From b85caf2bed319b5fa354495a86dca76910a9cb1b Mon Sep 17 00:00:00 2001
From: "C. Titus Brown" <titus@idyll.org>
Date: Sun, 10 Nov 2024 11:07:06 -0800
Subject: [PATCH] some scaled stuff

---
 src/python/tests/test_manysearch.py  | 30 ++++++++++++++++++++++++++++
 src/python/tests/test_multisearch.py |  6 ++++--
 src/python/tests/test_pairwise.py    | 22 ++++++++++++++++++++
 3 files changed, 56 insertions(+), 2 deletions(-)

diff --git a/src/python/tests/test_manysearch.py b/src/python/tests/test_manysearch.py
index f9283dfd..a91675ea 100644
--- a/src/python/tests/test_manysearch.py
+++ b/src/python/tests/test_manysearch.py
@@ -379,6 +379,36 @@ def test_simple_threshold(runtmp, indexed, zip_query):
     assert len(df) == 3
 
 
+def test_simple_scaled(runtmp, indexed, zip_query):
+    # test with a different scaled
+    query_list = runtmp.output("query.txt")
+    against_list = runtmp.output("against.txt")
+
+    sig2 = get_test_data("2.fa.sig.gz")
+    sig47 = get_test_data("47.fa.sig.gz")
+    sig63 = get_test_data("63.fa.sig.gz")
+
+    make_file_list(query_list, [sig2, sig47, sig63])
+    make_file_list(against_list, [sig2, sig47, sig63])
+
+    if indexed:
+        against_list = index_siglist(runtmp, against_list, runtmp.output("db"))
+
+    if zip_query:
+        query_list = zip_siglist(runtmp, query_list, runtmp.output("query.zip"))
+
+    output = runtmp.output("out.csv")
+
+    runtmp.sourmash(
+        "scripts", "manysearch", query_list, against_list, "-o", output, "-s", "10_000"
+    )
+    assert os.path.exists(output)
+
+    df = pandas.read_csv(output)
+    assert len(df) == 3
+    assert set(list(df['scaled'])) == {10000}
+
+
 def test_simple_manifest(runtmp, indexed):
     # test with a simple threshold => only 3 results
     query_list = runtmp.output("query.txt")
diff --git a/src/python/tests/test_multisearch.py b/src/python/tests/test_multisearch.py
index ef018a96..123b3872 100644
--- a/src/python/tests/test_multisearch.py
+++ b/src/python/tests/test_multisearch.py
@@ -1195,9 +1195,11 @@ def test_mismatched_scaled_query(runtmp):
 
     output = runtmp.output("out.csv")
 
-    runtmp.sourmash("scripts", "multisearch", query_list, against_list, "-o", output)
+    runtmp.sourmash("scripts", "multisearch", query_list, against_list, "-o", output, '-s', '10_000')
     assert os.path.exists(output)
-
+    df = pandas.read_csv(output)
+    assert len(df) == 5
+    assert set(list(df['scaled'])) == {10_000}
 
 def test_mismatched_scaled_against(runtmp):
     # test what happens if against scaled is too high
diff --git a/src/python/tests/test_pairwise.py b/src/python/tests/test_pairwise.py
index bd54c5cd..ce9d94f7 100644
--- a/src/python/tests/test_pairwise.py
+++ b/src/python/tests/test_pairwise.py
@@ -728,3 +728,25 @@ def test_simple_below_threshold_write_all_no_ani(runtmp):
             assert float(row["jaccard"]) == 1.0
             assert row["query_name"] == row["match_name"]
             assert row["query_md5"] == row["match_md5"]
+
+
+def test_simple_scaled(runtmp):
+    # test basic execution w/scaled!
+    query_list = runtmp.output("query.txt")
+    against_list = runtmp.output("against.txt")
+
+    sig2 = get_test_data("2.fa.sig.gz")
+    sig47 = get_test_data("47.fa.sig.gz")
+    sig63 = get_test_data("63.fa.sig.gz")
+
+    make_file_list(query_list, [sig2, sig47, sig63])
+
+    output = runtmp.output("out.csv")
+
+    runtmp.sourmash(
+        "scripts", "pairwise", query_list, "-o", output, "-s", "10_000"
+    )
+    assert os.path.exists(output)
+    df = pandas.read_csv(output)
+    assert len(df) == 1
+    assert set(list(df['scaled'])) == {10_000}