resolved RESOLVED UNSUBMITTED PASS · None tool calls · 0 s · Textualize/rich
Fix double-width characters disappearing when wrapping ## Type of changes - [x] Bug fix - [ ] New feature - [ ] Documentation / docstrings - [ ] Tests - [ ] Other ## Checklist - [x] I've run the latest [black](https://github.com/psf/black) with default args on new code. - [x] I've updated CHANGELOG.md and CONTRIBUTORS.md where appropriate. - [x] I've added tests for new code. - [x] I accept that @willmcgugan may be pedantic in the code review. ## Description Update wrapping logic to fix issues with CJK charcters disappearing when the "fold" location sat *within* a double-width character. Ensure we retain browser logic of: > if there is no space on the current line, move to a new line, and if theres not enough space on the entire new line, fold the text over multiple lines at appropriate locations. Adds some additional tests and docstrings, documentation etc. Fixes #3176 The wrapping process is overall still quite simple and doesn't match the browser in many cases. For example, wrapping does not consider punctuation (lines can begin with punctuation), and whitespace is handled differently (but practically speaking it seems sensible).
| # | Tool | Arguments | Result |
|---|---|---|---|
| No trace captured. | |||
--- a/rich/_wrap.py
+++ b/rich/_wrap.py
@@ -1,13 +1,19 @@
+from __future__ import annotations
+
import re
-from typing import Iterable, List, Tuple
+from typing import Iterable
from ._loop import loop_last
from .cells import cell_len, chop_cells
re_word = re.compile(r"\s*\S+\s*")
-def words(text: str) -> Iterable[Tuple[int, int, str]]:
+def words(text: str) -> Iterable[tuple[int, int, str]]:
+ """Yields each word from the text as a tuple
+ containing (start_index, end_index, word). A "word" in this context may
+ include the actual word and any whitespace to the right.
+ """
position = 0
word_match = re_word.match(text, position)
while word_match is not None:
@@ -17,40 +23,71 @@ def words(text: str) -> Iterable[Tuple[int, int, str]]:
word_match = re_word.match(text, end)
-def divide_line(text: str, width: int, fold: bool = True) -> List[int]:
- divides: List[int] = []
- append = divides.append
- line_position = 0
+def divide_line(text: str, width: int, fold: bool = True) -> list[int]:
+ """Given a string of text, and a width (measured in cells), return a list
+ of cell offsets which the string should be split at in order for it to fit
+ within the given width.
+
+ Args:
+ text: The text to examine.
+ width: The available cell width.
+ fold: If True, words longer than `width` will be folded onto a new line.
+
+ Returns:
+ A list of indices to break the line at.
+ """
+ break_positions: list[int] = [] # offsets to insert the breaks at
+ append = break_positions.append
+ cell_offset = 0
_cell_len = cell_len
+
for start, _end, word in words(text):
word_length = _cell_len(word.rstrip())
- if line_position + word_length > width:
+ remaining_space = width - cell_offset
+ word_fits_remaining_space = remaining_space >= word_length
+
+ if word_fits_remaining_space:
+ # Simplest case - the word fits within the remaining width for this line.
+ cell_offset += _cell_len(word)
+ else:
+ # Not enough space remaining for this word on the current line.
if word_length > width:
+ # The word doesn't fit on any line, so we can't simply
+ # place it on the next line...
if fold:
- chopped_words = chop_cells(word, max_size=width, position=0)
- for last, line in loop_last(chopped_words):
+ # Fold the word across multiple lines.
+ folded_word = chop_cells(word, width=width)
+ for last, line in loop_last(folded_word):
if start:
append(start)
-
if last:
- line_position = _cell_len(line)
+ cell_offset = _cell_len(line)
else:
start += len(line)
else:
+ # Folding isn't allowed, so crop the word.
if start:
append(start)
- line_position = _cell_len(word)
- elif line_position and start:
+ cell_offset = _cell_len(word)
+ elif cell_offset and start:
+ # The word doesn't fit within the remaining space on the current
+ # line, but it *can* fit on to the next (empty) line.
append(start)
- line_position = _cell_len(word)
- else:
- line_position += _cell_len(word)
- return divides
+ cell_offset = _cell_len(word)
+
+ return break_positions
if __name__ == "__main__": # pragma: no cover
from .console import Console
console = Console(width=10)
console.print("12345 abcdefghijklmnopqrstuvwyxzABCDEFGHIJKLMNOPQRSTUVWXYZ 12345")
- print(chop_cells("abcdefghijklmnopqrstuvwxyz", 10, position=2))
+ print(chop_cells("abcdefghijklmnopqrstuvwxyz", 10))
+
+ console = Console(width=20)
+ console.rule()
+ console.print("TextualはPythonの高速アプリケーション開発フレームワークです")
+
+ console.rule()
+ console.print("アプリケーションは1670万色を使用でき")
--- a/rich/cells.py
+++ b/rich/cells.py
@@ -1,6 +1,8 @@
+from __future__ import annotations
+
import re
from functools import lru_cache
-from typing import Callable, List
+from typing import Callable
from ._cell_widths import CELL_WIDTHS
@@ -119,27 +121,39 @@ def set_cell_size(text: str, total: int) -> str:
start = pos
-# TODO: This is inefficient
-# TODO: This might not work with CWJ type characters
-def chop_cells(text: str, max_size: int, position: int = 0) -> List[str]:
- """Break text in to equal (cell) length strings, returning the characters in reverse
- order"""
+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
- characters = [
- (character, _get_character_cell_size(character)) for character in text
- ]
- total_size = position
- lines: List[List[str]] = [[]]
- append = lines[-1].append
-
- for character, size in reversed(characters):
- if total_size + size > max_size:
- lines.append([character])
- append = lines[-1].append
- total_size = 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:
- total_size += size
- append(character)
+ append_to_last_line(character)
+ total_width += cell_width
return ["".join(line) for line in lines]
........................................................................ [ 63%] .......................................... [100%] 114 passed in 0.28s