sh.char.h revision 145479
1/* $Header: /src/pub/tcsh/sh.char.h,v 3.26 2005/03/03 16:49:15 kim Exp $ */
2/*
3 * sh.char.h: Table for spotting special characters quickly
4 * 	      Makes for very obscure but efficient coding.
5 */
6/*-
7 * Copyright (c) 1980, 1991 The Regents of the University of California.
8 * All rights reserved.
9 *
10 * Redistribution and use in source and binary forms, with or without
11 * modification, are permitted provided that the following conditions
12 * are met:
13 * 1. Redistributions of source code must retain the above copyright
14 *    notice, this list of conditions and the following disclaimer.
15 * 2. Redistributions in binary form must reproduce the above copyright
16 *    notice, this list of conditions and the following disclaimer in the
17 *    documentation and/or other materials provided with the distribution.
18 * 3. Neither the name of the University nor the names of its contributors
19 *    may be used to endorse or promote products derived from this software
20 *    without specific prior written permission.
21 *
22 * THIS SOFTWARE IS PROVIDED BY THE REGENTS AND CONTRIBUTORS ``AS IS'' AND
23 * ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
24 * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
25 * ARE DISCLAIMED.  IN NO EVENT SHALL THE REGENTS OR CONTRIBUTORS BE LIABLE
26 * FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL
27 * DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS
28 * OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION)
29 * HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT
30 * LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY
31 * OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF
32 * SUCH DAMAGE.
33 */
34#ifndef _h_sh_char
35#define _h_sh_char
36#if defined(NeXT) && defined(NLS)
37# include <appkit/NXCType.h>
38#else
39# include <ctype.h>
40# ifdef SHORT_STRINGS
41#  ifdef HAVE_WCTYPE_H
42#   include <wctype.h>
43#  else
44#   include <wchar.h>
45#  endif
46# endif
47#endif
48
49typedef unsigned char tcshuc;
50#ifdef _MINIX
51# undef _SP
52#endif /* _MINIX */
53extern unsigned short _cmap[];
54#if defined(DSPMBYTE)
55# define CHECK_MBYTEVAR	STRdspmbyte
56#endif
57extern unsigned short _cmap_c[];
58extern unsigned short _cmap_mbyte[];
59extern short _enable_mbdisp;
60extern unsigned short _mbmap[];
61extern unsigned short _mbmap_euc[];
62extern unsigned short _mbmap_sjis[];
63extern unsigned short _mbmap_big5[];
64extern unsigned short _mbmap_utf8[];
65/* VARIABLE Check str */
66/* same compiler require #define even not define DSPMBYTE */
67#define _MB1	0x0001
68#define _MB2	0x0002
69
70#ifndef NLS
71extern tcshuc _cmap_lower[], _cmap_upper[];
72
73#endif
74
75#define	_QF	0x0001		/* '" (Forward quotes) */
76#define	_QB	0x0002		/* ` (Backquote) */
77#define	_SP	0x0004		/* space and tab */
78#define	_NL	0x0008		/* \n */
79#define	_META	0x0010		/* lex meta characters, sp #'`";&<>()|\t\n */
80#define	_GLOB	0x0020		/* glob characters, *?{[` */
81#define	_ESC	0x0040		/* \ */
82#define	_DOL	0x0080		/* $ */
83#define	_DIG  	0x0100		/* 0-9 */
84#define	_LET  	0x0200		/* a-z, A-Z, _, or locale-specific */
85#define	_UP   	0x0400		/* A-Z, or locale-specific */
86#define	_DOW  	0x0800		/* a-z, or locale-specific */
87#define	_XD 	0x1000		/* 0-9, a-f, A-F */
88#define	_CMD	0x2000		/* lex end of command chars, ;&(|` */
89#define _CTR	0x4000		/* control */
90#define _PUN	0x8000		/* punctuation */
91
92#ifdef IS_ASCII
93# define ASC(ch) ch
94# define CTL_ESC(ch) ch
95#else
96# ifdef _OSD_POSIX
97/* "BS2000 OSD" is a POSIX on a main frame using a EBCDIC char set */
98#   include <ascii_ebcdic.h>
99# else
100/* "OS/390 USS" is a POSIX on a main frame using an IBM1047 char set */
101# endif
102  extern unsigned short _toascii[256];
103  extern unsigned short _toebcdic[256];
104
105/* mainly for comparisons if (ASC(ch)=='\177')... */
106#  define ASC(ch)     _toascii[(tcshuc)ch]
107
108/* Literal escapes ('\010') must be mapped to EBCDIC,
109 * for C-Escapes   ('\b'), the compiler already does it.
