1 /*
2 * unbwt.c for libdivsufsort
3 * Copyright (c) 2003-2008 Yuta Mori All Rights Reserved.
4 *
5 * Permission is hereby granted, free of charge, to any person
6 * obtaining a copy of this software and associated documentation
7 * files (the "Software"), to deal in the Software without
8 * restriction, including without limitation the rights to use,
9 * copy, modify, merge, publish, distribute, sublicense, and/or sell
10 * copies of the Software, and to permit persons to whom the
11 * Software is furnished to do so, subject to the following
12 * conditions:
13 *
14 * The above copyright notice and this permission notice shall be
15 * included in all copies or substantial portions of the Software.
16 *
17 * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
18 * EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES
19 * OF MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
20 * NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT
21 * HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY,
22 * WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING
23 * FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
24 * OTHER DEALINGS IN THE SOFTWARE.
25 */
26
27 #if HAVE_CONFIG_H
28 # include "config.h"
29 #endif
30 #include <stdio.h>
31 #if HAVE_STRING_H
32 # include <string.h>
33 #endif
34 #if HAVE_STDLIB_H
35 # include <stdlib.h>
36 #endif
37 #if HAVE_MEMORY_H
38 # include <memory.h>
39 #endif
40 #if HAVE_STDDEF_H
41 # include <stddef.h>
42 #endif
43 #if HAVE_STRINGS_H
44 # include <strings.h>
45 #endif
46 #if HAVE_SYS_TYPES_H
47 # include <sys/types.h>
48 #endif
49 #if HAVE_IO_H && HAVE_FCNTL_H
50 # include <io.h>
51 # include <fcntl.h>
52 #endif
53 #include <time.h>
54 #include <divsufsort.h>
55 #include "lfs.h"
56
57
58 static
59 size_t
read_int(FILE * fp,saidx_t * n)60 read_int(FILE *fp, saidx_t *n) {
61 unsigned char c[4];
62 size_t m = fread(c, sizeof(unsigned char), 4, fp);
63 if(m == 4) {
64 *n = (c[0] << 0) | (c[1] << 8) |
65 (c[2] << 16) | (c[3] << 24);
66 }
67 return m;
68 }
69
70 static
71 void
print_help(const char * progname,int status)72 print_help(const char *progname, int status) {
73 fprintf(stderr,
74 "unbwt, an inverse burrows-wheeler transform program, version %s.\n",
75 divsufsort_version());
76 fprintf(stderr, "usage: %s INFILE OUTFILE\n\n", progname);
77 exit(status);
78 }
79
80 int
main(int argc,const char * argv[])81 main(int argc, const char *argv[]) {
82 FILE *fp, *ofp;
83 const char *fname, *ofname;
84 sauchar_t *T;
85 saidx_t *A;
86 LFS_OFF_T n;
87 size_t m;
88 saidx_t pidx;
89 clock_t start, finish;
90 saint_t err, blocksize, needclose = 3;
91
92 /* Check arguments. */
93 if((argc == 1) ||
94 (strcmp(argv[1], "-h") == 0) ||
95 (strcmp(argv[1], "--help") == 0)) { print_help(argv[0], EXIT_SUCCESS); }
96 if(argc != 3) { print_help(argv[0], EXIT_FAILURE); }
97
98 /* Open a file for reading. */
99 if(strcmp(argv[1], "-") != 0) {
100 #if HAVE_FOPEN_S
101 if(fopen_s(&fp, fname = argv[1], "rb") != 0) {
