Struct spark_connect_rs::readwriter::DataFrameWriter

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

DataFrameWriter provides the ability to output a DataFrame to a specific file format supported by Spark

Implementations§

source§

impl DataFrameWriter

source

pub fn new(dataframe: DataFrame) -> Self

Create a new DataFrameWriter from a provided DataFrame

§Defaults
  • format: None,
  • mode: SaveMode::Overwrite,
  • bucket_by: None,
  • partition_by: vec![],
  • sort_by: vec![],
  • write_options: HashMap::new()
source

pub fn format(self, format: &str) -> Self

Target format to output the DataFrame

Examples found in repository?
examples/writer.rs (line 24)
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

async fn main() -> Result<(), Box<dyn std::error::Error>> {
    let spark: SparkSession = SparkSessionBuilder::default().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(())
}
More examples
Hide additional examples
examples/delta.rs (line 29)
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

async fn main() -> Result<(), Box<dyn std::error::Error>> {
    let spark: SparkSession = SparkSessionBuilder::default().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 mode(self, mode: SaveMode) -> Self

Specifies the behavior when data or table already exists

§Arguments:
Examples found in repository?
examples/writer.rs (line 25)
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

async fn main() -> Result<(), Box<dyn std::error::Error>> {
    let spark: SparkSession = SparkSessionBuilder::default().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(())
}
More examples
Hide additional examples
examples/delta.rs (line 30)
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

async fn main() -> Result<(), Box<dyn std::error::Error>> {
    let spark: SparkSession = SparkSessionBuilder::default().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 bucketBy<'a, I>(self, num_buckets: i32, buckets: I) -> Self
where I: IntoIterator<Item = &'a str>,

Buckets the output by the given columns. If specified, the output is laid out on the file system similar to Hive’s bucketing scheme.

source

pub fn sortBy<'a, I>(self, cols: I) -> Self
where I: IntoIterator<Item = &'a str>,

Sorts the output in each bucket by the given columns on the file system

source

pub fn partitionBy<'a, I>(self, cols: I) -> Self
where I: IntoIterator<Item = &'a str>,

Partitions the output by the given columns on the file system

source

pub fn option(self, key: &str, value: &str) -> Self

Add an input option for the underlying data source

Examples found in repository?
examples/writer.rs (line 26)
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

async fn main() -> Result<(), Box<dyn std::error::Error>> {
    let spark: SparkSession = SparkSessionBuilder::default().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 options<I, K, V>(self, options: I) -> Self
where I: IntoIterator<Item = (K, V)>, K: AsRef<str>, V: AsRef<str>,

Set many input options based on an iterator of (key/value pairs) for the underlying data source

source

pub async fn save(self, path: &str) -> Result<(), SparkError>

Save the contents of the DataFrame to a data source.

The data source is specified by the format and a set of options.

Examples found in repository?
examples/writer.rs (line 27)
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

async fn main() -> Result<(), Box<dyn std::error::Error>> {
    let spark: SparkSession = SparkSessionBuilder::default().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 async fn saveAsTable(self, table_name: &str) -> Result<(), SparkError>

Saves the context of the DataFrame as the specified table.

Examples found in repository?
examples/delta.rs (line 31)
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

async fn main() -> Result<(), Box<dyn std::error::Error>> {
    let spark: SparkSession = SparkSessionBuilder::default().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 async fn insertInto(self, table_name: &str) -> Result<(), SparkError>

Inserts the content of the DataFrame to the specified table.

It requires that the schema of the DataFrame is the same as the schema of the target table.

Unlike saveAsTable(), this method ignores the column names and just uses position-based resolution

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> 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, 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