feat(B2): add Microsoft Word (.docx) support
Implements ROADMAP task B2 — full .docx scraping support via mammoth + python-docx, producing SKILL.md + references/ output identical to other source types. New files: - src/skill_seekers/cli/word_scraper.py — WordToSkillConverter class + main() entry point (~600 lines); mammoth → BeautifulSoup pipeline; handles headings, code detection (incl. monospace <p><br> blocks), tables, images, metadata extraction - src/skill_seekers/cli/arguments/word.py — add_word_arguments() + WORD_ARGUMENTS dict - src/skill_seekers/cli/parsers/word_parser.py — WordParser for unified CLI parser registry - tests/test_word_scraper.py — comprehensive test suite (~300 lines) Modified files: - src/skill_seekers/cli/main.py — registered "word" command module - src/skill_seekers/cli/source_detector.py — .docx auto-detection + _detect_word() classmethod - src/skill_seekers/cli/create_command.py — _route_word() + --help-word - src/skill_seekers/cli/arguments/create.py — WORD_ARGUMENTS + routing - src/skill_seekers/cli/arguments/__init__.py — export word args - src/skill_seekers/cli/parsers/__init__.py — register WordParser - src/skill_seekers/cli/unified_scraper.py — _scrape_word() integration - src/skill_seekers/cli/pdf_scraper.py — fix: real enhancement instead of stub; remove [:3] reference file limit; capture run_workflows return - src/skill_seekers/cli/github_scraper.py — fix: remove arbitrary open_issues[:20] / closed_issues[:10] reference file limits - pyproject.toml — skill-seekers-word entry point + docx optional dep - tests/test_cli_parsers.py — update parser count 21→22 Bug fixes applied during real-world testing: - Code detection: detect monospace <p><br> blocks as code (mammoth renders Courier paragraphs this way, not as <pre>/<code>) - Language detector: fix wrong method name detect_from_text → detect_from_code - Description inference: pass None from main() so extract_docx() can infer description from Word document subject/title metadata - Bullet-point guard: exclude prose starting with •/-/* from code scoring - Enhancement: implement real API/LOCAL enhancement (was stub) - pip install message: add quotes around skill-seekers[docx] Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
This commit is contained in:
yusyus
677
tests/test_word_scraper.py
Normal file
677
tests/test_word_scraper.py
Normal file
@@ -0,0 +1,677 @@
|
||||
#!/usr/bin/env python3
|
||||
"""
|
||||
Tests for Word Document Scraper (cli/word_scraper.py)
|
||||
|
||||
Tests cover:
|
||||
- Config-based initialization
|
||||
- Direct DOCX path conversion
|
||||
- JSON-based workflow
|
||||
- Skill structure generation
|
||||
- Categorization
|
||||
- Code blocks handling
|
||||
- Tables handling
|
||||
- Image handling
|
||||
- Error handling
|
||||
- CLI argument parsing
|
||||
"""
|
||||
|
||||
import json
|
||||
import shutil
|
||||
import tempfile
|
||||
import unittest
|
||||
from pathlib import Path
|
||||
|
||||
try:
|
||||
import mammoth # noqa: F401
|
||||
import docx as python_docx # noqa: F401
|
||||
|
||||
WORD_AVAILABLE = True
|
||||
except ImportError:
|
||||
WORD_AVAILABLE = False
|
||||
|
||||
|
||||
def _make_sample_extracted_data(num_sections=2, include_code=False, include_tables=False,
|
||||
include_images=False):
|
||||
"""Helper to build a minimal extracted_data dict for testing."""
