Skip to main content

ExecutionPlan

Struct ExecutionPlan 

Source
pub struct ExecutionPlan {
    pub field_map: FxHashMap<String, String>,
    pub drop_fields: FxHashSet<String>,
    pub field_types: FxHashMap<String, FieldType>,
    pub dictionary_columns: FxHashSet<String>,
    pub filter: Option<FilterPredicate>,
    pub schema_order: Vec<String>,
    pub auto_dict: bool,
}
Expand description

A compiled execution plan that controls field renaming, dropping, type assignment, dictionary encoding, row filtering, and column ordering. Default (empty) is a no-op.

Fields§

§field_map: FxHashMap<String, String>

Map from raw field name to output column name.

§drop_fields: FxHashSet<String>

Set of raw field names to drop entirely.

§field_types: FxHashMap<String, FieldType>

Explicit type overrides per output column name.

§dictionary_columns: FxHashSet<String>

Set of output column names to dict-encode.

§filter: Option<FilterPredicate>

Optional row filter predicate.

§schema_order: Vec<String>

Desired output column order (names in order). Columns not listed here appear after all listed columns in first-appearance order. If empty, first-appearance order is used.

§auto_dict: bool

When true, string columns with low cardinality are automatically upgraded to dictionary encoding during parse.

Implementations§

Source§

impl ExecutionPlan

Source

pub fn new() -> Self

Examples found in repository?
examples/bench_throughput.rs (line 114)
103fn main() -> Result<()> {
104    let data = generate_data(ROWS);
105    let bytes = data.len();
106    let mb = bytes as f64 / 1_000_000.0;
107    println!("Generated {ROWS} rows ({mb:.1} MB)");
108
109    let mut path = std::env::temp_dir();
110    path.push("rypipe_bench_throughput.tsv");
111    File::create(&path)?.write_all(&data)?;
112
113    let pipeline = Pipeline::new(TsvSplitter, TsvParser).with_plan(
114        rypipe_core::ExecutionPlan::new()
115            .type_as("id", FieldType::Int64)
116            .type_as("amount", FieldType::Float64)
117            .type_as("count", FieldType::Int64),
118    );
119
120    run("single-thread", || {
121        let batch = pipeline.read_path(&path, false, false)?;
122        Ok(batch.num_rows())
123    });
124
125    run("parallel (4 chunks)", || {
126        let batches = pipeline.read_path_par(&path, 4, false, false)?;
127        Ok(batches.iter().map(|b| b.num_rows()).sum::<usize>())
128    });
129
130    run("parallel (8 chunks)", || {
131        let batches = pipeline.read_path_par(&path, 8, false, false)?;
132        Ok(batches.iter().map(|b| b.num_rows()).sum::<usize>())
133    });
134
135    run("bounded (64 MiB)", || {
136        let batches =
137            pipeline.read_path_stream(&path, MemoryBudget::new(64 * 1024 * 1024), false)?;
138        Ok(batches.iter().map(|b| b.num_rows()).sum::<usize>())
139    });
140
141    std::fs::remove_file(&path)?;
142    Ok(())
143}
Source

pub fn rename(self, raw: impl Into<String>, output: impl Into<String>) -> Self

Rename a raw field to an output column name.

Source

pub fn drop(self, field: impl Into<String>) -> Self

Drop a single raw/output field.

Source

pub fn drop_many<I, S>(self, fields: I) -> Self
where I: IntoIterator<Item = S>, S: Into<String>,

Drop many raw/output fields.

Source

pub fn type_as(self, field: impl Into<String>, field_type: FieldType) -> Self

Set the storage type for an output column.

Examples found in repository?
examples/bench_throughput.rs (line 115)
103fn main() -> Result<()> {
104    let data = generate_data(ROWS);
105    let bytes = data.len();
106    let mb = bytes as f64 / 1_000_000.0;
107    println!("Generated {ROWS} rows ({mb:.1} MB)");
108
109    let mut path = std::env::temp_dir();
110    path.push("rypipe_bench_throughput.tsv");
111    File::create(&path)?.write_all(&data)?;
112
113    let pipeline = Pipeline::new(TsvSplitter, TsvParser).with_plan(
114        rypipe_core::ExecutionPlan::new()
115            .type_as("id", FieldType::Int64)
116            .type_as("amount", FieldType::Float64)
117            .type_as("count", FieldType::Int64),
118    );
119
120    run("single-thread", || {
121        let batch = pipeline.read_path(&path, false, false)?;
122        Ok(batch.num_rows())
123    });
124
125    run("parallel (4 chunks)", || {
126        let batches = pipeline.read_path_par(&path, 4, false, false)?;
127        Ok(batches.iter().map(|b| b.num_rows()).sum::<usize>())
128    });
129
130    run("parallel (8 chunks)", || {
131        let batches = pipeline.read_path_par(&path, 8, false, false)?;
132        Ok(batches.iter().map(|b| b.num_rows()).sum::<usize>())
133    });
134
135    run("bounded (64 MiB)", || {
136        let batches =
137            pipeline.read_path_stream(&path, MemoryBudget::new(64 * 1024 * 1024), false)?;
138        Ok(batches.iter().map(|b| b.num_rows()).sum::<usize>())
139    });
140
141    std::fs::remove_file(&path)?;
142    Ok(())
143}
Source

pub fn dictionary(self, field: impl Into<String>) -> Self

Dict-encode an output column.

