Initial commit: Tamigo CLI with Gitea Actions and global installation support
This commit is contained in:
Daniel Dybing
43
venv/lib/python3.12/site-packages/wcwidth/__init__.py
Normal file
43
venv/lib/python3.12/site-packages/wcwidth/__init__.py
Normal file
@@ -0,0 +1,43 @@
|
||||
"""
|
||||
Wcwidth module.
|
||||
|
||||
https://github.com/jquast/wcwidth
|
||||
"""
|
||||
# re-export all functions & definitions, even private ones, from top-level
|
||||
# module path, to allow for 'from wcwidth import _private_func'. Of course,
|
||||
# user beware that any _private functions or variables not exported by __all__
|
||||
# may disappear or change signature at any future version.
|
||||
|
||||
# local
|
||||
from .wcwidth import ZERO_WIDTH # noqa
|
||||
from .wcwidth import (WIDE_EASTASIAN,
|
||||
AMBIGUOUS_EASTASIAN,
|
||||
VS16_NARROW_TO_WIDE,
|
||||
clip,
|
||||
ljust,
|
||||
rjust,
|
||||
width,
|
||||
center,
|
||||
wcwidth,
|
||||
wcswidth,
|
||||
list_versions,
|
||||
iter_sequences,
|
||||
strip_sequences,
|
||||
_wcmatch_version,
|
||||
_wcversion_value)
|
||||
from .bisearch import bisearch as _bisearch
|
||||
from .grapheme import grapheme_boundary_before # noqa
|
||||
from .grapheme import iter_graphemes, iter_graphemes_reverse
|
||||
from .textwrap import SequenceTextWrapper, wrap
|
||||
from .sgr_state import propagate_sgr
|
||||
|
||||
# The __all__ attribute defines the items exported from statement,
|
||||
# 'from wcwidth import *', but also to say, "This is the public API".
|
||||
__all__ = ('wcwidth', 'wcswidth', 'width', 'iter_sequences', 'iter_graphemes',
|
||||
'iter_graphemes_reverse', 'grapheme_boundary_before',
|
||||
'ljust', 'rjust', 'center', 'wrap', 'clip', 'strip_sequences',
|
||||
'list_versions', 'propagate_sgr')
|
||||
|
||||
# Using 'hatchling', it does not seem to provide the pyproject.toml nicety, "dynamic = ['version']"
|
||||
# like flit_core, maybe there is some better way but for now we have to duplicate it in both places
|
||||
__version__ = '0.6.0'
|
||||
Binary file not shown.
Binary file not shown.
Binary file not shown.
Binary file not shown.
Binary file not shown.
Binary file not shown.
Binary file not shown.
Binary file not shown.
Binary file not shown.
Binary file not shown.
Binary file not shown.
Binary file not shown.
Binary file not shown.
Binary file not shown.
Binary file not shown.
29
venv/lib/python3.12/site-packages/wcwidth/bisearch.py
Normal file
29
venv/lib/python3.12/site-packages/wcwidth/bisearch.py
Normal file
@@ -0,0 +1,29 @@
|
||||
"""Binary search function for Unicode interval tables."""
|
||||
from __future__ import annotations
|
||||
|
||||
|
||||
def bisearch(ucs: int, table: tuple[tuple[int, int], ...]) -> int:
|
||||
"""
|
||||
Binary search in interval table.
|
||||
|
||||
:param ucs: Ordinal value of unicode character.
|
||||
:param table: Tuple of starting and ending ranges of ordinal values,
|
||||
in form of ``((start, end), ...)``.
|
||||
:returns: 1 if ordinal value ucs is found within lookup table, else 0.
|
||||
"""
|
||||
lbound = 0
|
||||
ubound = len(table) - 1
|
||||
|
||||
if ucs < table[0][0] or ucs > table[ubound][1]:
|
||||
return 0
|
||||
|
||||
while ubound >= lbound:
|
||||
mid = (lbound + ubound) // 2
|
||||
if ucs > table[mid][1]:
|
||||
lbound = mid + 1
|
||||
elif ucs < table[mid][0]:
|
||||
ubound = mid - 1
|
||||
else:
|
||||
return 1
|
||||
|
||||
return 0
|
||||
46
venv/lib/python3.12/site-packages/wcwidth/control_codes.py
Normal file
46
venv/lib/python3.12/site-packages/wcwidth/control_codes.py
Normal file
@@ -0,0 +1,46 @@
|
||||
"""
|
||||
Control character sets for terminal handling.
|
||||
|
||||
This module provides the control character sets used by the width() function to handle terminal
|
||||
control characters.
|
||||
"""
|
||||
|
||||
# Illegal C0/C1 control characters.
|
||||
# These raise ValueError in 'strict' mode.
|
||||
ILLEGAL_CTRL = frozenset(
|
||||
chr(c) for c in (
|
||||
list(range(0x01, 0x07)) + # SOH, STX, ETX (^C), EOT (^D), ENQ, ACK
|
||||
list(range(0x10, 0x1b)) + # DLE through SUB (^Z)
|
||||
list(range(0x1c, 0x20)) + # FS, GS, RS, US
|
||||
[0x7f] + # DEL
|
||||
list(range(0x80, 0xa0)) # C1 control characters
|
||||
)
|
||||
)
|
||||
|
||||
# Vertical movement control characters.
|
||||
# These raise ValueError in 'strict' mode (indeterminate horizontal position).
|
||||
VERTICAL_CTRL = frozenset({
|
||||
'\x0a', # LF (line feed)
|
||||
'\x0b', # VT (vertical tab)
|
||||
'\x0c', # FF (form feed)
|
||||
})
|
||||
|
||||
# Horizontal movement control characters.
|
||||
# These affect cursor position and are tracked in 'strict' and 'parse' modes.
|
||||
HORIZONTAL_CTRL = frozenset({
|
||||
'\x08', # BS (backspace) - cursor left 1
|
||||
'\x09', # HT (horizontal tab) - advance to next tab stop
|
||||
'\x0d', # CR (carriage return) - cursor to column 0
|
||||
})
|
||||
|
||||
# Terminal-valid zero-width control characters.
|
||||
# These are allowed in all modes (zero-width, no movement).
|
||||
ZERO_WIDTH_CTRL = frozenset({
|
||||
'\x00', # NUL
|
||||
'\x07', # BEL (bell)
|
||||
'\x0e', # SO (shift out)
|
||||
'\x0f', # SI (shift in)
|
||||
})
|
||||
|
||||
# All control characters that need special handling (not regular printable).
|
||||
ALL_CTRL = ILLEGAL_CTRL | VERTICAL_CTRL | HORIZONTAL_CTRL | ZERO_WIDTH_CTRL | {'\x1b'}
|
||||
@@ -0,0 +1,69 @@
|
||||
r"""
|
||||
Terminal escape sequence patterns.
|
||||
|
||||
This module provides regex patterns for matching terminal escape sequences. All patterns match
|
||||
sequences that begin with ESC (``\x1b``). Before calling re.match with these patterns, callers
|
||||
should first check that the character at the current position is ESC for optimal performance.
|
||||
"""
|
||||
# std imports
|
||||
import re
|
||||
|
||||
# Zero-width escape sequences (SGR, OSC, CSI, etc.). This table, like INDETERMINATE_EFFECT_SEQUENCE,
|
||||
# originated from the 'blessed' library.
|
||||
ZERO_WIDTH_PATTERN = re.compile(
|
||||
# CSI sequences
|
||||
r'\x1b\[[\x30-\x3f]*[\x20-\x2f]*[\x40-\x7e]|'
|
||||
# OSC sequences
|
||||
r'\x1b\][^\x07\x1b]*(?:\x07|\x1b\\)|'
|
||||
# APC sequences
|
||||
r'\x1b_[^\x1b\x07]*(?:\x07|\x1b\\)|'
|
||||
# DCS sequences
|
||||
r'\x1bP[^\x1b\x07]*(?:\x07|\x1b\\)|'
|
||||
# PM sequences
|
||||
r'\x1b\^[^\x1b\x07]*(?:\x07|\x1b\\)|'
|
||||
# Character set designation
|
||||
r'\x1b[()].|'
|
||||
# Fe sequences
|
||||
r'\x1b[\x40-\x5f]|'
|
||||
# Fp sequences
|
||||
r'\x1b[78=>g]'
|
||||
)
|
||||
|
||||
# Cursor right movement: CSI [n] C, parameter may be parsed by width()
|
||||
CURSOR_RIGHT_SEQUENCE = re.compile(r'\x1b\[(\d*)C')
|
||||
|
||||
# Cursor left movement: CSI [n] D, parameter may be parsed by width()
|
||||
CURSOR_LEFT_SEQUENCE = re.compile(r'\x1b\[(\d*)D')
|
||||
|
||||
# Indeterminate effect sequences - raise ValueError in 'strict' mode. The effects of these sequences
|
||||
# are likely to be undesirable, moving the cursor vertically or to any unknown position, and
|
||||
# otherwise not managed by the 'width' method of this library.
|
||||
#
|
||||
# This table was created initially with code generation by extraction of termcap library with
|
||||
# techniques used at 'blessed' library runtime for 'xterm', 'alacritty', 'kitty', ghostty',
|
||||
# 'screen', 'tmux', and others. Then, these common capabilities were merged into the list below.
|
||||
INDETERMINATE_EFFECT_SEQUENCE = re.compile(
|
||||
'|'.join(f'(?:{_pattern})' for _pattern in (
|
||||
r'\x1b\[\d+;\d+r', # change_scroll_region
|
||||
r'\x1b\[\d*K', # erase_in_line (clr_eol, clr_bol)
|
||||
r'\x1b\[\d*J', # erase_in_display (clr_eos, erase_display)
|
||||
r'\x1b\[\d*G', # column_address
|
||||
r'\x1b\[\d+;\d+H', # cursor_address
|
||||
r'\x1b\[\d*H', # cursor_home
|
||||
r'\x1b\[\d*A', # cursor_up
|
||||
r'\x1b\[\d*B', # cursor_down
|
||||
r'\x1b\[\d*P', # delete_character
|
||||
r'\x1b\[\d*M', # delete_line
|
||||
r'\x1b\[\d*L', # insert_line
|
||||
r'\x1b\[\d*@', # insert_character
|
||||
r'\x1b\[\d+X', # erase_chars
|
||||
r'\x1b\[\d*S', # scroll_up (parm_index)
|
||||
r'\x1b\[\d*T', # scroll_down (parm_rindex)
|
||||
r'\x1b\[\d*d', # row_address
|
||||
r'\x1b\[\?1049[hl]', # alternate screen buffer
|
||||
r'\x1b\[\?47[hl]', # alternate screen (legacy)
|
||||
r'\x1b8', # restore_cursor
|
||||
r'\x1bD', # scroll_forward (index)
|
||||
r'\x1bM', # scroll_reverse (reverse index)
|
||||
))
|
||||
)
|
||||
428
venv/lib/python3.12/site-packages/wcwidth/grapheme.py
Normal file
428
venv/lib/python3.12/site-packages/wcwidth/grapheme.py
Normal file
@@ -0,0 +1,428 @@
|
||||
"""
|
||||
Grapheme cluster segmentation following Unicode Standard Annex #29.
|
||||
|
||||
This module provides pure-Python implementation of the grapheme cluster boundary algorithm as
|
||||
defined in UAX #29: Unicode Text Segmentation.
|
||||
|
||||
https://www.unicode.org/reports/tr29/
|
||||
"""
|
||||
|
||||
from __future__ import annotations
|
||||
|
||||
# std imports
|
||||
from enum import IntEnum
|
||||
from functools import lru_cache
|
||||
|
||||
from typing import TYPE_CHECKING, NamedTuple
|
||||
|
||||
# local
|
||||
from .bisearch import bisearch as _bisearch
|
||||
from .table_grapheme import (GRAPHEME_L,
|
||||
GRAPHEME_T,
|
||||
GRAPHEME_V,
|
||||
GRAPHEME_LV,
|
||||
INCB_EXTEND,
|
||||
INCB_LINKER,
|
||||
GRAPHEME_LVT,
|
||||
INCB_CONSONANT,
|
||||
GRAPHEME_EXTEND,
|
||||
GRAPHEME_CONTROL,
|
||||
GRAPHEME_PREPEND,
|
||||
GRAPHEME_SPACINGMARK,
|
||||
EXTENDED_PICTOGRAPHIC,
|
||||
GRAPHEME_REGIONAL_INDICATOR)
|
||||
|
||||
if TYPE_CHECKING: # pragma: no cover
|
||||
# std imports
|
||||
from collections.abc import Iterator
|
||||
|
||||
# Maximum backward scan distance when finding grapheme cluster boundaries.
|
||||
# Covers all known Unicode grapheme clusters with margin; longer sequences are pathological.
|
||||
MAX_GRAPHEME_SCAN = 32
|
||||
|
||||
|
||||
class GCB(IntEnum):
|
||||
"""Grapheme Cluster Break property values."""
|
||||
|
||||
OTHER = 0
|
||||
CR = 1
|
||||
LF = 2
|
||||
CONTROL = 3
|
||||
EXTEND = 4
|
||||
ZWJ = 5
|
||||
REGIONAL_INDICATOR = 6
|
||||
PREPEND = 7
|
||||
SPACING_MARK = 8
|
||||
L = 9
|
||||
V = 10
|
||||
T = 11
|
||||
LV = 12
|
||||
LVT = 13
|
||||
|
||||
|
||||
# All lru_cache sizes in this file use maxsize=1024, chosen by benchmarking UDHR data (500+
|
||||
# languages) and considering typical process-long sessions: western scripts need ~64 unique
|
||||
# codepoints, but CJK could reach ~2000 -- but likely not.
|
||||
@lru_cache(maxsize=1024)
|
||||
def _grapheme_cluster_break(ucs: int) -> GCB:
|
||||
# pylint: disable=too-many-branches,too-complex
|
||||
"""Return the Grapheme_Cluster_Break property for a codepoint."""
|
||||
# Single codepoint matches
|
||||
if ucs == 0x000d:
|
||||
return GCB.CR
|
||||
if ucs == 0x000a:
|
||||
return GCB.LF
|
||||
if ucs == 0x200d:
|
||||
return GCB.ZWJ
|
||||
# Matching by codepoint ranges, requiring binary search
|
||||
if _bisearch(ucs, GRAPHEME_CONTROL):
|
||||
return GCB.CONTROL
|
||||
if _bisearch(ucs, GRAPHEME_EXTEND):
|
||||
return GCB.EXTEND
|
||||
if _bisearch(ucs, GRAPHEME_REGIONAL_INDICATOR):
|
||||
return GCB.REGIONAL_INDICATOR
|
||||
if _bisearch(ucs, GRAPHEME_PREPEND):
|
||||
return GCB.PREPEND
|
||||
if _bisearch(ucs, GRAPHEME_SPACINGMARK):
|
||||
return GCB.SPACING_MARK
|
||||
if _bisearch(ucs, GRAPHEME_L):
|
||||
return GCB.L
|
||||
if _bisearch(ucs, GRAPHEME_V):
|
||||
return GCB.V
|
||||
if _bisearch(ucs, GRAPHEME_T):
|
||||
return GCB.T
|
||||
if _bisearch(ucs, GRAPHEME_LV):
|
||||
return GCB.LV
|
||||
if _bisearch(ucs, GRAPHEME_LVT):
|
||||
return GCB.LVT
|
||||
return GCB.OTHER
|
||||
|
||||
|
||||
@lru_cache(maxsize=1024)
|
||||
def _is_extended_pictographic(ucs: int) -> bool:
|
||||
"""Check if codepoint has Extended_Pictographic property."""
|
||||
return bool(_bisearch(ucs, EXTENDED_PICTOGRAPHIC))
|
||||
|
||||
|
||||
@lru_cache(maxsize=1024)
|
||||
def _is_incb_linker(ucs: int) -> bool:
|
||||
"""Check if codepoint has InCB=Linker property."""
|
||||
return bool(_bisearch(ucs, INCB_LINKER))
|
||||
|
||||
|
||||
@lru_cache(maxsize=1024)
|
||||
def _is_incb_consonant(ucs: int) -> bool:
|
||||
"""Check if codepoint has InCB=Consonant property."""
