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
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
|
// Copyright (C) 2016 and later: Unicode, Inc. and others.
// License & terms of use: http://www.unicode.org/copyright.html
/*
**********************************************************************
* Copyright (C) 2009-2016, International Business Machines
* Corporation and others. All Rights Reserved.
**********************************************************************
*
* File gencfu.c
*/
//--------------------------------------------------------------------
//
// Tool for generating Unicode Confusable data files (.cfu files).
// .cfu files contain the compiled of the confusable data
// derived from the Unicode Consortium data described in
// Unicode UAX 39.
//
// Usage: gencfu [options] -r confusables-file.txt -o output-file.cfu
//
// options: -v verbose
// -? or -h help
//
// The input rule filew is are plain text files containing confusable character
// definitions in the input format defined by Unicode UAX39 for the files
// confusables.txt. This source (.txt) format
// is also accepted direaccepted by ICU spoof detedtors. The
// files must be encoded in utf-8 format, with or without a BOM.
//
// The script used to compile confusablesWholeScript.txt into the CFU file
// until the Unicode consortium deprecated it.
//
//--------------------------------------------------------------------
#include "unicode/utypes.h"
#include "unicode/unistr.h"
#include "unicode/uclean.h"
#include "unicode/udata.h"
#include "unicode/putil.h"
#include "uoptions.h"
#include "unewdata.h"
#include "ucmndata.h"
#include "uspoof_impl.h"
#include "cmemory.h"
#include <stdio.h>
#include <stdlib.h>
#include <string.h>
U_NAMESPACE_USE
static char *progName;
static UOption options[]={
UOPTION_HELP_H, /* 0 */
UOPTION_HELP_QUESTION_MARK, /* 1 */
UOPTION_VERBOSE, /* 2 */
{ "rules", NULL, NULL, NULL, 'r', UOPT_REQUIRES_ARG, 0 }, /* 3 */
{ "wsrules", NULL, NULL, NULL, 'w', UOPT_REQUIRES_ARG, 0}, /* 4 */ // deprecated
{ "out", NULL, NULL, NULL, 'o', UOPT_REQUIRES_ARG, 0 }, /* 5 */
UOPTION_ICUDATADIR, /* 6 */
UOPTION_DESTDIR, /* 7 */
UOPTION_COPYRIGHT, /* 8 */
UOPTION_QUIET, /* 9 */
};
void usageAndDie(int retCode) {
printf("Usage: %s [-v] [-options] -r confusablesRules.txt -o output-file\n", progName);
printf("\tRead in Unicode confusable character definitions and write out the binary data\n"
"options:\n"
"\t-h or -? or --help this usage text\n"
"\t-V or --version show a version message\n"
"\t-c or --copyright include a copyright notice\n"
"\t-v or --verbose turn on verbose output\n"
"\t-q or --quiet do not display warnings and progress\n"
"\t-i or --icudatadir directory for locating any needed intermediate data files,\n"
"\t followed by path, defaults to %s\n"
"\t-d or --destdir destination directory, followed by the path\n",
u_getDataDirectory());
exit (retCode);
}
#if UCONFIG_NO_REGULAR_EXPRESSIONS || UCONFIG_NO_NORMALIZATION || UCONFIG_NO_FILE_IO
/* dummy UDataInfo cf. udata.h */
static UDataInfo dummyDataInfo = {
sizeof(UDataInfo),
0,
U_IS_BIG_ENDIAN,
U_CHARSET_FAMILY,
U_SIZEOF_UCHAR,
0,
{ 0, 0, 0, 0 }, /* dummy dataFormat */
{ 0, 0, 0, 0 }, /* dummy formatVersion */
{ 0, 0, 0, 0 } /* dummy dataVersion */
};
#else
//
// Set up the ICU data header, defined in ucmndata.h
//
DataHeader dh ={
{sizeof(DataHeader), // Struct MappedData
0xda,
0x27},
{ // struct UDataInfo
sizeof(UDataInfo), // size
0, // reserved
U_IS_BIG_ENDIAN,
U_CHARSET_FAMILY,
U_SIZEOF_UCHAR,
0, // reserved
{ 0x43, 0x66, 0x75, 0x20 }, // dataFormat="Cfu "
{ 0xff, 0, 0, 0 }, // formatVersion. Filled in later with values
// from the builder. The values declared
// here should never appear in any real data.
{ 5, 1, 0, 0 } // dataVersion (Unicode version)
}};
#endif
// Forward declaration for function for reading source files.
static const char *readFile(const char *fileName, int32_t *len);
//----------------------------------------------------------------------------
//
// main for gencfu
//
//----------------------------------------------------------------------------
int main(int argc, char **argv) {
UErrorCode status = U_ZERO_ERROR;
const char *confFileName;
const char *outFileName;
const char *outDir = NULL;
const char *copyright = NULL;
//
// Pick up and check the command line arguments,
// using the standard ICU tool utils option handling.
