1231990Smp/* $Header: /p/tcsh/cvsroot/tcsh/tc.nls.c,v 3.23 2010/02/12 22:17:20 christos Exp $ */ 2145479Smp/* 3145479Smp * tc.nls.c: NLS handling 4145479Smp */ 5145479Smp/*- 6145479Smp * Copyright (c) 1980, 1991 The Regents of the University of California. 7145479Smp * All rights reserved. 8145479Smp * 9145479Smp * Redistribution and use in source and binary forms, with or without 10145479Smp * modification, are permitted provided that the following conditions 11145479Smp * are met: 12145479Smp * 1. Redistributions of source code must retain the above copyright 13145479Smp * notice, this list of conditions and the following disclaimer. 14145479Smp * 2. Redistributions in binary form must reproduce the above copyright 15145479Smp * notice, this list of conditions and the following disclaimer in the 16145479Smp * documentation and/or other materials provided with the distribution. 17145479Smp * 3. Neither the name of the University nor the names of its contributors 18145479Smp * may be used to endorse or promote products derived from this software 19145479Smp * without specific prior written permission. 20145479Smp * 21145479Smp * THIS SOFTWARE IS PROVIDED BY THE REGENTS AND CONTRIBUTORS ``AS IS'' AND 22145479Smp * ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE 23145479Smp * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE 24145479Smp * ARE DISCLAIMED. IN NO EVENT SHALL THE REGENTS OR CONTRIBUTORS BE LIABLE 25145479Smp * FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL 26145479Smp * DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS 27145479Smp * OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) 28145479Smp * HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT 29145479Smp * LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY 30145479Smp * OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF 31145479Smp * SUCH DAMAGE. 32145479Smp */ 33145479Smp#include "sh.h" 34145479Smp 35231990SmpRCSID("$tcsh: tc.nls.c,v 3.23 2010/02/12 22:17:20 christos Exp $") 36145479Smp 37231990Smp 38167465Smp#ifdef WIDE_STRINGS 39231990Smp# ifdef HAVE_WCWIDTH 40231990Smp# ifdef UTF16_STRINGS 41145479Smpint 42231990Smpxwcwidth (wint_t wchar) 43231990Smp{ 44231990Smp wchar_t ws[2]; 45231990Smp 46231990Smp if (wchar <= 0xffff) 47231990Smp return wcwidth ((wchar_t) wchar); 48231990Smp /* UTF-16 systems can't handle these values directly in calls to wcwidth. 49231990Smp However, they can handle them as surrogate pairs in calls to wcswidth. 50231990Smp What we do here is to convert UTF-32 values >= 0x10000 into surrogate 51231990Smp pairs and compute the width by calling wcswidth. */ 52231990Smp wchar -= 0x10000; 53231990Smp ws[0] = 0xd800 | (wchar >> 10); 54231990Smp ws[1] = 0xdc00 | (wchar & 0x3ff); 55231990Smp return wcswidth (ws, 2); 56231990Smp} 57231990Smp# else 58231990Smp#define xwcwidth wcwidth 59231990Smp# endif /* !UTF16_STRINGS */ 60231990Smp# endif /* HAVE_WCWIDTH */ 61231990Smp 62231990Smpint 63167465SmpNLSWidth(Char c) 64145479Smp{ 65145479Smp# ifdef HAVE_WCWIDTH 66167465Smp int l; 67167465Smp if (c & INVALID_BYTE) 68145479Smp return 1; 69231990Smp l = xwcwidth((wchar_t) c); 70145479Smp return l >= 0 ? l : 0; 71145479Smp# else 72167465Smp return iswprint(c) != 0; 73145479Smp# endif 74145479Smp} 75167465Smp 76167465Smpint 77167465SmpNLSStringWidth(const Char *s) 78167465Smp{ 79167465Smp int w = 0, l; 80167465Smp Char c; 81167465Smp 82167465Smp while (*s) { 83167465Smp c = *s++; 84167465Smp#ifdef HAVE_WCWIDTH 85231990Smp if ((l = xwcwidth((wchar_t) c)) < 0) 86167465Smp l = 2; 87167465Smp#else 88167465Smp l = iswprint(c) != 0; 89145479Smp#endif 90167465Smp w += l; 91167465Smp } 92167465Smp return w; 93167465Smp} 94167465Smp#endif 95145479Smp 96145479SmpChar * 97167465SmpNLSChangeCase(const Char *p, int mode) 98145479Smp{ 99167465Smp Char c, *n, c2 = 0; 100167465Smp const Char *op = p; 101167465Smp 102145479Smp for (; (c = *p) != 0; p++) { 103145479Smp if (mode == 0 && Islower(c)) { 104145479Smp c2 = Toupper(c); 105145479Smp break; 106145479Smp } else if (mode && Isupper(c)) { 107145479Smp c2 = Tolower(c); 108145479Smp break; 109145479Smp } 110145479Smp } 111145479Smp if (!*p) 112145479Smp return 0; 113145479Smp n = Strsave(op); 114145479Smp n[p - op] = c2; 115145479Smp return n; 116145479Smp} 117145479Smp 118145479Smpint 119167465SmpNLSClassify(Char c, int nocomb) 120145479Smp{ 121145479Smp int w; 122167465Smp if (c & INVALID_BYTE) 123145479Smp return NLSCLASS_ILLEGAL; 124145479Smp w = NLSWidth(c); 125167465Smp if ((w > 0 && !(Iscntrl(c) && (c & CHAR) < 0x100)) || (Isprint(c) && !nocomb)) 126145479Smp return w; 127167465Smp if (Iscntrl(c) && (c & CHAR) < 0x100) { 128145479Smp if (c == '\n') 129145479Smp return NLSCLASS_NL; 130145479Smp if (c == '\t') 131145479Smp return NLSCLASS_TAB; 132145479Smp return NLSCLASS_CTRL; 133145479Smp } 134167465Smp#ifdef WIDE_STRINGS 135145479Smp if (c >= 0x1000000) 136145479Smp return NLSCLASS_ILLEGAL4; 137145479Smp if (c >= 0x10000) 138145479Smp return NLSCLASS_ILLEGAL3; 139167465Smp#endif 140145479Smp if (c >= 0x100) 141145479Smp return NLSCLASS_ILLEGAL2; 142145479Smp return NLSCLASS_ILLEGAL; 143145479Smp} 144