Rpa_Skills/skills/rpa-bot-handoff/templates/to_docx.py

"""Turn the Handover SOP (HANDOVER-SOP.md) into a Word document, and a PDF, ops can open, print and pass around.

    python to_docx.py HANDOVER-SOP.md                                  # writes HANDOVER-SOP.docx next to it
    python to_docx.py HANDOVER-SOP.md -o "<Project Name> Handover SOP.docx" --pdf   # + the .pdf next to it
    python to_docx.py --selfcheck

Prints the word count (at most MAX_WORDS) and, with --pdf, the real page count (at most MAX_PAGES).
The PDF is made by Word on Windows (through PowerShell) or by LibreOffice (soffice) elsewhere.

Handles what the template uses: # headings, paragraphs, - bullets, - [ ] checkboxes, 1. steps,
| tables |, ``` blocks, **bold**, *italic* and `code`. Needs python-docx (pip install python-docx).
"""
import argparse
import re
import subprocess
import sys
import tempfile
from pathlib import Path

from docx import Document
from docx.shared import Cm, Pt

MAX_WORDS = 1400  # about 4 pages with the margins and table font below
MAX_PAGES = 4
INLINE = re.compile(r"(\*\*[^*]+\*\*|\*[^*\s][^*]*\*|`[^`]+`)")


def add_runs(par, text):
    for part in INLINE.split(text):
        if part.startswith("**") and part.endswith("**"):
            par.add_run(part[2:-2]).bold = True
        elif len(part) > 2 and part.startswith("*") and part.endswith("*"):
            par.add_run(part[1:-1]).italic = True
        elif part.startswith("`") and part.endswith("`"):
            par.add_run(part[1:-1]).font.name = "Consolas"
        elif part:
            par.add_run(part)


def cells(line):
    return [c.strip() for c in line.strip().strip("|").split("|")]


def convert(md_text, out_path):
    doc = Document()
    doc.styles["Normal"].font.name = "Calibri"
    doc.styles["Normal"].font.size = Pt(10.5)
    for section in doc.sections:  # Word's 2.5 cm default margins push a 4-page SOP onto 5
        section.left_margin = section.right_margin = Cm(1.8)
        section.top_margin = section.bottom_margin = Cm(1.6)
    lines = md_text.splitlines()
    i = 0
    while i < len(lines):
        line = lines[i]
        if line.startswith("```"):
            block = []
            i += 1
            while i < len(lines) and not lines[i].startswith("```"):
                block.append(lines[i])
                i += 1
            run = doc.add_paragraph().add_run("\n".join(block))
            run.font.name = "Consolas"
            run.font.size = Pt(9.5)
        elif line.startswith("|"):
            rows = []
            while i < len(lines) and lines[i].startswith("|"):
                if not re.match(r"^\|[\s:|-]+\|\s*$", lines[i]):  # skip the |---| separator
                    rows.append(cells(lines[i]))
                i += 1
            i -= 1
            width = max(len(r) for r in rows)
            table = doc.add_table(rows=len(rows), cols=width)
            table.style = "Table Grid"
            for r, row in enumerate(rows):
                for c, text in enumerate(row):
                    par = table.cell(r, c).paragraphs[0]
                    add_runs(par, text)
                    for run in par.runs:
                        run.font.size = Pt(9.5)
                    if r == 0:
                        for run in par.runs:
                            run.bold = True
        elif m := re.match(r"^(#{1,3})\s+(.*)", line):
            doc.add_heading(m[2], level=len(m[1]) - 1 if len(m[1]) > 1 else 0)
        elif m := re.match(r"^\s*- \[ \]\s+(.*)", line):
            add_runs(doc.add_paragraph(style="List Bullet"), "☐ " + m[1])
        elif m := re.match(r"^\s*[-*]\s+(.*)", line):
            add_runs(doc.add_paragraph(style="List Bullet"), m[1])
        elif m := re.match(r"^\s*\d+\.\s+(.*)", line):
            add_runs(doc.add_paragraph(style="List Number"), m[1])
        elif line.strip() and line.strip() != "---":
            add_runs(doc.add_paragraph(), line.strip())
        i += 1
    doc.save(out_path)
    return doc


