Skip to content

ARROW-12109: [Rust][DataFusion] Implement SHOW COLUMNS #9866

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.

Sign up for GitHub

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

Closed
alamb wants to merge 2 commits into from
Closed

ARROW-12109: [Rust][DataFusion] Implement SHOW COLUMNS #9866

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
8722430
ARROW-12109: [Rust][DataFusion] Implement SHOW COLUMNS
alamb Mar 31, 2021
e3f1410
use into() rather than build()
alamb Mar 31, 2021
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
20 changes: 12 additions & 8 deletions rust/datafusion/src/catalog/information_schema.rs
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -115,7 +115,7 @@ impl InformationSchemaProvider {
builder.add_system_table(&catalog_name, INFORMATION_SCHEMA, COLUMNS);
}

let mem_table = builder.build();
let mem_table: MemTable = builder.into();

Arc::new(mem_table)
}
Expand Down Expand Up @@ -148,7 +148,7 @@ impl InformationSchemaProvider {
}
}

let mem_table = builder.build();
let mem_table: MemTable = builder.into();

Arc::new(mem_table)
}
Expand Down Expand Up @@ -231,21 +231,23 @@ impl InformationSchemaTablesBuilder {
self.table_names.append_value(table_name.as_ref()).unwrap();
self.table_types.append_value("VIEW").unwrap();
}
}

fn build(self) -> MemTable {
impl From<InformationSchemaTablesBuilder> for MemTable {
fn from(value: InformationSchemaTablesBuilder) -> MemTable {
let schema = Schema::new(vec![
Field::new("table_catalog", DataType::Utf8, false),
Field::new("table_schema", DataType::Utf8, false),
Field::new("table_name", DataType::Utf8, false),
Field::new("table_type", DataType::Utf8, false),
]);

let Self {
let InformationSchemaTablesBuilder {
mut catalog_names,
mut schema_names,
mut table_names,
mut table_types,
} = self;
} = value;

let schema = Arc::new(schema);
let batch = RecordBatch::try_new(
Expand Down Expand Up @@ -422,8 +424,10 @@ impl InformationSchemaColumnsBuilder {
self.datetime_precisions.append_option(None).unwrap();
self.interval_types.append_null().unwrap();
}
}

fn build(self) -> MemTable {
impl From<InformationSchemaColumnsBuilder> for MemTable {
fn from(value: InformationSchemaColumnsBuilder) -> MemTable {
let schema = Schema::new(vec![
Field::new("table_catalog", DataType::Utf8, false),
Field::new("table_schema", DataType::Utf8, false),
Expand All @@ -442,7 +446,7 @@ impl InformationSchemaColumnsBuilder {
Field::new("interval_type", DataType::Utf8, false),
]);

let Self {
let InformationSchemaColumnsBuilder {
mut catalog_names,
mut schema_names,
mut table_names,
Expand All @@ -458,7 +462,7 @@ impl InformationSchemaColumnsBuilder {
mut numeric_scales,
mut datetime_precisions,
mut interval_types,
} = self;
} = value;

let schema = Arc::new(schema);
let batch = RecordBatch::try_new(
Expand Down
144 changes: 144 additions & 0 deletions rust/datafusion/src/execution/context.rs
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -2253,6 +2253,150 @@ mod tests {
assert_batches_sorted_eq!(expected, &result);
}

#[tokio::test]
async fn information_schema_show_columns_no_information_schema() {
let mut ctx = ExecutionContext::with_config(ExecutionConfig::new());

ctx.register_table("t", table_with_sequence(1, 1).unwrap())
.unwrap();

let err = plan_and_collect(&mut ctx, "SHOW COLUMNS FROM t")
.await
.unwrap_err();

assert_eq!(err.to_string(), "Error during planning: SHOW COLUMNS is not supported unless information_schema is enabled");
}

#[tokio::test]
async fn information_schema_show_columns_like_where() {
let mut ctx = ExecutionContext::with_config(ExecutionConfig::new());

ctx.register_table("t", table_with_sequence(1, 1).unwrap())
.unwrap();

let expected =
"Error during planning: SHOW COLUMNS with WHERE or LIKE is not supported";

let err = plan_and_collect(&mut ctx, "SHOW COLUMNS FROM t LIKE 'f'")
.await
.unwrap_err();
assert_eq!(err.to_string(), expected);

let err =
plan_and_collect(&mut ctx, "SHOW COLUMNS FROM t WHERE column_name = 'bar'")
.await
.unwrap_err();
assert_eq!(err.to_string(), expected);
}

