Skip to content

Fix the tokenization of < edge cases #2280

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Open
ayman-sigma wants to merge 1 commit into
base: main
Choose a base branch
from
+99 −8
Open

Fix the tokenization of < edge cases #2280

Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
107 changes: 99 additions & 8 deletions src/tokenizer.rs
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -1627,6 +1627,8 @@ impl<'a> Tokenizer<'a> {
chars.next();
match chars.peek() {
Some('>') => self.consume_for_binop(chars, "<=>", Token::Spaceship),
Some('+') => Ok(Some(Token::LtEq)),
Some('-') => Ok(Some(Token::LtEq)),
_ => self.start_binop(chars, "<=", Token::LtEq),
}
}
Expand All @@ -1646,13 +1648,13 @@ impl<'a> Tokenizer<'a> {
}
}
Some('<') => self.consume_for_binop(chars, "<<", Token::ShiftLeft),
Some('+') => Ok(Some(Token::Lt)),
Some('-') if self.dialect.supports_geometric_types() => {
chars.next(); // consume
match chars.peek() {
Some('>') => {
self.consume_for_binop(chars, "<->", Token::TwoWayArrow)
}
_ => self.start_binop_opt(chars, "<-", None),
if chars.peekable.clone().nth(1) == Some('>') {
chars.next(); // consume
self.consume_for_binop(chars, "<->", Token::TwoWayArrow)
} else {
Ok(Some(Token::Lt))
}
}
Some('^') if self.dialect.supports_geometric_types() => {
Expand Down Expand Up @@ -2628,9 +2630,10 @@ fn take_char_from_hex_digits(
mod tests {
use super::*;
use crate::dialect::{
BigQueryDialect, ClickHouseDialect, HiveDialect, MsSqlDialect, MySqlDialect, SQLiteDialect,
BigQueryDialect, ClickHouseDialect, HiveDialect, MsSqlDialect, MySqlDialect,
PostgreSqlDialect, SQLiteDialect,
};
use crate::test_utils::{all_dialects_except, all_dialects_where};
use crate::test_utils::{all_dialects, all_dialects_except, all_dialects_where};
use core::fmt::Debug;

#[test]
Expand Down Expand Up @@ -4420,4 +4423,92 @@ mod tests {
tokens,
);
}

#[test]
fn tokenize_lt() {
all_dialects().tokenizes_to(
"select a <-50",
vec![
Token::make_keyword("select"),
Token::Whitespace(Whitespace::Space),
Token::make_word("a", None),
Token::Whitespace(Whitespace::Space),
Token::Lt,
Token::Minus,
Token::Number("50".to_string(), false),
],
);
all_dialects().tokenizes_to(
"select a <+50",
vec![
Token::make_keyword("select"),
Token::Whitespace(Whitespace::Space),
Token::make_word("a", None),
Token::Whitespace(Whitespace::Space),
Token::Lt,
Token::Plus,
Token::Number("50".to_string(), false),
],
);
all_dialects().tokenizes_to(
"select a <=-50",
vec![
Token::make_keyword("select"),
Token::Whitespace(Whitespace::Space),
Token::make_word("a", None),
Token::Whitespace(Whitespace::Space),
Token::LtEq,
Token::Minus,
Token::Number("50".to_string(), false),
],
);
all_dialects().tokenizes_to(
"select a <=+50",
vec![
Token::make_keyword("select"),
Token::Whitespace(Whitespace::Space),
Token::make_word("a", None),
Token::Whitespace(Whitespace::Space),
Token::LtEq,
Token::Plus,
Token::Number("50".to_string(), false),
],
);
all_dialects_where(|d| d.supports_geometric_types()).tokenizes_to(
"select a <->b",
vec![
Token::make_keyword("select"),
Token::Whitespace(Whitespace::Space),
Token::make_word("a", None),
Token::Whitespace(Whitespace::Space),
Token::TwoWayArrow,
Token::make_word("b", None),
],
);

all_dialects().tokenizes_to(
"select a <-b",
vec![
Token::make_keyword("select"),
Token::Whitespace(Whitespace::Space),
Token::make_word("a", None),
Token::Whitespace(Whitespace::Space),
Token::Lt,
Token::Minus,
Token::make_word("b", None),
],
);
all_dialects().tokenizes_to(
"select a <+b",
vec![
Token::make_keyword("select"),
Token::Whitespace(Whitespace::Space),
Token::make_word("a", None),
Token::Whitespace(Whitespace::Space),
Token::Lt,
Token::Plus,
Token::make_word("b", None),
],
);
}
}
Loading