test: add us-cpa module coverage and citations

skills/us-cpa/tests/test_document_extractors.py

@@ -0,0 +1,66 @@
+from __future__ import annotations
+
+import tempfile
+import unittest
+from pathlib import Path
+
+from us_cpa.document_extractors import extract_document_facts
+
+
+class DocumentExtractorTests(unittest.TestCase):
+    def test_extracts_common_w2_fields(self) -> None:
+        with tempfile.TemporaryDirectory() as temp_dir:
+            path = Path(temp_dir) / "w2.txt"
+            path.write_text(
+                "Form W-2 Wage and Tax Statement\n"
+                "Employee: Jane Doe\n"
+                "Box 1 Wages, tips, other compensation 50000\n"
+                "Box 2 Federal income tax withheld 6000\n"
+                "Box 16 State wages, tips, etc. 50000\n"
+                "Box 17 State income tax 1200\n"
+                "Box 3 Social security wages 50000\n"
+                "Box 5 Medicare wages and tips 50000\n"
+            )
+
+            extracted = extract_document_facts(path)
+
+            self.assertEqual(extracted["taxpayer.fullName"], "Jane Doe")
+            self.assertEqual(extracted["wages"], 50000.0)
+            self.assertEqual(extracted["federalWithholding"], 6000.0)
+            self.assertEqual(extracted["stateWages"], 50000.0)
+            self.assertEqual(extracted["stateWithholding"], 1200.0)
+            self.assertEqual(extracted["socialSecurityWages"], 50000.0)
+            self.assertEqual(extracted["medicareWages"], 50000.0)
+
+    def test_extracts_common_1099_patterns(self) -> None:
+        with tempfile.TemporaryDirectory() as temp_dir:
+            div_path = Path(temp_dir) / "1099-div.txt"
+            div_path.write_text("Form 1099-DIV\nRecipient: Jane Doe\nBox 1a Total ordinary dividends 250\n")
+            ret_path = Path(temp_dir) / "1099-r.txt"
+            ret_path.write_text("Form 1099-R\nRecipient: Jane Doe\nBox 1 Gross distribution 10000\n")
+            misc_path = Path(temp_dir) / "1099-misc.txt"
+            misc_path.write_text("Form 1099-MISC\nRecipient: Jane Doe\nBox 3 Other income 900\n")
+
+            self.assertEqual(extract_document_facts(div_path)["ordinaryDividends"], 250.0)
+            self.assertEqual(extract_document_facts(ret_path)["retirementDistribution"], 10000.0)
+            self.assertEqual(extract_document_facts(misc_path)["otherIncome"], 900.0)
+
+    def test_extracts_prior_year_return_summary_values(self) -> None:
+        with tempfile.TemporaryDirectory() as temp_dir:
+            path = Path(temp_dir) / "prior-return.txt"
+            path.write_text(
+                "2024 Form 1040 Summary\n"
+                "Adjusted gross income 72100\n"
+                "Taxable income 49800\n"
+                "Refund 2100\n"
+            )
+
+            extracted = extract_document_facts(path)
+
+            self.assertEqual(extracted["priorYear.adjustedGrossIncome"], 72100.0)
+            self.assertEqual(extracted["priorYear.taxableIncome"], 49800.0)
+            self.assertEqual(extracted["priorYear.refund"], 2100.0)
+
+
+if __name__ == "__main__":
+    unittest.main()