diff options
| author | Felix Cheung <felixcheung_m@hotmail.com> | 2017-03-02 01:02:38 -0800 |
|---|---|---|
| committer | Felix Cheung <felixcheung@apache.org> | 2017-03-02 01:02:38 -0800 |
| commit | 8d6ef895ee492b8febbaac7ab2ef2c907b48fa4a (patch) | |
| tree | 497d97fb9ca0c033baccc47eb5fddb4196fbf36a /sql/core/src | |
| parent | d2a879762a2b4f3c4d703cc183275af12b3c7de1 (diff) | |
| download | spark-8d6ef895ee492b8febbaac7ab2ef2c907b48fa4a.tar.gz spark-8d6ef895ee492b8febbaac7ab2ef2c907b48fa4a.tar.bz2 spark-8d6ef895ee492b8febbaac7ab2ef2c907b48fa4a.zip | |
[SPARK-18352][DOCS] wholeFile JSON update doc and programming guide
## What changes were proposed in this pull request?
Update doc for R, programming guide. Clarify default behavior for all languages.
## How was this patch tested?
manually
Author: Felix Cheung <felixcheung_m@hotmail.com>
Closes #17128 from felixcheung/jsonwholefiledoc.
Diffstat (limited to 'sql/core/src')
| -rw-r--r-- | sql/core/src/main/scala/org/apache/spark/sql/DataFrameReader.scala | 4 | ||||
| -rw-r--r-- | sql/core/src/main/scala/org/apache/spark/sql/streaming/DataStreamReader.scala | 4 |
2 files changed, 4 insertions, 4 deletions
diff --git a/sql/core/src/main/scala/org/apache/spark/sql/DataFrameReader.scala b/sql/core/src/main/scala/org/apache/spark/sql/DataFrameReader.scala index 63be1e5302..41470ae6aa 100644 --- a/sql/core/src/main/scala/org/apache/spark/sql/DataFrameReader.scala +++ b/sql/core/src/main/scala/org/apache/spark/sql/DataFrameReader.scala @@ -263,8 +263,8 @@ class DataFrameReader private[sql](sparkSession: SparkSession) extends Logging { /** * Loads a JSON file and returns the results as a `DataFrame`. * - * Both JSON (one record per file) and <a href="http://jsonlines.org/">JSON Lines</a> - * (newline-delimited JSON) are supported and can be selected with the `wholeFile` option. + * <a href="http://jsonlines.org/">JSON Lines</a> (newline-delimited JSON) is supported by + * default. For JSON (one record per file), set the `wholeFile` option to true. * * This function goes through the input once to determine the input schema. If you know the * schema in advance, use the version that specifies the schema to avoid the extra scan. diff --git a/sql/core/src/main/scala/org/apache/spark/sql/streaming/DataStreamReader.scala b/sql/core/src/main/scala/org/apache/spark/sql/streaming/DataStreamReader.scala index 6a275281d8..aed8074a64 100644 --- a/sql/core/src/main/scala/org/apache/spark/sql/streaming/DataStreamReader.scala +++ b/sql/core/src/main/scala/org/apache/spark/sql/streaming/DataStreamReader.scala @@ -143,8 +143,8 @@ final class DataStreamReader private[sql](sparkSession: SparkSession) extends Lo /** * Loads a JSON file stream and returns the results as a `DataFrame`. * - * Both JSON (one record per file) and <a href="http://jsonlines.org/">JSON Lines</a> - * (newline-delimited JSON) are supported and can be selected with the `wholeFile` option. + * <a href="http://jsonlines.org/">JSON Lines</a> (newline-delimited JSON) is supported by + * default. For JSON (one record per file), set the `wholeFile` option to true. * * This function goes through the input once to determine the input schema. If you know the * schema in advance, use the version that specifies the schema to avoid the extra scan. |