110 */
111#  define CTL_ESC(ch) _toebcdic[(tcshuc)ch]
112#endif /*IS_ASCII*/
113
114#ifdef WIDE_STRINGS
115# define cmap(c, bits)	\
116	(((c) & QUOTE) || (c) >= 0x0080 ? 0 : (_cmap[(tcshuc)ASC(c)] & (bits)))
117#elif defined(SHORT_STRINGS) && defined(KANJI)
118#  define cmap(c, bits)	\
119	((((c) & QUOTE) || ((ASC(c) & 0x80) && adrof(STRnokanji))) ? \
120	0 : (_cmap[(tcshuc)ASC(c)] & (bits)))
121#else /* SHORT_STRINGS && KANJI */
122# define cmap(c, bits)	\
123	(((c) & QUOTE) ? 0 : (_cmap[(tcshuc)ASC(c)] & (bits)))
124#endif /* SHORT_STRINGS && KANJI */
125
126#define isglob(c)	cmap(c, _GLOB)
127#define isspc(c)	cmap(c, _SP)
128#define ismeta(c)	cmap(c, _META)
129#define iscmdmeta(c)	cmap(c, _CMD)
130#ifdef WIDE_STRINGS
131#define letter(c)	(((c) & QUOTE) ? 0 :  \
132			 (iswalpha((tcshuc) (c)) || (c) == '_'))
133#define alnum(c)	(((c) & QUOTE) ? 0 :  \
134		         (iswalnum((tcshuc) (c)) || (c) == '_'))
135#else
136#define letter(c)	(((Char)(c) & QUOTE) ? 0 :  \
137			 (isalpha((tcshuc) (c)) || (c) == '_'))
138#define alnum(c)	(((Char)(c) & QUOTE) ? 0 :  \
139		         (isalnum((tcshuc) (c)) || (c) == '_'))
140#endif
141
142#if defined(DSPMBYTE)
143# define IsmbyteU(c)	(Ismbyte1((Char)(c))||(Ismbyte2((Char)(c))&&((c)&0200)))
144#endif
145
146#ifdef NLS
147# ifdef WIDE_STRINGS
148#  define Isspace(c)	(((c) & QUOTE) ? 0 : iswspace(c))
149#  define Isdigit(c)	(((c) & QUOTE) ? 0 : iswdigit(c))
150#  define Isalpha(c)	(((c) & QUOTE) ? 0 : iswalpha(c))
151#  define Islower(c)	(((c) & QUOTE) ? 0 : iswlower(c))
152#  define Isupper(c)	(((c) & QUOTE) ? 0 : iswupper(c))
153#  define Tolower(c) 	(((c) & QUOTE) ? 0 : (wchar_t)towlower(c))
154#  define Toupper(c) 	(((c) & QUOTE) ? 0 : (wchar_t)towupper(c))
155#  define Isxdigit(c)	(((c) & QUOTE) ? 0 : iswxdigit(c))
156#  define Isalnum(c)	(((c) & QUOTE) ? 0 : iswalnum(c))
157#  define Iscntrl(c) 	(((c) & QUOTE) ? 0 : iswcntrl(c))
158#  define Isprint(c) 	(((c) & QUOTE) ? 0 : iswprint(c))
159#  define Ispunct(c) 	(((c) & QUOTE) ? 0 : iswpunct(c))
160# elif defined (NeXT)
161#  define Isspace(c)	(((Char)(c) & QUOTE) ? 0 : NXIsSpace((unsigned) (c)))
162#  define Isdigit(c)	(((Char)(c) & QUOTE) ? 0 : NXIsDigit((unsigned) (c)))
163#  define Isalpha(c)	(((Char)(c) & QUOTE) ? 0 : NXIsAlpha((unsigned) (c)))
164#  define Islower(c)	(((Char)(c) & QUOTE) ? 0 : NXIsLower((unsigned) (c)))
165#  define Isupper(c)	(((Char)(c) & QUOTE) ? 0 : NXIsUpper((unsigned) (c)))
166#  define Tolower(c) 	(((Char)(c) & QUOTE) ? 0 : NXToLower((unsigned) (c)))
167#  define Toupper(c) 	(((Char)(c) & QUOTE) ? 0 : NXToUpper((unsigned) (c)))
168#  define Isxdigit(c)	(((Char)(c) & QUOTE) ? 0 : NXIsXDigit((unsigned) (c)))
169#if defined(DSPMBYTE)
170#  define IscntrlM(c) 	(((Char)(c) & QUOTE) ? 0 : NXIsCntrl((unsigned) (c)))
171#  define Iscntrl(c)	( (IscntrlM(c)) && !(_enable_mbdisp&&(IsmbyteU((c)))) )
