Annotation of src/usr.bin/tr/str.c, Revision 1.1.1.1
1.1 deraadt 1: /* $NetBSD: str.c,v 1.7 1995/08/31 22:13:47 jtc Exp $ */
2:
3: /*-
4: * Copyright (c) 1991, 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. All advertising materials mentioning features or use of this software
16: * must display the following acknowledgement:
17: * This product includes software developed by the University of
18: * California, Berkeley and its contributors.
19: * 4. Neither the name of the University nor the names of its contributors
20: * may be used to endorse or promote products derived from this software
21: * without specific prior written permission.
22: *
23: * THIS SOFTWARE IS PROVIDED BY THE REGENTS AND CONTRIBUTORS ``AS IS'' AND
24: * ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
25: * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
26: * ARE DISCLAIMED. IN NO EVENT SHALL THE REGENTS OR CONTRIBUTORS BE LIABLE
27: * FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL
28: * DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS
29: * OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION)
30: * HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT
31: * LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY
32: * OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF
33: * SUCH DAMAGE.
34: */
35:
36: #ifndef lint
37: #if 0
38: static char sccsid[] = "@(#)str.c 8.2 (Berkeley) 4/28/95";
39: #endif
40: static char rcsid[] = "$NetBSD: str.c,v 1.7 1995/08/31 22:13:47 jtc Exp $";
41: #endif /* not lint */
42:
43: #include <sys/cdefs.h>
44: #include <sys/types.h>
45:
46: #include <errno.h>
47: #include <stddef.h>
48: #include <stdio.h>
49: #include <stdlib.h>
50: #include <string.h>
51: #include <ctype.h>
52:
53: #include "extern.h"
54:
55: static int backslash __P((STR *));
56: static int bracket __P((STR *));
57: static int c_class __P((const void *, const void *));
58: static void genclass __P((STR *));
59: static void genequiv __P((STR *));
60: static int genrange __P((STR *));
61: static void genseq __P((STR *));
62:
63: int
64: next(s)
65: register STR *s;
66: {
67: register int ch;
68:
69: switch (s->state) {
70: case EOS:
71: return (0);
72: case INFINITE:
73: return (1);
74: case NORMAL:
75: switch (ch = *s->str) {
76: case '\0':
77: s->state = EOS;
78: return (0);
79: case '\\':
80: s->lastch = backslash(s);
81: break;
82: case '[':
83: if (bracket(s))
84: return (next(s));
85: /* FALLTHROUGH */
86: default:
87: ++s->str;
88: s->lastch = ch;
89: break;
90: }
91:
92: /* We can start a range at any time. */
93: if (s->str[0] == '-' && genrange(s))
94: return (next(s));
95: return (1);
96: case RANGE:
97: if (s->cnt-- == 0) {
98: s->state = NORMAL;
99: return (next(s));
100: }
101: ++s->lastch;
102: return (1);
103: case SEQUENCE:
104: if (s->cnt-- == 0) {
105: s->state = NORMAL;
106: return (next(s));
107: }
108: return (1);
109: case SET:
110: if ((s->lastch = s->set[s->cnt++]) == OOBCH) {
111: s->state = NORMAL;
112: return (next(s));
113: }
114: return (1);
115: }
116: /* NOTREACHED */
117: }
118:
119: static int
120: bracket(s)
121: register STR *s;
122: {
123: register char *p;
124:
125: switch (s->str[1]) {
126: case ':': /* "[:class:]" */
127: if ((p = strstr(s->str + 2, ":]")) == NULL)
128: return (0);
129: *p = '\0';
130: s->str += 2;
131: genclass(s);
132: s->str = p + 2;
133: return (1);
134: case '=': /* "[=equiv=]" */
135: if ((p = strstr(s->str + 2, "=]")) == NULL)
136: return (0);
137: s->str += 2;
138: genequiv(s);
139: return (1);
140: default: /* "[\###*n]" or "[#*n]" */
141: if ((p = strpbrk(s->str + 2, "*]")) == NULL)
142: return (0);
143: if (p[0] != '*' || index(p, ']') == NULL)
144: return (0);
145: s->str += 1;
146: genseq(s);
147: return (1);
148: }
149: /* NOTREACHED */
150: }
151:
152: typedef struct {
153: char *name;