102 #else
103 if((fp = LFS_FOPEN(fname = argv[1], "rb")) == NULL) {
104 #endif
105 fprintf(stderr, "%s: Cannot open file `%s': ", argv[0], fname);
106 perror(NULL);
107 exit(EXIT_FAILURE);
108 }
109 } else {
110 #if HAVE__SETMODE && HAVE__FILENO
111 if(_setmode(_fileno(stdin), _O_BINARY) == -1) {
112 fprintf(stderr, "%s: Cannot set mode: ", argv[0]);
113 perror(NULL);
114 exit(EXIT_FAILURE);
115 }
116 #endif
117 fp = stdin;
118 fname = "stdin";
119 needclose ^= 1;
120 }
121
122 /* Open a file for writing. */
123 if(strcmp(argv[2], "-") != 0) {
124 #if HAVE_FOPEN_S
125 if(fopen_s(&ofp, ofname = argv[2], "wb") != 0) {
126 #else
127 if((ofp = LFS_FOPEN(ofname = argv[2], "wb")) == NULL) {
128 #endif
129 fprintf(stderr, "%s: Cannot open file `%s': ", argv[0], ofname);
130 perror(NULL);
131 exit(EXIT_FAILURE);
132 }
133 } else {
134 #if HAVE__SETMODE && HAVE__FILENO
135 if(_setmode(_fileno(stdout), _O_BINARY) == -1) {
136 fprintf(stderr, "%s: Cannot set mode: ", argv[0]);
137 perror(NULL);
138 exit(EXIT_FAILURE);
139 }
140 #endif
141 ofp = stdout;
142 ofname = "stdout";
143 needclose ^= 2;
144 }
145
146 /* Read the blocksize. */
147 if(read_int(fp, &blocksize) != 4) {
148 fprintf(stderr, "%s: Cannot read from `%s': ", argv[0], fname);
149 perror(NULL);
150 exit(EXIT_FAILURE);
151 }
152
153 /* Allocate 5blocksize bytes of memory. */
154 T = (sauchar_t *)malloc(blocksize * sizeof(sauchar_t));
155 A = (saidx_t *)malloc(blocksize * sizeof(saidx_t));
156 if((T == NULL) || (A == NULL)) {
157 fprintf(stderr, "%s: Cannot allocate memory.\n", argv[0]);
158 exit(EXIT_FAILURE);
159 }
160
161 fprintf(stderr, "UnBWT (blocksize %" PRIdSAINT_T ") ... ", blocksize);
162 start = clock();
163 for(n = 0; (m = read_int(fp, &pidx)) != 0; n += m) {
164 /* Read blocksize bytes of data. */
165 if((m != 4) || ((m = fread(T, sizeof(sauchar_t), blocksize, fp)) == 0)) {
166 fprintf(stderr, "%s: %s `%s': ",
167 argv[0],
168 (ferror(fp) || !feof(fp)) ? "Cannot read from" : "Unexpected EOF in",
169 fname);
170 perror(NULL);
171 exit(EXIT_FAILURE);
172 }
173
174 /* Inverse Burrows-Wheeler Transform. */
175 if((err = inverse_bw_transform(T, T, A, m, pidx)) != 0) {
176 fprintf(stderr, "%s (reverseBWT): %s.\n",
177 argv[0],
178 (err == -1) ? "Invalid data" : "Cannot allocate memory");
179 exit(EXIT_FAILURE);
180 }
181
182 /* Write m bytes of data. */
183 if(fwrite(T, sizeof(sauchar_t), m, ofp) != m) {
184 fprintf(stderr, "%s: Cannot write to `%s': ", argv[0], ofname);
185 perror(NULL);
186 exit(EXIT_FAILURE);
187 }
188 }
189 if(ferror(fp)) {
190 fprintf(stderr, "%s: Cannot read from `%s': ", argv[0], fname);
191 perror(NULL);
192 exit(EXIT_FAILURE);
193 }
194 finish = clock();
195 fprintf(stderr, "%" PRIdOFF_T " bytes: %.4f sec\n",
196 n, (double)(finish - start) / (double)CLOCKS_PER_SEC);
197
198 /* Close files */
199 if(needclose & 1) { fclose(fp); }
200 if(needclose & 2) { fclose(ofp); }
201
202 /* Deallocate memory. */
203 free(A);
204 free(T);
205
206 return 0;
207 }
208