memind/skills/docx-generate/generate_docx.py

#!/usr/bin/env python3
"""Generate a minimal valid .docx using only Python stdlib (zipfile + XML)."""

from __future__ import annotations

import argparse
import json
import sys
import zipfile
from pathlib import Path
from xml.sax.saxutils import escape

W_NS = "http://schemas.openxmlformats.org/wordprocessingml/2006/main"
R_NS = "http://schemas.openxmlformats.org/officeDocument/2006/relationships"
CT_NS = "http://schemas.openxmlformats.org/package/2006/content-types"
REL_NS = "http://schemas.openxmlformats.org/package/2006/relationships"
CP_NS = "http://schemas.openxmlformats.org/package/2006/metadata/core-properties"
DC_NS = "http://purl.org/dc/elements/1.1"

CONTENT_TYPES = f"""<?xml version="1.0" encoding="UTF-8" standalone="yes"?>
<Types xmlns="{CT_NS}">
  <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="/docProps/core.xml" ContentType="application/vnd.openxmlformats-package.core-properties+xml"/>
</Types>"""

ROOT_RELS = f"""<?xml version="1.0" encoding="UTF-8" standalone="yes"?>
<Relationships xmlns="{REL_NS}">
  <Relationship Id="rId1" Type="http://schemas.openxmlformats.org/officeDocument/2006/relationships/officeDocument" Target="word/document.xml"/>
  <Relationship Id="rId2" Type="http://schemas.openxmlformats.org/package/2006/relationships/metadata/core-properties" Target="docProps/core.xml"/>
</Relationships>"""

DOCUMENT_RELS = f"""<?xml version="1.0" encoding="UTF-8" standalone="yes"?>
<Relationships xmlns="{REL_NS}"/>"""


def sanitize_text(text: str) -> str:
    """Strip emoji and XML-illegal control chars (Word/iOS rejects these)."""
    cleaned = str(text or "")
    cleaned = cleaned.encode("utf-8", "ignore").decode("utf-8")
    cleaned = "".join(
        ch
        for ch in cleaned
        if not (0xD800 <= ord(ch) <= 0xDFFF)
        and (ord(ch) == 0x9 or ord(ch) == 0xA or ord(ch) == 0xD or ord(ch) >= 0x20)
        and not (0x1F000 <= ord(ch) <= 0x1FAFF or 0x2600 <= ord(ch) <= 0x27BF)
    )
    return cleaned.strip()


def xml_text(text: str) -> str:
    return escape(sanitize_text(text))


def run(text: str, bold: bool = False) -> str:
    props = "<w:b/>" if bold else ""
    return (
        f'<w:r><w:rPr>{props}</w:rPr>'
        f'<w:t xml:space="preserve">{xml_text(text)}</w:t></w:r>'
    )


def paragraph(parts: str, style: str | None = None) -> str:
    ppr = f'<w:pPr><w:pStyle w:val="{style}"/></w:pPr>' if style else ""
    return f"<w:p>{ppr}{parts}</w:p>"


def heading(text: str) -> str:
    cleaned = sanitize_text(text)
    if not cleaned:
        return ""
    return paragraph(run(cleaned, bold=True))


def body_paragraph(text: str) -> str:
    cleaned = sanitize_text(text)
    if not cleaned:
        return ""
    return paragraph(run(cleaned))


def is_ooxml_fragment(text: str) -> bool:
    stripped = str(text or "").strip()
    return stripped.startswith("<w:") or "</w:" in stripped


def table_block(headers: list[str], rows: list[list[str]]) -> str:
    col_count = max(len(headers), max((len(r) for r in rows), default=0))
    if col_count == 0:
        return ""

    col_width = max(1800, 9000 // col_count)

    def cell(text: str) -> str:
        return (
            f'<w:tc><w:tcPr><w:tcW w:w="{col_width}" w:type="dxa"/></w:tcPr>'
            f"{paragraph(run(text))}</w:tc>"
        )

    def table_row(cells: list[str]) -> str:
        padded = cells + [""] * (col_count - len(cells))
        return f"<w:tr>{''.join(cell(c) for c in padded[:col_count])}</w:tr>"