172#  define IsprintM(c) 	(((Char)(c) & QUOTE) ? 0 : NXIsPrint((unsigned) (c)))
173#  define Isprint(c)	( (IsprintM(c)) || (_enable_mbdisp&&(IsmbyteU((c)))) )
174#else
175#  define Isalnum(c)	(((Char)(c) & QUOTE) ? 0 : NXIsAlNum((unsigned) (c)))
176#  define Iscntrl(c) 	(((Char)(c) & QUOTE) ? 0 : NXIsCntrl((unsigned) (c)))
177#  define Isprint(c) 	(((Char)(c) & QUOTE) ? 0 : NXIsPrint((unsigned) (c)))
178#endif /* !defined(DSPMBYTE) */
179#  define Ispunct(c) 	(((Char)(c) & QUOTE) ? 0 : NXIsPunct((unsigned) (c)))
180# else /* !NeXT */
181#  ifndef WINNT_NATIVE
182#   define Isspace(c)	(((Char)(c) & QUOTE) ? 0 : isspace((tcshuc) (c)))
183#   define Isdigit(c)	(((Char)(c) & QUOTE) ? 0 : isdigit((tcshuc) (c)))
184#   define Isalpha(c)	(((Char)(c) & QUOTE) ? 0 : isalpha((tcshuc) (c)))
185#   define Islower(c)	(((Char)(c) & QUOTE) ? 0 : islower((tcshuc) (c)))
186#   define Isupper(c)	(((Char)(c) & QUOTE) ? 0 : isupper((tcshuc) (c)))
187#   define Tolower(c) 	(((Char)(c) & QUOTE) ? 0 : tolower((tcshuc) (c)))
188#   define Toupper(c) 	(((Char)(c) & QUOTE) ? 0 : toupper((tcshuc) (c)))
189#   define Isxdigit(c)	(((Char)(c) & QUOTE) ? 0 : isxdigit((tcshuc) (c)))
190#   define Isalnum(c)	(((Char)(c) & QUOTE) ? 0 : isalnum((tcshuc) (c)))
191#if defined(DSPMBYTE)
192#   define IscntrlM(c) 	(((Char)(c) & QUOTE) ? 0 : iscntrl((tcshuc) (c)))
193#   define Iscntrl(c)	( (IscntrlM(c)) && !(_enable_mbdisp&&(IsmbyteU((c)))) )
194#else
195#   define Iscntrl(c) 	(((Char)(c) & QUOTE) ? 0 : iscntrl((tcshuc) (c)))
196#endif /* !defined(DSPMBYTE) */
197#   if SOLARIS2 == 24
198    /*
199     * From <casper@fwi.uva.nl> Casper Dik:
200     * In Solaris 2.4, isprint('\t') returns true after setlocal(LC_ALL,"").
201     * This breaks commandline editing when you include tabs.
202     * (This is in the en_US locale).
203     */
204#if defined(DSPMBYTE)
205#    define IsprintM(c) 	(((Char)(c) & QUOTE) ? 0 : \
206				(isprint((tcshuc) (c)) && (c) != '\t'))
207#else
208#    define Isprint(c) 	(((Char)(c) & QUOTE) ? 0 : \
209				(isprint((tcshuc) (c)) && (c) != '\t'))
210#endif /* !defined(DSPMBYTE) */
211#   else
212#if defined(DSPMBYTE)
213#    define IsprintM(c) (((Char)(c) & QUOTE) ? 0 : isprint((tcshuc) (c)))
214#else
215#    define Isprint(c) 	(((Char)(c) & QUOTE) ? 0 : isprint((tcshuc) (c)))
216#endif /* !defined(DSPMBYTE) */
217#   endif /* SOLARIS2 == 24 */
218#if defined(DSPMBYTE)
219#   define Isprint(c)	( (IsprintM(c)) || (_enable_mbdisp&&(IsmbyteU((c)))) )
220#endif /* !defined(DSPMBYTE) */
221#    define Ispunct(c) 	(((Char)(c) & QUOTE) ? 0 : ispunct((tcshuc) (c)))
222#  else /* WINNT_NATIVE */
223#   define Isspace(c) (((Char)(c) & QUOTE) ? 0 : isspace( oem_it((tcshuc)(c))))
224#   define Isdigit(c) (((Char)(c) & QUOTE) ? 0 : isdigit( oem_it((tcshuc)(c))))
