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
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
|
/**************************************************************************
*
* Copyright (C) 2002, International Business Machines
* Corporation and others. All Rights Reserved.
*
***************************************************************************
*/
//
// ugrep - an ICU sample program illustrating the use of ICU Regular Expressions.
//
// The use of the ICU Regex API all occurs within the main()
// function. The rest of the code deals with with opening files,
// encoding conversions, printing results, etc.
//
// This is not a full-featured grep program. The command line options
// have been kept to a minimum to avoid complicating the sample code.
//
#include <stdio.h>
#include <stdlib.h>
#include <string.h>
#include "unicode/utypes.h"
#include "unicode/ustring.h"
#include "unicode/regex.h"
#include "unicode/ucnv.h"
#include "unicode/uclean.h"
//
// The following variables contain paramters that may be set from the command line.
//
const char *pattern = NULL; // The regular expression
int firstFileNum; // argv index of the first file name
UBool displayFileName = FALSE;
UBool displayLineNum = FALSE;
//
// Info regarding the file currently being processed
//
const char *fileName;
int fileLen; // Length, in UTF-16 Code Units.
UChar *ucharBuf = 0; // Buffer, holds converted file. (Simple minded program, always reads
// the whole file at once.
char *charBuf = 0; // Buffer, for original, unconverted file data.
//
// Info regarding the line currently being processed
//
int lineStart; // Index of first char of the current line in the file buffer
int lineEnd; // Index of char following the new line sequence for the current line
int lineNum;
//
// Converter, used on output to convert Unicode data back to char *
// so that it will display in non-Unicode terminal windows.
//
UConverter *outConverter = 0;
//
// Function forward declarations
//
void processOptions(int argc, const char **argv);
void nextLine(int start);
void printMatch();
void printUsage();
void readFile(const char *name);
//------------------------------------------------------------------------------------------
//
// main for ugrep
//
// Structurally, all use of the ICU Regular Expression API is in main(),
// and all of the supporting stuff necessary to make a running program, but
// not directly related to regular expressions, is factored out into these other
// functions.
//
//------------------------------------------------------------------------------------------
int main(int argc, const char** argv) {
UBool matchFound = FALSE;
//
// Process the commmand line options.
//
processOptions(argc, argv);
//
// Create a RegexPattern object from the user supplied pattern string.
//
UErrorCode status = U_ZERO_ERROR; // All ICU operations report success or failure
// in a status variable.
UParseError parseErr; // In the event of a syntax error in the regex pattern,
// this struct will contain the position of the
// error.
RegexPattern *rePat = RegexPattern::compile(pattern, parseErr, status);
// Note that C++ is doing an automatic conversion
// of the (char *) pattern to a temporary
// UnicodeString object.
if (U_FAILURE(status)) {
fprintf(stderr, "ugrep: error in pattern: \"%s\" at position %d\n",
u_errorName(status), parseErr.offset);
exit(-1);
}
//
// Create a RegexMatcher from the newly created pattern.
//
UnicodeString empty;
RegexMatcher *matcher = rePat->matcher(empty, status);
if (U_FAILURE(status)) {
fprintf(stderr, "ugrep: error in creating RegexMatcher: \"%s\"\n",
u_errorName(status));
exit(-1);
}
//
// Loop, processing each of the input files.
//
for (int fileNum=firstFileNum; fileNum < argc; fileNum++) {
readFile(argv[fileNum]);
//
// Loop through the lines of a file, trying to match the regex pattern on each.
//
for (nextLine(0); lineStart<fileLen; nextLine(lineEnd)) {
UnicodeString s(FALSE, ucharBuf+lineStart, lineEnd-lineStart);
matcher->reset(s);
if (matcher->find()) {
matchFound = TRUE;
printMatch();
}
}
}
//
// Clean up
//
delete matcher;
delete rePat;
free(ucharBuf);
free(charBuf);
ucnv_close(outConverter);
u_cleanup(); // shut down ICU, release any cached data it owns.
return matchFound? 0: 1;
}
//------------------------------------------------------------------------------------------
//
// doOptions Run through the command line options, and set
// the global variables accordingly.
//
// exit without returning if an error occured and
// ugrep should not proceed further.
//
//------------------------------------------------------------------------------------------
void processOptions(int argc, const char **argv) {
int optInd;
UBool doUsage = FALSE;
UBool doVersion = FALSE;
const char *arg;
for(optInd = 1; optInd < argc; ++optInd) {
arg = argv[optInd];
/* version info */
if(strcmp(arg, "-V") == 0 || strcmp(arg, "--version") == 0) {
doVersion = TRUE;
}
/* usage info */
else if(strcmp(arg, "--help") == 0) {
doUsage = TRUE;
}
else if(strcmp(arg, "-n") == 0 || strcmp(arg, "--line-number") == 0) {
displayLineNum = TRUE;
}
/* POSIX.1 says all arguments after -- are not options */
else if(strcmp(arg, "--") == 0) {
/* skip the -- */
++optInd;
break;
}
/* unrecognized option */
else if(strncmp(arg, "-", strlen("-")) == 0) {
printf("ugrep: invalid option -- %s\n", arg+1);
doUsage = TRUE;
}
/* done with options */
else {
break;
}
}
if (doUsage) {
printUsage();
exit(0);
}
if (doVersion) {
printf("ugrep version 0.01\n");
if (optInd == argc) {
exit(0);
}
}
int remainingArgs = argc-optInd; // pattern file ...
if (remainingArgs < 2) {
fprintf(stderr, "ugrep: files or pattern are missing.\n");
printUsage();
exit(1);
}
if (remainingArgs > 2) {
// More than one file to be processed. Display file names with match output.
displayFileName = TRUE;
}
pattern = argv[optInd];
firstFileNum = optInd+1;
}
//------------------------------------------------------------------------------------------
//
// printUsage
//
//------------------------------------------------------------------------------------------
void printUsage() {
printf("ugrep [options] pattern file...\n"
" -V or --version display version information\n"
" --help display this help and exit\n"
" -- stop further option processing\n"
"-n, --line-number Prefix each line of output with the line number within its input file.\n"
);
exit(0);
}
//------------------------------------------------------------------------------------------
//
// readFile Read a file into memory, and convert it to Unicode.
