#!/usr/bin/env python3
"""Преобразование Markdown в PDF через ReportLab."""
from __future__ import annotations
import argparse
import html
import os
import re
import sys
import tempfile
from pathlib import Path
from reportlab.lib import colors
from reportlab.lib.pagesizes import A4
from reportlab.lib.styles import ParagraphStyle, getSampleStyleSheet
from reportlab.lib.units import mm
from reportlab.pdfbase import pdfmetrics
from reportlab.pdfbase.ttfonts import TTFont
from reportlab.platypus import HRFlowable, Paragraph, Preformatted, SimpleDocTemplate, Spacer, Table, TableStyle
FENCE = re.compile(r"^\s*(```|~~~)")
HEADING = re.compile(r"^(#{1,6})\s+(.*)$")
BULLET = re.compile(r"^\s*[-*+]\s+(.*)$")
NUMBERED = re.compile(r"^\s*\d+[.)]\s+(.*)$")
FONT_CANDIDATES = [
("/usr/share/fonts/truetype/dejavu/DejaVuSans.ttf", "/usr/share/fonts/truetype/dejavu/DejaVuSans-Bold.ttf"),
("/usr/share/fonts/TTF/DejaVuSans.ttf", "/usr/share/fonts/TTF/DejaVuSans-Bold.ttf"),
("C:/Windows/Fonts/arial.ttf", "C:/Windows/Fonts/arialbd.ttf"),
("/System/Library/Fonts/Supplemental/Arial.ttf", "/System/Library/Fonts/Supplemental/Arial Bold.ttf"),
("/Library/Fonts/DejaVuSans.ttf", "/Library/Fonts/DejaVuSans-Bold.ttf"),
]
def register_font(custom: str | None) -> str:
normal = bold = None
if custom:
normal = custom
candidate = Path(custom).with_name(Path(custom).stem + "-Bold" + Path(custom).suffix)
bold = str(candidate) if candidate.exists() else custom
else:
for regular, strong in FONT_CANDIDATES:
if Path(regular).exists():
normal = regular
bold = strong if Path(strong).exists() else regular
break
if not normal:
raise SystemExit("Не найден шрифт с кириллицей. Укажите --font path/to/font.ttf")
pdfmetrics.registerFont(TTFont("TextFont", normal))
pdfmetrics.registerFont(TTFont("TextFontBold", bold))
pdfmetrics.registerFontFamily("TextFont", normal="TextFont", bold="TextFontBold", italic="TextFont", boldItalic="TextFontBold")
return "TextFont"
def inline(text: str) -> str:
text = html.escape(text, quote=False)
text = re.sub(r"!\[([^\]]*)\]\([^)]+\)", r"\1", text)
def link_replacement(match: re.Match[str]) -> str:
label, url = match.group(1), match.group(2)
if re.match(r"https?://", url):
return f'{label}'
return label
text = re.sub(r"\[([^\]]+)\]\(([^)]+)\)", link_replacement, text)
text = re.sub(r"\*\*(.+?)\*\*", r"\1", text)
text = re.sub(r"__(.+?)__", r"\1", text)
text = re.sub(r"(?\1", text)
text = re.sub(r"`([^`]+)`", r'\1', text)
return text
def make_styles(font: str):
base = getSampleStyleSheet()
body = ParagraphStyle("Body", parent=base["BodyText"], fontName=font, fontSize=10.5, leading=15, spaceAfter=6)
title = ParagraphStyle("H1x", parent=body, fontSize=20, leading=24, spaceBefore=12, spaceAfter=10)
h2 = ParagraphStyle("H2x", parent=body, fontSize=16, leading=20, spaceBefore=12, spaceAfter=8)
h3 = ParagraphStyle("H3x", parent=body, fontSize=13, leading=17, spaceBefore=10, spaceAfter=6)
quote = ParagraphStyle("QuoteX", parent=body, leftIndent=14, textColor=colors.HexColor("#444444"), fontSize=10)
item = ParagraphStyle("ItemX", parent=body, leftIndent=14, bulletIndent=4, spaceAfter=3)
code = ParagraphStyle("CodeX", parent=body, fontName=font, fontSize=8.5, leading=11, backColor=colors.HexColor("#f3f4f6"), borderPadding=6, spaceAfter=8)
cell = ParagraphStyle("CellX", parent=body, fontSize=9, leading=12, spaceAfter=0)
return body, title, h2, h3, quote, item, code, cell
def build_table(rows: list[list[str]], cell_style, available: float) -> Table:
width = max(len(row) for row in rows)
data = []
for row in rows:
cells = [Paragraph(inline(row[index]) if index < len(row) else "", cell_style) for index in range(width)]
data.append(cells)
table = Table(data, colWidths=[available / width] * width, repeatRows=1)
table.setStyle(TableStyle([
("GRID", (0, 0), (-1, -1), 0.4, colors.HexColor("#999999")),
("BACKGROUND", (0, 0), (-1, 0), colors.HexColor("#e5e7eb")),
