cxxfilt 0.1.0 → 0.1.1
This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
- checksums.yaml +5 -5
- data/Gemfile.lock +2 -2
- data/README.md +32 -3
- data/cxxfilt.gemspec +1 -1
- data/ext/cxxfilt/cp-demangle.c +6772 -0
- data/ext/cxxfilt/cp-demangle.h +194 -0
- data/ext/cxxfilt/cp-demint.c +237 -0
- data/ext/cxxfilt/cplus-dem.c +5032 -0
- data/ext/cxxfilt/cxxfilt.c +2 -1
- data/ext/cxxfilt/d-demangle.c +1646 -0
- data/ext/cxxfilt/demangle.h +723 -0
- data/ext/cxxfilt/environ.h +35 -0
- data/ext/cxxfilt/extconf.rb +0 -1
- data/ext/cxxfilt/libiberty.h +755 -0
- data/ext/cxxfilt/rust-demangle.c +348 -0
- data/ext/cxxfilt/safe-ctype.c +254 -0
- data/ext/cxxfilt/safe-ctype.h +150 -0
- data/ext/cxxfilt/xexit.c +52 -0
- data/ext/cxxfilt/xmalloc.c +184 -0
- data/ext/cxxfilt/xmemdup.c +41 -0
- data/ext/cxxfilt/xstrdup.c +36 -0
- data/lib/cxxfilt/cxxfilt.rb +6 -6
- data/lib/cxxfilt/version.rb +1 -1
- metadata +19 -4
@@ -0,0 +1,348 @@
|
|
1
|
+
/* Demangler for the Rust programming language
|
2
|
+
Copyright (C) 2016-2018 Free Software Foundation, Inc.
|
3
|
+
Written by David Tolnay (dtolnay@gmail.com).
|
4
|
+
|
5
|
+
This file is part of the libiberty library.
|
6
|
+
Libiberty is free software; you can redistribute it and/or
|
7
|
+
modify it under the terms of the GNU Library General Public
|
8
|
+
License as published by the Free Software Foundation; either
|
9
|
+
version 2 of the License, or (at your option) any later version.
|
10
|
+
|
11
|
+
In addition to the permissions in the GNU Library General Public
|
12
|
+
License, the Free Software Foundation gives you unlimited permission
|
13
|
+
to link the compiled version of this file into combinations with other
|
14
|
+
programs, and to distribute those combinations without any restriction
|
15
|
+
coming from the use of this file. (The Library Public License
|
16
|
+
restrictions do apply in other respects; for example, they cover
|
17
|
+
modification of the file, and distribution when not linked into a
|
18
|
+
combined executable.)
|
19
|
+
|
20
|
+
Libiberty is distributed in the hope that it will be useful,
|
21
|
+
but WITHOUT ANY WARRANTY; without even the implied warranty of
|
22
|
+
MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
|
23
|
+
Library General Public License for more details.
|
24
|
+
|
25
|
+
You should have received a copy of the GNU Library General Public
|
26
|
+
License along with libiberty; see the file COPYING.LIB.
|
27
|
+
If not, see <http://www.gnu.org/licenses/>. */
|
28
|
+
|
29
|
+
|
30
|
+
#ifdef HAVE_CONFIG_H
|
31
|
+
#include "config.h"
|
32
|
+
#endif
|
33
|
+
|
34
|
+
#include "safe-ctype.h"
|
35
|
+
|
36
|
+
#include <sys/types.h>
|
37
|
+
#include <string.h>
|
38
|
+
#include <stdio.h>
|
39
|
+
|
40
|
+
#ifdef HAVE_STRING_H
|
41
|
+
#include <string.h>
|
42
|
+
#else
|
43
|
+
extern size_t strlen(const char *s);
|
44
|
+
extern int strncmp(const char *s1, const char *s2, size_t n);
|
45
|
+
extern void *memset(void *s, int c, size_t n);
|
46
|
+
#endif
|
47
|
+
|
48
|
+
#include <demangle.h>
|
49
|
+
#include "libiberty.h"
|
50
|
+
|
51
|
+
|
52
|
+
/* Mangled Rust symbols look like this:
|
53
|
+
_$LT$std..sys..fd..FileDesc$u20$as$u20$core..ops..Drop$GT$::drop::hc68340e1baa4987a
|
54
|
+
|
55
|
+
The original symbol is:
|
56
|
+
<std::sys::fd::FileDesc as core::ops::Drop>::drop
|
57
|
+
|
58
|
+
The last component of the path is a 64-bit hash in lowercase hex,
|
59
|
+
prefixed with "h". Rust does not have a global namespace between
|
60
|
+
crates, an illusion which Rust maintains by using the hash to
|
61
|
+
distinguish things that would otherwise have the same symbol.
