mirror of
https://github.com/espressif/binutils-gdb.git
synced 2025-09-27 09:25:04 +08:00
Support UTF-8 identifiers in C/C++ expressions (PR gdb/22973)
Factor out cp_ident_is_alpha/cp_ident_is_alnum out of gdb/cp-name-parser.y and use it in the C/C++ expression parser too. New test included. gdb/ChangeLog: 2018-05-22 Pedro Alves <palves@redhat.com> 張俊芝 <zjz@zjz.name> PR gdb/22973 * c-exp.y: Include "c-support.h". (parse_number, c_parse_escape, lex_one_token): Use TOLOWER instead of tolower. Use c_ident_is_alpha to scan names. * c-lang.c: Include "c-support.h". (convert_ucn, convert_octal, convert_hex, convert_escape): Use ISXDIGIT instead of isxdigit and ISDIGIT instead of isdigit. * c-support.h: New file, with bits factored out from ... * cp-name-parser.y: ... this file. Include "c-support.h". (cp_ident_is_alpha, cp_ident_is_alnum): Deleted, moved to c-support.h and renamed. (symbol_end, yylex): Adjust. gdb/testsuite/ChangeLog: 2018-05-22 Pedro Alves <palves@redhat.com> PR gdb/22973 * gdb.base/utf8-identifiers.c: New file. * gdb.base/utf8-identifiers.exp: New file.
This commit is contained in:
46
gdb/c-support.h
Normal file
46
gdb/c-support.h
Normal file
@ -0,0 +1,46 @@
|
||||
/* Helper routines for C support in GDB.
|
||||
Copyright (C) 2017-2018 Free Software Foundation, Inc.
|
||||
|
||||
This file is part of GDB.
|
||||
|
||||
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 <http://www.gnu.org/licenses/>. */
|
||||
|
||||
#ifndef C_SUPPORT_H
|
||||
#define C_SUPPORT_H
|
||||
|
||||
#include "safe-ctype.h"
|
||||
|
||||
/* Like ISALPHA, but also returns true for the union of all UTF-8
|
||||
multi-byte sequence bytes and non-ASCII characters in
|
||||
extended-ASCII charsets (e.g., Latin1). I.e., returns true if the
|
||||
high bit is set. Note that not all UTF-8 ranges are allowed in C++
|
||||
identifiers, but we don't need to be pedantic so for simplicity we
|
||||
ignore that here. Plus this avoids the complication of actually
|
||||
knowing what was the right encoding. */
|
||||
|
||||
static inline bool
|
||||
c_ident_is_alpha (unsigned char ch)
|
||||
{
|
||||
return ISALPHA (ch) || ch >= 0x80;
|
||||
}
|
||||
|
||||
/* Similarly, but Like ISALNUM. */
|
||||
|
||||
static inline bool
|
||||
c_ident_is_alnum (unsigned char ch)
|
||||
{
|
||||
return ISALNUM (ch) || ch >= 0x80;
|
||||
}
|
||||
|
||||
#endif /* C_SUPPORT_H */
|
Reference in New Issue
Block a user