mjestecko/tools/article_utils.py

import time, subprocess
from os import walk, path
import urllib.parse

def the_line_after_metadata(lines: []) -> int:
    i = 0
    while i < len(lines) and lines[i].strip():
        i += 1
    return i

def parse_metadata(filepath: str) -> {}:
    result = {}
    with open(filepath, "r") as f:
        content = f.readlines()
        i = the_line_after_metadata(content)

    for line in content[:i]:
        delim = line.find(":")
        key, val = (line[:delim].strip(), line[delim+1:].strip())
        if key == "Date":
            result["Date"] = time.gmtime(int(val))
        elif key == "Tags":
            result["Tags"] = [v.strip() for v in val.split(",")]
        elif val:
            result[key] = val
        result["Last Edit"] = time.gmtime(int(subprocess.getoutput(r"stat -c %Y " + filepath)))

    return result

def parse_article_directory(directory: str) -> {}:
    articles = {}
    for root, dirs, _ in walk(directory):
        for d in dirs:
            metadata = parse_metadata(path.abspath(root + '/' + d + "/page.mmd"))
            article = urllib.parse.quote(d)
            articles[article] = {
                "metadata": metadata
            }
        break
    return articles

def sort_titles_by_date(articles: {}) -> []:
    return sorted(articles.keys(), key=lambda a: articles[a]["metadata"].get("Date", time.gmtime(0)), reverse=True)