16204612549

Committed 10 Jul 2025 07:50PM UTC coverage: 81.152% (+2.9%) from 78.263%

Build # 16204612549

Build Type

Pull #3825

github

Committed by

web-flow

Commit Message

Merge d0d2717da into be9c2fd3e

Pull Request Pull Request #3825: feat: Add optimize ArrayOp with VBView implementation

Run Details

178 of 211 new or added lines in 4 files covered. (84.36%)

330 existing lines in 34 files now uncovered.

45433 of 55985 relevant lines covered (81.15%)

145951.87 hits per line

Source File
Press 'n' to go to next uncovered line, 'b' for previous

86.41

/vortex-array/src/arrays/struct_/mod.rs

// SPDX-License-Identifier: Apache-2.0
// SPDX-FileCopyrightText: Copyright the Vortex contributors

use std::fmt::Debug;

use itertools::Itertools;
use vortex_dtype::{DType, FieldName, FieldNames, StructFields};
use vortex_error::{VortexExpect, VortexResult, vortex_bail, vortex_err};
use vortex_scalar::Scalar;

use crate::stats::{ArrayStats, StatsSetRef};
use crate::validity::Validity;
use crate::vtable::{
    ArrayVTable, CanonicalVTable, NotSupported, OperationsVTable, VTable, ValidityHelper,
    ValidityVTableFromValidityHelper,
};
use crate::{Array, ArrayRef, Canonical, EncodingId, EncodingRef, IntoArray, vtable};

mod compute;
mod serde;

vtable!(Struct);

impl VTable for StructVTable {
    type Array = StructArray;
    type Encoding = StructEncoding;

    type ArrayVTable = Self;
    type CanonicalVTable = Self;
    type OperationsVTable = Self;
    type ValidityVTable = ValidityVTableFromValidityHelper;
    type VisitorVTable = Self;
    type ComputeVTable = NotSupported;
    type EncodeVTable = NotSupported;
    type SerdeVTable = Self;

    fn id(_encoding: &Self::Encoding) -> EncodingId {
        EncodingId::new_ref("vortex.struct")
    }

    fn encoding(_array: &Self::Array) -> EncodingRef {
        EncodingRef::new_ref(StructEncoding.as_ref())
    }
}

#[derive(Clone, Debug)]
pub struct StructArray {
    len: usize,
    dtype: DType,
    fields: Vec<ArrayRef>,
    validity: Validity,
    stats_set: ArrayStats,
}

#[derive(Clone, Debug)]
pub struct StructEncoding;

impl StructArray {
    pub fn fields(&self) -> &[ArrayRef] {
        &self.fields
    }

    pub fn field_by_name(&self, name: impl AsRef<str>) -> VortexResult<&ArrayRef> {
        let name = name.as_ref();
        self.field_by_name_opt(name).ok_or_else(|| {
            vortex_err!(
                "Field {name} not found in struct array with names {:?}",
                self.names()
            )
        })
    }

    pub fn field_by_name_opt(&self, name: impl AsRef<str>) -> Option<&ArrayRef> {
        let name = name.as_ref();
        self.names()
            .iter()
            .position(|field_name| field_name.as_ref() == name)
            .map(|idx| &self.fields[idx])
    }

    pub fn names(&self) -> &FieldNames {
        self.struct_fields().names()
    }

    pub fn struct_fields(&self) -> &StructFields {
        let Some(struct_dtype) = &self.dtype.as_struct() else {
            unreachable!(
                "struct arrays must have be a DType::Struct, this is likely an internal bug."
            )
        };
        struct_dtype
    }

