Merge branch 'main' into alter-operator

2025-12-23 11:12:51 +00:00 · 2025-12-04 11:35:12 +01:00 · 2025-12-04 11:35:12 +01:00 · 699ce46560
commit 699ce46560
parent 08e0a7011b effaac5c39
12 changed files with 213 additions and 10 deletions
--- a/Cargo.toml
+++ b/Cargo.toml
@ -18,7 +18,7 @@
 [package]
 name = "sqlparser"
 description = "Extensible SQL Lexer and Parser with support for ANSI SQL:2011"
-version = "0.59.0"
+version = "0.60.0"
 authors = ["Apache DataFusion <dev@datafusion.apache.org>"]
 homepage = "https://github.com/apache/datafusion-sqlparser-rs"
 documentation = "https://docs.rs/sqlparser/"
--- a/changelog/0.60.0.md
+++ b/changelog/0.60.0.md
@ -0,0 +1,98 @@
+<!--
+Licensed to the Apache Software Foundation (ASF) under one
+or more contributor license agreements.  See the NOTICE file
+distributed with this work for additional information
+regarding copyright ownership.  The ASF licenses this file
+to you under the Apache License, Version 2.0 (the
+"License"); you may not use this file except in compliance
+with the License.  You may obtain a copy of the License at
+
+  http://www.apache.org/licenses/LICENSE-2.0
+
+Unless required by applicable law or agreed to in writing,
+software distributed under the License is distributed on an
+"AS IS" BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY
+KIND, either express or implied.  See the License for the
+specific language governing permissions and limitations
+under the License.
+-->
+
+# sqlparser-rs 0.60.0 Changelog
+
+This release consists of 37 commits from 20 contributors. See credits at the end of this changelog for more information.
+
+**Implemented enhancements:**
+
+- feat: Add RESET to the base dialect #2078 [#2079](https://github.com/apache/datafusion-sqlparser-rs/pull/2079) (watford-ep)
+- feat: Add support for SET SESSION AUTHORIZATION #2086 [#2087](https://github.com/apache/datafusion-sqlparser-rs/pull/2087) (watford-ep)
+
+**Fixed bugs:**
+
+- fix: parse error on unnamed arg with default syntax [#2091](https://github.com/apache/datafusion-sqlparser-rs/pull/2091) (r1b)
+
+**Other:**
+
+- Add support for INVISIBLE columns in MySQL [#2033](https://github.com/apache/datafusion-sqlparser-rs/pull/2033) (altmannmarcelo)
+- Link to actual change logs in CHANGELOG.md [#2040](https://github.com/apache/datafusion-sqlparser-rs/pull/2040) (lovasoa)
+- Snowflake: ALTER USER and KeyValueOptions Refactoring [#2035](https://github.com/apache/datafusion-sqlparser-rs/pull/2035) (yoavcloud)
+- Correctly tokenize nested comments in Databricks, ClickHouse, and ANSI [#2044](https://github.com/apache/datafusion-sqlparser-rs/pull/2044) (jmhain)
+- MySQL: `CREATE INDEX`: allow `USING` clause before `ON` [#2029](https://github.com/apache/datafusion-sqlparser-rs/pull/2029) (MohamedAbdeen21)
+- [databricks] update dialect to support grouping by with modifier [#2047](https://github.com/apache/datafusion-sqlparser-rs/pull/2047) (n-young)
+- Moved constraint variant outside of `TableConstraint` enum [#2054](https://github.com/apache/datafusion-sqlparser-rs/pull/2054) (LucaCappelletti94)
+- Add support for procedure parameter default values [#2041](https://github.com/apache/datafusion-sqlparser-rs/pull/2041) (aharpervc)
+- Support updating PRs using github UI [#2052](https://github.com/apache/datafusion-sqlparser-rs/pull/2052) (blaginin)
+- Increase version of sqlparser_derive from 0.3.0 to 0.4.0 [#2060](https://github.com/apache/datafusion-sqlparser-rs/pull/2060) (jjbayer)
+- Moving several struct variants out of `Statement` enum to allow for trait impls for specific sub-variants [#2057](https://github.com/apache/datafusion-sqlparser-rs/pull/2057) (LucaCappelletti94)
+- Added support for SQLite triggers [#2037](https://github.com/apache/datafusion-sqlparser-rs/pull/2037) (LucaCappelletti94)
