Hard-Testing Importers with fixes and more Tests

Author: Pitastic

reader/Comdirect.py

@@ -82,8 +82,9 @@ def from_pdf(self, filepath):
             filepath,
             pages="2-end",
             flavor="stream",
-            row_tol=10,
-            columns=["115,187,305,500"]*16
+            row_tol=12,
+            columns=["115,187,305,500"],
+            table_areas=["0,830,590,0"]
         )
         #TODO: Hack-araound: https://github.com/atlanhq/camelot/issues/357#issuecomment-520986016
 
@@ -118,6 +119,7 @@ def from_pdf(self, filepath):
         for i, row in enumerated_table:
 
             if re_datecheck.match(row[0]) is None:
+                print("skip row", row)
                 continue  # Skip Header and unvalid Rows
 
             amount = float(row[4].replace('.', '').replace(',', '.'))

reader/Volksbank_Mittelhessen.py

@@ -82,7 +82,7 @@ def from_pdf(self, filepath):
             pages="all", # End -1
             flavor="stream",
             table_areas=["60,629,573,51"],
-            columns=["75,112,440,526"],
+            columns=["75,115,455"],
             split_text=True
         )
 
@@ -103,11 +103,11 @@ def from_pdf(self, filepath):
             if row[2].replace(' ', '').lower().startswith('alterkontostand'):
                 # Last row before transactions
                 start_index = self.all_rows.index(row) + 1
-                date_tx_year = row[2][-4:]  # Jahr für die Transaktionen merken
 
             if row[2].replace(' ', '').lower().startswith('neuerkontostand'):
                 # First row after transactions + final line
                 end_index = self.all_rows.index(row) - 1
+                date_tx_year = row[2][-4:]  # Jahr für die Transaktionen merken
                 break
 
         if date_tx_year is None or re.match(r'^\d{4}$', date_tx_year) is None:
@@ -125,8 +125,9 @@ def from_pdf(self, filepath):
                 continue  # Skip Header and unvalid Rows
 
             # Positives 'Haben' oder negatives 'Soll'
-            amount = f'-{row[3]}' if row[3] else row[4]
-            amount = amount[:-2].replace('.', '').replace(',', '.')
+            amount_prefix = '' if row[3][-1] == 'H' else '-'
+            amount = f"{amount_prefix}{re.sub(r'H|S', '', row[3]).strip()}"
+            amount = amount.replace('.', '').replace(',', '.')
 
             line = {
                 'date_tx': self._parse_from_strftime(f"{row[0]}{date_tx_year}", "%d.%m.%Y"),

tests/test_unit_reader_Comdirect.py

@@ -28,7 +28,7 @@ def test_read_from_csv(test_app):
 
 
 # Look for test files and create a tuple list
-test_folder = os.path.join('/tmp', 'comdirect')
+test_folder = os.path.join('/tmp', 'Comdirect')
 test_files = []
 if not os.path.isdir(test_folder):
     test_files = [()]
@@ -48,6 +48,7 @@ def test_read_from_pdf(test_app, full_path):
 
     with test_app.app_context():
         transaction_list = Comdirect().from_pdf(full_path)
+        assert transaction_list, "No transactions found in PDF file"
 
         # Check Reader Ergebnisse
         check_transaktion_list(transaction_list)

tests/test_unit_reader_Commerzbank.py

@@ -27,7 +27,7 @@ def test_read_from_csv(test_app):
 
 
 # Look for test files and create a tuple list
-test_folder = os.path.join('/tmp', 'commerzbank')
+test_folder = os.path.join('/tmp', 'Commerzbank')
 test_files = []
 if not os.path.isdir(test_folder):
     test_files = [()]
@@ -47,6 +47,7 @@ def test_read_from_pdf(test_app, full_path):
 
     with test_app.app_context():
         transaction_list = Commerzbank().from_pdf(full_path)
+        assert transaction_list, "No transactions found in PDF file"
 
         # Check Reader Ergebnisse
         check_transaktion_list(transaction_list)

tests/test_unit_reader_Generic.py

@@ -36,3 +36,29 @@ def test_read_from_pdf():
 def test_read_from_http():
     """Testet das Einlesen Kontoumsätzen aus einer Online-Quelle"""
     return None
+
+def test_strftime_parser(test_app):
+    """Testet den strftime Parser des Generic Readers"""
+    with test_app.app_context():
+        reader = Generic()
+
+        # Teste verschiedene Datumsformate
+        date_formats = [
+            ("%d.%m.%Y", "25.12.2023", 1703462400.0),
+            ("%Y-%m-%d", "2023-12-25", 1703462400.0),
+            ("%m/%d/%Y", "12/25/2023", 1703462400.0),
+        ]
+
+        for fmt, date_str, expected_timestamp in date_formats:
+            ts = reader._parse_from_strftime(date_str, fmt) # pylint: disable=protected-access
+            assert ts == expected_timestamp, f"Failed for format {fmt}"
+
+        # Teste automatische Korrektur (31.11. / 30.02. etc.)
+        date_formats = [
+            ("%d.%m.%Y", "31.11.2023", 1701302400.0),  # Korrigiert zu 30.11.2023
+            ("%d.%m.%Y", "30.02.2024", 1709164800.0),  # Korrigiert zu 28.02.2024
+        ]
+
+        for fmt, date_str, expected_timestamp in date_formats:
+            ts = reader._parse_from_strftime(date_str, fmt) # pylint: disable=protected-access
+            assert ts == expected_timestamp, f"Failed for format {fmt}"

tests/test_unit_reader_Volksbank-Mittelhessen.py

@@ -28,7 +28,7 @@ def test_read_from_csv(test_app):
 
 
 # Look for test files and create a tuple list
-test_folder = os.path.join('/tmp', 'volksbank-mittelhessen')
+test_folder = os.path.join('/tmp', 'Volksbank_Mittelhessen')
 test_files = []
 if not os.path.isdir(test_folder):
     test_files = [()]
@@ -48,6 +48,7 @@ def test_read_from_pdf(test_app, full_path):
 
     with test_app.app_context():
         transaction_list = Volksbank_Mittelhessen().from_pdf(full_path)
+        assert transaction_list, "No transactions found in PDF file"
 
         # Check Reader Ergebnisse
         check_transaktion_list(transaction_list)