Add support for BigQuery table and view options (apache#1061)

Author: iffyio

src/ast/ddl.rs

@@ -26,6 +26,7 @@ use sqlparser_derive::{Visit, VisitMut};
 use crate::ast::value::escape_single_quote_string;
 use crate::ast::{
     display_comma_separated, display_separated, DataType, Expr, Ident, ObjectName, SequenceOptions,
+    SqlOption,
 };
 use crate::tokenizer::Token;
 
@@ -634,6 +635,42 @@ impl fmt::Display for ColumnDef {
     }
 }
 
+/// Column definition specified in a `CREATE VIEW` statement.
+///
+/// Syntax
+/// ```markdown
+/// <name> [OPTIONS(option, ...)]
+///
+/// option: <name> = <value>
+/// ```
+///
+/// Examples:
+/// ```sql
+/// name
+/// age OPTIONS(description = "age column", tag = "prod")
+/// ```
+#[derive(Debug, Clone, PartialEq, PartialOrd, Eq, Ord, Hash)]
+#[cfg_attr(feature = "serde", derive(Serialize, Deserialize))]
+#[cfg_attr(feature = "visitor", derive(Visit, VisitMut))]
+pub struct ViewColumnDef {
+    pub name: Ident,
+    pub options: Option<Vec<SqlOption>>,
+}
+
+impl fmt::Display for ViewColumnDef {
+    fn fmt(&self, f: &mut fmt::Formatter) -> fmt::Result {
+        write!(f, "{}", self.name)?;
+        if let Some(options) = self.options.as_ref() {
+            write!(
+                f,
+                " OPTIONS({})",
+                display_comma_separated(options.as_slice())
+            )?;
+        }
+        Ok(())
+    }
+}
+
 /// An optionally-named `ColumnOption`: `[ CONSTRAINT <name> ] <column-option>`.
 ///
 /// Note that implementations are substantially more permissive than the ANSI
@@ -710,6 +747,14 @@ pub enum ColumnOption {
         /// false if 'GENERATED ALWAYS' is skipped (option starts with AS)
         generated_keyword: bool,
     },
+    /// BigQuery specific: Explicit column options in a view [1] or table [2]
+    /// Syntax
+    /// ```sql
+    /// OPTIONS(description="field desc")
+    /// ```
+    /// [1]: https://cloud.google.com/bigquery/docs/reference/standard-sql/data-definition-language#view_column_option_list
+    /// [2]: https://cloud.google.com/bigquery/docs/reference/standard-sql/data-definition-language#column_option_list
+    Options(Vec<SqlOption>),
 }
 
 impl fmt::Display for ColumnOption {
@@ -788,6 +833,9 @@ impl fmt::Display for ColumnOption {
                     Ok(())
                 }
             }
+            Options(options) => {
+                write!(f, "OPTIONS({})", display_comma_separated(options))
+            }
         }
     }
 }

src/ast/helpers/stmt_create_table.rs

@@ -8,8 +8,8 @@ use serde::{Deserialize, Serialize};
 use sqlparser_derive::{Visit, VisitMut};
 
 use crate::ast::{
-    ColumnDef, FileFormat, HiveDistributionStyle, HiveFormat, Ident, ObjectName, OnCommit, Query,
-    SqlOption, Statement, TableConstraint,
+    ColumnDef, Expr, FileFormat, HiveDistributionStyle, HiveFormat, Ident, ObjectName, OnCommit,
+    Query, SqlOption, Statement, TableConstraint,
 };
 use crate::parser::ParserError;
 
@@ -72,6 +72,9 @@ pub struct CreateTableBuilder {
     pub on_commit: Option<OnCommit>,
     pub on_cluster: Option<String>,
     pub order_by: Option<Vec<Ident>>,
+    pub partition_by: Option<Box<Expr>>,
+    pub cluster_by: Option<Vec<Ident>>,
+    pub options: Option<Vec<SqlOption>>,
     pub strict: bool,
 }
 
@@ -105,6 +108,9 @@ impl CreateTableBuilder {
             on_commit: None,
             on_cluster: None,
             order_by: None,
+            partition_by: None,
+            cluster_by: None,
+            options: None,
             strict: false,
         }
     }
@@ -236,6 +242,21 @@ impl CreateTableBuilder {
         self
     }
 
