Skip to content

National strings: check if dialect supports backslash escape #1672

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.

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 4 commits into from
Jan 23, 2025
Merged
Show file tree
Hide file tree
Changes from all commits
Commits
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
14 changes: 13 additions & 1 deletion src/test_utils.rs
Original file line number Diff line number Diff line change
Expand Up @@ -33,7 +33,7 @@ use core::fmt::Debug;

use crate::dialect::*;
use crate::parser::{Parser, ParserError};
use crate::tokenizer::Tokenizer;
use crate::tokenizer::{Token, Tokenizer};
use crate::{ast::*, parser::ParserOptions};

#[cfg(test)]
Expand Down Expand Up @@ -237,6 +237,18 @@ impl TestedDialects {
pub fn verified_expr(&self, sql: &str) -> Expr {
self.expr_parses_to(sql, sql)
}

/// Check that the tokenizer returns the expected tokens for the given SQL.
pub fn tokenizes_to(&self, sql: &str, expected: Vec<Token>) {
self.dialects.iter().for_each(|dialect| {
let mut tokenizer = Tokenizer::new(&**dialect, sql);
if let Some(options) = &self.options {
tokenizer = tokenizer.with_unescape(options.unescape);
}
let tokens = tokenizer.tokenize().unwrap();
assert_eq!(expected, tokens);
});
}
}

/// Returns all available dialects.
Expand Down
32 changes: 31 additions & 1 deletion src/tokenizer.rs
Original file line number Diff line number Diff line change
Expand Up @@ -971,7 +971,10 @@ impl<'a> Tokenizer<'a> {
match chars.peek() {
Some('\'') => {
// N'...' - a <national character string literal>
let s = self.tokenize_single_quoted_string(chars, '\'', true)?;
let backslash_escape =
self.dialect.supports_string_literal_backslash_escape();
let s =
self.tokenize_single_quoted_string(chars, '\'', backslash_escape)?;
Ok(Some(Token::NationalStringLiteral(s)))
}
_ => {
Expand Down Expand Up @@ -2155,6 +2158,7 @@ mod tests {
use crate::dialect::{
BigQueryDialect, ClickHouseDialect, HiveDialect, MsSqlDialect, MySqlDialect, SQLiteDialect,
};
use crate::test_utils::all_dialects_where;
use core::fmt::Debug;

#[test]
Expand Down Expand Up @@ -3543,4 +3547,30 @@ mod tests {
];
compare(expected, tokens);
}

#[test]
fn test_national_strings_backslash_escape_not_supported() {
all_dialects_where(|dialect| !dialect.supports_string_literal_backslash_escape())
.tokenizes_to(
"select n'''''\\'",
vec![
Token::make_keyword("select"),
Token::Whitespace(Whitespace::Space),
Token::NationalStringLiteral("''\\".to_string()),
],
);
}

#[test]
fn test_national_strings_backslash_escape_supported() {
all_dialects_where(|dialect| dialect.supports_string_literal_backslash_escape())
.tokenizes_to(
"select n'''''\\''",
vec![
Token::make_keyword("select"),
Token::Whitespace(Whitespace::Space),
Token::NationalStringLiteral("'''".to_string()),
],
);
}
}
Loading