    grid_cols = "".join(f'<w:gridCol w:w="{col_width}"/>' for _ in range(col_count))
    tbl_pr = (
        "<w:tblPr>"
        '<w:tblW w:w="5000" w:type="pct"/>'
        "<w:tblBorders>"
        '<w:top w:val="single" w:sz="4" w:space="0" w:color="auto"/>'
        '<w:left w:val="single" w:sz="4" w:space="0" w:color="auto"/>'
        '<w:bottom w:val="single" w:sz="4" w:space="0" w:color="auto"/>'
        '<w:right w:val="single" w:sz="4" w:space="0" w:color="auto"/>'
        '<w:insideH w:val="single" w:sz="4" w:space="0" w:color="auto"/>'
        '<w:insideV w:val="single" w:sz="4" w:space="0" w:color="auto"/>'
        "</w:tblBorders>"
        "</w:tblPr>"
    )
    parts = ["<w:tbl>", tbl_pr, f"<w:tblGrid>{grid_cols}</w:tblGrid>"]
    if headers:
        parts.append(table_row(headers))
    parts.extend(table_row(r) for r in rows)
    parts.append("</w:tbl>")
    return "".join(parts)


def build_document_xml(title: str, sections: list[dict]) -> str:
    body: list[str] = []
    if title:
        block = heading(title)
        if block:
            body.append(block)

    for section in sections:
        heading_text = section.get("heading") or section.get("title")
        if heading_text:
            block = heading(str(heading_text))
            if block:
                body.append(block)
        for para in section.get("paragraphs") or []:
            text = str(para).strip()
            if text and not is_ooxml_fragment(text):
                block = body_paragraph(text)
                if block:
                    body.append(block)
        table = section.get("table")
        if isinstance(table, dict):
            block = table_block(
                list(table.get("headers") or []),
                [list(r) for r in (table.get("rows") or [])],
            )
            if block:
                body.append(block)

    sect_pr = (
        f'<w:sectPr><w:pgSz w:w="11906" w:h="16838"/>'
        f'<w:pgMar w:top="1440" w:right="1440" w:bottom="1440" w:left="1440"/></w:sectPr>'
    )
    inner = "".join(body) + sect_pr
    return (
        f'<?xml version="1.0" encoding="UTF-8" standalone="yes"?>'
        f'<w:document xmlns:w="{W_NS}" xmlns:r="{R_NS}">'
        f"<w:body>{inner}</w:body></w:document>"
    )


def core_xml(title: str) -> str:
    return (
        f'<?xml version="1.0" encoding="UTF-8" standalone="yes"?>'
        f'<cp:coreProperties xmlns:cp="{CP_NS}" xmlns:dc="{DC_NS}">'
        f"<dc:title>{xml_text(title)}</dc:title>"
        f"</cp:coreProperties>"
    )


def write_docx(output: Path, title: str, sections: list[dict]) -> None:
    output.parent.mkdir(parents=True, exist_ok=True)
    document_xml = build_document_xml(title, sections)
    with zipfile.ZipFile(output, "w", compression=zipfile.ZIP_DEFLATED) as zf:
        zf.writestr("[Content_Types].xml", CONTENT_TYPES)
        zf.writestr("_rels/.rels", ROOT_RELS)
        zf.writestr("word/_rels/document.xml.rels", DOCUMENT_RELS)
        zf.writestr("word/document.xml", document_xml)
        zf.writestr("docProps/core.xml", core_xml(title))


def load_payload(args: argparse.Namespace) -> dict:
    if args.json:
        source = sys.stdin.read() if args.json == "-" else Path(args.json).read_text(encoding="utf-8")
        return json.loads(source)
    if args.title:
        return {"title": args.title, "sections": [{"paragraphs": args.paragraph or []}]}
    raise SystemExit("需要 --json <file>（或 - 读 stdin），或 --title")


def main() -> None:
    parser = argparse.ArgumentParser(description="用 Python 标准库生成 .docx（无需 python-docx）")
    parser.add_argument("--output", required=True, help="输出路径，如 oa/报告.docx")
    parser.add_argument("--json", help="JSON 内容文件；传 - 则从 stdin 读取")
    parser.add_argument("--title", help="仅标题 + --paragraph 时的文档标题")
    parser.add_argument("--paragraph", action="append", help="配合 --title 追加段落")
    args = parser.parse_args()

    payload = load_payload(args)
    title = str(payload.get("title") or "")
    sections = list(payload.get("sections") or [])
    output = Path(args.output)
    write_docx(output, title, sections)
    size = output.stat().st_size
    print(f"已生成 {output}（{size} 字节）")


if __name__ == "__main__":
    main()