1 |
330 |
jeremybenn |
/* Character set conversion support for GDB.
|
2 |
|
|
Copyright (C) 2001, 2007, 2008, 2009, 2010 Free Software Foundation, Inc.
|
3 |
|
|
|
4 |
|
|
This file is part of GDB.
|
5 |
|
|
|
6 |
|
|
This program is free software; you can redistribute it and/or modify
|
7 |
|
|
it under the terms of the GNU General Public License as published by
|
8 |
|
|
the Free Software Foundation; either version 3 of the License, or
|
9 |
|
|
(at your option) any later version.
|
10 |
|
|
|
11 |
|
|
This program is distributed in the hope that it will be useful,
|
12 |
|
|
but WITHOUT ANY WARRANTY; without even the implied warranty of
|
13 |
|
|
MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
|
14 |
|
|
GNU General Public License for more details.
|
15 |
|
|
|
16 |
|
|
You should have received a copy of the GNU General Public License
|
17 |
|
|
along with this program. If not, see <http://www.gnu.org/licenses/>. */
|
18 |
|
|
|
19 |
|
|
#ifndef CHARSET_H
|
20 |
|
|
#define CHARSET_H
|
21 |
|
|
|
22 |
|
|
/* If the target program uses a different character set than the host,
|
23 |
|
|
GDB has some support for translating between the two; GDB converts
|
24 |
|
|
characters and strings to the host character set before displaying
|
25 |
|
|
them, and converts characters and strings appearing in expressions
|
26 |
|
|
entered by the user to the target character set.
|
27 |
|
|
|
28 |
|
|
GDB's code pretty much assumes that the host character set is some
|
29 |
|
|
superset of ASCII; there are plenty if ('0' + n) expressions and
|
30 |
|
|
the like. */
|
31 |
|
|
|
32 |
|
|
/* Return the name of the current host/target character set. The
|
33 |
|
|
result is owned by the charset module; the caller should not free
|
34 |
|
|
it. */
|
35 |
|
|
const char *host_charset (void);
|
36 |
|
|
const char *target_charset (struct gdbarch *gdbarch);
|
37 |
|
|
const char *target_wide_charset (struct gdbarch *gdbarch);
|
38 |
|
|
|
39 |
|
|
/* These values are used to specify the type of transliteration done
|
40 |
|
|
by convert_between_encodings. */
|
41 |
|
|
enum transliterations
|
42 |
|
|
{
|
43 |
|
|
/* Error on failure to convert. */
|
44 |
|
|
translit_none,
|
45 |
|
|
/* Transliterate to host char. */
|
46 |
|
|
translit_char
|
47 |
|
|
};
|
48 |
|
|
|
49 |
|
|
/* Convert between two encodings.
|
50 |
|
|
|
51 |
|
|
FROM is the name of the source encoding.
|
52 |
|
|
TO is the name of the target encoding.
|
53 |
|
|
BYTES holds the bytes to convert; this is assumed to be characters
|
54 |
|
|
in the target encoding.
|
55 |
|
|
NUM_BYTES is the number of bytes.
|
56 |
|
|
WIDTH is the width of a character from the FROM charset, in bytes.
|
57 |
|
|
For a variable width encoding, WIDTH should be the size of a "base
|
58 |
|
|
character".
|
59 |
|
|
OUTPUT is an obstack where the converted data is written. The
|
60 |
|
|
caller is responsible for initializing the obstack, and for
|
61 |
|
|
destroying the obstack should an error occur.