+- Added support for MATCH syntax and unified column option ForeignKey [#2062](https://github.com/apache/datafusion-sqlparser-rs/pull/2062) (LucaCappelletti94)
+- chore: add stack overflow warning for Visitor and VisitorMut [#2068](https://github.com/apache/datafusion-sqlparser-rs/pull/2068) (niebayes)
+- Reused `CheckConstraint` in `ColumnOption` [#2063](https://github.com/apache/datafusion-sqlparser-rs/pull/2063) (LucaCappelletti94)
+- Refactored `ColumnOption::Unique` to reuse `UniqueConstraint` and `PrimaryKeyConstraint` [#2064](https://github.com/apache/datafusion-sqlparser-rs/pull/2064) (LucaCappelletti94)
+- Redshift: more copy options [#2072](https://github.com/apache/datafusion-sqlparser-rs/pull/2072) (yoavcloud)
+- SQLite: make period optional for CREATE TRIGGER [#2071](https://github.com/apache/datafusion-sqlparser-rs/pull/2071) (takluyver)
+- Added TIMESTAMP_NTZ type support with precision to Snowflake dialect [#2080](https://github.com/apache/datafusion-sqlparser-rs/pull/2080) (romanoff)
+- Make `BitwiseNot` ("~") available for all dialects, not just PostgreSQL [#2081](https://github.com/apache/datafusion-sqlparser-rs/pull/2081) (alexander-beedie)
+- Add snowflake dynamic table parsing [#2083](https://github.com/apache/datafusion-sqlparser-rs/pull/2083) (romanoff)
+- Add support for `INSERT INTO VALUE` [#2085](https://github.com/apache/datafusion-sqlparser-rs/pull/2085) (etgarperets)
+- Complete PostgreSQL `CREATE TYPE` Support [#2094](https://github.com/apache/datafusion-sqlparser-rs/pull/2094) (LucaCappelletti94)
+- Include DML keyword in statement span [#2090](https://github.com/apache/datafusion-sqlparser-rs/pull/2090) (xitep)
+- Add PostgreSQL Operator DDL Support [#2096](https://github.com/apache/datafusion-sqlparser-rs/pull/2096) (LucaCappelletti94)
+- impl `Spanned` for MERGE statements [#2100](https://github.com/apache/datafusion-sqlparser-rs/pull/2100) (xitep)
+- Preserve optional `AS` keyword in aliases [#2103](https://github.com/apache/datafusion-sqlparser-rs/pull/2103) (xitep)
+- Added support for `DROP OPERATOR` syntax [#2102](https://github.com/apache/datafusion-sqlparser-rs/pull/2102) (LucaCappelletti94)
+- Only set `hive_formats` on `CreateTable` if formats are present [#2105](https://github.com/apache/datafusion-sqlparser-rs/pull/2105) (mvzink)
+- Support PostgreSQL C Functions with Multiple AS Parameters [#2095](https://github.com/apache/datafusion-sqlparser-rs/pull/2095) (LucaCappelletti94)
+- Added support for `DROP OPERATOR FAMILY` [#2106](https://github.com/apache/datafusion-sqlparser-rs/pull/2106) (LucaCappelletti94)
+- Update criterion requirement from 0.7 to 0.8 in /sqlparser_bench [#2111](https://github.com/apache/datafusion-sqlparser-rs/pull/2111) (dependabot[bot])
+- Added support for `DROP OPERATOR CLASS` syntax [#2109](https://github.com/apache/datafusion-sqlparser-rs/pull/2109) (LucaCappelletti94)
+- Introduce Oracle dialect [#2113](https://github.com/apache/datafusion-sqlparser-rs/pull/2113) (xitep)
+
+## Credits
+
+Thank you to everyone who contributed to this release. Here is a breakdown of commits (PRs merged) per contributor.
+
+```
+    12	Luca Cappelletti
+     4	xitep
+     2	Andriy Romanov
+     2	Christopher Watford
+     2	Yoav Cohen
+     1	Alexander Beedie
+     1	Andrew Harper
+     1	Dmitrii Blaginin
+     1	Joey Hain
+     1	Joris Bayer
+     1	Marcelo Altmann
+     1	Michael Victor Zink
+     1	Mohamed Abdeen
+     1	Ophir LOJKINE
+     1	Thomas Kluyver
+     1	dependabot[bot]
+     1	etgarperets
+     1	nick young
+     1	niebayes
+     1	r1b
+```
+
+Thank you also to everyone who contributed in other ways such as filing issues, reviewing PRs, and providing feedback on this release.
+
--- a/dev/release/verify-release-candidate.sh
+++ b/dev/release/verify-release-candidate.sh
@ -124,13 +124,15 @@ test_source_distribution() {
  cargo build
  cargo test --all-features

