c86c93582e
- Add 8 new skills (62 total, up from 58) - Official Anthropic skills: docx, pdf, pptx, xlsx, brand-guidelines, internal-comms - Vercel Labs skills: react-best-practices, web-design-guidelines - Implement dual-versioning: -official/-anthropic and -community suffixes - Update README with new skill registry and credits - Regenerate skills_index.json (62 skills validated) - Add comprehensive walkthrough.md BREAKING CHANGE: Document skills (docx/pdf/pptx/xlsx) renamed with version suffixes
30 lines
1.0 KiB
Python
Executable File
30 lines
1.0 KiB
Python
Executable File
#!/usr/bin/env python3
|
|
"""Unpack and format XML contents of Office files (.docx, .pptx, .xlsx)"""
|
|
|
|
import random
|
|
import sys
|
|
import defusedxml.minidom
|
|
import zipfile
|
|
from pathlib import Path
|
|
|
|
# Get command line arguments
|
|
assert len(sys.argv) == 3, "Usage: python unpack.py <office_file> <output_dir>"
|
|
input_file, output_dir = sys.argv[1], sys.argv[2]
|
|
|
|
# Extract and format
|
|
output_path = Path(output_dir)
|
|
output_path.mkdir(parents=True, exist_ok=True)
|
|
zipfile.ZipFile(input_file).extractall(output_path)
|
|
|
|
# Pretty print all XML files
|
|
xml_files = list(output_path.rglob("*.xml")) + list(output_path.rglob("*.rels"))
|
|
for xml_file in xml_files:
|
|
content = xml_file.read_text(encoding="utf-8")
|
|
dom = defusedxml.minidom.parseString(content)
|
|
xml_file.write_bytes(dom.toprettyxml(indent=" ", encoding="ascii"))
|
|
|
|
# For .docx files, suggest an RSID for tracked changes
|
|
if input_file.endswith(".docx"):
|
|
suggested_rsid = "".join(random.choices("0123456789ABCDEF", k=8))
|
|
print(f"Suggested RSID for edit session: {suggested_rsid}")
|