Skip to content

parser: fix unicode escape strings being parsed as byte strings #871

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
kodiakhq merged 1 commit into from
Jan 20, 2026
Merged

parser: fix unicode escape strings being parsed as byte strings #871

Show file tree
Hide file tree
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
1 change: 1 addition & 0 deletions crates/squawk_ide/src/tokens.rs
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -6,6 +6,7 @@ pub(crate) fn is_string_or_comment(kind: SyntaxKind) -> bool {
SyntaxKind::COMMENT
| SyntaxKind::STRING
| SyntaxKind::BYTE_STRING
| SyntaxKind::UNICODE_ESC_STRING
| SyntaxKind::BIT_STRING
| SyntaxKind::DOLLAR_QUOTED_STRING
| SyntaxKind::ESC_STRING
Expand Down
1 change: 1 addition & 0 deletions crates/squawk_parser/src/generated/syntax_kind.rs
View file
Open in desktop

Some generated files are not rendered by default. Learn more about how customized files appear on GitHub.

3 changes: 2 additions & 1 deletion crates/squawk_parser/src/grammar.rs
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -35,7 +35,7 @@ fn literal(p: &mut Parser<'_>) -> Option<CompletedMarker> {
return None;
}
let m = p.start();
if p.eat(BYTE_STRING) {
if p.eat(UNICODE_ESC_STRING) {
if p.eat(UESCAPE_KW) {
p.eat(STRING);
}
Expand Down Expand Up @@ -4802,6 +4802,7 @@ const NUMERIC_FIRST: TokenSet = TokenSet::new(&[INT_NUMBER, FLOAT_NUMBER]);
const STRING_FIRST: TokenSet = TokenSet::new(&[
STRING,
BYTE_STRING,
UNICODE_ESC_STRING,
BIT_STRING,
DOLLAR_QUOTED_STRING,
ESC_STRING,
Expand Down
2 changes: 1 addition & 1 deletion crates/squawk_parser/src/lexed_str.rs
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -284,7 +284,7 @@ impl<'a> Converter<'a> {
err = "Missing trailing `'` symbol to terminate the unicode escape string literal";
}
// TODO: rust analzyer checks for un-escaped strings, we should too
SyntaxKind::BYTE_STRING
SyntaxKind::UNICODE_ESC_STRING
}
squawk_lexer::LiteralKind::EscStr { terminated } => {
if !terminated {
Expand Down
18 changes: 0 additions & 18 deletions crates/squawk_parser/src/lib.rs
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -424,24 +424,6 @@ impl<'t> Parser<'t> {
m.complete(self, SyntaxKind::IS_NOT);
return true;
}
// SyntaxKind::BYTE_STRING => {
// let m = self.start();
// self.bump(SyntaxKind::BYTE_STRING);
// if self.eat(SyntaxKind::UESCAPE_KW) {
// self.expect(SyntaxKind::STRING);
// }
// m.complete(self, SyntaxKind::BYTE_STRING);
// return true;
// }
// SyntaxKind::IDENT => {
// let m = self.start();
// self.bump(SyntaxKind::IDENT);
// if self.eat(SyntaxKind::UESCAPE_KW) {
// self.expect(SyntaxKind::STRING);
// }
// m.complete(self, SyntaxKind::IDENT);
// return true;
// }
SyntaxKind::CUSTOM_OP => {
let m = self.start();
while !self.at(SyntaxKind::EOF) {
Expand Down
2 changes: 1 addition & 1 deletion crates/squawk_parser/tests/snapshots/tests__select_ok.snap
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -6234,7 +6234,7 @@ SOURCE_FILE
TARGET_LIST
TARGET
LITERAL
BYTE_STRING "U&' \\'"
UNICODE_ESC_STRING "U&' \\'"
WHITESPACE " "
UESCAPE_KW "UESCAPE"
WHITESPACE " "
Expand Down
12 changes: 6 additions & 6 deletions crates/squawk_parser/tests/snapshots/tests__select_operators_ok.snap
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -1744,7 +1744,7 @@ SOURCE_FILE
TARGET
POSTFIX_EXPR
LITERAL
BYTE_STRING "U&'\\0061\\0308bc'"
UNICODE_ESC_STRING "U&'\\0061\\0308bc'"
WHITESPACE " "
IS_NORMALIZED
IS_KW "is"
Expand All @@ -1760,7 +1760,7 @@ SOURCE_FILE
TARGET
POSTFIX_EXPR
LITERAL
BYTE_STRING "U&'\\0061\\0308bc'"
UNICODE_ESC_STRING "U&'\\0061\\0308bc'"
WHITESPACE " "
IS_NORMALIZED
IS_KW "is"
Expand All @@ -1778,7 +1778,7 @@ SOURCE_FILE
TARGET
POSTFIX_EXPR
LITERAL
BYTE_STRING "U&'\\0061\\0308bc'"
UNICODE_ESC_STRING "U&'\\0061\\0308bc'"
WHITESPACE " "
IS_NORMALIZED
IS_KW "is"
Expand All @@ -1796,7 +1796,7 @@ SOURCE_FILE
TARGET
POSTFIX_EXPR
LITERAL
BYTE_STRING "U&'\\0061\\0308bc'"
UNICODE_ESC_STRING "U&'\\0061\\0308bc'"
WHITESPACE " "
IS_NORMALIZED
IS_KW "is"
Expand All @@ -1814,7 +1814,7 @@ SOURCE_FILE
TARGET
POSTFIX_EXPR
LITERAL
BYTE_STRING "U&'\\0061\\0308bc'"
UNICODE_ESC_STRING "U&'\\0061\\0308bc'"
WHITESPACE " "
IS_NORMALIZED
IS_KW "is"
Expand All @@ -1832,7 +1832,7 @@ SOURCE_FILE
TARGET
BIN_EXPR
LITERAL
BYTE_STRING "U&'\\0061\\0308bc'"
UNICODE_ESC_STRING "U&'\\0061\\0308bc'"
WHITESPACE " "
IS_NOT
IS_KW "is"
Expand Down
1 change: 1 addition & 0 deletions crates/squawk_syntax/src/postgresql.ungram
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -347,6 +347,7 @@ Literal =
| '@byte_string'
| '@bit_string'
| '@dollar_quoted_string'
| '@unicode_esc_string'
| '@esc_string'
| '@positional_param'
)
Expand Down
Loading