|
||||
mock_image_bytes = (
|
||||
b"\x89PNG\r\n\x1a\n\x00\x00\x00\rIHDR\x00\x00\x00\x01\x00\x00\x00\x01"
|
||||
b"\x08\x06\x00\x00\x00\x1f\x15\xc4\x89\x00\x00\x00\nIDATx\x9cc\x00\x01"
|
||||
b"\x00\x00\x05\x00\x01\r\n-\xb4\x00\x00\x00\x00IEND\xaeB`\x82"
|
||||
)
|
||||
|
||||
pages = []
|
||||
for i in range(1, num_sections + 1):
|
||||
section = {
|
||||
"section_number": i,
|
||||
"heading": f"Section {i}",
|
||||
"heading_level": "h1",
|
||||
"text": f"Content for section {i}.",
|
||||
"headings": [],
|
||||
"code_samples": [],
|
||||
"tables": [],
|
||||
"images": [],
|
||||
}
|
||||
if include_code:
|
||||
section["code_samples"] = [
|
||||
{"code": f"def hello_{i}():\n return 'world'", "language": "python",
|
||||
"quality_score": 7.5}
|
||||
]
|
||||
if include_tables:
|
||||
section["tables"] = [
|
||||
{"headers": ["Col A", "Col B"], "rows": [["val1", "val2"], ["val3", "val4"]]}
|
||||
]
|
||||
if include_images:
|
||||
section["images"] = [
|
||||
{"index": 0, "data": mock_image_bytes, "width": 100, "height": 80}
|
||||
]
|
||||
pages.append(section)
|
||||
|
||||
return {
|
||||
"source_file": "test.docx",
|
||||
"metadata": {"title": "Test Doc", "author": "Test Author", "created": "", "modified": "",
|
||||
"subject": ""},
|
||||
"total_sections": num_sections,
|
||||
"total_code_blocks": num_sections if include_code else 0,
|
||||
"total_images": num_sections if include_images else 0,
|
||||
"languages_detected": {"python": num_sections} if include_code else {},
|
||||
"pages": pages,
|
||||
}
|
||||
|
||||
|
||||
class TestWordToSkillConverterInit(unittest.TestCase):
|
||||
"""Test WordToSkillConverter initialization and basic functionality."""
|
||||
|
||||
def setUp(self):
|
||||
if not WORD_AVAILABLE:
|
||||
self.skipTest("mammoth and python-docx not installed")
|
||||
from skill_seekers.cli.word_scraper import WordToSkillConverter
|
||||
self.WordToSkillConverter = WordToSkillConverter
|
||||
self.temp_dir = tempfile.mkdtemp()
|
||||
|
||||
def tearDown(self):
|
||||
if hasattr(self, "temp_dir"):
|
||||
shutil.rmtree(self.temp_dir, ignore_errors=True)
|
||||
|
||||
def test_init_with_name_and_docx_path(self):
|
||||
"""Test initialization with name and docx path."""
|
||||
config = {"name": "test_skill", "docx_path": "test.docx"}
|
||||
converter = self.WordToSkillConverter(config)
|
||||
self.assertEqual(converter.name, "test_skill")
|
||||
self.assertEqual(converter.docx_path, "test.docx")
|
||||
|
||||
def test_init_with_full_config(self):
|
||||
"""Test initialization with full config."""
|
||||
config = {
|
||||
"name": "my_skill",
|
||||
"docx_path": "docs/api.docx",
|
||||
"description": "API documentation skill",
|
||||
}
|
||||
converter = self.WordToSkillConverter(config)
|
||||
self.assertEqual(converter.name, "my_skill")
|
||||
self.assertEqual(converter.description, "API documentation skill")
|
||||
|
||||
def test_init_requires_name(self):
|
||||
"""Test that missing 'name' field raises an error."""
|
||||
with self.assertRaises((KeyError, TypeError)):
|
||||
self.WordToSkillConverter({})
|
||||
|
||||
def test_default_description_uses_name(self):
|
||||
"""Test that default description is generated from name."""
|
||||
config = {"name": "my_api", "docx_path": "api.docx"}
|
||||
converter = self.WordToSkillConverter(config)
|
||||
self.assertIn("my_api", converter.description)
|
||||
|
||||
def test_skill_dir_uses_name(self):
|
||||
"""Test that skill_dir is derived from name."""
|
||||
config = {"name": "my_skill", "docx_path": "test.docx"}
|
||||
converter = self.WordToSkillConverter(config)
|
||||
self.assertIn("my_skill", converter.skill_dir)
|
||||
|
||||
def test_name_auto_detected_from_filename(self):
|
||||
"""Test name can be extracted from filename via infer_description_from_word."""
|
||||
from skill_seekers.cli.word_scraper import infer_description_from_word
|
||||
desc = infer_description_from_word({}, name="my_doc")
|
||||
self.assertIn("my_doc", desc)
|
||||
|
||||
|
||||
class TestWordCategorization(unittest.TestCase):
|
||||
"""Test content categorization functionality."""
|
||||
|
||||
def setUp(self):
|
||||
if not WORD_AVAILABLE:
|
||||
self.skipTest("mammoth and python-docx not installed")
|
||||
from skill_seekers.cli.word_scraper import WordToSkillConverter
|
||||
self.WordToSkillConverter = WordToSkillConverter
|
||||
self.temp_dir = tempfile.mkdtemp()
|
||||
|
||||
def tearDown(self):
|
||||
shutil.rmtree(self.temp_dir, ignore_errors=True)
|
||||
|
||||
def test_single_docx_creates_single_category(self):
|
||||
"""With docx_path set, categorize_content creates a single category."""
