bugfixed incorrect files created + store output

.gitignore

@@ -172,3 +172,6 @@ cython_debug/
 
 # PyPI configuration file
 .pypirc
+
+*.DS_Store
+src/.DS_Store

pyproject.toml

@@ -1,6 +1,6 @@
 [project]
 name = "HammingdistanceCalculator"
-version = "0.1.0"
+version = "0.2.0"
 description = "Script that calculates the hamming distance between a list of barcodes."
 readme = "README.md"
 authors = [

src/hammingdistancecalculator/hamming_distance.py

@@ -1,4 +1,3 @@
-import pathlib
 import re
 import typer
 import csv
@@ -210,12 +209,18 @@ def compare_sample_barcode_list(sample_barcode_list: list) -> dict:
 # main script
 @cli.command()
 def main(input_csv: Path = typer.Argument(help="Pad naar input CSV met kolommen: label,barcode"),
-         max_distance: int = typer.Option(
-             1,
-             "--max-distance",
-             "-d",
-             help="Maximale hamming distance waarvoor output wordt geschreven (default op 1, wat 0 & 1 schrijft)."
-         )):
+        max_distance: int = typer.Option(
+            1,
+            "--max-distance",
+            "-d",
+            help="Maximale hamming distance waarvoor output wordt geschreven (default op 1, wat 0 & 1 schrijft)."
+        ),
+        outpath: Path = typer.Option(
+            ".",
+            "--outpath",
+            "-o",
+            help="Directory waar output files worden geschreven (default huidige directory)."
+        )):
 
     # read input
     sample_barcode_list = load_barcodes(input_csv)
@@ -233,9 +238,15 @@ def main(input_csv: Path = typer.Argument(help="Pad naar input CSV met kolommen:
     for key, value in compare_dict.items():
         hamming_distance_dict[value].append(key)
 
-    # write output files for all distances of 0 to max_distance (2 by default)
-    for counter in range(max_distance):
-        output_path = pathlib.Path(f"hamming_distance_{counter}.txt")
+    # verify output path exists to write to
+    outpath.mkdir(parents=True, exist_ok=True)
+
+    # add 1 to the max distance because when you want a range of 1, you want to loop 'including' 1, not 'until' 1
+    effective_max_distance = max_distance + 1
+
+    # write output files for all distances of 0 to effective_max_distance (2 by default)
+    for counter in range(effective_max_distance):
+        output_path = outpath / f"hamming_distance_{counter}.txt"
 
         # write each file
         with output_path.open('w', newline='') as file_handle:

tests/test_hamming_distance.py

@@ -1,13 +1,15 @@
 import pytest
 import re
 from hammingdistancecalculator.hamming_distance import (
+    cli,
     hamming_distance,
     is_valid_dna,
     rev_comp,
     is_valid_input_csv,
     load_barcodes,
     compare_sample_barcode_list
 )
+from typer.testing import CliRunner
 
 # test hamming distance function
 @pytest.mark.parametrize(
@@ -153,28 +155,13 @@ def test_compare_sample_barcode_list_with_mocked_tpqm(mocker):
     progress_mock = mocker.MagicMock()
     tqdm_mock = mocker.MagicMock()
     tqdm_mock.return_value = progress_mock
-#    tqdm_mock.return_value.__enter__.return_value = progress_mock
 
     # patch the function we want to mock
     mocker.patch("hammingdistancecalculator.hamming_distance.tqdm", tqdm_mock)
 
     # store the return function so we can compare to the expected values
     return_value = compare_sample_barcode_list(test_set)
 
-    #
-    # # compare expected keys to return value
-    # expected_keys = {
-    #     "S1_vs_S2",
-    #     "S1_vs_revcomp_S2",
-    #     "S1_vs_S3",
-    #     "S1_vs_revcomp_S3",
-    #     "S2_vs_S3",
-    #     "S2_vs_revcomp_S3"
-    # }
-    #
-    # # check the keys are correct
-    # assert set(return_value.keys()) == expected_keys
-
     # compare expected values to return values
     expected_values = {
         "S1_vs_S2": 1,
@@ -193,4 +180,142 @@ def test_compare_sample_barcode_list_with_mocked_tpqm(mocker):
 