|
||||
return bool(_bisearch(ucs, INCB_CONSONANT))
|
||||
|
||||
|
||||
@lru_cache(maxsize=1024)
|
||||
def _is_incb_extend(ucs: int) -> bool:
|
||||
"""Check if codepoint has InCB=Extend property."""
|
||||
return bool(_bisearch(ucs, INCB_EXTEND))
|
||||
|
||||
|
||||
class BreakResult(NamedTuple):
|
||||
"""Result of grapheme cluster break decision."""
|
||||
|
||||
should_break: bool
|
||||
ri_count: int
|
||||
|
||||
|
||||
@lru_cache(maxsize=1024)
|
||||
def _simple_break_check(prev_gcb: GCB, curr_gcb: GCB) -> BreakResult | None:
|
||||
"""
|
||||
Check simple GCB-pair-based break rules (cacheable).
|
||||
|
||||
Returns BreakResult for rules that can be determined from GCB properties alone, or None if
|
||||
complex lookback rules (GB9c, GB11) need to be checked.
|
||||
"""
|
||||
# GB3: CR x LF
|
||||
if prev_gcb == GCB.CR and curr_gcb == GCB.LF:
|
||||
return BreakResult(should_break=False, ri_count=0)
|
||||
|
||||
# GB4: (Control|CR|LF) ÷
|
||||
if prev_gcb in (GCB.CONTROL, GCB.CR, GCB.LF):
|
||||
return BreakResult(should_break=True, ri_count=0)
|
||||
|
||||
# GB5: ÷ (Control|CR|LF)
|
||||
if curr_gcb in (GCB.CONTROL, GCB.CR, GCB.LF):
|
||||
return BreakResult(should_break=True, ri_count=0)
|
||||
|
||||
# GB6: L x (L|V|LV|LVT)
|
||||
if prev_gcb == GCB.L and curr_gcb in (GCB.L, GCB.V, GCB.LV, GCB.LVT):
|
||||
return BreakResult(should_break=False, ri_count=0)
|
||||
|
||||
# GB7: (LV|V) x (V|T)
|
||||
if prev_gcb in (GCB.LV, GCB.V) and curr_gcb in (GCB.V, GCB.T):
|
||||
return BreakResult(should_break=False, ri_count=0)
|
||||
|
||||
# GB8: (LVT|T) x T
|
||||
if prev_gcb in (GCB.LVT, GCB.T) and curr_gcb == GCB.T:
|
||||
return BreakResult(should_break=False, ri_count=0)
|
||||
|
||||
# GB9: x (Extend|ZWJ) - but ZWJ needs GB11 check, so only handle Extend here
|
||||
if curr_gcb == GCB.EXTEND:
|
||||
return BreakResult(should_break=False, ri_count=0)
|
||||
|
||||
# GB9a: x SpacingMark
|
||||
if curr_gcb == GCB.SPACING_MARK:
|
||||
return BreakResult(should_break=False, ri_count=0)
|
||||
|
||||
# GB9b: Prepend x
|
||||
if prev_gcb == GCB.PREPEND:
|
||||
return BreakResult(should_break=False, ri_count=0)
|
||||
|
||||
# GB9c and GB11 need lookback - return None to signal complex check needed
|
||||
# GB12/13 (RI pairs) need ri_count state - also handled in main function
|
||||
return None
|
||||
|
||||
|
||||
def _should_break(
|
||||
prev_gcb: GCB,
|
||||
curr_gcb: GCB,
|
||||
text: str,
|
||||
curr_idx: int,
|
||||
ri_count: int,
|
||||
) -> BreakResult:
|
||||
# pylint: disable=too-many-branches,too-complex
|
||||
"""
|
||||
Determine if there should be a grapheme cluster break between prev and curr.
|
||||
|
||||
Implements UAX #29 grapheme cluster boundary rules.
|
||||
"""
|
||||
# Try cached simple rules first
|
||||
result = _simple_break_check(prev_gcb, curr_gcb)
|
||||
if result is not None:
|
||||
return result
|
||||
|
||||
# GB9: x ZWJ (not cached because GB11 needs lookback when prev is ZWJ)
|
||||
if curr_gcb == GCB.ZWJ:
|
||||
return BreakResult(should_break=False, ri_count=0)
|
||||
|
||||
# GB9c: Indic conjunct cluster
|
||||
# \p{InCB=Consonant} [\p{InCB=Extend}\p{InCB=Linker}]* \p{InCB=Linker}
|
||||
# [\p{InCB=Extend}\p{InCB=Linker}]* x \p{InCB=Consonant}
|
||||
curr_ucs = ord(text[curr_idx])
|
||||
if _is_incb_consonant(curr_ucs):
|
||||
has_linker = False
|
||||
i = curr_idx - 1
|
||||
while i >= 0:
|
||||
prev_ucs = ord(text[i])
|
||||
if _is_incb_linker(prev_ucs):
|
||||
has_linker = True
|
||||
i -= 1
|
||||
elif _is_incb_extend(prev_ucs):
|
||||
i -= 1
|
||||
elif _is_incb_consonant(prev_ucs):
|
||||
if has_linker:
|
||||
return BreakResult(should_break=False, ri_count=0)
|
||||
break
|
||||
else:
|
||||
break
|
||||
|
||||
# GB11: ExtPict Extend* ZWJ x ExtPict
|
||||
if prev_gcb == GCB.ZWJ and _is_extended_pictographic(curr_ucs):
|
||||
i = curr_idx - 2 # Skip the ZWJ at curr_idx - 1
|
||||
while i >= 0:
|
||||
prev_ucs = ord(text[i])
|
||||
prev_prop = _grapheme_cluster_break(prev_ucs)
|
||||
if prev_prop == GCB.EXTEND:
|
||||
i -= 1
|
||||
elif _is_extended_pictographic(prev_ucs):
|
||||
return BreakResult(should_break=False, ri_count=0)
|
||||
else:
|
||||
break
|
||||
|
||||
# GB12/GB13: RI x RI (pair matching)
|
||||
if prev_gcb == GCB.REGIONAL_INDICATOR and curr_gcb == GCB.REGIONAL_INDICATOR:
|
||||
if ri_count % 2 == 1:
|
||||
return BreakResult(should_break=False, ri_count=ri_count + 1)
|
||||
return BreakResult(should_break=True, ri_count=1)
|
||||
|
||||
# GB999: Any ÷ Any
|
||||
ri_count = 1 if curr_gcb == GCB.REGIONAL_INDICATOR else 0
|
||||
return BreakResult(should_break=True, ri_count=ri_count)
|
||||
|
||||
|
||||
def iter_graphemes(
|
||||
unistr: str,
|
||||
start: int = 0,
|
||||
end: int | None = None,
|
||||
) -> Iterator[str]:
|
||||
r"""
|
||||
Iterate over grapheme clusters in a Unicode string.
|
||||
|
||||
Grapheme clusters are "user-perceived characters" - what a user would
|
||||
consider a single character, which may consist of multiple Unicode
|
||||
codepoints (e.g., a base character with combining marks, emoji sequences).
|
||||
|
||||
:param unistr: The Unicode string to segment.
|
||||
:param start: Starting index (default 0).
|
||||
:param end: Ending index (default len(unistr)).
|
||||
:yields: Grapheme cluster substrings.
|
||||
|
||||
Example::
|
||||
|
||||
>>> list(iter_graphemes('cafe\u0301'))
|
||||
['c', 'a', 'f', 'e\u0301']
|
||||
>>> list(iter_graphemes('\U0001F468\u200D\U0001F469\u200D\U0001F467'))
|
||||
['o', 'k', '\U0001F468\u200D\U0001F469\u200D\U0001F467']
|
||||
>>> list(iter_graphemes('\U0001F1FA\U0001F1F8'))
|
||||
['o', 'k', '\U0001F1FA\U0001F1F8']
|
||||
|
||||
.. versionadded:: 0.3.0
|
||||
"""
|
||||
if not unistr:
|
||||
return
|
||||
|
||||
length = len(unistr)
|
||||
|
||||
if end is None:
|
||||
end = length
|
||||
|
||||
if start >= end or start >= length:
|
||||
return
|
||||
|
||||
end = min(end, length)
|
||||
|
||||
# Track state for grapheme cluster boundaries
|
||||
cluster_start = start
|
||||
ri_count = 0
|
||||
|
||||
# Get GCB for first character
|
||||
prev_gcb = _grapheme_cluster_break(ord(unistr[start]))
|
||||
|
||||
# Handle Regional Indicator count initialization
|
||||
if prev_gcb == GCB.REGIONAL_INDICATOR:
|
||||
ri_count = 1
|
||||
|
||||
for idx in range(start + 1, end):
|
||||
curr_gcb = _grapheme_cluster_break(ord(unistr[idx]))
|
||||
|
||||
result = _should_break(prev_gcb, curr_gcb, unistr, idx, ri_count)
|
||||
ri_count = result.ri_count
|
||||
|
||||
if result.should_break:
|
||||
yield unistr[cluster_start:idx]
|
||||
cluster_start = idx
|
||||
|
||||
prev_gcb = curr_gcb
|
||||
|
||||
# Yield the final cluster
|
||||
yield unistr[cluster_start:end]
|
||||
|
||||
|
||||
def _find_cluster_start(text: str, pos: int) -> int:
|
||||
"""
|
||||
Find the start of the grapheme cluster containing the character before pos.
|
||||
|
||||
Scans backwards from pos to find a safe starting point, then iterates forward using standard
|
||||
break rules to find the actual cluster boundary.
|
||||
|
||||
:param text: The Unicode string.
|
||||
:param pos: Position to search before (exclusive).
|
||||
:returns: Start position of the grapheme cluster.
|
||||
"""
|
||||
target_cp = ord(text[pos - 1])
|
||||
|
||||
# GB3: CR x LF - LF after CR is part of same cluster
|
||||
if target_cp == 0x0A and pos >= 2 and text[pos - 2] == '\r':
|
||||
return pos - 2
|
||||
|
||||
# Fast path: ASCII (except LF) starts its own cluster
|
||||
if target_cp < 0x80:
|
||||
# GB9b: Check for preceding PREPEND (rare: Arabic/Brahmic)
|
||||
if pos >= 2 and target_cp >= 0x20:
|
||||
prev_cp = ord(text[pos - 2])
|
||||
if prev_cp >= 0x80 and _grapheme_cluster_break(prev_cp) == GCB.PREPEND:
|
||||
return _find_cluster_start(text, pos - 1)
|
||||
return pos - 1
|
||||
|
||||
# Scan backward to find a safe starting point
|
||||
safe_start = pos - 1
|
||||
while safe_start > 0 and (pos - safe_start) < MAX_GRAPHEME_SCAN:
|
||||
cp = ord(text[safe_start])
|
||||
if 0x20 <= cp < 0x80: # ASCII always starts a cluster
|
||||
break
|
||||
if _grapheme_cluster_break(cp) == GCB.CONTROL: # GB4
|
||||
break
|
||||
safe_start -= 1
|
||||
|
||||
# Verify forward to find the actual cluster boundary
|
||||
cluster_start = safe_start
|
||||
left_gcb = _grapheme_cluster_break(ord(text[safe_start]))
|
||||
ri_count = 1 if left_gcb == GCB.REGIONAL_INDICATOR else 0
|
||||
|
||||
for i in range(safe_start + 1, pos):
|
||||
right_gcb = _grapheme_cluster_break(ord(text[i]))
|
||||
result = _should_break(left_gcb, right_gcb, text, i, ri_count)
|
||||
ri_count = result.ri_count
|
||||
if result.should_break:
|
||||
cluster_start = i
|
||||
left_gcb = right_gcb
|
||||
|
||||
return cluster_start
|
||||
|
||||
|
||||
def grapheme_boundary_before(unistr: str, pos: int) -> int:
|
||||
r"""
|
||||
Find the grapheme cluster boundary immediately before a position.
|
||||
|
||||
:param unistr: The Unicode string to search.
|
||||
:param pos: Position in the string (0 < pos <= len(unistr)).
|
||||
:returns: Start index of the grapheme cluster containing the character at pos-1.
|
||||
|
||||
Example::
|
||||
|
||||
>>> grapheme_boundary_before('Hello \U0001F44B\U0001F3FB', 8)
|
||||
6
|
||||
>>> grapheme_boundary_before('a\r\nb', 3)
|
||||
1
|
||||
|
||||
.. versionadded:: 0.3.6
|
||||
"""
|
||||
if pos <= 0:
|
||||
return 0
|
||||
return _find_cluster_start(unistr, min(pos, len(unistr)))
|
||||
|
||||
|
||||
def iter_graphemes_reverse(
|
||||
unistr: str,
|
||||
start: int = 0,
|
||||
end: int | None = None,
|
||||
) -> Iterator[str]:
|
||||
r"""
|
||||
Iterate over grapheme clusters in reverse order (last to first).
|
||||
|
||||
:param unistr: The Unicode string to segment.
|
||||
:param start: Starting index (default 0).
|
||||
:param end: Ending index (default len(unistr)).
|
||||
:yields: Grapheme cluster substrings in reverse order.
|
||||
|
||||
Example::
|
||||
|
||||
>>> list(iter_graphemes_reverse('cafe\u0301'))
|
||||
['e\u0301', 'f', 'a', 'c']
|
||||
|
||||
.. versionadded:: 0.3.6
|
||||
"""
|
||||
if not unistr:
|
||||
return
|
||||
|
||||
length = len(unistr)
|
||||
|
||||
end = length if end is None else min(end, length)
|
||||
start = max(start, 0)
|
||||
|
||||
if start >= end or start >= length:
|
||||
return
|
||||
|
||||
pos = end
|
||||
while pos > start:
|
||||
cluster_start = _find_cluster_start(unistr, pos)
|
||||
# Don't yield partial graphemes that extend before start
|
||||
if cluster_start < start:
|
||||
break
|
||||
yield unistr[cluster_start:pos]
|
||||
pos = cluster_start
|
||||
0
venv/lib/python3.12/site-packages/wcwidth/py.typed
Normal file
0
venv/lib/python3.12/site-packages/wcwidth/py.typed
Normal file
338
venv/lib/python3.12/site-packages/wcwidth/sgr_state.py
Normal file
338
venv/lib/python3.12/site-packages/wcwidth/sgr_state.py
Normal file
@@ -0,0 +1,338 @@
|
||||
"""
|
||||
SGR (Select Graphic Rendition) state tracking for terminal escape sequences.
|
||||
|
||||
This module provides functions for tracking and propagating terminal styling (bold, italic, colors,
|
||||
etc.) via public API propagate_sgr(), and its dependent functions, cut() and wrap(). It only has
|
||||
attributes necessary to perform its functions, eg 'RED' and 'BLUE' attributes are not defined.
|
||||
"""
|
||||
from __future__ import annotations
|
||||
|
||||
# std imports
|
||||
import re
|
||||
from enum import IntEnum
|
||||
|
||||
from typing import TYPE_CHECKING, Iterator, NamedTuple
|
||||
|
||||
if TYPE_CHECKING: # pragma: no cover
|
||||
from typing import Sequence
|
||||
|
||||
|
||||
class _SGR(IntEnum):
|
||||
"""
|
||||
SGR (Select Graphic Rendition) parameter codes.
