Add BigQuery dialect (apache#490)

Author: komukomo

examples/cli.rs

@@ -38,6 +38,7 @@ $ cargo run --feature json_example --example cli FILENAME.sql [--dialectname]
 
     let dialect: Box<dyn Dialect> = match std::env::args().nth(2).unwrap_or_default().as_ref() {
         "--ansi" => Box::new(AnsiDialect {}),
+        "--bigquery" => Box::new(BigQueryDialect {}),
         "--postgres" => Box::new(PostgreSqlDialect {}),
         "--ms" => Box::new(MsSqlDialect {}),
         "--mysql" => Box::new(MySqlDialect {}),

src/dialect/bigquery.rs

@@ -0,0 +1,35 @@
+// Licensed 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 crate::dialect::Dialect;
+
+#[derive(Debug, Default)]
+pub struct BigQueryDialect;
+
+impl Dialect for BigQueryDialect {
+    // See https://cloud.google.com/bigquery/docs/reference/standard-sql/lexical#identifiers
+    fn is_delimited_identifier_start(&self, ch: char) -> bool {
+        ch == '`'
+    }
+
+    fn is_identifier_start(&self, ch: char) -> bool {
+        ('a'..='z').contains(&ch) || ('A'..='Z').contains(&ch) || ch == '_'
+    }
+
+    fn is_identifier_part(&self, ch: char) -> bool {
+        ('a'..='z').contains(&ch)
+            || ('A'..='Z').contains(&ch)
+            || ('0'..='9').contains(&ch)
+            || ch == '_'
+            || ch == '-'
+    }
+}

src/dialect/mod.rs

@@ -11,6 +11,7 @@
 // limitations under the License.
 
 mod ansi;
+mod bigquery;
 mod clickhouse;
 mod generic;
 mod hive;
@@ -27,6 +28,7 @@ use core::iter::Peekable;
 use core::str::Chars;
 
 pub use self::ansi::AnsiDialect;
+pub use self::bigquery::BigQueryDialect;
 pub use self::clickhouse::ClickHouseDialect;
 pub use self::generic::GenericDialect;
 pub use self::hive::HiveDialect;

tests/sqlparser_bigquery.rs

@@ -0,0 +1,86 @@
+// Licensed 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.
+
+#[macro_use]
+mod test_utils;
+
+use test_utils::*;
+
+use sqlparser::ast::*;
+use sqlparser::dialect::BigQueryDialect;
+
+#[test]
+fn parse_table_identifiers() {
+    fn test_table_ident(ident: &str, expected: Vec<Ident>) {
+        let sql = format!("SELECT 1 FROM {}", ident);
+        let select = bigquery().verified_only_select(&sql);
+        assert_eq!(
+            select.from,
+            vec![TableWithJoins {
+                relation: TableFactor::Table {
+                    name: ObjectName(expected),
+                    alias: None,
+                    args: vec![],
+                    with_hints: vec![],
+                },
+                joins: vec![]
+            },]
+        );
+    }
+    fn test_table_ident_err(ident: &str) {
+        let sql = format!("SELECT 1 FROM {}", ident);
+        assert!(bigquery().parse_sql_statements(&sql).is_err());
+    }
+
+    test_table_ident("da-sh-es", vec![Ident::new("da-sh-es")]);
+
+    test_table_ident("`spa ce`", vec![Ident::with_quote('`', "spa ce")]);
+
+    test_table_ident(
+        "`!@#$%^&*()-=_+`",
+        vec![Ident::with_quote('`', "!@#$%^&*()-=_+")],
+    );
+
+    test_table_ident(
+        "_5abc.dataField",
+        vec![Ident::new("_5abc"), Ident::new("dataField")],
+    );
+    test_table_ident(
+        "`5abc`.dataField",
+        vec![Ident::with_quote('`', "5abc"), Ident::new("dataField")],
+    );
+
+    test_table_ident_err("5abc.dataField");
+
+    test_table_ident(
+        "abc5.dataField",
+        vec![Ident::new("abc5"), Ident::new("dataField")],
+    );
+
+    test_table_ident_err("abc5!.dataField");
+
+    test_table_ident(
+        "`GROUP`.dataField",
+        vec![Ident::with_quote('`', "GROUP"), Ident::new("dataField")],
+    );
+
+    // TODO: this should be error
+    // test_table_ident_err("GROUP.dataField");
+
+    test_table_ident("abc5.GROUP", vec![Ident::new("abc5"), Ident::new("GROUP")]);
+}
+
+fn bigquery() -> TestedDialects {
+    TestedDialects {
+        dialects: vec![Box::new(BigQueryDialect {})],
+    }
+}

tests/sqlparser_common.rs

@@ -23,7 +23,8 @@ mod test_utils;
 use matches::assert_matches;
 use sqlparser::ast::*;
 use sqlparser::dialect::{
-    AnsiDialect, GenericDialect, MsSqlDialect, PostgreSqlDialect, SQLiteDialect, SnowflakeDialect,
+    AnsiDialect, BigQueryDialect, GenericDialect, MsSqlDialect, PostgreSqlDialect, SQLiteDialect,
+    SnowflakeDialect,
 };
 use sqlparser::keywords::ALL_KEYWORDS;
 use sqlparser::parser::{Parser, ParserError};
@@ -4556,6 +4557,7 @@ fn test_placeholder() {
             Box::new(PostgreSqlDialect {}),
             Box::new(MsSqlDialect {}),
             Box::new(AnsiDialect {}),
+            Box::new(BigQueryDialect {}),
             Box::new(SnowflakeDialect {}),
             // Note: `$` is the starting word for the HiveDialect identifier
             // Box::new(sqlparser::dialect::HiveDialect {}),