diff options
| -rw-r--r-- | string_utils.py | 73 |
1 files changed, 42 insertions, 31 deletions
diff --git a/string_utils.py b/string_utils.py index 6eda278..244c450 100644 --- a/string_utils.py +++ b/string_utils.py @@ -11,7 +11,16 @@ import numbers import random import re import string -from typing import Any, Callable, Dict, Iterable, List, Optional, Sequence, Tuple +from typing import ( + Any, + Callable, + Dict, + Iterable, + List, + Optional, + Sequence, + Tuple, +) import unicodedata from uuid import uuid4 import warnings @@ -32,7 +41,7 @@ URLS_RAW_STRING = ( r"([a-z-]+://)" # scheme r"([a-z_\d-]+:[a-z_\d-]+@)?" # user:password r"(www\.)?" # www. - r"((?<!\.)[a-z\d]+[a-z\d.-]+\.[a-z]{2,6}|\d{1,3}\.\d{1,3}\.\d{1,3}\.\d{1,3}|localhost)" # domain + r"((?<!\.)[a-z\d]+[a-z\d.-]+\.[a-z]{2,6}|\d{1,3}\.\d{1,3}\.\d{1,3}\.\d{1,3}|localhost)" # domain r"(:\d{2,})?" # port number r"(/[a-z\d_%+-]*)*" # folders r"(\.[a-z\d_%+-]+)*" # file extension @@ -254,10 +263,10 @@ def is_integer_number(in_str: str) -> bool: False """ return ( - (is_number(in_str) and "." not in in_str) or - is_hexidecimal_integer_number(in_str) or - is_octal_integer_number(in_str) or - is_binary_integer_number(in_str) + (is_number(in_str) and "." not in in_str) + or is_hexidecimal_integer_number(in_str) + or is_octal_integer_number(in_str) + or is_binary_integer_number(in_str) ) @@ -382,10 +391,7 @@ def strip_escape_sequences(in_str: str) -> str: def add_thousands_separator( - in_str: str, - *, - separator_char = ',', - places = 3 + in_str: str, *, separator_char=',', places=3 ) -> str: """ Add thousands separator to a numeric string. Also handles numbers. @@ -406,20 +412,21 @@ def add_thousands_separator( in_str = f'{in_str}' if is_number(in_str): return _add_thousands_separator( - in_str, - separator_char = separator_char, - places = places + in_str, separator_char=separator_char, places=places ) raise ValueError(in_str) -def _add_thousands_separator(in_str: str, *, separator_char = ',', places = 3) -> str: +def _add_thousands_separator( + in_str: str, *, separator_char=',', places=3 +) -> str: decimal_part = "" if '.' in in_str: (in_str, decimal_part) = in_str.split('.') tmp = [iter(in_str[::-1])] * places ret = separator_char.join( - "".join(x) for x in zip_longest(*tmp, fillvalue=""))[::-1] + "".join(x) for x in zip_longest(*tmp, fillvalue="") + )[::-1] if len(decimal_part) > 0: ret += '.' ret += decimal_part @@ -507,6 +514,7 @@ def suffix_string_to_number(in_str: str) -> Optional[int]: >>> suffix_string_to_number('13.1Gb') 14066017894 """ + def suffix_capitalize(s: str) -> str: if len(s) == 1: return s.upper() @@ -1093,6 +1101,7 @@ def to_date(in_str: str) -> Optional[datetime.date]: Parses a date string. See DateParser docs for details. """ import dateparse.dateparse_utils as dp + try: d = dp.DateParser() d.parse(in_str) @@ -1108,6 +1117,7 @@ def valid_date(in_str: str) -> bool: True if the string represents a valid date. """ import dateparse.dateparse_utils as dp + try: d = dp.DateParser() _ = d.parse(in_str) @@ -1123,6 +1133,7 @@ def to_datetime(in_str: str) -> Optional[datetime.datetime]: Parses a datetime string. See DateParser docs for more info. """ import dateparse.dateparse_utils as dp + try: d = dp.DateParser() dt = d.parse(in_str) @@ -1160,7 +1171,7 @@ def squeeze(in_str: str, character_to_squeeze: str = ' ') -> str: return re.sub( r'(' + re.escape(character_to_squeeze) + r')+', character_to_squeeze, - in_str + in_str, ) @@ -1232,6 +1243,7 @@ class SprintfStdout(object): 'test\n' """ + def __init__(self) -> None: self.destination = io.StringIO() self.recorder = None @@ -1331,9 +1343,7 @@ def trigrams(txt: str): def shuffle_columns_into_list( - input_lines: Iterable[str], - column_specs: Iterable[Iterable[int]], - delim='' + input_lines: Iterable[str], column_specs: Iterable[Iterable[int]], delim='' ) -> Iterable[str]: """Helper to shuffle / parse columnar data and return the results as a list. The column_specs argument is an iterable collection of @@ -1363,9 +1373,9 @@ def shuffle_columns_into_list( def shuffle_columns_into_dict( - input_lines: Iterable[str], - column_specs: Iterable[Tuple[str, Iterable[int]]], - delim='' + input_lines: Iterable[str], + column_specs: Iterable[Tuple[str, Iterable[int]]], + delim='', ) -> Dict[str, str]: """Helper to shuffle / parse columnar data and return the results as a dict. @@ -1475,10 +1485,12 @@ def chunk(txt: str, chunk_size): logger.warning(msg) warnings.warn(msg, stacklevel=2) for x in range(0, len(txt), chunk_size): - yield txt[x:x+chunk_size] + yield txt[x : x + chunk_size] -def to_bitstring(txt: str, *, delimiter='', encoding='utf-8', errors='surrogatepass') -> str: +def to_bitstring( + txt: str, *, delimiter='', encoding='utf-8', errors='surrogatepass' +) -> str: """Encode txt and then chop it into bytes. Note: only bitstrings with delimiter='' are interpretable by from_bitstring. @@ -1493,12 +1505,7 @@ def to_bitstring(txt: str, *, delimiter='', encoding='utf-8', errors='surrogatep """ etxt = to_ascii(txt) - bits = bin( - int.from_bytes( - etxt, - 'big' - ) - ) + bits = bin(int.from_bytes(etxt, 'big')) bits = bits[2:] return delimiter.join(chunk(bits.zfill(8 * ((len(bits) + 7) // 8)), 8)) @@ -1524,7 +1531,10 @@ def from_bitstring(bits: str, encoding='utf-8', errors='surrogatepass') -> str: """ n = int(bits, 2) - return n.to_bytes((n.bit_length() + 7) // 8, 'big').decode(encoding, errors) or '\0' + return ( + n.to_bytes((n.bit_length() + 7) // 8, 'big').decode(encoding, errors) + or '\0' + ) def ip_v4_sort_key(txt: str) -> Tuple[int]: @@ -1574,4 +1584,5 @@ def replace_all(in_str: str, replace_set: str, replacement: str) -> str: if __name__ == '__main__': import doctest + doctest.testmod() |