s3: Fix the charset_pull routine (bug 7531)
[Samba/wip.git] / lib / util / charset / charset.h
blobbd08f7efd9dc3ea5e5dbe7aa0fe1867cfee37509
1 /*
2 Unix SMB/CIFS implementation.
3 charset defines
4 Copyright (C) Andrew Tridgell 2001
5 Copyright (C) Jelmer Vernooij 2002
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.
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.
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/>.
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. */
25 #ifndef __CHARSET_H__
26 #define __CHARSET_H__
28 #include <talloc.h>
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;
33 #define NUM_CHARSETS 7
36 * SMB UCS2 (16-bit unicode) internal type.
37 * smb_ucs2_t is *always* in little endian format.
40 typedef uint16_t smb_ucs2_t;
43 * SMB UCS2 (16-bit unicode) internal type.
44 * smb_ucs2_t is *always* in little endian format.
47 #ifdef WORDS_BIGENDIAN
48 #define UCS2_SHIFT 8
49 #else
50 #define UCS2_SHIFT 0
51 #endif
53 /* turn a 7 bit character into a ucs2 character */
54 #define UCS2_CHAR(c) ((c) << UCS2_SHIFT)
56 /* return an ascii version of a ucs2 character */
57 #define UCS2_TO_CHAR(c) (((c) >> UCS2_SHIFT) & 0xff)
59 /* Copy into a smb_ucs2_t from a possibly unaligned buffer. Return the copied smb_ucs2_t */
60 #define COPY_UCS2_CHAR(dest,src) (((unsigned char *)(dest))[0] = ((unsigned char *)(src))[0],\
61 ((unsigned char *)(dest))[1] = ((unsigned char *)(src))[1], (dest))
66 * for each charset we have a function that pulls from that charset to
67 * a ucs2 buffer, and a function that pushes to a ucs2 buffer
68 * */
70 struct charset_functions {
71 const char *name;
72 size_t (*pull)(void *, const char **inbuf, size_t *inbytesleft,
73 char **outbuf, size_t *outbytesleft);
74 size_t (*push)(void *, const char **inbuf, size_t *inbytesleft,
75 char **outbuf, size_t *outbytesleft);
76 struct charset_functions *prev, *next;
79 /* this type is used for manipulating unicode codepoints */
80 typedef uint32_t codepoint_t;
82 #define INVALID_CODEPOINT ((codepoint_t)-1)
85 * This is auxiliary struct used by source/script/gen-8-bit-gap.sh script
86 * during generation of an encoding table for charset module
87 * */
89 struct charset_gap_table {
90 uint16_t start;
91 uint16_t end;
92 int32_t idx;
96 /* generic iconv conversion structure */
97 typedef struct smb_iconv_s {
98 size_t (*direct)(void *cd, const char **inbuf, size_t *inbytesleft,
99 char **outbuf, size_t *outbytesleft);
100 size_t (*pull)(void *cd, const char **inbuf, size_t *inbytesleft,
101 char **outbuf, size_t *outbytesleft);
102 size_t (*push)(void *cd, const char **inbuf, size_t *inbytesleft,
103 char **outbuf, size_t *outbytesleft);
104 void *cd_direct, *cd_pull, *cd_push;
105 char *from_name, *to_name;
106 } *smb_iconv_t;
108 /* string manipulation flags */
109 #define STR_TERMINATE 1
110 #define STR_UPPER 2
111 #define STR_ASCII 4
112 #define STR_UNICODE 8
113 #define STR_NOALIGN 16
114 #define STR_NO_RANGE_CHECK 32
115 #define STR_LEN8BIT 64
116 #define STR_TERMINATE_ASCII 128 /* only terminate if ascii */
117 #define STR_LEN_NOTERM 256 /* the length field is the unterminated length */
119 struct loadparm_context;
120 struct smb_iconv_convenience;
122 /* replace some string functions with multi-byte
123 versions */
124 #define strlower(s) strlower_m(s)
125 #define strupper(s) strupper_m(s)
127 char *strchr_m(const char *s, char c);
128 size_t strlen_m_term(const char *s);
129 size_t strlen_m_term_null(const char *s);
130 size_t strlen_m(const char *s);
131 char *alpha_strcpy(char *dest, const char *src, const char *other_safe_chars, size_t maxlength);
132 void string_replace_m(char *s, char oldc, char newc);
133 bool strcsequal_m(const char *s1,const char *s2);
134 bool strequal_m(const char *s1, const char *s2);
135 int strncasecmp_m(const char *s1, const char *s2, size_t n);
136 bool next_token(const char **ptr,char *buff, const char *sep, size_t bufsize);
137 int strcasecmp_m(const char *s1, const char *s2);
138 size_t count_chars_m(const char *s, char c);
139 void strupper_m(char *s);
140 void strlower_m(char *s);
141 char *strupper_talloc(TALLOC_CTX *ctx, const char *src);
142 char *talloc_strdup_upper(TALLOC_CTX *ctx, const char *src);
143 char *strupper_talloc_n(TALLOC_CTX *ctx, const char *src, size_t n);
144 char *strlower_talloc(TALLOC_CTX *ctx, const char *src);
145 bool strhasupper(const char *string);
146 bool strhaslower(const char *string);
147 char *strrchr_m(const char *s, char c);
148 char *strchr_m(const char *s, char c);
150 bool push_ascii_talloc(TALLOC_CTX *ctx, char **dest, const char *src, size_t *converted_size);
151 bool push_ucs2_talloc(TALLOC_CTX *ctx, smb_ucs2_t **dest, const char *src, size_t *converted_size);
