Skip to content
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

Nested Struct Access #2

Open
wants to merge 7 commits into
base: main
Choose a base branch
from
Open

Nested Struct Access #2

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
7 commits
Select commit Hold shift + click to select a range
1ec6fe6
plan compound_field_access syntax
goldmedal Dec 11, 2024
43e9307
fix compile
goldmedal Dec 26, 2024
1108f75
uprgrade sqlparser
goldmedal Dec 27, 2024
7096b76
update lock
goldmedal Dec 27, 2024
8bb8735
taplo fmt
goldmedal Dec 27, 2024
572ea6e
upgrade sqlparser
goldmedal Dec 28, 2024
56a96ab
cargo update
goldmedal Dec 28, 2024
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
4 changes: 3 additions & 1 deletion Cargo.toml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -147,7 +147,9 @@ recursive = "0.1.1"
regex = "1.8"
rstest = "0.23.0"
serde_json = "1"
sqlparser = { version = "0.53.0", features = ["visitor"] }
sqlparser = { git = "https://github.com/apache/datafusion-sqlparser-rs.git", rev = "6cbcfda74618e9d42caf4875b135288be1594cf0", features = [
"visitor",
] }
tempfile = "3"
tokio = { version = "1.36", features = ["macros", "rt", "sync"] }
url = "2.2"
Expand Down
17 changes: 8 additions & 9 deletions datafusion-cli/Cargo.lock
View file
Open in desktop

Some generated files are not rendered by default. Learn more about how customized files appear on GitHub.

220 changes: 138 additions & 82 deletions datafusion/sql/src/expr/mod.rs
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -21,14 +21,14 @@ use datafusion_expr::planner::{
PlannerResult, RawBinaryExpr, RawDictionaryExpr, RawFieldAccessExpr,
};
use sqlparser::ast::{
BinaryOperator, CastFormat, CastKind, DataType as SQLDataType, DictionaryField,
Expr as SQLExpr, ExprWithAlias as SQLExprWithAlias, MapEntry, StructField, Subscript,
TrimWhereField, Value,
AccessExpr, BinaryOperator, CastFormat, CastKind, DataType as SQLDataType,
DictionaryField, Expr as SQLExpr, ExprWithAlias as SQLExprWithAlias, MapEntry,
StructField, Subscript, TrimWhereField, Value,
};

use datafusion_common::{
internal_datafusion_err, internal_err, not_impl_err, plan_err, DFSchema, Result,
ScalarValue,
internal_datafusion_err, internal_err, not_impl_err, plan_err, Column, DFSchema,
Result, ScalarValue,
};
use datafusion_expr::expr::ScalarFunction;
use datafusion_expr::expr::{InList, WildcardOptions};
Expand Down Expand Up @@ -235,15 +235,14 @@ impl<S: ContextProvider> SqlToRel<'_, S> {
SQLExpr::Identifier(id) => {
self.sql_identifier_to_expr(id, schema, planner_context)
}

SQLExpr::MapAccess { .. } => {
not_impl_err!("Map Access")
}

// <expr>["foo"], <expr>[4] or <expr>[4:5]
SQLExpr::Subscript { expr, subscript } => {
self.sql_subscript_to_expr(*expr, subscript, schema, planner_context)
}
SQLExpr::CompoundFieldAccess { root, access_chain } => self
.sql_compound_field_access_to_expr(
*root,
access_chain,
schema,
planner_context,
),

SQLExpr::CompoundIdentifier(ids) => {
self.sql_compound_identifier_to_expr(ids, schema, planner_context)
Expand Down Expand Up @@ -984,84 +983,141 @@ impl<S: ContextProvider> SqlToRel<'_, S> {
Ok(Expr::Cast(Cast::new(Box::new(expr), dt)))
}

fn sql_subscript_to_expr(
fn sql_compound_field_access_to_expr(
&self,
expr: SQLExpr,
subscript: Box<Subscript>,
root: SQLExpr,
access_chain: Vec<AccessExpr>,
schema: &DFSchema,
planner_context: &mut PlannerContext,
) -> Result<Expr> {
let expr = self.sql_expr_to_logical_expr(expr, schema, planner_context)?;