    /// Create a new `StructArray` with the given length, but without any fields.
    pub fn new_with_len(len: usize) -> Self {
        Self::try_new(
            FieldNames::default(),
            Vec::new(),
            len,
            Validity::NonNullable,
        )
        .vortex_expect("StructArray::new_with_len should not fail")
    }

    pub fn try_new(
        names: FieldNames,
        fields: Vec<ArrayRef>,
        length: usize,
        validity: Validity,
    ) -> VortexResult<Self> {
        let nullability = validity.nullability();

        if names.len() != fields.len() {
            vortex_bail!("Got {} names and {} fields", names.len(), fields.len());
        }

        for field in fields.iter() {
            if field.len() != length {
                vortex_bail!(
                    "Expected all struct fields to have length {length}, found {}",
                    fields.iter().map(|f| f.len()).format(","),
                );
            }
        }

        let field_dtypes: Vec<_> = fields.iter().map(|d| d.dtype()).cloned().collect();
        let dtype = DType::Struct(StructFields::new(names, field_dtypes), nullability);

        if length != validity.maybe_len().unwrap_or(length) {
            vortex_bail!(
                "array length {} and validity length must match {}",
                length,
                validity
                    .maybe_len()
                    .vortex_expect("can only fail if maybe is some")
            )
        }

        Ok(Self {
            len: length,
            dtype,
            fields,
            validity,
            stats_set: Default::default(),
        })
    }

    pub fn try_new_with_dtype(
        fields: Vec<ArrayRef>,
        dtype: StructFields,
        length: usize,
        validity: Validity,
    ) -> VortexResult<Self> {
        for (field, struct_dt) in fields.iter().zip(dtype.fields()) {
            if field.len() != length {
                vortex_bail!(
                    "Expected all struct fields to have length {length}, found {}",
                    field.len()
                );
            }

            if &struct_dt != field.dtype() {
                vortex_bail!(
                    "Expected all struct fields to have dtype {}, found {}",
                    struct_dt,
                    field.dtype()
                );
            }
        }

        Ok(Self {
            len: length,
            dtype: DType::Struct(dtype, validity.nullability()),
            fields,
            validity,
            stats_set: Default::default(),
        })
    }

    pub fn from_fields<N: AsRef<str>>(items: &[(N, ArrayRef)]) -> VortexResult<Self> {
        Self::try_from_iter(items.iter().map(|(a, b)| (a, b.to_array())))
    }

    pub fn try_from_iter_with_validity<
        N: AsRef<str>,
        A: IntoArray,
        T: IntoIterator<Item = (N, A)>,
    >(
        iter: T,
        validity: Validity,
    ) -> VortexResult<Self> {
        let (names, fields): (Vec<FieldName>, Vec<ArrayRef>) = iter
            .into_iter()
            .map(|(name, fields)| (FieldName::from(name.as_ref()), fields.into_array()))
            .unzip();
        let len = fields
            .first()
            .map(|f| f.len())
            .ok_or_else(|| vortex_err!("StructArray cannot be constructed from an empty slice of arrays because the length is unspecified"))?;

        Self::try_new(FieldNames::from_iter(names), fields, len, validity)
    }

    pub fn try_from_iter<N: AsRef<str>, A: IntoArray, T: IntoIterator<Item = (N, A)>>(
        iter: T,
    ) -> VortexResult<Self> {
        Self::try_from_iter_with_validity(iter, Validity::NonNullable)
    }

    // TODO(aduffy): Add equivalent function to support field masks for nested column access.
    /// Return a new StructArray with the given projection applied.
    ///
    /// Projection does not copy data arrays. Projection is defined by an ordinal array slice
    /// which specifies the new ordering of columns in the struct. The projection can be used to
    /// perform column re-ordering, deletion, or duplication at a logical level, without any data
    /// copying.
    #[allow(clippy::same_name_method)]
    pub fn project(&self, projection: &[FieldName]) -> VortexResult<Self> {
        let mut children = Vec::with_capacity(projection.len());
        let mut names = Vec::with_capacity(projection.len());

        for f_name in projection.iter() {
            let idx = self
                .names()
                .iter()
                .position(|name| name == f_name)
                .ok_or_else(|| vortex_err!("Unknown field {f_name}"))?;

            names.push(self.names()[idx].clone());
            children.push(self.fields()[idx].clone());
        }