+    pub fn partition_by(mut self, partition_by: Option<Box<Expr>>) -> Self {
+        self.partition_by = partition_by;
+        self
+    }
+
+    pub fn cluster_by(mut self, cluster_by: Option<Vec<Ident>>) -> Self {
+        self.cluster_by = cluster_by;
+        self
+    }
+
+    pub fn options(mut self, options: Option<Vec<SqlOption>>) -> Self {
+        self.options = options;
+        self
+    }
+
     pub fn strict(mut self, strict: bool) -> Self {
         self.strict = strict;
         self
@@ -270,6 +291,9 @@ impl CreateTableBuilder {
             on_commit: self.on_commit,
             on_cluster: self.on_cluster,
             order_by: self.order_by,
+            partition_by: self.partition_by,
+            cluster_by: self.cluster_by,
+            options: self.options,
             strict: self.strict,
         }
     }
@@ -310,6 +334,9 @@ impl TryFrom<Statement> for CreateTableBuilder {
                 on_commit,
                 on_cluster,
                 order_by,
+                partition_by,
+                cluster_by,
+                options,
                 strict,
             } => Ok(Self {
                 or_replace,
@@ -339,6 +366,9 @@ impl TryFrom<Statement> for CreateTableBuilder {
                 on_commit,
                 on_cluster,
                 order_by,
+                partition_by,
+                cluster_by,
+                options,
                 strict,
             }),
             _ => Err(ParserError::ParserError(format!(
@@ -348,6 +378,14 @@ impl TryFrom<Statement> for CreateTableBuilder {
     }
 }
 
+/// Helper return type when parsing configuration for a BigQuery `CREATE TABLE` statement.
+#[derive(Default)]
+pub(crate) struct BigQueryTableConfiguration {
+    pub partition_by: Option<Box<Expr>>,
+    pub cluster_by: Option<Vec<Ident>>,
+    pub options: Option<Vec<SqlOption>>,
+}
+
 #[cfg(test)]
 mod tests {
     use crate::ast::helpers::stmt_create_table::CreateTableBuilder;

src/ast/mod.rs

@@ -34,7 +34,7 @@ pub use self::ddl::{
     AlterColumnOperation, AlterIndexOperation, AlterTableOperation, ColumnDef, ColumnOption,
     ColumnOptionDef, GeneratedAs, GeneratedExpressionMode, IndexType, KeyOrIndexDisplay, Partition,
     ProcedureParam, ReferentialAction, TableConstraint, UserDefinedTypeCompositeAttributeDef,
-    UserDefinedTypeRepresentation,
+    UserDefinedTypeRepresentation, ViewColumnDef,
 };
 pub use self::operator::{BinaryOperator, UnaryOperator};
 pub use self::query::{
@@ -1367,6 +1367,38 @@ pub enum Password {
     NullPassword,
 }
 
