Feature/add pytest parse ped

.github/workflows/utils_lint.yml

@@ -0,0 +1,11 @@
+name: Utils Lint
+on:
+  pull_request:
+    paths: Utils/**
+
+jobs:
+  ruff:
+    runs-on: ubuntu-latest
+    steps:
+      - uses: actions/checkout@v4
+      - uses: chartboost/ruff-action@v1

.github/workflows/utils_test.yml

@@ -0,0 +1,59 @@
+# Source: https://github.com/marketplace/actions/install-poetry-action
+name: Utils Test
+on:
+  pull_request:
+    paths: Utils/**
+jobs:
+  pytest:
+    runs-on: ubuntu-latest
+    defaults:
+      run:
+        working-directory: Utils/
+    steps:
+      #----------------------------------------------
+      # check-out repo and set-up python
+      #----------------------------------------------
+      - name: Check out repository
+        uses: actions/checkout@v4
+      - name: Set up python
+        id: setup-python
+        uses: actions/setup-python@v5
+        with:
+          python-version: '3.11.5'
+      #----------------------------------------------
+      # install & configure poetry
+      #----------------------------------------------
+      - name: Install Poetry
+        uses: snok/install-poetry@v1
+        with:
+          virtualenvs-create: true
+          virtualenvs-in-project: true
+          installer-parallel: true
+
+      #----------------------------------------------
+      # load cached venv if cache exists
+      #----------------------------------------------
+      - name: Load cached venv
+        id: cached-poetry-dependencies
+        uses: actions/cache@v4
+        with:
+          path: .venv
+          key: venv_utils-${{ runner.os }}-${{ steps.setup-python.outputs.python-version }}-${{ hashFiles('**/poetry.lock') }}
+      #----------------------------------------------
+      # install dependencies if cache does not exist
+      #----------------------------------------------
+      - name: Install dependencies
+        if: steps.cached-poetry-dependencies.outputs.cache-hit != 'true'
+        run: poetry install --no-interaction --no-root
+      #----------------------------------------------
+      # install root project
+      #----------------------------------------------
+      - name: Install project
+        run: poetry install --no-interaction
+      #----------------------------------------------
+      # run pytest
+      #----------------------------------------------
+      - name: Run tests
+        run: |
+          source .venv/bin/activate
+          pytest .

Utils/data/multi_family.ped

@@ -0,0 +1,6 @@
+U000001 2024D00001  0	0	1	1
+U000001 2024D00002  0	0	2	1
+U000001 2024D00003	2024D00001	2024D00002	2	2
+U000002 2024D00004	0	0	1	1
+U000002 2024D00005	0	0	2	1
+U000002 2024D00006	2024D00004	2024D00005	2	2

Utils/data/multi_siblings.ped

@@ -0,0 +1,4 @@
+U000001	2024D00001	0	0	1	1
+U000001	2024D00002	0	0	2	1
+U000001	2024D00003	2024D00001	2024D00002	2	2
+U000001	2024D00004	2024D00001	2024D00002	2	2

Utils/data/multi_unrelated_samples.ped

@@ -0,0 +1,2 @@
+U000001	2024D00001	0	0	1	1
+U000002	2024D00002	0	0	2	1

Utils/data/single_family.ped

@@ -0,0 +1,3 @@
+U000001	2024D00001	0	0	1	1
+U000001	2024D00002	0	0	2	1
+U000001	2024D00003	2024D00001	2024D00002	2	2

Utils/parse_child_from_fulltrio.py

@@ -4,7 +4,6 @@
 
 def parse_ped(ped_file):
     samples = {}  # 'sample_id': {'family': 'fam_id', 'parents': ['sample_id', 'sample_id']}
-
     for line in ped_file:
         ped_data = line.strip().split()
         family, sample, father, mother, sex, phenotype = ped_data

Utils/pyproject.toml

@@ -0,0 +1,20 @@
+[tool.poetry]
+name = "utils"
+version = "0.1.0"
+description = ""
+authors = ["Your Name <[email protected]>"]
+license = "MIT"
+package-mode = false
+
+[tool.poetry.dependencies]
+python = "^3.11"
+pytest-unordered = "0.5.2"
+pytest-datadir = "^1.5.0"
+
+[tool.ruff]
+line-length = 127
+indent-width = 4
+
+[build-system]
+requires = ["poetry-core"]
+build-backend = "poetry.core.masonry.api"

Utils/test_parse_child_from_fulltrio.py

@@ -0,0 +1,49 @@
+#!/usr/bin/env python
+# Import statements, alphabetic order of main package.
+
+# Third party libraries alphabetic order of main package.
+import pytest
+from pytest_unordered import unordered
+
+# Custom libraries alphabetic order of main package.
+from parse_child_from_fulltrio import parse_ped
+@pytest.mark.parametrize("input_file,exp_dict_samples", [
+    ("multi_family.ped",
+        {
+            "2024D00001": {'family': 'U000001', 'parents': [], 'children': ["2024D00003"]},
+            "2024D00002": {'family': 'U000001', 'parents': [], 'children': ["2024D00003"]},
+            "2024D00003": {'family': 'U000001', 'parents': ["2024D00001","2024D00002"], 'children': []},
+            "2024D00004": {'family': 'U000002', 'parents': [], 'children': ["2024D00006"]},
+            "2024D00005": {'family': 'U000002', 'parents': [], 'children': ["2024D00006"]},
+            "2024D00006": {'family': 'U000002', 'parents': ["2024D00004","2024D00005"], 'children': []},
+        },
+    ),
+    ("multi_siblings.ped",
+        {
+            "2024D00001": {'family': 'U000001', 'parents': [], 'children': ["2024D00003", "2024D00004"]},
+            "2024D00002": {'family': 'U000001', 'parents': [], 'children': ["2024D00003", "2024D00004"]},
+            "2024D00003": {'family': 'U000001', 'parents': ["2024D00001","2024D00002"], 'children': []},
+            "2024D00004": {'family': 'U000001', 'parents': ["2024D00001","2024D00002"], 'children': []},
+        },
+    ),
+    ("multi_unrelated_samples.ped",
+        {
+            "2024D00001": {'family': 'U000001', 'parents': [], 'children': []},
+            "2024D00002": {'family': 'U000002', 'parents': [], 'children': []},
+        },
+    ),
+    ("single_family.ped",
+        {
+            "2024D00001": {'family': 'U000001', 'parents': [], 'children': ["2024D00003"]},
+            "2024D00002": {'family': 'U000001', 'parents': [], 'children': ["2024D00003"]},
+            "2024D00003": {'family': 'U000001', 'parents': ["2024D00001","2024D00002"], 'children': []},
+        },
+    ),
+])
+def test_parse_ped(input_file, exp_dict_samples, shared_datadir):
+    dict_samples = parse_ped(open(f"{shared_datadir}/{input_file}", "r"))
+    assert dict_samples.keys() == unordered(exp_dict_samples.keys())
+    for sample, meta in dict_samples.items():
+        assert meta.get("family") == exp_dict_samples.get(sample).get("family")
+        assert meta.get("parents") == unordered(exp_dict_samples.get(sample).get("parents"))
+        assert meta.get("children") == unordered(exp_dict_samples.get(sample).get("children"))