        StructArray::try_new(
            FieldNames::from(names.as_slice()),
            children,
            self.len(),
            self.validity().clone(),
        )
    }

    /// Removes and returns a column from the struct array by name.
    /// If the column does not exist, returns `None`.
    pub fn remove_column(&mut self, name: impl Into<FieldName>) -> Option<ArrayRef> {
        let name = name.into();

        let Some(struct_dtype) = self.dtype.as_struct() else {
            unreachable!(
                "struct arrays must have be a DType::Struct, this is likely an internal bug."
            )
        };

        let position = struct_dtype
            .names()
            .iter()
            .position(|field_name| field_name.as_ref() == name.as_ref())?;

        let field = self.fields.remove(position);

        let new_dtype = struct_dtype.without_field(position);
        self.dtype = DType::Struct(new_dtype, self.dtype.nullability());

        Some(field)
    }
}

impl ValidityHelper for StructArray {
    fn validity(&self) -> &Validity {
        &self.validity
    }
}

impl ArrayVTable<StructVTable> for StructVTable {
    fn len(array: &StructArray) -> usize {
        array.len
    }

    fn dtype(array: &StructArray) -> &DType {
        &array.dtype
    }

    fn stats(array: &StructArray) -> StatsSetRef<'_> {
        array.stats_set.to_ref(array.as_ref())
    }
}

impl CanonicalVTable<StructVTable> for StructVTable {
    fn canonicalize(array: &StructArray) -> VortexResult<Canonical> {
        Ok(Canonical::Struct(array.clone()))
    }
}

impl OperationsVTable<StructVTable> for StructVTable {
    fn slice(array: &StructArray, start: usize, stop: usize) -> VortexResult<ArrayRef> {
        let fields = array
            .fields()
            .iter()
            .map(|field| field.slice(start, stop))
            .try_collect()?;
        StructArray::try_new_with_dtype(
            fields,
            array.struct_fields().clone(),
            stop - start,
            array.validity().slice(start, stop)?,
        )
        .map(|a| a.into_array())
    }

    fn scalar_at(array: &StructArray, index: usize) -> VortexResult<Scalar> {
        Ok(Scalar::struct_(
            array.dtype().clone(),
            array
                .fields()
                .iter()
                .map(|field| field.scalar_at(index))
                .try_collect()?,
        ))
    }
}

#[cfg(test)]
mod test {
    use vortex_buffer::buffer;
    use vortex_dtype::{DType, FieldName, FieldNames, Nullability, PType};

    use crate::IntoArray;
    use crate::arrays::primitive::PrimitiveArray;
    use crate::arrays::struct_::StructArray;
    use crate::arrays::varbin::VarBinArray;
    use crate::arrays::{BoolArray, BoolVTable, PrimitiveVTable};
    use crate::validity::Validity;

    #[test]
    fn test_project() {
        let xs = PrimitiveArray::new(buffer![0i64, 1, 2, 3, 4], Validity::NonNullable);
        let ys = VarBinArray::from_vec(
            vec!["a", "b", "c", "d", "e"],
            DType::Utf8(Nullability::NonNullable),
        );
        let zs = BoolArray::from_iter([true, true, true, false, false]);

        let struct_a = StructArray::try_new(
            FieldNames::from(["xs", "ys", "zs"]),
            vec![xs.into_array(), ys.into_array(), zs.into_array()],
            5,
            Validity::NonNullable,
        )
        .unwrap();

        let struct_b = struct_a
            .project(&[FieldName::from("zs"), FieldName::from("xs")])
            .unwrap();
        assert_eq!(
            struct_b.names().as_ref(),
            [FieldName::from("zs"), FieldName::from("xs")],
        );

        assert_eq!(struct_b.len(), 5);

        let bools = &struct_b.fields[0];
        assert_eq!(
            bools
                .as_::<BoolVTable>()
                .boolean_buffer()
                .iter()
                .collect::<Vec<_>>(),
            vec![true, true, true, false, false]
        );

        let prims = &struct_b.fields[1];
        assert_eq!(
            prims.as_::<PrimitiveVTable>().as_slice::<i64>(),
            [0i64, 1, 2, 3, 4]
        );
    }

