int pn_scanner_symbol(pn_scanner_t *scanner, const char *str)
{
char c = str[1];
if (c == '"') {
return pn_scanner_quoted(scanner, str, 2, PN_TOK_SYMBOL);
} else {
int n = pn_scanner_alpha_end(scanner, str, 1);
pn_scanner_emit(scanner, PN_TOK_SYMBOL, str, n);
return 0;
}
}
int pn_scanner_alpha(pn_scanner_t *scanner, const char *str)
{
int n = pn_scanner_alpha_end(scanner, str, 0);
pn_token_type_t type;
if (!strncmp(str, "true", n)) {
type = PN_TOK_TRUE;
} else if (!strncmp(str, "false", n)) {
type = PN_TOK_FALSE;
} else if (!strncmp(str, "null", n)) {
type = PN_TOK_NULL;
} else {
type = PN_TOK_ID;
}
pn_scanner_emit(scanner, type, str, n);
return type == PN_TOK_ERR ? pn_scanner_err(scanner, PN_ERR, "unrecognized keyword") : 0;
}
int pn_scanner_quoted(pn_scanner_t *scanner, const char *str, int start,
pn_token_type_t type)
{
bool escape = false;
for (int i = start; true; i++) {
char c = str[i];
if (escape) {
escape = false;
} else {
switch (c) {
case '\0':
case '"':
pn_scanner_emit(scanner, c ? type : PN_TOK_ERR,
str, c ? i + 1 : i);
return c ? 0 : pn_scanner_err(scanner, PN_ERR, "missmatched quote");
case '\\':
escape = true;
break;
}
}
}
}
int pn_scanner_scan(pn_scanner_t *scanner)
{
const char *str = scanner->position;
char n;
for (char c; true; str++) {
c = *str;
switch (c)
{
case '{':
return pn_scanner_single(scanner, str, PN_TOK_LBRACE);
case '}':
return pn_scanner_single(scanner, str, PN_TOK_RBRACE);
case'[':
return pn_scanner_single(scanner, str, PN_TOK_LBRACKET);
case ']':
return pn_scanner_single(scanner, str, PN_TOK_RBRACKET);
case '=':
return pn_scanner_single(scanner, str, PN_TOK_EQUAL);
case ',':
return pn_scanner_single(scanner, str, PN_TOK_COMMA);
case '.':
n = *(str+1);
if ((n >= '0' && n <= '9')) {
return pn_scanner_number(scanner, str);
} else {
return pn_scanner_single(scanner, str, PN_TOK_DOT);
}
case '@':
return pn_scanner_single(scanner, str, PN_TOK_AT);
case '$':
return pn_scanner_single(scanner, str, PN_TOK_DOLLAR);
case '-':
n = *(str+1);
if ((n >= '0' && n <= '9') || n == '.') {
return pn_scanner_number(scanner, str);
} else {
return pn_scanner_single(scanner, str, PN_TOK_NEG);
}
case '+':
n = *(str+1);
if ((n >= '0' && n <= '9') || n == '.') {
return pn_scanner_number(scanner, str);
} else {
return pn_scanner_single(scanner, str, PN_TOK_POS);
}
case ' ': case '\t': case '\r': case '\v': case '\f': case '\n':
break;
case '0': case '1': case '2': case '3': case '4': case '5': case '6':
case '7': case '8': case '9':
return pn_scanner_number(scanner, str);
case ':':
return pn_scanner_symbol(scanner, str);
case '"':
return pn_scanner_string(scanner, str);
case 'b':
if (str[1] == '"') {
return pn_scanner_binary(scanner, str);
}
case 'a': 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': 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':
return pn_scanner_alpha(scanner, str);
case '\0':
pn_scanner_emit(scanner, PN_TOK_EOS, str, 0);
return PN_EOS;
default:
pn_scanner_emit(scanner, PN_TOK_ERR, str, 1);
return pn_scanner_err(scanner, PN_ERR, "illegal character");
}
}
}
int pn_scanner_single(pn_scanner_t *scanner, const char *str, pn_token_type_t type)
{
pn_scanner_emit(scanner, type, str, 1);
return 0;
}