|
||||
|
||||
References:
|
||||
- https://invisible-island.net/xterm/ctlseqs/ctlseqs.html
|
||||
- https://github.com/tehmaze/ansi/tree/master/ansi/colour
|
||||
"""
|
||||
|
||||
RESET = 0
|
||||
BOLD = 1
|
||||
DIM = 2
|
||||
ITALIC = 3
|
||||
UNDERLINE = 4
|
||||
BLINK = 5
|
||||
RAPID_BLINK = 6
|
||||
INVERSE = 7
|
||||
HIDDEN = 8
|
||||
STRIKETHROUGH = 9
|
||||
DOUBLE_UNDERLINE = 21
|
||||
BOLD_DIM_OFF = 22
|
||||
ITALIC_OFF = 23
|
||||
UNDERLINE_OFF = 24
|
||||
BLINK_OFF = 25
|
||||
INVERSE_OFF = 27
|
||||
HIDDEN_OFF = 28
|
||||
STRIKETHROUGH_OFF = 29
|
||||
FG_BLACK = 30
|
||||
FG_WHITE = 37
|
||||
FG_EXTENDED = 38
|
||||
FG_DEFAULT = 39
|
||||
BG_BLACK = 40
|
||||
BG_WHITE = 47
|
||||
BG_EXTENDED = 48
|
||||
BG_DEFAULT = 49
|
||||
FG_BRIGHT_BLACK = 90
|
||||
FG_BRIGHT_WHITE = 97
|
||||
BG_BRIGHT_BLACK = 100
|
||||
BG_BRIGHT_WHITE = 107
|
||||
|
||||
|
||||
# SGR sequence pattern: CSI followed by params (digits, semicolons, colons) ending with 'm'
|
||||
# Colons are used in ITU T.416 (ISO 8613-6) extended color format: 38:2::R:G:B
|
||||
# This colon format is less common than semicolon (38;2;R;G;B) but supported by kitty,
|
||||
# iTerm2, and newer VTE-based terminals.
|
||||
_SGR_PATTERN = re.compile(r'\x1b\[([\d;:]*)m')
|
||||
|
||||
# Fast path: quick check if any SGR sequence exists
|
||||
_SGR_QUICK_CHECK = re.compile(r'\x1b\[[\d;:]*m')
|
||||
|
||||
# Reset sequence
|
||||
_SGR_RESET = '\x1b[0m'
|
||||
|
||||
|
||||
class _SGRState(NamedTuple):
|
||||
"""
|
||||
Track active SGR terminal attributes by category (immutable).
|
||||
|
||||
:param bold: Bold attribute (SGR 1).
|
||||
:param dim: Dim/faint attribute (SGR 2).
|
||||
:param italic: Italic attribute (SGR 3).
|
||||
:param underline: Underline attribute (SGR 4).
|
||||
:param blink: Slow blink attribute (SGR 5).
|
||||
:param rapid_blink: Rapid blink attribute (SGR 6).
|
||||
:param inverse: Inverse/reverse attribute (SGR 7).
|
||||
:param hidden: Hidden/invisible attribute (SGR 8).
|
||||
:param strikethrough: Strikethrough attribute (SGR 9).
|
||||
:param double_underline: Double underline attribute (SGR 21).
|
||||
:param foreground: Foreground color as tuple of SGR params, or None for default.
|
||||
:param background: Background color as tuple of SGR params, or None for default.
|
||||
"""
|
||||
|
||||
bold: bool = False
|
||||
dim: bool = False
|
||||
italic: bool = False
|
||||
underline: bool = False
|
||||
blink: bool = False
|
||||
rapid_blink: bool = False
|
||||
inverse: bool = False
|
||||
hidden: bool = False
|
||||
strikethrough: bool = False
|
||||
double_underline: bool = False
|
||||
foreground: tuple[int, ...] | None = None
|
||||
background: tuple[int, ...] | None = None
|
||||
|
||||
|
||||
# Default state with no attributes set
|
||||
_SGR_STATE_DEFAULT = _SGRState()
|
||||
|
||||
|
||||
def _sgr_state_is_active(state: _SGRState) -> bool:
|
||||
"""
|
||||
Return True if any attributes are set.
|
||||
|
||||
:param state: The SGR state to check.
|
||||
:returns: True if any attribute differs from default.
|
||||
"""
|
||||
return (state.bold or state.dim or state.italic or state.underline
|
||||
or state.blink or state.rapid_blink or state.inverse or state.hidden
|
||||
or state.strikethrough or state.double_underline
|
||||
or state.foreground is not None or state.background is not None)
|
||||
|
||||
|
||||
def _sgr_state_to_sequence(state: _SGRState) -> str:
|
||||
"""
|
||||
Generate minimal SGR sequence to restore this state from reset.
|
||||
|
||||
:param state: The SGR state to convert.
|
||||
:returns: SGR escape sequence string, or empty string if no attributes set.
|
||||
"""
|
||||
if not _sgr_state_is_active(state):
|
||||
return ''
|
||||
|
||||
# Map boolean attributes to their SGR codes
|
||||
bool_attrs = [
|
||||
(state.bold, '1'), (state.dim, '2'), (state.italic, '3'),
|
||||
(state.underline, '4'), (state.blink, '5'), (state.rapid_blink, '6'),
|
||||
(state.inverse, '7'), (state.hidden, '8'), (state.strikethrough, '9'),
|
||||
(state.double_underline, '21'),
|
||||
]
|
||||
params = [code for active, code in bool_attrs if active]
|
||||
|
||||
# Add color params (already formatted as tuples)
|
||||
if state.foreground is not None:
|
||||
params.append(';'.join(str(p) for p in state.foreground))
|
||||
if state.background is not None:
|
||||
params.append(';'.join(str(p) for p in state.background))
|
||||
|
||||
return f'\x1b[{";".join(params)}m'
|
||||
|
||||
|
||||
def _parse_sgr_params(sequence: str) -> list[int | tuple[int, ...]]:
|
||||
r"""
|
||||
Parse SGR sequence and return list of parameter values.
|
||||
|
||||
Handles compound sequences like ``\x1b[1;31;4m`` -> [1, 31, 4].
|
||||
Empty params (e.g., ``\x1b[m``) are treated as [0] (reset).
|
||||
Colon-separated extended colors like ``\x1b[38:2::255:0:0m`` are returned
|
||||
as tuples: [(38, 2, 255, 0, 0)].
|
||||
|
||||
:param sequence: SGR escape sequence string.
|
||||
:returns: List of integer parameters or tuples for colon-separated colors.
|
||||
"""
|
||||
match = _SGR_PATTERN.match(sequence)
|
||||
if not match:
|
||||
return []
|
||||
params_str = match.group(1)
|
||||
if not params_str:
|
||||
return [0] # \x1b[m is equivalent to \x1b[0m
|
||||
result: list[int | tuple[int, ...]] = []
|
||||
for param in params_str.split(';'):
|
||||
if ':' in param:
|
||||
# Colon-separated extended color (ITU T.416 format)
|
||||
# e.g., "38:2::255:0:0" or "38:2:1:255:0:0" (with colorspace)
|
||||
parts = [int(p) if p else 0 for p in param.split(':')]
|
||||
result.append(tuple(parts))
|
||||
else:
|
||||
result.append(int(param) if param else 0)
|
||||
return result
|
||||
|
||||
|
||||
def _parse_extended_color(
|
||||
params: Iterator[int | tuple[int, ...]], base: int
|
||||
) -> tuple[int, ...] | None:
|
||||
"""
|
||||
Parse extended color (256-color or RGB) from parameter iterator.
|
||||
|
||||
:param params: Iterator of remaining SGR parameters (semicolon-separated format).
|
||||
:param base: Base code (38 for foreground, 48 for background).
|
||||
:returns: Color tuple like (38, 5, N) or (38, 2, R, G, B), or None if malformed.
|
||||
"""
|
||||
try:
|
||||
mode = next(params)
|
||||
if isinstance(mode, tuple):
|
||||
return None # Unexpected tuple, colon format handled separately
|
||||
if mode == 5: # 256-color
|
||||
n = next(params)
|
||||
if isinstance(n, tuple):
|
||||
return None
|
||||
return (int(base), 5, n)
|
||||
if mode == 2: # RGB
|
||||
r, g, b = next(params), next(params), next(params)
|
||||
if isinstance(r, tuple) or isinstance(g, tuple) or isinstance(b, tuple):
|
||||
return None
|
||||
return (int(base), 2, r, g, b)
|
||||
except StopIteration:
|
||||
pass
|
||||
return None
|
||||
|
||||
|
||||
def _sgr_state_update(state: _SGRState, sequence: str) -> _SGRState:
|
||||
# pylint: disable=too-many-branches,too-complex,too-many-statements
|
||||
# NOTE: When minimum Python version is 3.10+, this can be simplified using match/case.
|
||||
"""
|
||||
Parse SGR sequence and return new state with updates applied.
|
||||
|
||||
:param state: Current SGR state.
|
||||
:param sequence: SGR escape sequence string.
|
||||
:returns: New SGRState with updates applied.
|
||||
"""
|
||||
params_list = _parse_sgr_params(sequence)
|
||||
params = iter(params_list)
|
||||
for p in params:
|
||||
# Handle colon-separated extended colors (ITU T.416 format)
|
||||
if isinstance(p, tuple):
|
||||
if len(p) >= 2 and p[0] == _SGR.FG_EXTENDED:
|
||||
# Foreground: (38, 2, [colorspace,] R, G, B) or (38, 5, N)
|
||||
state = state._replace(foreground=p)
|
||||
elif len(p) >= 2 and p[0] == _SGR.BG_EXTENDED:
|
||||
# Background: (48, 2, [colorspace,] R, G, B) or (48, 5, N)
|
||||
state = state._replace(background=p)
|
||||
continue
|
||||
if p == _SGR.RESET:
|
||||
state = _SGR_STATE_DEFAULT
|
||||
# Attribute ON codes
|
||||
elif p == _SGR.BOLD:
|
||||
state = state._replace(bold=True)
|
||||
elif p == _SGR.DIM:
|
||||
state = state._replace(dim=True)
|
||||
elif p == _SGR.ITALIC:
|
||||
state = state._replace(italic=True)
|
||||
elif p == _SGR.UNDERLINE:
|
||||
state = state._replace(underline=True)
|
||||
elif p == _SGR.BLINK:
|
||||
state = state._replace(blink=True)
|
||||
elif p == _SGR.RAPID_BLINK:
|
||||
state = state._replace(rapid_blink=True)
|
||||
elif p == _SGR.INVERSE:
|
||||
state = state._replace(inverse=True)
|
||||
elif p == _SGR.HIDDEN:
|
||||
state = state._replace(hidden=True)
|
||||
elif p == _SGR.STRIKETHROUGH:
|
||||
state = state._replace(strikethrough=True)
|
||||
elif p == _SGR.DOUBLE_UNDERLINE:
|
||||
state = state._replace(double_underline=True)
|
||||
# Attribute OFF codes
|
||||
elif p == _SGR.BOLD_DIM_OFF:
|
||||
state = state._replace(bold=False, dim=False)
|
||||
elif p == _SGR.ITALIC_OFF:
|
||||
state = state._replace(italic=False)
|
||||
elif p == _SGR.UNDERLINE_OFF:
|
||||
state = state._replace(underline=False, double_underline=False)
|
||||
elif p == _SGR.BLINK_OFF:
|
||||
state = state._replace(blink=False, rapid_blink=False)
|
||||
elif p == _SGR.INVERSE_OFF:
|
||||
state = state._replace(inverse=False)
|
||||
elif p == _SGR.HIDDEN_OFF:
|
||||
state = state._replace(hidden=False)
|
||||
elif p == _SGR.STRIKETHROUGH_OFF:
|
||||
state = state._replace(strikethrough=False)
|
||||
# Basic colors (30-37, 40-47 standard; 90-97, 100-107 bright)
|
||||
elif (_SGR.FG_BLACK <= p <= _SGR.FG_WHITE
|
||||
or _SGR.FG_BRIGHT_BLACK <= p <= _SGR.FG_BRIGHT_WHITE):
|
||||
state = state._replace(foreground=(p,))
|
||||
elif (_SGR.BG_BLACK <= p <= _SGR.BG_WHITE
|
||||
or _SGR.BG_BRIGHT_BLACK <= p <= _SGR.BG_BRIGHT_WHITE):
|
||||
state = state._replace(background=(p,))
|
||||
elif p == _SGR.FG_DEFAULT:
|
||||
state = state._replace(foreground=None)
|
||||
elif p == _SGR.BG_DEFAULT:
|
||||
state = state._replace(background=None)
|
||||
# Extended colors (semicolon-separated format)
|
||||
elif p == _SGR.FG_EXTENDED:
|
||||
if color := _parse_extended_color(params, _SGR.FG_EXTENDED):
|
||||
state = state._replace(foreground=color)
|
||||
elif p == _SGR.BG_EXTENDED:
|
||||
if color := _parse_extended_color(params, _SGR.BG_EXTENDED):
|
||||
state = state._replace(background=color)
|
||||
return state
|
||||
|
||||
|
||||
def propagate_sgr(lines: Sequence[str]) -> list[str]:
|
||||
r"""
|
||||
Propagate SGR codes across wrapped lines.
|
||||
|
||||
When text with SGR styling is wrapped across multiple lines, each line
|
||||
needs to be self-contained for proper display. This function:
|
||||
|
||||
- Ends each line with ``\x1b[0m`` if styles are active (prevents bleeding)
|
||||
- Starts each subsequent line with the active style restored
|
||||
|
||||
:param lines: List of text lines, possibly containing SGR sequences.
|
||||
:returns: List of lines with SGR codes propagated.
|
||||
|
||||
Example::
|
||||
|
||||
>>> propagate_sgr(['\x1b[31mhello', 'world\x1b[0m'])
|
||||
['\x1b[31mhello\x1b[0m', '\x1b[31mworld\x1b[0m']
|
||||
|
||||
This is useful in cases of making special editors and viewers, and is used for the
|
||||
default modes (propagate_sgr=True) of :func:`wcwidth.width` and :func:`wcwidth.clip`.
|
||||
|
||||
When wrapping and clipping text containing SGR sequences, maybe a previous line enabled the BLUE
|
||||
color--if we are viewing *only* the line following, we would want the carry over the BLUE color,
|
||||
and all lines with sequences should end with terminating reset (``\x1b[0m``).
|
||||
"""
|
||||
# Fast path: check if any line contains SGR sequences
|
||||
if not any(_SGR_QUICK_CHECK.search(line) for line in lines) or not lines:
|
||||
return list(lines)
|
||||
|
||||
result: list[str] = []
|
||||
state = _SGR_STATE_DEFAULT
|
||||
|
||||
for line in lines:
|
||||
# Prefix with restoration sequence if state is active
|
||||
prefix = _sgr_state_to_sequence(state)
|
||||
|
||||
# Update state by processing all SGR sequences in this line
|
||||
for match in _SGR_PATTERN.finditer(line):
|
||||
state = _sgr_state_update(state, match.group())
|
||||
|
||||
# Build output line
|
||||
output_line = prefix + line if prefix else line
|
||||
if _sgr_state_is_active(state):
|
||||
output_line = output_line + _SGR_RESET
|
||||
|
||||
result.append(output_line)
|
||||
|
||||
return result
|
||||
189
venv/lib/python3.12/site-packages/wcwidth/table_ambiguous.py
Normal file
189
venv/lib/python3.12/site-packages/wcwidth/table_ambiguous.py
Normal file
@@ -0,0 +1,189 @@
|
||||
"""
|
||||
Exports AMBIGUOUS_EASTASIAN table keyed by supporting unicode version level.
|
||||
|
||||
This code generated by wcwidth/bin/update-tables.py on 2026-01-18 23:27:15 UTC.
