#!/usr/bin/env python3
"""The manual as a PDF, and as an EPUB: the downloads the page links to.

    python3 tools/manual/pdf.py docs/manual out.pdf [out.epub]

The PDF is docs/manual/index.html through its print stylesheet; the EPUB is
README.md through pandoc, which reads Markdown better than a page. Needs
WeasyPrint (and so Pillow), and pandoc for the EPUB. The Manual pages
workflow runs this and publishes both beside the page.

The page's pictures are PNG screenshots and GIF recordings, 16 MB and 46 MB
of them, and WeasyPrint and pandoc embed a picture as they find it:
losslessly, a GIF whole (63 MB of EPUB, for e-readers that mostly do not
animate). So both are made from copies whose pictures are JPEGs
(a recording's first frame, which is all a page can show) at the size they
were recorded. Full chroma, because a 4:2:0 JPEG smears the coloured noise
the AI denoise close-ups exist to show.
"""
import os
import re
import shutil
import subprocess
import sys
import tempfile

from PIL import Image
from weasyprint import HTML

QUALITY = 88


def as_jpeg(src, dst):
    with Image.open(src) as im:
        im.seek(0)
        im.convert('RGB').save(dst, 'JPEG', quality=QUALITY, subsampling=0, optimize=True)


def main(manual_dir, pdf, epub=None):
    with tempfile.TemporaryDirectory() as tmp:
        os.mkdir(os.path.join(tmp, 'media'))
        renamed = {}
        for name in sorted(os.listdir(os.path.join(manual_dir, 'media'))):
            stem, ext = os.path.splitext(name)
            if ext.lower() not in ('.png', '.gif'):
                continue
            jpg = f'{stem}.{ext[1:].lower()}.jpg'   # two pictures may share a stem
            as_jpeg(os.path.join(manual_dir, 'media', name), os.path.join(tmp, 'media', jpg))
            renamed[name] = jpg

        def copy(source, pattern, out):
            text = open(os.path.join(manual_dir, source), encoding='utf-8').read()
            text = re.sub(pattern, lambda m: m.group(1) + renamed.get(m.group(2), m.group(2)), text)
            with open(os.path.join(tmp, out), 'w', encoding='utf-8') as f:
                f.write(text)
            return os.path.join(tmp, out)

        page = copy('index.html', r'(src="media/)([^"]+)', 'index.html')
        HTML(page).write_pdf(os.path.join(tmp, 'manual.pdf'))
        shutil.move(os.path.join(tmp, 'manual.pdf'), pdf)

        if epub:
            md = copy('README.md', r'(\]\(media/)([^)\s]+)', 'README.md')
            title = next(l[2:].strip() for l in open(md, encoding='utf-8') if l.startswith('# '))
            subprocess.run(['pandoc', 'README.md', '-o', 'manual.epub', '--metadata', f'title={title}',
                            '--toc', '--toc-depth=2', '--epub-chapter-level=2'], cwd=tmp, check=True)
            shutil.move(os.path.join(tmp, 'manual.epub'), epub)


if __name__ == '__main__':
    if len(sys.argv) not in (3, 4):
        sys.exit(__doc__)
    main(*sys.argv[1:])