Paragraph text
", + encoding="utf-8", + ) + + async def read(): + return await tool.execute( + action="read", + filename=str(html_file), + conversation_id="conv-1", + ) + + result = asyncio.run(read()) + assert result["success"] is True + # Content should contain the text — either stripped (bs4) or raw (fallback) + assert "Heading" in result["content"] + assert "Paragraph text" in result["content"] + # If bs4 is available, tags should be stripped; otherwise raw HTML is returned + try: + import bs4 # noqa: F401 + + bs4_available = True + except ImportError: + bs4_available = False + + if bs4_available: + assert "" not in result["content"]
+
+ def test_read_empty_file(self, tool: DocumentTool, tmp_path: Path) -> None:
+ """Read an empty file → returns empty content."""
+ empty_file = tmp_path / "empty.txt"
+ empty_file.write_text("", encoding="utf-8")
+
+ async def read():
+ return await tool.execute(
+ action="read",
+ filename=str(empty_file),
+ conversation_id="conv-1",
+ )
+
+ result = asyncio.run(read())
+ assert result["success"] is True
+ assert result["content"] == ""
+
+ def test_read_binary_file_as_text(self, tool: DocumentTool, tmp_path: Path) -> None:
+ """Read a binary file with .txt extension → doesn't crash, returns something."""
+ binary_file = tmp_path / "binary.txt"
+ binary_file.write_bytes(b"\x00\x01\x02\xff\xfe")
+
+ async def read():
+ return await tool.execute(
+ action="read",
+ filename=str(binary_file),
+ conversation_id="conv-1",
+ )
+
+ result = asyncio.run(read())
+ # Should not crash — text parser uses errors="replace"
+ assert result["success"] is True
+
+
+# ---------------------------------------------------------------------------
+# Database edge cases
+# ---------------------------------------------------------------------------
+
+
+class TestDatabaseEdgeCases:
+ """Edge cases for document metadata database."""
+
+ async def test_insert_and_retrieve_roundtrip(self, service: DocumentService) -> None:
+ """Insert a document and retrieve it — all fields preserved."""
+ meta = await service.create_document(
+ format="word",
+ content="# Roundtrip Test",
+ conversation_id="conv-roundtrip",
+ filename="roundtrip.docx",
+ )
+
+ retrieved = await service.get_document(meta.id)
+ assert retrieved is not None
+ assert retrieved.id == meta.id
+ assert retrieved.filename == meta.filename
+ assert retrieved.format == meta.format
+ assert retrieved.size == meta.size
+ assert retrieved.conversation_id == meta.conversation_id
+ assert retrieved.stored_name == meta.stored_name
+
+ async def test_get_nonexistent_document(self, service: DocumentService) -> None:
+ """get_document with non-existent ID returns None."""
+ result = await service.get_document("nonexistent-id")
+ assert result is None
+
+ async def test_delete_document_removes_metadata(self, service: DocumentService) -> None:
+ """After delete, get_document returns None."""
+ meta = await service.create_document(
+ format="word",
+ content="# Delete Me",
+ conversation_id="conv-delete",
+ )
+
+ deleted = await delete_document(meta.id, service.db_path)
+ assert deleted is True
+
+ # Metadata should be gone
+ result = await service.get_document(meta.id)
+ assert result is None
+
+ # Second delete returns False
+ deleted_again = await delete_document(meta.id, service.db_path)
+ assert deleted_again is False
diff --git a/tests/documents/test_excel_renderer.py b/tests/documents/test_excel_renderer.py
new file mode 100644
index 0000000..0988ec6
--- /dev/null
+++ b/tests/documents/test_excel_renderer.py
@@ -0,0 +1,124 @@
+"""Tests for ExcelRenderer — Markdown/JSON → .xlsx mapping (U3)."""
+
+from __future__ import annotations
+
+import json
+from pathlib import Path
+
+from openpyxl import load_workbook
+
+from agentkit.documents.renderers.excel_renderer import ExcelRenderer
+
+
+def _render(content: str, tmp_path: Path) -> Path:
+ out = tmp_path / "test.xlsx"
+ ExcelRenderer().render(content, out)
+ return out
+
+
+def _read_workbook(path: Path) -> dict[str, list[list[str]]]:
+ """Return {sheet_name: [[row cells], ...]} from a .xlsx file."""
