From 27be1948ad0ffbbc522444f51cda3ff5b7a3f162 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Bogumi=C5=82=20Kami=C5=84ski?= <bkamins@sgh.waw.pl>
Date: Fri, 20 Oct 2023 11:44:50 +0200
Subject: [PATCH] fix nonunique bug

---
 src/abstractdataframe/unique.jl | 2 +-
 src/groupeddataframe/utils.jl   | 6 +++++-
 test/duplicates.jl              | 9 ++++++---
 3 files changed, 12 insertions(+), 5 deletions(-)

diff --git a/src/abstractdataframe/unique.jl b/src/abstractdataframe/unique.jl
index fd94caac66..9441b825c0 100644
--- a/src/abstractdataframe/unique.jl
+++ b/src/abstractdataframe/unique.jl
@@ -87,7 +87,7 @@ function nonunique(df::AbstractDataFrame; keep::Symbol=:first)
     if !(keep in (:first, :last, :noduplicates))
         throw(ArgumentError("`keep` must be :first, :last, or :noduplicates"))
     end
-    ncol(df) == 0 && return Bool[]
+    nrow(df) == 0 && return Bool[]
     res = fill(true, nrow(df))
     cols = ntuple(i -> df[!, i], ncol(df))
     if keep == :first
diff --git a/src/groupeddataframe/utils.jl b/src/groupeddataframe/utils.jl
index 1a58b7ec44..0e4b1d9840 100644
--- a/src/groupeddataframe/utils.jl
+++ b/src/groupeddataframe/utils.jl
@@ -337,7 +337,11 @@ function row_group_slots!(cols::NTuple{N, AbstractVector},
        nt = max(1, lg ÷ 100_000)
     end
     # if there are few rows per group limit the number of threads used
-    nt = clamp(round(Int, (lg / 4) / ngroups - 2), 1, nt)
+    if ngroups == 0
+        nt = 1
+    else
+        nt = clamp(round(Int, (lg / 4) / ngroups - 2), 1, nt)
+    end
 
     seen = fill(false, ngroups)
     seen_vec = Vector{Vector{Bool}}(undef, nt)
diff --git a/test/duplicates.jl b/test/duplicates.jl
index 61c01874d2..d8c264962b 100644
--- a/test/duplicates.jl
+++ b/test/duplicates.jl
@@ -1,6 +1,6 @@
 module TestDuplicates
 
-using Test, DataFrames, CategoricalArrays, Random
+using Test, DataFrames, CategoricalArrays, Random, PooledArrays
 const ≅ = isequal
 
 @testset "nonunique" begin
@@ -30,8 +30,8 @@ const ≅ = isequal
     @test_throws ArgumentError unique!(df)
     @test_throws ArgumentError unique(df, true)
 
-     pdf = view(DataFrame(a=CategoricalArray(["a", "a", missing, missing, "b", missing, "a", missing]),
-                          b=CategoricalArray(["a", "b", missing, missing, "b", "a", "a", "a"])), :,  :)
+    pdf = view(DataFrame(a=CategoricalArray(["a", "a", missing, missing, "b", missing, "a", missing]),
+                         b=CategoricalArray(["a", "b", missing, missing, "b", "a", "a", "a"])), :,  :)
     updf = DataFrame(a=CategoricalArray(["a", "a", missing, "b", missing]),
                      b=CategoricalArray(["a", "b", missing, "b", "a"]))
     @test nonunique(pdf) == [false, false, false, true, false, false, true, true]
@@ -39,6 +39,9 @@ const ≅ = isequal
     @test updf ≅ unique(pdf)
     @test_throws ArgumentError unique!(pdf)
     @test_throws ArgumentError unique(pdf, true)
+
+    @test isempty(nonunique(DataFrame(a=PooledArray(Int[]))))
+    @test typeof(nonunique(DataFrame(a=PooledArray(Int[])))) === Vector{Bool}
 end
 
 @testset "nonunique, nonunique, unique! with extra argument" begin