1 /*
2 *******************************************************************************
3 *
4 * Copyright (C) 2003, International Business Machines
5 * Corporation and others. All Rights Reserved.
6 *
7 *******************************************************************************
8 * file name: ucdstrip.c
9 * encoding: US-ASCII
10 * tab size: 8 (not used)
11 * indentation:4
12 *
13 * created on: 2003feb20
14 * created by: Markus W. Scherer
15 *
16 * Simple tool for Unicode Character Database files with semicolon-delimited fields.
17 * Removes comments behind data lines but not in others.
18 *
19 * To compile, just call a C compiler/linker with this source file.
20 * On Windows: cl ucdstrip.c
21 */
22
23 #include <stdio.h>
24 #include <string.h>
25 #include <stdlib.h>
26
27 /* return the first character position after the end of the data */
28 static char *
endOfData(const char * l)29 endOfData(const char *l) {
30 char *end;
31 char c;
32
33 end=strchr(l, '#');
34 if(end!=NULL) {
35 /* ignore whitespace before the comment */
36 while(l!=end && ((c=*(end-1))==' ' || c=='\t')) {
37 --end;
38 }
39 } else {
40 end=strchr(l, 0);
41 }
42 return end;
43 }
44
45 extern int
main(int argc,const char * argv[])46 main(int argc, const char *argv[]) {
47 static char line[2000];
48 char *end;
49
50 while(gets(line)!=NULL) {
51 if(strtol(line, &end, 16)>=0 && end!=line) {
52 /* code point or range followed by semicolon and data, remove comment */
53 *endOfData(line)=0;
54 }
55 puts(line);
56 }
57
58 return 0;
59 }
60