Claude Code skill that extracts structured data from document collections into tabular format using Claude's native document understanding capabilities.
123 lines
3.4 KiB
Python
123 lines
3.4 KiB
Python
#!/usr/bin/env python3
|
|
"""Tests for convert_docx.py"""
|
|
|
|
import subprocess
|
|
import sys
|
|
import tempfile
|
|
import os
|
|
|
|
SCRIPT = os.path.join(os.path.dirname(__file__), "convert_docx.py")
|
|
|
|
|
|
def test_missing_argument():
|
|
"""Script should print usage and exit 1 when no args given."""
|
|
result = subprocess.run(
|
|
[sys.executable, SCRIPT],
|
|
capture_output=True, text=True
|
|
)
|
|
assert result.returncode == 1
|
|
assert "Usage:" in result.stderr
|
|
|
|
|
|
def test_nonexistent_file():
|
|
"""Script should error on a file that doesn't exist."""
|
|
result = subprocess.run(
|
|
[sys.executable, SCRIPT, "/tmp/nonexistent_file_abc123.docx"],
|
|
capture_output=True, text=True
|
|
)
|
|
assert result.returncode == 1
|
|
assert "Error" in result.stderr or "not found" in result.stderr.lower()
|
|
|
|
|
|
def test_non_docx_file():
|
|
"""Script should error on a non-DOCX file."""
|
|
with tempfile.NamedTemporaryFile(suffix=".txt", delete=False) as f:
|
|
f.write(b"hello world")
|
|
f.flush()
|
|
result = subprocess.run(
|
|
[sys.executable, SCRIPT, f.name],
|
|
capture_output=True, text=True
|
|
)
|
|
os.unlink(f.name)
|
|
assert result.returncode == 1
|
|
|
|
|
|
def test_valid_docx():
|
|
"""Script should extract text from a valid DOCX file."""
|
|
try:
|
|
from docx import Document
|
|
except ImportError:
|
|
print("SKIP: python-docx not installed")
|
|
return
|
|
|
|
doc = Document()
|
|
doc.add_paragraph("Hello from test document")
|
|
doc.add_paragraph("Second paragraph here")
|
|
|
|
with tempfile.NamedTemporaryFile(suffix=".docx", delete=False) as f:
|
|
doc.save(f.name)
|
|
result = subprocess.run(
|
|
[sys.executable, SCRIPT, f.name],
|
|
capture_output=True, text=True
|
|
)
|
|
os.unlink(f.name)
|
|
|
|
assert result.returncode == 0
|
|
assert "Hello from test document" in result.stdout
|
|
assert "Second paragraph here" in result.stdout
|
|
|
|
|
|
def test_docx_with_table():
|
|
"""Script should extract table content from a DOCX file."""
|
|
try:
|
|
from docx import Document
|
|
except ImportError:
|
|
print("SKIP: python-docx not installed")
|
|
return
|
|
|
|
doc = Document()
|
|
doc.add_paragraph("Before table")
|
|
table = doc.add_table(rows=2, cols=2)
|
|
table.cell(0, 0).text = "Header1"
|
|
table.cell(0, 1).text = "Header2"
|
|
table.cell(1, 0).text = "Value1"
|
|
table.cell(1, 1).text = "Value2"
|
|
doc.add_paragraph("After table")
|
|
|
|
with tempfile.NamedTemporaryFile(suffix=".docx", delete=False) as f:
|
|
doc.save(f.name)
|
|
result = subprocess.run(
|
|
[sys.executable, SCRIPT, f.name],
|
|
capture_output=True, text=True
|
|
)
|
|
os.unlink(f.name)
|
|
|
|
assert result.returncode == 0
|
|
assert "Header1" in result.stdout
|
|
assert "Value1" in result.stdout
|
|
|
|
|
|
if __name__ == "__main__":
|
|
tests = [
|
|
test_missing_argument,
|
|
test_nonexistent_file,
|
|
test_non_docx_file,
|
|
test_valid_docx,
|
|
test_docx_with_table,
|
|
]
|
|
passed = 0
|
|
failed = 0
|
|
for test in tests:
|
|
try:
|
|
test()
|
|
print(f" PASS: {test.__name__}")
|
|
passed += 1
|
|
except AssertionError as e:
|
|
print(f" FAIL: {test.__name__} - {e}")
|
|
failed += 1
|
|
except Exception as e:
|
|
print(f" ERROR: {test.__name__} - {e}")
|
|
failed += 1
|
|
print(f"\n{passed} passed, {failed} failed")
|
|
sys.exit(1 if failed else 0)
|