def words(md_text):
    return len(re.findall(r"[A-Za-z0-9][\w'’.-]*", re.sub(r"^\|[\s:|-]+\|\s*$", "", md_text, flags=re.M)))


def to_pdf(docx_path):
    """Write the PDF next to the docx. Returns (pdf path, page count or None); pdf path is None on failure."""
    docx_path = Path(docx_path).resolve()
    pdf = docx_path.with_suffix(".pdf")
    pages = None
    if sys.platform == "win32":
        q = lambda p: str(p).replace("'", "''")  # PowerShell single-quote escape
        ps = (f"$w = New-Object -ComObject Word.Application; $w.Visible = $false; "
              f"$d = $w.Documents.Open('{q(docx_path)}', $false, $true); "
              f"Write-Output ('pages=' + $d.ComputeStatistics(2)); $d.SaveAs2('{q(pdf)}', 17); "
              f"try {{ $d.Close(0) }} catch {{}}; try {{ $w.Quit() }} catch {{}}")
        r = subprocess.run(["powershell", "-NoProfile", "-Command", ps], capture_output=True, text=True)
        if m := re.search(r"pages=(\d+)", r.stdout):
            pages = int(m[1])
    else:
        subprocess.run(["soffice", "--headless", "--convert-to", "pdf", "--outdir", str(pdf.parent), str(docx_path)],
                       capture_output=True)
    return (pdf if pdf.exists() else None), pages


def selfcheck():
    example = Path(__file__).parent / "reference" / "mek-charge-reconciliation.md"
    sop = "# " + example.read_text(encoding="utf-8").split("\n---\n", 1)[1].split("\n# ", 1)[1]
    out = Path(tempfile.mkdtemp()) / "HANDOVER-SOP.docx"
    convert(sop, out)
    doc = Document(out)
    heads = [p.text for p in doc.paragraphs if p.style.name.startswith("Heading")]
    assert doc.paragraphs[0].text.endswith("Handover SOP"), doc.paragraphs[0].text
    assert [h.split(".")[0] for h in heads if h[:1].isdigit()] == [str(n) for n in range(1, 6)], heads
    assert len(doc.tables) >= 4, len(doc.tables)
    assert doc.tables[0].cell(0, 0).text == "Where on the screen", doc.tables[0].cell(0, 0).text
    assert not any("**" in p.text or "|---" in p.text for p in doc.paragraphs)
    assert words(sop) <= MAX_WORDS, words(sop)
    print(f"selfcheck ok: {len(heads)} headings, {len(doc.tables)} tables, {words(sop)} words -> {out}")


if __name__ == "__main__":
    ap = argparse.ArgumentParser()
    ap.add_argument("md", nargs="?")
    ap.add_argument("-o", "--out")
    ap.add_argument("--pdf", action="store_true", help="also write the PDF next to the docx")
    ap.add_argument("--selfcheck", action="store_true")
    a = ap.parse_args()
    if a.selfcheck:
        selfcheck()
        sys.exit(0)
    if not a.md:
        ap.error("give the HANDOVER.md path, or --selfcheck")
    src = Path(a.md)
    out = Path(a.out) if a.out else src.with_suffix(".docx")
    text = src.read_text(encoding="utf-8")
    convert(text, out)
    n = words(text)
    print(f"wrote {out} ({n} words{'' if n <= MAX_WORDS else f', OVER the {MAX_WORDS}-word limit: cut it'})")
    if a.pdf:
        pdf, pages = to_pdf(out)
        if not pdf:
            sys.exit("no PDF: needs Word (Windows) or LibreOffice (soffice). Hand over the docx instead.")
        over = pages and pages > MAX_PAGES
        print(f"wrote {pdf} ({pages or '?'} pages{f', OVER the {MAX_PAGES}-page limit: cut it' if over else ''})")