|
62
|
+
|
63
|
+
Any path component not starting with a XID_Start character is
|
64
|
+
prefixed with "_".
|
65
|
+
|
66
|
+
The following escape sequences are used:
|
67
|
+
|
68
|
+
"," => $C$
|
69
|
+
"@" => $SP$
|
70
|
+
"*" => $BP$
|
71
|
+
"&" => $RF$
|
72
|
+
"<" => $LT$
|
73
|
+
">" => $GT$
|
74
|
+
"(" => $LP$
|
75
|
+
")" => $RP$
|
76
|
+
" " => $u20$
|
77
|
+
"\"" => $u22$
|
78
|
+
"'" => $u27$
|
79
|
+
"+" => $u2b$
|
80
|
+
";" => $u3b$
|
81
|
+
"[" => $u5b$
|
82
|
+
"]" => $u5d$
|
83
|
+
"{" => $u7b$
|
84
|
+
"}" => $u7d$
|
85
|
+
"~" => $u7e$
|
86
|
+
|
87
|
+
A double ".." means "::" and a single "." means "-".
|
88
|
+
|
89
|
+
The only characters allowed in the mangled symbol are a-zA-Z0-9 and _.:$ */
|
90
|
+
|
91
|
+
static const char *hash_prefix = "::h";
|
92
|
+
static const size_t hash_prefix_len = 3;
|
93
|
+
static const size_t hash_len = 16;
|
94
|
+
|
95
|
+
static int is_prefixed_hash (const char *start);
|
96
|
+
static int looks_like_rust (const char *sym, size_t len);
|
97
|
+
static int unescape (const char **in, char **out, const char *seq, char value);
|
98
|
+
|
99
|
+
/* INPUT: sym: symbol that has been through C++ (gnu v3) demangling
|
100
|
+
|
101
|
+
This function looks for the following indicators:
|
102
|
+
|
103
|
+
1. The hash must consist of "h" followed by 16 lowercase hex digits.
|
104
|
+
|
105
|
+
2. As a sanity check, the hash must use between 5 and 15 of the 16
|
106
|
+
possible hex digits. This is true of 99.9998% of hashes so once
|
107
|
+
in your life you may see a false negative. The point is to
|
108
|
+
notice path components that could be Rust hashes but are
|
109
|
+
probably not, like "haaaaaaaaaaaaaaaa". In this case a false
|
110
|
+
positive (non-Rust symbol has an important path component
|
111
|
+
removed because it looks like a Rust hash) is worse than a false
|
112
|
+
negative (the rare Rust symbol is not demangled) so this sets
|
113
|
+
the balance in favor of false negatives.
|
114
|
+
|
115
|
+
3. There must be no characters other than a-zA-Z0-9 and _.:$
|
116
|
+
|
117
|
+
4. There must be no unrecognized $-sign sequences.
|
118
|
+
|
119
|
+
5. There must be no sequence of three or more dots in a row ("..."). */
|
120
|
+
|
121
|
+
int
|
122
|
+
rust_is_mangled (const char *sym)
|
123
|
+
{
|
124
|
+
size_t len, len_without_hash;
|
125
|
+
|
126
|
+
if (!sym)
|
127
|
+
return 0;
|
128
|
+
|
129
|
+
len = strlen (sym);
|
130
|
+
if (len <= hash_prefix_len + hash_len)
|
131
|
+
/* Not long enough to contain "::h" + hash + something else */
|
132
|
+
return 0;
|
133
|
+
|
134
|
+
len_without_hash = len - (hash_prefix_len + hash_len);
|
135
|
+
if (!is_prefixed_hash (sym + len_without_hash))
|
136
|
+
return 0;
|
137
|
+
|
138
|
+
return looks_like_rust (sym, len_without_hash);
|
139
|
+
}
|
140
|
+
|
141
|
+
/* A hash is the prefix "::h" followed by 16 lowercase hex digits. The
|
142
|
+
hex digits must comprise between 5 and 15 (inclusive) distinct
|
143
|
+
digits. */
|
144
|
+
|
145
|
+
static int
|
146