|
||||
"""
|
||||
# pylint: disable=duplicate-code
|
||||
AMBIGUOUS_EASTASIAN = {
|
||||
'17.0.0': (
|
||||
# Source: EastAsianWidth-17.0.0.txt
|
||||
# Date: 2025-07-24, 00:12:54 GMT
|
||||
#
|
||||
(0x000a1, 0x000a1,), # Inverted Exclamation Mark
|
||||
(0x000a4, 0x000a4,), # Currency Sign
|
||||
(0x000a7, 0x000a8,), # Section Sign ..Diaeresis
|
||||
(0x000aa, 0x000aa,), # Feminine Ordinal Indicator
|
||||
(0x000ad, 0x000ae,), # Soft Hyphen ..Registered Sign
|
||||
(0x000b0, 0x000b4,), # Degree Sign ..Acute Accent
|
||||
(0x000b6, 0x000ba,), # Pilcrow Sign ..Masculine Ordinal Indica
|
||||
(0x000bc, 0x000bf,), # Vulgar Fraction One Quar..Inverted Question Mark
|
||||
(0x000c6, 0x000c6,), # Latin Capital Letter Ae
|
||||
(0x000d0, 0x000d0,), # Latin Capital Letter Eth
|
||||
(0x000d7, 0x000d8,), # Multiplication Sign ..Latin Capital Letter O W
|
||||
(0x000de, 0x000e1,), # Latin Capital Letter Tho..Latin Small Letter A Wit
|
||||
(0x000e6, 0x000e6,), # Latin Small Letter Ae
|
||||
(0x000e8, 0x000ea,), # Latin Small Letter E Wit..Latin Small Letter E Wit
|
||||
(0x000ec, 0x000ed,), # Latin Small Letter I Wit..Latin Small Letter I Wit
|
||||
(0x000f0, 0x000f0,), # Latin Small Letter Eth
|
||||
(0x000f2, 0x000f3,), # Latin Small Letter O Wit..Latin Small Letter O Wit
|
||||
(0x000f7, 0x000fa,), # Division Sign ..Latin Small Letter U Wit
|
||||
(0x000fc, 0x000fc,), # Latin Small Letter U With Diaeresis
|
||||
(0x000fe, 0x000fe,), # Latin Small Letter Thorn
|
||||
(0x00101, 0x00101,), # Latin Small Letter A With Macron
|
||||
(0x00111, 0x00111,), # Latin Small Letter D With Stroke
|
||||
(0x00113, 0x00113,), # Latin Small Letter E With Macron
|
||||
(0x0011b, 0x0011b,), # Latin Small Letter E With Caron
|
||||
(0x00126, 0x00127,), # Latin Capital Letter H W..Latin Small Letter H Wit
|
||||
(0x0012b, 0x0012b,), # Latin Small Letter I With Macron
|
||||
(0x00131, 0x00133,), # Latin Small Letter Dotle..Latin Small Ligature Ij
|
||||
(0x00138, 0x00138,), # Latin Small Letter Kra
|
||||
(0x0013f, 0x00142,), # Latin Capital Letter L W..Latin Small Letter L Wit
|
||||
(0x00144, 0x00144,), # Latin Small Letter N With Acute
|
||||
(0x00148, 0x0014b,), # Latin Small Letter N Wit..Latin Small Letter Eng
|
||||
(0x0014d, 0x0014d,), # Latin Small Letter O With Macron
|
||||
(0x00152, 0x00153,), # Latin Capital Ligature O..Latin Small Ligature Oe
|
||||
(0x00166, 0x00167,), # Latin Capital Letter T W..Latin Small Letter T Wit
|
||||
(0x0016b, 0x0016b,), # Latin Small Letter U With Macron
|
||||
(0x001ce, 0x001ce,), # Latin Small Letter A With Caron
|
||||
(0x001d0, 0x001d0,), # Latin Small Letter I With Caron
|
||||
(0x001d2, 0x001d2,), # Latin Small Letter O With Caron
|
||||
(0x001d4, 0x001d4,), # Latin Small Letter U With Caron
|
||||
(0x001d6, 0x001d6,), # Latin Small Letter U With Diaeresis And Macron
|
||||
(0x001d8, 0x001d8,), # Latin Small Letter U With Diaeresis And Acute
|
||||
(0x001da, 0x001da,), # Latin Small Letter U With Diaeresis And Caron
|
||||
(0x001dc, 0x001dc,), # Latin Small Letter U With Diaeresis And Grave
|
||||
(0x00251, 0x00251,), # Latin Small Letter Alpha
|
||||
(0x00261, 0x00261,), # Latin Small Letter Script G
|
||||
(0x002c4, 0x002c4,), # Modifier Letter Up Arrowhead
|
||||
(0x002c7, 0x002c7,), # Caron
|
||||
(0x002c9, 0x002cb,), # Modifier Letter Macron ..Modifier Letter Grave Ac
|
||||
(0x002cd, 0x002cd,), # Modifier Letter Low Macron
|
||||
(0x002d0, 0x002d0,), # Modifier Letter Triangular Colon
|
||||
(0x002d8, 0x002db,), # Breve ..Ogonek
|
||||
(0x002dd, 0x002dd,), # Double Acute Accent
|
||||
(0x002df, 0x002df,), # Modifier Letter Cross Accent
|
||||
(0x00391, 0x003a1,), # Greek Capital Letter Alp..Greek Capital Letter Rho
|
||||
(0x003a3, 0x003a9,), # Greek Capital Letter Sig..Greek Capital Letter Ome
|
||||
(0x003b1, 0x003c1,), # Greek Small Letter Alpha..Greek Small Letter Rho
|
||||
(0x003c3, 0x003c9,), # Greek Small Letter Sigma..Greek Small Letter Omega
|
||||
(0x00401, 0x00401,), # Cyrillic Capital Letter Io
|
||||
(0x00410, 0x0044f,), # Cyrillic Capital Letter ..Cyrillic Small Letter Ya
|
||||
(0x00451, 0x00451,), # Cyrillic Small Letter Io
|
||||
(0x02010, 0x02010,), # Hyphen
|
||||
(0x02013, 0x02016,), # En Dash ..Double Vertical Line
|
||||
(0x02018, 0x02019,), # Left Single Quotation Ma..Right Single Quotation M
|
||||
(0x0201c, 0x0201d,), # Left Double Quotation Ma..Right Double Quotation M
|
||||
(0x02020, 0x02022,), # Dagger ..Bullet
|
||||
(0x02024, 0x02027,), # One Dot Leader ..Hyphenation Point
|
||||
(0x02030, 0x02030,), # Per Mille Sign
|
||||
(0x02032, 0x02033,), # Prime ..Double Prime
|
||||
(0x02035, 0x02035,), # Reversed Prime
|
||||
(0x0203b, 0x0203b,), # Reference Mark
|
||||
(0x0203e, 0x0203e,), # Overline
|
||||
(0x02074, 0x02074,), # Superscript Four
|
||||
(0x0207f, 0x0207f,), # Superscript Latin Small Letter N
|
||||
(0x02081, 0x02084,), # Subscript One ..Subscript Four
|
||||
(0x020ac, 0x020ac,), # Euro Sign
|
||||
(0x02103, 0x02103,), # Degree Celsius
|
||||
(0x02105, 0x02105,), # Care Of
|
||||
(0x02109, 0x02109,), # Degree Fahrenheit
|
||||
(0x02113, 0x02113,), # Script Small L
|
||||
(0x02116, 0x02116,), # Numero Sign
|
||||
(0x02121, 0x02122,), # Telephone Sign ..Trade Mark Sign
|
||||
(0x02126, 0x02126,), # Ohm Sign
|
||||
(0x0212b, 0x0212b,), # Angstrom Sign
|
||||
(0x02153, 0x02154,), # Vulgar Fraction One Thir..Vulgar Fraction Two Thir
|
||||
(0x0215b, 0x0215e,), # Vulgar Fraction One Eigh..Vulgar Fraction Seven Ei
|
||||
(0x02160, 0x0216b,), # Roman Numeral One ..Roman Numeral Twelve
|
||||
(0x02170, 0x02179,), # Small Roman Numeral One ..Small Roman Numeral Ten
|
||||
(0x02189, 0x02189,), # Vulgar Fraction Zero Thirds
|
||||
(0x02190, 0x02199,), # Leftwards Arrow ..South West Arrow
|
||||
(0x021b8, 0x021b9,), # North West Arrow To Long..Leftwards Arrow To Bar O
|
||||
(0x021d2, 0x021d2,), # Rightwards Double Arrow
|
||||
(0x021d4, 0x021d4,), # Left Right Double Arrow
|
||||
(0x021e7, 0x021e7,), # Upwards White Arrow
|
||||
(0x02200, 0x02200,), # For All
|
||||
(0x02202, 0x02203,), # Partial Differential ..There Exists
|
||||
(0x02207, 0x02208,), # Nabla ..Element Of
|
||||
(0x0220b, 0x0220b,), # Contains As Member
|
||||
(0x0220f, 0x0220f,), # N-ary Product
|
||||
(0x02211, 0x02211,), # N-ary Summation
|
||||
(0x02215, 0x02215,), # Division Slash
|
||||
(0x0221a, 0x0221a,), # Square Root
|
||||
(0x0221d, 0x02220,), # Proportional To ..Angle
|
||||
(0x02223, 0x02223,), # Divides
|
||||
(0x02225, 0x02225,), # Parallel To
|
||||
(0x02227, 0x0222c,), # Logical And ..Double Integral
|
||||
(0x0222e, 0x0222e,), # Contour Integral
|
||||
(0x02234, 0x02237,), # Therefore ..Proportion
|
||||
(0x0223c, 0x0223d,), # Tilde Operator ..Reversed Tilde
|
||||
(0x02248, 0x02248,), # Almost Equal To
|
||||
(0x0224c, 0x0224c,), # All Equal To
|
||||
(0x02252, 0x02252,), # Approximately Equal To Or The Image Of
|
||||
(0x02260, 0x02261,), # Not Equal To ..Identical To
|
||||
(0x02264, 0x02267,), # Less-than Or Equal To ..Greater-than Over Equal
|
||||
(0x0226a, 0x0226b,), # Much Less-than ..Much Greater-than
|
||||
(0x0226e, 0x0226f,), # Not Less-than ..Not Greater-than
|
||||
(0x02282, 0x02283,), # Subset Of ..Superset Of
|
||||
(0x02286, 0x02287,), # Subset Of Or Equal To ..Superset Of Or Equal To
|
||||
(0x02295, 0x02295,), # Circled Plus
|
||||
(0x02299, 0x02299,), # Circled Dot Operator
|
||||
(0x022a5, 0x022a5,), # Up Tack
|
||||
(0x022bf, 0x022bf,), # Right Triangle
|
||||
(0x02312, 0x02312,), # Arc
|
||||
(0x02460, 0x024e9,), # Circled Digit One ..Circled Latin Small Lett
|
||||
(0x024eb, 0x0254b,), # Negative Circled Number ..Box Drawings Heavy Verti
|
||||
(0x02550, 0x02573,), # Box Drawings Double Hori..Box Drawings Light Diago
|
||||
(0x02580, 0x0258f,), # Upper Half Block ..Left One Eighth Block
|
||||
(0x02592, 0x02595,), # Medium Shade ..Right One Eighth Block
|
||||
(0x025a0, 0x025a1,), # Black Square ..White Square
|
||||
(0x025a3, 0x025a9,), # White Square Containing ..Square With Diagonal Cro
|
||||
(0x025b2, 0x025b3,), # Black Up-pointing Triang..White Up-pointing Triang
|
||||
(0x025b6, 0x025b7,), # Black Right-pointing Tri..White Right-pointing Tri
|
||||
(0x025bc, 0x025bd,), # Black Down-pointing Tria..White Down-pointing Tria
|
||||
(0x025c0, 0x025c1,), # Black Left-pointing Tria..White Left-pointing Tria
|
||||
(0x025c6, 0x025c8,), # Black Diamond ..White Diamond Containing
|
||||
(0x025cb, 0x025cb,), # White Circle
|
||||
(0x025ce, 0x025d1,), # Bullseye ..Circle With Right Half B
|
||||
(0x025e2, 0x025e5,), # Black Lower Right Triang..Black Upper Right Triang
|
||||
(0x025ef, 0x025ef,), # Large Circle
|
||||
(0x02605, 0x02606,), # Black Star ..White Star
|
||||
(0x02609, 0x02609,), # Sun
|
||||
(0x0260e, 0x0260f,), # Black Telephone ..White Telephone
|
||||
(0x0261c, 0x0261c,), # White Left Pointing Index
|
||||
(0x0261e, 0x0261e,), # White Right Pointing Index
|
||||
(0x02640, 0x02640,), # Female Sign
|
||||
(0x02642, 0x02642,), # Male Sign
|
||||
(0x02660, 0x02661,), # Black Spade Suit ..White Heart Suit
|
||||
(0x02663, 0x02665,), # Black Club Suit ..Black Heart Suit
|
||||
(0x02667, 0x0266a,), # White Club Suit ..Eighth Note
|
||||
(0x0266c, 0x0266d,), # Beamed Sixteenth Notes ..Music Flat Sign
|
||||
(0x0266f, 0x0266f,), # Music Sharp Sign
|
||||
(0x0269e, 0x0269f,), # Three Lines Converging R..Three Lines Converging L
|
||||
(0x026bf, 0x026bf,), # Squared Key
|
||||
(0x026c6, 0x026cd,), # Rain ..Disabled Car
|
||||
(0x026cf, 0x026d3,), # Pick ..Chains
|
||||
(0x026d5, 0x026e1,), # Alternate One-way Left W..Restricted Left Entry-2
|
||||
(0x026e3, 0x026e3,), # Heavy Circle With Stroke And Two Dots Above
|
||||
(0x026e8, 0x026e9,), # Black Cross On Shield ..Shinto Shrine
|
||||
(0x026eb, 0x026f1,), # Castle ..Umbrella On Ground
|
||||
(0x026f4, 0x026f4,), # Ferry
|
||||
(0x026f6, 0x026f9,), # Square Four Corners ..Person With Ball
|
||||
(0x026fb, 0x026fc,), # Japanese Bank Symbol ..Headstone Graveyard Symb
|
||||
(0x026fe, 0x026ff,), # Cup On Black Square ..White Flag With Horizont
|
||||
(0x0273d, 0x0273d,), # Heavy Teardrop-spoked Asterisk
|
||||
(0x02776, 0x0277f,), # Dingbat Negative Circled..Dingbat Negative Circled
|
||||
(0x02b56, 0x02b59,), # Heavy Oval With Oval Ins..Heavy Circled Saltire
|
||||
(0x03248, 0x0324f,), # Circled Number Ten On Bl..Circled Number Eighty On
|
||||
(0x0e000, 0x0f8ff,), # (nil)
|
||||
(0x0fffd, 0x0fffd,), # Replacement Character
|
||||
(0x1f100, 0x1f10a,), # Digit Zero Full Stop ..Digit Nine Comma
|
||||
(0x1f110, 0x1f12d,), # Parenthesized Latin Capi..Circled Cd
|
||||
(0x1f130, 0x1f169,), # Squared Latin Capital Le..Negative Circled Latin C
|
||||
(0x1f170, 0x1f18d,), # Negative Squared Latin C..Negative Squared Sa
|
||||
(0x1f18f, 0x1f190,), # Negative Squared Wc ..Square Dj
|
||||
(0x1f19b, 0x1f1ac,), # Squared Three D ..Squared Vod
|
||||
(0xf0000, 0xffffd,), # (nil)
|
||||
(0x100000, 0x10fffd,), # (nil)
|
||||
),
|
||||
}
|
||||
2294
venv/lib/python3.12/site-packages/wcwidth/table_grapheme.py
Normal file
2294
venv/lib/python3.12/site-packages/wcwidth/table_grapheme.py
Normal file
File diff suppressed because it is too large
Load Diff
206
venv/lib/python3.12/site-packages/wcwidth/table_mc.py
Normal file
206
venv/lib/python3.12/site-packages/wcwidth/table_mc.py
Normal file
@@ -0,0 +1,206 @@
|
||||
"""
|
||||
Exports CATEGORY_MC table keyed by supporting unicode version level.
|
||||
|
||||
This code generated by wcwidth/bin/update-tables.py on 2026-01-29 00:47:54 UTC.
