shared/office_artifacts.py

from __future__ import annotations

import html
import zipfile
from pathlib import Path
from typing import Sequence


def _paragraph_xml(text: str, style: str = "") -> str:
    style_xml = f'<w:pPr><w:pStyle w:val="{style}"/></w:pPr>' if style else ""
    return f"<w:p>{style_xml}<w:r><w:t>{html.escape(str(text))}</w:t></w:r></w:p>"


def write_structured_docx(
    path: str | Path,
    title: str,
    sections: Sequence[tuple[str, Sequence[str]]],
) -> Path:
    target = Path(path)
    target.parent.mkdir(parents=True, exist_ok=True)
    body_parts = [_paragraph_xml(title, "Title")]
    for heading, paragraphs in sections:
        body_parts.append(_paragraph_xml(heading, "Heading1"))
        body_parts.extend(_paragraph_xml(paragraph or "Not provided") for paragraph in paragraphs)
    body = "".join(body_parts)
    with zipfile.ZipFile(target, "w", zipfile.ZIP_DEFLATED) as archive:
        archive.writestr(
            "[Content_Types].xml",
            '<?xml version="1.0" encoding="UTF-8"?><Types xmlns="http://schemas.openxmlformats.org/package/2006/content-types"><Default Extension="rels" ContentType="application/vnd.openxmlformats-package.relationships+xml"/><Default Extension="xml" ContentType="application/xml"/><Override PartName="/word/document.xml" ContentType="application/vnd.openxmlformats-officedocument.wordprocessingml.document.main+xml"/><Override PartName="/word/styles.xml" ContentType="application/vnd.openxmlformats-officedocument.wordprocessingml.styles+xml"/></Types>',
        )
        archive.writestr(
            "_rels/.rels",
            '<?xml version="1.0" encoding="UTF-8"?><Relationships xmlns="http://schemas.openxmlformats.org/package/2006/relationships"><Relationship Id="rId1" Type="http://schemas.openxmlformats.org/officeDocument/2006/relationships/officeDocument" Target="word/document.xml"/></Relationships>',
        )
        archive.writestr(
            "word/styles.xml",
            '<?xml version="1.0" encoding="UTF-8"?><w:styles xmlns:w="http://schemas.openxmlformats.org/wordprocessingml/2006/main"><w:style w:type="paragraph" w:styleId="Title"><w:name w:val="Title"/></w:style><w:style w:type="paragraph" w:styleId="Heading1"><w:name w:val="heading 1"/></w:style></w:styles>',
        )
        archive.writestr(
            "word/document.xml",
            f'<?xml version="1.0" encoding="UTF-8"?><w:document xmlns:w="http://schemas.openxmlformats.org/wordprocessingml/2006/main"><w:body>{body}<w:sectPr/></w:body></w:document>',
        )
    return target