From 5441a6269e00e3903ae6c1ea8deb4ddf3d2e9975 Mon Sep 17 00:00:00 2001 From: eyal farago Date: Tue, 1 Nov 2016 17:12:20 +0100 Subject: [SPARK-16839][SQL] redundant aliases after cleanupAliases ## What changes were proposed in this pull request? Simplify struct creation, especially the aspect of `CleanupAliases` which missed some aliases when handling trees created by `CreateStruct`. This PR includes: 1. A failing test (create struct with nested aliases, some of the aliases survive `CleanupAliases`). 2. A fix that transforms `CreateStruct` into a `CreateNamedStruct` constructor, effectively eliminating `CreateStruct` from all expression trees. 3. A `NamePlaceHolder` used by `CreateStruct` when column names cannot be extracted from unresolved `NamedExpression`. 4. A new Analyzer rule that resolves `NamePlaceHolder` into a string literal once the `NamedExpression` is resolved. 5. `CleanupAliases` code was simplified as it no longer has to deal with `CreateStruct`'s top level columns. ## How was this patch tested? running all tests-suits in package org.apache.spark.sql, especially including the analysis suite, making sure added test initially fails, after applying suggested fix rerun the entire analysis package successfully. modified few tests that expected `CreateStruct` which is now transformed into `CreateNamedStruct`. Credit goes to hvanhovell for assisting with this PR. Author: eyal farago Author: eyal farago Author: Herman van Hovell Author: Eyal Farago Author: Hyukjin Kwon Author: eyalfa Closes #14444 from eyalfa/SPARK-16839_redundant_aliases_after_cleanupAliases. --- R/pkg/inst/tests/testthat/test_sparkSQL.R | 12 ++++++------ 1 file changed, 6 insertions(+), 6 deletions(-) (limited to 'R/pkg/inst/tests') diff --git a/R/pkg/inst/tests/testthat/test_sparkSQL.R b/R/pkg/inst/tests/testthat/test_sparkSQL.R index 9289db57b6..5002655fc0 100644 --- a/R/pkg/inst/tests/testthat/test_sparkSQL.R +++ b/R/pkg/inst/tests/testthat/test_sparkSQL.R @@ -1222,16 +1222,16 @@ test_that("column functions", { # Test struct() df <- createDataFrame(list(list(1L, 2L, 3L), list(4L, 5L, 6L)), schema = c("a", "b", "c")) - result <- collect(select(df, struct("a", "c"))) + result <- collect(select(df, alias(struct("a", "c"), "d"))) expected <- data.frame(row.names = 1:2) - expected$"struct(a, c)" <- list(listToStruct(list(a = 1L, c = 3L)), - listToStruct(list(a = 4L, c = 6L))) + expected$"d" <- list(listToStruct(list(a = 1L, c = 3L)), + listToStruct(list(a = 4L, c = 6L))) expect_equal(result, expected) - result <- collect(select(df, struct(df$a, df$b))) + result <- collect(select(df, alias(struct(df$a, df$b), "d"))) expected <- data.frame(row.names = 1:2) - expected$"struct(a, b)" <- list(listToStruct(list(a = 1L, b = 2L)), - listToStruct(list(a = 4L, b = 5L))) + expected$"d" <- list(listToStruct(list(a = 1L, b = 2L)), + listToStruct(list(a = 4L, b = 5L))) expect_equal(result, expected) # Test encode(), decode() -- cgit v1.2.3