void ESISAPI
ESIS_Attr(ESIS_Writer pe, const ESIS_Char *name,
const ESIS_Char *val, size_t len)
{
size_t n;
n = strlen(name) + 1U;
esisStackPush(pe->S, name, n);
if (len == ESIS_NTS) {
esisStackPush(pe->S, val, strlen(val) + 1U);
} else {
esisStackPush(pe->S, val, len);
PUSH_CHAR('\0');
}
++pe->n_att;
}
int tokenize_whitespace(parser_t *self, size_t line_limit)
{
int i, slen, start_lines;
char c;
char *stream;
char *buf = self->data + self->datapos;
start_lines = self->lines;
if (make_stream_space(self, self->datalen - self->datapos) < 0) {
self->error_msg = "out of memory";
return -1;
}
stream = self->stream + self->stream_len;
slen = self->stream_len;
TRACE(("%s\n", buf));
for (i = self->datapos; i < self->datalen; ++i)
{
// Next character in file
c = *buf++;
TRACE(("Iter: %d Char: %c Line %d field_count %d, state %d\n",
i, c, self->file_lines + 1, self->line_fields[self->lines],
self->state));
switch(self->state) {
case EAT_WHITESPACE:
if (!IS_WHITESPACE(c)) {
// END_FIELD();
self->state = START_FIELD;
// Fall through to subsequent state
} else {
// if whitespace char, keep slurping
break;
}
case START_RECORD:
// start of record
if (c == '\n') {
// \n\r possible?
END_LINE();
break;
} else if (c == '\r') {
self->state = EAT_CRNL;
break;
} else if (IS_WHITESPACE(c)) {
END_FIELD();
self->state = EAT_WHITESPACE;
break;
} else {
/* normal character - handle as START_FIELD */
self->state = START_FIELD;
}
/* fallthru */
case START_FIELD:
/* expecting field */
if (c == '\n') {
END_FIELD();
END_LINE();
/* self->state = START_RECORD; */
} else if (c == '\r') {
END_FIELD();
self->state = EAT_CRNL;
}
else if (c == self->quotechar &&
self->quoting != QUOTE_NONE) {
/* start quoted field */
self->state = IN_QUOTED_FIELD;
}
else if (c == self->escapechar) {
/* possible escaped character */
self->state = ESCAPED_CHAR;
}
/* else if (c == ' ' && self->skipinitialspace) */
/* /\* ignore space at start of field *\/ */
/* ; */
else if (IS_WHITESPACE(c)) {
self->state = EAT_WHITESPACE;
}
else if (c == self->commentchar) {
END_FIELD();
self->state = EAT_COMMENT;
}
else {
/* begin new unquoted field */
if (self->quoting == QUOTE_NONNUMERIC)
self->numeric_field = 1;
// TRACE(("pushing %c", c));
PUSH_CHAR(c);
self->state = IN_FIELD;
}
break;
case ESCAPED_CHAR:
/* if (c == '\0') */
/* c = '\n'; */
PUSH_CHAR(c);
self->state = IN_FIELD;
break;
case IN_FIELD:
/* in unquoted field */
if (c == '\n') {
END_FIELD();
END_LINE();
/* self->state = START_RECORD; */
} else if (c == '\r') {
END_FIELD();
self->state = EAT_CRNL;
}
else if (c == self->escapechar) {
/* possible escaped character */
self->state = ESCAPED_CHAR;
}
else if (IS_WHITESPACE(c)) {
// End of field. End of line not reached yet
END_FIELD();
self->state = EAT_WHITESPACE;
}
else if (c == self->commentchar) {
END_FIELD();
self->state = EAT_COMMENT;
}
else {
/* normal character - save in field */
PUSH_CHAR(c);
}
break;
case IN_QUOTED_FIELD:
/* in quoted field */
if (c == self->escapechar) {
/* Possible escape character */
self->state = ESCAPE_IN_QUOTED_FIELD;
}
else if (c == self->quotechar &&
self->quoting != QUOTE_NONE) {
if (self->doublequote) {
/* doublequote; " represented by "" */
self->state = QUOTE_IN_QUOTED_FIELD;
}
else {
/* end of quote part of field */
self->state = IN_FIELD;
}
}
else {
/* normal character - save in field */
PUSH_CHAR(c);
}
break;
case ESCAPE_IN_QUOTED_FIELD:
/* if (c == '\0') */
/* c = '\n'; */
PUSH_CHAR(c);
self->state = IN_QUOTED_FIELD;
break;
case QUOTE_IN_QUOTED_FIELD:
/* doublequote - seen a quote in an quoted field */
if (self->quoting != QUOTE_NONE && c == self->quotechar) {
/* save "" as " */
PUSH_CHAR(c);
self->state = IN_QUOTED_FIELD;
}
else if (IS_WHITESPACE(c)) {
// End of field. End of line not reached yet
END_FIELD();
self->state = EAT_WHITESPACE;
}
else if (c == '\n') {
END_FIELD();
END_LINE();
/* self->state = START_RECORD; */
}
else if (c == '\r') {
END_FIELD();
self->state = EAT_CRNL;
}
else if (!self->strict) {
PUSH_CHAR(c);
self->state = IN_FIELD;
}
else {
self->error_msg = (char*) malloc(50);
sprintf(self->error_msg, "'%c' expected after '%c'",
self->delimiter, self->quotechar);
goto parsingerror;
}
break;
case EAT_CRNL:
if (c == '\n') {
END_LINE();
/* self->state = START_RECORD; */
} else if (IS_WHITESPACE(c)){
// Handle \r-delimited files
END_LINE_AND_FIELD_STATE(EAT_WHITESPACE);
} else {
PUSH_CHAR(c);
END_LINE_STATE(IN_FIELD);
}
break;
case EAT_COMMENT:
if (c == '\n') {
END_LINE();
} else if (c == '\r') {
self->state = EAT_CRNL;
}
break;
default:
break;
}
}
_TOKEN_CLEANUP();
TRACE(("Finished tokenizing input\n"))
return 0;
parsingerror:
i++;
_TOKEN_CLEANUP();
return -1;
linelimit:
i++;
_TOKEN_CLEANUP();
return 0;
}