|
+
is_prefixed_hash (const char *str)
|
147
|
+
{
|
148
|
+
const char *end;
|
149
|
+
char seen[16];
|
150
|
+
size_t i;
|
151
|
+
int count;
|
152
|
+
|
153
|
+
if (strncmp (str, hash_prefix, hash_prefix_len))
|
154
|
+
return 0;
|
155
|
+
str += hash_prefix_len;
|
156
|
+
|
157
|
+
memset (seen, 0, sizeof(seen));
|
158
|
+
for (end = str + hash_len; str < end; str++)
|
159
|
+
if (*str >= '0' && *str <= '9')
|
160
|
+
seen[*str - '0'] = 1;
|
161
|
+
else if (*str >= 'a' && *str <= 'f')
|
162
|
+
seen[*str - 'a' + 10] = 1;
|
163
|
+
else
|
164
|
+
return 0;
|
165
|
+
|
166
|
+
/* Count how many distinct digits seen */
|
167
|
+
count = 0;
|
168
|
+
for (i = 0; i < 16; i++)
|
169
|
+
if (seen[i])
|
170
|
+
count++;
|
171
|
+
|
172
|
+
return count >= 5 && count <= 15;
|
173
|
+
}
|
174
|
+
|
175
|
+
static int
|
176
|
+
looks_like_rust (const char *str, size_t len)
|
177
|
+
{
|
178
|
+
const char *end = str + len;
|
179
|
+
|
180
|
+
while (str < end)
|
181
|
+
switch (*str)
|
182
|
+
{
|
183
|
+
case '$':
|
184
|
+
if (!strncmp (str, "$C$", 3))
|
185
|
+
str += 3;
|
186
|
+
else if (!strncmp (str, "$SP$", 4)
|
187
|
+
|| !strncmp (str, "$BP$", 4)
|
188
|
+
|| !strncmp (str, "$RF$", 4)
|
189
|
+
|| !strncmp (str, "$LT$", 4)
|
190
|
+
|| !strncmp (str, "$GT$", 4)
|
191
|
+
|| !strncmp (str, "$LP$", 4)
|
192
|
+
|| !strncmp (str, "$RP$", 4))
|
193
|
+
str += 4;
|
194
|
+
else if (!strncmp (str, "$u20$", 5)
|
195
|
+
|| !strncmp (str, "$u22$", 5)
|
196
|
+
|| !strncmp (str, "$u27$", 5)
|
197
|
+
|| !strncmp (str, "$u2b$", 5)
|
198
|
+
|| !strncmp (str, "$u3b$", 5)
|
199
|
+
|| !strncmp (str, "$u5b$", 5)
|
200
|
+
|| !strncmp (str, "$u5d$", 5)
|
201
|
+
|| !strncmp (str, "$u7b$", 5)
|
202
|
+
|| !strncmp (str, "$u7d$", 5)
|
203
|
+
|| !strncmp (str, "$u7e$", 5))
|
204
|
+
str += 5;
|
205
|
+
else
|
206
|
+
return 0;
|
207
|
+
break;
|
208
|
+
case '.':
|
209
|
+
/* Do not allow three or more consecutive dots */
|
210
|
+
if (!strncmp (str, "...", 3))
|
211
|
+
return 0;
|
212
|
+
/* Fall through */
|
213
|
+
case 'a': case 'b': case 'c': case 'd': case 'e': case 'f':
|
214
|
+
case 'g': case 'h': case 'i': case 'j': case 'k': case 'l':
|
215
|
+
case 'm': case 'n': case 'o': case 'p': case 'q': case 'r':
|
216
|
+
case 's': case 't': case 'u': case 'v': case 'w': case 'x':
|
217
|
+
case 'y': case 'z':
|
218
|
+
case 'A': case 'B': case 'C': case 'D': case 'E': case 'F':
|
219
|
+
case 'G': case 'H': case 'I': case 'J': case 'K': case 'L':
|
220
|
+
case 'M': case 'N': case 'O': case 'P': case 'Q': case 'R':
|
221
|
+
case 'S': case 'T': case 'U': case 'V': case 'W': case 'X':
|
222
|
+
case 'Y': case 'Z':
|
223
|
+
case '0': case '1': case '2': case '3': case '4': case '5':
|
224
|
+
case '6': case '7': case '8': case '9':
|
225
|
+
case '_':
|
226
|
+
case ':':
|
227
|
+
str++;
|
228
|
+
break;
|
229
|
+
default:
|
230
|
+
return 0;
|
231
|
+
}
|
232
|
+
|
233
|
+
return 1;
|
234
|
+
}
|
235
|
+
|
236
|
+
/*
|
237
|
+
INPUT: sym: symbol for which rust_is_mangled(sym) returned 1.
