first budget template parser

superx_budget/__init__.py

@@ -4,3 +4,7 @@ Creating a budget overview from a SuperX export
 """
 
 __version__ = "0.0.1"
+
+
+from .superx import parse_export_data  # noqa: F401
+from .exceptions import BudgetParserError, SuperXParserError  # noqa: F401

superx_budget/budget.py

@@ -0,0 +1,59 @@
+""" Budget Parser """
+
+from collections import namedtuple
+
+from .exceptions import BudgetParserError
+
+EXPECTED_TABLE_HEADERS = [
+    "Nr.",
+    "Projekt",
+    "Laufzeit",
+    "BA",
+    "Budget",
+    "Ausgaben",
+    "Rest",
+]
+
+BudgetData = namedtuple(
+    "BudgetData",
+    [
+        "row",
+        "number",
+        "project_name",
+        "period",
+        "project",
+        "budget",
+        "expenses",
+        "rest",
+    ],
+)
+
+
+def _check_table_header(row):
+    fields = [c.strip() for c in row[:7]]
+    print(fields)
+    print(EXPECTED_TABLE_HEADERS)
+    if fields != EXPECTED_TABLE_HEADERS:
+        raise BudgetParserError(f"unexpected headers: '{row}'")
+
+
+def _skip_empty_lines(rows, start=0):
+    for i, row in enumerate(rows, start=start):
+        first_cell = row[0]
+        if first_cell is None:
+            continue
+        if isinstance(first_cell, str) and first_cell.strip() == "":
+            continue
+        yield i, row
+
+
+def _parse_data_table(rows, start=2):
+    for i, data in _skip_empty_lines(rows, start):
+        yield BudgetData(i, *data[:7])
+
+
+def parse_budget_data(xls_sheet):
+    """ parses the budget data """
+    rows = xls_sheet.values
+    _check_table_header(next(rows))
+    return list(_parse_data_table(rows, start=2))

superx_budget/exceptions.py

@@ -0,0 +1,13 @@
+""" Exceptions used in the Project """
+
+
+class SuperXBudgetError(ValueError):
+    """ Base class for project errors """
+
+
+class SuperXParserError(SuperXBudgetError):
+    pass
+
+
+class BudgetParserError(SuperXBudgetError):
+    pass

superx_budget/superx.py

@@ -3,6 +3,8 @@
 from datetime import datetime
 from collections import namedtuple
 
+from .exceptions import SuperXParserError
+
 EXPECTED_HEADLINE = "Verwendungsnachweis und Kassenstand SAP"
 EXPECTED_METADATA_KEYS = {"Haushaltsjahr", "Stand", "Gruppierung"}
 EXPECTED_EXPORT_GROUPING = "automatisch"
@@ -29,15 +31,11 @@ SuperXData = namedtuple(
 )
 
 
-class SuperXError(ValueError):
-    pass
-
-
 def _check_export_headline(row):
     """ checks the first line of the excel data if it's what we'd expect """
     headline = row[0]
     if headline != EXPECTED_HEADLINE:
-        raise SuperXError(f"unexpected headline: '{headline}'")
+        raise SuperXParserError(f"unexpected headline: '{headline}'")
 
 
 def _get_export_metadata(row):
@@ -47,9 +45,11 @@ def _get_export_metadata(row):
     parts = [entry.split(":", 1) for entry in entries]
     metadata = {key.strip(): value.strip() for key, value in parts}
     if EXPECTED_METADATA_KEYS - set(metadata.keys()):
-        raise SuperXError(f"unexpected metadata: '{data}'")
+        raise SuperXParserError(f"unexpected metadata: '{data}'")
     if metadata["Gruppierung"] != EXPECTED_EXPORT_GROUPING:
-        raise SuperXError(f"unexpected grouping: {metadata['Gruppierung']}")
+        raise SuperXParserError(
+            f"unexpected grouping: {metadata['Gruppierung']}"
+        )
     return SuperXResult(
         metadata["Haushaltsjahr"],
         datetime.strptime(metadata["Stand"], "%d.%m.%Y"),
@@ -64,7 +64,7 @@ def _skip_export_data_until_table_header(rows):
         if first_cell == EXPECTED_DATA_TABLE_HEADER:
             break
     else:
-        raise SuperXError("could not find table header")
+        raise SuperXParserError("could not find table header")
 
 
 def _parse_data_table(rows):

tests/conftest.py

@@ -15,7 +15,6 @@ class MockWorkbookSheet:
 