let field_access = match *subscript {
Subscript::Index { index } => {
// index can be a name, in which case it is a named field access
match index {
SQLExpr::Value(
Value::SingleQuotedString(s) | Value::DoubleQuotedString(s),
) => GetFieldAccess::NamedStructField {
name: ScalarValue::from(s),
},
SQLExpr::JsonAccess { .. } => {
return not_impl_err!("JsonAccess");
let mut root = self.sql_expr_to_logical_expr(root, schema, planner_context)?;
let fields = access_chain
.into_iter()
.map(|field| match field {
AccessExpr::Subscript(subscript) => {
match subscript {
Subscript::Index { index } => {
// index can be a name, in which case it is a named field access
match index {
SQLExpr::Value(
Value::SingleQuotedString(s)
| Value::DoubleQuotedString(s),
) => Ok(Some(GetFieldAccess::NamedStructField {
name: ScalarValue::from(s),
})),
SQLExpr::JsonAccess { .. } => {
not_impl_err!("JsonAccess")
}
// otherwise treat like a list index
_ => Ok(Some(GetFieldAccess::ListIndex {
key: Box::new(self.sql_expr_to_logical_expr(
index,
schema,
planner_context,
)?),
})),
}
}
Subscript::Slice {
lower_bound,
upper_bound,
stride,
} => {
// Means access like [:2]
let lower_bound = if let Some(lower_bound) = lower_bound {
self.sql_expr_to_logical_expr(
lower_bound,
schema,
planner_context,
)
} else {
not_impl_err!("Slice subscript requires a lower bound")
}?;

// means access like [2:]
let upper_bound = if let Some(upper_bound) = upper_bound {
self.sql_expr_to_logical_expr(
upper_bound,
schema,
planner_context,
)
} else {
not_impl_err!("Slice subscript requires an upper bound")
}?;

// stride, default to 1
let stride = if let Some(stride) = stride {
self.sql_expr_to_logical_expr(
stride,
schema,
planner_context,
)?
} else {
lit(1i64)
};

Ok(Some(GetFieldAccess::ListRange {
start: Box::new(lower_bound),
stop: Box::new(upper_bound),
stride: Box::new(stride),
}))
}
}
// otherwise treat like a list index
_ => GetFieldAccess::ListIndex {
key: Box::new(self.sql_expr_to_logical_expr(
index,
schema,
planner_context,
)?),
},
}
}
Subscript::Slice {
lower_bound,
upper_bound,
stride,
} => {
// Means access like [:2]
let lower_bound = if let Some(lower_bound) = lower_bound {
self.sql_expr_to_logical_expr(lower_bound, schema, planner_context)
} else {
not_impl_err!("Slice subscript requires a lower bound")
}?;

// means access like [2:]
let upper_bound = if let Some(upper_bound) = upper_bound {
self.sql_expr_to_logical_expr(upper_bound, schema, planner_context)
} else {
not_impl_err!("Slice subscript requires an upper bound")
}?;

// stride, default to 1
let stride = if let Some(stride) = stride {
self.sql_expr_to_logical_expr(stride, schema, planner_context)?
} else {
lit(1i64)
};

GetFieldAccess::ListRange {
start: Box::new(lower_bound),
stop: Box::new(upper_bound),
stride: Box::new(stride),
AccessExpr::Dot(expr) => {
let expr =
self.sql_expr_to_logical_expr(expr, schema, planner_context)?;
match expr {
Expr::Column(Column { name, relation }) => {
if let Some(relation) = &relation {
// If the first part of the dot access is a column reference, we should
// check if the column is from the same table as the root expression.
// If it is, we should replace the root expression with the column reference.
// Otherwise, we should treat the dot access as a named field access.
if relation.table() == root.schema_name().to_string() {
root = Expr::Column(Column {
name,
relation: Some(relation.clone()),
});
Ok(None)
} else {
plan_err!(
"table name mismatch: {} != {}",
relation.table(),
root.schema_name()
)
}
} else {
Ok(Some(GetFieldAccess::NamedStructField {
name: ScalarValue::from(name),
}))
}
}
_ => not_impl_err!(
"Dot access not supported for non-column expr: {expr:?}"
),
}
}
}
};
})
.collect::<Result<Vec<_>>>()?;

