From c97f6bd79014129deb88bc71b6a3e4f455fd1824 Mon Sep 17 00:00:00 2001
From: Etienne Bacher <52219252+etiennebacher@users.noreply.github.com>
Date: Thu, 9 Nov 2023 17:22:23 +0000
Subject: [PATCH] Error if wrong schema in `pl$DataFrame()` (#486)

---
 NEWS.md                         | 2 ++
 R/dataframe__frame.R            | 9 ++++++++-
 tests/testthat/test-dataframe.R | 9 ++++++---
 3 files changed, 16 insertions(+), 4 deletions(-)

diff --git a/NEWS.md b/NEWS.md
index 3789dc834..b6a0fe110 100644
--- a/NEWS.md
+++ b/NEWS.md
@@ -4,6 +4,8 @@
 
 - The argument `quote_style` in `$write_csv()` and `$sink_csv()` can now take 
   the value `"never"` (#483).
+- `pl$DataFrame()` now errors if the variables specified in `schema` do not exist
+  in the data (#486).
 
 # polars 0.10.0
 
diff --git a/R/dataframe__frame.R b/R/dataframe__frame.R
index ad4ccd4cf..7c97143b8 100644
--- a/R/dataframe__frame.R
+++ b/R/dataframe__frame.R
@@ -136,6 +136,13 @@ DataFrame
 pl$DataFrame = function(..., make_names_unique = TRUE, schema = NULL) {
   largs = unpack_list(...)
 
+  uw = \(res) unwrap(res, "in $DataFrame():")
+
+  if (!is.null(schema) && !all(names(schema) %in% names(largs))) {
+    Err_plain("Some columns in `schema` are not in the DataFrame.") |>
+      uw()
+  }
+
   # no args crete empty DataFrame
   if (length(largs) == 0L) {
     return(.pr$DataFrame$default())
@@ -188,7 +195,7 @@ pl$DataFrame = function(..., make_names_unique = TRUE, schema = NULL) {
     }) |>
       do.call(what = pl$select)
   }) |>
-    unwrap("in pl$DataFrame()")
+    uw()
 }
 
 
diff --git a/tests/testthat/test-dataframe.R b/tests/testthat/test-dataframe.R
index 9a754f5c6..a883abb67 100644
--- a/tests/testthat/test-dataframe.R
+++ b/tests/testthat/test-dataframe.R
@@ -160,15 +160,18 @@ test_that("DataFrame, custom schema", {
   expect_no_error(
     pl$DataFrame(list(schema = 1), schema = list(schema = pl$Float32))
   )
-  # errors if incorrect datatype
+  # incorrect datatype
   expect_error(pl$DataFrame(x = 1, schema = list(schema = foo)))
   expect_error(
     pl$DataFrame(x = 1, schema = list(x = "foo")),
     "expected RPolarsDataType"
   )
 
-  # TODO: why doesn't this error?
-  # expect_error(pl$DataFrame(x = 1, schema = list(schema = pl$foo)))
+  # wrong variable name in schema
+  expect_error(
+    pl$DataFrame(x = 1, schema = list(schema = pl$Float32)),
+    "Some columns in `schema` are not in the DataFrame"
+  )
 })