Files
claude-plugins/dev-tools/skills/docx/scripts/office/validate.py
Emanuel Almeida 6b3a6f2698 feat: refactor 30+ skills to Anthropic progressive disclosure pattern
- All SKILL.md files now <500 lines (avg reduction 69%)
- Detailed content extracted to references/ subdirectories
- Frontmatter standardised: only name + description (Anthropic standard)
- New skills: brand-guidelines, spec-coauthor, report-templates, skill-creator
- Design skills: anti-slop guidelines, premium-proposals reference
- Removed non-standard frontmatter fields (triggers, version, author, category)

Plugins affected: infraestrutura, marketing, dev-tools, crm-ops, gestao,
core-tools, negocio, perfex-dev, wordpress, design-media

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
2026-03-12 15:05:03 +00:00

112 lines
3.6 KiB
Python
Executable File

"""
Command line tool to validate Office document XML files against XSD schemas and tracked changes.
Usage:
python validate.py <path> [--original <original_file>] [--auto-repair] [--author NAME]
The first argument can be either:
- An unpacked directory containing the Office document XML files
- A packed Office file (.docx/.pptx/.xlsx) which will be unpacked to a temp directory
Auto-repair fixes:
- paraId/durableId values that exceed OOXML limits
- Missing xml:space="preserve" on w:t elements with whitespace
"""
import argparse
import sys
import tempfile
import zipfile
from pathlib import Path
from validators import DOCXSchemaValidator, PPTXSchemaValidator, RedliningValidator
def main():
parser = argparse.ArgumentParser(description="Validate Office document XML files")
parser.add_argument(
"path",
help="Path to unpacked directory or packed Office file (.docx/.pptx/.xlsx)",
)
parser.add_argument(
"--original",
required=False,
default=None,
help="Path to original file (.docx/.pptx/.xlsx). If omitted, all XSD errors are reported and redlining validation is skipped.",
)
parser.add_argument(
"-v",
"--verbose",
action="store_true",
help="Enable verbose output",
)
parser.add_argument(
"--auto-repair",
action="store_true",
help="Automatically repair common issues (hex IDs, whitespace preservation)",
)
parser.add_argument(
"--author",
default="Claude",
help="Author name for redlining validation (default: Claude)",
)
args = parser.parse_args()
path = Path(args.path)
assert path.exists(), f"Error: {path} does not exist"
original_file = None
if args.original:
original_file = Path(args.original)
assert original_file.is_file(), f"Error: {original_file} is not a file"
assert original_file.suffix.lower() in [".docx", ".pptx", ".xlsx"], (
f"Error: {original_file} must be a .docx, .pptx, or .xlsx file"
)
file_extension = (original_file or path).suffix.lower()
assert file_extension in [".docx", ".pptx", ".xlsx"], (
f"Error: Cannot determine file type from {path}. Use --original or provide a .docx/.pptx/.xlsx file."
)
if path.is_file() and path.suffix.lower() in [".docx", ".pptx", ".xlsx"]:
temp_dir = tempfile.mkdtemp()
with zipfile.ZipFile(path, "r") as zf:
zf.extractall(temp_dir)
unpacked_dir = Path(temp_dir)
else:
assert path.is_dir(), f"Error: {path} is not a directory or Office file"
unpacked_dir = path
match file_extension:
case ".docx":
validators = [
DOCXSchemaValidator(unpacked_dir, original_file, verbose=args.verbose),
]
if original_file:
validators.append(
RedliningValidator(unpacked_dir, original_file, verbose=args.verbose, author=args.author)
)
case ".pptx":
validators = [
PPTXSchemaValidator(unpacked_dir, original_file, verbose=args.verbose),
]
case _:
print(f"Error: Validation not supported for file type {file_extension}")
sys.exit(1)
if args.auto_repair:
total_repairs = sum(v.repair() for v in validators)
if total_repairs:
print(f"Auto-repaired {total_repairs} issue(s)")
success = all(v.validate() for v in validators)
if success:
print("All validations PASSED!")
sys.exit(0 if success else 1)
if __name__ == "__main__":
main()