From 930a50aa09f220c64415183754829e48b487157e Mon Sep 17 00:00:00 2001
From: Elmar Zander <elmar.zander@googlemail.com>
Date: Tue, 1 Oct 2024 14:48:12 +0200
Subject: [PATCH] Fixed path problems probably causing errors under windows

---
 tests/conftest.py                 | 29 ++++++++---------------------
 tests/system_tests/test_rollup.py | 16 +++++-----------
 2 files changed, 13 insertions(+), 32 deletions(-)

diff --git a/tests/conftest.py b/tests/conftest.py
index f6bd71a..4734b24 100644
--- a/tests/conftest.py
+++ b/tests/conftest.py
@@ -254,9 +254,7 @@ def psms_dataset(psm_df_1000):
 def psms_ondisk():
     """A small OnDiskPsmDataset"""
     filename = Path("data", "scope2_FP97AA.pin")
-    df_spectra = pd.read_csv(
-        filename, sep="\t", usecols=["ScanNr", "ExpMass", "Label"]
-    )
+    df_spectra = pd.read_csv(filename, sep="\t", usecols=["ScanNr", "ExpMass", "Label"])
     with open(filename) as perc:
         columns = perc.readline().rstrip().split("\t")
     psms = OnDiskPsmDataset(
@@ -308,7 +306,7 @@ def psms_ondisk():
 @pytest.fixture
 def psms_ondisk_from_parquet():
     """A small OnDiskPsmDataset"""
-    filename = Path("data/10k_psms_test.parquet")
+    filename = Path("data") / "10k_psms_test.parquet"
     df_spectra = pq.read_table(
         filename, columns=["ScanNr", "ExpMass", "Label"]
     ).to_pandas()
@@ -451,9 +449,7 @@ def targets_decoys_psms_scored(tmp_path):
     scores = scores[idx]
     label = label[idx]
     qval = tdc(scores, label)
-    pep = getQvaluesFromScores(
-        target_scores, decoy_scores, includeDecoys=True
-    )[1]
+    pep = getQvaluesFromScores(target_scores, decoy_scores, includeDecoys=True)[1]
     peptides = np.hstack([np.arange(1, n + 1), np.arange(1, n + 1)])
     peptides.sort()
     df = pd.DataFrame(
@@ -468,19 +464,13 @@ def targets_decoys_psms_scored(tmp_path):
         ],
     )
     df["proteinIds"] = "dummy"
-    df[df["Label"] == 1].drop("Label", axis=1).to_csv(
-        psms_t, sep="\t", index=False
-    )
-    df[df["Label"] == -1].drop("Label", axis=1).to_csv(
-        psms_d, sep="\t", index=False
-    )
+    df[df["Label"] == 1].drop("Label", axis=1).to_csv(psms_t, sep="\t", index=False)
+    df[df["Label"] == -1].drop("Label", axis=1).to_csv(psms_d, sep="\t", index=False)
 
     return [psms_t, psms_d]
 
 
-def _make_fasta(
-    num_proteins, peptides, peptides_per_protein, random_state, prefix=""
-):
+def _make_fasta(num_proteins, peptides, peptides_per_protein, random_state, prefix=""):
     """Create a FASTA string from a set of peptides
 
     Parameters
@@ -504,9 +494,7 @@ def _make_fasta(
     lines = []
     for protein in range(num_proteins):
         lines.append(f">{prefix}sp|test|test_{protein}")
-        lines.append(
-            "".join(list(random_state.choice(peptides, peptides_per_protein)))
-        )
+        lines.append("".join(list(random_state.choice(peptides, peptides_per_protein))))
 
     return lines
 
@@ -514,8 +502,7 @@ def _make_fasta(
 def _random_peptide(length, random_state):
     """Generate a random peptide"""
     return "".join(
-        list(random_state.choice(list("ACDEFGHILMNPQSTVWY"), length - 1))
-        + ["K"]
+        list(random_state.choice(list("ACDEFGHILMNPQSTVWY"), length - 1)) + ["K"]
     )
 
 
diff --git a/tests/system_tests/test_rollup.py b/tests/system_tests/test_rollup.py
index 3d05851..841391c 100644
--- a/tests/system_tests/test_rollup.py
+++ b/tests/system_tests/test_rollup.py
@@ -79,9 +79,7 @@ def test_extra_cols(tmp_path):
     """Test that two identical mokapot runs produce same results."""
 
     extended_file = Path("data", "percolator-noSplit-extended-10000.tab")
-    non_extended_file = Path(
-        "data", "percolator-noSplit-non-extended-10000.tab"
-    )
+    non_extended_file = Path("data", "percolator-noSplit-non-extended-10000.tab")
 
     params = [
         ("--dest_dir", tmp_path),
@@ -110,12 +108,8 @@ def test_extra_cols(tmp_path):
         df_run1_t_psms[df_run2_t_psms.columns], df_run2_t_psms
     )
 
-    df_run1_t_peptides = pd.read_csv(
-        tmp_path / "run1.targets.peptides.csv", sep="\t"
-    )
-    df_run2_t_peptides = pd.read_csv(
-        tmp_path / "run2.targets.peptides.csv", sep="\t"
-    )
+    df_run1_t_peptides = pd.read_csv(tmp_path / "run1.targets.peptides.csv", sep="\t")
+    df_run2_t_peptides = pd.read_csv(tmp_path / "run2.targets.peptides.csv", sep="\t")
     pd.testing.assert_frame_equal(
         df_run1_t_peptides[df_run2_t_peptides.columns], df_run2_t_peptides
     )
@@ -124,7 +118,7 @@ def test_extra_cols(tmp_path):
 def test_deduplication(tmp_path):
     """Test that deduplication of psms works."""
     path = tmp_path
-    file = "data/scope2_FP97AA.pin"
+    file = Path("data") / "scope2_FP97AA.pin"
 
     params = [
         file,
@@ -172,7 +166,7 @@ def test_deduplication(tmp_path):
 def test_streaming(tmp_path, percolator_extended_file_big):
     """Test that streaming of confidence assignments works."""
     path = tmp_path
-    file = "data/scope2_FP97AA.pin"
+    file = Path("data") / "scope2_FP97AA.pin"
 
     base_params = [
         file,