|
||||
config = {"name": "test", "docx_path": "test.docx"}
|
||||
converter = self.WordToSkillConverter(config)
|
||||
converter.extracted_data = _make_sample_extracted_data(num_sections=3)
|
||||
|
||||
categories = converter.categorize_content()
|
||||
|
||||
self.assertEqual(len(categories), 1)
|
||||
# Category key is sanitized docx basename
|
||||
self.assertIn("test", categories)
|
||||
self.assertEqual(len(categories["test"]["pages"]), 3)
|
||||
|
||||
def test_keyword_based_categorization(self):
|
||||
"""Test keyword-based categorization without docx_path."""
|
||||
config = {
|
||||
"name": "test",
|
||||
"docx_path": "",
|
||||
"categories": {
|
||||
"api": ["api", "reference"],
|
||||
"guide": ["getting started", "tutorial"],
|
||||
},
|
||||
}
|
||||
converter = self.WordToSkillConverter(config)
|
||||
converter.docx_path = ""
|
||||
converter.extracted_data = {
|
||||
"pages": [
|
||||
{"section_number": 1, "heading": "API Reference", "text": "api reference docs",
|
||||
"code_samples": [], "tables": [], "images": []},
|
||||
{"section_number": 2, "heading": "Getting Started", "text": "getting started guide",
|
||||
"code_samples": [], "tables": [], "images": []},
|
||||
]
|
||||
}
|
||||
|
||||
categories = converter.categorize_content()
|
||||
self.assertIsInstance(categories, dict)
|
||||
self.assertGreater(len(categories), 0)
|
||||
|
||||
def test_fallback_to_content_category(self):
|
||||
"""Without docx_path and no categories config, uses 'content' category."""
|
||||
config = {"name": "test", "docx_path": ""}
|
||||
converter = self.WordToSkillConverter(config)
|
||||
converter.docx_path = ""
|
||||
converter.extracted_data = _make_sample_extracted_data(num_sections=1)
|
||||
|
||||
categories = converter.categorize_content()
|
||||
self.assertIsInstance(categories, dict)
|
||||
self.assertGreater(len(categories), 0)
|
||||
|
||||
|
||||
class TestWordSkillBuilding(unittest.TestCase):
|
||||
"""Test skill structure generation."""
|
||||
|
||||
def setUp(self):
|
||||
if not WORD_AVAILABLE:
|
||||
self.skipTest("mammoth and python-docx not installed")
|
||||
from skill_seekers.cli.word_scraper import WordToSkillConverter
|
||||
self.WordToSkillConverter = WordToSkillConverter
|
||||
self.temp_dir = tempfile.mkdtemp()
|
||||
|
||||
def tearDown(self):
|
||||
shutil.rmtree(self.temp_dir, ignore_errors=True)
|
||||
|
||||
def test_build_skill_creates_directory_structure(self):
|
||||
"""build_skill creates required directory structure."""
|
||||
config = {"name": "test_skill", "docx_path": "test.docx"}
|
||||
converter = self.WordToSkillConverter(config)
|
||||
converter.skill_dir = str(Path(self.temp_dir) / "test_skill")
|
||||
converter.extracted_data = _make_sample_extracted_data()
|
||||
|
||||
converter.build_skill()
|
||||
|
||||
skill_dir = Path(self.temp_dir) / "test_skill"
|
||||
self.assertTrue(skill_dir.exists())
|
||||
self.assertTrue((skill_dir / "references").exists())
|
||||
self.assertTrue((skill_dir / "scripts").exists())
|
||||
self.assertTrue((skill_dir / "assets").exists())
|
||||
|
||||
def test_build_skill_creates_skill_md(self):
|
||||
"""build_skill creates SKILL.md with correct content."""
|
||||
config = {
|
||||
"name": "test_skill",
|
||||
"docx_path": "test.docx",
|
||||
"description": "Test description for docs",
|
||||
}
|
||||
converter = self.WordToSkillConverter(config)
|
||||
converter.skill_dir = str(Path(self.temp_dir) / "test_skill")
|
||||
converter.extracted_data = _make_sample_extracted_data()
|
||||
|
||||
converter.build_skill()
|
||||
|
||||
skill_md = Path(self.temp_dir) / "test_skill" / "SKILL.md"
|
||||
self.assertTrue(skill_md.exists())
|
||||
|
||||
content = skill_md.read_text()
|
||||
self.assertIn("test_skill", content)
|
||||
self.assertIn("Test description for docs", content)
|
||||
|
||||
def test_build_skill_creates_reference_files(self):
|
||||
"""build_skill creates reference markdown files."""
