lib/utils.py

import unicodedata
import re
import time
import random
import string
from datetime import datetime


def normalize_text(value: str) -> str:
    """Normalize text: remove accents, lowercase, trim."""
    if not value:
        return ""
    text = str(value)
    text = unicodedata.normalize("NFD", text)
    text = re.sub(r"[\u0300-\u036f]", "", text)
    text = text.replace("\u0111", "d").replace("\u0110", "D")
    return text.strip().lower()


def slugify(value: str) -> str:
    """Convert to slug: no accents, lowercase, underscores."""
    if not value:
        return ""
    text = normalize_text(value)
    text = re.sub(r"[^a-z0-9\s_]", "", text)
    text = text.strip()
    text = re.sub(r"\s+", "_", text)
    return text


def remove_accents(value: str) -> str:
    """Remove Vietnamese accents but keep case."""
    if not value:
        return ""
    text = str(value)
    text = unicodedata.normalize("NFD", text)
    text = re.sub(r"[\u0300-\u036f]", "", text)
    text = text.replace("\u0111", "d").replace("\u0110", "D")
    return text


def safe_filename(raw_name: str) -> str:
    """Make a safe filename from raw text."""
    base = remove_accents(raw_name or "file")
    base = re.sub(r"[^a-zA-Z0-9._ -]", "", base)
    base = re.sub(r"\s+", " ", base).strip()
    return base or "file"


def make_id(prefix: str = "id") -> str:
    ts = int(time.time() * 1000)
    rand = "".join(random.choices(string.ascii_lowercase + string.digits, k=6))
    return f"{prefix}_{ts}_{rand}"


def format_timestamp() -> str:
    now = datetime.now()
    return now.strftime("%d/%m/%Y %H:%M:%S")


def now_iso() -> str:
    return datetime.utcnow().isoformat() + "Z"


def sanitize_field_type(field_type: str) -> str:
    norm = normalize_text(field_type or "")
    if norm == "number":
        return "number"
    if norm == "none":
        return "none"
    return "text"