Source

pub fn filter_eq( self, field: impl Into<String>, value: impl Into<String>, ) -> Self

Keep only rows where field == value (string comparison, per-row).

Source

pub fn filter_ne( self, field: impl Into<String>, value: impl Into<String>, ) -> Self

Keep only rows where field != value (string comparison, per-row).

Source

pub fn filter_compare( self, field_a: impl Into<String>, op: CompareOp, field_b: impl Into<String>, ) -> Self

Keep only rows where field_a op field_b (post-reduce via Arrow compute).

Source

pub fn schema_order<I, S>(self, order: I) -> Self
where I: IntoIterator<Item = S>, S: Into<String>,

Set the output column order. Columns not listed appear after the listed ones in first-appearance order.

Source

pub fn with_auto_dict(self, yes: bool) -> Self

Enable or disable automatic dictionary upgrade for low-cardinality string columns.

Source

pub fn column_type(&self, name: &str) -> FieldType

Determine the storage type for an output column name.

Source

pub fn resolve_field<'a>(&'a self, raw: &'a str) -> Option<&'a str>

Resolve a raw field name to its output column name. Returns None if the field should be dropped.

Application order: rename first, then drop, matching left-to-right pipeline semantics.

Trait Implementations§

Source§

impl Clone for ExecutionPlan

Source§

fn clone(&self) -> ExecutionPlan

Returns a duplicate of the value. Read more
1.0.0 (const: unstable) · Source§

fn clone_from(&mut self, source: &Self)

Performs copy-assignment from source. Read more
Source§

impl Debug for ExecutionPlan

Source§

fn fmt(&self, f: &mut Formatter<'_>) -> Result

Formats the value using the given formatter. Read more
Source§

impl Default for ExecutionPlan

Source§

fn default() -> ExecutionPlan

Returns the “default value” for a type. Read more

Auto Trait Implementations§

Blanket Implementations§

Source§

impl<T> Allocation for T
where T: RefUnwindSafe + Send + Sync,

Source§

impl<T> Any for T
where T: 'static + ?Sized,

Source§

fn type_id(&self) -> TypeId

Gets the TypeId of self. Read more
Source§

impl<T> Borrow<T> for T
where T: ?Sized,

Source§

fn borrow(&self) -> &T

Immutably borrows from an owned value. Read more
Source§

impl<T> BorrowMut<T> for T
where T: ?Sized,

Source§

fn borrow_mut(&mut self) -> &mut T

Mutably borrows from an owned value. Read more
Source§

impl<ST, DT> CastableFrom<ST, Initialized, Initialized> for DT
where ST: ?Sized, DT: ?Sized,

Source§

impl<ST, DT> CastableFrom<ST, Uninit, Uninit> for DT
where ST: ?Sized, DT: ?Sized,

Source§

impl<T> CloneToUninit for T
where T: Clone,

Source§

unsafe fn clone_to_uninit(&self, dest: *mut u8)

🔬This is a nightly-only experimental API. (clone_to_uninit)
Performs copy-assignment from self to dest. Read more
Source§

impl<T> From<T> for T

Source§

fn from(t: T) -> T

Returns the argument unchanged.

Source§

impl<T, U> Into<U> for T
where U: From<T>,

Source§

fn into(self) -> U

Calls U::from(self).

That is, this conversion is whatever the implementation of From<T> for U chooses to do.

Source§

impl<T> IntoEither for T

Source§

fn into_either(self, into_left: bool) -> Either<Self, Self> ⓘ

Converts self into a Left variant of Either<Self, Self> if into_left is true. Converts self into a Right variant of Either<Self, Self> otherwise. Read more
Source§

fn into_either_with<F>(self, into_left: F) -> Either<Self, Self> ⓘ
where F: FnOnce(&Self) -> bool,

Converts self into a Left variant of Either<Self, Self> if into_left(&self) returns true. Converts self into a Right variant of Either<Self, Self> otherwise. Read more
Source§

impl<T> Pointable for T

Source§

const ALIGN: usize

The alignment of pointer.
Source§

type Init = T

The type for initializers.
Source§

unsafe fn init(init: <T as Pointable>::Init) -> usize

Initializes a with the given initializer. Read more
Source§

unsafe fn deref<'a>(ptr: usize) -> &'a T

Dereferences the given pointer. Read more
Source§

unsafe fn deref_mut<'a>(ptr: usize) -> &'a mut T

Mutably dereferences the given pointer. Read more
Source§

unsafe fn drop(ptr: usize)

Drops the object pointed to by the given pointer. Read more
Source§

impl<T> Read<Exclusive, BecauseExclusive> for T
where T: ?Sized,

Source§

impl<T> ToOwned for T
where T: Clone,

Source§

type Owned = T

The resulting type after obtaining ownership.
Source§

fn to_owned(&self) -> T

Creates owned data from borrowed data, usually by cloning. Read more
Source§

fn clone_into(&self, target: &mut T)

Uses borrowed data to replace owned data, usually by cloning. Read more
Source§

impl<T, U> TryFrom<U> for T
where U: Into<T>,

Source§

type Error = Infallible

The type returned in the event of a conversion error.
Source§

fn try_from(value: U) -> Result<T, <T as TryFrom<U>>::Error>

Performs the conversion.
Source§

impl<T, U> TryInto<U> for T
where U: TryFrom<T>,

Source§

type Error = <U as TryFrom<T>>::Error

The type returned in the event of a conversion error.
Source§

fn try_into(self) -> Result<U, <U as TryFrom<T>>::Error>

Performs the conversion.