/* rlmbutil.h -- utility functions for multibyte characters. */
-/* Copyright (C) 2001, 2003 Free Software Foundation, Inc.
+/* Copyright (C) 2001-2015 Free Software Foundation, Inc.
- This file is part of the GNU Readline Library, a library for
- reading lines of text with interactive input and history editing.
+ This file is part of the GNU Readline Library (Readline), a library
+ for reading lines of text with interactive input and history editing.
- The GNU Readline Library 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 2, or
+ Readline 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.
- The GNU Readline Library 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
+ Readline 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.
- The GNU General Public License is often shipped with GNU software, and
- is generally kept in a file called COPYING or LICENSE. If you do not
- have a copy of the license, write to the Free Software Foundation,
- 59 Temple Place, Suite 330, Boston, MA 02111 USA. */
+ You should have received a copy of the GNU General Public License
+ along with Readline. If not, see <http://www.gnu.org/licenses/>.
+*/
#if !defined (_RL_MBUTIL_H_)
#define _RL_MBUTIL_H_
/************************************************/
/* For platforms which support the ISO C amendement 1 functionality we
- support user defined character classes.
-
- Some platforms have the multibyte functions such as mbsrtowcs but
- are lacking the multitype type mbstate_t. BeOS (unknown version)
- and HP/UX 11.23 without _XOPEN_SOURCE=500 are like this.
-
- We really need mbstate_t type to operate properly. For example, see
- compute_lcd_of_matches, where two mbstate_t's are active at the same
- time. So we require both the functions and the mbstate_t type in
- order to enable multibyte support. */
-
+ support user defined character classes. */
/* Solaris 2.5 has a bug: <wchar.h> must be included before <wctype.h>. */
-#if defined (HAVE_WCTYPE_H) && defined (HAVE_WCHAR_H)
+#if defined (HAVE_WCTYPE_H) && defined (HAVE_WCHAR_H) && defined (HAVE_LOCALE_H)
# include <wchar.h>
# include <wctype.h>
-# if defined (HAVE_MBSTATE_T) && defined (HAVE_MBSRTOWCS) && defined (HAVE_MBRTOWC) && defined (HAVE_MBRLEN) && defined (HAVE_WCWIDTH)
+# if defined (HAVE_ISWCTYPE) && \
+ defined (HAVE_ISWLOWER) && \
+ defined (HAVE_ISWUPPER) && \
+ defined (HAVE_MBSRTOWCS) && \
+ defined (HAVE_MBRTOWC) && \
+ defined (HAVE_MBRLEN) && \
+ defined (HAVE_TOWLOWER) && \
+ defined (HAVE_TOWUPPER) && \
+ defined (HAVE_WCHAR_T) && \
+ defined (HAVE_WCWIDTH)
/* system is supposed to support XPG5 */
# define HANDLE_MULTIBYTE 1
# endif
#define MB_INVALIDCH(x) ((x) == (size_t)-1 || (x) == (size_t)-2)
#define MB_NULLWCH(x) ((x) == 0)
+/* Try and shortcut the printable ascii characters to cut down the number of
+ calls to a libc wcwidth() */
+static inline int
+_rl_wcwidth (wc)
+ wchar_t wc;
+{
+ switch (wc)
+ {
+ 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 '~':
+ return 1;
+ default:
+ return wcwidth (wc);
+ }
+}
+
+/* Unicode combining characters range from U+0300 to U+036F */
+#define UNICODE_COMBINING_CHAR(x) ((x) >= 768 && (x) <= 879)
+
+#if defined (WCWIDTH_BROKEN)
+# define WCWIDTH(wc) ((_rl_utf8locale && UNICODE_COMBINING_CHAR(wc)) ? 0 : _rl_wcwidth(wc))
+#else
+# define WCWIDTH(wc) _rl_wcwidth(wc)
+#endif
+
+#if defined (WCWIDTH_BROKEN)
+# define IS_COMBINING_CHAR(x) (WCWIDTH(x) == 0 && iswcntrl(x) == 0)
+#else
+# define IS_COMBINING_CHAR(x) (WCWIDTH(x) == 0)
+#endif
+
+#define UTF8_SINGLEBYTE(c) (((c) & 0x80) == 0)
+#define UTF8_MBFIRSTCHAR(c) (((c) & 0xc0) == 0xc0)
+#define UTF8_MBCHAR(c) (((c) & 0xc0) == 0x80)
+
#else /* !HANDLE_MULTIBYTE */
#undef MB_LEN_MAX
#define MB_INVALIDCH(x) (0)
#define MB_NULLWCH(x) (0)
+#define UTF8_SINGLEBYTE(c) (1)
+
+#if !defined (HAVE_WCHAR_T) && !defined (wchar_t)
+# define wchar_t int
+#endif
+
#endif /* !HANDLE_MULTIBYTE */
extern int rl_byte_oriented;