src/bfile_heuristics.c

Thu, 23 Aug 2018 19:45:36 +0200

author
Mike Becker <universe@uap-core.de>
date
Thu, 23 Aug 2018 19:45:36 +0200
changeset 57
68018eac46c3
parent 48
0d2c13c24fd0
permissions
-rw-r--r--

adds simple tiny test suite and updates license headers

     1 /*
     2  * DO NOT ALTER OR REMOVE COPYRIGHT NOTICES OR THIS HEADER. 
     3  * Copyright 2018 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  */
    27 #include "bfile_heuristics.h"
    28 #include <ctype.h>
    30 bfile_heuristics_t *new_bfile_heuristics_t() {
    31   bfile_heuristics_t *ret = malloc(sizeof(bfile_heuristics_t));
    32   ret->level = BFILE_MEDIUM_ACCURACY;
    33   bfile_reset(ret);
    34   return ret;
    35 }
    37 void destroy_bfile_heuristics_t(bfile_heuristics_t *def) {
    38   free(def);
    39 }
    41 void bfile_reset(bfile_heuristics_t *def) {
    42   def->bcount = 0;
    43   def->tcount = 0;
    44 }
    46 bool bfile_check(bfile_heuristics_t *def, int next_char) {
    47   bool ret = false;
    48   if (def->level != BFILE_IGNORE) {
    49     def->tcount++;
    50     if (!isprint(next_char) && !isspace(next_char)) {
    51       def->bcount++;
    52     }
    54     if (def->tcount > 1) { /* empty files are text files */
    55       switch (def->level) {
    56       case BFILE_LOW_ACCURACY:
    57         if (def->tcount > 15 || next_char == EOF) {
    58           ret = (1.0*def->bcount)/def->tcount > 0.32;
    59         }
    60         break;
    61       case BFILE_HIGH_ACCURACY:
    62         if (def->tcount > 500 || next_char == EOF) {
    63           ret = (1.0*def->bcount)/def->tcount > 0.1;
    64         }
    65         break;
    66       default: /* BFILE_MEDIUM_ACCURACY */
    67         if (def->tcount > 100 || next_char == EOF) {
    68           ret = (1.0*def->bcount)/def->tcount > 0.1;
    69         }
    70         break;
    71       }
    72     }
    73   }
    75   return ret;
    76 }

mercurial