KudoBot / bot /utils.py
saske560's picture
Upload 9 files
337aa19 verified
Raw History Blame Contribute Delete
3.97 kB
from __future__ import annotations
import hashlib
import html
import re
import unicodedata
from datetime import datetime, timezone
from difflib import SequenceMatcher
from typing import Iterable, List
COMMON_STOPWORDS = {
"the", "a", "an", "de", "del", "la", "el", "los", "las", "y", "en", "por", "para", "con",
"temporada", "season", "capitulo", "capítulo", "episodio", "episode", "parte", "part", "sub",
"espanol", "español", "latino", "castellano", "dual", "audio", "pelicula", "movie", "serie", "series",
}
def utc_now() -> datetime:
return datetime.now(timezone.utc)
def iso_now() -> str:
return utc_now().isoformat()
def today_key() -> str:
return utc_now().date().isoformat()
def safe_html(text: str | None) -> str:
return html.escape(text or "")
def normalize_text(text: str | None) -> str:
text = text or ""
text = unicodedata.normalize("NFKD", text)
text = "".join(ch for ch in text if not unicodedata.combining(ch))
text = text.lower()
text = re.sub(r"\.(mkv|mp4|avi|mov|m4v|ts|webm|srt|ass|mka|zip|rar)$", "", text)
text = re.sub(r"[^a-z0-9]+", " ", text)
text = re.sub(r"\s+", " ", text).strip()
return text
def tokenize(text: str | None) -> List[str]:
norm = normalize_text(text)
tokens = [t for t in norm.split() if t and t not in COMMON_STOPWORDS]
return tokens
def compact_title(text: str | None) -> str:
if not text:
return "Sin título"
clean = re.sub(r"\s+", " ", text).strip(" -_\n\t")
return clean[:1].upper() + clean[1:] if clean else "Sin título"
def short_text(text: str | None, limit: int = 280) -> str:
if not text:
return ""
clean = " ".join((text or "").split())
return clean if len(clean) <= limit else clean[: limit - 1].rstrip() + "…"
def to_item_id(chat_id: int, message_id: int) -> str:
return hashlib.sha1(f"{chat_id}:{message_id}".encode("utf-8")).hexdigest()[:18]
def chunked(items: Iterable, size: int):
bucket = []
for item in items:
bucket.append(item)
if len(bucket) >= size:
yield bucket
bucket = []
if bucket:
yield bucket
def parse_bool(value: str | None) -> bool:
return (value or "").strip().lower() in {"1", "true", "yes", "on", "si", "sí"}
def human_size(value: int | None) -> str:
if not value:
return "0 B"
suffixes = ["B", "KB", "MB", "GB", "TB"]
num = float(value)
idx = 0
while num >= 1024 and idx < len(suffixes) - 1:
num /= 1024
idx += 1
if idx == 0:
return f"{int(num)} {suffixes[idx]}"
return f"{num:.1f} {suffixes[idx]}"
def human_duration(seconds: int | None) -> str:
if not seconds:
return "—"
h, r = divmod(int(seconds), 3600)
m, s = divmod(r, 60)
if h:
return f"{h}:{m:02d}:{s:02d}"
return f"{m}:{s:02d}"
def similarity(a: str, b: str) -> float:
if not a or not b:
return 0.0
return SequenceMatcher(None, normalize_text(a), normalize_text(b)).ratio()
def score_match(query: str, text: str, title: str) -> float:
q_norm = normalize_text(query)
t_norm = normalize_text(text)
title_norm = normalize_text(title)
q_tokens = set(tokenize(query))
t_tokens = set(tokenize(text))
score = 0.0
if not q_norm:
return 0.0
if q_norm == title_norm:
score += 200
if q_norm in title_norm:
score += 120
if q_norm in t_norm:
score += 80
common = q_tokens & t_tokens
score += len(common) * 18
score += similarity(query, title) * 70
score += similarity(query, text) * 25
return score
def format_expiry(value: str | None) -> str:
if not value:
return "—"
try:
dt = datetime.fromisoformat(value)
if dt.tzinfo is None:
dt = dt.replace(tzinfo=timezone.utc)
return dt.astimezone().strftime("%d/%m/%Y %H:%M")
except ValueError:
return value