    #[test]
    fn test_remove_column() {
        let xs = PrimitiveArray::new(buffer![0i64, 1, 2, 3, 4], Validity::NonNullable);
        let ys = PrimitiveArray::new(buffer![4u64, 5, 6, 7, 8], Validity::NonNullable);

        let mut struct_a = StructArray::try_new(
            FieldNames::from(["xs", "ys"]),
            vec![xs.into_array(), ys.into_array()],
            5,
            Validity::NonNullable,
        )
        .unwrap();

        let removed = struct_a.remove_column("xs").unwrap();
        assert_eq!(
            removed.dtype(),
            &DType::Primitive(PType::I64, Nullability::NonNullable)
        );
        assert_eq!(
            removed.as_::<PrimitiveVTable>().as_slice::<i64>(),
            [0i64, 1, 2, 3, 4]
        );

        assert_eq!(struct_a.names(), &[FieldName::from("ys")].into());
        assert_eq!(struct_a.fields.len(), 1);
        assert_eq!(struct_a.len(), 5);
        assert_eq!(
            struct_a.fields[0].dtype(),
            &DType::Primitive(PType::U64, Nullability::NonNullable)
        );
        assert_eq!(
            struct_a.fields[0]
                .as_::<PrimitiveVTable>()
                .as_slice::<u64>(),
            [4u64, 5, 6, 7, 8]
        );

        let empty = struct_a.remove_column("non_existent");
        assert!(
            empty.is_none(),
            "Expected None when removing non-existent column"
        );
        assert_eq!(struct_a.names(), &[FieldName::from("ys")].into());
    }
}