let mut field_access_expr = RawFieldAccessExpr { expr, field_access };
for planner in self.context_provider.get_expr_planners() {
match planner.plan_field_access(field_access_expr, schema)? {
PlannerResult::Planned(expr) => return Ok(expr),
PlannerResult::Original(expr) => {
field_access_expr = expr;
fields
.into_iter()
.flatten()
.try_fold(root, |expr, field_access| {
let mut field_access_expr = RawFieldAccessExpr { expr, field_access };
for planner in self.context_provider.get_expr_planners() {
match planner.plan_field_access(field_access_expr, schema)? {
PlannerResult::Planned(expr) => return Ok(expr),
PlannerResult::Original(expr) => {
field_access_expr = expr;
}
}
}
}
}

not_impl_err!(
"GetFieldAccess not supported by ExprPlanner: {field_access_expr:?}"
)
not_impl_err!(
"GetFieldAccess not supported by ExprPlanner: {field_access_expr:?}"
)
})
}
}

Expand Down
6 changes: 3 additions & 3 deletions datafusion/sql/src/parser.rs
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -563,7 +563,7 @@ impl<'a> DFParser<'a> {

loop {
if let Token::Word(_) = self.parser.peek_token().token {
let identifier = self.parser.parse_identifier(false)?;
let identifier = self.parser.parse_identifier()?;
partitions.push(identifier.to_string());
} else {
return self.expected("partition name", self.parser.peek_token());
Expand Down Expand Up @@ -666,7 +666,7 @@ impl<'a> DFParser<'a> {
}

fn parse_column_def(&mut self) -> Result<ColumnDef, ParserError> {
let name = self.parser.parse_identifier(false)?;
let name = self.parser.parse_identifier()?;
let data_type = self.parser.parse_data_type()?;
let collation = if self.parser.parse_keyword(Keyword::COLLATE) {
Some(self.parser.parse_object_name(false)?)
Expand All @@ -676,7 +676,7 @@ impl<'a> DFParser<'a> {
let mut options = vec![];
loop {
if self.parser.parse_keyword(Keyword::CONSTRAINT) {
let name = Some(self.parser.parse_identifier(false)?);
let name = Some(self.parser.parse_identifier()?);
if let Some(option) = self.parser.parse_optional_column_option()? {
options.push(ColumnOptionDef { name, option });
} else {
Expand Down
3 changes: 2 additions & 1 deletion datafusion/sql/src/planner.rs
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -430,7 +430,7 @@ impl<'a, S: ContextProvider> SqlToRel<'a, S> {
SQLDataType::UnsignedBigInt(_) | SQLDataType::UnsignedInt8(_) => Ok(DataType::UInt64),
SQLDataType::Float(_) => Ok(DataType::Float32),
SQLDataType::Real | SQLDataType::Float4 => Ok(DataType::Float32),
SQLDataType::Double | SQLDataType::DoublePrecision | SQLDataType::Float8 => Ok(DataType::Float64),
SQLDataType::Double(_) | SQLDataType::DoublePrecision | SQLDataType::Float8 => Ok(DataType::Float64),
SQLDataType::Char(_)
| SQLDataType::Text
| SQLDataType::String(_) => Ok(DataType::Utf8),
Expand Down Expand Up @@ -514,6 +514,7 @@ impl<'a, S: ContextProvider> SqlToRel<'a, S> {
| SQLDataType::Regclass
| SQLDataType::Custom(_, _)
| SQLDataType::Array(_)
| SQLDataType::AnyType
| SQLDataType::Enum(_, _)
| SQLDataType::Set(_)
| SQLDataType::MediumInt(_)
Expand Down
6 changes: 5 additions & 1 deletion datafusion/sql/src/statement.rs
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -56,7 +56,7 @@ use datafusion_expr::{
};
use sqlparser::ast::{
self, BeginTransactionKind, NullsDistinctOption, ShowStatementIn,
ShowStatementOptions, SqliteOnConflict,
ShowStatementOptions, SqliteOnConflict, UpdateTableFromKind,
};
use sqlparser::ast::{
Assignment, AssignmentTarget, ColumnDef, CreateIndex, CreateTable,
Expand Down Expand Up @@ -890,6 +890,10 @@ impl<S: ContextProvider> SqlToRel<'_, S> {
if or.is_some() {
plan_err!("ON conflict not supported")?;
}
let from = from.map(|update| match update {
UpdateTableFromKind::BeforeSet(t)
| UpdateTableFromKind::AfterSet(t) => t,
});
self.update_to_plan(table, assignments, from, selection)
}

Expand Down
Loading
Loading