|
238
|
+
|
239
|
+
The input is demangled in-place because the mangled name is always
|
240
|
+
longer than the demangled one. */
|
241
|
+
|
242
|
+
void
|
243
|
+
rust_demangle_sym (char *sym)
|
244
|
+
{
|
245
|
+
const char *in;
|
246
|
+
char *out;
|
247
|
+
const char *end;
|
248
|
+
|
249
|
+
if (!sym)
|
250
|
+
return;
|
251
|
+
|
252
|
+
in = sym;
|
253
|
+
out = sym;
|
254
|
+
end = sym + strlen (sym) - (hash_prefix_len + hash_len);
|
255
|
+
|
256
|
+
while (in < end)
|
257
|
+
switch (*in)
|
258
|
+
{
|
259
|
+
case '$':
|
260
|
+
if (!(unescape (&in, &out, "$C$", ',')
|
261
|
+
|| unescape (&in, &out, "$SP$", '@')
|
262
|
+
|| unescape (&in, &out, "$BP$", '*')
|
263
|
+
|| unescape (&in, &out, "$RF$", '&')
|
264
|
+
|| unescape (&in, &out, "$LT$", '<')
|
265
|
+
|| unescape (&in, &out, "$GT$", '>')
|
266
|
+
|| unescape (&in, &out, "$LP$", '(')
|
267
|
+
|| unescape (&in, &out, "$RP$", ')')
|
268
|
+
|| unescape (&in, &out, "$u20$", ' ')
|
269
|
+
|| unescape (&in, &out, "$u22$", '\"')
|
270
|
+
|| unescape (&in, &out, "$u27$", '\'')
|
271
|
+
|| unescape (&in, &out, "$u2b$", '+')
|
272
|
+
|| unescape (&in, &out, "$u3b$", ';')
|
273
|
+
|| unescape (&in, &out, "$u5b$", '[')
|
274
|
+
|| unescape (&in, &out, "$u5d$", ']')
|
275
|
+
|| unescape (&in, &out, "$u7b$", '{')
|
276
|
+
|| unescape (&in, &out, "$u7d$", '}')
|
277
|
+
|| unescape (&in, &out, "$u7e$", '~'))) {
|
278
|
+
/* unexpected escape sequence, not looks_like_rust. */
|
279
|
+
goto fail;
|
280
|
+
}
|
281
|
+
break;
|
282
|
+
case '_':
|
283
|
+
/* If this is the start of a path component and the next
|
284
|
+
character is an escape sequence, ignore the underscore. The
|
285
|
+
mangler inserts an underscore to make sure the path
|
286
|
+
component begins with a XID_Start character. */
|
287
|
+
if ((in == sym || in[-1] == ':') && in[1] == '$')
|
288
|
+
in++;
|
289
|
+
else
|
290
|
+
*out++ = *in++;
|
291
|
+
break;
|
292
|
+
case '.':
|
293
|
+
if (in[1] == '.')
|
294
|
+
{
|
295
|
+
/* ".." becomes "::" */
|
296
|
+
*out++ = ':';
|
297
|
+
*out++ = ':';
|
298
|
+
in += 2;
|
299
|
+
}
|
300
|
+
else
|
301
|
+
{
|
302
|
+
/* "." becomes "-" */
|
303
|
+
*out++ = '-';
|
304
|
+
in++;
|
305
|
+
}
|
306
|
+
break;
|
307
|
+
case 'a': case 'b': case 'c': case 'd': case 'e': case 'f':
|
308
|
+
case 'g': case 'h': case 'i': case 'j': case 'k': case 'l':
|
309
|
+
case 'm': case 'n': case 'o': case 'p': case 'q': case 'r':
|
310
|
+
case 's': case 't': case 'u': case 'v': case 'w': case 'x':
|
311
|
+
case 'y': case 'z':
|
312
|
+
case 'A': case 'B': case 'C': case 'D': case 'E': case 'F':
|
313
|
+
case 'G': case 'H': case 'I': case 'J': case 'K': case 'L':
|
314
|
+
case 'M': case 'N': case 'O': case 'P': case 'Q': case 'R':
|
315
|
+
case 'S': case 'T': case 'U': case 'V': case 'W': case 'X':
|
316
|
+
case 'Y': case 'Z':
|
317
|
+
case '0': case '1': case '2': case '3': case '4': case '5':
|
318
|
+
case '6': case '7': case '8': case '9':
|
319
|
+
case ':':
|
320
|
+
*out++ = *in++;
|
321
|
+
break;
|
322
|
+
default:
|
323
|
+
/* unexpected character in symbol, not looks_like_rust. */
|
324
|
+
goto fail;
|
325
|
+
}
|
326
|
+
goto done;
|
327
|
+
|
328
|
+
fail:
|
329
|
+
*out++ = '?'; /* This is pretty lame, but it's hard to do better. */
|
330
|
+
done:
|
331
|
+
*out = '\0';
|
332
|
+
}
|
333
|
+
|
334
|
+
static int
|
335
|
+
unescape (const char **in, char **out, const char *seq, char value)
|
336
|
+
{
|
337
|
+
size_t len = strlen (seq);
|
338
|
+
|
339
|
+
if (strncmp (*in, seq, len))
|
340
|
+
return 0;
|
341
|
+
|
342
|
+
**out = value;
|
343
|
+
|
344
|
+
*in += len;
|
345
|
+
*out += 1;
|
346
|
+
|
347
|
+
return 1;
|
348
|
+
}
|
@@ -0,0 +1,254 @@
|
|
1
|
+
/* <ctype.h> replacement macros.
