptr,char *buff, const char *sep, size_t bufsize);
|
---|
135 | int strcasecmp_m(const char *s1, const char *s2);
|
---|
136 | size_t count_chars_m(const char *s, char c);
|
---|
137 | void strupper_m(char *s);
|
---|
138 | void strlower_m(char *s);
|
---|
139 | char *strupper_talloc(TALLOC_CTX *ctx, const char *src);
|
---|
140 | char *talloc_strdup_upper(TALLOC_CTX *ctx, const char *src);
|
---|
141 | char *strupper_talloc_n(TALLOC_CTX *ctx, const char *src, size_t n);
|
---|
142 | char *strlower_talloc(TALLOC_CTX *ctx, const char *src);
|
---|
143 | bool strhasupper(const char *string);
|
---|
144 | bool strhaslower(const char *string);
|
---|
145 | char *strrchr_m(const char *s, char c);
|
---|
146 | char *strchr_m(const char *s, char c);
|
---|
147 |
|
---|
148 | bool push_ascii_talloc(TALLOC_CTX *ctx, char **dest, const char *src, size_t *converted_size);
|
---|
149 | bool push_ucs2_talloc(TALLOC_CTX *ctx, smb_ucs2_t **dest, const char *src, size_t *converted_size);
|
---|
150 | bool push_utf8_talloc(TALLOC_CTX *ctx, char **dest, const char *src, size_t *converted_size);
|
---|
151 | bool pull_ascii_talloc(TALLOC_CTX *ctx, char **dest, const char *src, size_t *converted_size);
|
---|
152 | bool pull_ucs2_talloc(TALLOC_CTX *ctx, char **dest, const smb_ucs2_t *src, size_t *converted_size);
|
---|
153 | bool pull_utf8_talloc(TALLOC_CTX *ctx, char **dest, const char *src, size_t *converted_size);
|
---|
154 | ssize_t push_string(void *dest, const char *src, size_t dest_len, int flags);
|
---|
155 | ssize_t pull_string(char *dest, const void *src, size_t dest_len, size_t src_len, int flags);
|
---|
156 |
|
---|
157 | bool convert_string_talloc(TALLOC_CTX *ctx,
|
---|
158 | charset_t from, charset_t to,
|
---|
159 | void const *src, size_t srclen,
|
---|
160 | void *dest, size_t *converted_size,
|
---|
161 | bool allow_badcharcnv);
|
---|
162 |
|
---|
163 | size_t convert_string(charset_t from, charset_t to,
|
---|
164 | void const *src, size_t srclen,
|
---|
165 | void *dest, size_t destlen, bool allow_badcharcnv);
|
---|
166 |
|
---|
167 | ssize_t iconv_talloc(TALLOC_CTX *mem_ctx,
|
---|
168 | smb_iconv_t cd,
|
---|
169 | void const *src, size_t srclen,
|
---|
170 | void *dest);
|
---|
171 |
|
---|
172 | extern struct smb_iconv_convenience *global_iconv_convenience;
|
---|
173 | struct smb_iconv_convenience *get_iconv_convenience(void);
|
---|
174 | smb_iconv_t get_conv_handle(struct smb_iconv_convenience *ic,
|
---|
175 | charset_t from, charset_t to);
|
---|
176 | const char *charset_name(struct smb_iconv_convenience *ic, charset_t ch);
|
---|
177 |
|
---|
178 | codepoint_t next_codepoint_ext(const char *str, charset_t src_charset,
|
---|
179 | size_t *size);
|
---|
180 | codepoint_t next_codepoint(const char *str, size_t *size);
|
---|
181 | ssize_t push_codepoint(char *str, codepoint_t c);
|
---|
182 |
|
---|
183 | /* codepoints */
|
---|
184 | codepoint_t next_codepoint_convenience_ext(struct smb_iconv_convenience *ic,
|
---|
185 | const char *str, charset_t src_charset,
|
---|
186 | size_t *size);
|
---|
187 | codepoint_t next_codepoint_convenience(struct smb_iconv_convenience *ic,
|
---|
188 | const char *str, size_t *size);
|
---|
189 | ssize_t push_codepoint_convenience(struct smb_iconv_convenience *ic,
|
---|
190 | char *str, codepoint_t c);
|
---|
191 |
|
---|
192 | codepoint_t toupper_m(codepoint_t val);
|
---|
193 | codepoint_t tolower_m(codepoint_t val);
|
---|
194 | bool islower_m(codepoint_t val);
|
---|
195 | bool isupper_m(codepoint_t val);
|
---|
196 | int codepoint_cmpi(codepoint_t c1, codepoint_t c2);
|
---|
197 |
|
---|
198 | /* Iconv convenience functions */
|
---|
199 | struct smb_iconv_convenience *smb_iconv_convenience_reinit(TALLOC_CTX *mem_ctx,
|
---|
200 | const char *dos_charset,
|
---|
201 | const char *unix_charset,
|
---|
202 | const char *display_charset,
|
---|
203 | bool native_iconv,
|
---|
204 | struct smb_iconv_convenience *old_ic);
|
---|
205 |
|
---|
206 | bool convert_string_convenience(struct smb_iconv_convenience *ic,
|
---|
207 | charset_t from, charset_t to,
|
---|
208 | void const *src, size_t srclen,
|
---|
209 | void *dest, size_t destlen, size_t *converted_size,
|
---|
210 | bool allow_badcharcnv);
|
---|
211 | bool convert_string_talloc_convenience(TALLOC_CTX *ctx,
|
---|
212 | struct smb_iconv_convenience *ic,
|
---|
213 | charset_t from, charset_t to,
|
---|
214 | void const *src, size_t srclen,
|
---|
215 | void *dest, size_t *converted_size, bool allow_badcharcnv);
|
---|
216 | /* iconv */
|
---|
217 | smb_iconv_t smb_iconv_open(const char *tocode, const char *fromcode);
|
---|
218 | int smb_iconv_close(smb_iconv_t cd);
|
---|
219 | size_t smb_iconv(smb_iconv_t cd,
|
---|
220 | const char **inbuf, size_t *inbytesleft,
|
---|
221 | char **outbuf, size_t *outbytesleft);
|
---|
222 | smb_iconv_t smb_iconv_open_ex(TALLOC_CTX *mem_ctx, const char *tocode,
|
---|
223 | const char *fromcode, bool native_iconv);
|
---|
224 |
|
---|
225 | void load_case_tables(void);
|
---|
226 | void load_case_tables_library(void);
|
---|
227 | bool smb_register_charset(const struct charset_functions *funcs_in);
|
---|
228 |
|
---|
229 | /*
|
---|
230 | * Define stub for charset module which implements 8-bit encoding with gaps.