-  if ( find -iname 'Cargo.toml' | xargs grep SNAPSHOT ); then
+  if ( find . -iname 'Cargo.toml' | xargs grep SNAPSHOT ); then
    echo "Cargo.toml version should not contain SNAPSHOT for releases"
    exit 1
  fi

+  # Can't test using dry-run because sqlparser depends on sqlparser_derive
+  # see https://github.com/crate-ci/cargo-release/issues/691#issuecomment-2059866021
  # Check that publish works
-  cargo publish --dry-run
+  # cargo publish --dry-run
 }

 TEST_SUCCESS=no
--- a/examples/cli.rs
+++ b/examples/cli.rs
@ -58,6 +58,7 @@ $ cargo run --example cli - [--dialectname]
        "--clickhouse" => Box::new(ClickHouseDialect {}),
        "--duckdb" => Box::new(DuckDbDialect {}),
        "--sqlite" => Box::new(SQLiteDialect {}),
+        "--oracle" => Box::new(OracleDialect {}),
        "--generic" | "" => Box::new(GenericDialect {}),
        s => panic!("Unexpected parameter: {s}"),
    };
--- a/src/ast/ddl.rs
+++ b/src/ast/ddl.rs
@ -2900,7 +2900,9 @@ impl fmt::Display for CreateTable {
            if let Some(file_format) = self.file_format {
                write!(f, " STORED AS {file_format}")?;
            }
-            write!(f, " LOCATION '{}'", self.location.as_ref().unwrap())?;
+            if let Some(location) = &self.location {
+                write!(f, " LOCATION '{location}'")?;
+            }
        }

