import re
import requests
from bs4 import BeautifulSoup

GIT_BASE = 'http://git.nowherejezfoltodf4jiyl6r56jnzintap5vyjlia7fkirfsnfizflqd.onion/nihilist/blog-contributions'
PROXIES = {'http': 'socks5h://127.0.0.1:9050'}
PATTERN = re.compile(r'<a[^>]*href="' + GIT_BASE + r'/issues/(?P<issue_id>\d+)"[^>]*>(?P<symbol>[✅❌🚧])', re.DOTALL)

# makes HTTP request to the git page of given issue
# retrieves the labels and returns them as dictionary
def check_issue_labels(iid: int) -> dict[str, bool]:
    r = requests.get(GIT_BASE+f'/issues/{iid}', proxies=PROXIES)

    soup = BeautifulSoup(r.content, "html.parser")

    # find the labels list element in html
    labels_span = soup.find('span', class_='labels-list ugc-labels')

    result_dict = {}

    if labels_span:
        anchors = labels_span.find_all("a", class_="item")

        for anchor in anchors:
            label_text = anchor.find('div', class_='ui label').get_text(strip=True)
            # if label has 'tw-hidden' class, it means it's not present
            result_dict[label_text] = "tw-hidden" not in anchor['class']

    return result_dict

# if there're no labels, the blog is done
def is_done_by_labels(labels: dict[str, bool]) -> bool:
    return not any(labels.values())

f = open('opsec/index.html')
html_content = f.read()
f.close()

# used for changing the symbols
scratch_hc = list(html_content)

# iterate over found git issue references
for match in PATTERN.finditer(html_content):
    issue_id = match.group('issue_id')
    symbol_offset = match.start('symbol')
    
    print(f"Issue ID: {issue_id}\tSymbol Offset: {symbol_offset}\tCurrent: {html_content[symbol_offset]}\t", end='')
    
    issue_labels = check_issue_labels(issue_id)
    is_done = is_done_by_labels(issue_labels)
    symbol = '✅' if is_done else '❌'
    print(f"Determined: {symbol}")
    
    scratch_hc[symbol_offset] = symbol

fo = open('opsec/index.autogen.html', 'w', encoding='utf-8')
fo.write(''.join(scratch_hc))
fo.close()