|
||||
"""
|
||||
# pylint: disable=duplicate-code
|
||||
CATEGORY_MC = {
|
||||
'17.0.0': (
|
||||
# Source: DerivedGeneralCategory-17.0.0.txt
|
||||
# Date: 2025-07-24, 00:12:50 GMT
|
||||
#
|
||||
(0x00903, 0x00903,), # Devanagari Sign Visarga
|
||||
(0x0093b, 0x0093b,), # Devanagari Vowel Sign Ooe
|
||||
(0x0093e, 0x00940,), # Devanagari Vowel Sign Aa..Devanagari Vowel Sign Ii
|
||||
(0x00949, 0x0094c,), # Devanagari Vowel Sign Ca..Devanagari Vowel Sign Au
|
||||
(0x0094e, 0x0094f,), # Devanagari Vowel Sign Pr..Devanagari Vowel Sign Aw
|
||||
(0x00982, 0x00983,), # Bengali Sign Anusvara ..Bengali Sign Visarga
|
||||
(0x009be, 0x009c0,), # Bengali Vowel Sign Aa ..Bengali Vowel Sign Ii
|
||||
(0x009c7, 0x009c8,), # Bengali Vowel Sign E ..Bengali Vowel Sign Ai
|
||||
(0x009cb, 0x009cc,), # Bengali Vowel Sign O ..Bengali Vowel Sign Au
|
||||
(0x009d7, 0x009d7,), # Bengali Au Length Mark
|
||||
(0x00a03, 0x00a03,), # Gurmukhi Sign Visarga
|
||||
(0x00a3e, 0x00a40,), # Gurmukhi Vowel Sign Aa ..Gurmukhi Vowel Sign Ii
|
||||
(0x00a83, 0x00a83,), # Gujarati Sign Visarga
|
||||
(0x00abe, 0x00ac0,), # Gujarati Vowel Sign Aa ..Gujarati Vowel Sign Ii
|
||||
(0x00ac9, 0x00ac9,), # Gujarati Vowel Sign Candra O
|
||||
(0x00acb, 0x00acc,), # Gujarati Vowel Sign O ..Gujarati Vowel Sign Au
|
||||
(0x00b02, 0x00b03,), # Oriya Sign Anusvara ..Oriya Sign Visarga
|
||||
(0x00b3e, 0x00b3e,), # Oriya Vowel Sign Aa
|
||||
(0x00b40, 0x00b40,), # Oriya Vowel Sign Ii
|
||||
(0x00b47, 0x00b48,), # Oriya Vowel Sign E ..Oriya Vowel Sign Ai
|
||||
(0x00b4b, 0x00b4c,), # Oriya Vowel Sign O ..Oriya Vowel Sign Au
|
||||
(0x00b57, 0x00b57,), # Oriya Au Length Mark
|
||||
(0x00bbe, 0x00bbf,), # Tamil Vowel Sign Aa ..Tamil Vowel Sign I
|
||||
(0x00bc1, 0x00bc2,), # Tamil Vowel Sign U ..Tamil Vowel Sign Uu
|
||||
(0x00bc6, 0x00bc8,), # Tamil Vowel Sign E ..Tamil Vowel Sign Ai
|
||||
(0x00bca, 0x00bcc,), # Tamil Vowel Sign O ..Tamil Vowel Sign Au
|
||||
(0x00bd7, 0x00bd7,), # Tamil Au Length Mark
|
||||
(0x00c01, 0x00c03,), # Telugu Sign Candrabindu ..Telugu Sign Visarga
|
||||
(0x00c41, 0x00c44,), # Telugu Vowel Sign U ..Telugu Vowel Sign Vocali
|
||||
(0x00c82, 0x00c83,), # Kannada Sign Anusvara ..Kannada Sign Visarga
|
||||
(0x00cbe, 0x00cbe,), # Kannada Vowel Sign Aa
|
||||
(0x00cc0, 0x00cc4,), # Kannada Vowel Sign Ii ..Kannada Vowel Sign Vocal
|
||||
(0x00cc7, 0x00cc8,), # Kannada Vowel Sign Ee ..Kannada Vowel Sign Ai
|
||||
(0x00cca, 0x00ccb,), # Kannada Vowel Sign O ..Kannada Vowel Sign Oo
|
||||
(0x00cd5, 0x00cd6,), # Kannada Length Mark ..Kannada Ai Length Mark
|
||||
(0x00cf3, 0x00cf3,), # Kannada Sign Combining Anusvara Above Right
|
||||
(0x00d02, 0x00d03,), # Malayalam Sign Anusvara ..Malayalam Sign Visarga
|
||||
(0x00d3e, 0x00d40,), # Malayalam Vowel Sign Aa ..Malayalam Vowel Sign Ii
|
||||
(0x00d46, 0x00d48,), # Malayalam Vowel Sign E ..Malayalam Vowel Sign Ai
|
||||
(0x00d4a, 0x00d4c,), # Malayalam Vowel Sign O ..Malayalam Vowel Sign Au
|
||||
(0x00d57, 0x00d57,), # Malayalam Au Length Mark
|
||||
(0x00d82, 0x00d83,), # Sinhala Sign Anusvaraya ..Sinhala Sign Visargaya
|
||||
(0x00dcf, 0x00dd1,), # Sinhala Vowel Sign Aela-..Sinhala Vowel Sign Diga
|
||||
(0x00dd8, 0x00ddf,), # Sinhala Vowel Sign Gaett..Sinhala Vowel Sign Gayan
|
||||
(0x00df2, 0x00df3,), # Sinhala Vowel Sign Diga ..Sinhala Vowel Sign Diga
|
||||
(0x00f3e, 0x00f3f,), # Tibetan Sign Yar Tshes ..Tibetan Sign Mar Tshes
|
||||
(0x00f7f, 0x00f7f,), # Tibetan Sign Rnam Bcad
|
||||
(0x0102b, 0x0102c,), # Myanmar Vowel Sign Tall ..Myanmar Vowel Sign Aa
|
||||
(0x01031, 0x01031,), # Myanmar Vowel Sign E
|
||||
(0x01038, 0x01038,), # Myanmar Sign Visarga
|
||||
(0x0103b, 0x0103c,), # Myanmar Consonant Sign M..Myanmar Consonant Sign M
|
||||
(0x01056, 0x01057,), # Myanmar Vowel Sign Vocal..Myanmar Vowel Sign Vocal
|
||||
(0x01062, 0x01064,), # Myanmar Vowel Sign Sgaw ..Myanmar Tone Mark Sgaw K
|
||||
(0x01067, 0x0106d,), # Myanmar Vowel Sign Weste..Myanmar Sign Western Pwo
|
||||
(0x01083, 0x01084,), # Myanmar Vowel Sign Shan ..Myanmar Vowel Sign Shan
|
||||
(0x01087, 0x0108c,), # Myanmar Sign Shan Tone-2..Myanmar Sign Shan Counci
|
||||
(0x0108f, 0x0108f,), # Myanmar Sign Rumai Palaung Tone-5
|
||||
(0x0109a, 0x0109c,), # Myanmar Sign Khamti Tone..Myanmar Vowel Sign Aiton
|
||||
(0x01715, 0x01715,), # Tagalog Sign Pamudpod
|
||||
(0x01734, 0x01734,), # Hanunoo Sign Pamudpod
|
||||
(0x017b6, 0x017b6,), # Khmer Vowel Sign Aa
|
||||
(0x017be, 0x017c5,), # Khmer Vowel Sign Oe ..Khmer Vowel Sign Au
|
||||
(0x017c7, 0x017c8,), # Khmer Sign Reahmuk ..Khmer Sign Yuukaleapintu
|
||||
(0x01923, 0x01926,), # Limbu Vowel Sign Ee ..Limbu Vowel Sign Au
|
||||
(0x01929, 0x0192b,), # Limbu Subjoined Letter Y..Limbu Subjoined Letter W
|
||||
(0x01930, 0x01931,), # Limbu Small Letter Ka ..Limbu Small Letter Nga
|
||||
(0x01933, 0x01938,), # Limbu Small Letter Ta ..Limbu Small Letter La
|
||||
(0x01a19, 0x01a1a,), # Buginese Vowel Sign E ..Buginese Vowel Sign O
|
||||
(0x01a55, 0x01a55,), # Tai Tham Consonant Sign Medial Ra
|
||||
(0x01a57, 0x01a57,), # Tai Tham Consonant Sign La Tang Lai
|
||||
(0x01a61, 0x01a61,), # Tai Tham Vowel Sign A
|
||||
(0x01a63, 0x01a64,), # Tai Tham Vowel Sign Aa ..Tai Tham Vowel Sign Tall
|
||||
(0x01a6d, 0x01a72,), # Tai Tham Vowel Sign Oy ..Tai Tham Vowel Sign Tham
|
||||
(0x01b04, 0x01b04,), # Balinese Sign Bisah
|
||||
(0x01b35, 0x01b35,), # Balinese Vowel Sign Tedung
|
||||
(0x01b3b, 0x01b3b,), # Balinese Vowel Sign Ra Repa Tedung
|
||||
(0x01b3d, 0x01b41,), # Balinese Vowel Sign La L..Balinese Vowel Sign Tali
|
||||
(0x01b43, 0x01b44,), # Balinese Vowel Sign Pepe..Balinese Adeg Adeg
|
||||
(0x01b82, 0x01b82,), # Sundanese Sign Pangwisad
|
||||
(0x01ba1, 0x01ba1,), # Sundanese Consonant Sign Pamingkal
|
||||
(0x01ba6, 0x01ba7,), # Sundanese Vowel Sign Pan..Sundanese Vowel Sign Pan
|
||||
(0x01baa, 0x01baa,), # Sundanese Sign Pamaaeh
|
||||
(0x01be7, 0x01be7,), # Batak Vowel Sign E
|
||||
(0x01bea, 0x01bec,), # Batak Vowel Sign I ..Batak Vowel Sign O
|
||||
(0x01bee, 0x01bee,), # Batak Vowel Sign U
|
||||
(0x01bf2, 0x01bf3,), # Batak Pangolat ..Batak Panongonan
|
||||
(0x01c24, 0x01c2b,), # Lepcha Subjoined Letter ..Lepcha Vowel Sign Uu
|
||||
(0x01c34, 0x01c35,), # Lepcha Consonant Sign Ny..Lepcha Consonant Sign Ka
|
||||
(0x01ce1, 0x01ce1,), # Vedic Tone Atharvavedic Independent Svarita
|
||||
(0x01cf7, 0x01cf7,), # Vedic Sign Atikrama
|
||||
(0x0302e, 0x0302f,), # Hangul Single Dot Tone M..Hangul Double Dot Tone M
|
||||
(0x0a823, 0x0a824,), # Syloti Nagri Vowel Sign ..Syloti Nagri Vowel Sign
|
||||
(0x0a827, 0x0a827,), # Syloti Nagri Vowel Sign Oo
|
||||
(0x0a880, 0x0a881,), # Saurashtra Sign Anusvara..Saurashtra Sign Visarga
|
||||
(0x0a8b4, 0x0a8c3,), # Saurashtra Consonant Sig..Saurashtra Vowel Sign Au
|
||||
(0x0a952, 0x0a953,), # Rejang Consonant Sign H ..Rejang Virama
|
||||
(0x0a983, 0x0a983,), # Javanese Sign Wignyan
|
||||
(0x0a9b4, 0x0a9b5,), # Javanese Vowel Sign Taru..Javanese Vowel Sign Tolo
|
||||
(0x0a9ba, 0x0a9bb,), # Javanese Vowel Sign Tali..Javanese Vowel Sign Dirg
|
||||
(0x0a9be, 0x0a9c0,), # Javanese Consonant Sign ..Javanese Pangkon
|
||||
(0x0aa2f, 0x0aa30,), # Cham Vowel Sign O ..Cham Vowel Sign Ai
|
||||
(0x0aa33, 0x0aa34,), # Cham Consonant Sign Ya ..Cham Consonant Sign Ra
|
||||
(0x0aa4d, 0x0aa4d,), # Cham Consonant Sign Final H
|
||||
(0x0aa7b, 0x0aa7b,), # Myanmar Sign Pao Karen Tone
|
||||
(0x0aa7d, 0x0aa7d,), # Myanmar Sign Tai Laing Tone-5
|
||||
(0x0aaeb, 0x0aaeb,), # Meetei Mayek Vowel Sign Ii
|
||||
(0x0aaee, 0x0aaef,), # Meetei Mayek Vowel Sign ..Meetei Mayek Vowel Sign
|
||||
(0x0aaf5, 0x0aaf5,), # Meetei Mayek Vowel Sign Visarga
|
||||
(0x0abe3, 0x0abe4,), # Meetei Mayek Vowel Sign ..Meetei Mayek Vowel Sign
|
||||
(0x0abe6, 0x0abe7,), # Meetei Mayek Vowel Sign ..Meetei Mayek Vowel Sign
|
||||
(0x0abe9, 0x0abea,), # Meetei Mayek Vowel Sign ..Meetei Mayek Vowel Sign
|
||||
(0x0abec, 0x0abec,), # Meetei Mayek Lum Iyek
|
||||
(0x11000, 0x11000,), # Brahmi Sign Candrabindu
|
||||
(0x11002, 0x11002,), # Brahmi Sign Visarga
|
||||
(0x11082, 0x11082,), # Kaithi Sign Visarga
|
||||
(0x110b0, 0x110b2,), # Kaithi Vowel Sign Aa ..Kaithi Vowel Sign Ii
|
||||
(0x110b7, 0x110b8,), # Kaithi Vowel Sign O ..Kaithi Vowel Sign Au
|
||||
(0x1112c, 0x1112c,), # Chakma Vowel Sign E
|
||||
(0x11145, 0x11146,), # Chakma Vowel Sign Aa ..Chakma Vowel Sign Ei
|
||||
(0x11182, 0x11182,), # Sharada Sign Visarga
|
||||
(0x111b3, 0x111b5,), # Sharada Vowel Sign Aa ..Sharada Vowel Sign Ii
|
||||
(0x111bf, 0x111c0,), # Sharada Vowel Sign Au ..Sharada Sign Virama
|
||||
(0x111ce, 0x111ce,), # Sharada Vowel Sign Prishthamatra E
|
||||
(0x1122c, 0x1122e,), # Khojki Vowel Sign Aa ..Khojki Vowel Sign Ii
|
||||
(0x11232, 0x11233,), # Khojki Vowel Sign O ..Khojki Vowel Sign Au
|
||||
(0x11235, 0x11235,), # Khojki Sign Virama
|
||||
(0x112e0, 0x112e2,), # Khudawadi Vowel Sign Aa ..Khudawadi Vowel Sign Ii
|
||||
(0x11302, 0x11303,), # Grantha Sign Anusvara ..Grantha Sign Visarga
|
||||
(0x1133e, 0x1133f,), # Grantha Vowel Sign Aa ..Grantha Vowel Sign I
|
||||
(0x11341, 0x11344,), # Grantha Vowel Sign U ..Grantha Vowel Sign Vocal
|
||||
(0x11347, 0x11348,), # Grantha Vowel Sign Ee ..Grantha Vowel Sign Ai
|
||||
(0x1134b, 0x1134d,), # Grantha Vowel Sign Oo ..Grantha Sign Virama
|
||||
(0x11357, 0x11357,), # Grantha Au Length Mark
|
||||
(0x11362, 0x11363,), # Grantha Vowel Sign Vocal..Grantha Vowel Sign Vocal
|
||||
(0x113b8, 0x113ba,), # Tulu-tigalari Vowel Sign..Tulu-tigalari Vowel Sign
|
||||
(0x113c2, 0x113c2,), # Tulu-tigalari Vowel Sign Ee
|
||||
(0x113c5, 0x113c5,), # Tulu-tigalari Vowel Sign Ai
|
||||
(0x113c7, 0x113ca,), # Tulu-tigalari Vowel Sign..Tulu-tigalari Sign Candr
|
||||
(0x113cc, 0x113cd,), # Tulu-tigalari Sign Anusv..Tulu-tigalari Sign Visar
|
||||
(0x113cf, 0x113cf,), # Tulu-tigalari Sign Looped Virama
|
||||
(0x11435, 0x11437,), # Newa Vowel Sign Aa ..Newa Vowel Sign Ii
|
||||
(0x11440, 0x11441,), # Newa Vowel Sign O ..Newa Vowel Sign Au
|
||||
(0x11445, 0x11445,), # Newa Sign Visarga
|
||||
(0x114b0, 0x114b2,), # Tirhuta Vowel Sign Aa ..Tirhuta Vowel Sign Ii
|
||||
(0x114b9, 0x114b9,), # Tirhuta Vowel Sign E
|
||||
(0x114bb, 0x114be,), # Tirhuta Vowel Sign Ai ..Tirhuta Vowel Sign Au
|
||||
(0x114c1, 0x114c1,), # Tirhuta Sign Visarga
|
||||
(0x115af, 0x115b1,), # Siddham Vowel Sign Aa ..Siddham Vowel Sign Ii
|
||||
(0x115b8, 0x115bb,), # Siddham Vowel Sign E ..Siddham Vowel Sign Au
|
||||
(0x115be, 0x115be,), # Siddham Sign Visarga
|
||||
(0x11630, 0x11632,), # Modi Vowel Sign Aa ..Modi Vowel Sign Ii
|
||||
(0x1163b, 0x1163c,), # Modi Vowel Sign O ..Modi Vowel Sign Au
|
||||
(0x1163e, 0x1163e,), # Modi Sign Visarga
|
||||
(0x116ac, 0x116ac,), # Takri Sign Visarga
|
||||
(0x116ae, 0x116af,), # Takri Vowel Sign I ..Takri Vowel Sign Ii
|
||||
(0x116b6, 0x116b6,), # Takri Sign Virama
|
||||
(0x1171e, 0x1171e,), # Ahom Consonant Sign Medial Ra
|
||||
(0x11720, 0x11721,), # Ahom Vowel Sign A ..Ahom Vowel Sign Aa
|
||||
(0x11726, 0x11726,), # Ahom Vowel Sign E
|
||||
(0x1182c, 0x1182e,), # Dogra Vowel Sign Aa ..Dogra Vowel Sign Ii
|
||||
(0x11838, 0x11838,), # Dogra Sign Visarga
|
||||
(0x11930, 0x11935,), # Dives Akuru Vowel Sign A..Dives Akuru Vowel Sign E
|
||||
(0x11937, 0x11938,), # Dives Akuru Vowel Sign A..Dives Akuru Vowel Sign O
|
||||
(0x1193d, 0x1193d,), # Dives Akuru Sign Halanta
|
||||
(0x11940, 0x11940,), # Dives Akuru Medial Ya
|
||||
(0x11942, 0x11942,), # Dives Akuru Medial Ra
|
||||
(0x119d1, 0x119d3,), # Nandinagari Vowel Sign A..Nandinagari Vowel Sign I
|
||||
(0x119dc, 0x119df,), # Nandinagari Vowel Sign O..Nandinagari Sign Visarga
|
||||
(0x119e4, 0x119e4,), # Nandinagari Vowel Sign Prishthamatra E
|
||||
(0x11a39, 0x11a39,), # Zanabazar Square Sign Visarga
|
||||
(0x11a57, 0x11a58,), # Soyombo Vowel Sign Ai ..Soyombo Vowel Sign Au
|
||||
(0x11a97, 0x11a97,), # Soyombo Sign Visarga
|
||||
(0x11b61, 0x11b61,), # Sharada Vowel Sign Ooe
|
||||
(0x11b65, 0x11b65,), # Sharada Vowel Sign Short O
|
||||
(0x11b67, 0x11b67,), # Sharada Vowel Sign Candra O
|
||||
(0x11c2f, 0x11c2f,), # Bhaiksuki Vowel Sign Aa
|
||||
(0x11c3e, 0x11c3e,), # Bhaiksuki Sign Visarga
|
||||
(0x11ca9, 0x11ca9,), # Marchen Subjoined Letter Ya
|
||||
(0x11cb1, 0x11cb1,), # Marchen Vowel Sign I
|
||||
(0x11cb4, 0x11cb4,), # Marchen Vowel Sign O
|
||||
(0x11d8a, 0x11d8e,), # Gunjala Gondi Vowel Sign..Gunjala Gondi Vowel Sign
|
||||
(0x11d93, 0x11d94,), # Gunjala Gondi Vowel Sign..Gunjala Gondi Vowel Sign
|
||||
(0x11d96, 0x11d96,), # Gunjala Gondi Sign Visarga
|
||||
(0x11ef5, 0x11ef6,), # Makasar Vowel Sign E ..Makasar Vowel Sign O
|
||||
(0x11f03, 0x11f03,), # Kawi Sign Visarga
|
||||
(0x11f34, 0x11f35,), # Kawi Vowel Sign Aa ..Kawi Vowel Sign Alternat
|
||||
(0x11f3e, 0x11f3f,), # Kawi Vowel Sign E ..Kawi Vowel Sign Ai
|
||||
(0x11f41, 0x11f41,), # Kawi Sign Killer
|
||||
(0x1612a, 0x1612c,), # Gurung Khema Consonant S..Gurung Khema Consonant S
|
||||
(0x16f51, 0x16f87,), # Miao Sign Aspiration ..Miao Vowel Sign Ui
|
||||
(0x16ff0, 0x16ff1,), # Vietnamese Alternate Rea..Vietnamese Alternate Rea
|
||||
(0x1d165, 0x1d166,), # Musical Symbol Combining..Musical Symbol Combining
|
||||
(0x1d16d, 0x1d172,), # Musical Symbol Combining..Musical Symbol Combining
|
||||
),
|
||||
}
|
||||
126
venv/lib/python3.12/site-packages/wcwidth/table_vs16.py
Normal file
126
venv/lib/python3.12/site-packages/wcwidth/table_vs16.py
Normal file
@@ -0,0 +1,126 @@
|
||||
"""
|
||||
Exports VS16_NARROW_TO_WIDE table keyed by supporting unicode version level.
