Release govoplan-connectors v0.1.26: bound spreadsheet traversal

tests/test_xlsx_safety_bounds.py

@@ -0,0 +1,70 @@
+from __future__ import annotations
+
+import re
+import unittest
+from io import BytesIO
+from unittest.mock import patch
+from zipfile import ZipFile
+
+from openpyxl import Workbook
+
+from govoplan_core.core.tabular_sources import TabularSourceValidationError
+from govoplan_connectors.backend import tabular_adapters as adapters
+
+
+def workbook_bytes(*, dimension: str | None = None, last_cell: str = "A2") -> bytes:
+    workbook = Workbook()
+    workbook.active.append(["name"])
+    workbook.active.append(["Ada"])
+    output = BytesIO()
+    workbook.save(output)
+    workbook.close()
+    result = BytesIO()
+    with ZipFile(BytesIO(output.getvalue())) as original, ZipFile(result, "w") as modified:
+        for entry in original.infolist():
+            content = original.read(entry)
+            if entry.filename == "xl/worksheets/sheet1.xml":
+                xml = content.decode()
+                if dimension is not None:
+                    xml = re.sub(r'<dimension ref="[^"]+"\s*/>', f'<dimension ref="{dimension}"/>', xml)
+                xml = xml.replace('r="A2"', f'r="{last_cell}"')
+                xml = xml.replace('<row r="2">', f'<row r="{re.search(r"[0-9]+$", last_cell).group()}">')
+                content = xml.encode()
+            modified.writestr(entry, content)
+    return result.getvalue()
+
+
+def parse(payload: bytes):
+    return adapters.parse_managed_tabular_content(payload, filename="fixture.xlsx", content_type=None, delimiter=",", sheet_name=None)
+
+
+class XlsxSafetyBoundsTests(unittest.TestCase):
+    def test_sparse_rows_cannot_bypass_limit_by_not_counting_as_data(self):
+        with patch.object(adapters, "MAX_FILE_ROWS", 3):
+            with self.assertRaisesRegex(TabularSourceValidationError, "row"):
+                parse(workbook_bytes(last_cell="A6"))
+
+    def test_forged_small_dimensions_cannot_hide_far_away_cells(self):
+        with patch.object(adapters, "MAX_FILE_ROWS", 3):
+            with self.assertRaisesRegex(TabularSourceValidationError, "row"):
+                parse(workbook_bytes(dimension="A1:A2", last_cell="A1000000"))
+
+    def test_forged_small_dimensions_cannot_hide_out_of_range_columns(self):
+        with self.assertRaisesRegex(TabularSourceValidationError, "column"):
+            parse(workbook_bytes(dimension="A1:A2", last_cell="XFD2"))
+
+    def test_declared_dimensions_do_not_expand_or_truncate_real_rows(self):
+        for dimension in ("A1:XFD1048576", "A1:A1"):
+            with self.subTest(dimension=dimension):
+                rows, sheet = parse(workbook_bytes(dimension=dimension))
+                self.assertEqual(({"name": "Ada"},), rows)
+                self.assertEqual("Sheet", sheet)
+
+    def test_small_blank_gaps_and_exact_limit_remain_usable(self):
+        with patch.object(adapters, "MAX_FILE_ROWS", 3):
+            rows, _sheet = parse(workbook_bytes(last_cell="A4"))
+            self.assertEqual(({"name": "Ada"},), rows)
+
+
+if __name__ == "__main__":
+    unittest.main()