1 /* $NetBSD: printable.c,v 1.3 2020/03/18 19:05:22 christos Exp $ */
2
3 /*++
4 /* NAME
5 /* printable 3
6 /* SUMMARY
7 /* mask non-printable characters
8 /* SYNOPSIS
9 /* #include <stringops.h>
10 /*
11 /* int util_utf8_enable;
12 /*
13 /* char *printable(buffer, replacement)
14 /* char *buffer;
15 /* int replacement;
16 /*
17 /* char *printable_except(buffer, replacement, except)
18 /* char *buffer;
19 /* int replacement;
20 /* const char *except;
21 /* DESCRIPTION
22 /* printable() replaces non-printable characters
23 /* in its input with the given replacement.
24 /*
25 /* util_utf8_enable controls whether UTF8 is considered printable.
26 /* With util_utf8_enable equal to zero, non-ASCII text is replaced.
27 /*
28 /* Arguments:
29 /* .IP buffer
30 /* The null-terminated input string.
31 /* .IP replacement
32 /* Replacement value for characters in \fIbuffer\fR that do not
33 /* pass the ASCII isprint(3) test or that are not valid UTF8.
34 /* .IP except
35 /* Null-terminated sequence of non-replaced ASCII characters.
36 /* LICENSE
37 /* .ad
38 /* .fi
39 /* The Secure Mailer license must be distributed with this software.
40 /* AUTHOR(S)
41 /* Wietse Venema
42 /* IBM T.J. Watson Research
43 /* P.O. Box 704
44 /* Yorktown Heights, NY 10598, USA
45 /*
46 /* Wietse Venema
47 /* Google, Inc.
48 /* 111 8th Avenue
49 /* New York, NY 10011, USA
50 /*--*/
51
52 /* System library. */
53
54 #include "sys_defs.h"
55 #include <ctype.h>
56 #include <string.h>
57
58 /* Utility library. */
59
60 #include "stringops.h"
61
62 int util_utf8_enable = 0;
63
64 /* printable - binary compatibility */
65
66 #undef printable
67
68 char *printable(char *, int);
69
printable(char * string,int replacement)70 char *printable(char *string, int replacement)
71 {
72 return (printable_except(string, replacement, (char *) 0));
73 }
74
75 /* printable_except - pass through printable or other preserved characters */
76
printable_except(char * string,int replacement,const char * except)77 char *printable_except(char *string, int replacement, const char *except)
78 {
79 unsigned char *cp;
80 int ch;
81
82 /*
83 * XXX Replace invalid UTF8 sequences (too short, over-long encodings,
84 * out-of-range code points, etc). See valid_utf8_string.c.
85 */
86 cp = (unsigned char *) string;
87 while ((ch = *cp) != 0) {
88 if (ISASCII(ch) && (ISPRINT(ch) || (except && strchr(except, ch)))) {
89 /* ok */
90 } else if (util_utf8_enable && ch >= 194 && ch <= 254
91 && cp[1] >= 128 && cp[1] < 192) {
92 /* UTF8; skip the rest of the bytes in the character. */
93 while (cp[1] >= 128 && cp[1] < 192)
94 cp++;
95 } else {
96 /* Not ASCII and not UTF8. */
97 *cp = replacement;
98 }
99 cp++;
100 }
101 return (string);
102 }
103