|
||||
|
||||
This code generated by wcwidth/bin/update-tables.py on 2025-09-15 16:57:50 UTC.
|
||||
"""
|
||||
# pylint: disable=duplicate-code
|
||||
VS16_NARROW_TO_WIDE = {
|
||||
'9.0.0': (
|
||||
# Source: 9.0.0
|
||||
# Date: 2025-01-30, 21:48:29 GMT
|
||||
#
|
||||
(0x00023, 0x00023,), # Number Sign
|
||||
(0x0002a, 0x0002a,), # Asterisk
|
||||
(0x00030, 0x00039,), # Digit Zero ..Digit Nine
|
||||
(0x000a9, 0x000a9,), # Copyright Sign
|
||||
(0x000ae, 0x000ae,), # Registered Sign
|
||||
(0x0203c, 0x0203c,), # Double Exclamation Mark
|
||||
(0x02049, 0x02049,), # Exclamation Question Mark
|
||||
(0x02122, 0x02122,), # Trade Mark Sign
|
||||
(0x02139, 0x02139,), # Information Source
|
||||
(0x02194, 0x02199,), # Left Right Arrow ..South West Arrow
|
||||
(0x021a9, 0x021aa,), # Leftwards Arrow With Hoo..Rightwards Arrow With Ho
|
||||
(0x02328, 0x02328,), # Keyboard
|
||||
(0x023cf, 0x023cf,), # Eject Symbol
|
||||
(0x023ed, 0x023ef,), # Black Right-pointing Dou..Black Right-pointing Tri
|
||||
(0x023f1, 0x023f2,), # Stopwatch ..Timer Clock
|
||||
(0x023f8, 0x023fa,), # Double Vertical Bar ..Black Circle For Record
|
||||
(0x024c2, 0x024c2,), # Circled Latin Capital Letter M
|
||||
(0x025aa, 0x025ab,), # Black Small Square ..White Small Square
|
||||
(0x025b6, 0x025b6,), # Black Right-pointing Triangle
|
||||
(0x025c0, 0x025c0,), # Black Left-pointing Triangle
|
||||
(0x025fb, 0x025fc,), # White Medium Square ..Black Medium Square
|
||||
(0x02600, 0x02604,), # Black Sun With Rays ..Comet
|
||||
(0x0260e, 0x0260e,), # Black Telephone
|
||||
(0x02611, 0x02611,), # Ballot Box With Check
|
||||
(0x02618, 0x02618,), # Shamrock
|
||||
(0x0261d, 0x0261d,), # White Up Pointing Index
|
||||
(0x02620, 0x02620,), # Skull And Crossbones
|
||||
(0x02622, 0x02623,), # Radioactive Sign ..Biohazard Sign
|
||||
(0x02626, 0x02626,), # Orthodox Cross
|
||||
(0x0262a, 0x0262a,), # Star And Crescent
|
||||
(0x0262e, 0x0262f,), # Peace Symbol ..Yin Yang
|
||||
(0x02638, 0x0263a,), # Wheel Of Dharma ..White Smiling Face
|
||||
(0x02640, 0x02640,), # Female Sign
|
||||
(0x02642, 0x02642,), # Male Sign
|
||||
(0x0265f, 0x02660,), # Black Chess Pawn ..Black Spade Suit
|
||||
(0x02663, 0x02663,), # Black Club Suit
|
||||
(0x02665, 0x02666,), # Black Heart Suit ..Black Diamond Suit
|
||||
(0x02668, 0x02668,), # Hot Springs
|
||||
(0x0267b, 0x0267b,), # Black Universal Recycling Symbol
|
||||
(0x0267e, 0x0267e,), # Permanent Paper Sign
|
||||
(0x02692, 0x02692,), # Hammer And Pick
|
||||
(0x02694, 0x02697,), # Crossed Swords ..Alembic
|
||||
(0x02699, 0x02699,), # Gear
|
||||
(0x0269b, 0x0269c,), # Atom Symbol ..Fleur-de-lis
|
||||
(0x026a0, 0x026a0,), # Warning Sign
|
||||
(0x026a7, 0x026a7,), # Male With Stroke And Male And Female Sign
|
||||
(0x026b0, 0x026b1,), # Coffin ..Funeral Urn
|
||||
(0x026c8, 0x026c8,), # Thunder Cloud And Rain
|
||||
(0x026cf, 0x026cf,), # Pick
|
||||
(0x026d1, 0x026d1,), # Helmet With White Cross
|
||||
(0x026d3, 0x026d3,), # Chains
|
||||
(0x026e9, 0x026e9,), # Shinto Shrine
|
||||
(0x026f0, 0x026f1,), # Mountain ..Umbrella On Ground
|
||||
(0x026f4, 0x026f4,), # Ferry
|
||||
(0x026f7, 0x026f9,), # Skier ..Person With Ball
|
||||
(0x02702, 0x02702,), # Black Scissors
|
||||
(0x02708, 0x02709,), # Airplane ..Envelope
|
||||
(0x0270c, 0x0270d,), # Victory Hand ..Writing Hand
|
||||
(0x0270f, 0x0270f,), # Pencil
|
||||
(0x02712, 0x02712,), # Black Nib
|
||||
(0x02714, 0x02714,), # Heavy Check Mark
|
||||
(0x02716, 0x02716,), # Heavy Multiplication X
|
||||
(0x0271d, 0x0271d,), # Latin Cross
|
||||
(0x02721, 0x02721,), # Star Of David
|
||||
(0x02733, 0x02734,), # Eight Spoked Asterisk ..Eight Pointed Black Star
|
||||
(0x02744, 0x02744,), # Snowflake
|
||||
(0x02747, 0x02747,), # Sparkle
|
||||
(0x02763, 0x02764,), # Heavy Heart Exclamation ..Heavy Black Heart
|
||||
(0x027a1, 0x027a1,), # Black Rightwards Arrow
|
||||
(0x02934, 0x02935,), # Arrow Pointing Rightward..Arrow Pointing Rightward
|
||||
(0x02b05, 0x02b07,), # Leftwards Black Arrow ..Downwards Black Arrow
|
||||
(0x1f170, 0x1f171,), # Negative Squared Latin C..Negative Squared Latin C
|
||||
(0x1f17e, 0x1f17f,), # Negative Squared Latin C..Negative Squared Latin C
|
||||
(0x1f321, 0x1f321,), # Thermometer
|
||||
(0x1f324, 0x1f32c,), # White Sun With Small Clo..Wind Blowing Face
|
||||
(0x1f336, 0x1f336,), # Hot Pepper
|
||||
(0x1f37d, 0x1f37d,), # Fork And Knife With Plate
|
||||
(0x1f396, 0x1f397,), # Military Medal ..Reminder Ribbon
|
||||
(0x1f399, 0x1f39b,), # Studio Microphone ..Control Knobs
|
||||
(0x1f39e, 0x1f39f,), # Film Frames ..Admission Tickets
|
||||
(0x1f3cb, 0x1f3ce,), # Weight Lifter ..Racing Car
|
||||
(0x1f3d4, 0x1f3df,), # Snow Capped Mountain ..Stadium
|
||||
(0x1f3f3, 0x1f3f3,), # Waving White Flag
|
||||
(0x1f3f5, 0x1f3f5,), # Rosette
|
||||
(0x1f3f7, 0x1f3f7,), # Label
|
||||
(0x1f43f, 0x1f43f,), # Chipmunk
|
||||
(0x1f441, 0x1f441,), # Eye
|
||||
(0x1f4fd, 0x1f4fd,), # Film Projector
|
||||
(0x1f549, 0x1f54a,), # Om Symbol ..Dove Of Peace
|
||||
(0x1f56f, 0x1f570,), # Candle ..Mantelpiece Clock
|
||||
(0x1f573, 0x1f579,), # Hole ..Joystick
|
||||
(0x1f587, 0x1f587,), # Linked Paperclips
|
||||
(0x1f58a, 0x1f58d,), # Lower Left Ballpoint Pen..Lower Left Crayon
|
||||
(0x1f590, 0x1f590,), # Raised Hand With Fingers Splayed
|
||||
(0x1f5a5, 0x1f5a5,), # Desktop Computer
|
||||
(0x1f5a8, 0x1f5a8,), # Printer
|
||||
(0x1f5b1, 0x1f5b2,), # Three Button Mouse ..Trackball
|
||||
(0x1f5bc, 0x1f5bc,), # Frame With Picture
|
||||
(0x1f5c2, 0x1f5c4,), # Card Index Dividers ..File Cabinet
|
||||
(0x1f5d1, 0x1f5d3,), # Wastebasket ..Spiral Calendar Pad
|
||||
(0x1f5dc, 0x1f5de,), # Compression ..Rolled-up Newspaper
|
||||
(0x1f5e1, 0x1f5e1,), # Dagger Knife
|
||||
(0x1f5e3, 0x1f5e3,), # Speaking Head In Silhouette
|
||||
(0x1f5e8, 0x1f5e8,), # Left Speech Bubble
|
||||
(0x1f5ef, 0x1f5ef,), # Right Anger Bubble
|
||||
(0x1f5f3, 0x1f5f3,), # Ballot Box With Ballot
|
||||
(0x1f5fa, 0x1f5fa,), # World Map
|
||||
(0x1f6cb, 0x1f6cb,), # Couch And Lamp
|
||||
(0x1f6cd, 0x1f6cf,), # Shopping Bags ..Bed
|
||||
(0x1f6e0, 0x1f6e5,), # Hammer And Wrench ..Motor Boat
|
||||
(0x1f6e9, 0x1f6e9,), # Small Airplane
|
||||
(0x1f6f0, 0x1f6f0,), # Satellite
|
||||
(0x1f6f3, 0x1f6f3,), # Passenger Ship
|
||||
),
|
||||
}
|
||||
138
venv/lib/python3.12/site-packages/wcwidth/table_wide.py
Normal file
138
venv/lib/python3.12/site-packages/wcwidth/table_wide.py
Normal file
@@ -0,0 +1,138 @@
|
||||
"""
|
||||
Exports WIDE_EASTASIAN table keyed by supporting unicode version level.
|
||||
|
||||
This code generated by wcwidth/bin/update-tables.py on 2026-01-30 00:58:17 UTC.
