R_API ut64 r_num_calc(RNum *num, const char *str, const char **err) {
RNumCalcValue n;
RNumCalc *nc, nc_local;
if (!str || !*str) {
return 0LL;
}
if (num) {
nc = &num->nc;
num->dbz = 0;
} else {
nc = &nc_local;
}
/* init */
nc->curr_tok = RNCPRINT;
nc->number_value.d = 0.0;
nc->number_value.n = 0LL;
nc->errors = 0;
nc->oc = 0;
nc->calc_err = NULL;
nc->calc_i = 0;
nc->calc_len = 0;
nc->calc_buf = NULL;
load_token (num, nc, str);
get_token (num, nc);
n = expr (num, nc, 0);
if (err) {
*err = nc->calc_err;
}
if (num) {
num->fvalue = n.d;
}
return n.n;
}
R_API ut64 r_num_calc (RNum *num, const char *str, const char **err) {
RNumCalcValue n;
RNumCalc *nc, nc_local;
if (!str || !*str)
return 0LL;
if (num) {
nc = &num->nc;
num->dbz = 0;
} else {
nc = &nc_local;
}
/* init */
nc->curr_tok = RNCPRINT;
nc->number_value.d = 0.0;
nc->number_value.n = 0LL;
nc->errors = 0;
nc->oc = 0;
nc->calc_err = NULL;
nc->calc_i = 0;
nc->calc_len = 0;
nc->calc_buf = NULL;
load_token (num, nc, str);
get_token (num, nc);
n = expr (num, nc, 0);
if (err) *err = nc->calc_err;
//if (nc->curr_tok == RNCEND) return 0LL; // XXX: Error
//if (nc->curr_tok == RNCPRINT) //return 0LL; // XXX: the f**k
// n = expr (num, nc, 0);
if (n.d != ((double)(ut64)n.d)) {
if (num) num->fvalue = n.d;
} else if (num) num->fvalue = (double)n.n;
return n.n;
}
R_API ut64 r_num_calc (RNum *num, const char *str, const char **err) {
NumValue n;
if (!*str)
return 0LL;
calc_num = num;
load_token (str);
get_token ();
n = expr (0);
if (err) *err = calc_err;
//if (curr_tok == END) return 0LL; // XXX: Error
//if (curr_tok == PRINT) //return 0LL; // XXX: the f**k
// n = expr (0);
if (n.d != ((double)(ut64)n.d)) {
if (num) num->fvalue = n.d;
} else if (num) num->fvalue = (double)n.n;
return n.n;
}
void urdutag_file(const char *input_filename, const char *output_filename,
const char *lexicon_filename)
{
FILE *source;
FILE *dest;
entry *lexicon;
token *word;
/* open the source file and check for (then discard) directionality character */
if (!(source = fopen(input_filename, "rb")))
{
puts("Error opening original file!");
fcloseall();
return;
}
if (!( ucheckdir(source) ))
{
fputs("Specified source file not recognised as Unicode!", stderr);
fcloseall();
return;
}
/* open file to write, insert directionality character */
if( !(dest = fopen(output_filename, "wb")) )
{
puts("Error opening processed file!");
fcloseall();
return;
}
if ( fputuc( RIGHTWAY , dest) == UERR )
{
puts("Error writing to processed file!");
fcloseall();
return;
}
if (! ( lexicon = load_lexicon(lexicon_filename) ) )
return;
while (1)
{
/* read a line */
if ( ! (word = load_token(source)) )
break;
/* urdutag that token IF it has no tags already */
if (word->tag[0][0] == 0x0000)
urdutag(lexicon, word);
/* if split-signal tag returned , perform the special actions */
if ( word->tag[0][0] == 0x0053 && word->tag[0][1] == 0x0050 )
word = do_the_splits(word, lexicon, dest);
/* write the line to file */
if (write_token(word, dest))
break;
free(word);
}
/* check "word". If it is still alloc'd, then the loop broke prematurely */
/* and "word" will need freeing. */
if (word)
free(word);
/* free the lexicon */
free_lexicon(lexicon);
/* close read and write files */
if (fclose(source) < 0)
{
puts("Error closing original file!");
fcloseall();
return;
}
if (fclose(dest) < 0)
{
puts("Error closing processed file!");
fcloseall();
return;
}
}
index_t get_token(FILE *fin, TDynamic_buffer *buffer, TDynamic_structure_buffer *struct_buffer) {
args_assert(buffer != NULL && struct_buffer != NULL, INTERNAL_ERROR);
debug_print("%s\n", "GET_TOKEN");
char hx[3] = {0, 0, '\0'};
char x;
int c;
int previous = 0;
int state = START;
bool read = true;
bool signed_scientific = false;
bool wrong_identifier = false;
bool is_number_after_sign = false;
bool is_number_after_dot = false;