|
---|
231 | * Encoding tables for such module should be produced from glibc's CHARMAPs
|
---|
232 | * using script source/script/gen-8bit-gap.sh
|
---|
233 | * CHARSETNAME is CAPITALIZED charset name
|
---|
234 | *
|
---|
235 | * */
|
---|
236 | #define SMB_GENERATE_CHARSET_MODULE_8_BIT_GAP(CHARSETNAME) \
|
---|
237 | static size_t CHARSETNAME ## _push(void *cd, const char **inbuf, size_t *inbytesleft, \
|
---|
238 | char **outbuf, size_t *outbytesleft) \
|
---|
239 | { \
|
---|
240 | while (*inbytesleft >= 2 && *outbytesleft >= 1) { \
|
---|
241 | int i; \
|
---|
242 | int done = 0; \
|
---|
243 | \
|
---|
244 | uint16 ch = SVAL(*inbuf,0); \
|
---|
245 | \
|
---|
246 | for (i=0; from_idx[i].start != 0xffff; i++) { \
|
---|
247 | if ((from_idx[i].start <= ch) && (from_idx[i].end >= ch)) { \
|
---|
248 | ((unsigned char*)(*outbuf))[0] = from_ucs2[from_idx[i].idx+ch]; \
|
---|
249 | (*inbytesleft) -= 2; \
|
---|
250 | (*outbytesleft) -= 1; \
|
---|
251 | (*inbuf) += 2; \
|
---|
252 | (*outbuf) += 1; \
|
---|
253 | done = 1; \
|
---|
254 | break; \
|
---|
255 | } \
|
---|
256 | } \
|
---|
257 | if (!done) { \
|
---|
258 | errno = EINVAL; \
|
---|
259 | return -1; \
|
---|
260 | } \
|
---|
261 | \
|
---|
262 | } \
|
---|
263 | \
|
---|
264 | if (*inbytesleft == 1) { \
|
---|
265 | errno = EINVAL; \
|
---|
266 | return -1; \
|
---|
267 | } \
|
---|
268 | \
|
---|
269 | if (*inbytesleft > 1) { \
|
---|
270 | errno = E2BIG; \
|
---|
271 | return -1; \
|
---|
272 | } \
|
---|
273 | \
|
---|
274 | return 0; \
|
---|
275 | } \
|
---|
276 | \
|
---|
277 | static size_t CHARSETNAME ## _pull(void *cd, const char **inbuf, size_t *inbytesleft, \
|
---|
278 | char **outbuf, size_t *outbytesleft) \
|
---|
279 | { \
|
---|
280 | while (*inbytesleft >= 1 && *outbytesleft >= 2) { \
|
---|
281 | SSVAL(*outbuf, 0, to_ucs2[((unsigned char*)(*inbuf))[0]]); \
|
---|
282 | (*inbytesleft) -= 1; \
|
---|
283 | (*outbytesleft) -= 2; \
|
---|
284 | (*inbuf) += 1; \
|
---|
285 | (*outbuf) += 2; \
|
---|
286 | } \
|
---|
287 | \
|
---|
288 | if (*inbytesleft > 0) { \
|
---|
289 | errno = E2BIG; \
|
---|
290 | return -1; \
|
---|
291 | } \
|
---|
292 | \
|
---|
293 | return 0; \
|
---|
294 | } \
|
---|
295 | \
|
---|
296 | struct charset_functions CHARSETNAME ## _functions = \
|
---|
297 | {#CHARSETNAME, CHARSETNAME ## _pull, CHARSETNAME ## _push}; \
|
---|
298 | \
|
---|
299 | NTSTATUS charset_ ## CHARSETNAME ## _init(void); \
|
---|
300 | NTSTATUS charset_ ## CHARSETNAME ## _init(void) \
|
---|
301 | { \
|
---|
302 | if (!smb_register_charset(& CHARSETNAME ## _functions)) { \
|
---|
303 | return NT_STATUS_INTERNAL_ERROR; \
|
---|
304 | } \
|
---|
305 | return NT_STATUS_OK; \
|
---|
306 | } \
|
---|
307 |
|
---|
308 |
|
---|
309 | #endif /* __CHARSET_H__ */
|
---|