X-Git-Url: https://wannabe.guru.org/gitweb/?a=blobdiff_plain;f=string_utils.py;h=4bec031738e989d10507992387e18aa47996da8e;hb=f2600f30801c849fc1d139386e3ddc3c9eb43e30;hp=bae59068b9063cece6fe401f649401e07efa138d;hpb=ffed473528c4feb836253758e86f7839af98f57b;p=python_utils.git diff --git a/string_utils.py b/string_utils.py index bae5906..4bec031 100644 --- a/string_utils.py +++ b/string_utils.py @@ -1,4 +1,5 @@ #!/usr/bin/env python3 +# -*- coding: utf-8 -*- """The MIT License (MIT) @@ -39,7 +40,17 @@ import string import unicodedata import warnings from itertools import zip_longest -from typing import Any, Callable, Dict, Iterable, List, Optional, Sequence, Tuple +from typing import ( + Any, + Callable, + Dict, + Iterable, + List, + Literal, + Optional, + Sequence, + Tuple, +) from uuid import uuid4 import list_utils @@ -72,9 +83,7 @@ URLS_RE = re.compile(r"({})".format(URLS_RAW_STRING), re.IGNORECASE) ESCAPED_AT_SIGN = re.compile(r'(?!"[^"]*)@+(?=[^"]*")|\\@') -EMAILS_RAW_STRING = ( - r"[a-zA-Z\d._\+\-'`!%#$&*/=\?\^\{\}\|~\\]+@[a-z\d-]+\.?[a-z\d-]+\.[a-z]{2,4}" -) +EMAILS_RAW_STRING = r"[a-zA-Z\d._\+\-'`!%#$&*/=\?\^\{\}\|~\\]+@[a-z\d-]+\.?[a-z\d-]+\.[a-z]{2,4}" EMAIL_RE = re.compile(r"^{}$".format(EMAILS_RAW_STRING)) @@ -84,13 +93,9 @@ CAMEL_CASE_TEST_RE = re.compile(r"^[a-zA-Z]*([a-z]+[A-Z]+|[A-Z]+[a-z]+)[a-zA-Z\d CAMEL_CASE_REPLACE_RE = re.compile(r"([a-z]|[A-Z]+)(?=[A-Z])") -SNAKE_CASE_TEST_RE = re.compile( - r"^([a-z]+\d*_[a-z\d_]*|_+[a-z\d]+[a-z\d_]*)$", re.IGNORECASE -) +SNAKE_CASE_TEST_RE = re.compile(r"^([a-z]+\d*_[a-z\d_]*|_+[a-z\d]+[a-z\d_]*)$", re.IGNORECASE) -SNAKE_CASE_TEST_DASH_RE = re.compile( - r"([a-z]+\d*-[a-z\d-]*|-+[a-z\d]+[a-z\d-]*)$", re.IGNORECASE -) +SNAKE_CASE_TEST_DASH_RE = re.compile(r"([a-z]+\d*-[a-z\d-]*|-+[a-z\d]+[a-z\d-]*)$", re.IGNORECASE) SNAKE_CASE_REPLACE_RE = re.compile(r"(_)([a-z\d])") @@ -107,9 +112,7 @@ CREDIT_CARDS = { JSON_WRAPPER_RE = re.compile(r"^\s*[\[{]\s*(.*)\s*[\}\]]\s*$", re.MULTILINE | re.DOTALL) -UUID_RE = re.compile( - r"^[a-f\d]{8}-[a-f\d]{4}-[a-f\d]{4}-[a-f\d]{4}-[a-f\d]{12}$", re.IGNORECASE -) +UUID_RE = re.compile(r"^[a-f\d]{8}-[a-f\d]{4}-[a-f\d]{4}-[a-f\d]{4}-[a-f\d]{12}$", re.IGNORECASE) UUID_HEX_OK_RE = re.compile( r"^[a-f\d]{8}-?[a-f\d]{4}-?[a-f\d]{4}-?[a-f\d]{4}-?[a-f\d]{12}$", @@ -126,9 +129,7 @@ ANYWHERE_IP_V6_RE = re.compile(r"([a-z\d]{0,4}:){7}[a-z\d]{0,4}", re.IGNORECASE) MAC_ADDRESS_RE = re.compile(r"^([0-9A-F]{2}[:-]){5}([0-9A-F]{2})$", re.IGNORECASE) -ANYWHERE_MAC_ADDRESS_RE = re.compile( - r"([0-9A-F]{2}[:-]){5}([0-9A-F]{2})", re.IGNORECASE -) +ANYWHERE_MAC_ADDRESS_RE = re.compile(r"([0-9A-F]{2}[:-]){5}([0-9A-F]{2})", re.IGNORECASE) WORDS_COUNT_RE = re.compile(r"\W*[^\W_]+\W*", re.IGNORECASE | re.MULTILINE | re.UNICODE) @@ -151,16 +152,16 @@ MARGIN_RE = re.compile(r"^[^\S\r\n]+") ESCAPE_SEQUENCE_RE = re.compile(r"\[[^A-Za-z]*[A-Za-z]") NUM_SUFFIXES = { - "Pb": (1024 ** 5), - "P": (1024 ** 5), - "Tb": (1024 ** 4), - "T": (1024 ** 4), - "Gb": (1024 ** 3), - "G": (1024 ** 3), - "Mb": (1024 ** 2), - "M": (1024 ** 2), - "Kb": (1024 ** 1), - "K": (1024 ** 1), + "Pb": (1024**5), + "P": (1024**5), + "Tb": (1024**4), + "T": (1024**4), + "Gb": (1024**3), + "G": (1024**3), + "Mb": (1024**2), + "M": (1024**2), + "Kb": (1024**1), + "K": (1024**1), } @@ -418,9 +419,7 @@ def add_thousands_separator(in_str: str, *, separator_char=',', places=3) -> str if isinstance(in_str, numbers.Number): in_str = f'{in_str}' if is_number(in_str): - return _add_thousands_separator( - in_str, separator_char=separator_char, places=places - ) + return _add_thousands_separator(in_str, separator_char=separator_char, places=places) raise ValueError(in_str) @@ -1086,13 +1085,13 @@ def to_date(in_str: str) -> Optional[datetime.date]: """ Parses a date string. See DateParser docs for details. """ - import dateparse.dateparse_utils as dp # type: ignore + import dateparse.dateparse_utils as du try: - d = dp.DateParser() + d = du.DateParser() # type: ignore d.parse(in_str) return d.get_date() - except dp.ParseException: + except du.ParseException: # type: ignore msg = f'Unable to parse date {in_str}.' logger.warning(msg) return None @@ -1105,10 +1104,10 @@ def valid_date(in_str: str) -> bool: import dateparse.dateparse_utils as dp try: - d = dp.DateParser() + d = dp.DateParser() # type: ignore _ = d.parse(in_str) return True - except dp.ParseException: + except dp.ParseException: # type: ignore msg = f'Unable to parse date {in_str}.' logger.warning(msg) return False @@ -1121,9 +1120,9 @@ def to_datetime(in_str: str) -> Optional[datetime.datetime]: import dateparse.dateparse_utils as dp try: - d = dp.DateParser() + d = dp.DateParser() # type: ignore dt = d.parse(in_str) - if type(dt) == datetime.datetime: + if isinstance(dt, datetime.datetime): return dt except ValueError: msg = f'Unable to parse datetime {in_str}.' @@ -1219,7 +1218,7 @@ def sprintf(*args, **kwargs) -> str: return ret -class SprintfStdout(object): +class SprintfStdout(contextlib.AbstractContextManager): """ A context manager that captures outputs to stdout. @@ -1239,10 +1238,10 @@ class SprintfStdout(object): self.recorder.__enter__() return lambda: self.destination.getvalue() - def __exit__(self, *args) -> None: + def __exit__(self, *args) -> Literal[False]: self.recorder.__exit__(*args) self.destination.seek(0) - return None # don't suppress exceptions + return False def capitalize_first_letter(txt: str) -> str: @@ -1368,11 +1367,13 @@ def make_contractions(txt: str) -> str: # Special cases: can't, shan't and won't. txt = re.sub(r'\b(can)\s*no(t)\b', r"\1'\2", txt, count=0, flags=re.IGNORECASE) + txt = re.sub(r'\b(sha)ll\s*(n)o(t)\b', r"\1\2'\3", txt, count=0, flags=re.IGNORECASE) txt = re.sub( - r'\b(sha)ll\s*(n)o(t)\b', r"\1\2'\3", txt, count=0, flags=re.IGNORECASE - ) - txt = re.sub( - r'\b(w)ill\s*(n)(o)(t)\b', r"\1\3\2'\4", txt, count=0, flags=re.IGNORECASE + r'\b(w)ill\s*(n)(o)(t)\b', + r"\1\3\2'\4", + txt, + count=0, + flags=re.IGNORECASE, ) for first_list, second_list in first_second: @@ -1380,7 +1381,7 @@ def make_contractions(txt: str) -> str: for second in second_list: # Disallow there're/where're. They're valid English # but sound weird. - if (first == 'there' or first == 'where') and second == 'a(re)': + if (first in ('there', 'where')) and second == 'a(re)': continue pattern = fr'\b({first})\s+{second}\b' @@ -1466,11 +1467,11 @@ def shuffle_columns_into_list( # Column specs map input lines' columns into outputs. # [col1, col2...] for spec in column_specs: - chunk = '' + hunk = '' for n in spec: - chunk = chunk + delim + input_lines[n] - chunk = chunk.strip(delim) - out.append(chunk) + hunk = hunk + delim + input_lines[n] + hunk = hunk.strip(delim) + out.append(hunk) return out @@ -1496,11 +1497,11 @@ def shuffle_columns_into_dict( # Column specs map input lines' columns into outputs. # "key", [col1, col2...] for spec in column_specs: - chunk = '' + hunk = '' for n in spec[1]: - chunk = chunk + delim + input_lines[n] - chunk = chunk.strip(delim) - out[spec[0]] = chunk + hunk = hunk + delim + input_lines[n] + hunk = hunk.strip(delim) + out[spec[0]] = hunk return out @@ -1525,9 +1526,9 @@ def to_ascii(x: str): b'1, 2, 3' """ - if type(x) is str: + if isinstance(x, str): return x.encode('ascii') - if type(x) is bytes: + if isinstance(x, bytes): return x raise Exception('to_ascii works with strings and bytes') @@ -1590,9 +1591,7 @@ def chunk(txt: str, 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.