comparison: src/bfile_heuristics.c
src/bfile_heuristics.c
- changeset 34
- fa9bda32de17
- parent 23
- 778388400f7b
- child 36
- a7ff583e153f
equal
deleted
inserted
replaced
| 33:1a2d7298bc82 | 34:fa9bda32de17 |
|---|---|
| 1 /* | |
| 2 * DO NOT ALTER OR REMOVE COPYRIGHT NOTICES OR THIS HEADER. | |
| 3 * Copyright 2011 Mike Becker. All rights reserved. | |
| 4 * | |
| 5 * Redistribution and use in source and binary forms, with or without | |
| 6 * modification, are permitted provided that the following conditions are met: | |
| 7 * | |
| 8 * 1. Redistributions of source code must retain the above copyright | |
| 9 * notice, this list of conditions and the following disclaimer. | |
| 10 * | |
| 11 * 2. Redistributions in binary form must reproduce the above copyright | |
| 12 * notice, this list of conditions and the following disclaimer in the | |
| 13 * documentation and/or other materials provided with the distribution. | |
| 14 * | |
| 15 * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS" | |
| 16 * AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE | |
| 17 * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE | |
| 18 * DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT HOLDER OR CONTRIBUTORS BE LIABLE | |
| 19 * FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL | |
| 20 * DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR | |
| 21 * SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER | |
| 22 * CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, | |
| 23 * OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE | |
| 24 * OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE. | |
| 25 * | |
| 26 * bfile_heuristics.c | |
| 27 * | |
| 28 * Created on: 20.10.2011 | |
| 29 * Author: Mike | |
| 30 */ | |
| 31 | |
| 32 #include "bfile_heuristics.h" | |
| 33 #include <ctype.h> | |
| 34 | |
| 35 bfile_heuristics_t *new_bfile_heuristics_t() { | |
| 36 bfile_heuristics_t *ret = malloc(sizeof(bfile_heuristics_t)); | |
| 37 ret->level = BFILE_MEDIUM_ACCURACY; | |
| 38 bfile_reset(ret); | |
| 39 return ret; | |
| 40 } | |
| 41 | |
| 42 void destroy_bfile_heuristics_t(bfile_heuristics_t *def) { | |
| 43 free(def); | |
| 44 } | |
| 45 | |
| 46 void bfile_reset(bfile_heuristics_t *def) { | |
| 47 def->bcount = 0; | |
| 48 def->tcount = 0; | |
| 49 } | |
| 50 | |
| 51 bool bfile_check(bfile_heuristics_t *def, int next_char) { | |
| 52 bool ret = false; | |
| 53 if (def->level != BFILE_IGNORE) { | |
| 54 def->tcount++; | |
| 55 if (!isprint(next_char) && !isspace(next_char)) { | |
| 56 def->bcount++; | |
| 57 } | |
| 58 | |
| 59 if (def->tcount > 1) { /* empty files are text files */ | |
| 60 switch (def->level) { | |
| 61 case BFILE_LOW_ACCURACY: | |
| 62 if (def->tcount > 15 || next_char == EOF) { | |
| 63 ret = (1.0*def->bcount)/def->tcount > 0.32; | |
| 64 } | |
| 65 break; | |
| 66 case BFILE_HIGH_ACCURACY: | |
| 67 if (def->tcount > 500 || next_char == EOF) { | |
| 68 ret = (1.0*def->bcount)/def->tcount > 0.1; | |
| 69 } | |
| 70 break; | |
| 71 default: /* BFILE_MEDIUM_ACCURACY */ | |
| 72 if (def->tcount > 100 || next_char == EOF) { | |
| 73 ret = (1.0*def->bcount)/def->tcount > 0.1; | |
| 74 } | |
| 75 break; | |
| 76 } | |
| 77 } | |
| 78 } | |
| 79 | |
| 80 return ret; | |
| 81 } |
