Spaces:
Sleeping
Sleeping
| import os | |
| import shutil | |
| import sys | |
| import tempfile | |
| import zipfile | |
| from pathlib import Path | |
| sys.path.insert(0, os.path.join(os.path.dirname(__file__), "..")) | |
| from docx_comments import apply_docx_comments | |
| from models import ReviewFinding | |
| def _finding( | |
| *, | |
| finding_id: str = "test_finding_1", | |
| paragraph_id: str = "P_0008", | |
| target_text: str = "", | |
| anchor_mode: str = "paragraph", | |
| ) -> ReviewFinding: | |
| return ReviewFinding( | |
| id=finding_id, | |
| risk_level="high", | |
| clause_type="Indemnification", | |
| issue="Test issue", | |
| comment="This is a test comment from the Mike system.", | |
| review_reasoning={"clause_section": "test", "violated_standard": "test", "zamil_exposure": "Manual test run"}, | |
| target_text=target_text, | |
| anchor_mode=anchor_mode, | |
| start_paragraph_id=paragraph_id, | |
| end_paragraph_id=paragraph_id, | |
| start_anchor=target_text[:220], | |
| end_anchor=target_text[-220:] if target_text else "", | |
| before_anchor="", | |
| after_anchor="", | |
| confidence=1.0, | |
| ) | |
| def _write_minimal_table_docx(path: Path) -> None: | |
| path.parent.mkdir(parents=True, exist_ok=True) | |
| with zipfile.ZipFile(path, "w") as zf: | |
| zf.writestr( | |
| "[Content_Types].xml", | |
| """<?xml version="1.0" encoding="UTF-8" standalone="yes"?> | |
| <Types xmlns="http://schemas.openxmlformats.org/package/2006/content-types"> | |
| <Default Extension="rels" ContentType="application/vnd.openxmlformats-package.relationships+xml"/> | |
| <Default Extension="xml" ContentType="application/xml"/> | |
| <Override PartName="/word/document.xml" ContentType="application/vnd.openxmlformats-officedocument.wordprocessingml.document.main+xml"/> | |
| </Types>""", | |
| ) | |
| zf.writestr( | |
| "_rels/.rels", | |
| """<?xml version="1.0" encoding="UTF-8" standalone="yes"?> | |
| <Relationships xmlns="http://schemas.openxmlformats.org/package/2006/relationships"> | |
| <Relationship Id="rId1" Type="http://schemas.openxmlformats.org/officeDocument/2006/relationships/officeDocument" Target="word/document.xml"/> | |
| </Relationships>""", | |
| ) | |
| zf.writestr( | |
| "word/document.xml", | |
| """<?xml version="1.0" encoding="UTF-8" standalone="yes"?><w:document xmlns:w="http://schemas.openxmlformats.org/wordprocessingml/2006/main"><w:body><w:p><w:r><w:t>Body paragraph.</w:t></w:r></w:p><w:tbl><w:tr><w:tc><w:p><w:r><w:t>Table cell clause.</w:t></w:r></w:p></w:tc></w:tr></w:tbl><w:sectPr/></w:body></w:document>""", | |
| ) | |
| def test_apply_paragraph_comment_without_target_text(): | |
| if shutil.which("dotnet") is None: | |
| import pytest | |
| pytest.skip("dotnet is required for the DOCX commenter integration test") | |
| root = Path(__file__).resolve().parents[1] | |
| sample_docx = root / "data" / "uploads" / "run_20260508_120049_e4b2552b55" / "test_contract.docx" | |
| output_docx = root / "data" / "artifacts" / "test_comments_output.docx" | |
| work_dir = root / "data" / "artifacts" / "test_comments_work" | |
| findings = [_finding(target_text="")] | |
| assert sample_docx.exists(), f"Missing test DOCX fixture: {sample_docx}" | |
| import tempfile | |
| with tempfile.TemporaryDirectory() as tmpdir: | |
| work_dir = Path(tmpdir) | |
| results = apply_docx_comments( | |
| input_docx=sample_docx, | |
| output_docx=output_docx, | |
| findings=findings, | |
| work_dir=work_dir, | |
| ) | |
| assert results | |
| assert results[0].id == "test_finding_1" | |
| assert results[0].status == "applied" | |
| assert results[0].failure_code == "editable" | |
| assert results[0].resolve_strategy == "paragraph_anchor" | |
| def test_apply_paragraph_comment_ignores_non_matching_quote_hint(): | |
| if shutil.which("dotnet") is None: | |
| import pytest | |
| pytest.skip("dotnet is required for the DOCX commenter integration test") | |
