feat: remove leading zeros from patient id (#190)

* feat: remove leading zeros from patient id

This also moves test files into subfolder `tests`.

* feat: enable removing of leading zeros using env var

This will enable removing of leading zeros only if env var
`REMOVE_LEADING_PATIENTID_ZEROS` is set to 'true'.

* chore: add new env var to compose.decompose-xmls.yaml

* fix: change code to apply MegaLinter rules

* tests: add ci job to run tests

.github/workflows/ci.yaml

@@ -66,6 +66,29 @@ jobs:
     secrets:
       github-token: ${{ secrets.GITHUB_TOKEN }}
 
+  tests:
+    strategy:
+      matrix:
+        # Python versions to run tests for
+        python-version: ["3.11"]
+    runs-on: ubuntu-22.04
+    steps:
+      - uses: actions/checkout@v4
+      - name: Set up Python ${{ matrix.python-version }}
+        uses: actions/setup-python@v5
+        with:
+          python-version: ${{ matrix.python-version }}
+      - name: Install dependencies
+        run: |
+          cd src/decompose_xmls
+          pip install pytest
+          pip install -r requirements.txt
+          pip install -r requirements-test.txt
+      - name: Run decompose_xmls tests
+        run: |
+          cd src/decompose_xmls
+          pytest
+
   test-k8s:
     runs-on: ubuntu-22.04
     # disabled since the major deployment platform is currently

docker-compose/compose.decompose-xmls.yaml

@@ -7,6 +7,8 @@ services:
       KAFKA_BOOTSTRAP_SERVERS: "kafka:9092"
       KAFKA_OUTPUT_TOPIC: "onkostar.MELDUNG_EXPORT"
       SAVE_AS_FILES_ENABLED: "false"
+      # Set to 'true' to enable removing of leading zeros in patient IDs
+      REMOVE_LEADING_PATIENTID_ZEROS: "false"
     volumes:
       - ./input-obds-reports:/app/input-obds-reports
       - ./output-obds-reports:/app/output-obds-reports

src/decompose_xmls/decompose_xmls.py

@@ -1,6 +1,7 @@
 import json
 import os
 import time
+import regex
 import xml.etree.ElementTree as ET
 from io import BytesIO
 
@@ -46,6 +47,13 @@ def kafka_delivery_report(err, msg):
         print(f"Message delivered to {msg.topic()}@{msg.partition()}")
 
 
+def remove_leading_zeros(patient_id: str) -> str:
+    if os.environ.get('REMOVE_LEADING_PATIENTID_ZEROS') == 'true':
+        return regex.sub(r'^0+', '', patient_id)
+    else:
+        return patient_id
+
+
 def decompose_sammelmeldung(root: ET.Element, filename: str):
     results = []
     settings = Settings()
@@ -91,8 +99,15 @@ def decompose_sammelmeldung(root: ET.Element, filename: str):
                 # append child Patient_Stammdaten first,
                 # append child Menge_Meldung_Group second
                 element_patient = ET.Element("Patient")
+
+                # Fix leading IDs in
+                if patient_id is not None:
+                    patient_id = remove_leading_zeros(patient_id)
+                    patient_stammdaten.set("Patient_ID", patient_id)
+
                 element_patient.append(patient_stammdaten)
                 element_patient.append(menge_meldung_group)
+
                 # build grandparent tag Menge_Patient and add Patient + children
                 menge_patient = ET.Element("Menge_Patient")
                 menge_patient.append(element_patient)

src/decompose_xmls/decompose_xmls_test.py

@@ -1,14 +1,41 @@
+import os
 import xml.etree.ElementTree as ET
 
 import pytest
 
-from decompose_xmls.decompose_xmls import decompose_sammelmeldung
+from .decompose_xmls import decompose_sammelmeldung
 
 
 @pytest.mark.parametrize(
     "obds_input_file_path", [("input-obds-reports/test-2patients.xml")]
 )
 def test_decompose_sammelmeldung(snapshot, obds_input_file_path):
+    os.environ['REMOVE_LEADING_PATIENTID_ZEROS'] = 'false'
+    tree = ET.parse(obds_input_file_path)
+    root = tree.getroot()
+
+    result = decompose_sammelmeldung(root, obds_input_file_path)
+    assert result == snapshot
+
+
+@pytest.mark.parametrize(
+    "obds_input_file_path", [("input-obds-reports/test-patientid-with-zeros.xml")]
+)
+def test_decompose_with_pathient_id_starting_with_zero(snapshot, obds_input_file_path):
+    os.environ['REMOVE_LEADING_PATIENTID_ZEROS'] = 'true'
+    tree = ET.parse(obds_input_file_path)
+    root = tree.getroot()
+
+    result = decompose_sammelmeldung(root, obds_input_file_path)
+    assert result == snapshot
+
+
+@pytest.mark.parametrize(
+    "obds_input_file_path", [("input-obds-reports/test-patientid-with-zeros.xml")]
+)
+def test_decompose_keep_pathient_id_starting_with_zero(snapshot, obds_input_file_path):
+    os.environ['REMOVE_LEADING_PATIENTID_ZEROS'] = 'false'
+
     tree = ET.parse(obds_input_file_path)
     root = tree.getroot()