bool is_end = true;
index_t index = 0;
TToken *token;
new_item(struct_buffer, index, token);
while (1) {
if (read)
{
c = fgetc(fin);
if (feof(fin) && is_end)
{
if (state == BLOCK_COMMENT) {
token->token_index = save_token(buffer);
token->token_type = ERRORT;
} else {
token->token_index = save_token(buffer);
token->token_type = EOFT;
}
return index;
}
}
else
{
c = previous;
read = true;
}
switch (state)
{
case START:
if ((c > 64 && c < 91) || (c > 96 && c < 123) || c == '_') // A-Z || a-z || _
{
state = IDENTIFIER;
catch_token_internal_error(add_char(buffer, c), INTERNAL_ERROR, token, index);
}
else if (c > 47 && c < 58) // 0-9
{
state = L_INT;
catch_token_internal_error(add_char(buffer, c), INTERNAL_ERROR, token, index);
}
else
{
switch (c)
{
case '+':
token->token_index = save_token(buffer);
token->token_type = O_PLUS;
return index;
break;
case '-':
token->token_index = save_token(buffer);
token->token_type = O_MINUS;
return index;
break;
case '/':
state = COMMENT;
is_end = false;
break;
case '*':
token->token_index = save_token(buffer);
token->token_type = O_MUL;
return index;
break;
case ';':
token->token_index = save_token(buffer);
token->token_type = SEMICOLON;
return index;
break;
case ',':
token->token_index = save_token(buffer);
token->token_type = COMMA;
return index;
break;
case '(':
token->token_index = save_token(buffer);
token->token_type = OPENING_BRACKET;
return index;
break;
case ')':
token->token_index = save_token(buffer);
token->token_type = CLOSING_BRACKET;
return index;
break;
case '{':
token->token_index = save_token(buffer);
token->token_type = OPENING_CURLY_BRACKET;
return index;
break;
case '}':
token->token_index = save_token(buffer);
token->token_type = CLOSING_CURLY_BRACKET;
return index;
break;
case '=':
state = O_EQUALS;
is_end = false;
break;
case '<':
state = O_L;
is_end = false;
break;
case '>':
state = O_G;
is_end = false;
break;
case '!':
state = UO_EXCLAMATION;
is_end = false;
break;
case '"':
state = L_STRING;
is_end = false;
break;
default:
if (!isspace(c))
{
catch_token_internal_error(add_char(buffer, c), INTERNAL_ERROR, token, index);
token->token_index = save_token(buffer);
token->token_type = ERRORT;
return index;
}
break;
} // switch(c)
} // else
break;
case COMMENT:
debug_print("%s","COMMENT COMMENT COMMENT COMMENT COMMENT\n");
if (c == '/') // //
{
state = LINE_COMMENT;
is_end = false;
}
else if (c == '*') // /*
{
state = BLOCK_COMMENT;
is_end = false;
}
else // /
{
ungetc(c, fin);
state = START;
token->token_index = save_token(buffer);
token->token_type = O_DIV;
return index;
}
break;
case LINE_COMMENT:
is_end = true;
if (c == '\n')
{
state = START;
}
break;
case BLOCK_COMMENT:
is_end = true;
if (c == '*')
{
state = BLOCK_COMMENT_END;
}
break;
case BLOCK_COMMENT_END:
if (c == '/')
{
state = START;
is_end = true;
}
else
state = BLOCK_COMMENT;
break;
case O_EQUALS:
if (c == '=') // ==
{
token->token_index = save_token(buffer);
token->token_type = O_EQUALS;
state = START;
return index;
break;
}
else // =
{
ungetc(c, fin);
state = START;
token->token_index = save_token(buffer);
token->token_type = O_ASSIGN;
return index;
break;
}
case O_G:
if (c == '=') // >=
{
token->token_index = save_token(buffer);
token->token_type = O_GE;
state = START;
return index;
break;
}
else if (c == '>') // >>
{
token->token_index = save_token(buffer);
token->token_type = O_RIGHT_ARROW;
state = START;
return index;
break;
}
else // >
{
ungetc(c, fin);
token->token_index = save_token(buffer);
token->token_type = O_G;
state = START;
return index;
break;
}
case O_L:
if (c == '=') // <=
{
token->token_index = save_token(buffer);
token->token_type = O_LE;
state = START;
return index;
break;
}
else if (c == '<') // <<
{
token->token_index = save_token(buffer);
token->token_type = O_LEFT_ARROW;
state = START;