|
2
|
+
|
3
|
+
Copyright (C) 2000-2018 Free Software Foundation, Inc.
|
4
|
+
Contributed by Zack Weinberg <zackw@stanford.edu>.
|
5
|
+
|
6
|
+
This file is part of the libiberty library.
|
7
|
+
Libiberty is free software; you can redistribute it and/or
|
8
|
+
modify it under the terms of the GNU Library General Public
|
9
|
+
License as published by the Free Software Foundation; either
|
10
|
+
version 2 of the License, or (at your option) any later version.
|
11
|
+
|
12
|
+
Libiberty is distributed in the hope that it will be useful,
|
13
|
+
but WITHOUT ANY WARRANTY; without even the implied warranty of
|
14
|
+
MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
|
15
|
+
Library General Public License for more details.
|
16
|
+
|
17
|
+
You should have received a copy of the GNU Library General Public
|
18
|
+
License along with libiberty; see the file COPYING.LIB. If
|
19
|
+
not, write to the Free Software Foundation, Inc., 51 Franklin Street - Fifth Floor,
|
20
|
+
Boston, MA 02110-1301, USA. */
|
21
|
+
|
22
|
+
/*
|
23
|
+
|
24
|
+
@defvr Extension HOST_CHARSET
|
25
|
+
This macro indicates the basic character set and encoding used by the
|
26
|
+
host: more precisely, the encoding used for character constants in
|
27
|
+
preprocessor @samp{#if} statements (the C "execution character set").
|
28
|
+
It is defined by @file{safe-ctype.h}, and will be an integer constant
|
29
|
+
with one of the following values:
|
30
|
+
|
31
|
+
@ftable @code
|
32
|
+
@item HOST_CHARSET_UNKNOWN
|
33
|
+
The host character set is unknown - that is, not one of the next two
|
34
|
+
possibilities.
|
35
|
+
|
36
|
+
@item HOST_CHARSET_ASCII
|
37
|
+
The host character set is ASCII.
|
38
|
+
|
39
|
+
@item HOST_CHARSET_EBCDIC
|
40
|
+
The host character set is some variant of EBCDIC. (Only one of the
|
41
|
+
nineteen EBCDIC varying characters is tested; exercise caution.)
|
42
|
+
@end ftable
|
43
|
+
@end defvr
|
44
|
+
|
45
|
+
@deffn Extension ISALPHA (@var{c})
|
46
|
+
@deffnx Extension ISALNUM (@var{c})
|
47
|
+
@deffnx Extension ISBLANK (@var{c})
|
48
|
+
@deffnx Extension ISCNTRL (@var{c})
|
49
|
+
@deffnx Extension ISDIGIT (@var{c})
|
50
|
+
@deffnx Extension ISGRAPH (@var{c})
|
51
|
+
@deffnx Extension ISLOWER (@var{c})
|
52
|
+
@deffnx Extension ISPRINT (@var{c})
|
53
|
+
@deffnx Extension ISPUNCT (@var{c})
|
54
|
+
@deffnx Extension ISSPACE (@var{c})
|
55
|
+
@deffnx Extension ISUPPER (@var{c})
|
56
|
+
@deffnx Extension ISXDIGIT (@var{c})
|
57
|
+
|
58
|
+
These twelve macros are defined by @file{safe-ctype.h}. Each has the
|
59
|
+
same meaning as the corresponding macro (with name in lowercase)
|
60
|
+
defined by the standard header @file{ctype.h}. For example,
|
61
|
+
@code{ISALPHA} returns true for alphabetic characters and false for
|
62
|
+
others. However, there are two differences between these macros and
|
63
|
+
those provided by @file{ctype.h}:
|
64
|
+
|
65
|
+
@itemize @bullet
|
66
|
+
@item These macros are guaranteed to have well-defined behavior for all
|
67
|
+
values representable by @code{signed char} and @code{unsigned char}, and
|
68
|
+
for @code{EOF}.