     # create tqdm & update it while going over the items
     # N = 3 -> total = N * (N - 1) = 6
-    tqdm_mock.assert_called_once_with(total=6, desc="Compare_barcodes", unit="cmp")
+    tqdm_mock.assert_called_once_with(total=6, desc="Compare_barcodes", unit="cmp")
+
+
+def test_cli_outpath_parameter_creates_directory(tmp_path):
+    """Test dat --outpath directory automatisch maakt"""
+    input_file = tmp_path / "input.csv"
+    input_file.write_text("label,barcode\nS1,ACTG\nS2,ACCG", encoding="utf-8")
+
+    output_dir = tmp_path / "custom_output"
+    assert not output_dir.exists()
+
+    runner = CliRunner()
+    result = runner.invoke(cli, [str(input_file), "--outpath", str(output_dir)])
+
+    assert result.exit_code == 0
+    assert output_dir.exists(), "Directory werd niet aangemaakt!"
+
+
+def test_cli_max_distance_plus_one_logic(tmp_path):
+    """Test dat max_distance+1 correct werkt (effectieve range telt 1 op bij max)"""
+    input_file = tmp_path / "data.csv"
+    input_file.write_text("label,barcode\nS1,AAAA\nS2,CCCC", encoding="utf-8")
+
+    output_dir = tmp_path / "max_test"
+
+    runner = CliRunner()
+    result = runner.invoke(cli, [str(input_file), "-d", "2", "-o", str(output_dir)])
+
+    assert result.exit_code == 0
+
+    # max_distance=2, effectiveMaxDistance=3 → files 0, 1, 2 (3 files totaal)
+    created_files = sorted([f.name for f in output_dir.glob("hamming_distance_*.txt")])
+    expected_files = ["hamming_distance_0.txt", "hamming_distance_1.txt", "hamming_distance_2.txt"]
+
+    assert created_files == expected_files, f"Verwacht {expected_files}, kreeg {created_files}"
+
+
+def test_cli_both_short_and_long_flags_work(tmp_path):
+    """Test dat zowel -d/-o als --max-distance/--outpath werken"""
+    input_file = tmp_path / "test.csv"
+    input_file.write_text("label,barcode\nX,ATGC\nY,ATGA", encoding="utf-8")
+
+    output_dir = tmp_path / "flags_test"
+
+    runner = CliRunner()
+    # Gebruik korte flags
+    result = runner.invoke(cli, [str(input_file), "-d", "1", "-o", str(output_dir)])
+
+    assert result.exit_code == 0
+    assert len(list(output_dir.glob("*.txt"))) > 0
+
+
+def test_cli_default_behavior_without_options(tmp_path):
+    """Test default gedrag met expliciete . directory"""
+    input_file = tmp_path / "default.csv"
+    input_file.write_text("label,barcode\nA,ACTG\nB,ACCG", encoding="utf-8")
+
+    output_dir = tmp_path / "dot_output"
+
+    runner = CliRunner()
+    result = runner.invoke(cli, [str(input_file), "-o", str(output_dir)])
+
+    assert result.exit_code == 0
+    assert (output_dir / "hamming_distance_0.txt").exists()
+
+
+def test_cli_help_shows_all_options():
+    """Test dat --help beide opties toont"""
+    runner = CliRunner()
+    result = runner.invoke(cli, ["--help"])
+
+    assert result.exit_code == 0
+    assert "--outpath" in result.stdout or "-o" in result.stdout
+    assert "--max-distance" in result.stdout or "-d" in result.stdout
+
+
+def test_cli_multiple_barcodes_different_distances(tmp_path):
+    """Test met diverse afstanden tussen barcodes"""
+    input_file = tmp_path / "multi.csv"
+    # AAAA vs AAAA = dist 0
+    # AAAA vs AAAA = dist 0
+    # AAAA vs AAAG = dist 1
+    # AAAA vs GGTC = dist 4
+    input_file.write_text("label,barcode\nM,AAAA\nN,AAAA\nO,AAAG\nP,GGTC", encoding="utf-8")
+
+    output_dir = tmp_path / "mixed_distances"
+
+    runner = CliRunner()
+    result = runner.invoke(cli, [str(input_file), "-d", "5", "-o", str(output_dir)])
+
+    assert result.exit_code == 0
+
+    # Minstens dist 0 en 1 moeten bestaan
+    assert (output_dir / "hamming_distance_0.txt").exists()
+    assert (output_dir / "hamming_distance_1.txt").exists()
+
+
+def test_cli_output_content_verification(tmp_path):
+    """Test dat output file inhoud correct is"""
+    input_file = tmp_path / "verify.csv"
+    input_file.write_text("label,barcode\nFirst,AAAA\nSecond,AAAA", encoding="utf-8")
+
+    output_dir = tmp_path / "content_check"
+
+    runner = CliRunner()
+    result = runner.invoke(cli, [str(input_file), "--outpath", str(output_dir)])
+
+    assert result.exit_code == 0
+
+    dist0 = output_dir / "hamming_distance_0.txt"
+    content = dist0.read_text()
+
+    # Check juiste format (LET OP: "vs" met spaties, NIET "_vs_"!)
+    assert "Number of comparisons found with hamming distance 0:" in content
+    assert "Barcode First vs barcode Second" in content
+    assert "has hamming distance 0" in content
+
+
+def test_cli_nonexistent_parent_directory_created(tmp_path):
+    """Test nested directory (parents=True)"""
+    input_file = tmp_path / "input.csv"
+    input_file.write_text("label,barcode\nS1,ACTG", encoding="utf-8")
+
+    output_dir = tmp_path / "level1" / "level2" / "deep_output"
+
+    runner = CliRunner()
+    result = runner.invoke(cli, [str(input_file), "-o", str(output_dir)])
+
+    assert result.exit_code == 0
+    assert output_dir.exists(), "Nested directories werden niet aangemaakt!"
+
+
+def test_cli_missing_required_argument_fails():
+    """Test dat ontbrekend verplicht argument een error geeft"""
+    runner = CliRunner()
+    result = runner.invoke(cli, [])  # Geen input argument
+
+    assert result.exit_code != 0
+    assert "Missing argument" in result.output or "Usage:" in result.output