|
||||
config = {"name": "test_skill", "docx_path": "test.docx"}
|
||||
converter = self.WordToSkillConverter(config)
|
||||
converter.skill_dir = str(Path(self.temp_dir) / "test_skill")
|
||||
converter.extracted_data = _make_sample_extracted_data(num_sections=2)
|
||||
|
||||
converter.build_skill()
|
||||
|
||||
refs_dir = Path(self.temp_dir) / "test_skill" / "references"
|
||||
# Single-source: named after docx basename
|
||||
self.assertTrue((refs_dir / "test.md").exists())
|
||||
self.assertTrue((refs_dir / "index.md").exists())
|
||||
|
||||
def test_skill_md_has_yaml_frontmatter(self):
|
||||
"""SKILL.md starts with valid YAML frontmatter."""
|
||||
config = {"name": "myskill", "docx_path": "doc.docx"}
|
||||
converter = self.WordToSkillConverter(config)
|
||||
converter.skill_dir = str(Path(self.temp_dir) / "myskill")
|
||||
converter.extracted_data = _make_sample_extracted_data()
|
||||
|
||||
converter.build_skill()
|
||||
|
||||
skill_md = Path(self.temp_dir) / "myskill" / "SKILL.md"
|
||||
content = skill_md.read_text()
|
||||
self.assertTrue(content.startswith("---\n"))
|
||||
self.assertIn("name:", content)
|
||||
self.assertIn("description:", content)
|
||||
|
||||
def test_skill_md_includes_section_overview(self):
|
||||
"""SKILL.md includes a Section Overview."""
|
||||
config = {"name": "test_skill", "docx_path": "test.docx"}
|
||||
converter = self.WordToSkillConverter(config)
|
||||
converter.skill_dir = str(Path(self.temp_dir) / "test_skill")
|
||||
converter.extracted_data = _make_sample_extracted_data(num_sections=3)
|
||||
|
||||
converter.build_skill()
|
||||
|
||||
skill_md = Path(self.temp_dir) / "test_skill" / "SKILL.md"
|
||||
content = skill_md.read_text()
|
||||
self.assertIn("Section Overview", content)
|
||||
self.assertIn("Total Sections", content)
|
||||
|
||||
|
||||
class TestWordCodeBlocks(unittest.TestCase):
|
||||
"""Test code block extraction and inclusion."""
|
||||
|
||||
def setUp(self):
|
||||
if not WORD_AVAILABLE:
|
||||
self.skipTest("mammoth and python-docx not installed")
|
||||
from skill_seekers.cli.word_scraper import WordToSkillConverter
|
||||
self.WordToSkillConverter = WordToSkillConverter
|
||||
self.temp_dir = tempfile.mkdtemp()
|
||||
|
||||
def tearDown(self):
|
||||
shutil.rmtree(self.temp_dir, ignore_errors=True)
|
||||
|
||||
def test_code_blocks_included_in_references(self):
|
||||
"""Code blocks are included in reference files."""
|
||||
config = {"name": "test_skill", "docx_path": "test.docx"}
|
||||
converter = self.WordToSkillConverter(config)
|
||||
converter.skill_dir = str(Path(self.temp_dir) / "test_skill")
|
||||
converter.extracted_data = _make_sample_extracted_data(include_code=True)
|
||||
|
||||
converter.build_skill()
|
||||
|
||||
ref_file = Path(self.temp_dir) / "test_skill" / "references" / "test.md"
|
||||
content = ref_file.read_text()
|
||||
self.assertIn("```python", content)
|
||||
self.assertIn("def hello_", content)
|
||||
|
||||
def test_code_examples_in_skill_md(self):
|
||||
"""SKILL.md includes code examples section when code is present."""
|
||||
config = {"name": "test_skill", "docx_path": "test.docx"}
|
||||
converter = self.WordToSkillConverter(config)
|
||||
converter.skill_dir = str(Path(self.temp_dir) / "test_skill")
|
||||
converter.extracted_data = _make_sample_extracted_data(include_code=True)
|
||||
|
||||
converter.build_skill()
|
||||
|
||||
skill_md = Path(self.temp_dir) / "test_skill" / "SKILL.md"
|
||||
content = skill_md.read_text()
|
||||
self.assertIn("Code Examples", content)
|
||||
|
||||
def test_language_detected_in_statistics(self):
|
||||
"""Language statistics are included in SKILL.md."""