152 bool push_utf8_talloc(TALLOC_CTX *ctx, char **dest, const char *src, size_t *converted_size);
153 bool pull_ascii_talloc(TALLOC_CTX *ctx, char **dest, const char *src, size_t *converted_size);
154 bool pull_ucs2_talloc(TALLOC_CTX *ctx, char **dest, const smb_ucs2_t *src, size_t *converted_size);
155 bool pull_utf8_talloc(TALLOC_CTX *ctx, char **dest, const char *src, size_t *converted_size);
156 ssize_t push_string(void *dest, const char *src, size_t dest_len, int flags);
157 ssize_t pull_string(char *dest, const void *src, size_t dest_len, size_t src_len, int flags);
159 bool convert_string_talloc(TALLOC_CTX *ctx,
160 charset_t from, charset_t to,
161 void const *src, size_t srclen,
162 void *dest, size_t *converted_size,
163 bool allow_badcharcnv);
165 size_t convert_string(charset_t from, charset_t to,
166 void const *src, size_t srclen,
167 void *dest, size_t destlen, bool allow_badcharcnv);
169 ssize_t iconv_talloc(TALLOC_CTX *mem_ctx,
170 smb_iconv_t cd,
171 void const *src, size_t srclen,
172 void *dest);
174 extern struct smb_iconv_convenience *global_iconv_convenience;
176 codepoint_t next_codepoint(const char *str, size_t *size);
177 ssize_t push_codepoint(char *str, codepoint_t c);
179 /* codepoints */
180 codepoint_t next_codepoint_convenience(struct smb_iconv_convenience *ic,
181 const char *str, size_t *size);
182 ssize_t push_codepoint_convenience(struct smb_iconv_convenience *ic,
183 char *str, codepoint_t c);
184 codepoint_t toupper_m(codepoint_t val);
185 codepoint_t tolower_m(codepoint_t val);
186 int codepoint_cmpi(codepoint_t c1, codepoint_t c2);
188 /* Iconv convenience functions */
189 struct smb_iconv_convenience *smb_iconv_convenience_reinit(TALLOC_CTX *mem_ctx,
190 const char *dos_charset,
191 const char *unix_charset,
192 bool native_iconv,
193 struct smb_iconv_convenience *old_ic);
195 bool convert_string_convenience(struct smb_iconv_convenience *ic,
196 charset_t from, charset_t to,
197 void const *src, size_t srclen,
198 void *dest, size_t destlen, size_t *converted_size,
199 bool allow_badcharcnv);
200 bool convert_string_talloc_convenience(TALLOC_CTX *ctx,
201 struct smb_iconv_convenience *ic,
202 charset_t from, charset_t to,
203 void const *src, size_t srclen,
204 void *dest, size_t *converted_size, bool allow_badcharcnv);
205 /* iconv */
206 smb_iconv_t smb_iconv_open(const char *tocode, const char *fromcode);
207 int smb_iconv_close(smb_iconv_t cd);
208 size_t smb_iconv(smb_iconv_t cd,
209 const char **inbuf, size_t *inbytesleft,
210 char **outbuf, size_t *outbytesleft);
211 smb_iconv_t smb_iconv_open_ex(TALLOC_CTX *mem_ctx, const char *tocode,
212 const char *fromcode, bool native_iconv);
214 void load_case_tables(void);
215 bool charset_register_backend(const void *_funcs);
218 * Define stub for charset module which implements 8-bit encoding with gaps.
219 * Encoding tables for such module should be produced from glibc's CHARMAPs
220 * using script source/script/gen-8bit-gap.sh
221 * CHARSETNAME is CAPITALIZED charset name
223 * */
224 #define SMB_GENERATE_CHARSET_MODULE_8_BIT_GAP(CHARSETNAME) \
225 static size_t CHARSETNAME ## _push(void *cd, const char **inbuf, size_t *inbytesleft, \
226 char **outbuf, size_t *outbytesleft) \
228 while (*inbytesleft >= 2 && *outbytesleft >= 1) { \
229 int i; \
230 int done = 0; \
232 uint16 ch = SVAL(*inbuf,0); \
234 for (i=0; from_idx[i].start != 0xffff; i++) { \
235 if ((from_idx[i].start <= ch) && (from_idx[i].end >= ch)) { \
236 ((unsigned char*)(*outbuf))[0] = from_ucs2[from_idx[i].idx+ch]; \
237 (*inbytesleft) -= 2; \
238 (*outbytesleft) -= 1; \
239 (*inbuf) += 2; \
240 (*outbuf) += 1; \
241 done = 1; \
242 break; \
245 if (!done) { \
246 errno = EINVAL; \
247 return -1; \
252 if (*inbytesleft == 1) { \
253 errno = EINVAL; \
254 return -1; \
257 if (*inbytesleft > 1) { \
258 errno = E2BIG; \
259 return -1; \
262 return 0; \
265 static size_t CHARSETNAME ## _pull(void *cd, const char **inbuf, size_t *inbytesleft, \
266 char **outbuf, size_t *outbytesleft) \
268 while (*inbytesleft >= 1 && *outbytesleft >= 2) { \
269 SSVAL(*outbuf, 0, to_ucs2[((unsigned char*)(*inbuf))[0]]); \
270 (*inbytesleft) -= 1; \
271 (*outbytesleft) -= 2; \
272 (*inbuf) += 1; \
273 (*outbuf) += 2; \
276 if (*inbytesleft > 0) { \
277 errno = E2BIG; \
278 return -1; \
281 return 0; \
284 struct charset_functions CHARSETNAME ## _functions = \
285 {#CHARSETNAME, CHARSETNAME ## _pull, CHARSETNAME ## _push}; \
287 NTSTATUS charset_ ## CHARSETNAME ## _init(void); \
288 NTSTATUS charset_ ## CHARSETNAME ## _init(void) \
290 return smb_register_charset(& CHARSETNAME ## _functions); \
294 #endif /* __CHARSET_H__ */