|
62 |
|
|
TRANSLIT specifies how invalid conversions should be handled. */
|
63 |
|
|
void convert_between_encodings (const char *from, const char *to,
|
64 |
|
|
const gdb_byte *bytes, unsigned int num_bytes,
|
65 |
|
|
int width, struct obstack *output,
|
66 |
|
|
enum transliterations translit);
|
67 |
|
|
|
68 |
|
|
|
69 |
|
|
/* These values are used by wchar_iterate to report errors. */
|
70 |
|
|
enum wchar_iterate_result
|
71 |
|
|
{
|
72 |
|
|
/* Ordinary return. */
|
73 |
|
|
wchar_iterate_ok,
|
74 |
|
|
/* Invalid input sequence. */
|
75 |
|
|
wchar_iterate_invalid,
|
76 |
|
|
/* Incomplete input sequence at the end of the input. */
|
77 |
|
|
wchar_iterate_incomplete,
|
78 |
|
|
/* EOF. */
|
79 |
|
|
wchar_iterate_eof
|
80 |
|
|
};
|
81 |
|
|
|
82 |
|
|
/* Declaration of the opaque wchar iterator type. */
|
83 |
|
|
struct wchar_iterator;
|
84 |
|
|
|
85 |
|
|
/* Create a new character iterator which returns wchar_t's. INPUT is
|
86 |
|
|
the input buffer. BYTES is the number of bytes in the input
|
87 |
|
|
buffer. CHARSET is the name of the character set in which INPUT is
|
88 |
|
|
encoded. WIDTH is the number of bytes in a base character of
|
89 |
|
|
CHARSET.
|
90 |
|
|
|
91 |
|
|
This function either returns a new character set iterator, or calls
|
92 |
|
|
error. The result can be freed using a cleanup; see
|
93 |
|
|
make_cleanup_wchar_iterator. */
|
94 |
|
|
struct wchar_iterator *make_wchar_iterator (const gdb_byte *input, size_t bytes,
|
95 |
|
|
const char *charset,
|
96 |
|
|
size_t width);
|
97 |
|
|
|
98 |
|
|
/* Return a new cleanup suitable for destroying the wchar iterator
|
99 |
|
|
ITER. */
|
100 |
|
|
struct cleanup *make_cleanup_wchar_iterator (struct wchar_iterator *iter);
|
101 |
|
|
|
102 |
|
|
/* Perform a single iteration of a wchar_t iterator.
|
103 |
|
|
|
104 |
|
|
Returns the number of characters converted. A negative result
|
105 |
|
|
means that EOF has been reached. A positive result indicates the
|
106 |
|
|
number of valid wchar_ts in the result; *OUT_CHARS is updated to
|
107 |
|
|
point to the first valid character.
|
108 |
|
|
|
109 |
|
|
In all cases aside from EOF, *PTR is set to point to the first
|
110 |
|
|
converted target byte. *LEN is set to the number of bytes
|
111 |
|
|
converted.
|
112 |
|
|
|
113 |
|
|
A zero result means one of several unusual results. *OUT_RESULT is
|
114 |
|
|
set to indicate the type of un-ordinary return.
|
115 |
|
|
|
116 |
|
|
wchar_iterate_invalid means that an invalid input character was
|
117 |
|
|
seen. The iterator is advanced by WIDTH (the argument to
|
118 |
|
|
make_wchar_iterator) bytes.
|
119 |
|
|
|
120 |
|
|
wchar_iterate_incomplete means that an incomplete character was
|
121 |
|
|
seen at the end of the input sequence.
|
122 |
|
|
|
123 |
|
|
wchar_iterate_eof means that all bytes were successfully
|
124 |
|
|
converted. The other output arguments are not set. */
|
125 |
|
|
int wchar_iterate (struct wchar_iterator *iter,
|
126 |
|
|
enum wchar_iterate_result *out_result,
|
127 |
|
|
gdb_wchar_t **out_chars,
|
128 |
|
|
const gdb_byte **ptr, size_t *len);
|
129 |
|
|
|
130 |
|
|
|
131 |
|
|
|
132 |
|
|
/* GDB needs to know a few details of its execution character set.
|
133 |
|
|
This knowledge is isolated here and in charset.c. */
|
134 |
|
|
|
135 |
|
|
/* The escape character. */
|
136 |
|
|
#define HOST_ESCAPE_CHAR 27
|
137 |
|
|
|
138 |
|
|
/* Convert a letter, like 'c', to its corresponding control
|
139 |
|
|
character. */
|
140 |
|
|
char host_letter_to_control_character (char c);
|
141 |
|
|
|
142 |
|
|
/* Convert a hex digit character to its numeric value. E.g., 'f' is
|
143 |
|
|
converted to 15. This function assumes that C is a valid hex
|
144 |
|
|
digit. Both upper- and lower-case letters are recognized. */
|
145 |
|
|
int host_hex_value (char c);
|
146 |
|
|
|
147 |
|
|
#endif /* CHARSET_H */
|