1	// SPDX-License-Identifier: Apache-2.0
2	// SPDX-FileCopyrightText: Copyright the Vortex contributors
3
4	use std::fmt::Debug;
5
6	use itertools::Itertools;
7	use vortex_dtype::{DType, FieldName, FieldNames, StructFields};
8	use vortex_error::{VortexExpect, VortexResult, vortex_bail, vortex_err};
9	use vortex_scalar::Scalar;
10
11	use crate::stats::{ArrayStats, StatsSetRef};
12	use crate::validity::Validity;
13	use crate::vtable::{
14	ArrayVTable, CanonicalVTable, NotSupported, OperationsVTable, VTable, ValidityHelper,
15	ValidityVTableFromValidityHelper,
16	};
17	use crate::{Array, ArrayRef, Canonical, EncodingId, EncodingRef, IntoArray, vtable};
18
19	mod compute;
20	mod serde;
21
22	vtable!(Struct);
23
24	impl VTable for StructVTable {
25	type Array = StructArray;
26	type Encoding = StructEncoding;
27
28	type ArrayVTable = Self;
29	type CanonicalVTable = Self;
30	type OperationsVTable = Self;
31	type ValidityVTable = ValidityVTableFromValidityHelper;
32	type VisitorVTable = Self;
33	type ComputeVTable = NotSupported;
34	type EncodeVTable = NotSupported;
35	type SerdeVTable = Self;
36
37	fn id(_encoding: &Self::Encoding) -> EncodingId {	63,776✔
38	EncodingId::new_ref("vortex.struct")	63,776✔
39	}	63,776✔
40
41	fn encoding(_array: &Self::Array) -> EncodingRef {	9,615✔
42	EncodingRef::new_ref(StructEncoding.as_ref())	9,615✔
43	}	9,615✔
44	}
45
46	#[derive(Clone, Debug)]
47	pub struct StructArray {
48	len: usize,
49	dtype: DType,
50	fields: Vec<ArrayRef>,
51	validity: Validity,
52	stats_set: ArrayStats,
53	}
54
55	#[derive(Clone, Debug)]
56	pub struct StructEncoding;
57
58	impl StructArray {
59	pub fn fields(&self) -> &[ArrayRef] {	65,373✔
60	&self.fields	65,373✔
61	}	65,373✔
62
63	pub fn field_by_name(&self, name: impl AsRef<str>) -> VortexResult<&ArrayRef> {	12,794✔
64	let name = name.as_ref();	12,794✔
65	self.field_by_name_opt(name).ok_or_else(\|\| {	12,794✔
66	vortex_err!(	20✔
67	"Field {name} not found in struct array with names {:?}",	20✔
68	self.names()	20✔
69	)	20✔
70	})	12,794✔
71	}	12,794✔
72
73	pub fn field_by_name_opt(&self, name: impl AsRef<str>) -> Option<&ArrayRef> {	20,003✔
74	let name = name.as_ref();	20,003✔
75	self.names()	20,003✔
76	.iter()	20,003✔
77	.position(\|field_name\| field_name.as_ref() == name)	48,629✔
78	.map(\|idx\| &self.fields[idx])	20,003✔
79	}	20,003✔
80
81	pub fn names(&self) -> &FieldNames {	42,145✔
82	self.struct_fields().names()	42,145✔
83	}	42,145✔
84
85	pub fn struct_fields(&self) -> &StructFields {	43,722✔
86	let Some(struct_dtype) = &self.dtype.as_struct() else {	43,722✔
87	unreachable!(	×
88	"struct arrays must have be a DType::Struct, this is likely an internal bug."	×
89	)	×
90	};
91	struct_dtype	43,722✔
92	}	43,722✔
93
94	/// Create a new `StructArray` with the given length, but without any fields.
95	pub fn new_with_len(len: usize) -> Self {	36✔
96	Self::try_new(	36✔
97	FieldNames::default(),	36✔
98	Vec::new(),	36✔
99	len,	36✔
100	Validity::NonNullable,	36✔
101	)	36✔
102	.vortex_expect("StructArray::new_with_len should not fail")	36✔
103	}	36✔
104
105	pub fn try_new(	21,976✔
106	names: FieldNames,	21,976✔
107	fields: Vec<ArrayRef>,	21,976✔
108	length: usize,	21,976✔
109	validity: Validity,	21,976✔
110	) -> VortexResult<Self> {	21,976✔
111	let nullability = validity.nullability();	21,976✔
112		21,976✔
