1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315
|
/*
Unix SMB/Netbios implementation.
Version 2.0.x.
Create unicode map files from unicode_def.XXX files.
Copyright (C) Jeremy Allison 1997-1999.
This program is free software; you can redistribute it and/or modify
it under the terms of the GNU General Public License as published by
the Free Software Foundation; either version 2 of the License, or
(at your option) any later version.
This program is distributed in the hope that it will be useful,
but WITHOUT ANY WARRANTY; without even the implied warranty of
MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
GNU General Public License for more details.
You should have received a copy of the GNU General Public License
along with this program; if not, write to the Free Software
Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA.
*/
#include "includes.h"
#undef strchr
static char *prog_name = NULL;
/*
* Print program usage and die.
*/
static void unicode_map_usage(char *progname)
{
fprintf(stderr, "Usage is : %s <codepage> <inputfile> <outputfile>\n",
progname);
exit(1);
}
/*
* Read a line from a buffer into a line buffer. Ensure null
* terminated.
*/
static void read_line( char **buf, char *line_buf, size_t size)
{
char *p = *buf;
size_t num = 0;
for(; *p && (*p != '\n') && (*p != '\032'); p++) {
if(num < (size - 1))
line_buf[num++] = *p;
}
if(*p)
p++; /* Go past the '\n' */
line_buf[num] = '\0';
*buf = p;
}
/*
* Strip comment lines and blank lines from the data.
* Copies into a new buffer and frees the old.
* Returns the number of lines copied.
*/
static size_t clean_data( char **buf, size_t *size)
{
pstring linebuf;
char *p = *buf;
size_t num_lines = 0;
char *newbuf = (char *)malloc( *size + 1);
char *newbuf_p = NULL;
if(newbuf == NULL) {
fprintf(stderr, "%s: malloc fail for size %u.\n", prog_name, (unsigned int)(*size + 1));
exit(1);
}
newbuf_p = newbuf;
*newbuf_p = '\0';
while( *p ) {
char *cp;
read_line( &p, linebuf, sizeof(linebuf));
/* Null terminate after comment. */
if((cp = strchr( linebuf, '#'))!= NULL)
*cp = '\0';
for(cp = linebuf;*cp && isspace(*cp); cp++)
;
if(*cp == '\0')
continue;
safe_strcpy(newbuf_p, cp, *size - (newbuf_p - newbuf));
num_lines++;
newbuf_p += (strlen(newbuf_p) + 1);
}
SAFE_FREE(*buf);
*buf = newbuf;
return num_lines;
}
/*
* Parse a uint16 from a codepage file.
*/
static BOOL parse_uint16(char *buf, uint16 *uip)
{
unsigned int ui;
char *endptr = NULL;
ui = (unsigned int)strtol(buf, &endptr, 0);
if(endptr == buf || ui > 65535)
return False;
*uip = (uint16)ui;
return True;
}
/*
* Print a parse error and exit.
*/
static void parse_error(const char *buf, const char *input_file, const char *msg)
{
fprintf(stderr, "%s: In file %s : %s whilst parsing line \n%s\n", prog_name,
input_file, msg, buf);
exit(1);
}
/*
* Create a compiled unicode map file from a unicode map definition file.
*/
static int do_compile(const char *codepage, const char *input_file, const char *output_file)
{
FILE *fp = NULL;
size_t size = 0;
size_t offset = 0;
char *buf = NULL;
char *orig_buf = NULL;
char *output_buf = NULL;
uint16 cp_to_ucs2[65536];
uint16 ucs2_to_cp[65536];
BOOL multibyte_code_page = False;
int num_lines = 0;
int i = 0;
SMB_STRUCT_STAT st;
/* Get the size of the input file. Read the entire thing into memory. */
if(sys_stat(input_file, &st)!= 0) {
fprintf(stderr, "%s: failed to get the file size for file %s. Error was %s\n",
prog_name, input_file, strerror(errno));
exit(1);
}
size = (size_t)st.st_size;
if((fp = sys_fopen(input_file, "r")) == NULL) {
fprintf(stderr, "%s: cannot open file %s for input.\n", prog_name, input_file);
exit(1);
}
/* As we will be reading text, allocate one more byte for a '\0' */
if((buf = (char *)malloc( size + 1 )) == NULL) {
fprintf(stderr, "%s: malloc fail for size %d.\n", prog_name, size + 1);
fclose(fp);
exit(1);
}
if(fread( buf, 1, size, fp) != size) {
fprintf(stderr, "%s: read failed for file %s. Error was %s.\n", prog_name,
input_file, strerror(errno));
SAFE_FREE(buf);
fclose(fp);
exit(1);
}
/* Null terminate the text read. */
buf[size] = '\0';
/* Go through the data line by line, strip out comments (anything
after a '#' to end-of-line) and blank lines. The rest should be
the codepage data.