+ wb = load_workbook(str(path))
+ result: dict[str, list[list[str]]] = {}
+ for ws in wb.worksheets:
+ rows: list[list[str]] = []
+ for row in ws.iter_rows(values_only=True):
+ rows.append([str(c) if c is not None else "" for c in row])
+ result[ws.title] = rows
+ return result
+
+
+def test_markdown_single_table(tmp_path: Path) -> None:
+ """A single GFM table becomes a Table1 sheet with correct data."""
+ md = "| Name | Age |\n| --- | --- |\n| Alice | 30 |\n| Bob | 25 |\n"
+ path = _render(md, tmp_path)
+ sheets = _read_workbook(path)
+ assert "Table1" in sheets
+ rows = sheets["Table1"]
+ assert rows[0] == ["Name", "Age"]
+ assert rows[1] == ["Alice", "30"]
+ assert rows[2] == ["Bob", "25"]
+
+
+def test_markdown_multiple_tables(tmp_path: Path) -> None:
+ """Multiple GFM tables become separate sheets (Table1, Table2)."""
+ md = (
+ "| A | B |\n| --- | --- |\n| 1 | 2 |\n\n"
+ "Some text between.\n\n"
+ "| C | D |\n| --- | --- |\n| 3 | 4 |\n"
+ )
+ path = _render(md, tmp_path)
+ sheets = _read_workbook(path)
+ assert "Table1" in sheets
+ assert "Table2" in sheets
+ assert sheets["Table1"][0] == ["A", "B"]
+ assert sheets["Table2"][0] == ["C", "D"]
+
+
+def test_markdown_no_table_creates_summary(tmp_path: Path) -> None:
+ """Markdown without tables puts text lines in a Summary sheet."""
+ md = "Just some text.\nAnother line.\n"
+ path = _render(md, tmp_path)
+ sheets = _read_workbook(path)
+ # At least one sheet exists with the text
+ all_text = []
+ for rows in sheets.values():
+ all_text.extend(cell for row in rows for cell in row)
+ assert "Just some text." in all_text
+ assert "Another line." in all_text
+
+
+def test_json_input_multi_sheet(tmp_path: Path) -> None:
+ """JSON input {sheet: rows} creates named sheets."""
+ data = {
+ "Sales": [["Product", "Revenue"], ["Widget", "1000"], ["Gadget", "2000"]],
+ "Costs": [["Item", "Amount"], ["Rent", "500"]],
+ }
+ path = _render(json.dumps(data), tmp_path)
+ sheets = _read_workbook(path)
+ assert "Sales" in sheets
+ assert "Costs" in sheets
+ assert sheets["Sales"][0] == ["Product", "Revenue"]
+ assert sheets["Sales"][1] == ["Widget", "1000"]
+ assert sheets["Costs"][1] == ["Rent", "500"]
+
+
+def test_json_input_single_sheet(tmp_path: Path) -> None:
+ """JSON with one sheet creates exactly that sheet."""
+ data = {"Data": [["X", "Y"], ["1", "2"]]}
+ path = _render(json.dumps(data), tmp_path)
+ sheets = _read_workbook(path)
+ assert "Data" in sheets
+ assert sheets["Data"][0] == ["X", "Y"]
+
+
+def test_empty_markdown(tmp_path: Path) -> None:
+ """Empty input produces a valid workbook with at least one sheet."""
+ path = _render("", tmp_path)
+ assert path.exists()
+ wb = load_workbook(str(path))
+ assert len(wb.sheetnames) >= 1
+
+
+def test_mixed_table_and_text(tmp_path: Path) -> None:
+ """Text before/after a table goes to Summary, table goes to Table1."""
+ md = "Intro line.\n\n| Col1 | Col2 |\n| --- | --- |\n| a | b |\n\nOutro line.\n"
+ path = _render(md, tmp_path)
+ sheets = _read_workbook(path)
+ assert "Table1" in sheets
+ # Summary should contain intro and outro
+ if "Summary" in sheets:
+ summary_cells = [cell for row in sheets["Summary"] for cell in row]
+ assert "Intro line." in summary_cells
+ assert "Outro line." in summary_cells
+
+
+def test_long_sheet_name_truncated(tmp_path: Path) -> None:
+ """Sheet names longer than 31 chars are truncated (Excel limit)."""
