fix merge when one column is missing

junder873 · Jan 5, 2022 · 2f662e7 · 2f662e7 · junder873 · Jan 6, 2022
1 parent 7f10272
commit 2f662e7
Show file tree

Hide file tree

Showing 2 changed files with 4 additions and 3 deletions.
diff --git a/Project.toml b/Project.toml
@@ -1,7 +1,7 @@
 name = "WRDSMerger"
 uuid = "59d27aa3-834e-4232-9046-52ef43e86786"
 authors = ["junder873 <junder873@gmail.com>"]
-version = "0.3.1"
+version = "0.3.2"
 
 [deps]
 AbstractTrees = "1520ce14-60c1-5f80-bbc7-55ef81b5835c"

diff --git a/src/mergeFunctions.jl b/src/mergeFunctions.jl
@@ -225,9 +225,10 @@ end
 
 function adjust_date_cols(df::DataFrame, table::LinkTable, date_min::Date, date_max::Date)
     if ismissing(table.date_col_max) && !ismissing(table.date_col_min)
+        col = Dict(table.type_translations...)[table.id_cols[1]] |> string
         df[!, table.date_col_min] = coalesce.(df[:, table.date_col_min], date_min)
-        sort!(df, [table.id_cols[1], table.date_col_min])
-        gdf = groupby(df, [table.id_cols[1]])
+        sort!(df, [col, table.date_col_min])
+        gdf = groupby(df, [col])
         df = transform(gdf, table.date_col_min => lead => "date_max")
         df[!, "date_max"] = coalesce.(df[:, "date_max"] .- Day(1), date_max)# I subtract a day since use <= later
         table.date_col_max = "date_max"