iffyio commented on code in PR #1835:
URL:
https://github.com/apache/datafusion-sqlparser-rs/pull/1835#discussion_r2080640522
##########
src/tokenizer.rs:
##########
@@ -1281,20 +1262,91 @@ impl<'a> Tokenizer<'a> {
return Ok(Some(Token::make_word(s.as_str(),
None)));
}
} else if prev_token == Some(&Token::Period) {
- // If the previous token was a period, thus not
belonging to a number,
- // the value we have is part of an identifier.
+ // Handle as word if it follows a period
return Ok(Some(Token::make_word(s.as_str(),
None)));
}
}
+ // Handle "L" suffix for long numbers
let long = if chars.peek() == Some(&'L') {
chars.next();
true
} else {
false
};
+
+ // Return the final token for the number
Ok(Some(Token::Number(s, long)))
}
+
+ // Period (`.`) handling
+ '.' => {
+ chars.next(); // consume the dot
+
+ match chars.peek() {
+ // Handle "._" case as a period followed by identifier
+ // if the last token was a word
+ Some('_') if matches!(prev_token,
Some(Token::Word(_))) => {
+ Ok(Some(Token::Period))
+ }
+ Some('_') => {
+ self.tokenizer_error(
+ chars.location(),
+ "Unexpected underscore here".to_string(),
+ )
+ }
+ Some(ch)
+ // Hive and mysql dialects allow numeric prefixes
for identifers
+ if ch.is_ascii_digit()
+ && self.dialect.supports_numeric_prefix()
+ && matches!(prev_token, Some(Token::Word(_)))
=>
+ {
+ Ok(Some(Token::Period))
+ }
+ Some(ch) if ch.is_ascii_digit() => {
+ // Handle numbers starting with a dot (e.g.,
".123")
+ let mut s = String::from(".");
+ let is_number_separator = |ch: char, next_char:
Option<char>| {
+
self.dialect.supports_numeric_literal_underscores()
+ && ch == '_'
+ && next_char.is_some_and(|c|
c.is_ascii_digit())
+ };
+
+ s += &peeking_next_take_while(chars, |ch, next_ch|
{
+ ch.is_ascii_digit() || is_number_separator(ch,
next_ch)
+ });
+
+ // Handle exponent part
+ if matches!(chars.peek(), Some('e' | 'E')) {
+ let mut exp = String::new();
+ exp.push(chars.next().unwrap());
+
+ if matches!(chars.peek(), Some('+' | '-')) {
+ exp.push(chars.next().unwrap());
+ }
+
+ if matches!(chars.peek(), Some(c) if
c.is_ascii_digit()) {
+ exp += &peeking_take_while(chars, |c|
c.is_ascii_digit());
+ s += &exp;
+ }
+ }
+
+ // Handle "L" suffix for long numbers
+ let long = if chars.peek() == Some(&'L') {
+ chars.next();
+ true
Review Comment:
Oh is that really the case that cloning the peekable iterator would clone
the entire stream? (iirc it should only clone a struct with pointer offsets),
the functionality is used in a few places in the tokenizer so I think it would
be preferrable to avoid dup logic (if it turns out its an expensive thing to do
then maybe we need to do a pass through the tokenizer to avoid that pattern
overall, but that would be unrelated to this PR ofc)
--
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.
To unsubscribe, e-mail: github-unsubscr...@datafusion.apache.org
For queries about this service, please contact Infrastructure at:
us...@infra.apache.org
---------------------------------------------------------------------
To unsubscribe, e-mail: github-unsubscr...@datafusion.apache.org
For additional commands, e-mail: github-h...@datafusion.apache.org