113	if names.len() != fields.len() {	21,976✔
UNCOV 114	vortex_bail!("Got {} names and {} fields", names.len(), fields.len());	×
115	}	21,976✔
116
117	for field in fields.iter() {	64,920✔
118	if field.len() != length {	64,920✔
119	vortex_bail!(	×
120	"Expected all struct fields to have length {length}, found {}",	×
121	fields.iter().map(\|f\| f.len()).format(","),	×
122	);	×
123	}	64,920✔
124	}
125
126	let field_dtypes: Vec<_> = fields.iter().map(\|d\| d.dtype()).cloned().collect();	64,920✔
127	let dtype = DType::Struct(StructFields::new(names, field_dtypes), nullability);	21,976✔
128		21,976✔
129	if length != validity.maybe_len().unwrap_or(length) {	21,976✔
UNCOV 130	vortex_bail!(	×
UNCOV 131	"array length {} and validity length must match {}",	×
UNCOV 132	length,	×
UNCOV 133	validity	×
UNCOV 134	.maybe_len()	×
UNCOV 135	.vortex_expect("can only fail if maybe is some")	×
UNCOV 136	)	×
137	}	21,976✔
138		21,976✔
139	Ok(Self {	21,976✔
140	len: length,	21,976✔
141	dtype,	21,976✔
142	fields,	21,976✔
143	validity,	21,976✔
144	stats_set: Default::default(),	21,976✔
145	})	21,976✔
146	}	21,976✔
147
148	pub fn try_new_with_dtype(	1,173✔
149	fields: Vec<ArrayRef>,	1,173✔
150	dtype: StructFields,	1,173✔
151	length: usize,	1,173✔
152	validity: Validity,	1,173✔
153	) -> VortexResult<Self> {	1,173✔
154	for (field, struct_dt) in fields.iter().zip(dtype.fields()) {	4,501✔
155	if field.len() != length {	4,501✔
156	vortex_bail!(	×
UNCOV 157	"Expected all struct fields to have length {length}, found {}",	×
UNCOV 158	field.len()	×
UNCOV 159	);	×
160	}	4,501✔
161		4,501✔
162	if &struct_dt != field.dtype() {	4,501✔
UNCOV 163	vortex_bail!(	×
UNCOV 164	"Expected all struct fields to have dtype {}, found {}",	×
UNCOV 165	struct_dt,	×
UNCOV 166	field.dtype()	×
UNCOV 167	);	×
168	}	4,501✔
169	}
170
171	Ok(Self {	1,173✔
172	len: length,	1,173✔
173	dtype: DType::Struct(dtype, validity.nullability()),	1,173✔
174	fields,	1,173✔
175	validity,	1,173✔
176	stats_set: Default::default(),	1,173✔
177	})	1,173✔
178	}	1,173✔
179
180	pub fn from_fields<N: AsRef<str>>(items: &[(N, ArrayRef)]) -> VortexResult<Self> {	53✔
181	Self::try_from_iter(items.iter().map(\|(a, b)\| (a, b.to_array())))	102✔
182	}	53✔
183
184	pub fn try_from_iter_with_validity<	65✔
185	N: AsRef<str>,	65✔
186	A: IntoArray,	65✔
187	T: IntoIterator<Item = (N, A)>,	65✔
188	>(	65✔
189	iter: T,	65✔
190	validity: Validity,	65✔
191	) -> VortexResult<Self> {	65✔
192	let (names, fields): (Vec<FieldName>, Vec<ArrayRef>) = iter	65✔
193	.into_iter()	65✔
194	.map(\|(name, fields)\| (FieldName::from(name.as_ref()), fields.into_array()))	118✔
195	.unzip();	65✔
196	let len = fields	65✔
197	.first()	65✔
198	.map(\|f\| f.len())	65✔
199	.ok_or_else(\|\| vortex_err!("StructArray cannot be constructed from an empty slice of arrays because the length is unspecified"))?;	65✔
200
201	Self::try_new(FieldNames::from_iter(names), fields, len, validity)	65✔
202	}	65✔
203
204	pub fn try_from_iter<N: AsRef<str>, A: IntoArray, T: IntoIterator<Item = (N, A)>>(	63✔
205	iter: T,	63✔
206	) -> VortexResult<Self> {	63✔
207	Self::try_from_iter_with_validity(iter, Validity::NonNullable)	63✔
208	}	63✔
209
210	// TODO(aduffy): Add equivalent function to support field masks for nested column access.
211	/// Return a new StructArray with the given projection applied.
212	///