|
||||
config = {"name": "test_skill", "docx_path": "test.docx"}
|
||||
converter = self.WordToSkillConverter(config)
|
||||
converter.skill_dir = str(Path(self.temp_dir) / "test_skill")
|
||||
converter.extracted_data = _make_sample_extracted_data(include_code=True)
|
||||
|
||||
converter.build_skill()
|
||||
|
||||
skill_md = Path(self.temp_dir) / "test_skill" / "SKILL.md"
|
||||
content = skill_md.read_text()
|
||||
self.assertIn("python", content)
|
||||
|
||||
|
||||
class TestWordTables(unittest.TestCase):
|
||||
"""Test table extraction and rendering."""
|
||||
|
||||
def setUp(self):
|
||||
if not WORD_AVAILABLE:
|
||||
self.skipTest("mammoth and python-docx not installed")
|
||||
from skill_seekers.cli.word_scraper import WordToSkillConverter
|
||||
self.WordToSkillConverter = WordToSkillConverter
|
||||
self.temp_dir = tempfile.mkdtemp()
|
||||
|
||||
def tearDown(self):
|
||||
shutil.rmtree(self.temp_dir, ignore_errors=True)
|
||||
|
||||
def test_tables_rendered_in_references(self):
|
||||
"""Tables are rendered as markdown tables in reference files."""
|
||||
config = {"name": "test_skill", "docx_path": "test.docx"}
|
||||
converter = self.WordToSkillConverter(config)
|
||||
converter.skill_dir = str(Path(self.temp_dir) / "test_skill")
|
||||
converter.extracted_data = _make_sample_extracted_data(include_tables=True)
|
||||
|
||||
converter.build_skill()
|
||||
|
||||
ref_file = Path(self.temp_dir) / "test_skill" / "references" / "test.md"
|
||||
content = ref_file.read_text()
|
||||
# Markdown table syntax
|
||||
self.assertIn("| Col A |", content)
|
||||
self.assertIn("| --- |", content)
|
||||
|
||||
def test_table_summary_in_skill_md(self):
|
||||
"""Table summary section appears in SKILL.md when tables exist."""
|
||||
config = {"name": "test_skill", "docx_path": "test.docx"}
|
||||
converter = self.WordToSkillConverter(config)
|
||||
converter.skill_dir = str(Path(self.temp_dir) / "test_skill")
|
||||
converter.extracted_data = _make_sample_extracted_data(include_tables=True)
|
||||
|
||||
converter.build_skill()
|
||||
|
||||
skill_md = Path(self.temp_dir) / "test_skill" / "SKILL.md"
|
||||
content = skill_md.read_text()
|
||||
self.assertIn("Table Summary", content)
|
||||
|
||||
|
||||
class TestWordImages(unittest.TestCase):
|
||||
"""Test image extraction and handling."""
|
||||
|
||||
def setUp(self):
|
||||
if not WORD_AVAILABLE:
|
||||
self.skipTest("mammoth and python-docx not installed")
|
||||
from skill_seekers.cli.word_scraper import WordToSkillConverter
|
||||
self.WordToSkillConverter = WordToSkillConverter
|
||||
self.temp_dir = tempfile.mkdtemp()
|
||||
|
||||
def tearDown(self):
|
||||
shutil.rmtree(self.temp_dir, ignore_errors=True)
|
||||
|
||||
def test_images_saved_to_assets(self):
|
||||
"""Images are saved to the assets/ directory."""
|
||||
config = {"name": "test_skill", "docx_path": "test.docx"}
|
||||
converter = self.WordToSkillConverter(config)
|
||||
converter.skill_dir = str(Path(self.temp_dir) / "test_skill")
|
||||
converter.extracted_data = _make_sample_extracted_data(include_images=True)
|
||||
|
||||
converter.build_skill()
|
||||
|
||||
assets_dir = Path(self.temp_dir) / "test_skill" / "assets"
|
||||
png_files = list(assets_dir.glob("*.png"))
|
||||
self.assertGreater(len(png_files), 0)
|
||||
|
||||
def test_image_references_in_markdown(self):
|
||||
"""Images are referenced with markdown syntax in reference files."""