|
69
|
+
|
70
|
+
@item These macros ignore the current locale; they are true for these
|
71
|
+
fixed sets of characters:
|
72
|
+
@multitable {@code{XDIGIT}} {yada yada yada yada yada yada yada yada}
|
73
|
+
@item @code{ALPHA} @tab @kbd{A-Za-z}
|
74
|
+
@item @code{ALNUM} @tab @kbd{A-Za-z0-9}
|
75
|
+
@item @code{BLANK} @tab @kbd{space tab}
|
76
|
+
@item @code{CNTRL} @tab @code{!PRINT}
|
77
|
+
@item @code{DIGIT} @tab @kbd{0-9}
|
78
|
+
@item @code{GRAPH} @tab @code{ALNUM || PUNCT}
|
79
|
+
@item @code{LOWER} @tab @kbd{a-z}
|
80
|
+
@item @code{PRINT} @tab @code{GRAPH ||} @kbd{space}
|
81
|
+
@item @code{PUNCT} @tab @kbd{`~!@@#$%^&*()_-=+[@{]@}\|;:'",<.>/?}
|
82
|
+
@item @code{SPACE} @tab @kbd{space tab \n \r \f \v}
|
83
|
+
@item @code{UPPER} @tab @kbd{A-Z}
|
84
|
+
@item @code{XDIGIT} @tab @kbd{0-9A-Fa-f}
|
85
|
+
@end multitable
|
86
|
+
|
87
|
+
Note that, if the host character set is ASCII or a superset thereof,
|
88
|
+
all these macros will return false for all values of @code{char} outside
|
89
|
+
the range of 7-bit ASCII. In particular, both ISPRINT and ISCNTRL return
|
90
|
+
false for characters with numeric values from 128 to 255.
|
91
|
+
@end itemize
|
92
|
+
@end deffn
|
93
|
+
|
94
|
+
@deffn Extension ISIDNUM (@var{c})
|
95
|
+
@deffnx Extension ISIDST (@var{c})
|
96
|
+
@deffnx Extension IS_VSPACE (@var{c})
|
97
|
+
@deffnx Extension IS_NVSPACE (@var{c})
|
98
|
+
@deffnx Extension IS_SPACE_OR_NUL (@var{c})
|
99
|
+
@deffnx Extension IS_ISOBASIC (@var{c})
|
100
|
+
These six macros are defined by @file{safe-ctype.h} and provide
|
101
|
+
additional character classes which are useful when doing lexical
|
102
|
+
analysis of C or similar languages. They are true for the following
|
103
|
+
sets of characters:
|
104
|
+
|
105
|
+
@multitable {@code{SPACE_OR_NUL}} {yada yada yada yada yada yada yada yada}
|
106
|
+
@item @code{IDNUM} @tab @kbd{A-Za-z0-9_}
|
107
|
+
@item @code{IDST} @tab @kbd{A-Za-z_}
|
108
|
+
@item @code{VSPACE} @tab @kbd{\r \n}
|
109
|
+
@item @code{NVSPACE} @tab @kbd{space tab \f \v \0}
|
110
|
+
@item @code{SPACE_OR_NUL} @tab @code{VSPACE || NVSPACE}
|
111
|
+
@item @code{ISOBASIC} @tab @code{VSPACE || NVSPACE || PRINT}
|
112
|
+
@end multitable
|
113
|
+
@end deffn
|
114
|
+
|
115
|
+
*/
|
116
|
+
|
117
|
+
#include "ansidecl.h"
|
118
|
+
#include <safe-ctype.h>
|
119
|
+
#include <stdio.h> /* for EOF */
|
120
|
+
|
121
|
+
#if EOF != -1
|
122
|
+
#error "<safe-ctype.h> requires EOF == -1"
|
123
|
+
#endif
|
124
|
+
|
125
|
+
/* Shorthand */
|
126
|
+
#define bl _sch_isblank
|
127
|
+
#define cn _sch_iscntrl
|
128
|
+
#define di _sch_isdigit
|
129
|
+
#define is _sch_isidst
|
130
|
+
#define lo _sch_islower
|
131
|
+
#define nv _sch_isnvsp
|
132
|
+
#define pn _sch_ispunct
|
133
|
+
#define pr _sch_isprint
|
134
|
+
#define sp _sch_isspace
|
135
|
+
#define up _sch_isupper
|
136
|
+
#define vs _sch_isvsp
|
137
|
+
#define xd _sch_isxdigit
|
138
|
+
|
139
|