| root = Path(__file__).resolve().parents[1] | |
| sample_docx = root / "data" / "uploads" / "run_20260508_120049_e4b2552b55" / "test_contract.docx" | |
| output_docx = root / "data" / "artifacts" / "test_comments_output.docx" | |
| with tempfile.TemporaryDirectory() as tmpdir: | |
| results = apply_docx_comments( | |
| input_docx=sample_docx, | |
| output_docx=output_docx, | |
| findings=[_finding(target_text="this exact quote does not exist")], | |
| work_dir=Path(tmpdir), | |
| ) | |
| assert results[0].status == "applied" | |
| def test_apply_exact_comment_still_uses_target_text(): | |
| if shutil.which("dotnet") is None: | |
| import pytest | |
| pytest.skip("dotnet is required for the DOCX commenter integration test") | |
| root = Path(__file__).resolve().parents[1] | |
| sample_docx = root / "data" / "uploads" / "run_20260508_120049_e4b2552b55" / "test_contract.docx" | |
| output_docx = root / "data" / "artifacts" / "test_comments_output.docx" | |
| with tempfile.TemporaryDirectory() as tmpdir: | |
| results = apply_docx_comments( | |
| input_docx=sample_docx, | |
| output_docx=output_docx, | |
| findings=[_finding(paragraph_id="P_0007", target_text="Article 3: Indemnification", anchor_mode="exact")], | |
| work_dir=Path(tmpdir), | |
| ) | |
| assert results[0].status == "applied" | |
| assert results[0].resolve_strategy == "exact" | |
| def test_apply_paragraph_comment_invalid_block_id(): | |
| if shutil.which("dotnet") is None: | |
| import pytest | |
| pytest.skip("dotnet is required for the DOCX commenter integration test") | |
| root = Path(__file__).resolve().parents[1] | |
| sample_docx = root / "data" / "uploads" / "run_20260508_120049_e4b2552b55" / "test_contract.docx" | |
| output_docx = root / "data" / "artifacts" / "test_comments_output.docx" | |
| with tempfile.TemporaryDirectory() as tmpdir: | |
| results = apply_docx_comments( | |
| input_docx=sample_docx, | |
| output_docx=output_docx, | |
| findings=[_finding(paragraph_id="P_9999")], | |
| work_dir=Path(tmpdir), | |
| ) | |
| assert results[0].status == "not_applied" | |
| assert results[0].failure_code == "paragraph_not_found" | |
| def test_apply_paragraph_comment_hash_mismatch_reports_expected_and_actual(): | |
| if shutil.which("dotnet") is None: | |
| import pytest | |
| pytest.skip("dotnet is required for the DOCX commenter integration test") | |
| root = Path(__file__).resolve().parents[1] | |
| sample_docx = root / "data" / "uploads" / "run_20260508_120049_e4b2552b55" / "test_contract.docx" | |
| output_docx = root / "data" / "artifacts" / "test_comments_output.docx" | |
| finding = _finding().model_copy(update={"text_hash": "definitely_wrong"}) | |
| with tempfile.TemporaryDirectory() as tmpdir: | |
| results = apply_docx_comments( | |
| input_docx=sample_docx, | |
| output_docx=output_docx, | |
| findings=[finding], | |
| work_dir=Path(tmpdir), | |
| ) | |
| assert results[0].status == "not_applied" | |
| assert results[0].failure_code == "anchor_stale" | |
| assert results[0].expected_text_hash == "definitely_wrong" | |
| assert results[0].actual_text_hash | |
| assert results[0].actual_text_hash != results[0].expected_text_hash | |
| def test_apply_paragraph_comment_inside_table_cell(): | |
| if shutil.which("dotnet") is None: | |
| import pytest | |
| pytest.skip("dotnet is required for the DOCX commenter integration test") | |
| with tempfile.TemporaryDirectory() as tmpdir: | |
| tmp = Path(tmpdir) | |
| input_docx = tmp / "table.docx" | |
| output_docx = tmp / "table_commented.docx" | |
| _write_minimal_table_docx(input_docx) | |
| results = apply_docx_comments( | |
| input_docx=input_docx, | |
| output_docx=output_docx, | |
| findings=[_finding(paragraph_id="P_0002")], | |
| work_dir=tmp / "work", | |
| ) | |
| assert results[0].status == "applied" | |
| assert results[0].paragraph_id == "P_0002" | |
| if __name__ == "__main__": | |
| test_apply_paragraph_comment_without_target_text() | |