|
||||
"""
|
||||
# pylint: disable=duplicate-code
|
||||
WIDE_EASTASIAN = {
|
||||
'17.0.0': (
|
||||
# Source: EastAsianWidth-17.0.0.txt
|
||||
# Date: 2025-07-24, 00:12:54 GMT
|
||||
#
|
||||
(0x01100, 0x0115f,), # Hangul Choseong Kiyeok ..Hangul Choseong Filler
|
||||
(0x0231a, 0x0231b,), # Watch ..Hourglass
|
||||
(0x02329, 0x0232a,), # Left-pointing Angle Brac..Right-pointing Angle Bra
|
||||
(0x023e9, 0x023ec,), # Black Right-pointing Dou..Black Down-pointing Doub
|
||||
(0x023f0, 0x023f0,), # Alarm Clock
|
||||
(0x023f3, 0x023f3,), # Hourglass With Flowing Sand
|
||||
(0x025fd, 0x025fe,), # White Medium Small Squar..Black Medium Small Squar
|
||||
(0x02614, 0x02615,), # Umbrella With Rain Drops..Hot Beverage
|
||||
(0x02630, 0x02637,), # Trigram For Heaven ..Trigram For Earth
|
||||
(0x02648, 0x02653,), # Aries ..Pisces
|
||||
(0x0267f, 0x0267f,), # Wheelchair Symbol
|
||||
(0x0268a, 0x0268f,), # Monogram For Yang ..Digram For Greater Yin
|
||||
(0x02693, 0x02693,), # Anchor
|
||||
(0x026a1, 0x026a1,), # High Voltage Sign
|
||||
(0x026aa, 0x026ab,), # Medium White Circle ..Medium Black Circle
|
||||
(0x026bd, 0x026be,), # Soccer Ball ..Baseball
|
||||
(0x026c4, 0x026c5,), # Snowman Without Snow ..Sun Behind Cloud
|
||||
(0x026ce, 0x026ce,), # Ophiuchus
|
||||
(0x026d4, 0x026d4,), # No Entry
|
||||
(0x026ea, 0x026ea,), # Church
|
||||
(0x026f2, 0x026f3,), # Fountain ..Flag In Hole
|
||||
(0x026f5, 0x026f5,), # Sailboat
|
||||
(0x026fa, 0x026fa,), # Tent
|
||||
(0x026fd, 0x026fd,), # Fuel Pump
|
||||
(0x02705, 0x02705,), # White Heavy Check Mark
|
||||
(0x0270a, 0x0270b,), # Raised Fist ..Raised Hand
|
||||
(0x02728, 0x02728,), # Sparkles
|
||||
(0x0274c, 0x0274c,), # Cross Mark
|
||||
(0x0274e, 0x0274e,), # Negative Squared Cross Mark
|
||||
(0x02753, 0x02755,), # Black Question Mark Orna..White Exclamation Mark O
|
||||
(0x02757, 0x02757,), # Heavy Exclamation Mark Symbol
|
||||
(0x02795, 0x02797,), # Heavy Plus Sign ..Heavy Division Sign
|
||||
(0x027b0, 0x027b0,), # Curly Loop
|
||||
(0x027bf, 0x027bf,), # Double Curly Loop
|
||||
(0x02b1b, 0x02b1c,), # Black Large Square ..White Large Square
|
||||
(0x02b50, 0x02b50,), # White Medium Star
|
||||
(0x02b55, 0x02b55,), # Heavy Large Circle
|
||||
(0x02e80, 0x02e99,), # Cjk Radical Repeat ..Cjk Radical Rap
|
||||
(0x02e9b, 0x02ef3,), # Cjk Radical Choke ..Cjk Radical C-simplified
|
||||
(0x02f00, 0x02fd5,), # Kangxi Radical One ..Kangxi Radical Flute
|
||||
(0x02ff0, 0x03029,), # Ideographic Description ..Hangzhou Numeral Nine
|
||||
(0x03030, 0x0303e,), # Wavy Dash ..Ideographic Variation In
|
||||
(0x03041, 0x03096,), # Hiragana Letter Small A ..Hiragana Letter Small Ke
|
||||
(0x0309b, 0x030ff,), # Katakana-hiragana Voiced..Katakana Digraph Koto
|
||||
(0x03105, 0x0312f,), # Bopomofo Letter B ..Bopomofo Letter Nn
|
||||
(0x03131, 0x03163,), # Hangul Letter Kiyeok ..Hangul Letter I
|
||||
(0x03165, 0x0318e,), # Hangul Letter Ssangnieun..Hangul Letter Araeae
|
||||
(0x03190, 0x031e5,), # Ideographic Annotation L..Cjk Stroke Szp
|
||||
(0x031ef, 0x0321e,), # Ideographic Description ..Parenthesized Korean Cha
|
||||
(0x03220, 0x03247,), # Parenthesized Ideograph ..Circled Ideograph Koto
|
||||
(0x03250, 0x0a48c,), # Partnership Sign ..Yi Syllable Yyr
|
||||
(0x0a490, 0x0a4c6,), # Yi Radical Qot ..Yi Radical Ke
|
||||
(0x0a960, 0x0a97c,), # Hangul Choseong Tikeut-m..Hangul Choseong Ssangyeo
|
||||
(0x0ac00, 0x0d7a3,), # Hangul Syllable Ga ..Hangul Syllable Hih
|
||||
(0x0f900, 0x0faff,), # Cjk Compatibility Ideogr..(nil)
|
||||
(0x0fe10, 0x0fe19,), # Presentation Form For Ve..Presentation Form For Ve
|
||||
(0x0fe30, 0x0fe52,), # Presentation Form For Ve..Small Full Stop
|
||||
(0x0fe54, 0x0fe66,), # Small Semicolon ..Small Equals Sign
|
||||
(0x0fe68, 0x0fe6b,), # Small Reverse Solidus ..Small Commercial At
|
||||
(0x0ff01, 0x0ff60,), # Fullwidth Exclamation Ma..Fullwidth Right White Pa
|
||||
(0x0ffe0, 0x0ffe6,), # Fullwidth Cent Sign ..Fullwidth Won Sign
|
||||
(0x16fe0, 0x16fe3,), # Tangut Iteration Mark ..Old Chinese Iteration Ma
|
||||
(0x16ff2, 0x16ff6,), # Chinese Small Simplified..Yangqin Sign Slow Two Be
|
||||
(0x17000, 0x18cd5,), # (nil) ..Khitan Small Script Char
|
||||
(0x18cff, 0x18d1e,), # Khitan Small Script Char..(nil)
|
||||
(0x18d80, 0x18df2,), # Tangut Component-769 ..Tangut Component-883
|
||||
(0x1aff0, 0x1aff3,), # Katakana Letter Minnan T..Katakana Letter Minnan T
|
||||
(0x1aff5, 0x1affb,), # Katakana Letter Minnan T..Katakana Letter Minnan N
|
||||
(0x1affd, 0x1affe,), # Katakana Letter Minnan N..Katakana Letter Minnan N
|
||||
(0x1b000, 0x1b122,), # Katakana Letter Archaic ..Katakana Letter Archaic
|
||||
(0x1b132, 0x1b132,), # Hiragana Letter Small Ko
|
||||
(0x1b150, 0x1b152,), # Hiragana Letter Small Wi..Hiragana Letter Small Wo
|
||||
(0x1b155, 0x1b155,), # Katakana Letter Small Ko
|
||||
(0x1b164, 0x1b167,), # Katakana Letter Small Wi..Katakana Letter Small N
|
||||
(0x1b170, 0x1b2fb,), # Nushu Character-1b170 ..Nushu Character-1b2fb
|
||||
(0x1d300, 0x1d356,), # Monogram For Earth ..Tetragram For Fostering
|
||||
(0x1d360, 0x1d376,), # Counting Rod Unit Digit ..Ideographic Tally Mark F
|
||||
(0x1f004, 0x1f004,), # Mahjong Tile Red Dragon
|
||||
(0x1f0cf, 0x1f0cf,), # Playing Card Black Joker
|
||||
(0x1f18e, 0x1f18e,), # Negative Squared Ab
|
||||
(0x1f191, 0x1f19a,), # Squared Cl ..Squared Vs
|
||||
(0x1f1e6, 0x1f202,), # Regional Indicator Symbo..Squared Katakana Sa
|
||||
(0x1f210, 0x1f23b,), # Squared Cjk Unified Ideo..Squared Cjk Unified Ideo
|
||||
(0x1f240, 0x1f248,), # Tortoise Shell Bracketed..Tortoise Shell Bracketed
|
||||
(0x1f250, 0x1f251,), # Circled Ideograph Advant..Circled Ideograph Accept
|
||||
(0x1f260, 0x1f265,), # Rounded Symbol For Fu ..Rounded Symbol For Cai
|
||||
(0x1f300, 0x1f320,), # Cyclone ..Shooting Star
|
||||
(0x1f32d, 0x1f335,), # Hot Dog ..Cactus
|
||||
(0x1f337, 0x1f37c,), # Tulip ..Baby Bottle
|
||||
(0x1f37e, 0x1f393,), # Bottle With Popping Cork..Graduation Cap
|
||||
(0x1f3a0, 0x1f3ca,), # Carousel Horse ..Swimmer
|
||||
(0x1f3cf, 0x1f3d3,), # Cricket Bat And Ball ..Table Tennis Paddle And
|
||||
(0x1f3e0, 0x1f3f0,), # House Building ..European Castle
|
||||
(0x1f3f4, 0x1f3f4,), # Waving Black Flag
|
||||
(0x1f3f8, 0x1f43e,), # Badminton Racquet And Sh..Paw Prints
|
||||
(0x1f440, 0x1f440,), # Eyes
|
||||
(0x1f442, 0x1f4fc,), # Ear ..Videocassette
|
||||
(0x1f4ff, 0x1f53d,), # Prayer Beads ..Down-pointing Small Red
|
||||
(0x1f54b, 0x1f54e,), # Kaaba ..Menorah With Nine Branch
|
||||
(0x1f550, 0x1f567,), # Clock Face One Oclock ..Clock Face Twelve-thirty
|
||||
(0x1f57a, 0x1f57a,), # Man Dancing
|
||||
(0x1f595, 0x1f596,), # Reversed Hand With Middl..Raised Hand With Part Be
|
||||
(0x1f5a4, 0x1f5a4,), # Black Heart
|
||||
(0x1f5fb, 0x1f64f,), # Mount Fuji ..Person With Folded Hands
|
||||
(0x1f680, 0x1f6c5,), # Rocket ..Left Luggage
|
||||
(0x1f6cc, 0x1f6cc,), # Sleeping Accommodation
|
||||
(0x1f6d0, 0x1f6d2,), # Place Of Worship ..Shopping Trolley
|
||||
(0x1f6d5, 0x1f6d8,), # Hindu Temple ..Landslide
|
||||
(0x1f6dc, 0x1f6df,), # Wireless ..Ring Buoy
|
||||
(0x1f6eb, 0x1f6ec,), # Airplane Departure ..Airplane Arriving
|
||||
(0x1f6f4, 0x1f6fc,), # Scooter ..Roller Skate
|
||||
(0x1f7e0, 0x1f7eb,), # Large Orange Circle ..Large Brown Square
|
||||
(0x1f7f0, 0x1f7f0,), # Heavy Equals Sign
|
||||
(0x1f90c, 0x1f93a,), # Pinched Fingers ..Fencer
|
||||
(0x1f93c, 0x1f945,), # Wrestlers ..Goal Net
|
||||
(0x1f947, 0x1f9ff,), # First Place Medal ..Nazar Amulet
|
||||
(0x1fa70, 0x1fa7c,), # Ballet Shoes ..Crutch
|
||||
(0x1fa80, 0x1fa8a,), # Yo-yo ..Trombone
|
||||
(0x1fa8e, 0x1fac6,), # Treasure Chest ..Fingerprint
|
||||
(0x1fac8, 0x1fac8,), # Hairy Creature
|
||||
(0x1facd, 0x1fadc,), # Orca ..Root Vegetable
|
||||
(0x1fadf, 0x1faea,), # Splatter ..Distorted Face
|
||||
(0x1faef, 0x1faf8,), # Fight Cloud ..Rightwards Pushing Hand
|
||||
(0x20000, 0x2fffd,), # Cjk Unified Ideograph-20..(nil)
|
||||
(0x30000, 0x3fffd,), # Cjk Unified Ideograph-30..(nil)
|
||||
),
|
||||
}
|
||||
350
venv/lib/python3.12/site-packages/wcwidth/table_zero.py
Normal file
350
venv/lib/python3.12/site-packages/wcwidth/table_zero.py
Normal file
@@ -0,0 +1,350 @@
|
||||
"""
|
||||
Exports ZERO_WIDTH table keyed by supporting unicode version level.
|
||||
|
||||
This code generated by wcwidth/bin/update-tables.py on 2026-01-30 00:48:24 UTC.
|
||||
"""
|
||||
# pylint: disable=duplicate-code
|
||||
ZERO_WIDTH = {
|
||||
'17.0.0': (
|
||||
# Source: DerivedGeneralCategory-17.0.0.txt
|
||||
# Date: 2025-07-24, 00:12:50 GMT
|
||||
#
|
||||
(0x00000, 0x00000,), # (nil)
|
||||
(0x00300, 0x0036f,), # Combining Grave Accent ..Combining Latin Small Le
|
||||
(0x00483, 0x00489,), # Combining Cyrillic Titlo..Combining Cyrillic Milli
|
||||
(0x00591, 0x005bd,), # Hebrew Accent Etnahta ..Hebrew Point Meteg
|
||||
(0x005bf, 0x005bf,), # Hebrew Point Rafe
|
||||
(0x005c1, 0x005c2,), # Hebrew Point Shin Dot ..Hebrew Point Sin Dot
|
||||
(0x005c4, 0x005c5,), # Hebrew Mark Upper Dot ..Hebrew Mark Lower Dot
|
||||
(0x005c7, 0x005c7,), # Hebrew Point Qamats Qatan
|
||||
(0x00610, 0x0061a,), # Arabic Sign Sallallahou ..Arabic Small Kasra
|
||||
(0x0061c, 0x0061c,), # Arabic Letter Mark
|
||||
(0x0064b, 0x0065f,), # Arabic Fathatan ..Arabic Wavy Hamza Below
|
||||
(0x00670, 0x00670,), # Arabic Letter Superscript Alef
|
||||
(0x006d6, 0x006dc,), # Arabic Small High Ligatu..Arabic Small High Seen
|
||||
(0x006df, 0x006e4,), # Arabic Small High Rounde..Arabic Small High Madda
|
||||
(0x006e7, 0x006e8,), # Arabic Small High Yeh ..Arabic Small High Noon
|
||||
(0x006ea, 0x006ed,), # Arabic Empty Centre Low ..Arabic Small Low Meem
|
||||
(0x00711, 0x00711,), # Syriac Letter Superscript Alaph
|
||||
(0x00730, 0x0074a,), # Syriac Pthaha Above ..Syriac Barrekh
|
||||
(0x007a6, 0x007b0,), # Thaana Abafili ..Thaana Sukun
|
||||
(0x007eb, 0x007f3,), # Nko Combining Short High..Nko Combining Double Dot
|
||||
(0x007fd, 0x007fd,), # Nko Dantayalan
|
||||
(0x00816, 0x00819,), # Samaritan Mark In ..Samaritan Mark Dagesh
|
||||
(0x0081b, 0x00823,), # Samaritan Mark Epentheti..Samaritan Vowel Sign A
|
||||
(0x00825, 0x00827,), # Samaritan Vowel Sign Sho..Samaritan Vowel Sign U
|
||||
(0x00829, 0x0082d,), # Samaritan Vowel Sign Lon..Samaritan Mark Nequdaa
|
||||
(0x00859, 0x0085b,), # Mandaic Affrication Mark..Mandaic Gemination Mark
|
||||
(0x00897, 0x0089f,), # Arabic Pepet ..Arabic Half Madda Over M
|
||||
(0x008ca, 0x008e1,), # Arabic Small High Farsi ..Arabic Small High Sign S
|
||||
(0x008e3, 0x00903,), # Arabic Turned Damma Belo..Devanagari Sign Visarga
|
||||
(0x0093a, 0x0093c,), # Devanagari Vowel Sign Oe..Devanagari Sign Nukta
|
||||
(0x0093e, 0x0094f,), # Devanagari Vowel Sign Aa..Devanagari Vowel Sign Aw
|
||||
(0x00951, 0x00957,), # Devanagari Stress Sign U..Devanagari Vowel Sign Uu
|
||||