+
/* Masks. */
|
140
|
+
#define L (const unsigned short) (lo|is |pr) /* lower case letter */
|
141
|
+
#define XL (const unsigned short) (lo|is|xd|pr) /* lowercase hex digit */
|
142
|
+
#define U (const unsigned short) (up|is |pr) /* upper case letter */
|
143
|
+
#define XU (const unsigned short) (up|is|xd|pr) /* uppercase hex digit */
|
144
|
+
#define D (const unsigned short) (di |xd|pr) /* decimal digit */
|
145
|
+
#define P (const unsigned short) (pn |pr) /* punctuation */
|
146
|
+
#define _ (const unsigned short) (pn|is |pr) /* underscore */
|
147
|
+
|
148
|
+
#define C (const unsigned short) ( cn) /* control character */
|
149
|
+
#define Z (const unsigned short) (nv |cn) /* NUL */
|
150
|
+
#define M (const unsigned short) (nv|sp |cn) /* cursor movement: \f \v */
|
151
|
+
#define V (const unsigned short) (vs|sp |cn) /* vertical space: \r \n */
|
152
|
+
#define T (const unsigned short) (nv|sp|bl|cn) /* tab */
|
153
|
+
#define S (const unsigned short) (nv|sp|bl|pr) /* space */
|
154
|
+
|
155
|
+
/* Are we ASCII? */
|
156
|
+
#if HOST_CHARSET == HOST_CHARSET_ASCII
|
157
|
+
|
158
|
+
const unsigned short _sch_istable[256] =
|
159
|
+
{
|
160
|
+
Z, C, C, C, C, C, C, C, /* NUL SOH STX ETX EOT ENQ ACK BEL */
|
161
|
+
C, T, V, M, M, V, C, C, /* BS HT LF VT FF CR SO SI */
|
162
|
+
C, C, C, C, C, C, C, C, /* DLE DC1 DC2 DC3 DC4 NAK SYN ETB */
|
163
|
+
C, C, C, C, C, C, C, C, /* CAN EM SUB ESC FS GS RS US */
|
164
|
+
S, P, P, P, P, P, P, P, /* SP ! " # $ % & ' */
|
165
|
+
P, P, P, P, P, P, P, P, /* ( ) * + , - . / */
|
166
|
+
D, D, D, D, D, D, D, D, /* 0 1 2 3 4 5 6 7 */
|
167
|
+
D, D, P, P, P, P, P, P, /* 8 9 : ; < = > ? */
|
168
|
+
P, XU, XU, XU, XU, XU, XU, U, /* @ A B C D E F G */
|
169
|
+
U, U, U, U, U, U, U, U, /* H I J K L M N O */
|
170
|
+
U, U, U, U, U, U, U, U, /* P Q R S T U V W */
|
171
|
+
U, U, U, P, P, P, P, _, /* X Y Z [ \ ] ^ _ */
|
172
|
+
P, XL, XL, XL, XL, XL, XL, L, /* ` a b c d e f g */
|
173
|
+
L, L, L, L, L, L, L, L, /* h i j k l m n o */
|
174
|
+
L, L, L, L, L, L, L, L, /* p q r s t u v w */
|
175
|
+
L, L, L, P, P, P, P, C, /* x y z { | } ~ DEL */
|
176
|
+
|
177
|
+
/* high half of unsigned char is locale-specific, so all tests are
|
178
|
+
false in "C" locale */
|
179
|
+
0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
|
180
|
+
0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
|
181
|
+
0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
|
182
|
+
0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
|
183
|
+
|
184
|
+
0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
|
185
|
+
0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
|
186
|
+
0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
|
187
|
+
0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
|
188
|
+
};
|
189
|
+
|
190
|
+
const unsigned char _sch_tolower[256] =
|
191
|
+
{
|
192
|
+
0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15,
|
193
|
+