        match &self.table_options {
--- a/src/dialect/mod.rs
+++ b/src/dialect/mod.rs
@ -24,6 +24,7 @@ mod generic;
 mod hive;
 mod mssql;
 mod mysql;
+mod oracle;
 mod postgresql;
 mod redshift;
 mod snowflake;
@ -45,6 +46,7 @@ pub use self::generic::GenericDialect;
 pub use self::hive::HiveDialect;
 pub use self::mssql::MsSqlDialect;
 pub use self::mysql::MySqlDialect;
+pub use self::oracle::OracleDialect;
 pub use self::postgresql::PostgreSqlDialect;
 pub use self::redshift::RedshiftSqlDialect;
 pub use self::snowflake::SnowflakeDialect;
@ -1260,6 +1262,7 @@ pub fn dialect_from_str(dialect_name: impl AsRef<str>) -> Option<Box<dyn Dialect
        "ansi" => Some(Box::new(AnsiDialect {})),
        "duckdb" => Some(Box::new(DuckDbDialect {})),
        "databricks" => Some(Box::new(DatabricksDialect {})),
+        "oracle" => Some(Box::new(OracleDialect {})),
        _ => None,
    }
 }
--- a/src/dialect/oracle.rs
+++ b/src/dialect/oracle.rs
@ -0,0 +1,81 @@
+// Licensed to the Apache Software Foundation (ASF) under one
+// or more contributor license agreements.  See the NOTICE file
+// distributed with this work for additional information
+// regarding copyright ownership.  The ASF licenses this file
+// to you under the Apache License, Version 2.0 (the
+// "License"); you may not use this file except in compliance
+// with the License.  You may obtain a copy of the License at
+//
+//   http://www.apache.org/licenses/LICENSE-2.0
+//
+// Unless required by applicable law or agreed to in writing,
+// software distributed under the License is distributed on an
+// "AS IS" BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY
+// KIND, either express or implied.  See the License for the
+// specific language governing permissions and limitations
+// under the License.
+
+use super::Dialect;
+
+/// A [`Dialect`] for [Oracle Databases](https://docs.oracle.com/en/database/oracle/oracle-database/21/sqlrf/index.html)
+#[derive(Debug)]
+pub struct OracleDialect;
+
+impl Dialect for OracleDialect {
+    // ~ appears not to be called anywhere
+    fn identifier_quote_style(&self, _identifier: &str) -> Option<char> {
+        Some('"')
+    }
+
+    fn is_delimited_identifier_start(&self, ch: char) -> bool {
+        ch == '"'
+    }
+
+    fn is_identifier_start(&self, ch: char) -> bool {
+        ch.is_alphabetic()
+    }
+
+    fn is_identifier_part(&self, ch: char) -> bool {
+        ch.is_alphanumeric() || ch == '_' || ch == '$' || ch == '#' || ch == '@'
+    }
+
+    fn supports_outer_join_operator(&self) -> bool {
+        true
+    }
+
+    fn supports_connect_by(&self) -> bool {
+        true
+    }
+
+    fn supports_execute_immediate(&self) -> bool {
+        true
+    }
+
+    fn supports_match_recognize(&self) -> bool {
+        true
+    }
+
+    fn supports_window_function_null_treatment_arg(&self) -> bool {
+        true
+    }
+
+    fn supports_boolean_literals(&self) -> bool {
+        false
+    }
+
+    fn supports_comment_on(&self) -> bool {
+        true
+    }
+
+    fn supports_create_table_select(&self) -> bool {
+        true
+    }
+
+    fn supports_set_stmt_without_operator(&self) -> bool {
+        true
+    }
+
+    fn supports_group_by_expr(&self) -> bool {
+        true
+    }
+}
--- a/src/keywords.rs
+++ b/src/keywords.rs
@ -229,6 +229,7 @@ define_keywords!(
    COMMITTED,
    COMMUTATOR,
    COMPATIBLE,
+    COMPRESS,
    COMPRESSION,
    COMPUPDATE,
    COMPUTE,
@ -473,6 +474,7 @@ define_keywords!(
    IAM_ROLE,
    ICEBERG,
    ID,
+    IDENTIFIED,
    IDENTITY,
    IDENTITY_INSERT,
    IF,
@ -576,6 +578,7 @@ define_keywords!(
    LOG,
    LOGIN,
    LOGS,
+    LONG,
    LONGBLOB,
    LONGTEXT,
    LOWCARDINALITY,
@ -661,6 +664,7 @@ define_keywords!(
    NFKD,
    NO,
    NOBYPASSRLS,
+    NOCOMPRESS,
    NOCREATEDB,
    NOCREATEROLE,
    NOINHERIT,
@ -684,6 +688,7 @@ define_keywords!(
    NULLABLE,
    NULLIF,
    NULLS,
+    NUMBER,
    NUMERIC,
    NVARCHAR,
    OBJECT,
@ -750,6 +755,7 @@ define_keywords!(
    PAST,
    PATH,
    PATTERN,
+    PCTFREE,
    PER,
    PERCENT,
    PERCENTILE_CONT,
@ -922,6 +928,7 @@ define_keywords!(
    SIGNED,
    SIMILAR,
    SIMPLE,
+    SIZE,
    SKIP,
    SLOW,
    SMALLINT,
@ -983,6 +990,7 @@ define_keywords!(
    SWAP,
    SYMMETRIC,
    SYNC,
+    SYNONYM,
    SYSTEM,
    SYSTEM_TIME,
    SYSTEM_USER,
@ -1094,6 +1102,7 @@ define_keywords!(
    VARBINARY,
    VARBIT,
    VARCHAR,
+    VARCHAR2,
    VARIABLE,
    VARIABLES,
    VARYING,
--- a/src/parser/mod.rs
+++ b/src/parser/mod.rs
@ -12400,7 +12400,7 @@ impl<'a> Parser<'a> {
        let (tables, with_from_keyword) = if !self.parse_keyword(Keyword::FROM) {
            // `FROM` keyword is optional in BigQuery SQL.
            // https://cloud.google.com/bigquery/docs/reference/standard-sql/dml-syntax#delete_statement
-            if dialect_of!(self is BigQueryDialect | GenericDialect) {
+            if dialect_of!(self is BigQueryDialect | OracleDialect | GenericDialect) {
                (vec![], false)
            } else {
                let tables = self.parse_comma_separated(|p| p.parse_object_name(false))?;
--- a/src/test_utils.rs
+++ b/src/test_utils.rs
@ -291,6 +291,7 @@ pub fn all_dialects() -> TestedDialects {
        Box::new(DuckDbDialect {}),
        Box::new(DatabricksDialect {}),
        Box::new(ClickHouseDialect {}),
+        Box::new(OracleDialect {}),
    ])
 }

