// load automata for scanning valid identifiers
void Scanner::load_id_machine() {
// create the id scan automata
auto id_machine = FSMachinePtr(
new FiniteMachineContainer(get_token_info(TokType::MP_ID).first,
true));
// detects ids without two underscores
id_machine->add_state("0", true, false);
id_machine->add_state("1", false, true);
id_machine->add_state("2", false, true);
id_machine->add_state("3", false, false);
id_machine->add_state("4", false, false);
// add transitions
id_machine->add_alphabet("0", "1");
id_machine->add_alphabet("1", "1");
id_machine->add_digits("1", "1");
id_machine->add_transition("1", '_', "4");
id_machine->add_alphabet("4", "1");
id_machine->add_digits("4", "1");
// other part
id_machine->add_transition("0", '_', "3");
id_machine->add_alphabet("3", "2");
id_machine->add_digits("3", "2");
id_machine->add_alphabet("2", "2");
id_machine->add_digits("2", "2");
id_machine->add_transition("2", '_', "3");
// set priority
id_machine->set_priority(2);
// add to finite machines
this->fsmachines->push_back(FSMachinePtr(id_machine));
}
void Scanner::load_strand_machines(unsigned int within) {
// comments and strings, take that!
// add nested strings and comments feature using within variable
auto comment_machine = FSMachinePtr(
new FiniteMachineContainer(get_token_info(TokType::MP_COMMENT).first, true));
// add states
comment_machine->add_state("0", true, false);
comment_machine->add_state("1", false, false);
comment_machine->add_state("2", false, true);
// for state 1
comment_machine->add_alphabet("1", "1");
comment_machine->add_symbols("1", "1");
comment_machine->add_digits("1", "1");
comment_machine->add_transition("1", ' ', "1");
comment_machine->add_transition("1", '\n', "1");
comment_machine->add_transition("1", '\t', "1");
comment_machine->add_transition("1", '\v', "1");
comment_machine->add_transition("1", '\r', "1");
comment_machine->add_transition("1", '\f', "1");
comment_machine->remove_transition("1", '{');
comment_machine->remove_transition("1", '}');
comment_machine->add_transition("0", '{', "1");
comment_machine->add_transition("1", '}', "2");
// new machine
auto string_machine = FSMachinePtr(
new FiniteMachineContainer(get_token_info(TokType::MP_STRING_LITERAL).first, true));
// add states
string_machine->add_state("0", true, false);
string_machine->add_state("1", false, false);
string_machine->add_state("2", false, true);
// add transitions
string_machine->add_transition("0", '\'', "1");
string_machine->add_alphabet("1", "1");
string_machine->add_symbols("1", "1");
string_machine->add_digits("1", "1");
string_machine->add_transition("1", ' ', "1");
string_machine->remove_transition("1", '\'');
string_machine->remove_transition("1", '\'');
string_machine->add_transition("1", '\'', "2");
// set machine priority
comment_machine->set_priority(1);
string_machine->set_priority(1);
// add the machines to our FSMachines list
this->fsmachines->push_back(comment_machine);
this->fsmachines->push_back(string_machine);
}
int map_sequences(STRING *s1, STRING *s2, STRING **sary, int arylen)
{
int i, j, num, same, alpha;
char *s, *t, map[128], characters[129];
ALPHABET *tptr;
/*
* Check the simple case where all have the same alphabet.
*/
same = 1;
alpha = ALPHA_UNKNOWN;
if (s1 != NULL)
alpha = s1->raw_alpha;
if (s2 != NULL) {
if (alpha == ALPHA_UNKNOWN)
alpha = s2->raw_alpha;
else if (alpha != s2->raw_alpha)
same = 0;
}
if (sary != NULL) {
for (i=0; i < arylen; i++) {
if (sary[i] != NULL) {
if (alpha == ALPHA_UNKNOWN)
alpha = sary[i]->raw_alpha;
else if (alpha != sary[i]->raw_alpha)
same = 0;
}
}
}
/*
* If not, print a warning message and create a new alphabet formed
* by the combination of all the characters in the alphabets.
*/
if (!same) {
fprintf(stderr, "Warning: Alphabets are not identical...\n");
for (i=0; i < 128; i++)
map[i] = '\0';
if (s1 != NULL) {
tptr = &alpha_tables[s1->raw_alpha];
for (i=0; i < 128; i++)
if (tptr->rawmap[i] != '\0')
map[(int) tptr->rawmap[i]] = 1;
}
if (s2 != NULL) {
tptr = &alpha_tables[s2->raw_alpha];
for (i=0; i < 128; i++)
if (tptr->rawmap[i] != '\0')
map[(int) tptr->rawmap[i]] = 1;
}
if (sary != NULL) {
for (num=0; num < arylen; num++) {
if (sary[num] != NULL) {
tptr = &alpha_tables[sary[num]->raw_alpha];
for (i=0; i < 128; i++)
if (tptr->rawmap[i] != '\0')
map[(int) tptr->rawmap[i]] = 1;
}
}
}
for (i=1,j=0; i < 128; i++)
if (map[i] == 1)
characters[j++] = (char) i;
characters[j] = '\0';
if ((alpha = add_alphabet(characters)) == -1)
return -1;
}
/*
* Map the sequences to the new alphabet.
*/
if (s1 != NULL && (!same || s1->alphabet != alpha)) {
s1->alphabet = alpha;
s1->alpha_size = alpha_tables[alpha].alpha_size;
for (i=0,s=s1->sequence,t=s1->raw_seq; i < s1->length; i++,s++,t++)
if ((*s = mapchar(alpha, *t)) == -1) {
fprintf(stderr,
"\nError: Sequence %s contains unmappable characters.\n",
s1->title);
return -1;
}
}
if (s2 != NULL && (!same || s2->alphabet != alpha)) {
s2->alphabet = alpha;
s2->alpha_size = alpha_tables[alpha].alpha_size;
for (i=0,s=s2->sequence,t=s2->raw_seq; i < s2->length; i++,s++,t++)
if ((*s = mapchar(alpha, *t)) == -1) {
fprintf(stderr,
"\nError: Sequence %s contains unmappable characters.\n",
s2->title);
return -1;
}
}
if (sary != NULL) {
for (num=0; num < arylen; num++) {
if (sary[num] != NULL && (!same || sary[num]->alphabet != alpha)) {
sary[num]->alphabet = alpha;
sary[num]->alpha_size = alpha_tables[alpha].alpha_size;
s = sary[num]->sequence;
for (i=0,t=sary[num]->raw_seq; i < sary[num]->length; i++)
if ((*s++ = mapchar(alpha, *t++)) == -1) {
fprintf(stderr,
"\nError: Sequence %s contains unmappable characters.\n",
sary[num]->title);
return -1;
}
}
}
}
return alpha;
}
