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
|
/* qmark.c -- quote 'dangerous' filenames
Derived from coreutils' ls.c.
Copyright (C) 1985-2022 Free Software Foundation, Inc.
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 3 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, see <https://www.gnu.org/licenses/>.
*/
/* config.h must be included first. */
#include <config.h>
/* system headers. */
#include <ctype.h>
#include <stdlib.h>
#include <string.h>
#include <wchar.h>
/* gnulib headers would go here if any needed to be included. */
/* find headers. */
#include "printquoted.h"
/*
This comment, IN_CTYPE_DOMAIN and ISPRINT were borrowed from
coreutils at Sun Jun 5 21:17:40 2005 UTC.
Jim Meyering writes:
"... Some ctype macros are valid only for character codes that
isascii says are ASCII (SGI's IRIX-4.0.5 is one such system --when
using /bin/cc or gcc but without giving an ansi option). So, all
ctype uses should be through macros like ISPRINT... If
STDC_HEADERS is defined, then autoconf has verified that the ctype
macros don't need to be guarded with references to isascii. ...
Defining isascii to 1 should let any compiler worth its salt
eliminate the && through constant folding."
Bruno Haible adds:
"... Furthermore, isupper(c) etc. have an undefined result if c is
outside the range -1 <= c <= 255. One is tempted to write isupper(c)
with c being of type `char', but this is wrong if c is an 8-bit
character >= 128 which gets sign-extended to a negative value.
The macro ISUPPER protects against this as well."
(Actually that rule of ISUPPER is now taken by to_uchar).
*/
#if STDC_HEADERS
# define IN_CTYPE_DOMAIN(c) 1
#else
# define IN_CTYPE_DOMAIN(c) isascii(c)
#endif
/* ISPRINT is defined in <sys/euc.h> on at least Solaris2.6 systems. */
#undef ISPRINT
#define ISPRINT(c) (IN_CTYPE_DOMAIN (c) && isprint (c))
/* Convert a possibly-signed character to an unsigned character. This is
* a bit safer than casting to unsigned char, since it catches some type
* errors that the cast doesn't.
*
* This code taken from coreutils' system.h header at
* Sun Jun 5 21:05:21 2005 UTC.
*/
static inline unsigned char to_uchar (char ch)
{
return ch;
}
static size_t
unibyte_qmark_chars (char *buf, size_t len)
{
char *p = buf;
char const *plimit = buf + len;
while (p < plimit)
{
if (! ISPRINT (to_uchar (*p)))
*p = '?';
p++;
}
return len;
}
/* Scan BUF, replacing any dangerous-looking characters with question
* marks. This code is taken from the ls.c file in coreutils as at
* Sun Jun 5 20:51:54 2005 UTC.
*
* This function may shrink the buffer. Either way, the new length
* is returned.
*/
size_t
qmark_chars (char *buf, size_t len)
{
if (MB_CUR_MAX <= 1)
{
return unibyte_qmark_chars (buf, len);
}
else
{
char const *p = buf;
char const *plimit = buf + len;
char *q = buf;
while (p < plimit)
switch (*p)
{
case ' ': case '!': case '"': case '#': case '%':
case '&': case '\'': case '(': case ')': case '*':
case '+': case ',': case '-': case '.': case '/':
case '0': case '1': case '2': case '3': case '4':
case '5': case '6': case '7': case '8': case '9':
case ':': case ';': case '<': case '=': case '>':
case '?':
case 'A': case 'B': case 'C': case 'D': case 'E':
case 'F': case 'G': case 'H': case 'I': case 'J':
case 'K': case 'L': case 'M': case 'N': case 'O':
case 'P': case 'Q': case 'R': case 'S': case 'T':
case 'U': case 'V': case 'W': case 'X': case 'Y':
case 'Z':
case '[': case '\\': case ']': case '^': case '_':
case 'a': case 'b': case 'c': case 'd': case 'e':
case 'f': case 'g': case 'h': case 'i': case 'j':
case 'k': case 'l': case 'm': case 'n': case 'o':
case 'p': case 'q': case 'r': case 's': case 't':
case 'u': case 'v': case 'w': case 'x': case 'y':
case 'z': case '{': case '|': case '}': case '~':
/* These characters are printable ASCII characters. */
*q++ = *p++;
break;
default:
/* If we have a multibyte sequence, copy it until we
reach its end, replacing each non-printable multibyte
character with a single question mark. */
{
mbstate_t mbstate;
memset (&mbstate, 0, sizeof mbstate);
do
{
wchar_t wc;
size_t bytes;
int w;
bytes = mbrtowc (&wc, p, plimit - p, &mbstate);
if (bytes == (size_t) -1)
{
/* An invalid multibyte sequence was
encountered. Skip one input byte, and
put a question mark. */
p++;
*q++ = '?';
break;
}
if (bytes == (size_t) -2)
{
/* An incomplete multibyte character
at the end. Replace it entirely with
a question mark. */
p = plimit;
*q++ = '?';
break;
}
if (bytes == 0)
/* A null wide character was encountered. */
bytes = 1;
w = wcwidth (wc);
if (w >= 0)
{
/* A printable multibyte character.
Keep it. */
for (; bytes > 0; --bytes)
*q++ = *p++;
}
else
{
/* An unprintable multibyte character.
Replace it entirely with a question
mark. */
p += bytes;
*q++ = '?';
}
}
while (! mbsinit (&mbstate));
}
break;
}
/* The buffer may have shrunk. */
len = q - buf;
return len;
}
}
|
