gen_blog.py

#!/usr/bin/env nix-shell
#! nix-shell -i python3 -p python3.pkgs.mistune

#            DO WHAT THE FUCK YOU WANT TO PUBLIC LICENSE
#                    Version 2, December 2004
#
# Copyright (C) 2024 Thiago Kenji Okada <thiagokokada@gmail.com>
#
# Everyone is permitted to copy and distribute verbatim or modified
# copies of this license document, and changing it is allowed as long
# as the name is changed.
#
#            DO WHAT THE FUCK YOU WANT TO PUBLIC LICENSE
#   TERMS AND CONDITIONS FOR COPYING, DISTRIBUTION AND MODIFICATION
#
#  0. You just DO WHAT THE FUCK YOU WANT TO.

"""\
Usage: gen_blog.py

Needs to be run at the root directory of the repository.

Will output the generated README.md file to the stdout, you can redirect its
contents by:

  $ ./gen_blog.py > README.md

Will also generate the RSS file in `rss.xml`.\
"""

import os
import re
import sys
import xml.etree.cElementTree as ET
from collections import defaultdict
from dataclasses import dataclass
from datetime import datetime
from pathlib import Path
from urllib.parse import urljoin
from typing import Optional

try:
    import mistune
except ImportError:
    print(
        "WARN: mistune not available, markdown contents is unavailable", file=sys.stderr
    )
    mistune = None


README_TEMPLATE = """\
# Blog

Mirror of my blog in https://kokada.capivaras.dev/.

## Posts

[![RSS](https://img.shields.io/badge/RSS-FFA562?style=for-the-badge&logo=rss&logoColor=white)](https://raw.githubusercontent.com/thiagokokada/blog/main/rss.xml)

{posts}\
"""
RSS_TITLE = "kokada's blog"
RSS_LINK = "https://github.com/thiagokokada/blog"
RSS_DESCRIPTION = "dd if=/dev/urandom of=/dev/brain0"
RSS_POST_LINK_PREFIX = f"{RSS_LINK}/blob/main/"


@dataclass
class Post:
    title: str
    file: str
    contents: Optional[str] = None


Posts = dict[datetime, list[Post]]


def grab_posts(pwd: Path) -> Posts:
    posts = defaultdict(list)

    for dir in sorted(pwd.iterdir(), reverse=True):
        # Ignore non-directories or hidden files
        if not dir.is_dir() or dir.name[0] == ".":
            continue

        # Try to parse date from directory name
        try:
            date = datetime.strptime(dir.name, "%Y-%m-%d")
        except ValueError:
            print(f"WARN: ignoring non-date directory: {dir}", file=sys.stderr)
            continue

        # Iterate between the files in the date directory
        for dateDir in sorted(dir.iterdir(), reverse=True):
            # Ignore non-markdown files or hidden files (draft)
            if not dateDir.suffix == ".md" or dateDir.name[0] == ".":
                continue

            # Grab the first H1 section to parse as title
            text = dateDir.read_text()
            mTitle = re.match(r"# (?P<title>.*)\r?\n", text)
            if mTitle and (title := mTitle.groupdict().get("title")):
                post = Post(title=title, file=str(dateDir))
                if mistune:
                    post.contents = mistune.html(text)
                posts[date].append(post)
            else:
                print(f"WARN: did not find title for file: {post}", file=sys.stderr)

    return posts


def gen_readme(posts: Posts):
    titles = []

    for date, dayPosts in posts.items():
        for post in dayPosts:
            link = os.path.join(".", post.file)  # to format as ./{filepath}
            title = date.strftime(f"- [{post.title}]({link}) - %Y-%m-%d")
            titles.append(title)

    print(README_TEMPLATE.format(posts="\n".join(titles)))


def gen_rss(posts: Posts):
    rss = ET.Element("rss", version="2.0")

    channel = ET.SubElement(rss, "channel")
    ET.SubElement(channel, "title").text = RSS_TITLE
    ET.SubElement(channel, "link").text = RSS_LINK
    ET.SubElement(channel, "description").text = RSS_DESCRIPTION

    for date, dayPost in posts.items():
        for post in dayPost:
            item = ET.SubElement(channel, "item")
            link = urljoin(RSS_POST_LINK_PREFIX, post.file)
            ET.SubElement(item, "title").text = post.title
            ET.SubElement(item, "guid").text = link
            ET.SubElement(item, "description").text = post.contents
            ET.SubElement(item, "link").text = link
            ET.SubElement(item, "pubDate").text = date.strftime(
                "%a, %d %b %Y %H:%M:%S GMT"
            )

    tree = ET.ElementTree(rss)
    ET.indent(tree, space="\t", level=0)
    tree.write("rss.xml", xml_declaration=True, encoding="UTF-8")


def main():
    if "-h" in sys.argv:
        print(__doc__, file=sys.stderr)
        sys.exit(0)
    posts = grab_posts(Path())
    gen_readme(posts)
    gen_rss(posts)


if __name__ == "__main__":
    main()