#[tokio::test]
async fn information_schema_show_columns() {
let mut ctx = ExecutionContext::with_config(
ExecutionConfig::new().with_information_schema(true),
);

ctx.register_table("t", table_with_sequence(1, 1).unwrap())
.unwrap();

let result = plan_and_collect(&mut ctx, "SHOW COLUMNS FROM t")
.await
.unwrap();

let expected = vec![
"+---------------+--------------+------------+-------------+-----------+-------------+",
"| table_catalog | table_schema | table_name | column_name | data_type | is_nullable |",
"+---------------+--------------+------------+-------------+-----------+-------------+",
"| datafusion | public | t | i | Int32 | YES |",
"+---------------+--------------+------------+-------------+-----------+-------------+",
];
assert_batches_sorted_eq!(expected, &result);

let result = plan_and_collect(&mut ctx, "SHOW columns from t")
.await
.unwrap();
assert_batches_sorted_eq!(expected, &result);

// This isn't ideal but it is consistent behavior for `SELECT * from T`
let err = plan_and_collect(&mut ctx, "SHOW columns from T")
.await
.unwrap_err();
assert_eq!(
err.to_string(),
"Error during planning: Unknown relation for SHOW COLUMNS: T"
);
}

// test errors with WHERE and LIKE
#[tokio::test]
async fn information_schema_show_columns_full_extended() {
let mut ctx = ExecutionContext::with_config(
ExecutionConfig::new().with_information_schema(true),
);

ctx.register_table("t", table_with_sequence(1, 1).unwrap())
.unwrap();

let result = plan_and_collect(&mut ctx, "SHOW FULL COLUMNS FROM t")
.await
.unwrap();
let expected = vec![

"+---------------+--------------+------------+-------------+------------------+----------------+-------------+-----------+--------------------------+------------------------+-------------------+-------------------------+---------------+--------------------+---------------+",
"| table_catalog | table_schema | table_name | column_name | ordinal_position | column_default | is_nullable | data_type | character_maximum_length | character_octet_length | numeric_precision | numeric_precision_radix | numeric_scale | datetime_precision | interval_type |",
"+---------------+--------------+------------+-------------+------------------+----------------+-------------+-----------+--------------------------+------------------------+-------------------+-------------------------+---------------+--------------------+---------------+",
"| datafusion | public | t | i | 0 | | YES | Int32 | | | 32 | 2 | | | |",
"+---------------+--------------+------------+-------------+------------------+----------------+-------------+-----------+--------------------------+------------------------+-------------------+-------------------------+---------------+--------------------+---------------+",

];
assert_batches_sorted_eq!(expected, &result);

let result = plan_and_collect(&mut ctx, "SHOW EXTENDED COLUMNS FROM t")
.await
.unwrap();
assert_batches_sorted_eq!(expected, &result);
}

#[tokio::test]
async fn information_schema_show_table_table_names() {
let mut ctx = ExecutionContext::with_config(
ExecutionConfig::new().with_information_schema(true),
);

ctx.register_table("t", table_with_sequence(1, 1).unwrap())
.unwrap();

let result = plan_and_collect(&mut ctx, "SHOW COLUMNS FROM public.t")
.await
.unwrap();

let expected = vec![
"+---------------+--------------+------------+-------------+-----------+-------------+",
"| table_catalog | table_schema | table_name | column_name | data_type | is_nullable |",
"+---------------+--------------+------------+-------------+-----------+-------------+",
"| datafusion | public | t | i | Int32 | YES |",
"+---------------+--------------+------------+-------------+-----------+-------------+",
];
assert_batches_sorted_eq!(expected, &result);

let result = plan_and_collect(&mut ctx, "SHOW columns from datafusion.public.t")
.await
.unwrap();
assert_batches_sorted_eq!(expected, &result);

let err = plan_and_collect(&mut ctx, "SHOW columns from t2")
.await
.unwrap_err();
assert_eq!(
err.to_string(),
"Error during planning: Unknown relation for SHOW COLUMNS: t2"
);

let err = plan_and_collect(&mut ctx, "SHOW columns from datafusion.public.t2")
.await
.unwrap_err();
assert_eq!(err.to_string(), "Error during planning: Unknown relation for SHOW COLUMNS: datafusion.public.t2");
}