return index;
break;
}
else // <
{
ungetc(c, fin);
token->token_index = save_token(buffer);
token->token_type = O_L;
state = START;
return index;
break;
}
case UO_EXCLAMATION:
if (c == '=') // !=
{
token->token_index = save_token(buffer);
token->token_type = O_NE;
state = START;
return index;
break;
}
else // ! je zatial errort
{
ungetc(c, fin);
token->token_index = save_token(buffer);
token->token_type = ERRORT; // token->token_type = UO_EXCLAMATION;
state = START;
return index;
break;
}
case IDENTIFIER:
if ((c > 64 && c < 91) || (c > 96 && c < 123) || (c > 47 && c < 58) || c == '_') { // (A-Z, a-z, 0-9, _)
catch_token_internal_error(add_char(buffer, c), INTERNAL_ERROR, token, index);
is_end = false;
}
else if (SEPARATOR)
{
token->token_index = save_token(buffer);
if (!wrong_identifier)
token->token_type = reservedWord(load_token(buffer, token->token_index));
else
token->token_type = ERRORT;
wrong_identifier = false;
is_number_after_dot = false;
is_number_after_sign = false;
ungetc(c,fin);
state = START;
return index;
}
else
{
catch_token_internal_error(add_char(buffer, c), INTERNAL_ERROR, token, index);
wrong_identifier = true;
is_end = false;
}
break;
case L_INT:
if (c > 47 && c < 58) // 0-9
{
catch_token_internal_error(add_char(buffer, c), INTERNAL_ERROR, token, index);
is_end = false;
}
else if (c == 46) // c == "."
{
catch_token_internal_error(add_char(buffer, c), INTERNAL_ERROR, token, index);
state = L_DOUBLE;
is_end = false;
}
else if (SEPARATOR)
{
token->token_index = save_token(buffer);
token->token_type = L_INT;
ungetc(c,fin);
state = START;
return index;
}
else if (c == 'e' || c == 'E')
{
catch_token_internal_error(add_char(buffer, c), INTERNAL_ERROR, token, index);
state = SCIENTIFIC;
is_end = false;
}
else
{
catch_token_internal_error(add_char(buffer, c), INTERNAL_ERROR, token, index);
wrong_identifier = true;
state = IDENTIFIER;
is_end = false;
}
break;
case L_DOUBLE:
if (c > 47 && c < 58) // 0-9
{
catch_token_internal_error(add_char(buffer, c), INTERNAL_ERROR, token, index);
is_number_after_dot = true;
is_end = false;
}
else if ((SEPARATOR) && is_number_after_dot)
{
token->token_type = L_DOUBLE;
token->token_index = save_token(buffer);
ungetc(c,fin);
state = START;
return index;
}
else if ((SEPARATOR) && !is_number_after_dot)
{
token->token_type = ERRORT;
token->token_index = save_token(buffer);
ungetc(c,fin);
state = START;
return index;
}
else if ((c == 'e' || c == 'E') && is_number_after_dot)
{
catch_token_internal_error(add_char(buffer, c), INTERNAL_ERROR, token, index);
state = SCIENTIFIC;
is_end = false;
}
else
{
catch_token_internal_error(add_char(buffer, c), INTERNAL_ERROR, token, index);
wrong_identifier = true;
state = IDENTIFIER;
is_end = false;
}
break;
case SCIENTIFIC:
if ((c == '+' || c == '-') && !signed_scientific && !is_number_after_sign)
{
signed_scientific = true;
catch_token_internal_error(add_char(buffer, c), INTERNAL_ERROR, token, index);
state = SCIENTIFIC;
is_end = false;
}
else if (c > 47 && c < 58)
{
catch_token_internal_error(add_char(buffer, c), INTERNAL_ERROR, token, index);
is_number_after_sign = true;
is_end = false;
}
else if ((SEPARATOR) && is_number_after_sign)
{
token->token_type = L_DOUBLE;
token->token_index = save_token(buffer);
ungetc(c,fin);
state = START;
return index;
}
else
{
// catch_token_internal_error(add_char(buffer, c), INTERNAL_ERROR, token, index);
wrong_identifier = true;
state = IDENTIFIER;
is_end = false;
ungetc(c, fin);
}
break;
case L_STRING:
if (c == '"')
{
token->token_type = L_STRING;
token->token_index = save_token(buffer);
state = START;
return index;
}
else if (c == '\\')
{
// catch_token_internal_error(add_char(buffer, c), INTERNAL_ERROR, token, index);
state = L_STRING_BACKSLASH;
is_end = false;
}
else
{
catch_token_internal_error(add_char(buffer, c), INTERNAL_ERROR, token, index);