 
 @pytest.fixture
-def example_file(request):
+def example_root(request):
     root_dir = Path(request.config.rootdir)
-    data_dir = root_dir / "test data"
-    return data_dir / "Verwendungsnachweis_und_Kassenstand_SAP_Zahlen.xlsx"
+    yield root_dir / "test data"

tests/test_budget_parser.py

@@ -0,0 +1,77 @@
+import pytest
+
+
+@pytest.fixture
+def example_file(example_root):
+    return example_root / "Verbrauchsmittel-Toto-2020.xlsx"
+
+
+@pytest.fixture
+def example_workbook(example_file):
+    import openpyxl
+
+    yield openpyxl.open(example_file)
+
+
+@pytest.fixture
+def example_sheet(example_workbook):
+    sheets = example_workbook.sheetnames
+    first = sheets[0]
+    yield example_workbook[first]
+
+
+def test_check_table_header_raises_error():
+    from superx_budget.budget import _check_table_header
+    from superx_budget.exceptions import BudgetParserError
+
+    row = ["not", "the", "expected", "row"]
+
+    with pytest.raises(BudgetParserError):
+        _check_table_header(row)
+
+
+def test_skip_empty_lines():
+    from superx_budget.budget import _skip_empty_lines
+
+    rows = [[""], ["one"], [None], [""], ["two"], [""]]
+
+    result = _skip_empty_lines(rows)
+
+    assert list(result) == [(1, ["one"]), (4, ["two"])]
+
+
+def test_parse_data_table():
+    from superx_budget.budget import _parse_data_table
+
+    rows = [
+        list("ABCDEFG"),
+        [None for i in range(7)],
+        list("tuvwxyzX"),  # one item more
+    ]
+
+    result = _parse_data_table(rows)
+    first, last = list(result)
+
+    assert first.row == 2
+    assert first.number == "A"
+    assert first.rest == "G"
+    assert last.row == 4
+    assert last.number == "t"
+    assert last.rest == "z"
+
+
+def test_parse_budget_data(example_sheet):
+    from superx_budget.budget import parse_budget_data
+
+    result = parse_budget_data(example_sheet)
+    first, last = result[0], result[-1]
+
+    assert len(result) == 18
+    assert first.row == 3
+    assert first.number == 1
+    assert first.project_name == "Safegurard I (neu)"
+    assert first.rest == "=E3-F3"
+    assert last.row == 54
+    assert last.number == "=A51+1"
+    assert last.project_name == "ZIM Microcoat II"
+    assert last.rest == "=E54-F54"

tests/test_superx_parser.py

@@ -4,19 +4,25 @@
 import pytest
 
 
+@pytest.fixture
+def example_file(example_root):
+    return example_root / "Verwendungsnachweis_und_Kassenstand_SAP_Zahlen.xlsx"
+
+
 @pytest.fixture
 def example_workbook(example_file):
     import openpyxl
 
-    return openpyxl.open(example_file)
+    yield openpyxl.open(example_file)
 
 
 def test_check_export_headline():
-    from superx_budget.superx import _check_export_headline, SuperXError
+    from superx_budget.superx import _check_export_headline
+    from superx_budget.exceptions import SuperXParserError
 
     row = ["nomatching header"]
 
-    with pytest.raises(SuperXError):
+    with pytest.raises(SuperXParserError):
         _check_export_headline(row)
 
 
@@ -48,7 +54,9 @@ def test_get_export_metadata_raises_error(faulty_data):
 
     row = [faulty_data]
 
-    with pytest.raises(ValueError):  # SuperXError is a subclass of ValueError
+    with pytest.raises(
+        ValueError
+    ):  # SuperXParserError is a subclass of ValueError
         _get_export_metadata(row)
 
 
@@ -69,10 +77,8 @@ def test_skip_export_data_until_table_header_ok():
 
 
 def test_skip_export_data_until_table_header_raises_error():
-    from superx_budget.superx import (
-        _skip_export_data_until_table_header,
-        SuperXError,
-    )
+    from superx_budget.superx import _skip_export_data_until_table_header
+    from superx_budget.exceptions import SuperXParserError
 
     rows = [
         [""],
@@ -81,7 +87,7 @@ def test_skip_export_data_until_table_header_raises_error():
         ["Daten"],
     ]
     iterator = iter(rows)
-    with pytest.raises(SuperXError):
+    with pytest.raises(SuperXParserError):
         _skip_export_data_until_table_header(iterator)