Pier_v1/Code/교각모델링/md_to_pdf.py

"""Render a project Markdown report (headings, tables, bullets, quotes) to an A4 PDF with Korean fonts.

usage: python md_to_pdf.py <input.md> <output.pdf> [header text]
The .md file stays the canonical document; the PDF is a rendition of it.
"""
import re
import sys
from pathlib import Path

from reportlab.lib import colors
from reportlab.lib.enums import TA_LEFT
from reportlab.lib.pagesizes import A4
from reportlab.lib.styles import ParagraphStyle
from reportlab.lib.units import mm
from reportlab.pdfbase import pdfmetrics
from reportlab.pdfbase.ttfonts import TTFont
from reportlab.platypus import (HRFlowable, KeepTogether, Paragraph, SimpleDocTemplate, Spacer, Table,
                                TableStyle)

pdfmetrics.registerFont(TTFont("Malgun", r"C:\Windows\Fonts\malgun.ttf"))
pdfmetrics.registerFont(TTFont("MalgunBd", r"C:\Windows\Fonts\malgunbd.ttf"))
pdfmetrics.registerFontFamily("Malgun", normal="Malgun", bold="MalgunBd", italic="Malgun", boldItalic="MalgunBd")

BASE = ParagraphStyle("base", fontName="Malgun", fontSize=9, leading=13, alignment=TA_LEFT)
ST = {
    "h1": ParagraphStyle("h1", parent=BASE, fontName="MalgunBd", fontSize=15, leading=20, spaceAfter=6),
    "h2": ParagraphStyle("h2", parent=BASE, fontName="MalgunBd", fontSize=12, leading=16, spaceBefore=10, spaceAfter=4),
    "h3": ParagraphStyle("h3", parent=BASE, fontName="MalgunBd", fontSize=10, leading=14, spaceBefore=6, spaceAfter=3),
    "p": BASE,
    "quote": ParagraphStyle("q", parent=BASE, leftIndent=8, textColor=colors.HexColor("#444444"),
                            backColor=colors.HexColor("#F2F2F2"), borderPadding=4, spaceBefore=4, spaceAfter=4),
    "li": ParagraphStyle("li", parent=BASE, leftIndent=12, bulletIndent=4),
    "li2": ParagraphStyle("li2", parent=BASE, leftIndent=24, bulletIndent=16),
    "cell": ParagraphStyle("cell", parent=BASE, fontSize=7.5, leading=10),
    "cellh": ParagraphStyle("cellh", parent=BASE, fontName="MalgunBd", fontSize=7.5, leading=10),
}
WIDTH = A4[0] - 30 * mm


def inline(text):
    text = text.replace("−", "-")          # Malgun Gothic has no U+2212 minus glyph (renders blank)
    text = text.replace("&", "&amp;").replace("<", "&lt;").replace(">", "&gt;")
    text = re.sub(r"\*\*(.+?)\*\*", r"<b>\1</b>", text)
    text = re.sub(r"`(.+?)`", r'<font color="#7A3E00">\1</font>', text)
    text = re.sub(r"~~(.+?)~~", r"<strike>\1</strike>", text)
    return text


def table(lines):
    rows = [[c.strip() for c in l.strip().strip("|").split("|")] for l in lines]
    rows = [r for r in rows if not all(re.fullmatch(r":?-{2,}:?", c) for c in r if c)]
    n = max(len(r) for r in rows)
    rows = [r + [""] * (n - len(r)) for r in rows]
    # minimum width = longest unbreakable token (so short codes like 'E-01' or '오류' never wrap per glyph),
    # the remaining width is shared in proportion to text length
    from reportlab.pdfbase.pdfmetrics import stringWidth
    plain = lambda c: re.sub(r"[*`~]", "", c)
    mins = [max(stringWidth(tok, "MalgunBd", 7.5) for r in rows for tok in (plain(r[i]).split() or [""])) + 8
            for i in range(n)]
    mins = [min(m, WIDTH * 0.3) for m in mins]
    weights = [max(min(len(r[i]), 60) for r in rows) + 2 for i in range(n)]
    spare = max(WIDTH - sum(mins), 0)
    widths = [m + spare * w / sum(weights) for m, w in zip(mins, weights)]
    if sum(widths) > WIDTH:
        widths = [w * WIDTH / sum(widths) for w in widths]
    data = [[Paragraph(inline(c), ST["cellh"] if k == 0 else ST["cell"]) for c in r] for k, r in enumerate(rows)]
    t = Table(data, colWidths=widths, repeatRows=1)
    t.setStyle(TableStyle([
        ("GRID", (0, 0), (-1, -1), 0.4, colors.HexColor("#999999")),
        ("BACKGROUND", (0, 0), (-1, 0), colors.HexColor("#E6E6E6")),
        ("VALIGN", (0, 0), (-1, -1), "TOP"),
        ("LEFTPADDING", (0, 0), (-1, -1), 3), ("RIGHTPADDING", (0, 0), (-1, -1), 3),
    ]))
    return t


def build(md, out, header):
    lines = md.splitlines()
    story, i = [], 0
    while i < len(lines):
        l = lines[i]
        if l.startswith("|"):
            block = []
            while i < len(lines) and lines[i].startswith("|"):
                block.append(lines[i])
                i += 1
            story += [table(block), Spacer(1, 4)]
            continue
        if l.startswith("### "):
            story.append(Paragraph(inline(l[4:]), ST["h3"]))
        elif l.startswith("## "):
            story.append(Paragraph(inline(l[3:]), ST["h2"]))
        elif l.startswith("# "):
            story.append(Paragraph(inline(l[2:]), ST["h1"]))
        elif l.startswith(">"):
            story.append(Paragraph(inline(l.lstrip("> ")), ST["quote"]))
        elif re.match(r"^\s{2,}- ", l):
            story.append(Paragraph(inline(l.strip()[2:]), ST["li2"], bulletText="–"))
        elif l.startswith("- "):
            story.append(Paragraph(inline(l[2:]), ST["li"], bulletText="•"))
        elif l.strip() == "---":
            story.append(HRFlowable(width="100%", thickness=0.5, color=colors.HexColor("#BBBBBB"), spaceBefore=4,
                                    spaceAfter=4))
        elif l.strip():
            story.append(Paragraph(inline(l), ST["p"]))
        i += 1

    def deco(c, d):
        c.saveState()
        c.setFont("Malgun", 7.5)
        c.setFillColor(colors.HexColor("#666666"))
        c.drawString(15 * mm, A4[1] - 10 * mm, header)
        c.drawRightString(A4[0] - 15 * mm, 10 * mm, f"{d.page}")
        c.restoreState()

    doc = SimpleDocTemplate(str(out), pagesize=A4, leftMargin=15 * mm, rightMargin=15 * mm, topMargin=16 * mm,
                            bottomMargin=16 * mm, title=Path(out).stem, author="심영표")
    doc.build(story, onFirstPage=deco, onLaterPages=deco)


if __name__ == "__main__":
    src, dst = Path(sys.argv[1]), Path(sys.argv[2])
    hdr = sys.argv[3] if len(sys.argv) > 3 else src.stem
    build(src.read_text(encoding="utf-8"), dst, hdr)
    print(dst, dst.stat().st_size)