is_end = false;
}
break;
case L_STRING_BACKSLASH:
switch(c) {
case 'n':
catch_token_internal_error(add_char(buffer, '\n'), INTERNAL_ERROR, token, index);
state = L_STRING;
is_end = false;
break;
case 't':
catch_token_internal_error(add_char(buffer, '\t'), INTERNAL_ERROR, token, index);
state = L_STRING;
is_end = false;
break;
case '"':
catch_token_internal_error(add_char(buffer, '"'), INTERNAL_ERROR, token, index);
state = L_STRING;
is_end = false;
break;
case '\\':
catch_token_internal_error(add_char(buffer, '\\'), INTERNAL_ERROR, token, index);
state = L_STRING;
is_end = false;
break;
case 'x':
hx[0] = fgetc(fin);
hx[1] = fgetc(fin);
x = (char)(int)strtol(hx, NULL, 16);
if (strcmp(&x, "")) {
catch_token_internal_error(add_char(buffer, x), INTERNAL_ERROR, token, index);
state = L_STRING;
break;
}
default:
token->token_type = ERRORT;
token->token_index = save_token(buffer);
ungetc(c,fin);
state = START;
return index;
}
// catch_token_internal_error(add_char(buffer, c), INTERNAL_ERROR, token, index);
state = L_STRING;
break;
} // switch(state)
} // while(1)
return 0;
}
int short_reduction(Resources *res, TStack *stack) {
args_assert(res != NULL && stack != NULL, INTERNAL_ERROR);
TToken *token_to_reduce;
int err;
debug_print("%s\n", "ONE TOKEN REDUCED");
catch_internal_error(
dereference_structure(&res->struct_buff, stack->top, (void **)&token_to_reduce),
INTERNAL_ERROR,
"Failed to dereference structure buffer."
);
int type = token_to_reduce->token_type;
if (type == IDENTIFIER) {
debug_print("%s\n", "TOKEN ID CHECKING TYPE");
err = is_var_declared(res, token_to_reduce->token_index);
catch_internal_error(err, INTERNAL_ERROR, "Failed to check if var was declared");
catch_undefined_error(err, SEMANTIC_ERROR, "Failed to check if var was declared", 1);
type = get_var_type(res, token_to_reduce->token_index);
catch_internal_error(type, INTERNAL_ERROR, "Failed to get variable type");
catch_undefined_error(type, SEMANTIC_ERROR, "Failed to get variable type", 1);
index_t offset;
catch_undefined_error(load_var_index(res, token_to_reduce->token_index, &offset),
SEMANTIC_ERROR,
"Failed to get var offset", 1
);
if (type == L_INT)
catch_internal_error(new_instruction_mem_mem(&res->instruction_buffer, 0lu, offset, 0lu, PUSH_INT_MEM),
INTERNAL_ERROR, "Failed to generate new instruction");
else if (type == L_DOUBLE)
catch_internal_error(new_instruction_mem_mem(&res->instruction_buffer, 0lu, offset, 0lu, PUSH_DBL_MEM),
INTERNAL_ERROR, "Failed to generate new instruction");
else
catch_internal_error(new_instruction_mem_mem(&res->instruction_buffer, 0lu, offset, 0lu, PUSH_INDEX_MEM),
INTERNAL_ERROR, "Failed to generate new instruction");
} else { // LITERAL
if (type == L_INT) {
int value;
if ((value = to_int(load_token(&res->string_buff, token_to_reduce->token_index))) < 0)
return LEXICAL_ERROR;
catch_internal_error(new_instruction_int_int(&res->instruction_buffer, 0lu, value, 0, PUSH_INT_CONST),
INTERNAL_ERROR, "Failed to generate new ");
} else
if (type == L_DOUBLE) {
double value;
if ((value = to_double(load_token(&res->string_buff, token_to_reduce->token_index))) < 0.0)
return LEXICAL_ERROR;
catch_internal_error(new_instruction_dbl_dbl(&res->instruction_buffer, 0lu, value, 0.0, PUSH_DBL_CONST),
INTERNAL_ERROR, "Failed to generate new instruction");
} else
if (type == L_STRING) {
catch_internal_error(new_instruction_mem_mem(&res->instruction_buffer, 0lu, token_to_reduce->token_index, 0lu, PUSH_INDEX_CONST),
INTERNAL_ERROR, "Failed to generate new instruction");
}
}
debug_print("%s: %d\n", "ORIGINAL_TYPE:", type);
index_t top_index = stack->top;
pop(&res->struct_buff, stack);
pop(&res->struct_buff, stack); // Remove SHIFT from stack
push(&res->struct_buff, stack, top_index);
return overwrite_top(&res->struct_buff, stack, RVALUE, type);
}