src/regex_parser.c

Mon, 19 Mar 2018 16:36:14 +0100

author
Mike Becker <universe@uap-core.de>
date
Mon, 19 Mar 2018 16:36:14 +0100
changeset 54
76d46533b9a9
parent 48
0d2c13c24fd0
child 57
68018eac46c3
permissions
-rw-r--r--

regex parser was not properly reset before each file, sometimes resulting in wrong line counts, when the previous scanned file ended with a match

     1 /*
     2  * DO NOT ALTER OR REMOVE COPYRIGHT NOTICES OR THIS HEADER. 
     3  * Copyright 2017 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  * regex_parser.c
    27  *
    28  *  Created on: 26.01.2012
    29  *      Author: Mike
    30  */
    32 #include "regex_parser.h"
    34 regex_parser_t* new_regex_parser_t() {
    35   regex_parser_t* ret = malloc(sizeof(regex_parser_t));
    36   if (ret != NULL) {
    37     ret->pattern_list = new_string_list_t();
    38     ret->matched_lines = 0;
    39     ret->pattern_match = 0;
    40     ret->compiled_patterns = NULL;
    41     ret->compiled_pattern_count = 0;
    42   }
    43   return ret;
    44 }
    46 void regex_parser_reset(regex_parser_t* parser) {
    47   parser->pattern_match = parser->matched_lines = 0;
    48 }
    50 void regex_destcomppats(regex_parser_t* parser) {
    51   if (parser->compiled_patterns != NULL) {
    52     for (int i = 0 ; i < parser->compiled_pattern_count ; i++) {
    53       if (parser->compiled_patterns[i] != NULL) {
    54         free(parser->compiled_patterns[i]);
    55       }
    56     }
    57     free(parser->compiled_patterns);
    58     parser->compiled_patterns = NULL;
    59     parser->compiled_pattern_count = 0;
    60   }
    61 }
    63 void destroy_regex_parser_t(regex_parser_t* parser) {
    64   regex_destcomppats(parser);
    65   destroy_string_list_t(parser->pattern_list);
    66   free(parser);
    67 }
    69 bool regex_parser_matching(regex_parser_t* parser) {
    70   return parser->pattern_match > 0;
    71 }
    73 int regex_parser_do(regex_parser_t* parser, char* input) {
    74   int err = REG_NOMATCH;
    75   if (parser->compiled_pattern_count > 0) {
    76     regmatch_t match;
    78     if (regex_parser_matching(parser)) {
    79       parser->matched_lines++;
    81       err = regexec(parser->compiled_patterns[parser->pattern_match],
    82           input, 1, &match, 0);
    83       if (err > 0 && err != REG_NOMATCH) {
    84         fprintf(stderr, "Regex-Error: 0x%08x", err);
    85       }
    86       if (err == 0) {
    87         parser->pattern_match = 0;
    88         /* do not match line, if it does not end with the pattern */
    89         if (match.rm_eo < strlen(input)) {
    90           parser->matched_lines--;
    91         }
    92       }
    93     } else {
    94       for (int i = 0 ; i < parser->compiled_pattern_count - 1 ; i += 2) {
    95         err = regexec(parser->compiled_patterns[i], input, 1, &match, 0);
    96         if (err > 0 && err != REG_NOMATCH) {
    97           fprintf(stderr, "Regex-Error: 0x%08x", err);
    98         }
    99         if (err == 0) {
   100           parser->pattern_match = i+1;
   101           parser->matched_lines = 0;
   102           /* Check, if end pattern is also in this line */
   103           regex_parser_do(parser, input);
   104           /* do not match line, if it does not start with the pattern */
   105           if (match.rm_so > 0 && parser->matched_lines > 0) {
   106             parser->matched_lines--;
   107           }
   108           break;
   109         }
   110       }
   111     }
   112   }
   113   return err;
   114 }
   116 bool regex_compile_all(regex_parser_t* parser) {
   117   bool success = true;
   118   size_t pcount = parser->pattern_list->count;
   119   if (pcount > 0) {
   120     regex_destcomppats(parser);
   121     parser->compiled_patterns = calloc(pcount, sizeof(regex_t));
   122     parser->compiled_pattern_count = pcount;
   124     regex_t* re;
   125     for (int i = 0 ; i < pcount ; i++) {
   126       re = malloc(sizeof(regex_t));
   127       if (regcomp(re, parser->pattern_list->items[i], REG_EXTENDED) == 0) {
   128         parser->compiled_patterns[i] = re;
   129       } else {
   130         fprintf(stderr, "Cannot compile pattern: %s\n",
   131             (parser->pattern_list->items[i]));
   132         parser->compiled_patterns[i] = NULL;
   133         success = false;
   134       }
   135     }
   136   }
   137   return success;
   138 }

mercurial