ARROW-13887 [R] Capture error produced when reading in CSV file with headers and using a schema, and add suggestion

dragosmg · jonkeane · commit a0c650415bc2 · 2021-11-01T15:42:37.000-05:00
Closes apache#11432 from dragosmg/ARROW-13887_csv_header_schema_error Lead-authored-by: Dragos Moldovan-Grünfeld <dragos.mold@gmail.com> Co-authored-by: Dragoș Moldovan-Grünfeld <dragos.mold@gmail.com> Signed-off-by: Jonathan Keane <jkeane@gmail.com>
diff --git a/r/R/csv.R b/r/R/csv.R
@@ -192,7 +192,12 @@ read_delim_arrow <- function(file,
     convert_options = convert_options
   )
 
-  tab <- reader$Read()
+  tryCatch(
+    tab <- reader$Read(),
+    error = function(e) {
+      handle_csv_read_error(e, schema)
+    }
+  )
 
   # TODO: move this into convert_options using include_columns
   col_select <- enquo(col_select)
diff --git a/r/R/util.R b/r/R/util.R
@@ -193,3 +193,18 @@ repeat_value_as_array <- function(object, n) {
   }
   return(Scalar$create(object)$as_array(n))
 }
+
+handle_csv_read_error <- function(e, schema) {
+  msg <- conditionMessage(e)
+
+  if (grepl("conversion error", msg) && inherits(schema, "Schema")) {
+    abort(c(
+      msg,
+      i = paste("If you have supplied a schema and your data contains a header",
+                "row, you should supply the argument `skip = 1` to prevent the",
+                "header being read in as data.")
+    ))
+  }
+
+  abort(e)
+}
diff --git a/r/tests/testthat/test-csv.R b/r/tests/testthat/test-csv.R
@@ -266,6 +266,27 @@ test_that("Mix of guessing and declaring types", {
   expect_identical(df, tbl[, c("dbl", "false", "chr")])
 })
 
+test_that("more informative error when reading a CSV with headers and schema", {
+  tf <- tempfile()
+  on.exit(unlink(tf))
+
+  write.csv(example_data, tf, row.names = FALSE)
+
+  share_schema <- schema(
+    int = int32(),
+    dbl = float64(),
+    dbl2 = float64(),
+    lgl = boolean(),
+    false = boolean(),
+    chr = utf8(),
+    fct = utf8()
+  )
+
+  expect_error(
+    read_csv_arrow(tf, schema = share_schema),
+    "header row"
+  )
+})
 
 test_that("Write a CSV file with header", {
   tbl_out <- write_csv_arrow(tbl_no_dates, csv_file)