#[tokio::test]
async fn show_unsupported() {
let mut ctx = ExecutionContext::with_config(ExecutionConfig::new());
Expand Down
87 changes: 77 additions & 10 deletions rust/datafusion/src/sql/planner.rs
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -46,7 +46,8 @@ use crate::prelude::JoinType;
use sqlparser::ast::{
BinaryOperator, DataType as SQLDataType, DateTimeField, Expr as SQLExpr, FunctionArg,
Ident, Join, JoinConstraint, JoinOperator, ObjectName, Query, Select, SelectItem,
SetExpr, SetOperator, TableFactor, TableWithJoins, UnaryOperator, Value,
SetExpr, SetOperator, ShowStatementFilter, TableFactor, TableWithJoins,
UnaryOperator, Value,
};
use sqlparser::ast::{ColumnDef as SQLColumnDef, ColumnOption};
use sqlparser::ast::{OrderByExpr, Statement};
Expand Down Expand Up @@ -100,6 +101,12 @@ impl<'a, S: ContextProvider> SqlToRel<'a, S> {
} => self.explain_statement_to_plan(*verbose, &statement),
Statement::Query(query) => self.query_to_plan(&query),
Statement::ShowVariable { variable } => self.show_variable_to_plan(&variable),
Statement::ShowColumns {
extended,
full,
table_name,
filter,
} => self.show_columns_to_plan(*extended, *full, table_name, filter.as_ref()),
_ => Err(DataFusionError::NotImplemented(
"Only SELECT statements are implemented".to_string(),
)),
Expand Down Expand Up @@ -1280,15 +1287,7 @@ impl<'a, S: ContextProvider> SqlToRel<'a, S> {
// Special case SHOW TABLES
let variable = ObjectName(variable.to_vec()).to_string();
if variable.as_str().eq_ignore_ascii_case("tables") {
let tables_reference = TableReference::Partial {
schema: "information_schema",
table: "tables",
};
if self
.schema_provider
.get_table_provider(tables_reference)
.is_some()
{
if self.has_table("information_schema", "tables") {
let rewrite =
DFParser::parse_sql("SELECT * FROM information_schema.tables;")?;
self.statement_to_plan(&rewrite[0])
Expand All @@ -1305,6 +1304,74 @@ impl<'a, S: ContextProvider> SqlToRel<'a, S> {
)))
}
}

fn show_columns_to_plan(
&self,
extended: bool,
full: bool,
table_name: &ObjectName,
filter: Option<&ShowStatementFilter>,
) -> Result<LogicalPlan> {
if filter.is_some() {
return Err(DataFusionError::Plan(
"SHOW COLUMNS with WHERE or LIKE is not supported".to_string(),
));
}

if !self.has_table("information_schema", "columns") {
return Err(DataFusionError::Plan(
"SHOW COLUMNS is not supported unless information_schema is enabled"
.to_string(),
));
}

if self
.schema_provider
.get_table_provider(table_name.try_into()?)
.is_none()
{
return Err(DataFusionError::Plan(format!(
"Unknown relation for SHOW COLUMNS: {}",
table_name
)));
}

// Figure out the where clause
let columns = vec!["table_name", "table_schema", "table_catalog"].into_iter();
let where_clause = table_name
.0
.iter()
.rev()
Copy link
Contributor

@Dandandan Dandandan Apr 1, 2021 •
edited
Loading

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Why rev and not listing the items in columns in reverse?

Copy link
Contributor Author

@alamb alamb Apr 1, 2021

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

I was thinking because the identifier may not have a table_catalog or table_schema

So you have to handle the case of

table_name (position 0)
table_name (position 1), schema_name (postition 0)
table_name (postition 2), schema_name (postition 1), catalog_name (position 0),

So this formulation was what I could come up with that would match them up to the information_schema column names

I am open to other ways of doing it as well if you have suggestions

Copy link
Contributor

@Dandandan Dandandan Apr 5, 2021

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

You are totally right 👍 I don't have a suggestion for an easier way

.zip(columns)
.map(|(ident, column_name)| {
format!(r#"{} = '{}'"#, column_name, ident.to_string())
})
.collect::<Vec<_>>()
.join(" AND ");

// treat both FULL and EXTENDED as the same
let select_list = if full || extended {
"*"
} else {
"table_catalog, table_schema, table_name, column_name, data_type, is_nullable"
};

let query = format!(
"SELECT {} FROM information_schema.columns WHERE {}",
select_list, where_clause
);

let rewrite = DFParser::parse_sql(&query)?;
self.statement_to_plan(&rewrite[0])
}

/// Return true if there is a table provider available for "schema.table"
fn has_table(&self, schema: &str, table: &str) -> bool {
let tables_reference = TableReference::Partial { schema, table };
self.schema_provider
.get_table_provider(tables_reference)
.is_some()
}
}

/// Remove join expressions from a filter expression
Expand Down