utils.py

"""
utils.py
Common helper functions
"""

from __future__ import annotations

import hashlib
from pathlib import Path
from typing import Iterable

from config import (
    CHARS_PER_TOKEN,
    LANGUAGE_MAP,
)


def estimate_tokens(text: str) -> int:
    """
    Rough token estimation.
    """
    return max(1, int(len(text) / CHARS_PER_TOKEN))


def short_sha256(text: str) -> str:
    """
    First 12 chars of sha256.
    """
    return hashlib.sha256(
        text.encode("utf-8", errors="ignore")
    ).hexdigest()[:12]


def xml_safe(text: str) -> str:
    """
    Prevent CDATA termination.
    """
    return text.replace("]]>", "]]]]><![CDATA[>")


def language_from_extension(ext: str) -> str:
    return LANGUAGE_MAP.get(
        ext.lower(),
        ext.lower() if ext else "Unknown",
    )


def human_size(num_bytes: int) -> str:
    value = float(num_bytes)

    for unit in ("B", "KB", "MB", "GB", "TB"):
        if value < 1024:
            return f"{value:.2f} {unit}"
        value /= 1024

    return f"{value:.2f} PB"


def count_lines(text: str) -> int:
    if not text:
        return 0
    return text.count("\n") + 1


def unique_languages(entries: Iterable[dict]) -> list[str]:
    langs = {
        language_from_extension(
            e.get("ext", "")
        )
        for e in entries
    }
    return sorted(langs)


def safe_relative(path: Path, root: Path) -> str:
    return path.relative_to(root).as_posix()


def average_file_size(total_size: int, count: int) -> int:
    if count == 0:
        return 0
    return total_size // count


def project_name(root: Path) -> str:
    return root.resolve().name