File size: 5,130 Bytes
9c6594c |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 |
from __future__ import annotations
from functools import lru_cache
from typing import Callable
from ._cell_widths import CELL_WIDTHS
# Ranges of unicode ordinals that produce a 1-cell wide character
# This is non-exhaustive, but covers most common Western characters
_SINGLE_CELL_UNICODE_RANGES: list[tuple[int, int]] = [
(0x20, 0x7E), # Latin (excluding non-printable)
(0xA0, 0xAC),
(0xAE, 0x002FF),
(0x00370, 0x00482), # Greek / Cyrillic
(0x02500, 0x025FC), # Box drawing, box elements, geometric shapes
(0x02800, 0x028FF), # Braille
]
# A set of characters that are a single cell wide
_SINGLE_CELLS = frozenset(
[
character
for _start, _end in _SINGLE_CELL_UNICODE_RANGES
for character in map(chr, range(_start, _end + 1))
]
)
# When called with a string this will return True if all
# characters are single-cell, otherwise False
_is_single_cell_widths: Callable[[str], bool] = _SINGLE_CELLS.issuperset
@lru_cache(4096)
def cached_cell_len(text: str) -> int:
"""Get the number of cells required to display text.
This method always caches, which may use up a lot of memory. It is recommended to use
`cell_len` over this method.
Args:
text (str): Text to display.
Returns:
int: Get the number of cells required to display text.
"""
if _is_single_cell_widths(text):
return len(text)
return sum(map(get_character_cell_size, text))
def cell_len(text: str, _cell_len: Callable[[str], int] = cached_cell_len) -> int:
"""Get the number of cells required to display text.
Args:
text (str): Text to display.
Returns:
int: Get the number of cells required to display text.
"""
if len(text) < 512:
return _cell_len(text)
if _is_single_cell_widths(text):
return len(text)
return sum(map(get_character_cell_size, text))
@lru_cache(maxsize=4096)
def get_character_cell_size(character: str) -> int:
"""Get the cell size of a character.
Args:
character (str): A single character.
Returns:
int: Number of cells (0, 1 or 2) occupied by that character.
"""
codepoint = ord(character)
_table = CELL_WIDTHS
lower_bound = 0
upper_bound = len(_table) - 1
index = (lower_bound + upper_bound) // 2
while True:
start, end, width = _table[index]
if codepoint < start:
upper_bound = index - 1
elif codepoint > end:
lower_bound = index + 1
else:
return 0 if width == -1 else width
if upper_bound < lower_bound:
break
index = (lower_bound + upper_bound) // 2
return 1
def set_cell_size(text: str, total: int) -> str:
"""Set the length of a string to fit within given number of cells."""
if _is_single_cell_widths(text):
size = len(text)
if size < total:
return text + " " * (total - size)
return text[:total]
if total <= 0:
return ""
cell_size = cell_len(text)
if cell_size == total:
return text
if cell_size < total:
return text + " " * (total - cell_size)
start = 0
end = len(text)
# Binary search until we find the right size
while True:
pos = (start + end) // 2
before = text[: pos + 1]
before_len = cell_len(before)
if before_len == total + 1 and cell_len(before[-1]) == 2:
return before[:-1] + " "
if before_len == total:
return before
if before_len > total:
end = pos
else:
start = pos
def chop_cells(
text: str,
width: int,
) -> list[str]:
"""Split text into lines such that each line fits within the available (cell) width.
Args:
text: The text to fold such that it fits in the given width.
width: The width available (number of cells).
Returns:
A list of strings such that each string in the list has cell width
less than or equal to the available width.
"""
_get_character_cell_size = get_character_cell_size
lines: list[list[str]] = [[]]
append_new_line = lines.append
append_to_last_line = lines[-1].append
total_width = 0
for character in text:
cell_width = _get_character_cell_size(character)
char_doesnt_fit = total_width + cell_width > width
if char_doesnt_fit:
append_new_line([character])
append_to_last_line = lines[-1].append
total_width = cell_width
else:
append_to_last_line(character)
total_width += cell_width
return ["".join(line) for line in lines]
if __name__ == "__main__": # pragma: no cover
print(get_character_cell_size("π½"))
for line in chop_cells("""θΏζ―ε―ΉδΊζ΄²θ―θ¨ζ―ζηζ΅θ―γι’对樑棱一ε―ηζ³ζ³οΌζη»ηζ΅ηθ―±ζγ""", 8):
print(line)
for n in range(80, 1, -1):
print(set_cell_size("""θΏζ―ε―ΉδΊζ΄²θ―θ¨ζ―ζηζ΅θ―γι’对樑棱一ε―ηζ³ζ³οΌζη»ηζ΅ηθ―±ζγ""", n) + "|")
print("x" * n)
|