#!/usr/bin/env python3
+# -*- coding: utf-8 -*-
"""The MIT License (MIT)
"""
import base64
-import contextlib
+import contextlib # type: ignore
import datetime
import io
-from itertools import zip_longest
import json
import logging
import numbers
import random
import re
import string
+import unicodedata
+import warnings
+from itertools import zip_longest
from typing import (
Any,
Callable,
Dict,
Iterable,
List,
+ Literal,
Optional,
Sequence,
Tuple,
)
-import unicodedata
from uuid import uuid4
-import warnings
import list_utils
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"^{}$".format(EMAILS_RAW_STRING))
CAMEL_CASE_REPLACE_RE = re.compile(r"([a-z]|[A-Z]+)(?=[A-Z])")
-SNAKE_CASE_TEST_RE = re.compile(
- r"^([a-z]+\d*_[a-z\d_]*|_+[a-z\d]+[a-z\d_]*)$", 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])")
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}$", re.IGNORECASE)
UUID_HEX_OK_RE = re.compile(
r"^[a-f\d]{8}-?[a-f\d]{4}-?[a-f\d]{4}-?[a-f\d]{4}-?[a-f\d]{12}$",
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)
ESCAPE_SEQUENCE_RE = re.compile(r"\e\[[^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),
}
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)
return len(WORDS_COUNT_RE.findall(in_str))
+def word_count(in_str: str) -> int:
+ return words_count(in_str)
+
+
def generate_uuid(omit_dashes: bool = False) -> str:
"""
Generated an UUID string (using `uuid.uuid4()`).
Returns a string of the specified size containing random
characters (uppercase/lowercase ascii letters and digits).
- random_string(9) # possible output: "cx3QQbzYg"
+ >>> random.seed(22)
+ >>> generate_random_alphanumeric_string(9)
+ '96ipbNClS'
"""
if size < 1:
return from_char_list(chars)
+def scramble(in_str: str) -> str:
+ return shuffle(in_str)
+
+
def strip_html(in_str: str, keep_tag_content: bool = False) -> str:
"""
Remove html code contained into the given string.
"""
Parses a date string. See DateParser docs for details.
"""
- import dateparse.dateparse_utils as dp
+ 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
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
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}.'
return ret
-class SprintfStdout(object):
+def strip_ansi_sequences(in_str: str) -> str:
+ """Strips ANSI sequences out of strings.
+
+ >>> import ansi as a
+ >>> s = a.fg('blue') + 'blue!' + a.reset()
+ >>> len(s) # '\x1b[38;5;21mblue!\x1b[m'
+ 18
+ >>> len(strip_ansi_sequences(s))
+ 5
+ >>> strip_ansi_sequences(s)
+ 'blue!'
+
+ """
+ return re.sub(r'\x1b\[[\d+;]*[a-z]', '', in_str)
+
+
+class SprintfStdout(contextlib.AbstractContextManager):
"""
A context manager that captures outputs to stdout.
def __init__(self) -> None:
self.destination = io.StringIO()
- self.recorder = None
+ self.recorder: contextlib.redirect_stdout
def __enter__(self) -> Callable[[], str]:
self.recorder = contextlib.redirect_stdout(self.destination)
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:
+ """Capitalize the first letter of a string.
+
+ >>> capitalize_first_letter('test')
+ 'Test'
+ >>> capitalize_first_letter("ALREADY!")
+ 'ALREADY!'
+
+ """
+ return txt[0].upper() + txt[1:]
+
+
+def it_they(n: int) -> str:
+ """It or they?
+
+ >>> it_they(1)
+ 'it'
+ >>> it_they(100)
+ 'they'
+
+ """
+ if n == 1:
+ return "it"
+ return "they"
def is_are(n: int) -> str:
return "s"
+def make_contractions(txt: str) -> str:
+ """Glue words together to form contractions.
+
+ >>> make_contractions('It is nice today.')
+ "It's nice today."
+
+ >>> make_contractions('I can not even...')
+ "I can't even..."
+
+ >>> make_contractions('She could not see!')
+ "She couldn't see!"
+
+ >>> make_contractions('But she will not go.')
+ "But she won't go."
+
+ >>> make_contractions('Verily, I shall not.')
