(datafusion-sqlparser-rs) branch main updated: Redshift utf8 idents (#1915)

[iffyio]

This is an automated email from the ASF dual-hosted git repository.

iffyio pushed a commit to branch main
in repository https://gitbox.apache.org/repos/asf/datafusion-sqlparser-rs.git


The following commit(s) were added to refs/heads/main by this push:
     new f32a41a0 Redshift utf8 idents (#1915)
f32a41a0 is described below

commit f32a41a00451888fea24ee3487e303c85b8204b3
Author: Yoav Cohen <59807311+yoavcl...@users.noreply.github.com>
AuthorDate: Tue Jul 1 13:52:29 2025 +0200

    Redshift utf8 idents (#1915)
---
 src/dialect/redshift.rs     | 10 ++++++----
 tests/sqlparser_common.rs   |  9 ++++++++-
 tests/sqlparser_redshift.rs |  5 +++++
 3 files changed, 19 insertions(+), 5 deletions(-)

diff --git a/src/dialect/redshift.rs b/src/dialect/redshift.rs
index feccca5d..9ad9c5fd 100644
--- a/src/dialect/redshift.rs
+++ b/src/dialect/redshift.rs
@@ -80,13 +80,15 @@ impl Dialect for RedshiftSqlDialect {
     }
 
     fn is_identifier_start(&self, ch: char) -> bool {
-        // Extends Postgres dialect with sharp
-        PostgreSqlDialect {}.is_identifier_start(ch) || ch == '#'
+        // Extends Postgres dialect with sharp and UTF-8 multibyte chars
+        // https://docs.aws.amazon.com/redshift/latest/dg/r_names.html
+        PostgreSqlDialect {}.is_identifier_start(ch) || ch == '#' || 
!ch.is_ascii()
     }
 
     fn is_identifier_part(&self, ch: char) -> bool {
-        // Extends Postgres dialect with sharp
-        PostgreSqlDialect {}.is_identifier_part(ch) || ch == '#'
+        // Extends Postgres dialect with sharp and UTF-8 multibyte chars
+        // https://docs.aws.amazon.com/redshift/latest/dg/r_names.html
+        PostgreSqlDialect {}.is_identifier_part(ch) || ch == '#' || 
!ch.is_ascii()
     }
 
     /// redshift has `CONVERT(type, value)` instead of `CONVERT(value, type)`
diff --git a/tests/sqlparser_common.rs b/tests/sqlparser_common.rs
index 42bdeae1..10a79252 100644
--- a/tests/sqlparser_common.rs
+++ b/tests/sqlparser_common.rs
@@ -11068,10 +11068,17 @@ fn parse_non_latin_identifiers() {
         Box::new(RedshiftSqlDialect {}),
         Box::new(MySqlDialect {}),
     ]);
-
     supported_dialects.verified_stmt("SELECT a.説明 FROM test.public.inter01 AS 
a");
     supported_dialects.verified_stmt("SELECT a.説明 FROM inter01 AS a, 
inter01_transactions AS b WHERE a.説明 = b.取引 GROUP BY a.説明");
     supported_dialects.verified_stmt("SELECT 説明, hühnervögel, garçon, Москва, 
東京 FROM inter01");
+
+    let supported_dialects = TestedDialects::new(vec![
+        Box::new(GenericDialect {}),
+        Box::new(DuckDbDialect {}),
+        Box::new(PostgreSqlDialect {}),
+        Box::new(MsSqlDialect {}),
+        Box::new(MySqlDialect {}),
+    ]);
     assert!(supported_dialects
         .parse_sql_statements("SELECT 💝 FROM table1")
         .is_err());
diff --git a/tests/sqlparser_redshift.rs b/tests/sqlparser_redshift.rs
index be2b6722..d539adf6 100644
--- a/tests/sqlparser_redshift.rs
+++ b/tests/sqlparser_redshift.rs
@@ -402,3 +402,8 @@ fn parse_extract_single_quotes() {
 fn parse_string_literal_backslash_escape() {
     redshift().one_statement_parses_to(r#"SELECT 'l\'auto'"#, "SELECT 
'l''auto'");
 }
+
+#[test]
+fn parse_utf8_multibyte_idents() {
+    redshift().verified_stmt("SELECT 🚀.city AS 🎸 FROM customers AS 🚀");
+}


---------------------------------------------------------------------
To unsubscribe, e-mail: commits-unsubscr...@datafusion.apache.org
For additional commands, e-mail: commits-h...@datafusion.apache.org