|
||||
config = {"name": "test_skill", "docx_path": "test.docx"}
|
||||
converter = self.WordToSkillConverter(config)
|
||||
converter.skill_dir = str(Path(self.temp_dir) / "test_skill")
|
||||
converter.extracted_data = _make_sample_extracted_data(include_images=True)
|
||||
|
||||
converter.build_skill()
|
||||
|
||||
ref_file = Path(self.temp_dir) / "test_skill" / "references" / "test.md"
|
||||
content = ref_file.read_text()
|
||||
self.assertIn("![", content)
|
||||
self.assertIn("../assets/", content)
|
||||
|
||||
|
||||
class TestWordErrorHandling(unittest.TestCase):
|
||||
"""Test error handling for invalid inputs."""
|
||||
|
||||
def setUp(self):
|
||||
if not WORD_AVAILABLE:
|
||||
self.skipTest("mammoth and python-docx not installed")
|
||||
from skill_seekers.cli.word_scraper import WordToSkillConverter
|
||||
self.WordToSkillConverter = WordToSkillConverter
|
||||
self.temp_dir = tempfile.mkdtemp()
|
||||
|
||||
def tearDown(self):
|
||||
shutil.rmtree(self.temp_dir, ignore_errors=True)
|
||||
|
||||
def test_missing_docx_file_raises_error(self):
|
||||
"""extract_docx raises FileNotFoundError for missing file."""
|
||||
config = {"name": "test", "docx_path": "/nonexistent/path/test.docx"}
|
||||
converter = self.WordToSkillConverter(config)
|
||||
with self.assertRaises((FileNotFoundError, RuntimeError)):
|
||||
converter.extract_docx()
|
||||
|
||||
def test_invalid_config_raises_error(self):
|
||||
"""Non-dict config raises TypeError or AttributeError."""
|
||||
with self.assertRaises((TypeError, AttributeError)):
|
||||
self.WordToSkillConverter("invalid string")
|
||||
|
||||
def test_missing_name_raises_key_error(self):
|
||||
"""Config without 'name' raises KeyError."""
|
||||
with self.assertRaises((KeyError, TypeError)):
|
||||
self.WordToSkillConverter({"docx_path": "test.docx"})
|
||||
|
||||
|
||||
class TestWordJSONWorkflow(unittest.TestCase):
|
||||
"""Test building skills from extracted JSON."""
|
||||
|
||||
def setUp(self):
|
||||
if not WORD_AVAILABLE:
|
||||
self.skipTest("mammoth and python-docx not installed")
|
||||
from skill_seekers.cli.word_scraper import WordToSkillConverter
|
||||
self.WordToSkillConverter = WordToSkillConverter
|
||||
self.temp_dir = tempfile.mkdtemp()
|
||||
|
||||
def tearDown(self):
|
||||
shutil.rmtree(self.temp_dir, ignore_errors=True)
|
||||
|
||||
def test_load_from_json(self):
|
||||
"""load_extracted_data loads the JSON correctly."""
|
||||
extracted_data = _make_sample_extracted_data(num_sections=3)
|
||||
json_path = Path(self.temp_dir) / "extracted.json"
|
||||
json_path.write_text(json.dumps(extracted_data, indent=2))
|
||||
|
||||
config = {"name": "test_skill", "docx_path": "test.docx"}
|
||||
converter = self.WordToSkillConverter(config)
|
||||
converter.load_extracted_data(str(json_path))
|
||||
|
||||
self.assertEqual(converter.extracted_data["total_sections"], 3)
|
||||
self.assertEqual(len(converter.extracted_data["pages"]), 3)
|
||||
|
||||
def test_build_from_json_without_extraction(self):
|
||||
"""JSON workflow skips extract_docx() and goes directly to build."""
|
||||
extracted_data = _make_sample_extracted_data(num_sections=2)
|
||||
json_path = Path(self.temp_dir) / "extracted.json"
|
||||
json_path.write_text(json.dumps(extracted_data))
|
||||
|
||||
config = {"name": "test_skill", "docx_path": "test.docx"}
|
||||
converter = self.WordToSkillConverter(config)
|
||||
converter.load_extracted_data(str(json_path))
|
||||
|
||||
self.assertIsNotNone(converter.extracted_data)
|
||||
self.assertEqual(len(converter.extracted_data["pages"]), 2)
|
||||
|
||||
def test_skill_built_from_json_has_skill_md(self):
|
||||
"""build_skill() works after load_extracted_data()."""