+ "Verily, I shan't."
+
+ >>> make_contractions('No you cannot.')
+ "No you can't."
+
+ >>> make_contractions('I said you can not go.')
+ "I said you can't go."
+
+ """
+
+ first_second = [
+ (
+ [
+ 'are',
+ 'could',
+ 'did',
+ 'has',
+ 'have',
+ 'is',
+ 'must',
+ 'should',
+ 'was',
+ 'were',
+ 'would',
+ ],
+ ['(n)o(t)'],
+ ),
+ (
+ [
+ "I",
+ "you",
+ "he",
+ "she",
+ "it",
+ "we",
+ "they",
+ "how",
+ "why",
+ "when",
+ "where",
+ "who",
+ "there",
+ ],
+ ['woul(d)', 'i(s)', 'a(re)', 'ha(s)', 'ha(ve)', 'ha(d)', 'wi(ll)'],
+ ),
+ ]
+
+ # 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(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:
+ for first in first_list:
+ for second in second_list:
+ # Disallow there're/where're. They're valid English
+ # but sound weird.
+ if (first in ('there', 'where')) and second == 'a(re)':
+ continue
+
+ pattern = fr'\b({first})\s+{second}\b'
+ if second == '(n)o(t)':
+ replacement = r"\1\2'\3"
+ else:
+ replacement = r"\1'\2"
+ txt = re.sub(pattern, replacement, txt, count=0, flags=re.IGNORECASE)
+
+ return txt
+
+
def thify(n: int) -> str:
"""Return the proper cardinal suffix for a number.
def shuffle_columns_into_list(
- input_lines: Iterable[str], column_specs: Iterable[Iterable[int]], delim=''
+ input_lines: Sequence[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
# 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
def shuffle_columns_into_dict(
- input_lines: Iterable[str],
+ input_lines: Sequence[str],
column_specs: Iterable[Tuple[str, Iterable[int]]],
delim='',
) -> Dict[str, str]:
# 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
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')
-def to_base64(txt: str, *, encoding='utf-8', errors='surrogatepass') -> str:
+def to_base64(txt: str, *, encoding='utf-8', errors='surrogatepass') -> bytes:
"""Encode txt and then encode the bytes with a 64-character
alphabet. This is compatible with uudecode.
return True
-def from_base64(b64: str, encoding='utf-8', errors='surrogatepass') -> str:
+def from_base64(b64: bytes, encoding='utf-8', errors='surrogatepass') -> str:
"""Convert base64 encoded string back to normal strings.
>>> from_base64(b'aGVsbG8/\\n')
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.
return n.to_bytes((n.bit_length() + 7) // 8, 'big').decode(encoding, errors) or '\0'
-def ip_v4_sort_key(txt: str) -> Tuple[int]:
+def ip_v4_sort_key(txt: str) -> Optional[Tuple[int, ...]]:
"""Turn an IPv4 address into a tuple for sorting purposes.
>>> ip_v4_sort_key('10.0.0.18')
if not is_ip_v4(txt):
print(f"not IP: {txt}")
return None
- return tuple([int(x) for x in txt.split('.')])
+ return tuple(int(x) for x in txt.split('.'))
-def path_ancestors_before_descendants_sort_key(volume: str) -> Tuple[str]:
+def path_ancestors_before_descendants_sort_key(volume: str) -> Tuple[str, ...]:
"""Chunk up a file path so that parent/ancestor paths sort before
children/descendant paths.
['/usr', '/usr/local', '/usr/local/bin']
"""
- return tuple([x for x in volume.split('/') if len(x) > 0])
+ return tuple(x for x in volume.split('/') if len(x) > 0)
def replace_all(in_str: str, replace_set: str, replacement: str) -> str:
return in_str
+def replace_nth(in_str: str, source: str, target: str, nth: int):
+ """Replaces the nth occurrance of a substring within a string.
+
+ >>> replace_nth('this is a test', ' ', '-', 3)
+ 'this is a-test'
+
+ """
+ where = [m.start() for m in re.finditer(source, in_str)][nth - 1]
+ before = in_str[:where]
+ after = in_str[where:]
+ after = after.replace(source, target, 1)
+ return before + after
+
+
if __name__ == '__main__':
import doctest