rhodecode/lib/str_utils.py

# Copyright (C) 2011-2024 RhodeCode GmbH
#
# This program is free software: you can redistribute it and/or modify
# it under the terms of the GNU Affero General Public License, version 3
# (only), as published by the Free Software Foundation.
#
# This program is distributed in the hope that it will be useful,
# but WITHOUT ANY WARRANTY; without even the implied warranty of
# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
# GNU General Public License for more details.
#
# You should have received a copy of the GNU Affero General Public License
# along with this program.  If not, see <http://www.gnu.org/licenses/>.
#
# This program is dual-licensed. If you wish to learn more about the
# RhodeCode Enterprise Edition, including its added features, Support services,
# and proprietary license terms, please see https://rhodecode.com/licenses/

import typing
import base64
import logging
from unidecode import unidecode

import rhodecode
from rhodecode.lib.type_utils import aslist


log = logging.getLogger(__name__)


def safe_int(val, default=None) -> int:
    """
    Returns int() of val if val is not convertable to int use default
    instead

    :param val:
    :param default:
    """

    try:
        val = int(val)
    except (ValueError, TypeError):
        val = default

    return val


def safe_float(val, default=None) -> float:
    """
    Returns float() of val if val is not convertable to float use default
    instead

    :param val:
    :param default:
    """

    try:
        val = float(val)
    except (ValueError, TypeError):
        val = default

    return val


def base64_to_str(text: str | bytes) -> str:
    return safe_str(base64.encodebytes(safe_bytes(text))).strip()


def get_default_encodings() -> list[str]:
    return aslist(rhodecode.CONFIG.get('default_encoding', 'utf8'), sep=',')


DEFAULT_ENCODINGS = get_default_encodings()


def safe_str(str_, to_encoding=None) -> str:
    """
    safe str function. Does few trick to turn unicode_ into string

    :param str_: str to encode
    :param to_encoding: encode to this type UTF8 default
    """
    if isinstance(str_, str):
        return str_

    # if it's bytes cast to str
    if not isinstance(str_, bytes):
        return str(str_)

    to_encoding = to_encoding or DEFAULT_ENCODINGS
    if not isinstance(to_encoding, (list, tuple)):
        to_encoding = [to_encoding]

    for enc in to_encoding:
        try:
            return str(str_, enc)
        except UnicodeDecodeError:
            pass

    return str(str_, to_encoding[0], 'replace')


def safe_bytes(str_, from_encoding=None) -> bytes:
    """
    safe bytes function. Does few trick to turn str_ into bytes string:

    :param str_: string to decode
    :param from_encoding: encode from this type UTF8 default
    """
    if isinstance(str_, bytes):
        return str_

    if not isinstance(str_, str):
        raise ValueError(f'safe_bytes cannot convert other types than str: got: {type(str_)}')

    from_encoding = from_encoding or get_default_encodings()
    if not isinstance(from_encoding, (list, tuple)):
        from_encoding = [from_encoding]

    for enc in from_encoding:
        try:
            return str_.encode(enc)
        except UnicodeDecodeError:
            pass

    return str_.encode(from_encoding[0], 'replace')


def ascii_bytes(str_, allow_bytes=False) -> bytes:
    """
    Simple conversion from str to bytes, with assumption that str_ is pure ASCII.
    Fails with UnicodeError on invalid input.
    This should be used where encoding and "safe" ambiguity should be avoided.
    Where strings already have been encoded in other ways but still are unicode
    string - for example to hex, base64, json, urlencoding, or are known to be
    identifiers.
    """
    if allow_bytes and isinstance(str_, bytes):
        return str_

    if not isinstance(str_, str):
        raise ValueError(f'ascii_bytes cannot convert other types than str: got: {type(str_)}')
    return str_.encode('ascii')


def ascii_str(str_) -> str:
    """
    Simple conversion from bytes to str, with assumption that str_ is pure ASCII.
    Fails with UnicodeError on invalid input.
    This should be used where encoding and "safe" ambiguity should be avoided.
    Where strings are encoded but also in other ways are known to be ASCII, and
    where a unicode string is wanted without caring about encoding. For example
    to hex, base64, urlencoding, or are known to be identifiers.
    """

    if not isinstance(str_, bytes):
        raise ValueError(f'ascii_str cannot convert other types than bytes: got: {type(str_)}')
    return str_.decode('ascii')


def convert_special_chars(str_) -> str:
    """
        trie to replace non-ascii letters to their ascii representation eg::

            `żołw` converts into `zolw`
    """
    value = safe_str(str_)
    converted_value = unidecode(value)
    return converted_value


def splitnewlines(text: bytes):
    """
    like splitlines, but only split on newlines.
    """

    lines = [_l + b'\n' for _l in text.split(b'\n')]
    if lines:
        if lines[-1] == b'\n':
            lines.pop()
        else:
            lines[-1] = lines[-1][:-1]
    return lines


def header_safe_str(val):
    return safe_bytes(val).decode('latin-1', errors='replace')