213	/// Projection does not copy data arrays. Projection is defined by an ordinal array slice
214	/// which specifies the new ordering of columns in the struct. The projection can be used to
215	/// perform column re-ordering, deletion, or duplication at a logical level, without any data
216	/// copying.
217	#[allow(clippy::same_name_method)]
218	pub fn project(&self, projection: &[FieldName]) -> VortexResult<Self> {	73✔
219	let mut children = Vec::with_capacity(projection.len());	73✔
220	let mut names = Vec::with_capacity(projection.len());	73✔
221
222	for f_name in projection.iter() {	74✔
223	let idx = self	74✔
224	.names()	74✔
225	.iter()	74✔
226	.position(\|name\| name == f_name)	112✔
227	.ok_or_else(\|\| vortex_err!("Unknown field {f_name}"))?;	74✔
228
229	names.push(self.names()[idx].clone());	74✔
230	children.push(self.fields()[idx].clone());	74✔
231	}
232
233	StructArray::try_new(	73✔
234	FieldNames::from(names.as_slice()),	73✔
235	children,	73✔
236	self.len(),	73✔
237	self.validity().clone(),	73✔
238	)	73✔
239	}	73✔
240
241	/// Removes and returns a column from the struct array by name.
242	/// If the column does not exist, returns `None`.
243	pub fn remove_column(&mut self, name: impl Into<FieldName>) -> Option<ArrayRef> {	2✔
244	let name = name.into();	2✔
245
246	let Some(struct_dtype) = self.dtype.as_struct() else {	2✔
UNCOV 247	unreachable!(	×
UNCOV 248	"struct arrays must have be a DType::Struct, this is likely an internal bug."	×
UNCOV 249	)	×
250	};
251
252	let position = struct_dtype	2✔
253	.names()	2✔
254	.iter()	2✔
255	.position(\|field_name\| field_name.as_ref() == name.as_ref())?;	2✔
256
257	let field = self.fields.remove(position);	1✔
258		1✔
259	let new_dtype = struct_dtype.without_field(position);	1✔
260	self.dtype = DType::Struct(new_dtype, self.dtype.nullability());	1✔
261		1✔
262	Some(field)	1✔
263	}	2✔
264	}
265
266	impl ValidityHelper for StructArray {
267	fn validity(&self) -> &Validity {	18,973✔
268	&self.validity	18,973✔
269	}	18,973✔
270	}
271
272	impl ArrayVTable<StructVTable> for StructVTable {
273	fn len(array: &StructArray) -> usize {	120,232✔
274	array.len	120,232✔
275	}	120,232✔
276
277	fn dtype(array: &StructArray) -> &DType {	155,213✔
278	&array.dtype	155,213✔
279	}	155,213✔
280
281	fn stats(array: &StructArray) -> StatsSetRef<'_> {	84,799✔
282	array.stats_set.to_ref(array.as_ref())	84,799✔
283	}	84,799✔
284	}
285
286	impl CanonicalVTable<StructVTable> for StructVTable {
287	fn canonicalize(array: &StructArray) -> VortexResult<Canonical> {	28,871✔
288	Ok(Canonical::Struct(array.clone()))	28,871✔
289	}	28,871✔
290	}
291
292	impl OperationsVTable<StructVTable> for StructVTable {
UNCOV 293	fn slice(array: &StructArray, start: usize, stop: usize) -> VortexResult<ArrayRef> {	×
294	let fields = array	×
295	.fields()	×
UNCOV 296	.iter()	×
UNCOV 297	.map(\|field\| field.slice(start, stop))	×
UNCOV 298	.try_collect()?;	×
299	StructArray::try_new_with_dtype(
UNCOV 300	fields,	×
UNCOV 301	array.struct_fields().clone(),	×
UNCOV 302	stop - start,	×
UNCOV 303	array.validity().slice(start, stop)?,	×
304	)
UNCOV 305	.map(\|a\| a.into_array())	×
UNCOV 306	}	×
307
308	fn scalar_at(array: &StructArray, index: usize) -> VortexResult<Scalar> {	630✔
309	Ok(Scalar::struct_(	630✔
310	array.dtype().clone(),	630✔
311	array	630✔
312	.fields()	630✔
313	.iter()	630✔