*/
num_lines = clean_data( &buf, &size);
orig_buf = buf; /* Store for free(). */
/*
* Initialize the output data.
*/
memset(cp_to_ucs2, '\0', sizeof(cp_to_ucs2));
ucs2_to_cp[0] = 0;
for (i = 1; i < 65536; i++)
ucs2_to_cp[i] = (uint16)'_';
/* Now convert the lines into the compiled form. */
for(i = 0; i < num_lines; i++) {
char token_buf[512];
const char *p = buf;
uint16 cp = 0;
uint16 ucs2 = 0;
/* Get the codepage value. */
if(!next_token(&p, token_buf, NULL, sizeof(token_buf)))
parse_error(buf, input_file, "cannot parse first value");
if(!parse_uint16( token_buf, &cp))
parse_error(buf, input_file, "first value doesn't resolve to an unsigned 16 bit integer");
if(cp > 255)
multibyte_code_page = True;
/* Get the ucs2 value. */
if(!next_token(&p, token_buf, NULL, sizeof(token_buf))) {
/*
* Some of the multibyte codepage to unicode map files
* list a single byte as a leading multibyte and have no
* second value.
*/
buf += (strlen(buf) + 1);
continue;
}
if(!parse_uint16( token_buf, &ucs2))
parse_error(buf, input_file, "second value doesn't resolve to an unsigned 16 bit integer");
/*
* Set up the cross reference in little-endian format.
*/
SSVAL(((char *)&cp_to_ucs2[cp]),0,ucs2);
SSVAL(((char *)&ucs2_to_cp[ucs2]),0,cp);
/*
* Next line.
*/
buf += (strlen(buf) + 1);
}
size = UNICODE_MAP_HEADER_SIZE + (multibyte_code_page ? (4*65536) : (2*256 + 2*65536));
if((output_buf = (char *)malloc( size )) == NULL) {
fprintf(stderr, "%s: output buffer malloc fail for size %d.\n", prog_name, size);
fclose(fp);
exit(1);
}
/* Setup the output file header. */
SSVAL(output_buf,UNICODE_MAP_VERSION_OFFSET,UNICODE_MAP_FILE_VERSION_ID);
memset(&output_buf[UNICODE_MAP_CLIENT_CODEPAGE_OFFSET],'\0',UNICODE_MAP_CODEPAGE_ID_SIZE);
safe_strcpy(&output_buf[UNICODE_MAP_CLIENT_CODEPAGE_OFFSET], codepage, UNICODE_MAP_CODEPAGE_ID_SIZE - 1);
output_buf[UNICODE_MAP_CLIENT_CODEPAGE_OFFSET+UNICODE_MAP_CODEPAGE_ID_SIZE-1] = '\0';
offset = UNICODE_MAP_HEADER_SIZE;
if (multibyte_code_page) {
SIVAL(output_buf,UNICODE_MAP_CP_TO_UNICODE_LENGTH_OFFSET,2*65536);
memcpy(output_buf+offset, (char *)cp_to_ucs2, 2*65536);
offset += 2*65536;
} else {
SIVAL(output_buf,UNICODE_MAP_CP_TO_UNICODE_LENGTH_OFFSET,2*256);
memcpy(output_buf+offset, (char *)cp_to_ucs2, 2*256);
offset += 2*256;
}
SIVAL(output_buf,UNICODE_MAP_UNICODE_TO_CP_LENGTH_OFFSET,65536*2);
memcpy(output_buf+offset, (char *)ucs2_to_cp, 2*65536);
/* Now write out the output_buf. */
if((fp = sys_fopen(output_file, "w"))==NULL) {
fprintf(stderr, "%s: Cannot open output file %s. Error was %s.\n",
prog_name, output_file, strerror(errno));
exit(1);
}
if(fwrite(output_buf, 1, size, fp) != size) {
fprintf(stderr, "%s: Cannot write output file %s. Error was %s.\n",
prog_name, output_file, strerror(errno));
exit(1);
}
fclose(fp);
SAFE_FREE(orig_buf);
SAFE_FREE(output_buf);
return 0;
}
int main(int argc, char **argv)
{
const char *codepage = NULL;
char *input_file = NULL;
char *output_file = NULL;
prog_name = argv[0];
if(argc != 4)
unicode_map_usage(prog_name);
codepage = argv[1];
input_file = argv[2];
output_file = argv[3];
return do_compile( codepage, input_file, output_file);
}
|