|
||||
extracted_data = _make_sample_extracted_data(num_sections=2)
|
||||
json_path = Path(self.temp_dir) / "extracted.json"
|
||||
json_path.write_text(json.dumps(extracted_data))
|
||||
|
||||
config = {"name": "test_skill", "docx_path": "test.docx"}
|
||||
converter = self.WordToSkillConverter(config)
|
||||
converter.skill_dir = str(Path(self.temp_dir) / "test_skill")
|
||||
converter.load_extracted_data(str(json_path))
|
||||
converter.build_skill()
|
||||
|
||||
skill_md = Path(self.temp_dir) / "test_skill" / "SKILL.md"
|
||||
self.assertTrue(skill_md.exists())
|
||||
|
||||
|
||||
class TestWordCLIArguments(unittest.TestCase):
|
||||
"""Test word subcommand CLI argument parsing via the main CLI."""
|
||||
|
||||
def setUp(self):
|
||||
import sys
|
||||
from pathlib import Path as P
|
||||
|
||||
sys.path.insert(0, str(P(__file__).parent.parent / "src"))
|
||||
from skill_seekers.cli.main import create_parser
|
||||
|
||||
self.parser = create_parser()
|
||||
|
||||
def test_docx_argument_accepted(self):
|
||||
"""--docx flag is accepted for the word subcommand."""
|
||||
args = self.parser.parse_args(["word", "--docx", "test.docx"])
|
||||
self.assertEqual(args.docx, "test.docx")
|
||||
|
||||
def test_api_key_accepted(self):
|
||||
"""--api-key is accepted for word subcommand."""
|
||||
args = self.parser.parse_args(["word", "--docx", "test.docx", "--api-key", "sk-ant-test"])
|
||||
self.assertEqual(args.api_key, "sk-ant-test")
|
||||
|
||||
def test_enhance_level_accepted(self):
|
||||
"""--enhance-level is accepted for word subcommand."""
|
||||
args = self.parser.parse_args(["word", "--docx", "test.docx", "--enhance-level", "1"])
|
||||
self.assertEqual(args.enhance_level, 1)
|
||||
|
||||
def test_enhance_workflow_accepted(self):
|
||||
"""--enhance-workflow is accepted and stores a list."""
|
||||
args = self.parser.parse_args(
|
||||
["word", "--docx", "test.docx", "--enhance-workflow", "minimal"]
|
||||
)
|
||||
self.assertEqual(args.enhance_workflow, ["minimal"])
|
||||
|
||||
def test_workflow_dry_run_accepted(self):
|
||||
"""--workflow-dry-run is accepted."""
|
||||
args = self.parser.parse_args(["word", "--docx", "test.docx", "--workflow-dry-run"])
|
||||
self.assertTrue(args.workflow_dry_run)
|
||||
|
||||
def test_dry_run_accepted(self):
|
||||
"""--dry-run is accepted for word subcommand."""
|
||||
args = self.parser.parse_args(["word", "--docx", "test.docx", "--dry-run"])
|
||||
self.assertTrue(args.dry_run)
|
||||
|
||||
def test_from_json_accepted(self):
|
||||
"""--from-json is accepted."""
|
||||
args = self.parser.parse_args(["word", "--from-json", "data.json"])
|
||||
self.assertEqual(args.from_json, "data.json")
|
||||
|
||||
def test_name_accepted(self):
|
||||
"""--name is accepted."""
|
||||
args = self.parser.parse_args(["word", "--docx", "test.docx", "--name", "myskill"])
|
||||
self.assertEqual(args.name, "myskill")
|
||||
|
||||
|
||||
class TestWordHelperFunctions(unittest.TestCase):
|
||||
"""Test module-level helper functions."""
|
||||
|
||||
def setUp(self):
|
||||
if not WORD_AVAILABLE:
|
||||
self.skipTest("mammoth and python-docx not installed")
|
||||
|
||||
def test_build_section_basic(self):
|
||||
"""_build_section returns a well-formed dict."""
|
||||
from skill_seekers.cli.word_scraper import _build_section
|
||||
from bs4 import BeautifulSoup
|
||||
|
||||
html = "<p>Hello world.</p><p>Second paragraph.</p>"
|
||||
soup = BeautifulSoup(html, "html.parser")
|
||||
elements = list(soup.children)
|
||||
|
||||
section = _build_section(1, "Intro", "h1", elements, None)
|
||||
|
||||
self.assertEqual(section["section_number"], 1)
|
||||
self.assertEqual(section["heading"], "Intro")
|
||||
self.assertEqual(section["heading_level"], "h1")
|
||||
self.assertIn("Hello world", section["text"])
|
||||
|
||||
def test_extract_table_from_html(self):
|
||||
"""_extract_table_from_html extracts headers and rows."""
