Read files created by the stream

stream_read_csv

Description

Read files created by the stream

Usage

stream_read_csv(
  sc,
  path,
  name = NULL,
  header = TRUE,
  columns = NULL,
  delimiter = ",",
  quote = "\"",
  escape = "\\",
  charset = "UTF-8",
  null_value = NULL,
  options = list(),
  ...
)

stream_read_text(sc, path, name = NULL, options = list(), ...)

stream_read_json(sc, path, name = NULL, columns = NULL, options = list(), ...)

stream_read_parquet(
  sc,
  path,
  name = NULL,
  columns = NULL,
  options = list(),
  ...
)

stream_read_orc(sc, path, name = NULL, columns = NULL, options = list(), ...)

stream_read_kafka(sc, name = NULL, options = list(), ...)

stream_read_socket(sc, name = NULL, columns = NULL, options = list(), ...)

stream_read_delta(sc, path, name = NULL, options = list(), ...)

stream_read_cloudfiles(sc, path, name = NULL, options = list(), ...)

stream_read_table(sc, path, name = NULL, options = list(), ...)

Arguments

Arguments	Description
sc	A spark_connection.
path	The path to the file. Needs to be accessible from the cluster. Supports the "hdfs://", "s3a://" and "file://" protocols.
name	The name to assign to the newly generated stream.
header	Boolean; should the first row of data be used as a header? Defaults to TRUE.
columns	A vector of column names or a named vector of column types. If specified, the elements can be "binary" for BinaryType, "boolean" for BooleanType, "byte" for ByteType, "integer" for IntegerType, "integer64" for LongType, "double" for DoubleType, "character" for StringType, "timestamp" for TimestampType and "date" for DateType.
delimiter	The character used to delimit each column. Defaults to ','.
quote	The character used as a quote. Defaults to '"'.
escape	The character used to escape other characters. Defaults to '\'.
charset	The character set. Defaults to "UTF-8".
null_value	The character to use for null, or missing, values. Defaults to NULL.
options	A list of strings with additional options.
…	Optional arguments; currently unused.

Examples

sc <- spark_connect(master = "local")

dir.create("csv-in")
write.csv(iris, "csv-in/data.csv", row.names = FALSE)

csv_path <- file.path("file://", getwd(), "csv-in")

stream <- stream_read_csv(sc, csv_path) %>% stream_write_csv("csv-out")

stream_stop(stream)