314	.map(\|field\| field.scalar_at(index))	1,233✔
315	.try_collect()?,	630✔
316	))
317	}	630✔
318	}
319
320	#[cfg(test)]
321	mod test {
322	use vortex_buffer::buffer;
323	use vortex_dtype::{DType, FieldName, FieldNames, Nullability, PType};
324
325	use crate::IntoArray;
326	use crate::arrays::primitive::PrimitiveArray;
327	use crate::arrays::struct_::StructArray;
328	use crate::arrays::varbin::VarBinArray;
329	use crate::arrays::{BoolArray, BoolVTable, PrimitiveVTable};
330	use crate::validity::Validity;
331
332	#[test]
333	fn test_project() {	1✔
334	let xs = PrimitiveArray::new(buffer![0i64, 1, 2, 3, 4], Validity::NonNullable);	1✔
335	let ys = VarBinArray::from_vec(	1✔
336	vec!["a", "b", "c", "d", "e"],	1✔
337	DType::Utf8(Nullability::NonNullable),	1✔
338	);	1✔
339	let zs = BoolArray::from_iter([true, true, true, false, false]);	1✔
340		1✔
341	let struct_a = StructArray::try_new(	1✔
342	FieldNames::from(["xs", "ys", "zs"]),	1✔
343	vec![xs.into_array(), ys.into_array(), zs.into_array()],	1✔
344	5,	1✔
345	Validity::NonNullable,	1✔
346	)	1✔
347	.unwrap();	1✔
348		1✔
349	let struct_b = struct_a	1✔
350	.project(&[FieldName::from("zs"), FieldName::from("xs")])	1✔
351	.unwrap();	1✔
352	assert_eq!(	1✔
353	struct_b.names().as_ref(),	1✔
354	[FieldName::from("zs"), FieldName::from("xs")],	1✔
355	);	1✔
356
357	assert_eq!(struct_b.len(), 5);	1✔
358
359	let bools = &struct_b.fields[0];	1✔
360	assert_eq!(	1✔
361	bools	1✔
362	.as_::<BoolVTable>()	1✔
363	.boolean_buffer()	1✔
364	.iter()	1✔
365	.collect::<Vec<_>>(),	1✔
366	vec![true, true, true, false, false]	1✔
367	);	1✔
368
369	let prims = &struct_b.fields[1];	1✔
370	assert_eq!(	1✔
371	prims.as_::<PrimitiveVTable>().as_slice::<i64>(),	1✔
372	[0i64, 1, 2, 3, 4]	1✔
373	);	1✔
374	}	1✔
375
376	#[test]
377	fn test_remove_column() {	1✔
378	let xs = PrimitiveArray::new(buffer![0i64, 1, 2, 3, 4], Validity::NonNullable);	1✔
379	let ys = PrimitiveArray::new(buffer![4u64, 5, 6, 7, 8], Validity::NonNullable);	1✔
380		1✔
381	let mut struct_a = StructArray::try_new(	1✔
382	FieldNames::from(["xs", "ys"]),	1✔
383	vec![xs.into_array(), ys.into_array()],	1✔
384	5,	1✔
385	Validity::NonNullable,	1✔
386	)	1✔
387	.unwrap();	1✔
388		1✔
389	let removed = struct_a.remove_column("xs").unwrap();	1✔
390	assert_eq!(	1✔
391	removed.dtype(),	1✔
392	&DType::Primitive(PType::I64, Nullability::NonNullable)	1✔
393	);	1✔
394	assert_eq!(	1✔
395	removed.as_::<PrimitiveVTable>().as_slice::<i64>(),	1✔
396	[0i64, 1, 2, 3, 4]	1✔
397	);	1✔
398
399	assert_eq!(struct_a.names(), &[FieldName::from("ys")].into());	1✔
400	assert_eq!(struct_a.fields.len(), 1);	1✔
401	assert_eq!(struct_a.len(), 5);	1✔
402	assert_eq!(	1✔
403	struct_a.fields[0].dtype(),	1✔
404	&DType::Primitive(PType::U64, Nullability::NonNullable)	1✔
405	);	1✔
406	assert_eq!(	1✔
407	struct_a.fields[0]	1✔
408	.as_::<PrimitiveVTable>()	1✔
409	.as_slice::<u64>(),	1✔
410	[4u64, 5, 6, 7, 8]	1✔
411	);	1✔
412
413	let empty = struct_a.remove_column("non_existent");	1✔
414	assert!(	1✔
415	empty.is_none(),	1✔
416	"Expected None when removing non-existent column"
417	);
418	assert_eq!(struct_a.names(), &[FieldName::from("ys")].into());	1✔
419	}	1✔
420	}

vortex-data / vortex / 16204612549

Source File Press 'n' to go to next uncovered line, 'b' for previous

Source File
Press 'n' to go to next uncovered line, 'b' for previous