+/// Sql options of a `CREATE TABLE` statement.
+#[derive(Debug, Clone, PartialEq, PartialOrd, Eq, Ord, Hash)]
+#[cfg_attr(feature = "serde", derive(Serialize, Deserialize))]
+#[cfg_attr(feature = "visitor", derive(Visit, VisitMut))]
+pub enum CreateTableOptions {
+    None,
+    /// Options specified using the `WITH` keyword.
+    /// e.g. `WITH (description = "123")`
+    ///
+    /// <https://www.postgresql.org/docs/current/sql-createtable.html>
+    With(Vec<SqlOption>),
+    /// Options specified using the `OPTIONS` keyword.
+    /// e.g. `OPTIONS(description = "123")`
+    ///
+    /// <https://cloud.google.com/bigquery/docs/reference/standard-sql/data-definition-language#table_option_list>
+    Options(Vec<SqlOption>),
+}
+
+impl fmt::Display for CreateTableOptions {
+    fn fmt(&self, f: &mut fmt::Formatter) -> fmt::Result {
+        match self {
+            CreateTableOptions::With(with_options) => {
+                write!(f, "WITH ({})", display_comma_separated(with_options))
+            }
+            CreateTableOptions::Options(options) => {
+                write!(f, "OPTIONS({})", display_comma_separated(options))
+            }
+            CreateTableOptions::None => Ok(()),
+        }
+    }
+}
+
 /// A top-level statement (SELECT, INSERT, CREATE, etc.)
 #[allow(clippy::large_enum_variant)]
 #[derive(Debug, Clone, PartialEq, PartialOrd, Eq, Ord, Hash)]
@@ -1550,9 +1582,9 @@ pub enum Statement {
         materialized: bool,
         /// View name
         name: ObjectName,
-        columns: Vec<Ident>,
+        columns: Vec<ViewColumnDef>,
         query: Box<Query>,
-        with_options: Vec<SqlOption>,
+        options: CreateTableOptions,
         cluster_by: Vec<Ident>,
         /// if true, has RedShift [`WITH NO SCHEMA BINDING`] clause <https://docs.aws.amazon.com/redshift/latest/dg/r_CREATE_VIEW.html>
         with_no_schema_binding: bool,
@@ -1600,6 +1632,15 @@ pub enum Statement {
         /// than empty (represented as ()), the latter meaning "no sorting".
         /// <https://clickhouse.com/docs/en/sql-reference/statements/create/table/>
         order_by: Option<Vec<Ident>>,
+        /// BigQuery: A partition expression for the table.
+        /// <https://cloud.google.com/bigquery/docs/reference/standard-sql/data-definition-language#partition_expression>
+        partition_by: Option<Box<Expr>>,
+        /// BigQuery: Table clustering column list.
+        /// <https://cloud.google.com/bigquery/docs/reference/standard-sql/data-definition-language#table_option_list>
+        cluster_by: Option<Vec<Ident>>,
+        /// BigQuery: Table options list.
+        /// <https://cloud.google.com/bigquery/docs/reference/standard-sql/data-definition-language#table_option_list>
+        options: Option<Vec<SqlOption>>,
         /// SQLite "STRICT" clause.
         /// if the "STRICT" table-option keyword is added to the end, after the closing ")",
         /// then strict typing rules apply to that table.
@@ -2731,7 +2772,7 @@ impl fmt::Display for Statement {
                 columns,
                 query,
                 materialized,
-                with_options,
+                options,
                 cluster_by,
                 with_no_schema_binding,
                 if_not_exists,
@@ -2746,15 +2787,18 @@ impl fmt::Display for Statement {
                     temporary = if *temporary { "TEMPORARY " } else { "" },
                     if_not_exists = if *if_not_exists { "IF NOT EXISTS " } else { "" }
                 )?;
-                if !with_options.is_empty() {
-                    write!(f, " WITH ({})", display_comma_separated(with_options))?;
+                if matches!(options, CreateTableOptions::With(_)) {
+                    write!(f, " {options}")?;
                 }
                 if !columns.is_empty() {
                     write!(f, " ({})", display_comma_separated(columns))?;
                 }
                 if !cluster_by.is_empty() {
                     write!(f, " CLUSTER BY ({})", display_comma_separated(cluster_by))?;
                 }
+                if matches!(options, CreateTableOptions::Options(_)) {
+                    write!(f, " {options}")?;
+                }
                 write!(f, " AS {query}")?;
                 if *with_no_schema_binding {
                     write!(f, " WITH NO SCHEMA BINDING")?;
@@ -2789,6 +2833,9 @@ impl fmt::Display for Statement {
                 on_commit,
                 on_cluster,
                 order_by,
+                partition_by,
+                cluster_by,
+                options,
                 strict,
             } => {
                 // We want to allow the following options
@@ -2945,6 +2992,23 @@ impl fmt::Display for Statement {
                 if let Some(order_by) = order_by {
                     write!(f, " ORDER BY ({})", display_comma_separated(order_by))?;
                 }
+                if let Some(partition_by) = partition_by.as_ref() {
+                    write!(f, " PARTITION BY {partition_by}")?;
+                }
+                if let Some(cluster_by) = cluster_by.as_ref() {
+                    write!(
+                        f,
+                        " CLUSTER BY {}",
+                        display_comma_separated(cluster_by.as_slice())
+                    )?;
+                }
+                if let Some(options) = options.as_ref() {
+                    write!(
+                        f,
+                        " OPTIONS({})",
+                        display_comma_separated(options.as_slice())
+                    )?;
+                }
                 if let Some(query) = query {
                     write!(f, " AS {query}")?;
                 }
@@ -4496,7 +4560,7 @@ pub struct HiveFormat {
 #[cfg_attr(feature = "visitor", derive(Visit, VisitMut))]
 pub struct SqlOption {
     pub name: Ident,
-    pub value: Value,
+    pub value: Expr,
 }
 
 impl fmt::Display for SqlOption {