2024-03-04 01:15:23 +08:00
|
|
|
from __future__ import annotations
|
|
|
|
|
2022-01-24 12:07:52 +08:00
|
|
|
import re
|
2022-11-08 02:06:49 +08:00
|
|
|
from functools import lru_cache
|
2024-03-04 01:15:23 +08:00
|
|
|
from typing import Callable
|
2021-04-13 12:02:29 +08:00
|
|
|
|
|
|
|
from ._cell_widths import CELL_WIDTHS
|
|
|
|
|
2022-01-24 12:07:52 +08:00
|
|
|
# Regex to match sequence of the most common character ranges
|
|
|
|
_is_single_cell_widths = re.compile("^[\u0020-\u006f\u00a0\u02ff\u0370-\u0482]*$").match
|
|
|
|
|
2021-04-13 12:02:29 +08:00
|
|
|
|
2022-11-08 02:06:49 +08:00
|
|
|
@lru_cache(4096)
|
|
|
|
def cached_cell_len(text: str) -> int:
|
2021-04-13 12:02:29 +08:00
|
|
|
"""Get the number of cells required to display text.
|
|
|
|
|
2022-11-08 02:06:49 +08:00
|
|
|
This method always caches, which may use up a lot of memory. It is recommended to use
|
|
|
|
`cell_len` over this method.
|
|
|
|
|
2021-04-13 12:02:29 +08:00
|
|
|
Args:
|
|
|
|
text (str): Text to display.
|
|
|
|
|
|
|
|
Returns:
|
2022-01-24 12:07:52 +08:00
|
|
|
int: Get the number of cells required to display text.
|
2021-04-13 12:02:29 +08:00
|
|
|
"""
|
2022-11-08 02:06:49 +08:00
|
|
|
_get_size = get_character_cell_size
|
|
|
|
total_size = sum(_get_size(character) for character in text)
|
|
|
|
return total_size
|
2022-01-24 12:07:52 +08:00
|
|
|
|
2022-11-08 02:06:49 +08:00
|
|
|
|
|
|
|
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)
|
|
|
|
_get_size = get_character_cell_size
|
|
|
|
total_size = sum(_get_size(character) for character in text)
|
2021-04-13 12:02:29 +08:00
|
|
|
return total_size
|
|
|
|
|
|
|
|
|
2022-01-24 12:07:52 +08:00
|
|
|
@lru_cache(maxsize=4096)
|
2021-04-13 12:02:29 +08:00
|
|
|
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.
|
|
|
|
"""
|
2022-01-24 12:07:52 +08:00
|
|
|
return _get_codepoint_cell_size(ord(character))
|
2021-04-13 12:02:29 +08:00
|
|
|
|
|
|
|
|
|
|
|
@lru_cache(maxsize=4096)
|
|
|
|
def _get_codepoint_cell_size(codepoint: int) -> int:
|
|
|
|
"""Get the cell size of a character.
|
|
|
|
|
|
|
|
Args:
|
2024-03-04 01:15:23 +08:00
|
|
|
codepoint (int): Codepoint of a character.
|
2021-04-13 12:02:29 +08:00
|
|
|
|
|
|
|
Returns:
|
|
|
|
int: Number of cells (0, 1 or 2) occupied by that 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."""
|
2022-01-24 12:07:52 +08:00
|
|
|
|
|
|
|
if _is_single_cell_widths(text):
|
|
|
|
size = len(text)
|
|
|
|
if size < total:
|
|
|
|
return text + " " * (total - size)
|
|
|
|
return text[:total]
|
|
|
|
|
2022-11-08 02:06:49 +08:00
|
|
|
if total <= 0:
|
2022-01-24 12:07:52 +08:00
|
|
|
return ""
|
2021-04-13 12:02:29 +08:00
|
|
|
cell_size = cell_len(text)
|
|
|
|
if cell_size == total:
|
|
|
|
return text
|
|
|
|
if cell_size < total:
|
|
|
|
return text + " " * (total - cell_size)
|
|
|
|
|
2022-01-24 12:07:52 +08:00
|
|
|
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
|
2021-04-13 12:02:29 +08:00
|
|
|
|
|
|
|
|
2024-03-04 01:15:23 +08:00
|
|
|
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.
|
|
|
|
"""
|
2021-04-13 12:02:29 +08:00
|
|
|
_get_character_cell_size = get_character_cell_size
|
2024-03-04 01:15:23 +08:00
|
|
|
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
|
2021-04-13 12:02:29 +08:00
|
|
|
else:
|
2024-03-04 01:15:23 +08:00
|
|
|
append_to_last_line(character)
|
|
|
|
total_width += cell_width
|
2022-11-08 02:06:49 +08:00
|
|
|
|
2021-04-13 12:02:29 +08:00
|
|
|
return ["".join(line) for line in lines]
|
|
|
|
|
|
|
|
|
|
|
|
if __name__ == "__main__": # pragma: no cover
|
|
|
|
print(get_character_cell_size("😽"))
|
|
|
|
for line in chop_cells("""这是对亚洲语言支持的测试。面对模棱两可的想法,拒绝猜测的诱惑。""", 8):
|
|
|
|
print(line)
|
|
|
|
for n in range(80, 1, -1):
|
|
|
|
print(set_cell_size("""这是对亚洲语言支持的测试。面对模棱两可的想法,拒绝猜测的诱惑。""", n) + "|")
|
|
|
|
print("x" * n)
|