//
// Since this is just a demo program, take the simple minded approach
// of always reading the whole file at once. No intelligent buffering
// is done.
//
//------------------------------------------------------------------------------------------
void readFile(const char *name) {
//
// Initialize global file variables
//
fileName = name;
fileLen = 0; // zero length prevents processing in case of errors.
//
// Open the file and determine its size.
//
FILE *file = fopen(name, "rb");
if (file == 0 ) {
fprintf(stderr, "ugrep: Could not open file \"%s\"\n", fileName);
return;
}
fseek(file, 0, SEEK_END);
int rawFileLen = ftell(file);
fseek(file, 0, SEEK_SET);
//
// Read in the file
//
charBuf = (char *)realloc(charBuf, rawFileLen+1); // Need error checking...
int t = fread(charBuf, 1, rawFileLen, file);
if (t != rawFileLen) {
fprintf(stderr, "Error reading file \"%s\"\n", fileName);
return;
}
charBuf[rawFileLen]=0;
fclose(file);
//
// Look for a Unicode Signature (BOM) in the data
//
int32_t signatureLength;
const char * charDataStart = charBuf;
UErrorCode status = U_ZERO_ERROR;
const char* encoding = ucnv_detectUnicodeSignature(
charDataStart, rawFileLen, &signatureLength, &status);
if (U_FAILURE(status)) {
fprintf(stderr, "ugrep: ICU Error \"%s\" from ucnv_detectUnicodeSignature()\n",
u_errorName(status));
return;
}
if(encoding!=NULL ){
charDataStart += signatureLength;
rawFileLen -= signatureLength;
}
//
// Open a converter to take the file to UTF-16
//
UConverter* conv;
conv = ucnv_open(encoding, &status);
if (U_FAILURE(status)) {
fprintf(stderr, "ugrep: ICU Error \"%s\" from ucnv_open()\n", u_errorName(status));
return;
}
//
// Convert the file data to UChar.
// Preflight first to determine required buffer size.
//
uint32_t destCap = ucnv_toUChars(conv,
NULL, // dest,
0, // destCapacity,
charDataStart,
rawFileLen,
&status);
if (status != U_BUFFER_OVERFLOW_ERROR) {
fprintf(stderr, "ugrep: ucnv_toUChars: ICU Error \"%s\"\n", u_errorName(status));
return;
};
status = U_ZERO_ERROR;
ucharBuf = (UChar *)realloc(ucharBuf, (destCap+1) * sizeof(UChar));
ucnv_toUChars(conv,
ucharBuf, // dest,
destCap+1,
charDataStart,
rawFileLen,
&status);
if (U_FAILURE(status)) {
fprintf(stderr, "ugrep: ucnv_toUChars: ICU Error \"%s\"\n", u_errorName(status));
return;
};
ucnv_close(conv);
//
// Successful conversion. Set the global size variables so that
// the rest of the processing will proceed for this file.
//
fileLen = destCap;
}
//------------------------------------------------------------------------------------------
//
// nextLine Advance the line index variables, starting at the
// specified position in the input file buffer, by
// scanning forwrd until the next end-of-line.
//
// Need to take into account all of the possible Unicode
// line ending sequences.
//
//------------------------------------------------------------------------------------------
void nextLine(int startPos) {
if (startPos == 0) {
lineNum = 0;
} else {
lineNum++;
}
lineStart = lineEnd = startPos;
for (;;) {
if (lineEnd >= fileLen) {
return;
}
UChar c = ucharBuf[lineEnd];
lineEnd++;
if (c == 0x0a || // Line Feed
c == 0x0c || // Form Feed
c == 0x0d || // Carriage Return
c == 0x85 || // Next Line
c == 0x2028 || // Line Separator
c == 0x2029) // Paragraph separator
{
break;
}
}
// Check for CR/LF sequence, and advance over the LF if we're in the middle of one.
if (lineEnd < fileLen &&
ucharBuf[lineEnd-1] == 0x0d &&
ucharBuf[lineEnd] == 0x0a)
{
lineEnd++;
}
}
//------------------------------------------------------------------------------------------
//
// printMatch Called when a matching line has been located.
// Print out the line from the file with the match, after
// converting it back to the default code page.
//
//------------------------------------------------------------------------------------------
void printMatch() {
char buf[2000];
UErrorCode status = U_ZERO_ERROR;
// If we haven't already created a converter for output, do it now.
if (outConverter == 0) {
outConverter = ucnv_open(NULL, &status);
if (U_FAILURE(status)) {
fprintf(stderr, "ugrep: Error opening default converter: \"%s\"\n",
u_errorName(status));
exit(-1);
}
};
// Convert the line to be printed back to the default 8 bit code page.
// If the line is too long for our buffer, just truncate it.
ucnv_fromUChars(outConverter,
buf, // destination buffer for conversion
sizeof(buf), // capacity of destination buffer
&ucharBuf[lineStart], // Input to conversion
lineEnd-lineStart, // number of UChars to convert
&status);
buf[sizeof(buf)-1] = 0; // Add null for use in case of too long lines.
// The converter null-terminates its output unless
// the buffer completely fills.
if (displayFileName) {
printf("%s:", fileName);
}
if (displayLineNum) {
printf("%d:", lineNum);
}
printf("%s", buf);
}
|