16, 17, 18, 19, 20, 21, 22, 23, 24, 25, 26, 27, 28, 29, 30, 31,
|
194
|
+
32, 33, 34, 35, 36, 37, 38, 39, 40, 41, 42, 43, 44, 45, 46, 47,
|
195
|
+
48, 49, 50, 51, 52, 53, 54, 55, 56, 57, 58, 59, 60, 61, 62, 63,
|
196
|
+
64,
|
197
|
+
|
198
|
+
'a', 'b', 'c', 'd', 'e', 'f', 'g', 'h', 'i', 'j', 'k', 'l', 'm',
|
199
|
+
'n', 'o', 'p', 'q', 'r', 's', 't', 'u', 'v', 'w', 'x', 'y', 'z',
|
200
|
+
|
201
|
+
91, 92, 93, 94, 95, 96,
|
202
|
+
|
203
|
+
'a', 'b', 'c', 'd', 'e', 'f', 'g', 'h', 'i', 'j', 'k', 'l', 'm',
|
204
|
+
'n', 'o', 'p', 'q', 'r', 's', 't', 'u', 'v', 'w', 'x', 'y', 'z',
|
205
|
+
|
206
|
+
123,124,125,126,127,
|
207
|
+
|
208
|
+
128,129,130,131, 132,133,134,135, 136,137,138,139, 140,141,142,143,
|
209
|
+
144,145,146,147, 148,149,150,151, 152,153,154,155, 156,157,158,159,
|
210
|
+
160,161,162,163, 164,165,166,167, 168,169,170,171, 172,173,174,175,
|
211
|
+
176,177,178,179, 180,181,182,183, 184,185,186,187, 188,189,190,191,
|
212
|
+
|
213
|
+
192,193,194,195, 196,197,198,199, 200,201,202,203, 204,205,206,207,
|
214
|
+
208,209,210,211, 212,213,214,215, 216,217,218,219, 220,221,222,223,
|
215
|
+
224,225,226,227, 228,229,230,231, 232,233,234,235, 236,237,238,239,
|
216
|
+
240,241,242,243, 244,245,246,247, 248,249,250,251, 252,253,254,255,
|
217
|
+
};
|
218
|
+
|
219
|
+
const unsigned char _sch_toupper[256] =
|
220
|
+
{
|
221
|
+
0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15,
|
222
|
+
16, 17, 18, 19, 20, 21, 22, 23, 24, 25, 26, 27, 28, 29, 30, 31,
|
223
|
+
32, 33, 34, 35, 36, 37, 38, 39, 40, 41, 42, 43, 44, 45, 46, 47,
|
224
|
+
48, 49, 50, 51, 52, 53, 54, 55, 56, 57, 58, 59, 60, 61, 62, 63,
|
225
|
+
64,
|
226
|
+
|
227
|
+
'A', 'B', 'C', 'D', 'E', 'F', 'G', 'H', 'I', 'J', 'K', 'L', 'M',
|
228
|
+
'N', 'O', 'P', 'Q', 'R', 'S', 'T', 'U', 'V', 'W', 'X', 'Y', 'Z',
|
229
|
+
|
230
|
+
91, 92, 93, 94, 95, 96,
|
231
|
+
|
232
|
+
'A', 'B', 'C', 'D', 'E', 'F', 'G', 'H', 'I', 'J', 'K', 'L', 'M',
|
233
|
+
'N', 'O', 'P', 'Q', 'R', 'S', 'T', 'U', 'V', 'W', 'X', 'Y', 'Z',
|
234
|
+
|
235
|
+
123,124,125,126,127,
|
236
|
+
|
237
|
+
128,129,130,131, 132,133,134,135, 136,137,138,139, 140,141,142,143,
|
238
|
+
144,145,146,147, 148,149,150,151, 152,153,154,155, 156,157,158,159,
|
239
|
+
160,161,162,163, 164,165,166,167, 168,169,170,171, 172,173,174,175,
|
240
|
+
176,177,178,179, 180,181,182,183, 184,185,186,187, 188,189,190,191,
|
241
|
+
|
242
|
+
192,193,194,195, 196,197,198,199, 200,201,202,203, 204,205,206,207,
|
243
|
+
208,209,210,211, 212,213,214,215, 216,217,218,219, 220,221,222,223,
|
244
|
+
224,225,226,227, 228,229,230,231, 232,233,234,235, 236,237,238,239,
|
245
|
+
240,241,242,243, 244,245,246,247, 248,249,250,251, 252,253,254,255,
|
246
|
+
};
|
247
|
+
|
248
|
+
#else
|
249
|
+
# if HOST_CHARSET == HOST_CHARSET_EBCDIC
|
250
|
+
#error "FIXME: write tables for EBCDIC"
|
251
|
+
# else
|
252
|
+
#error "Unrecognized host character set"
|
253
|
+
# endif
|
254
|
+
#endif
|