str_utils: added common non-ascii replacer

rhodecode/lib/str_utils.py

@@ -1,135 +1,147 b''
 # -*- coding: utf-8 -*-
 
 # Copyright (C) 2011-2020 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 logging
 import rhodecode
+import unicodedata
 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 get_default_encodings():
     return aslist(rhodecode.CONFIG.get('default_encoding', 'utf8'), sep=',')
 
 
 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
     :rtype: str
     :returns: str object
     """
     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 get_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
     :rtype: unicode
     :returns: unicode object
     """
     if isinstance(str_, bytes):
         return str_
 
     if not isinstance(str_, str):
         raise ValueError('safe_bytes cannot convert other types than str: got: {}'.format(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('ascii_bytes cannot convert other types than str: got: {}'.format(type(str_)))
     return str_.encode('ascii')
 
 
 def ascii_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('ascii_str cannot convert other types than bytes: got: {}'.format(type(str_)))
     return str_.decode('ascii')
+
+
+def convert_special_chars(str_):
+    """
+        trie to replace non-ascii letters to their ascii representation eg::
+
+            `żołw` converts into `zolw`
+    """
+    value = safe_str(str_)
+    converted_value = unicodedata.normalize('NFKD', value).encode('ascii', 'ignore').decode()
+    return converted_value