1 /*- 2 * SPDX-License-Identifier: BSD-3-Clause 3 * 4 * Copyright (c) 1980, 1993 5 * The Regents of the University of California. All rights reserved. 6 * 7 * Redistribution and use in source and binary forms, with or without 8 * modification, are permitted provided that the following conditions 9 * are met: 10 * 1. Redistributions of source code must retain the above copyright 11 * notice, this list of conditions and the following disclaimer. 12 * 2. Redistributions in binary form must reproduce the above copyright 13 * notice, this list of conditions and the following disclaimer in the 14 * documentation and/or other materials provided with the distribution. 15 * 3. Neither the name of the University nor the names of its contributors 16 * may be used to endorse or promote products derived from this software 17 * without specific prior written permission. 18 * 19 * THIS SOFTWARE IS PROVIDED BY THE REGENTS AND CONTRIBUTORS ``AS IS'' AND 20 * ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE 21 * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE 22 * ARE DISCLAIMED. IN NO EVENT SHALL THE REGENTS OR CONTRIBUTORS BE LIABLE 23 * FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL 24 * DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS 25 * OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) 26 * HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT 27 * LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY 28 * OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF 29 * SUCH DAMAGE. 30 */ 31 32 33 #ifndef lint 34 static const char copyright[] = 35 "@(#) Copyright (c) 1980, 1993\n\ 36 The Regents of the University of California. All rights reserved.\n"; 37 #endif 38 39 #ifndef lint 40 static const char sccsid[] = "@(#)unexpand.c 8.1 (Berkeley) 6/6/93"; 41 #endif 42 43 /* 44 * unexpand - put tabs into a file replacing blanks 45 */ 46 #include <ctype.h> 47 #include <err.h> 48 #include <limits.h> 49 #include <locale.h> 50 #include <stdio.h> 51 #include <stdlib.h> 52 #include <string.h> 53 #include <unistd.h> 54 #include <wchar.h> 55 #include <wctype.h> 56 57 static int all; 58 static int nstops; 59 static int tabstops[100]; 60 61 static void getstops(const char *); 62 static void usage(void) __dead2; 63 static int tabify(const char *); 64 65 int 66 main(int argc, char *argv[]) 67 { 68 int ch, failed; 69 char *filename; 70 71 setlocale(LC_CTYPE, ""); 72 73 nstops = 1; 74 tabstops[0] = 8; 75 while ((ch = getopt(argc, argv, "at:")) != -1) { 76 switch (ch) { 77 case 'a': /* Un-expand all spaces, not just leading. */ 78 all = 1; 79 break; 80 case 't': /* Specify tab list, implies -a. */ 81 getstops(optarg); 82 all = 1; 83 break; 84 default: 85 usage(); 86 /*NOTREACHED*/ 87 } 88 } 89 argc -= optind; 90 argv += optind; 91 92 failed = 0; 93 if (argc == 0) 94 failed |= tabify("stdin"); 95 else { 96 while ((filename = *argv++) != NULL) { 97 if (freopen(filename, "r", stdin) == NULL) { 98 warn("%s", filename); 99 failed = 1; 100 } else 101 failed |= tabify(filename); 102 } 103 } 104 exit(failed != 0); 105 } 106 107 static void 108 usage(void) 109 { 110 fprintf(stderr, "usage: unexpand [-a | -t tablist] [file ...]\n"); 111 exit(1); 112 } 113 114 static int 115 tabify(const char *curfile) 116 { 117 int dcol, doneline, limit, n, ocol, width; 118 wint_t ch; 119 120 limit = nstops == 1 ? INT_MAX : tabstops[nstops - 1] - 1; 121 122 doneline = ocol = dcol = 0; 123 while ((ch = getwchar()) != WEOF) { 124 if (ch == ' ' && !doneline) { 125 if (++dcol >= limit) 126 doneline = 1; 127 continue; 128 } else if (ch == '\t') { 129 if (nstops == 1) { 130 dcol = (1 + dcol / tabstops[0]) * 131 tabstops[0]; 132 continue; 133 } else { 134 for (n = 0; n < nstops && 135 tabstops[n] - 1 < dcol; n++) 136 ; 137 if (n < nstops - 1 && tabstops[n] - 1 < limit) { 138 dcol = tabstops[n]; 139 continue; 140 } 141 doneline = 1; 142 } 143 } 144 145 /* Output maximal number of tabs. */ 146 if (nstops == 1) { 147 while (((ocol + tabstops[0]) / tabstops[0]) 148 <= (dcol / tabstops[0])) { 149 if (dcol - ocol < 2) 150 break; 151 putwchar('\t'); 152 ocol = (1 + ocol / tabstops[0]) * 153 tabstops[0]; 154 } 155 } else { 156 for (n = 0; n < nstops && tabstops[n] - 1 < ocol; n++) 157 ; 158 while (ocol < dcol && n < nstops && ocol < limit) { 159 putwchar('\t'); 160 ocol = tabstops[n++]; 161 } 162 } 163 164 /* Then spaces. */ 165 while (ocol < dcol && ocol < limit) { 166 putwchar(' '); 167 ocol++; 168 } 169 170 if (ch == '\b') { 171 putwchar('\b'); 172 if (ocol > 0) 173 ocol--, dcol--; 174 } else if (ch == '\n') { 175 putwchar('\n'); 176 doneline = ocol = dcol = 0; 177 continue; 178 } else if (ch != ' ' || dcol > limit) { 179 putwchar(ch); 180 if ((width = wcwidth(ch)) > 0) 181 ocol += width, dcol += width; 182 } 183 184 /* 185 * Only processing leading blanks or we've gone past the 186 * last tab stop. Emit remainder of this line unchanged. 187 */ 188 if (!all || dcol >= limit) { 189 while ((ch = getwchar()) != '\n' && ch != WEOF) 190 putwchar(ch); 191 if (ch == '\n') 192 putwchar('\n'); 193 doneline = ocol = dcol = 0; 194 } 195 } 196 if (ferror(stdin)) { 197 warn("%s", curfile); 198 return (1); 199 } 200 return (0); 201 } 202 203 static void 204 getstops(const char *cp) 205 { 206 int i; 207 208 nstops = 0; 209 for (;;) { 210 i = 0; 211 while (*cp >= '0' && *cp <= '9') 212 i = i * 10 + *cp++ - '0'; 213 if (i <= 0) 214 errx(1, "bad tab stop spec"); 215 if (nstops > 0 && i <= tabstops[nstops-1]) 216 errx(1, "bad tab stop spec"); 217 if (nstops == sizeof(tabstops) / sizeof(*tabstops)) 218 errx(1, "too many tab stops"); 219 tabstops[nstops++] = i; 220 if (*cp == 0) 221 break; 222 if (*cp != ',' && !isblank((unsigned char)*cp)) 223 errx(1, "bad tab stop spec"); 224 cp++; 225 } 226 } 227