//
U_MAIN_INIT_ARGS(argc, argv);
progName = argv[0];
argc=u_parseArgs(argc, argv, UPRV_LENGTHOF(options), options);
if(argc<0) {
// Unrecognized option
fprintf(stderr, "error in command line argument \"%s\"\n", argv[-argc]);
usageAndDie(U_ILLEGAL_ARGUMENT_ERROR);
}
if(options[0].doesOccur || options[1].doesOccur) {
// -? or -h for help.
usageAndDie(0);
}
if (!(options[3].doesOccur && options[5].doesOccur)) {
fprintf(stderr, "confusables file and output file must all be specified.\n");
usageAndDie(U_ILLEGAL_ARGUMENT_ERROR);
}
confFileName = options[3].value;
outFileName = options[5].value;
if (options[6].doesOccur) {
u_setDataDirectory(options[6].value);
}
status = U_ZERO_ERROR;
/* Combine the directory with the file name */
if(options[7].doesOccur) {
outDir = options[7].value;
}
if (options[8].doesOccur) {
copyright = U_COPYRIGHT_STRING;
}
UBool quiet = FALSE;
if (options[9].doesOccur) {
quiet = TRUE;
}
#if UCONFIG_NO_REGULAR_EXPRESSIONS || UCONFIG_NO_NORMALIZATION || UCONFIG_NO_FILE_IO
// spoof detection data file parsing is dependent on regular expressions.
// TODO: have the tool return an error status. Requires fixing the ICU data build
// so that it doesn't abort entirely on that error.
UNewDataMemory *pData;
char msg[1024];
/* write message with just the name */
sprintf(msg, "gencfu writes dummy %s because of UCONFIG_NO_REGULAR_EXPRESSIONS and/or UCONFIG_NO_NORMALIZATION and/or UCONFIG_NO_FILE_IO, see uconfig.h", outFileName);
fprintf(stderr, "%s\n", msg);
/* write the dummy data file */
pData = udata_create(outDir, NULL, outFileName, &dummyDataInfo, NULL, &status);
udata_writeBlock(pData, msg, strlen(msg));
udata_finish(pData, &status);
return (int)status;
#else
/* Initialize ICU */
u_init(&status);
if (U_FAILURE(status)) {
fprintf(stderr, "%s: can not initialize ICU. status = %s\n",
argv[0], u_errorName(status));
exit(1);
}
status = U_ZERO_ERROR;
// Read in the confusables source file
int32_t confusablesLen = 0;
const char *confusables = readFile(confFileName, &confusablesLen);
if (confusables == NULL) {
printf("gencfu: error reading file \"%s\"\n", confFileName);
exit(-1);
}
//
// Create the Spoof Detector from the source confusables files.
// This will compile the data.
//
UParseError parseError;
parseError.line = 0;
parseError.offset = 0;
int32_t errType;
USpoofChecker *sc = uspoof_openFromSource(confusables, confusablesLen,
NULL, 0,
&errType, &parseError, &status);
if (U_FAILURE(status)) {
fprintf(stderr, "gencfu: uspoof_openFromSource error \"%s\" at file %s, line %d, column %d\n",
u_errorName(status), confFileName, (int)parseError.line, (int)parseError.offset);
exit(status);
};
//
// Get the compiled rule data from the USpoofChecker.
//
uint32_t outDataSize;
uint8_t *outData;
outDataSize = uspoof_serialize(sc, NULL, 0, &status);
if (status != U_BUFFER_OVERFLOW_ERROR) {
fprintf(stderr, "gencfu: uspoof_serialize() returned %s\n", u_errorName(status));
exit(status);
}
status = U_ZERO_ERROR;
outData = new uint8_t[outDataSize];
uspoof_serialize(sc, outData, outDataSize, &status);
// Copy the data format version numbers from the spoof data header into the UDataMemory header.
uprv_memcpy(dh.info.formatVersion,
reinterpret_cast<SpoofDataHeader *>(outData)->fFormatVersion,
sizeof(dh.info.formatVersion));
//
// Create the output file
//
size_t bytesWritten;
UNewDataMemory *pData;
pData = udata_create(outDir, NULL, outFileName, &(dh.info), copyright, &status);
if(U_FAILURE(status)) {
fprintf(stderr, "gencfu: Could not open output file \"%s\", \"%s\"\n",
outFileName, u_errorName(status));
exit(status);
}
// Write the data itself.
udata_writeBlock(pData, outData, outDataSize);
// finish up
bytesWritten = udata_finish(pData, &status);
if(U_FAILURE(status)) {
fprintf(stderr, "gencfu: Error %d writing the output file\n", status);
exit(status);
}
if (bytesWritten != outDataSize) {
fprintf(stderr, "gencfu: Error writing to output file \"%s\"\n", outFileName);
exit(-1);
}
uspoof_close(sc);
delete [] outData;
delete [] confusables;
u_cleanup();
if (!quiet) {
printf("gencfu: tool completed successfully.\n");
}
return 0;
#endif // UCONFIG_NO_REGULAR_EXPRESSIONS
}
//
// Read in a confusables source file
//
static const char *readFile(const char *fileName, int32_t *len) {
char *result;
long fileSize;
FILE *file;
file = fopen(fileName, "rb");
if( file == 0 ) {
return NULL;
}
fseek(file, 0, SEEK_END);
fileSize = ftell(file);
fseek(file, 0, SEEK_SET);
result = new char[fileSize+10];
if (result==NULL) {
fclose(file);
return NULL;
}
long t = fread(result, 1, fileSize, file);
if (t != fileSize) {
delete [] result;
fclose(file);
return NULL;
}
result[fileSize]=0;
*len = static_cast<int32_t>(fileSize);
fclose(file);
return result;
}
|