Advanced Office Tool

Advanced office document processing toolkit — Word (DOCX), Excel (XLSX), and other formats.

Installation

pip install advanced-office-tool

Usage

Use ServerAgent for all document operations. Import once, call methods on any file path.

from advanced_office_tool import ServerAgent

agent = ServerAgent()

DOCX Translation

result = agent.translate_file(
    "manual.docx",
    target_language="en",       # "en", "zh", "auto", etc.
    target_format="{translated}" # or "{original}" or "{original}{translated}"
)
print(result["output_file_path"])
# → /home/ovos/.hermes/skills/office-tool/uploads/manual_en.docx

DOCX Merge (with auto CRC-32 repair)

from advanced_office_tool import DocxAgent, SafeDocument

# Merge with auto repair for corrupted files
agent = DocxAgent()
agent.load_document("chapter1.docx")
agent.merge_docx(["chapter2.docx", "chapter3.docx"], "merged.docx")

SafeDocument transparently repairs bad CRC-32 ZIP checksums:

from advanced_office_tool import SafeDocument
from docx import Document

# Broken DOCX auto-repairs on first access
doc = SafeDocument("corrupted.docx")
for p in doc.paragraphs:
    print(p.text)

PDF Conversion

# PDF → DOCX
result = agent.pdf_to_docx("scan.pdf")
print(result["content"])

# DOCX → PDF
result = agent.docx_to_pdf("report.docx")
print(result["content"])

# XLSX → PDF
result = agent.xlsx_to_pdf("data.xlsx")
print(result["content"])

# Images → PDF
result = agent.pngs_to_pdf(["img1.png", "img2.png"])
print(result["output_pdf_path"])

# PDF → PNG images
images = agent.pdf_to_png("document.pdf", dpi=300)
print(images)  # ["/path/to/page0.png", ...]

PDF Stamp

result = agent.add_stamp_to_pdf(
    "contract.pdf",
    position="80,80",           # top-right corner
    scale="1.5",                # stamp size multiplier
    stamp_image="./stamp.png"   # stamp image path
)
print(result["output_pdf_after_stamp"])

Excel Price Adjustment

result = agent.adjust_price_in_excel(
    "quote.xlsx",
    price_multiplier="1.3/6.9",  # unit_price * multiplier / divisor
    decimal_places="0"            # round to 0 decimals
)
print(result["output_file_path"])

Template Rendering

result = agent.render_docx_template(
    "template.docx",
    obj={"name": "Company A", "amount": 50000},
    output_path="output.docx"
)

PDF Merge to DOCX (N images per page)

result = agent.merge_pdfs_folder_to_docx_vertical(
    pdf_folder="./invoices",   # folder with PDF files
    number_in_page=2           # 2 PDF pages per DOCX page
)
print(result["output_file_path"])

Unzip

result = agent.uncompress_zip("archive.zip", "mt123456")
print(result["message"])

Available Classes

License

Apache-2.0