void
NasmLexer::LexIdentifier(Token* result, const char* cur_ptr, bool is_label)
{
// Match [_$#@~.?A-Za-z0-9]*, we have already matched [_?@A-Za-z]
unsigned int size;
unsigned char ch = *cur_ptr++;
while (isIdentifierBody(ch))
ch = *cur_ptr++;
--cur_ptr; // Back up over the skipped character.
// Fast path, no \ in identifier found. '\' might be an escaped newline.
if (ch != '\\')
{
FinishIdentifier:
const char* id_start = m_buf_ptr;
if (is_label)
FormTokenWithChars(result, cur_ptr, NasmToken::label);
else
FormTokenWithChars(result, cur_ptr, NasmToken::identifier);
// If we are in raw mode, return this identifier raw. There is no need
// to look up identifier information or attempt to macro expand it.
if (isLexingRawMode())
return;
// Fill in result.IdentifierInfo, looking up the identifier in the
// identifier table.
IdentifierInfo* ii = m_preproc->LookUpIdentifierInfo(result, id_start);
// Change the kind of this identifier to the appropriate token kind,
// e.g. turning "for" into a keyword.
unsigned int newtokkind = ii->getTokenKind();
if (newtokkind != Token::unknown)
result->setKind(newtokkind);
#if 0
// Finally, now that we know we have an identifier, pass this off to
// the preprocessor, which may macro expand it or something.
if (ii->isHandleIdentifierCase())
m_preproc->HandleIdentifier(result);
#endif
++num_identifier;
return;
}
// Otherwise, \ in identifier found. Enter slower path.
ch = getCharAndSize(cur_ptr, &size);
for (;;)
{
if (!isIdentifierBody(ch))
goto FinishIdentifier; // Found end of identifier.
// Otherwise, this character is good, consume it.
cur_ptr = ConsumeChar(cur_ptr, size, result);
ch = getCharAndSize(cur_ptr, &size);
while (isIdentifierBody(ch))
{
cur_ptr = ConsumeChar(cur_ptr, size, result);
ch = getCharAndSize(cur_ptr, &size);
}
}
}