("VALIGN", (0, 0), (-1, -1), "TOP"),
]))
return table
def convert(source: Path, target: Path, title: str | None, custom_font: str | None) -> None:
font = register_font(custom_font)
body, h1, h2, h3, quote, item, code, cell = make_styles(font)
text = source.read_text(encoding="utf-8")
available = A4[0] - 36 * mm
story = []
lines = text.splitlines()
index = 0
paragraph: list[str] = []
def flush() -> None:
if paragraph:
story.append(Paragraph(inline(" ".join(part.strip() for part in paragraph)), body))
paragraph.clear()
while index < len(lines):
line = lines[index]
stripped = line.strip()
if FENCE.match(line):
flush()
index += 1
code_lines = []
while index < len(lines) and not FENCE.match(lines[index]):
code_lines.append(lines[index])
index += 1
story.append(Preformatted("\n".join(code_lines), code))
index += 1
continue
if not stripped:
flush()
index += 1
continue
heading = HEADING.match(line)
if heading:
flush()
level = len(heading.group(1))
style = h1 if level == 1 else h2 if level == 2 else h3
story.append(Paragraph(inline(heading.group(2).strip()), style))
index += 1
continue
if stripped in ("---", "***", "___"):
flush()
story.append(HRFlowable(width="100%", thickness=0.6, color=colors.HexColor("#999999"), spaceBefore=6, spaceAfter=8))
index += 1
continue
if stripped.startswith(">"):
flush()
quote_lines = []
while index < len(lines) and lines[index].strip().startswith(">"):
quote_lines.append(lines[index].strip()[1:].strip())
index += 1
story.append(Paragraph(inline(" ".join(quote_lines)), quote))
continue
bullet = BULLET.match(line)
if bullet:
flush()
story.append(Paragraph(inline(bullet.group(1)), item, bulletText="-"))
index += 1
continue
numbered = NUMBERED.match(line)
if numbered:
flush()
story.append(Paragraph(inline(numbered.group(1)), item, bulletText="1."))
index += 1
continue
if stripped.startswith("|") and stripped.endswith("|"):
flush()
rows = []
while index < len(lines):
candidate = lines[index].strip()
if not (candidate.startswith("|") and candidate.endswith("|")):
break
cells = [value.strip() for value in candidate.strip("|").split("|")]
if all(re.fullmatch(r":?-{3,}:?", value) for value in cells):
index += 1
continue
rows.append(cells)
index += 1
if rows:
story.append(build_table(rows, cell, available))
story.append(Spacer(1, 6))
continue
paragraph.append(line)
index += 1
flush()
if not story:
story.append(Paragraph("", body))
document = SimpleDocTemplate(
str(target),
pagesize=A4,
leftMargin=18 * mm,
rightMargin=18 * mm,
topMargin=18 * mm,
bottomMargin=18 * mm,
title=title or source.stem,
)
document.build(story)
def main() -> int:
parser = argparse.ArgumentParser(description="Собрать PDF из Markdown")
parser.add_argument("input", type=Path, help="Markdown-файл")
parser.add_argument("--output", type=Path, help="Куда сохранить PDF")
parser.add_argument("--title", help="Заголовок документа")
parser.add_argument("--font", help="Путь к TTF-шрифту с кириллицей")
parser.add_argument("--force", action="store_true", help="Перезаписать PDF")
args = parser.parse_args()
source = args.input.expanduser()
if not source.is_file():
parser.error(f"Файл не найден: {source}")
target = args.output.expanduser() if args.output else source.with_suffix(".pdf")
if target.resolve() == source.resolve():
parser.error("PDF не должен совпадать с входным Markdown")
if target.exists() and not args.force:
parser.error(f"Файл уже существует: {target}. Добавьте --force")
target.parent.mkdir(parents=True, exist_ok=True)
descriptor, temporary = tempfile.mkstemp(prefix="pdf-", suffix=".pdf", dir=str(target.parent))
os.close(descriptor)
temporary_path = Path(temporary)
try:
convert(source, temporary_path, args.title, args.font)
os.replace(temporary_path, target)
except Exception as error:
temporary_path.unlink(missing_ok=True)
print(f"Ошибка сборки PDF: {error}", file=sys.stderr)
return 1
print(f"PDF сохранён: {target}")
return 0
if __name__ == "__main__":
raise SystemExit(main())