hermes-agent/skills/productivity/docx/scripts/accept_changes.py
Teknium afb7bf6a5a
feat(skills): bundle docx, xlsx, and pdf office skills; refresh powerpoint (#68595)
Non-technical users asking for Word docs, spreadsheets, or PDF work had
no bundled skill coverage — docx/xlsx creation required discovering and
installing hub skills, and PDF manipulation had no skill at all beyond
OCR extraction and nano-pdf edits.

- skills/productivity/docx: create (docx-js), edit (unzip -> XML -> zip),
  tracked changes, comments, validation. Adapted from anthropics/skills.
- skills/productivity/xlsx: openpyxl creation/editing, mandatory
  LibreOffice recalc gate, formula-compatibility rules, financial-model
  conventions. Points at optional excel-author for finance-grade work.
- skills/productivity/pdf: merge/split/rotate/watermark/encrypt, form
  filling (AcroForm + flat overlay scripts), text/table extraction,
  reportlab creation, forms.md + reference.md companions.
- skills/productivity/powerpoint: synced to current upstream pptx skill —
  richer pptxgenjs corruption footguns, template workflow, validate.py +
  validators + thumbnail.py, font-substitution QA guidance; drops the
  stale pack.py/editing.md/pptxgenjs.md workflow files.
- Cross-linked ocr-and-documents, nano-pdf, excel-author via
  related_skills so each office skill routes to its siblings.
- deliverable-mode docs mention the new skills; regenerated per-skill
  docs pages, catalogs, and sidebar.
- tests/skills/test_office_document_skills.py: frontmatter contracts,
  referenced-script existence, schema-map integrity, cross-link
  resolution, script compilation.

E2E validated: docx create->render->edit->validate, xlsx recalc
(SUM + _xlfn.TEXTJOIN evaluate correctly), pdf create->merge->extract,
pptx generate->validate->thumbnail.
2026-07-21 05:39:23 -07:00

135 lines
4 KiB
Python
Executable file

"""Accept all tracked changes in a DOCX file using LibreOffice.
Requires LibreOffice (soffice) to be installed.
"""
import argparse
import logging
import shutil
import subprocess
from pathlib import Path
from office.soffice import get_soffice_env
logger = logging.getLogger(__name__)
LIBREOFFICE_PROFILE = "/tmp/libreoffice_docx_profile"
MACRO_DIR = f"{LIBREOFFICE_PROFILE}/user/basic/Standard"
ACCEPT_CHANGES_MACRO = """<?xml version="1.0" encoding="UTF-8"?>
<!DOCTYPE script:module PUBLIC "-//OpenOffice.org//DTD OfficeDocument 1.0//EN" "module.dtd">
<script:module xmlns:script="http://openoffice.org/2000/script" script:name="Module1" script:language="StarBasic">
Sub AcceptAllTrackedChanges()
Dim document As Object
Dim dispatcher As Object
document = ThisComponent.CurrentController.Frame
dispatcher = createUnoService("com.sun.star.frame.DispatchHelper")
dispatcher.executeDispatch(document, ".uno:AcceptAllTrackedChanges", "", 0, Array())
ThisComponent.store()
ThisComponent.close(True)
End Sub
</script:module>"""
def accept_changes(
input_file: str,
output_file: str,
) -> tuple[None, str]:
input_path = Path(input_file)
output_path = Path(output_file)
if not input_path.exists():
return None, f"Error: Input file not found: {input_file}"
if not input_path.suffix.lower() == ".docx":
return None, f"Error: Input file is not a DOCX file: {input_file}"
try:
output_path.parent.mkdir(parents=True, exist_ok=True)
shutil.copy2(input_path, output_path)
except Exception as e:
return None, f"Error: Failed to copy input file to output location: {e}"
if not _setup_libreoffice_macro():
return None, "Error: Failed to setup LibreOffice macro"
cmd = [
"soffice",
"--headless",
f"-env:UserInstallation=file://{LIBREOFFICE_PROFILE}",
"--norestore",
"vnd.sun.star.script:Standard.Module1.AcceptAllTrackedChanges?language=Basic&location=application",
str(output_path.absolute()),
]
try:
result = subprocess.run(
cmd,
capture_output=True,
text=True,
timeout=30,
check=False,
env=get_soffice_env(),
)
except subprocess.TimeoutExpired:
return (
None,
f"Successfully accepted all tracked changes: {input_file} -> {output_file}",
)
if result.returncode != 0:
return None, f"Error: LibreOffice failed: {result.stderr}"
return (
None,
f"Successfully accepted all tracked changes: {input_file} -> {output_file}",
)
def _setup_libreoffice_macro() -> bool:
macro_dir = Path(MACRO_DIR)
macro_file = macro_dir / "Module1.xba"
if macro_file.exists() and "AcceptAllTrackedChanges" in macro_file.read_text():
return True
if not macro_dir.exists():
subprocess.run(
[
"soffice",
"--headless",
f"-env:UserInstallation=file://{LIBREOFFICE_PROFILE}",
"--terminate_after_init",
],
capture_output=True,
timeout=10,
check=False,
env=get_soffice_env(),
)
macro_dir.mkdir(parents=True, exist_ok=True)
try:
macro_file.write_text(ACCEPT_CHANGES_MACRO)
return True
except Exception as e:
logger.warning(f"Failed to setup LibreOffice macro: {e}")
return False
if __name__ == "__main__":
parser = argparse.ArgumentParser(
description="Accept all tracked changes in a DOCX file"
)
parser.add_argument("input_file", help="Input DOCX file with tracked changes")
parser.add_argument(
"output_file", help="Output DOCX file (clean, no tracked changes)"
)
args = parser.parse_args()
_, message = accept_changes(args.input_file, args.output_file)
print(message)
if "Error" in message:
raise SystemExit(1)