spark-commits mailing list archives

Site index · List index
Message view « Date » · « Thread »
Top « Date » · « Thread »
From felixche...@apache.org
Subject spark git commit: [SPARK-19795][SPARKR] add column functions to_json, from_json
Date Sun, 05 Mar 2017 20:37:07 GMT
Repository: spark
Updated Branches:
  refs/heads/master 14bb398fa -> 80d5338b3


[SPARK-19795][SPARKR] add column functions to_json, from_json

## What changes were proposed in this pull request?

Add column functions: to_json, from_json, and tests covering error cases.

## How was this patch tested?

unit tests, manual

Author: Felix Cheung <felixcheung_m@hotmail.com>

Closes #17134 from felixcheung/rtojson.


Project: http://git-wip-us.apache.org/repos/asf/spark/repo
Commit: http://git-wip-us.apache.org/repos/asf/spark/commit/80d5338b
Tree: http://git-wip-us.apache.org/repos/asf/spark/tree/80d5338b
Diff: http://git-wip-us.apache.org/repos/asf/spark/diff/80d5338b

Branch: refs/heads/master
Commit: 80d5338b32e856870cf187ce17bc87335d690761
Parents: 14bb398
Author: Felix Cheung <felixcheung_m@hotmail.com>
Authored: Sun Mar 5 12:37:02 2017 -0800
Committer: Felix Cheung <felixcheung@apache.org>
Committed: Sun Mar 5 12:37:02 2017 -0800

----------------------------------------------------------------------
 R/pkg/NAMESPACE                           |  2 +
 R/pkg/R/functions.R                       | 57 ++++++++++++++++++++++++++
 R/pkg/R/generics.R                        |  8 ++++
 R/pkg/inst/tests/testthat/test_sparkSQL.R | 43 +++++++++++++++----
 4 files changed, 103 insertions(+), 7 deletions(-)
----------------------------------------------------------------------


http://git-wip-us.apache.org/repos/asf/spark/blob/80d5338b/R/pkg/NAMESPACE
----------------------------------------------------------------------
diff --git a/R/pkg/NAMESPACE b/R/pkg/NAMESPACE
index 81e1936..871f8e4 100644
--- a/R/pkg/NAMESPACE
+++ b/R/pkg/NAMESPACE
@@ -229,6 +229,7 @@ exportMethods("%in%",
               "floor",
               "format_number",
               "format_string",
+              "from_json",
               "from_unixtime",
               "from_utc_timestamp",
               "getField",
@@ -327,6 +328,7 @@ exportMethods("%in%",
               "toDegrees",
               "toRadians",
               "to_date",
+              "to_json",
               "to_timestamp",
               "to_utc_timestamp",
               "translate",

http://git-wip-us.apache.org/repos/asf/spark/blob/80d5338b/R/pkg/R/functions.R
----------------------------------------------------------------------
diff --git a/R/pkg/R/functions.R b/R/pkg/R/functions.R
index 9e50844..edf2bcf 100644
--- a/R/pkg/R/functions.R
+++ b/R/pkg/R/functions.R
@@ -1793,6 +1793,33 @@ setMethod("to_date",
             column(jc)
           })
 
+#' to_json
+#'
+#' Converts a column containing a \code{structType} into a Column of JSON string.
+#' Resolving the Column can fail if an unsupported type is encountered.
+#'
+#' @param x Column containing the struct
+#' @param ... additional named properties to control how it is converted, accepts the same
options
+#'            as the JSON data source.
+#'
+#' @family normal_funcs
+#' @rdname to_json
+#' @name to_json
+#' @aliases to_json,Column-method
+#' @export
+#' @examples
+#' \dontrun{
+#' to_json(df$t, dateFormat = 'dd/MM/yyyy')
+#' select(df, to_json(df$t))
+#'}
+#' @note to_json since 2.2.0
+setMethod("to_json", signature(x = "Column"),
+          function(x, ...) {
+            options <- varargsToStrEnv(...)
+            jc <- callJStatic("org.apache.spark.sql.functions", "to_json", x@jc, options)
+            column(jc)
+          })
+
 #' to_timestamp
 #'
 #' Converts the column into a TimestampType. You may optionally specify a format
@@ -2403,6 +2430,36 @@ setMethod("date_format", signature(y = "Column", x = "character"),
             column(jc)
           })
 