+ long_name = "A" * 50
+ data = {long_name: [["x"]]}
+ path = _render(json.dumps(data), tmp_path)
+ wb = load_workbook(str(path))
+ # The sheet name should be at most 31 chars
+ for name in wb.sheetnames:
+ assert len(name) <= 31
diff --git a/tests/documents/test_pdf_renderer.py b/tests/documents/test_pdf_renderer.py
new file mode 100644
index 0000000..0576454
--- /dev/null
+++ b/tests/documents/test_pdf_renderer.py
@@ -0,0 +1,99 @@
+"""Tests for PDFRenderer — Markdown → PDF mapping (U4)."""
+
+from __future__ import annotations
+
+from pathlib import Path
+
+from agentkit.documents.renderers.pdf_renderer import PDFRenderer
+
+
+def _render(markdown: str, tmp_path: Path) -> Path:
+ out = tmp_path / "test.pdf"
+ PDFRenderer().render(markdown, out)
+ return out
+
+
+def test_basic_pdf_generation(tmp_path: Path) -> None:
+ """Markdown with heading + paragraph produces a valid PDF."""
+ md = "# Title\n\nThis is a paragraph.\n"
+ path = _render(md, tmp_path)
+ assert path.exists()
+ assert path.stat().st_size > 0
+ # PDF magic bytes
+ assert path.read_bytes()[:4] == b"%PDF"
+
+
+def test_empty_markdown(tmp_path: Path) -> None:
+ """Empty Markdown produces a valid (minimal) PDF."""
+ path = _render("", tmp_path)
+ assert path.exists()
+ assert path.read_bytes()[:4] == b"%PDF"
+
+
+def test_headings(tmp_path: Path) -> None:
+ """Multiple heading levels render without error."""
+ md = "# H1\n## H2\n### H3\n"
+ path = _render(md, tmp_path)
+ assert path.read_bytes()[:4] == b"%PDF"
+
+
+def test_bullet_list(tmp_path: Path) -> None:
+ """Bullet list renders without error."""
+ md = "- Apple\n- Banana\n- Cherry\n"
+ path = _render(md, tmp_path)
+ assert path.read_bytes()[:4] == b"%PDF"
+
+
+def test_numbered_list(tmp_path: Path) -> None:
+ """Numbered list renders without error."""
+ md = "1. First\n2. Second\n3. Third\n"
+ path = _render(md, tmp_path)
+ assert path.read_bytes()[:4] == b"%PDF"
+
+
+def test_table(tmp_path: Path) -> None:
+ """GFM table renders without error."""
+ md = "| Name | Age |\n| --- | --- |\n| Alice | 30 |\n| Bob | 25 |\n"
+ path = _render(md, tmp_path)
+ assert path.read_bytes()[:4] == b"%PDF"
+
+
+def test_bold_italic(tmp_path: Path) -> None:
+ """Bold and italic inline formatting render without error."""
+ md = "This has **bold** and *italic* text.\n"
+ path = _render(md, tmp_path)
+ assert path.read_bytes()[:4] == b"%PDF"
+
+
+def test_chinese_text(tmp_path: Path) -> None:
+ """Chinese characters produce a valid PDF (font fallback is OK)."""
+ md = "# 中文标题\n\n这是中文段落内容。\n"
+ path = _render(md, tmp_path)
+ assert path.read_bytes()[:4] == b"%PDF"
+ assert path.stat().st_size > 0
+
+
+def test_mixed_content(tmp_path: Path) -> None:
+ """Heading + paragraph + list + table renders without error."""
+ md = """# Report
+
+Intro paragraph.
+
+- Item one
+- Item two
+
+| Col A | Col B |
+| ----- | ----- |
+| 1 | 2 |
+
+Final paragraph.
+"""
+ path = _render(md, tmp_path)
+ assert path.read_bytes()[:4] == b"%PDF"
+
+
+def test_xml_special_chars(tmp_path: Path) -> None:
+ """XML special characters (<, >, &) are escaped and don't break rendering."""
+ md = "Use