225#   define Isalpha(c) (((Char)(c) & QUOTE) ? 0 : isalpha( oem_it((tcshuc)(c))))
226#   define Islower(c) (((Char)(c) & QUOTE) ? 0 : islower( oem_it((tcshuc)(c))))
227#   define Isupper(c) (((Char)(c) & QUOTE) ? 0 : isupper( oem_it((tcshuc)(c))))
228#   define Tolower(c) (((Char)(c) & QUOTE) ? 0 : tolower( oem_it((tcshuc)(c))))
229#   define Toupper(c) (((Char)(c) & QUOTE) ? 0 : toupper( oem_it((tcshuc)(c))))
230#   define Isxdigit(c)(((Char)(c) & QUOTE) ? 0 : isxdigit(oem_it((tcshuc)(c))))
231#   define Isalnum(c) (((Char)(c) & QUOTE) ? 0 : isalnum( oem_it((tcshuc)(c))))
232#   define Ispunct(c) (((Char)(c) & QUOTE) ? 0 : ispunct( oem_it((tcshuc)(c))))
233#if defined(DSPMBYTE)
234#   define IscntrlM(c) (((Char)(c) & QUOTE) ? 0 : iscntrl( oem_it((tcshuc)(c))))
235#   define Iscntrl(c)	( (IscntrlM(c)) && !(_enable_mbdisp&&(IsmbyteU((c)))) )
236#   define IsprintM(c) (((Char)(c) & QUOTE) ? 0 : isprint( oem_it((tcshuc)(c))))
237#   define Isprint(c)	( (IsprintM(c)) || (_enable_mbdisp&&(IsmbyteU((c)))) )
238#else
239#   define Iscntrl(c) (((Char)(c) & QUOTE) ? 0 : iscntrl( oem_it((tcshuc)(c))))
240#   define Isprint(c) (((Char)(c) & QUOTE) ? 0 : isprint( oem_it((tcshuc)(c))))
241#endif /* !defined(DSPMBYTE) */
242#  endif /* WINNT_NATIVE */
243# endif /* !NeXT */
244#else /* !NLS */
245# define Isspace(c)	cmap(c, _SP|_NL)
246# define Isdigit(c)	cmap(c, _DIG)
247# define Isalpha(c)	(cmap(c,_LET) && !(((c) & META) && AsciiOnly))
248# define Islower(c)	(cmap(c,_DOW) && !(((c) & META) && AsciiOnly))
249# define Isupper(c)	(cmap(c, _UP) && !(((c) & META) && AsciiOnly))
250# define Tolower(c)	(_cmap_lower[ASC(c)])
251# define Toupper(c)	(_cmap_upper[ASC(c)])
252# define Isxdigit(c)	cmap(c, _XD)
253# define Isalnum(c)	(cmap(c, _DIG|_LET) && !(((Char)(c) & META) && AsciiOnly))
254#if defined(DSPMBYTE)
255# define IscntrlM(c)	(cmap(c,_CTR) && !(((c) & META) && AsciiOnly))
256# define Iscntrl(c)	( (IscntrlM(c)) && !(_enable_mbdisp&&(IsmbyteU((c)))) )
257# define IsprintM(c)	(!cmap(c,_CTR) && !(((c) & META) && AsciiOnly))
258# define Isprint(c)	( (IsprintM(c)) || (_enable_mbdisp&&(IsmbyteU((c)))) )
259#else
260# define Iscntrl(c)	(cmap(c,_CTR) && !(((c) & META) && AsciiOnly))
261# define Isprint(c)	(!cmap(c,_CTR) && !(((c) & META) && AsciiOnly))
262#endif /* !defined(DSPMBYTE) */
263# define Ispunct(c)	(cmap(c,_PUN) && !(((c) & META) && AsciiOnly))
264
265#endif /* !NLS */
266
267#if defined (SHORT_STRINGS) && defined (NLS)
268# define Iswcntrl(c) 	(((c) & QUOTE) ? 0 : iswcntrl(c))
269# define Iswprint(c) 	(((c) & QUOTE) ? 0 : iswprint(c))
270#else
271# define Iswcntrl(c) 	Iscntrl(c)
272# define Iswprint(c) 	Isprint(c)
273#endif
274
275#if defined(DSPMBYTE)
276# define Ismbyte1(c)	((_mbmap[(c) & 0377] & _MB1) ? 1 : 0)
277# define Ismbyte2(c)	((_mbmap[(c) & 0377] & _MB2) ? 1 : 0)
278#endif
279
280#endif /* _h_sh_char */
281