regex_internal.h

Go to the documentation of this file.

/*
     This file is part of GNUnet
     Copyright (C) 2012 GNUnet e.V.
 
     GNUnet is free software: you can redistribute it and/or modify it
     under the terms of the GNU Affero General Public License as published
     by the Free Software Foundation, either version 3 of the License,
     or (at your option) any later version.
 
     GNUnet is distributed in the hope that it will be useful, but
     WITHOUT ANY WARRANTY; without even the implied warranty of
     MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
     Affero General Public License for more details.
 
     You should have received a copy of the GNU Affero General Public License
     along with this program.  If not, see <http://www.gnu.org/licenses/>.
 
     SPDX-License-Identifier: AGPL3.0-or-later
 */
#ifndef REGEX_INTERNAL_H
#define REGEX_INTERNAL_H
 
#include "regex_internal_lib.h"
 
#ifdef __cplusplus
extern "C"
{
#if 0                           /* keep Emacsens' auto-indent happy */
}
#endif
#endif
 
#define ALLOWED_LITERALS \
  "0123456789ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz"
 
 
struct REGEX_INTERNAL_Transition
{
  struct REGEX_INTERNAL_Transition *prev;
 
  struct REGEX_INTERNAL_Transition *next;
 
  unsigned int id;
 
  char *label;
 
  struct REGEX_INTERNAL_State *to_state;
 
  struct REGEX_INTERNAL_State *from_state;
};
 
 
struct REGEX_INTERNAL_State;
 
 
struct REGEX_INTERNAL_StateSet
{
  struct REGEX_INTERNAL_State **states;
 
  unsigned int off;
 
  unsigned int size;
};
 
 
struct REGEX_INTERNAL_State
{
  struct REGEX_INTERNAL_State *prev;
 
  struct REGEX_INTERNAL_State *next;
 
  struct REGEX_INTERNAL_State *prev_SS;
 
  struct REGEX_INTERNAL_State *next_SS;
 
  struct REGEX_INTERNAL_State *prev_ST;
 
  struct REGEX_INTERNAL_State *next_ST;
 
  unsigned int id;
 
  unsigned int traversal_id;
 
  int accepting;
 
  int marked;
 
  int contained;
 
  unsigned int scc_id;
 
  int index;
 
  int lowlink;
 
  char *name;
 
  struct GNUNET_HashCode hash;
 
  unsigned int dfs_id;
 
  char *proof;
 
  unsigned int transition_count;
 
  struct REGEX_INTERNAL_Transition *transitions_head;
 
  struct REGEX_INTERNAL_Transition *transitions_tail;
 
  unsigned int incoming_transition_count;
 
  struct REGEX_INTERNAL_StateSet nfa_set;
};
 
 
enum REGEX_INTERNAL_AutomatonType
{
  NFA,
  DFA
};
 
 
struct REGEX_INTERNAL_Automaton
{
  struct REGEX_INTERNAL_Automaton *prev;
 
  struct REGEX_INTERNAL_Automaton *next;
 
  struct REGEX_INTERNAL_State *start;
 
  struct REGEX_INTERNAL_State *end;
 
  unsigned int state_count;
 
  struct REGEX_INTERNAL_State *states_head;
 
  struct REGEX_INTERNAL_State *states_tail;
 
  enum REGEX_INTERNAL_AutomatonType type;
 
  char *regex;
 
  char *canonical_regex;
 
  int is_multistrided;
};
 
 
struct REGEX_INTERNAL_Automaton *
REGEX_INTERNAL_construct_nfa (const char *regex, const size_t len);
 
 
typedef int
(*REGEX_INTERNAL_traverse_check) (void *cls,
                                  struct REGEX_INTERNAL_State *s,
                                  struct REGEX_INTERNAL_Transition *t);
 
 
typedef void
(*REGEX_INTERNAL_traverse_action) (void *cls,
                                   const unsigned int count,
                                   struct REGEX_INTERNAL_State *s);
 
 
void
REGEX_INTERNAL_automaton_traverse (const struct REGEX_INTERNAL_Automaton *a,
                                   struct REGEX_INTERNAL_State *start,
                                   REGEX_INTERNAL_traverse_check check,
                                   void *check_cls,
                                   REGEX_INTERNAL_traverse_action action,
                                   void *action_cls);
 
const char *
REGEX_INTERNAL_get_canonical_regex (struct REGEX_INTERNAL_Automaton *a);
 
 
unsigned int
REGEX_INTERNAL_get_transition_count (struct REGEX_INTERNAL_Automaton *a);
 
 
struct REGEX_INTERNAL_Context
{
  unsigned int state_id;
 
  unsigned int transition_id;
 
  struct REGEX_INTERNAL_Automaton *stack_head;
 
  struct REGEX_INTERNAL_Automaton *stack_tail;
};
 
 
void
REGEX_INTERNAL_dfa_add_multi_strides (struct REGEX_INTERNAL_Context *regex_ctx,
                                      struct REGEX_INTERNAL_Automaton *dfa,
                                      const unsigned int stride_len);
 
 
#if 0                           /* keep Emacsens' auto-indent happy */
{
#endif
#ifdef __cplusplus
}
#endif
 
#endif