154: int (*func) __P((int));
155: int *set;
156: } CLASS;
157:
158: static CLASS classes[] = {
159: { "alnum", isalnum, },
160: { "alpha", isalpha, },
161: { "blank", isblank, },
162: { "cntrl", iscntrl, },
163: { "digit", isdigit, },
164: { "graph", isgraph, },
165: { "lower", islower, },
166: { "print", isupper, },
167: { "punct", ispunct, },
168: { "space", isspace, },
169: { "upper", isupper, },
170: { "xdigit", isxdigit, },
171: };
172:
173: static void
174: genclass(s)
175: STR *s;
176: {
177: register int cnt, (*func) __P((int));
178: CLASS *cp, tmp;
179: int *p;
180:
181: tmp.name = s->str;
182: if ((cp = (CLASS *)bsearch(&tmp, classes, sizeof(classes) /
183: sizeof(CLASS), sizeof(CLASS), c_class)) == NULL)
184: err("unknown class %s", s->str);
185:
186: if ((cp->set = p = malloc((NCHARS + 1) * sizeof(int))) == NULL)
187: err("%s", strerror(errno));
188: bzero(p, (NCHARS + 1) * sizeof(int));
189: for (cnt = 0, func = cp->func; cnt < NCHARS; ++cnt)
190: if ((func)(cnt))
191: *p++ = cnt;
192: *p = OOBCH;
193:
194: s->cnt = 0;
195: s->state = SET;
196: s->set = cp->set;
197: }
198:
199: static int
200: c_class(a, b)
201: const void *a, *b;
202: {
203: return (strcmp(((CLASS *)a)->name, ((CLASS *)b)->name));
204: }
205:
206: /*
207: * English doesn't have any equivalence classes, so for now
208: * we just syntax check and grab the character.
209: */
210: static void
211: genequiv(s)
212: STR *s;
213: {
214: if (*s->str == '\\') {
215: s->equiv[0] = backslash(s);
216: if (*s->str != '=')
217: err("misplaced equivalence equals sign");
218: } else {
219: s->equiv[0] = s->str[0];
220: if (s->str[1] != '=')
221: err("misplaced equivalence equals sign");
222: }
223: s->str += 2;
224: s->cnt = 0;
225: s->state = SET;
226: s->set = s->equiv;
227: }
228:
229: static int
230: genrange(s)
231: STR *s;
232: {
233: int stopval;
234: char *savestart;
235:
236: savestart = s->str;
237: stopval = *++s->str == '\\' ? backslash(s) : *s->str++;
238: if (stopval < (u_char)s->lastch) {
239: s->str = savestart;
240: return (0);
241: }
242: s->cnt = stopval - s->lastch + 1;
243: s->state = RANGE;
244: --s->lastch;
245: return (1);
246: }
247:
248: static void
249: genseq(s)
250: STR *s;
251: {
252: char *ep;
253:
254: if (s->which == STRING1)
255: err("sequences only valid in string2");
256:
257: if (*s->str == '\\')
258: s->lastch = backslash(s);
259: else
260: s->lastch = *s->str++;
261: if (*s->str != '*')
262: err("misplaced sequence asterisk");
263:
264: switch (*++s->str) {
265: case '\\':
266: s->cnt = backslash(s);
267: break;
268: case ']':
269: s->cnt = 0;
270: ++s->str;
271: break;
272: default:
273: if (isdigit(*s->str)) {
274: s->cnt = strtol(s->str, &ep, 0);
275: if (*ep == ']') {
276: s->str = ep + 1;
277: break;
278: }
279: }
280: err("illegal sequence count");
281: /* NOTREACHED */
282: }
283:
284: s->state = s->cnt ? SEQUENCE : INFINITE;
285: }
286:
287: /*
288: * Translate \??? into a character. Up to 3 octal digits, if no digits either
289: * an escape code or a literal character.
290: */
291: static int
292: backslash(s)
293: register STR *s;
294: {
295: register int ch, cnt, val;
296:
297: for (cnt = val = 0;;) {
298: ch = *++s->str;
299: if (!isascii(ch) || !isdigit(ch))
300: break;
301: val = val * 8 + ch - '0';
302: if (++cnt == 3) {
303: ++s->str;
304: break;
305: }
306: }
307: if (cnt)
308: return (val);
309: if (ch != '\0')
310: ++s->str;
311: switch (ch) {
312: case 'a': /* escape characters */
313: return ('\7');
314: case 'b':
315: return ('\b');
316: case 'f':
317: return ('\f');
318: case 'n':
319: return ('\n');
320: case 'r':
321: return ('\r');
322: case 't':
323: return ('\t');
324: case 'v':
325: return ('\13');
326: case '\0': /* \" -> \ */
327: s->state = EOS;
328: return ('\\');
329: default: /* \x" -> x */
330: return (ch);
331: }
332: }