Annotation of src/usr.bin/sort/append.c, Revision 1.9
1.9 ! deraadt 1: /* $OpenBSD: append.c,v 1.8 2003/06/03 02:56:16 millert Exp $ */
1.1 millert 2:
3: /*-
4: * Copyright (c) 1993
5: * The Regents of the University of California. All rights reserved.
6: *
7: * This code is derived from software contributed to Berkeley by
8: * Peter McIlroy.
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.
1.8 millert 18: * 3. Neither the name of the University nor the names of its contributors
1.1 millert 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:
35: #ifndef lint
36: #if 0
37: static char sccsid[] = "@(#)append.c 8.1 (Berkeley) 6/6/93";
38: #else
1.9 ! deraadt 39: static char rcsid[] = "$OpenBSD: append.c,v 1.8 2003/06/03 02:56:16 millert Exp $";
1.1 millert 40: #endif
41: #endif /* not lint */
42:
43: #include "sort.h"
44:
45: #include <stdlib.h>
46: #include <string.h>
47:
48: #define OUTPUT { \
49: if ((n = cpos - ppos) > 1) { \
50: for (; ppos < cpos; ++ppos) \
51: *ppos -= odepth; \
52: ppos -= n; \
53: radixsort((const u_char **)ppos, n, wts1, REC_D); \
54: for (; ppos < cpos; ppos++) { \
55: prec = (RECHEADER *) (*ppos - sizeof(TRECHEADER));\
56: put(prec, fp); \
57: } \
1.2 millert 58: } else \
59: put(prec, fp); \
1.1 millert 60: }
61:
62: /*
63: * copy sorted lines to output; check for uniqueness
64: */
65: void
1.9 ! deraadt 66: append(u_char **keylist, int nelem, int depth, FILE *fp,
! 67: void (*put)(RECHEADER *, FILE *), struct field *ftbl)
1.1 millert 68: {
1.6 ericj 69: u_char *wts, *wts1;
70: int n, odepth;
71: u_char **cpos, **ppos, **lastkey;
72: u_char *cend, *pend, *start;
73: RECHEADER *crec, *prec;
1.1 millert 74:
1.7 millert 75: if (*keylist == NULL)
1.1 millert 76: return;
77: wts1 = wts = ftbl[0].weights;
78: if ((!UNIQUE) && SINGL_FLD) {
79: if (ftbl[0].flags & F && ftbl[0].flags & R)
80: wts1 = Rascii;
81: else if (ftbl[0].flags & F)
82: wts1 = ascii;
83: odepth = depth;
84: }
85: lastkey = keylist + nelem;
86: depth += sizeof(TRECHEADER);
87: if (SINGL_FLD && (UNIQUE || wts1 != wts)) {
88: ppos = keylist;
89: prec = (RECHEADER *) (*ppos - depth);
90: if (UNIQUE)
91: put(prec, fp);
1.6 ericj 92: for (cpos = &keylist[1]; cpos < lastkey; cpos++) {
1.1 millert 93: crec = (RECHEADER *) (*cpos - depth);
94: if (crec->length == prec->length) {
1.6 ericj 95: /*
96: * Set pend and cend so that trailing NUL and
97: * record separator is ignored.
98: */
99: pend = (u_char *)&prec->data + prec->length - 2;
100: cend = (u_char *)&crec->data + crec->length - 2;
1.1 millert 101: for (start = *cpos; cend >= start; cend--) {
102: if (wts[*cend] != wts[*pend])
103: break;
104: pend--;
105: }
106: if (pend + 1 != *ppos) {
1.2 millert 107: if (!UNIQUE)
108: OUTPUT
109: else
1.1 millert 110: put(crec, fp);
111: ppos = cpos;
112: prec = crec;
113: }
114: } else {
1.2 millert 115: if (!UNIQUE)
116: OUTPUT
117: else
1.1 millert 118: put(crec, fp);
119: ppos = cpos;
120: prec = crec;
121: }
122: }
1.2 millert 123: if (!UNIQUE)
1.4 mickey 124: OUTPUT
1.1 millert 125: } else if (UNIQUE) {
126: ppos = keylist;
127: prec = (RECHEADER *) (*ppos - depth);
128: put(prec, fp);
1.6 ericj 129: for (cpos = &keylist[1]; cpos < lastkey; cpos++) {
1.1 millert 130: crec = (RECHEADER *) (*cpos - depth);
131: if (crec->offset == prec->offset) {
1.6 ericj 132: /*
133: * Set pend and cend so that trailing NUL and
134: * record separator is ignored.
135: */
136: pend = (u_char *)&prec->data + prec->offset - 2;
137: cend = (u_char *)&crec->data + crec->offset - 2;
1.1 millert 138: for (start = *cpos; cend >= start; cend--) {
139: if (wts[*cend] != wts[*pend])
140: break;
141: pend--;
142: }
143: if (pend + 1 != *ppos) {
144: ppos = cpos;
145: prec = crec;
146: put(prec, fp);
147: }
148: } else {
149: ppos = cpos;
150: prec = crec;
151: put(prec, fp);
152: }
153: }
154: } else for (cpos = keylist; cpos < lastkey; cpos++) {
155: crec = (RECHEADER *) (*cpos - depth);
156: put(crec, fp);
157: }
158: }
159:
160: /*
161: * output the already sorted eol bin.
162: */
163: void
1.9 ! deraadt 164: rd_append(int binno, union f_handle infl0, int nfiles, FILE *outfp,
! 165: u_char *buffer, u_char *bufend)
1.1 millert 166: {
1.3 millert 167: RECHEADER *rec;
1.2 millert 168:
1.1 millert 169: rec = (RECHEADER *) buffer;
170: if (!getnext(binno, infl0, nfiles, (RECHEADER *) buffer, bufend, 0)) {
171: putline(rec, outfp);
172: while (getnext(binno, infl0, nfiles, (RECHEADER *) buffer,
173: bufend, 0) == 0) {
174: if (!UNIQUE)
175: putline(rec, outfp);
176: }
177: }
178: }
179:
180: /*
181: * append plain text--used after sorting the biggest bin.
182: */
183: void
1.9 ! deraadt 184: concat(FILE *a, FILE *b)
1.1 millert 185: {
186: int nread;
187: char buffer[4096];
188:
189: rewind(b);
190: while ((nread = fread(buffer, 1, 4096, b)) > 0)
191: EWRITE(buffer, 1, nread, a);
192: }