python_arango_ogm.utils.str_util

  1from copy import copy
  2import re
  3import textwrap
  4
  5from enum import StrEnum, auto
  6from typing import Iterable
  7
  8CR = '\n'
  9LF = '\n'
 10EMPTY = ''
 11INDENT = '  '
 12QUOTE = '"'
 13SPACE = ' '
 14SCORE = '_'
 15
 16RE_COMBINE_WHITESPACE = re.compile(r"\s+")
 17RE_ENCLOSE_WS_BEFORE = re.compile(r"(\s+)([\{\[\(])")
 18RE_ENCLOSE_NO_WS_BEFORE = re.compile(r"(\S)([\}\]\)])")
 19RE_ENCLOSE_NO_WS_AFTER = re.compile(r"([\{\[\(\}\]\)])(\S)")
 20RE_ENCLOSEEMPTY = re.compile(r"([\{\[\(])(\s+)([\}\]\)])")
 21RE_TOSNAKECASE = re.compile(r"(?:(?<=[a-z])(?=[A-Z]))|[^a-zA-Z]")
 22RE_CAPITALIZED = re.compile(r"(\s+)([A-Z])")
 23RE_CAPITAL = re.compile(r"([A-Z]+)")
 24RE_NOT_ALPHNUM_SCORE = re.compile(r"[^\w+]")
 25
 26RE_NOT_ALPHNUM = re.compile(r"[^\w]+")
 27RE_NOT_ALPHNUM_SPACE = re.compile(r"[^a-zA-Z0-9\s]+")
 28RE_NOT_ALPHNUM_STRICT = re.compile(r"[^a-zA-Z0-9]+")
 29
 30
 31class QuoteEnum(StrEnum):
 32    """ Quote Enum """
 33    SINGLE = auto()
 34    DOUBLE = auto()
 35    TRIPLE = auto()
 36
 37
 38QUOTE_TYPES = {
 39    QuoteEnum.SINGLE: "'",
 40    QuoteEnum.DOUBLE: '"',
 41    QuoteEnum.TRIPLE: '"""',
 42}
 43
 44
 45class SurroundEnum(StrEnum):
 46    QUOTE_SINGLE = auto()
 47    QUOTE_DOUBLE = auto()
 48    QUOTE_TRIPLE = auto()
 49    BRACE = auto()
 50    BRACKET = auto()
 51    PARENS = auto()
 52
 53
 54SURROUND_TYPES = {
 55    SurroundEnum.QUOTE_SINGLE: ("'", "'"),
 56    SurroundEnum.QUOTE_DOUBLE: ('"', '"'),
 57    SurroundEnum.QUOTE_TRIPLE: ('"""', '"""'),
 58    SurroundEnum.BRACE: ('{', '}'),
 59    SurroundEnum.BRACKET: ('[', ']'),
 60    SurroundEnum.PARENS: ('(', ')'),
 61}
 62
 63
 64def indent(text, amount=4, pre=''):
 65    txt = f"{pre} {text}" if pre else str(text)
 66    return textwrap.indent(txt, INDENT * amount)
 67
 68
 69def prefix(text, pre):
 70    return f"{pre}{text}" if text else copy(EMPTY)
 71
 72
 73def pluralize(val):
 74    s = str(val).strip()
 75
 76    if s:
 77        last_char = s[-1]
 78        if last_char == 'y':
 79            p = s[:-1] + 'ies'
 80        elif last_char == 's':
 81            p = s + 'es'
 82        else:
 83            p = s + 's'
 84    else:
 85        p = copy(EMPTY)
 86
 87    return p
 88
 89
 90def collapse(ary, join_char=LF):
 91    return join_char.join(ary)
 92
 93
 94def surround(text: str, surround_with: SurroundEnum = SurroundEnum.PARENS):
 95    if not text:
 96        return copy(EMPTY)
 97
 98    stype = SURROUND_TYPES[surround_with]
 99    return "{o}{text}{c}".format(o=stype[0], c=stype[1], text=text)
100
101
102def surround_all(iterable: Iterable, surround_with: SurroundEnum = SurroundEnum.PARENS) -> Iterable:
103    return [surround(t, surround_with=surround_with) for t in iterable]
104
105
106def squish_text(text, format_braces=True):
107    squished = RE_COMBINE_WHITESPACE.sub(SPACE, text).strip()
108    if format_braces:
109        squished = RE_ENCLOSE_WS_BEFORE.sub(r'\g<2>', squished)
110        squished = RE_ENCLOSE_NO_WS_BEFORE.sub(r'\g<1> \g<2>', squished)
111        squished = RE_ENCLOSE_NO_WS_AFTER.sub(r'\g<1> \g<2>', squished)
112        squished = RE_ENCLOSEEMPTY.sub(r'\g<1>\g<3>', squished)
113        squished = RE_COMBINE_WHITESPACE.sub(SPACE, squished).strip()
114
115    return squished
116
117
118def score_text(text):
119    return RE_COMBINE_WHITESPACE.sub('_', text.strip()).lower()
120
121
122def combine_space(text):
123    return RE_COMBINE_WHITESPACE.sub(SPACE, text.strip())
124
125
126def snake_text(text, lower: bool = True):
127    def score_cap(txt: str, position:int):
128        return txt if not (txt.isupper() and position) else f"_{txt}"
129    # Separate capitalized words:
130    terms = RE_CAPITAL.split(text)
131    terms.remove('')
132
133    snaked = [score_cap(t, i) for i, t in enumerate(terms) if t]
134    txt = "".join(snaked)
135    return txt.lower() if lower else txt
136
137
138def capitalize_text(text):
139    txt = str(text).strip()
140    return txt if txt.isupper() else txt.capitalize()
141
142
143def title_text(text):
144    txt = RE_CAPITAL.sub(r" \1", text)
145    terms = RE_NOT_ALPHNUM_STRICT.split(txt)
146    clean_terms = filter(None, terms)
147
148    words = [capitalize_text(t) for t in clean_terms]
149    return SPACE.join(words)