Struct spark_connect_rs::SparkSession

source · 
pub struct SparkSession { /* private fields */ }
Expand description

The spark-connect-rs crate is currently just a meta-package shim for spark-connect-core The entry point to connecting to a Spark Cluster using the Spark Connection gRPC protocol.

Implementations§

source§

impl SparkSession

source

pub fn new( client: SparkConnectClient<InterceptedService<Channel, MetadataInterceptor>> ) -> SparkSession

source

pub fn range( self, start: Option<i64>, end: i64, step: i64, num_partitions: Option<i32> ) -> DataFrame

Create a DataFrame with a spingle column named id, containing elements in a range from start (default 0) to end (exclusive) with a step value step, and control the number of partitions with num_partitions

Examples found in repository?
examples/writer.rs (line 20)
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64

async fn main() -> Result<(), Box<dyn std::error::Error>> {
    let spark: SparkSession = SparkSessionBuilder::remote("sc://127.0.0.1:15002/")
        .build()
        .await?;

    let df = spark
        .clone()
        .range(None, 1000, 1, Some(16))
        .select(col("id").alias("range_id"));

    let path = "/opt/spark/examples/src/main/rust/employees/";

    df.write()
        .format("csv")
        .mode(SaveMode::Overwrite)
        .option("header", "true")
        .save(path)
        .await?;

    let df = spark
        .clone()
        .read()
        .format("csv")
        .option("header", "true")
        .load([path])?;

    df.show(Some(10), None, None).await?;

    // print results may slighty vary but should be close to the below
    // +--------------------------+
    // | show_string              |
    // +--------------------------+
    // | +--------+               |
    // | |range_id|               |
    // | +--------+               |
    // | |312     |               |
    // | |313     |               |
    // | |314     |               |
    // | |315     |               |
    // | |316     |               |
    // | |317     |               |
    // | |318     |               |
    // | |319     |               |
    // | |320     |               |
    // | |321     |               |
    // | +--------+               |
    // | only showing top 10 rows |
    // |                          |
    // +--------------------------+

    Ok(())
}
source

pub fn read(self) -> DataFrameReader

Returns a DataFrameReader that can be used to read datra in as a DataFrame

Examples found in repository?
examples/sql.rs (line 25)
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43

async fn main() -> Result<(), Box<dyn std::error::Error>> {
    let spark: SparkSession = SparkSessionBuilder::remote("sc://127.0.0.1:15002/")
        .build()
        .await?;

    let df = spark
        .clone()
        .sql("select 'apple' as word, 123 as count")
        .await?;

    df.write()
        .mode(SaveMode::Overwrite)
        .format("parquet")
        .save("file:///tmp/spark-connect-write-example-output.parquet")
        .await?;

    let df = spark
        .read()
        .format("parquet")
        .load(["file:///tmp/spark-connect-write-example-output.parquet"])?;

    df.show(Some(100), None, None).await?;

    // +---------------+
    // | show_string   |
    // +---------------+
    // | +-----+-----+ |
    // | |word |count| |
    // | +-----+-----+ |
    // | |apple|123  | |
    // | +-----+-----+ |
    // |               |
    // +---------------+

    Ok(())
}
More examples
Hide additional examples
examples/reader.rs (line 16)
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45

async fn main() -> Result<(), Box<dyn std::error::Error>> {
    let spark: SparkSession = SparkSessionBuilder::default().build().await?;

    let path = ["/opt/spark/examples/src/main/resources/people.csv"];

    let df = spark
        .read()
        .format("csv")
        .option("header", "True")
        .option("delimiter", ";")
        .load(path)?;

    df.select([
        F::col("name"),
        F::col("age").cast("int").alias("age_int"),
        (F::lit(3.0) + F::col("age").cast("int")).alias("addition"),
    ])
    .sort(vec![F::col("name").desc()])
    .show(Some(5), None, None)
    .await?;

    // print results
    // +--------------------------+
    // | show_string              |
    // +--------------------------+
    // | +-----+-------+--------+ |
    // | |name |age_int|addition| |
    // | +-----+-------+--------+ |
    // | |Jorge|30     |33.0    | |
    // | |Bob  |32     |35.0    | |
    // | +-----+-------+--------+ |
    // |                          |
    // +--------------------------+

    Ok(())
}
examples/writer.rs (line 34)
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64

async fn main() -> Result<(), Box<dyn std::error::Error>> {
    let spark: SparkSession = SparkSessionBuilder::remote("sc://127.0.0.1:15002/")
        .build()
        .await?;

    let df = spark
        .clone()
        .range(None, 1000, 1, Some(16))
        .select(col("id").alias("range_id"));

    let path = "/opt/spark/examples/src/main/rust/employees/";

    df.write()
        .format("csv")
        .mode(SaveMode::Overwrite)
        .option("header", "true")
        .save(path)
        .await?;

    let df = spark
        .clone()
        .read()
        .format("csv")
        .option("header", "true")
        .load([path])?;

    df.show(Some(10), None, None).await?;

