backend/utils/file_utils.py

from __future__ import annotations

import os
from pathlib import Path
from typing import Iterable


TEXT_EXTENSIONS = {
    ".py",
    ".js",
    ".jsx",
    ".ts",
    ".tsx",
    ".java",
    ".go",
    ".rb",
    ".php",
    ".cs",
    ".cpp",
    ".c",
    ".rs",
    ".swift",
    ".kt",
    ".scala",
    ".vue",
    ".svelte",
    ".html",
    ".css",
    ".scss",
    ".json",
    ".yaml",
    ".yml",
    ".toml",
    ".md",
    ".env.example",
}


def to_posix_path(path: str | os.PathLike[str]) -> str:
    return Path(path).as_posix()


def is_text_file(path: str, size: int) -> bool:
    return Path(path).suffix.lower() in TEXT_EXTENSIONS and size <= 100_000


def safe_read_text(path: str, max_chars: int = 100_000) -> str:
    try:
        with open(path, "r", encoding="utf-8", errors="ignore") as file:
            return file.read(max_chars)
    except OSError:
        return ""


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


def has_any_token(value: str, tokens: Iterable[str]) -> bool:
    lower = value.lower()
    return any(token.lower() in lower for token in tokens)