+#' from_json
+#'
+#' Parses a column containing a JSON string into a Column of \code{structType} with the specified
+#' \code{schema}. If the string is unparseable, the Column will contains the value NA.
+#'
+#' @param x Column containing the JSON string.
+#' @param schema a structType object to use as the schema to use when parsing the JSON string.
+#' @param ... additional named properties to control how the json is parsed, accepts the
same
+#'            options as the JSON data source.
+#'
+#' @family normal_funcs
+#' @rdname from_json
+#' @name from_json
+#' @aliases from_json,Column,structType-method
+#' @export
+#' @examples
+#' \dontrun{
+#' schema <- structType(structField("name", "string"),
+#' select(df, from_json(df$value, schema, dateFormat = "dd/MM/yyyy"))
+#'}
+#' @note from_json since 2.2.0
+setMethod("from_json", signature(x = "Column", schema = "structType"),
+          function(x, schema, ...) {
+            options <- varargsToStrEnv(...)
+            jc <- callJStatic("org.apache.spark.sql.functions",
+                              "from_json",
+                              x@jc, schema$jobj, options)
+            column(jc)
+          })
+
 #' from_utc_timestamp
 #'
 #' Given a timestamp, which corresponds to a certain time of day in UTC, returns another
timestamp

http://git-wip-us.apache.org/repos/asf/spark/blob/80d5338b/R/pkg/R/generics.R
----------------------------------------------------------------------
diff --git a/R/pkg/R/generics.R b/R/pkg/R/generics.R
index 647cbbd..45bc127 100644
--- a/R/pkg/R/generics.R
+++ b/R/pkg/R/generics.R
@@ -991,6 +991,10 @@ setGeneric("format_number", function(y, x) { standardGeneric("format_number")
})
 #' @export
 setGeneric("format_string", function(format, x, ...) { standardGeneric("format_string") })
 
+#' @rdname from_json
+#' @export
+setGeneric("from_json", function(x, schema, ...) { standardGeneric("from_json") })
+
 #' @rdname from_unixtime
 #' @export
 setGeneric("from_unixtime", function(x, ...) { standardGeneric("from_unixtime") })
@@ -1265,6 +1269,10 @@ setGeneric("toRadians", function(x) { standardGeneric("toRadians")
})
 #' @export
 setGeneric("to_date", function(x, format) { standardGeneric("to_date") })
 
+#' @rdname to_json
+#' @export
+setGeneric("to_json", function(x, ...) { standardGeneric("to_json") })
+
 #' @rdname to_timestamp
 #' @export
 setGeneric("to_timestamp", function(x, format) { standardGeneric("to_timestamp") })

http://git-wip-us.apache.org/repos/asf/spark/blob/80d5338b/R/pkg/inst/tests/testthat/test_sparkSQL.R
----------------------------------------------------------------------
diff --git a/R/pkg/inst/tests/testthat/test_sparkSQL.R b/R/pkg/inst/tests/testthat/test_sparkSQL.R
index 1dd8c5c..7c09659 100644
--- a/R/pkg/inst/tests/testthat/test_sparkSQL.R
+++ b/R/pkg/inst/tests/testthat/test_sparkSQL.R
@@ -88,6 +88,13 @@ mockLinesComplexType <-
 complexTypeJsonPath <- tempfile(pattern = "sparkr-test", fileext = ".tmp")
 writeLines(mockLinesComplexType, complexTypeJsonPath)
 