    // print results may slighty vary but should be close to the below
    // +--------------------------+
    // | show_string              |
    // +--------------------------+
    // | +--------+               |
    // | |range_id|               |
    // | +--------+               |
    // | |312     |               |
    // | |313     |               |
    // | |314     |               |
    // | |315     |               |
    // | |316     |               |
    // | |317     |               |
    // | |318     |               |
    // | |319     |               |
    // | |320     |               |
    // | |321     |               |
    // | +--------+               |
    // | only showing top 10 rows |
    // |                          |
    // +--------------------------+

    Ok(())
}
examples/delta.rs (line 23)
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67

async fn main() -> Result<(), Box<dyn std::error::Error>> {
    let spark: SparkSession = SparkSessionBuilder::remote("sc://127.0.0.1:15002/")
        .build()
        .await?;

    let paths = ["/opt/spark/examples/src/main/resources/people.csv"];

    let df = spark
        .clone()
        .read()
        .format("csv")
        .option("header", "True")
        .option("delimiter", ";")
        .option("inferSchema", "True")
        .load(paths)?;

    df.write()
        .format("delta")
        .mode(SaveMode::Overwrite)
        .saveAsTable("default.people_delta")
        .await?;

    spark
        .sql("DESCRIBE HISTORY default.people_delta")
        .await?
        .show(Some(1), None, Some(true))
        .await?;

    // print results
    // +-------------------------------------------------------------------------------------------------------+
    // | show_string                                                                                           |
    // +-------------------------------------------------------------------------------------------------------+
    // | -RECORD 0-------------------------------------------------------------------------------------------- |
    // |  version             | 3                                                                              |
    // |  timestamp           | 2024-03-16 13:46:23.552                                                        |
    // |  userId              | NULL                                                                           |
    // |  userName            | NULL                                                                           |
    // |  operation           | CREATE OR REPLACE TABLE AS SELECT                                              |
    // |  operationParameters | {isManaged -> true, description -> NULL, partitionBy -> [], properties -> {}}  |
    // |  job                 | NULL                                                                           |
    // |  notebook            | NULL                                                                           |
    // |  clusterId           | NULL                                                                           |
    // |  readVersion         | 2                                                                              |
    // |  isolationLevel      | Serializable                                                                   |
    // |  isBlindAppend       | false                                                                          |
    // |  operationMetrics    | {numFiles -> 1, numOutputRows -> 2, numOutputBytes -> 988}                     |
    // |  userMetadata        | NULL                                                                           |
    // |  engineInfo          | Apache-Spark/3.5.0 Delta-Lake/3.0.0                                            |
    // | only showing top 1 row                                                                                |
    // |                                                                                                       |
    // +-------------------------------------------------------------------------------------------------------+

    Ok(())
}
source

pub fn readStream(self) -> DataStreamReader

Returns a DataFrameReader that can be used to read datra in as a DataFrame

Examples found in repository?
examples/readstream.rs (line 17)
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42

async fn main() -> Result<(), Box<dyn std::error::Error>> {
    let spark: SparkSession =
        SparkSessionBuilder::remote("sc://127.0.0.1:15002/;user_id=stream_example")
            .build()
            .await?;

    let df = spark
        .readStream()
        .format("rate")
        .option("rowsPerSecond", "5")
        .load(None)?;

    let query = df
        .writeStream()
        .format("console")
        .queryName("example_stream")
        .outputMode(OutputMode::Append)
        .trigger(Trigger::ProcessingTimeInterval("1 seconds".to_string()))
        .start(None)
        .await?;

    // loop to get multiple progression stats
    for _ in 1..5 {
        thread::sleep(time::Duration::from_secs(5));
        let val = &query.clone().lastProgress().await?;
        println!("{}", val);
    }

    // stop the active stream
    query.stop().await?;

    Ok(())
}
source

pub fn table(self, name: &str) -> Result<DataFrame, SparkError>

source

pub fn catalog(self) -> Catalog

Interface through which the user may create, drop, alter or query underlying databases, tables, functions, etc.

source

pub async fn sql(self, sql_query: &str) -> Result<DataFrame, SparkError>

Returns a DataFrame representing the result of the given query

Examples found in repository?
examples/sql.rs (line 15)
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43

async fn main() -> Result<(), Box<dyn std::error::Error>> {
    let spark: SparkSession = SparkSessionBuilder::remote("sc://127.0.0.1:15002/")
        .build()
        .await?;

    let df = spark
        .clone()
        .sql("select 'apple' as word, 123 as count")
        .await?;

    df.write()
        .mode(SaveMode::Overwrite)
        .format("parquet")
        .save("file:///tmp/spark-connect-write-example-output.parquet")
        .await?;

    let df = spark
        .read()
        .format("parquet")
        .load(["file:///tmp/spark-connect-write-example-output.parquet"])?;

    df.show(Some(100), None, None).await?;

