From d4f633514a393320c9ae64c00a75f702e6f58c67 Mon Sep 17 00:00:00 2001
From: Yu ISHIKAWA <yuu.ishikawa@gmail.com>
Date: Mon, 22 Jun 2015 23:04:36 -0700
Subject: [PATCH] [SPARK-8431] [SPARKR] Add in operator to DataFrame Column in
SparkR
[[SPARK-8431] Add in operator to DataFrame Column in SparkR - ASF JIRA](https://issues.apache.org/jira/browse/SPARK-8431)
Author: Yu ISHIKAWA <yuu.ishikawa@gmail.com>
Closes #6941 from yu-iskw/SPARK-8431 and squashes the following commits:
1f64423 [Yu ISHIKAWA] Modify the comment
f4309a7 [Yu ISHIKAWA] Make a `setMethod` for `%in%` be independent
6e37936 [Yu ISHIKAWA] Modify a variable name
c196173 [Yu ISHIKAWA] [SPARK-8431][SparkR] Add in operator to DataFrame Column in SparkR
---
R/pkg/R/column.R | 16 ++++++++++++++++
R/pkg/inst/tests/test_sparkSQL.R | 10 ++++++++++
2 files changed, 26 insertions(+)
diff --git a/R/pkg/R/column.R b/R/pkg/R/column.R
index 80e92d3105..8e4b0f5bf1 100644
--- a/R/pkg/R/column.R
+++ b/R/pkg/R/column.R
@@ -210,6 +210,22 @@ setMethod("cast",
}
})
+#' Match a column with given values.
+#'
+#' @rdname column
+#' @return a matched values as a result of comparing with given values.
+#' \dontrun{
+#' filter(df, "age in (10, 30)")
+#' where(df, df$age %in% c(10, 30))
+#' }
+setMethod("%in%",
+ signature(x = "Column"),
+ function(x, table) {
+ table <- listToSeq(as.list(table))
+ jc <- callJMethod(x@jc, "in", table)
+ return(column(jc))
+ })
+
#' Approx Count Distinct
#'
#' @rdname column
diff --git a/R/pkg/inst/tests/test_sparkSQL.R b/R/pkg/inst/tests/test_sparkSQL.R
index fc7f3f074b..417153dc09 100644
--- a/R/pkg/inst/tests/test_sparkSQL.R
+++ b/R/pkg/inst/tests/test_sparkSQL.R
@@ -693,6 +693,16 @@ test_that("filter() on a DataFrame", {
filtered2 <- where(df, df$name != "Michael")
expect_true(count(filtered2) == 2)
expect_true(collect(filtered2)$age[2] == 19)
+
+ # test suites for %in%
+ filtered3 <- filter(df, "age in (19)")
+ expect_equal(count(filtered3), 1)
+ filtered4 <- filter(df, "age in (19, 30)")
+ expect_equal(count(filtered4), 2)
+ filtered5 <- where(df, df$age %in% c(19))
+ expect_equal(count(filtered5), 1)
+ filtered6 <- where(df, df$age %in% c(19, 30))
+ expect_equal(count(filtered6), 2)
})
test_that("join() on a DataFrame", {
--
GitLab