Skip to content

Correctly tokenize nested comments in Databricks, Clickhouse, and ANSI #2044

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

Merged
merged 5 commits into from
Sep 26, 2025
Merged

Correctly tokenize nested comments in Databricks, Clickhouse, and ANSI #2044

Show file tree
Hide file tree
Changes from 3 commits
Commits
Show all changes
5 commits
Select commit Hold shift + click to select a range
9a9fd52
Correctly tokenize nested comments in Databricks
jmhain Sep 23, 2025
124184b
clickhouse too
jmhain Sep 24, 2025
3464a8f
believe it or not, ansi
jmhain Sep 24, 2025
ab18487
address feedback
jmhain Sep 25, 2025
db2bbfd
fix doc error
jmhain Sep 25, 2025
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
5 changes: 5 additions & 0 deletions src/dialect/ansi.rs
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -33,4 +33,9 @@ impl Dialect for AnsiDialect {
fn require_interval_qualifier(&self) -> bool {
true
}

// The SQL standard explictly states that block comments nest.
fn supports_nested_comments(&self) -> bool {
true
}
}
6 changes: 6 additions & 0 deletions src/dialect/clickhouse.rs
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -94,4 +94,10 @@ impl Dialect for ClickHouseDialect {
fn supports_group_by_with_modifier(&self) -> bool {
true
}

// Supported since 2020.
// See <https://clickhouse.com/docs/whats-new/changelog/2020#backward-incompatible-change-2>
fn supports_nested_comments(&self) -> bool {
true
}
}
5 changes: 5 additions & 0 deletions src/dialect/databricks.rs
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -64,4 +64,9 @@ impl Dialect for DatabricksDialect {
fn supports_struct_literal(&self) -> bool {
true
}

// https://docs.databricks.com/aws/en/sql/language-manual/sql-ref-syntax-comment
fn supports_nested_comments(&self) -> bool {
true
}
}
141 changes: 65 additions & 76 deletions src/tokenizer.rs
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -2419,7 +2419,7 @@ mod tests {
use crate::dialect::{
BigQueryDialect, ClickHouseDialect, HiveDialect, MsSqlDialect, MySqlDialect, SQLiteDialect,
};
use crate::test_utils::all_dialects_where;
use crate::test_utils::{all_dialects_except, all_dialects_where};
use core::fmt::Debug;

#[test]
Expand Down Expand Up @@ -3169,90 +3169,79 @@ mod tests {

#[test]
fn tokenize_nested_multiline_comment() {
let dialect = GenericDialect {};
let test_cases = vec![
(
"0/*multi-line\n* \n/* comment \n /*comment*/*/ */ /comment*/1",
vec![
Token::Number("0".to_string(), false),
Token::Whitespace(Whitespace::MultiLineComment(
"multi-line\n* \n/* comment \n /*comment*/*/ ".into(),
)),
Token::Whitespace(Whitespace::Space),
Token::Div,
Token::Word(Word {
value: "comment".to_string(),
quote_style: None,
keyword: Keyword::COMMENT,
}),
Token::Mul,
Token::Div,
Token::Number("1".to_string(), false),
],
),
(
"0/*multi-line\n* \n/* comment \n /*comment/**/ */ /comment*/*/1",
vec![
Token::Number("0".to_string(), false),
Token::Whitespace(Whitespace::MultiLineComment(
"multi-line\n* \n/* comment \n /*comment/**/ */ /comment*/".into(),
)),
Token::Number("1".to_string(), false),
],
),
(
"SELECT 1/* a /* b */ c */0",
vec![
Token::make_keyword("SELECT"),
Token::Whitespace(Whitespace::Space),
Token::Number("1".to_string(), false),
Token::Whitespace(Whitespace::MultiLineComment(" a /* b */ c ".to_string())),
Token::Number("0".to_string(), false),
],
),
];
all_dialects_where(|d| d.supports_nested_comments()).tokenizes_to(
"0/*multi-line\n* \n/* comment \n /*comment*/*/ */ /comment*/1",
vec![
Token::Number("0".to_string(), false),
Token::Whitespace(Whitespace::MultiLineComment(
"multi-line\n* \n/* comment \n /*comment*/*/ ".into(),
)),
Token::Whitespace(Whitespace::Space),
Token::Div,
Token::Word(Word {
value: "comment".to_string(),
quote_style: None,
keyword: Keyword::COMMENT,
}),
Token::Mul,
Token::Div,
Token::Number("1".to_string(), false),
],
);

for (sql, expected) in test_cases {
let tokens = Tokenizer::new(&dialect, sql).tokenize().unwrap();
compare(expected, tokens);
}
all_dialects_where(|d| d.supports_nested_comments()).tokenizes_to(
"0/*multi-line\n* \n/* comment \n /*comment/**/ */ /comment*/*/1",
vec![
Token::Number("0".to_string(), false),
Token::Whitespace(Whitespace::MultiLineComment(
"multi-line\n* \n/* comment \n /*comment/**/ */ /comment*/".into(),
)),
Token::Number("1".to_string(), false),
],
);

all_dialects_where(|d| d.supports_nested_comments()).tokenizes_to(
"SELECT 1/* a /* b */ c */0",
vec![
Token::make_keyword("SELECT"),
Token::Whitespace(Whitespace::Space),
Token::Number("1".to_string(), false),
Token::Whitespace(Whitespace::MultiLineComment(" a /* b */ c ".to_string())),
Token::Number("0".to_string(), false),
],
);
}

#[test]
fn tokenize_nested_multiline_comment_empty() {
let sql = "select 1/*/**/*/0";

let dialect = GenericDialect {};
let tokens = Tokenizer::new(&dialect, sql).tokenize().unwrap();
let expected = vec![
Token::make_keyword("select"),
Token::Whitespace(Whitespace::Space),
Token::Number("1".to_string(), false),
Token::Whitespace(Whitespace::MultiLineComment("/**/".to_string())),
Token::Number("0".to_string(), false),
];

compare(expected, tokens);
all_dialects_where(|d| d.supports_nested_comments()).tokenizes_to(
"select 1/*/**/*/0",
vec![
Token::make_keyword("select"),
Token::Whitespace(Whitespace::Space),
Token::Number("1".to_string(), false),
Token::Whitespace(Whitespace::MultiLineComment("/**/".to_string())),
Token::Number("0".to_string(), false),
],
);
}

#[test]
fn tokenize_nested_comments_if_not_supported() {
let dialect = SQLiteDialect {};
let sql = "SELECT 1/*/* nested comment */*/0";
let tokens = Tokenizer::new(&dialect, sql).tokenize();
let expected = vec![
Token::make_keyword("SELECT"),
Token::Whitespace(Whitespace::Space),
Token::Number("1".to_string(), false),
Token::Whitespace(Whitespace::MultiLineComment(
"/* nested comment ".to_string(),
)),
Token::Mul,
Token::Div,
Token::Number("0".to_string(), false),
];

compare(expected, tokens.unwrap());
all_dialects_except(|d| d.supports_nested_comments()).tokenizes_to(
"SELECT 1/*/* nested comment */*/0",
vec![
Token::make_keyword("SELECT"),
Token::Whitespace(Whitespace::Space),
Token::Number("1".to_string(), false),
Token::Whitespace(Whitespace::MultiLineComment(
"/* nested comment ".to_string(),
)),
Token::Mul,
Token::Div,
Token::Number("0".to_string(), false),
],
);
}

#[test]
Expand Down