int
get_token(void)
{
int type = TOKEN_TYPE_ERR;
int index = 0;
int status = SCAN_STATUS_START;
int save;
int c;
while (status != SCAN_STATUS_DONE) {
c = get_char();
save = BOOL_YES;
switch (status) {
case SCAN_STATUS_START:
if (' ' == c || '\t' == c) {
save = BOOL_NO;
}
else if ('\n' == c) {
save = BOOL_NO;
++g_line_numer;
}
else if (isdigit(c)) {
status = SCAN_STATUS_IN_CINT;
}
else if (isalpha(c) || '_' == c) {
status = SCAN_STATUS_IN_ID;
}
else if ('.' == c) {
status = SCAN_STATUS_IN_ACCESS;
}
else if ('#' == c) {
save = BOOL_NO;
status = SCAN_STATUE_IN_COMMENT;
}
else {
status = SCAN_STATUS_DONE;
switch (c) {
case EOF:
save = BOOL_NO;
type = TOKEN_TYPE_EOF;
break;
case '=':
type = TOKEN_TYPE_ASSIGN;
break;
case '<':
type = TOKEN_TYPE_INHERIT;
break;
case '[':
type = TOKEN_TYPE_LBRACKET;
break;
case ']':
type = TOKEN_TYPE_RBRACKET;
break;
case '{':
type = TOKEN_TYPE_LBRACE;
break;
case '}':
type = TOKEN_TYPE_RBRACE;
break;
default:
save = BOOL_NO;
type = TOKEN_TYPE_ERR;
break;
}
}
break;
case SCAN_STATUS_IN_ACCESS:
if (isalpha(c) || '_' == c) {
unget_char();
save = BOOL_NO;
status = SCAN_STATUS_DONE;
type = TOKEN_TYPE_ACCESS;
}
else {
fprintf(stderr, "Lexial error: [%d] after '.' ...\n", g_line_numer);
exit(1);
}
break;
case SCAN_STATUS_IN_ID:
if (!isalnum(c) && '_' != c) {
unget_char();
save = BOOL_NO;
status = SCAN_STATUS_DONE;
type = TOKEN_TYPE_ID;
}
break;
case SCAN_STATUS_IN_CINT:
if ('.' == c) {
status = SCAN_STATUS_IN_CREAL;
}
else {
if (!isdigit(c)) {
unget_char();
save = BOOL_NO;
status = SCAN_STATUS_DONE;
type = TOKEN_TYPE_CINT;
}
}
break;
case SCAN_STATUS_IN_CREAL:
if (!isdigit(c)) {
unget_char();
save = BOOL_NO;
status = SCAN_STATUS_DONE;
type = TOKEN_TYPE_CREAL;
}
break;
case SCAN_STATUE_IN_COMMENT:
save = BOOL_NO;
if (EOF == c) {
status = SCAN_STATUS_DONE;
type = TOKEN_TYPE_EOF;
}
else if ('\n' == c) {
++g_line_numer;
status = SCAN_STATUS_START;
}
break;
case SCAN_STATUS_DONE:
default:
fprintf(g_scan_stream, "Scanner bug: status = %d\n", status);
status = SCAN_STATUS_DONE;
type = TOKEN_TYPE_ERR;
break;
}
if (save && index < MAX_TOKEN)
g_token[index++] = (char)c;
if (SCAN_STATUS_DONE == status) {
g_token[index] = 0;
if (TOKEN_TYPE_ID == type)
type = lookup_reserved(g_token);
}
}
echo_scanner(g_scan_stream, g_line_numer, type, g_token);
return type;
}
static int
ScanOneToken (FILE *fp, struct token_t *token)
{
int i, ch, nextch, prevch;
ch = getc(fp); // read next char from input stream
while (isspace(ch)) // if necessary, keep reading til non-space char
ch = getc(fp); // (discard any white space)
switch(ch) {
case '/': // could either begin comment or T_DIVIDE op
nextch = getc(fp);
if (nextch == '/' || nextch == '*')
; // here you would skip over the comment
else
ungetc(nextch, fp); // fall-through to single-char token case
case ';': case '(': case ')': case ',': case '=': // ... and other single char tokens
token->type = ch; // ASCII value is used as token type
return ch; // ASCII value used as token type
case '\"':
token->type = T_STRING;
prevch = ch;
ch = getc(fp);
for (i = 0; (prevch != '\\') && (ch != '\"'); i++) {
token->val.stringValue[i] = ch;
prevch = ch;
ch = getc(fp);
}
token->val.stringValue[i] = '\0';
return token->type;
case 'A': case 'B': case 'C': case 'D': case 'E': case 'F': case 'G':
case 'H': case 'I': case 'J': case 'K': case 'L': case 'M': case 'N':
case 'O': case 'P': case 'Q': case 'R': case 'S': case 'T': case 'U':
case 'V': case 'W': case 'X': case 'Y': case 'Z':
token->val.stringValue[0] = ch;
for (i = 1; isupper(ch = getc(fp)); i++) // gather uppercase
token->val.stringValue[i] = ch;
ungetc(ch, fp);
token->val.stringValue[i] = '\0'; // lookup reserved word
token->type = lookup_reserved(token->val.stringValue);
return token->type;
case 'a': case 'b': case 'c': case 'd': case 'e': case 'f': case 'g':
case 'h': case 'i': case 'j': case 'k': case 'l': case 'm': case 'n':
case 'o': case 'p': case 'q': case 'r': case 's': case 't': case 'u':
case 'v': case 'w': case 'x': case 'y': case 'z':
token->type = T_IDENTIFIER;
token->val.stringValue[0] = ch;
for (i = 1; islower(ch = getc(fp)); i++)
token->val.stringValue[i] = ch; // gather lowercase
ungetc(ch, fp);
token->val.stringValue[i] = '\0';
return T_IDENTIFIER;
case '0': case '1': case '2': case '3': case '4':
case '5': case '6': case '7': case '8': case '9':
token->type = T_INTEGER;
token->val.intValue = ch - '0';
while (isdigit(ch = getc(fp))) // convert digit char to number
token->val.intValue = token->val.intValue * 10 + ch - '0';
ungetc(ch, fp);
return T_INTEGER;
case EOF:
return T_END;
default: // anything else is not recognized
token->val.intValue = ch;
token->type = T_UNKNOWN;
return T_UNKNOWN;
}
}
