1 /* Character set conversion support for GDB. 2 Copyright (C) 2001-2013 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 64 void convert_between_encodings (const char *from, const char *to, 65 const gdb_byte *bytes, 66 unsigned int num_bytes, 67 int width, struct obstack *output, 68 enum transliterations translit); 69 70 71 /* These values are used by wchar_iterate to report errors. */ 72 enum wchar_iterate_result 73 { 74 /* Ordinary return. */ 75 wchar_iterate_ok, 76 /* Invalid input sequence. */ 77 wchar_iterate_invalid, 78 /* Incomplete input sequence at the end of the input. */ 79 wchar_iterate_incomplete, 80 /* EOF. */ 81 wchar_iterate_eof 82 }; 83 84 /* Declaration of the opaque wchar iterator type. */ 85 struct wchar_iterator; 86 87 /* Create a new character iterator which returns wchar_t's. INPUT is 88 the input buffer. BYTES is the number of bytes in the input 89 buffer. CHARSET is the name of the character set in which INPUT is 90 encoded. WIDTH is the number of bytes in a base character of 91 CHARSET. 92 93 This function either returns a new character set iterator, or calls 94 error. The result can be freed using a cleanup; see 95 make_cleanup_wchar_iterator. */ 96 struct wchar_iterator *make_wchar_iterator (const gdb_byte *input, 97 size_t bytes, 98 const char *charset, 99 size_t width); 100 101 /* Return a new cleanup suitable for destroying the wchar iterator 102 ITER. */ 103 struct cleanup *make_cleanup_wchar_iterator (struct wchar_iterator *iter); 104 105 /* Perform a single iteration of a wchar_t iterator. 106 107 Returns the number of characters converted. A negative result 108 means that EOF has been reached. A positive result indicates the 109 number of valid wchar_ts in the result; *OUT_CHARS is updated to 110 point to the first valid character. 111 112 In all cases aside from EOF, *PTR is set to point to the first 113 converted target byte. *LEN is set to the number of bytes 114 converted. 115 116 A zero result means one of several unusual results. *OUT_RESULT is 117 set to indicate the type of un-ordinary return. 118 119 wchar_iterate_invalid means that an invalid input character was 120 seen. The iterator is advanced by WIDTH (the argument to 121 make_wchar_iterator) bytes. 122 123 wchar_iterate_incomplete means that an incomplete character was 124 seen at the end of the input sequence. 125 126 wchar_iterate_eof means that all bytes were successfully 127 converted. The other output arguments are not set. */ 128 int wchar_iterate (struct wchar_iterator *iter, 129 enum wchar_iterate_result *out_result, 130 gdb_wchar_t **out_chars, 131 const gdb_byte **ptr, size_t *len); 132 133 134 135 /* GDB needs to know a few details of its execution character set. 136 This knowledge is isolated here and in charset.c. */ 137 138 /* The escape character. */ 139 #define HOST_ESCAPE_CHAR 27 140 141 /* Convert a letter, like 'c', to its corresponding control 142 character. */ 143 char host_letter_to_control_character (char c); 144 145 /* Convert a hex digit character to its numeric value. E.g., 'f' is 146 converted to 15. This function assumes that C is a valid hex 147 digit. Both upper- and lower-case letters are recognized. */ 148 int host_hex_value (char c); 149 150 #endif /* CHARSET_H */ 151