diff options
| author | Felix Cheung <felixcheung_m@hotmail.com> | 2016-10-21 12:35:37 -0700 |
|---|---|---|
| committer | Felix Cheung <felixcheung@apache.org> | 2016-10-21 12:35:37 -0700 |
| commit | e21e1c946c4b7448fb150cfa2d9419864ae6f9b5 (patch) | |
| tree | 44da3487f4b5403b889fc5e4f33a40a679f20e9a /R/pkg/inst/tests | |
| parent | 4efdc764edfbc4971f0e863947258482ca2017df (diff) | |
| download | spark-e21e1c946c4b7448fb150cfa2d9419864ae6f9b5.tar.gz spark-e21e1c946c4b7448fb150cfa2d9419864ae6f9b5.tar.bz2 spark-e21e1c946c4b7448fb150cfa2d9419864ae6f9b5.zip | |
[SPARK-18013][SPARKR] add crossJoin API
## What changes were proposed in this pull request?
Add crossJoin and do not default to cross join if joinExpr is left out
## How was this patch tested?
unit test
Author: Felix Cheung <felixcheung_m@hotmail.com>
Closes #15559 from felixcheung/rcrossjoin.
Diffstat (limited to 'R/pkg/inst/tests')
| -rw-r--r-- | R/pkg/inst/tests/testthat/test_sparkSQL.R | 11 |
1 files changed, 9 insertions, 2 deletions
diff --git a/R/pkg/inst/tests/testthat/test_sparkSQL.R b/R/pkg/inst/tests/testthat/test_sparkSQL.R index 1c806869e9..3a987cd862 100644 --- a/R/pkg/inst/tests/testthat/test_sparkSQL.R +++ b/R/pkg/inst/tests/testthat/test_sparkSQL.R @@ -1572,7 +1572,7 @@ test_that("filter() on a DataFrame", { #expect_true(is.ts(filter(1:100, rep(1, 3)))) # nolint }) -test_that("join() and merge() on a DataFrame", { +test_that("join(), crossJoin() and merge() on a DataFrame", { df <- read.json(jsonPath) mockLines2 <- c("{\"name\":\"Michael\", \"test\": \"yes\"}", @@ -1583,7 +1583,14 @@ test_that("join() and merge() on a DataFrame", { writeLines(mockLines2, jsonPath2) df2 <- read.json(jsonPath2) - joined <- join(df, df2) + # inner join, not cartesian join + expect_equal(count(where(join(df, df2), df$name == df2$name)), 3) + # cartesian join + expect_error(tryCatch(count(join(df, df2)), error = function(e) { stop(e) }), + paste0(".*(org.apache.spark.sql.AnalysisException: Detected cartesian product for", + " INNER join between logical plans).*")) + + joined <- crossJoin(df, df2) expect_equal(names(joined), c("age", "name", "name", "test")) expect_equal(count(joined), 12) expect_equal(names(collect(joined)), c("age", "name", "name", "test")) |