--- a/tests/sqlparser_common.rs
+++ b/tests/sqlparser_common.rs
@ -34,8 +34,8 @@ use sqlparser::ast::TableFactor::{Pivot, Unpivot};
 use sqlparser::ast::*;
 use sqlparser::dialect::{
    AnsiDialect, BigQueryDialect, ClickHouseDialect, DatabricksDialect, Dialect, DuckDbDialect,
-    GenericDialect, HiveDialect, MsSqlDialect, MySqlDialect, PostgreSqlDialect, RedshiftSqlDialect,
-    SQLiteDialect, SnowflakeDialect,
+    GenericDialect, HiveDialect, MsSqlDialect, MySqlDialect, OracleDialect, PostgreSqlDialect,
+    RedshiftSqlDialect, SQLiteDialect, SnowflakeDialect,
 };
 use sqlparser::keywords::{Keyword, ALL_KEYWORDS};
 use sqlparser::parser::{Parser, ParserError, ParserOptions};
@ -712,7 +712,9 @@ fn parse_delete_statement() {
 fn parse_delete_without_from_error() {
    let sql = "DELETE \"table\" WHERE 1";

-    let dialects = all_dialects_except(|d| d.is::<BigQueryDialect>() || d.is::<GenericDialect>());
+    let dialects = all_dialects_except(|d| {
+        d.is::<BigQueryDialect>() || d.is::<OracleDialect>() || d.is::<GenericDialect>()
+    });
    let res = dialects.parse_sql_statements(sql);
    assert_eq!(
        ParserError::ParserError("Expected: FROM, found: WHERE".to_string()),
@ -723,7 +725,9 @@ fn parse_delete_without_from_error() {
 #[test]
 fn parse_delete_statement_for_multi_tables() {
    let sql = "DELETE schema1.table1, schema2.table2 FROM schema1.table1 JOIN schema2.table2 ON schema2.table2.col1 = schema1.table1.col1 WHERE schema2.table2.col2 = 1";
-    let dialects = all_dialects_except(|d| d.is::<BigQueryDialect>() || d.is::<GenericDialect>());
+    let dialects = all_dialects_except(|d| {
+        d.is::<BigQueryDialect>() || d.is::<OracleDialect>() || d.is::<GenericDialect>()
+    });
    match dialects.verified_stmt(sql) {
        Statement::Delete(Delete {
            tables,
@ -12943,7 +12947,7 @@ fn test_match_recognize_patterns() {
    fn check(pattern: &str, expect: MatchRecognizePattern) {
        let select =
            all_dialects_where(|d| d.supports_match_recognize()).verified_only_select(&format!(
-                "SELECT * FROM my_table MATCH_RECOGNIZE(PATTERN ({pattern}) DEFINE DUMMY AS true)" // "select * from my_table match_recognize ("
+                "SELECT * FROM my_table MATCH_RECOGNIZE(PATTERN ({pattern}) DEFINE DUMMY AS 1 = 1)" // "select * from my_table match_recognize ("
            ));
        let TableFactor::MatchRecognize {
            pattern: actual, ..
--- a/tests/sqlparser_hive.rs
+++ b/tests/sqlparser_hive.rs
@ -34,10 +34,12 @@ fn parse_table_create() {
    let sql = r#"CREATE TABLE IF NOT EXISTS db.table (a BIGINT, b STRING, c TIMESTAMP) PARTITIONED BY (d STRING, e TIMESTAMP) STORED AS ORC LOCATION 's3://...' TBLPROPERTIES ("prop" = "2", "asdf" = '1234', 'asdf' = "1234", "asdf" = 2)"#;
    let iof = r#"CREATE TABLE IF NOT EXISTS db.table (a BIGINT, b STRING, c TIMESTAMP) PARTITIONED BY (d STRING, e TIMESTAMP) STORED AS INPUTFORMAT 'org.apache.hadoop.hive.ql.io.orc.OrcInputFormat' OUTPUTFORMAT 'org.apache.hadoop.hive.ql.io.orc.OrcOutputFormat' LOCATION 's3://...'"#;
    let serdeproperties = r#"CREATE EXTERNAL TABLE IF NOT EXISTS db.table (a STRING, b STRING, c STRING) PARTITIONED BY (d STRING, e STRING) ROW FORMAT SERDE 'org.apache.hadoop.hive.serde.config' WITH SERDEPROPERTIES ('prop_a' = 'a', 'prop_b' = 'b') STORED AS TEXTFILE LOCATION 's3://...' TBLPROPERTIES ('prop_c' = 'c')"#;
+    let externaltable = r#"CREATE EXTERNAL TABLE t (c INT)"#;

    hive().verified_stmt(sql);
    hive().verified_stmt(iof);
    hive().verified_stmt(serdeproperties);
+    hive().verified_stmt(externaltable);
 }

 #[test]