+# For test map type and struct type in DataFrame
+mockLinesMapType <- c("{\"name\":\"Bob\",\"info\":{\"age\":16,\"height\":176.5}}",
+                      "{\"name\":\"Alice\",\"info\":{\"age\":20,\"height\":164.3}}",
+                      "{\"name\":\"David\",\"info\":{\"age\":60,\"height\":180}}")
+mapTypeJsonPath <- tempfile(pattern = "sparkr-test", fileext = ".tmp")
+writeLines(mockLinesMapType, mapTypeJsonPath)
+
 test_that("calling sparkRSQL.init returns existing SQL context", {
   sqlContext <- suppressWarnings(sparkRSQL.init(sc))
   expect_equal(suppressWarnings(sparkRSQL.init(sc)), sqlContext)
@@ -466,13 +473,6 @@ test_that("create DataFrame from a data.frame with complex types", {
   expect_equal(ldf$an_envir, collected$an_envir)
 })
 
-# For test map type and struct type in DataFrame
-mockLinesMapType <- c("{\"name\":\"Bob\",\"info\":{\"age\":16,\"height\":176.5}}",
-                      "{\"name\":\"Alice\",\"info\":{\"age\":20,\"height\":164.3}}",
-                      "{\"name\":\"David\",\"info\":{\"age\":60,\"height\":180}}")
-mapTypeJsonPath <- tempfile(pattern = "sparkr-test", fileext = ".tmp")
-writeLines(mockLinesMapType, mapTypeJsonPath)
-
 test_that("Collect DataFrame with complex types", {
   # ArrayType
   df <- read.json(complexTypeJsonPath)
@@ -1337,6 +1337,33 @@ test_that("column functions", {
   df <- createDataFrame(data.frame(x = c(2.5, 3.5)))
   expect_equal(collect(select(df, bround(df$x, 0)))[[1]][1], 2)
   expect_equal(collect(select(df, bround(df$x, 0)))[[1]][2], 4)
+
+  # Test to_json(), from_json()
+  df <- read.json(mapTypeJsonPath)
+  j <- collect(select(df, alias(to_json(df$info), "json")))
+  expect_equal(j[order(j$json), ][1], "{\"age\":16,\"height\":176.5}")
+  df <- as.DataFrame(j)
+  schema <- structType(structField("age", "integer"),
+                       structField("height", "double"))
+  s <- collect(select(df, alias(from_json(df$json, schema), "structcol")))
+  expect_equal(ncol(s), 1)
+  expect_equal(nrow(s), 3)
+  expect_is(s[[1]][[1]], "struct")
+  expect_true(any(apply(s, 1, function(x) { x[[1]]$age == 16 } )))
+
+  # passing option
+  df <- as.DataFrame(list(list("col" = "{\"date\":\"21/10/2014\"}")))
+  schema2 <- structType(structField("date", "date"))
+  expect_error(tryCatch(collect(select(df, from_json(df$col, schema2))),
+                        error = function(e) { stop(e) }),
+               paste0(".*(java.lang.NumberFormatException: For input string:).*"))
+  s <- collect(select(df, from_json(df$col, schema2, dateFormat = "dd/MM/yyyy")))
+  expect_is(s[[1]][[1]]$date, "Date")
+  expect_equal(as.character(s[[1]][[1]]$date), "2014-10-21")
+
+  # check for unparseable
+  df <- as.DataFrame(list(list("a" = "")))
+  expect_equal(collect(select(df, from_json(df$a, schema)))[[1]][[1]], NA)
 })
 
 test_that("column binary mathfunctions", {
@@ -2867,5 +2894,7 @@ unlink(parquetPath)
 unlink(orcPath)
 unlink(jsonPath)
 unlink(jsonPathNa)
+unlink(complexTypeJsonPath)
+unlink(mapTypeJsonPath)
 
 sparkR.session.stop()


---------------------------------------------------------------------
To unsubscribe, e-mail: commits-unsubscribe@spark.apache.org
For additional commands, e-mail: commits-help@spark.apache.org


Mime
View raw message