    // +---------------+
    // | show_string   |
    // +---------------+
    // | +-----+-----+ |
    // | |word |count| |
    // | +-----+-----+ |
    // | |apple|123  | |
    // | +-----+-----+ |
    // |               |
    // +---------------+

    Ok(())
}
More examples
Hide additional examples
examples/delta.rs (line 37)
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67

async fn main() -> Result<(), Box<dyn std::error::Error>> {
    let spark: SparkSession = SparkSessionBuilder::remote("sc://127.0.0.1:15002/")
        .build()
        .await?;

    let paths = ["/opt/spark/examples/src/main/resources/people.csv"];

    let df = spark
        .clone()
        .read()
        .format("csv")
        .option("header", "True")
        .option("delimiter", ";")
        .option("inferSchema", "True")
        .load(paths)?;

    df.write()
        .format("delta")
        .mode(SaveMode::Overwrite)
        .saveAsTable("default.people_delta")
        .await?;

    spark
        .sql("DESCRIBE HISTORY default.people_delta")
        .await?
        .show(Some(1), None, Some(true))
        .await?;

    // print results
    // +-------------------------------------------------------------------------------------------------------+
    // | show_string                                                                                           |
    // +-------------------------------------------------------------------------------------------------------+
    // | -RECORD 0-------------------------------------------------------------------------------------------- |
    // |  version             | 3                                                                              |
    // |  timestamp           | 2024-03-16 13:46:23.552                                                        |
    // |  userId              | NULL                                                                           |
    // |  userName            | NULL                                                                           |
    // |  operation           | CREATE OR REPLACE TABLE AS SELECT                                              |
    // |  operationParameters | {isManaged -> true, description -> NULL, partitionBy -> [], properties -> {}}  |
    // |  job                 | NULL                                                                           |
    // |  notebook            | NULL                                                                           |
    // |  clusterId           | NULL                                                                           |
    // |  readVersion         | 2                                                                              |
    // |  isolationLevel      | Serializable                                                                   |
    // |  isBlindAppend       | false                                                                          |
    // |  operationMetrics    | {numFiles -> 1, numOutputRows -> 2, numOutputBytes -> 988}                     |
    // |  userMetadata        | NULL                                                                           |
    // |  engineInfo          | Apache-Spark/3.5.0 Delta-Lake/3.0.0                                            |
    // | only showing top 1 row                                                                                |
    // |                                                                                                       |
    // +-------------------------------------------------------------------------------------------------------+

    Ok(())
}
source

pub fn createDataFrame( self, data: &RecordBatch ) -> Result<DataFrame, SparkError>

source

pub fn session_id(&self) -> &str

Return the session ID

source

pub fn client( self ) -> SparkConnectClient<InterceptedService<Channel, MetadataInterceptor>>

Spark Connection gRPC client interface

Trait Implementations§

source§

impl Clone for SparkSession

source§

fn clone(&self) -> SparkSession

Returns a copy of the value. Read more
1.0.0 · source§

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

Performs copy-assignment from source. Read more
source§

impl Debug for SparkSession

source§

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

Formats the value using the given formatter. Read more

Auto Trait Implementations§

Blanket Implementations§

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<T> From<T> for T

source§

fn from(t: T) -> T

Returns the argument unchanged.

source§

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

source§

fn from_ref(input: &T) -> T

Converts to this type from a reference to the input type.
source§

impl<T> Instrument for T

source§

fn instrument(self, span: Span) -> Instrumented<Self>

Instruments this type with the provided Span, returning an Instrumented wrapper. Read more
source§

fn in_current_span(self) -> Instrumented<Self>

Instruments this type with the current Span, returning an Instrumented wrapper. Read more
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> IntoRequest<T> for T

source§

fn into_request(self) -> Request<T>

Wrap the input message T in a tonic::Request
source§

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

§

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>,

§

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>,

§

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.
source§

impl<V, T> VZip<V> for T
where V: MultiLane<T>,

source§

fn vzip(self) -> V

source§

impl<T> WithSubscriber for T

source§

fn with_subscriber<S>(self, subscriber: S) -> WithDispatch<Self>
where S: Into<Dispatch>,

Attaches the provided Subscriber to this type, returning a WithDispatch wrapper. Read more
source§

fn with_current_subscriber(self) -> WithDispatch<Self>

Attaches the current default Subscriber to this type, returning a WithDispatch wrapper. Read more