|
||||
from skill_seekers.cli.word_scraper import _extract_table_from_html
|
||||
from bs4 import BeautifulSoup
|
||||
|
||||
html = """
|
||||
<table>
|
||||
<thead><tr><th>Name</th><th>Value</th></tr></thead>
|
||||
<tbody>
|
||||
<tr><td>foo</td><td>1</td></tr>
|
||||
<tr><td>bar</td><td>2</td></tr>
|
||||
</tbody>
|
||||
</table>"""
|
||||
soup = BeautifulSoup(html, "html.parser")
|
||||
table_elem = soup.find("table")
|
||||
|
||||
result = _extract_table_from_html(table_elem)
|
||||
|
||||
self.assertIsNotNone(result)
|
||||
self.assertEqual(result["headers"], ["Name", "Value"])
|
||||
self.assertEqual(len(result["rows"]), 2)
|
||||
self.assertIn(["foo", "1"], result["rows"])
|
||||
|
||||
def test_score_code_quality_basic(self):
|
||||
"""_score_code_quality returns a score in [0, 10]."""
|
||||
from skill_seekers.cli.word_scraper import _score_code_quality
|
||||
|
||||
score = _score_code_quality("def foo():\n return 'bar'\n")
|
||||
self.assertGreaterEqual(score, 0.0)
|
||||
self.assertLessEqual(score, 10.0)
|
||||
|
||||
def test_score_code_quality_empty(self):
|
||||
"""_score_code_quality returns 0.0 for empty code."""
|
||||
from skill_seekers.cli.word_scraper import _score_code_quality
|
||||
|
||||
self.assertEqual(_score_code_quality(""), 0.0)
|
||||
|
||||
def test_infer_description_from_word_subject(self):
|
||||
"""infer_description_from_word uses subject field when available."""
|
||||
from skill_seekers.cli.word_scraper import infer_description_from_word
|
||||
|
||||
metadata = {"title": "Some Doc", "subject": "Writing API documentation for REST services"}
|
||||
desc = infer_description_from_word(metadata, "api_docs")
|
||||
self.assertIn("writing api documentation", desc.lower())
|
||||
|
||||
def test_infer_description_from_word_fallback(self):
|
||||
"""infer_description_from_word falls back to name."""
|
||||
from skill_seekers.cli.word_scraper import infer_description_from_word
|
||||
|
||||
desc = infer_description_from_word({}, name="myskill")
|
||||
self.assertIn("myskill", desc)
|
||||
|
||||
|
||||
class TestWordSourceDetection(unittest.TestCase):
|
||||
"""Test .docx source detection in SourceDetector."""
|
||||
|
||||
def test_docx_detected_as_word_type(self):
|
||||
"""SourceDetector.detect() returns type='word' for .docx files."""
|
||||
from skill_seekers.cli.source_detector import SourceDetector
|
||||
|
||||
# Use a path that ends in .docx (doesn't need to exist for detection)
|
||||
source_info = SourceDetector.detect("/tmp/test_document.docx")
|
||||
self.assertEqual(source_info.type, "word")
|
||||
self.assertEqual(source_info.parsed["file_path"], "/tmp/test_document.docx")
|
||||
self.assertEqual(source_info.suggested_name, "test_document")
|
||||
|
||||
def test_docx_validation_missing_file(self):
|
||||
"""validate_source raises ValueError for missing .docx file."""
|
||||
from skill_seekers.cli.source_detector import SourceDetector
|
||||
|
||||
source_info = SourceDetector.detect("/tmp/nonexistent_12345.docx")
|
||||
with self.assertRaises(ValueError) as ctx:
|
||||
SourceDetector.validate_source(source_info)
|
||||
self.assertIn("does not exist", str(ctx.exception))
|
||||
|
||||
def test_pdf_still_detected(self):
|
||||
"""Existing PDF detection is unaffected by Word support."""
|
||||
from skill_seekers.cli.source_detector import SourceDetector
|
||||
|
||||
source_info = SourceDetector.detect("/tmp/test.pdf")
|
||||
self.assertEqual(source_info.type, "pdf")
|
||||
|
||||
|
||||
if __name__ == "__main__":
|
||||
unittest.main()
|
||||
Reference in New Issue
Block a user