(0x00962, 0x00963,), # Devanagari Vowel Sign Vo..Devanagari Vowel Sign Vo
|
||||
(0x00981, 0x00983,), # Bengali Sign Candrabindu..Bengali Sign Visarga
|
||||
(0x009bc, 0x009bc,), # Bengali Sign Nukta
|
||||
(0x009be, 0x009c4,), # Bengali Vowel Sign Aa ..Bengali Vowel Sign Vocal
|
||||
(0x009c7, 0x009c8,), # Bengali Vowel Sign E ..Bengali Vowel Sign Ai
|
||||
(0x009cb, 0x009cd,), # Bengali Vowel Sign O ..Bengali Sign Virama
|
||||
(0x009d7, 0x009d7,), # Bengali Au Length Mark
|
||||
(0x009e2, 0x009e3,), # Bengali Vowel Sign Vocal..Bengali Vowel Sign Vocal
|
||||
(0x009fe, 0x009fe,), # Bengali Sandhi Mark
|
||||
(0x00a01, 0x00a03,), # Gurmukhi Sign Adak Bindi..Gurmukhi Sign Visarga
|
||||
(0x00a3c, 0x00a3c,), # Gurmukhi Sign Nukta
|
||||
(0x00a3e, 0x00a42,), # Gurmukhi Vowel Sign Aa ..Gurmukhi Vowel Sign Uu
|
||||
(0x00a47, 0x00a48,), # Gurmukhi Vowel Sign Ee ..Gurmukhi Vowel Sign Ai
|
||||
(0x00a4b, 0x00a4d,), # Gurmukhi Vowel Sign Oo ..Gurmukhi Sign Virama
|
||||
(0x00a51, 0x00a51,), # Gurmukhi Sign Udaat
|
||||
(0x00a70, 0x00a71,), # Gurmukhi Tippi ..Gurmukhi Addak
|
||||
(0x00a75, 0x00a75,), # Gurmukhi Sign Yakash
|
||||
(0x00a81, 0x00a83,), # Gujarati Sign Candrabind..Gujarati Sign Visarga
|
||||
(0x00abc, 0x00abc,), # Gujarati Sign Nukta
|
||||
(0x00abe, 0x00ac5,), # Gujarati Vowel Sign Aa ..Gujarati Vowel Sign Cand
|
||||
(0x00ac7, 0x00ac9,), # Gujarati Vowel Sign E ..Gujarati Vowel Sign Cand
|
||||
(0x00acb, 0x00acd,), # Gujarati Vowel Sign O ..Gujarati Sign Virama
|
||||
(0x00ae2, 0x00ae3,), # Gujarati Vowel Sign Voca..Gujarati Vowel Sign Voca
|
||||
(0x00afa, 0x00aff,), # Gujarati Sign Sukun ..Gujarati Sign Two-circle
|
||||
(0x00b01, 0x00b03,), # Oriya Sign Candrabindu ..Oriya Sign Visarga
|
||||
(0x00b3c, 0x00b3c,), # Oriya Sign Nukta
|
||||
(0x00b3e, 0x00b44,), # Oriya Vowel Sign Aa ..Oriya Vowel Sign Vocalic
|
||||
(0x00b47, 0x00b48,), # Oriya Vowel Sign E ..Oriya Vowel Sign Ai
|
||||
(0x00b4b, 0x00b4d,), # Oriya Vowel Sign O ..Oriya Sign Virama
|
||||
(0x00b55, 0x00b57,), # Oriya Sign Overline ..Oriya Au Length Mark
|
||||
(0x00b62, 0x00b63,), # Oriya Vowel Sign Vocalic..Oriya Vowel Sign Vocalic
|
||||
(0x00b82, 0x00b82,), # Tamil Sign Anusvara
|
||||
(0x00bbe, 0x00bc2,), # Tamil Vowel Sign Aa ..Tamil Vowel Sign Uu
|
||||
(0x00bc6, 0x00bc8,), # Tamil Vowel Sign E ..Tamil Vowel Sign Ai
|
||||
(0x00bca, 0x00bcd,), # Tamil Vowel Sign O ..Tamil Sign Virama
|
||||
(0x00bd7, 0x00bd7,), # Tamil Au Length Mark
|
||||
(0x00c00, 0x00c04,), # Telugu Sign Combining Ca..Telugu Sign Combining An
|
||||
(0x00c3c, 0x00c3c,), # Telugu Sign Nukta
|
||||
(0x00c3e, 0x00c44,), # Telugu Vowel Sign Aa ..Telugu Vowel Sign Vocali
|
||||
(0x00c46, 0x00c48,), # Telugu Vowel Sign E ..Telugu Vowel Sign Ai
|
||||
(0x00c4a, 0x00c4d,), # Telugu Vowel Sign O ..Telugu Sign Virama
|
||||
(0x00c55, 0x00c56,), # Telugu Length Mark ..Telugu Ai Length Mark
|
||||
(0x00c62, 0x00c63,), # Telugu Vowel Sign Vocali..Telugu Vowel Sign Vocali
|
||||
(0x00c81, 0x00c83,), # Kannada Sign Candrabindu..Kannada Sign Visarga
|
||||
(0x00cbc, 0x00cbc,), # Kannada Sign Nukta
|
||||
(0x00cbe, 0x00cc4,), # Kannada Vowel Sign Aa ..Kannada Vowel Sign Vocal
|
||||
(0x00cc6, 0x00cc8,), # Kannada Vowel Sign E ..Kannada Vowel Sign Ai
|
||||
(0x00cca, 0x00ccd,), # Kannada Vowel Sign O ..Kannada Sign Virama
|
||||
(0x00cd5, 0x00cd6,), # Kannada Length Mark ..Kannada Ai Length Mark
|
||||
(0x00ce2, 0x00ce3,), # Kannada Vowel Sign Vocal..Kannada Vowel Sign Vocal
|
||||
(0x00cf3, 0x00cf3,), # Kannada Sign Combining Anusvara Above Right
|
||||
(0x00d00, 0x00d03,), # Malayalam Sign Combining..Malayalam Sign Visarga
|
||||
(0x00d3b, 0x00d3c,), # Malayalam Sign Vertical ..Malayalam Sign Circular
|
||||
(0x00d3e, 0x00d44,), # Malayalam Vowel Sign Aa ..Malayalam Vowel Sign Voc
|
||||
(0x00d46, 0x00d48,), # Malayalam Vowel Sign E ..Malayalam Vowel Sign Ai
|
||||
(0x00d4a, 0x00d4d,), # Malayalam Vowel Sign O ..Malayalam Sign Virama
|
||||
(0x00d57, 0x00d57,), # Malayalam Au Length Mark
|
||||
(0x00d62, 0x00d63,), # Malayalam Vowel Sign Voc..Malayalam Vowel Sign Voc
|
||||
(0x00d81, 0x00d83,), # Sinhala Sign Candrabindu..Sinhala Sign Visargaya
|
||||
(0x00dca, 0x00dca,), # Sinhala Sign Al-lakuna
|
||||
(0x00dcf, 0x00dd4,), # Sinhala Vowel Sign Aela-..Sinhala Vowel Sign Ketti
|
||||
(0x00dd6, 0x00dd6,), # Sinhala Vowel Sign Diga Paa-pilla
|
||||
(0x00dd8, 0x00ddf,), # Sinhala Vowel Sign Gaett..Sinhala Vowel Sign Gayan
|
||||
(0x00df2, 0x00df3,), # Sinhala Vowel Sign Diga ..Sinhala Vowel Sign Diga
|
||||
(0x00e31, 0x00e31,), # Thai Character Mai Han-akat
|
||||
(0x00e34, 0x00e3a,), # Thai Character Sara I ..Thai Character Phinthu
|
||||
(0x00e47, 0x00e4e,), # Thai Character Maitaikhu..Thai Character Yamakkan
|
||||
(0x00eb1, 0x00eb1,), # Lao Vowel Sign Mai Kan
|
||||
(0x00eb4, 0x00ebc,), # Lao Vowel Sign I ..Lao Semivowel Sign Lo
|
||||
(0x00ec8, 0x00ece,), # Lao Tone Mai Ek ..Lao Yamakkan
|
||||
(0x00f18, 0x00f19,), # Tibetan Astrological Sig..Tibetan Astrological Sig
|
||||
(0x00f35, 0x00f35,), # Tibetan Mark Ngas Bzung Nyi Zla
|
||||
(0x00f37, 0x00f37,), # Tibetan Mark Ngas Bzung Sgor Rtags
|
||||
(0x00f39, 0x00f39,), # Tibetan Mark Tsa -phru
|
||||
(0x00f3e, 0x00f3f,), # Tibetan Sign Yar Tshes ..Tibetan Sign Mar Tshes
|
||||
(0x00f71, 0x00f84,), # Tibetan Vowel Sign Aa ..Tibetan Mark Halanta
|
||||
(0x00f86, 0x00f87,), # Tibetan Sign Lci Rtags ..Tibetan Sign Yang Rtags
|
||||
(0x00f8d, 0x00f97,), # Tibetan Subjoined Sign L..Tibetan Subjoined Letter
|
||||
(0x00f99, 0x00fbc,), # Tibetan Subjoined Letter..Tibetan Subjoined Letter
|
||||
(0x00fc6, 0x00fc6,), # Tibetan Symbol Padma Gdan
|
||||
(0x0102b, 0x0103e,), # Myanmar Vowel Sign Tall ..Myanmar Consonant Sign M
|
||||
(0x01056, 0x01059,), # Myanmar Vowel Sign Vocal..Myanmar Vowel Sign Vocal
|
||||
(0x0105e, 0x01060,), # Myanmar Consonant Sign M..Myanmar Consonant Sign M
|
||||
(0x01062, 0x01064,), # Myanmar Vowel Sign Sgaw ..Myanmar Tone Mark Sgaw K
|
||||
(0x01067, 0x0106d,), # Myanmar Vowel Sign Weste..Myanmar Sign Western Pwo
|
||||
(0x01071, 0x01074,), # Myanmar Vowel Sign Geba ..Myanmar Vowel Sign Kayah
|
||||
(0x01082, 0x0108d,), # Myanmar Consonant Sign S..Myanmar Sign Shan Counci
|
||||
(0x0108f, 0x0108f,), # Myanmar Sign Rumai Palaung Tone-5
|
||||
(0x0109a, 0x0109d,), # Myanmar Sign Khamti Tone..Myanmar Vowel Sign Aiton
|
||||
(0x01160, 0x011ff,), # Hangul Jungseong Filler ..Hangul Jongseong Ssangni
|
||||
(0x0135d, 0x0135f,), # Ethiopic Combining Gemin..Ethiopic Combining Gemin
|
||||
(0x01712, 0x01715,), # Tagalog Vowel Sign I ..Tagalog Sign Pamudpod
|
||||
(0x01732, 0x01734,), # Hanunoo Vowel Sign I ..Hanunoo Sign Pamudpod
|
||||
(0x01752, 0x01753,), # Buhid Vowel Sign I ..Buhid Vowel Sign U
|
||||
(0x01772, 0x01773,), # Tagbanwa Vowel Sign I ..Tagbanwa Vowel Sign U
|
||||
(0x017b4, 0x017d3,), # Khmer Vowel Inherent Aq ..Khmer Sign Bathamasat
|
||||
(0x017dd, 0x017dd,), # Khmer Sign Atthacan
|
||||
(0x0180b, 0x0180f,), # Mongolian Free Variation..Mongolian Free Variation
|
||||
(0x01885, 0x01886,), # Mongolian Letter Ali Gal..Mongolian Letter Ali Gal
|
||||
(0x018a9, 0x018a9,), # Mongolian Letter Ali Gali Dagalga
|
||||
(0x01920, 0x0192b,), # Limbu Vowel Sign A ..Limbu Subjoined Letter W
|
||||
(0x01930, 0x0193b,), # Limbu Small Letter Ka ..Limbu Sign Sa-i
|
||||
(0x01a17, 0x01a1b,), # Buginese Vowel Sign I ..Buginese Vowel Sign Ae
|
||||
(0x01a55, 0x01a5e,), # Tai Tham Consonant Sign ..Tai Tham Consonant Sign
|
||||
(0x01a60, 0x01a7c,), # Tai Tham Sign Sakot ..Tai Tham Sign Khuen-lue
|
||||
(0x01a7f, 0x01a7f,), # Tai Tham Combining Cryptogrammic Dot
|
||||
(0x01ab0, 0x01add,), # Combining Doubled Circum..Combining Dot-and-ring B
|
||||
(0x01ae0, 0x01aeb,), # Combining Left Tack Abov..Combining Double Rightwa
|
||||
(0x01b00, 0x01b04,), # Balinese Sign Ulu Ricem ..Balinese Sign Bisah
|
||||
(0x01b34, 0x01b44,), # Balinese Sign Rerekan ..Balinese Adeg Adeg
|
||||
(0x01b6b, 0x01b73,), # Balinese Musical Symbol ..Balinese Musical Symbol
|
||||
(0x01b80, 0x01b82,), # Sundanese Sign Panyecek ..Sundanese Sign Pangwisad
|
||||
(0x01ba1, 0x01bad,), # Sundanese Consonant Sign..Sundanese Consonant Sign
|
||||
(0x01be6, 0x01bf3,), # Batak Sign Tompi ..Batak Panongonan
|
||||
(0x01c24, 0x01c37,), # Lepcha Subjoined Letter ..Lepcha Sign Nukta
|
||||
(0x01cd0, 0x01cd2,), # Vedic Tone Karshana ..Vedic Tone Prenkha
|
||||
(0x01cd4, 0x01ce8,), # Vedic Sign Yajurvedic Mi..Vedic Sign Visarga Anuda
|
||||
(0x01ced, 0x01ced,), # Vedic Sign Tiryak
|
||||
(0x01cf4, 0x01cf4,), # Vedic Tone Candra Above
|
||||
(0x01cf7, 0x01cf9,), # Vedic Sign Atikrama ..Vedic Tone Double Ring A
|
||||
(0x01dc0, 0x01dff,), # Combining Dotted Grave A..Combining Right Arrowhea
|
||||
(0x0200b, 0x0200f,), # Zero Width Space ..Right-to-left Mark
|
||||
(0x02028, 0x0202e,), # Line Separator ..Right-to-left Override
|
||||
(0x02060, 0x0206f,), # Word Joiner ..Nominal Digit Shapes
|
||||
(0x020d0, 0x020f0,), # Combining Left Harpoon A..Combining Asterisk Above
|
||||
(0x02cef, 0x02cf1,), # Coptic Combining Ni Abov..Coptic Combining Spiritu
|
||||
(0x02d7f, 0x02d7f,), # Tifinagh Consonant Joiner
|
||||
(0x02de0, 0x02dff,), # Combining Cyrillic Lette..Combining Cyrillic Lette
|
||||
(0x0302a, 0x0302f,), # Ideographic Level Tone M..Hangul Double Dot Tone M
|
||||
(0x03099, 0x0309a,), # Combining Katakana-hirag..Combining Katakana-hirag
|
||||
(0x03164, 0x03164,), # Hangul Filler
|
||||
(0x0a66f, 0x0a672,), # Combining Cyrillic Vzmet..Combining Cyrillic Thous
|
||||
(0x0a674, 0x0a67d,), # Combining Cyrillic Lette..Combining Cyrillic Payer
|
||||
(0x0a69e, 0x0a69f,), # Combining Cyrillic Lette..Combining Cyrillic Lette
|
||||
(0x0a6f0, 0x0a6f1,), # Bamum Combining Mark Koq..Bamum Combining Mark Tuk
|
||||
(0x0a802, 0x0a802,), # Syloti Nagri Sign Dvisvara
|
||||
(0x0a806, 0x0a806,), # Syloti Nagri Sign Hasanta
|
||||
(0x0a80b, 0x0a80b,), # Syloti Nagri Sign Anusvara
|
||||
(0x0a823, 0x0a827,), # Syloti Nagri Vowel Sign ..Syloti Nagri Vowel Sign
|
||||
(0x0a82c, 0x0a82c,), # Syloti Nagri Sign Alternate Hasanta
|
||||
(0x0a880, 0x0a881,), # Saurashtra Sign Anusvara..Saurashtra Sign Visarga
|
||||
(0x0a8b4, 0x0a8c5,), # Saurashtra Consonant Sig..Saurashtra Sign Candrabi
|
||||
(0x0a8e0, 0x0a8f1,), # Combining Devanagari Dig..Combining Devanagari Sig
|
||||
(0x0a8ff, 0x0a8ff,), # Devanagari Vowel Sign Ay
|
||||
(0x0a926, 0x0a92d,), # Kayah Li Vowel Ue ..Kayah Li Tone Calya Plop
|
||||
(0x0a947, 0x0a953,), # Rejang Vowel Sign I ..Rejang Virama
|
||||
(0x0a980, 0x0a983,), # Javanese Sign Panyangga ..Javanese Sign Wignyan
|
||||
(0x0a9b3, 0x0a9c0,), # Javanese Sign Cecak Telu..Javanese Pangkon
|
||||
(0x0a9e5, 0x0a9e5,), # Myanmar Sign Shan Saw
|
||||
(0x0aa29, 0x0aa36,), # Cham Vowel Sign Aa ..Cham Consonant Sign Wa
|
||||
(0x0aa43, 0x0aa43,), # Cham Consonant Sign Final Ng
|
||||
(0x0aa4c, 0x0aa4d,), # Cham Consonant Sign Fina..Cham Consonant Sign Fina
|
||||
(0x0aa7b, 0x0aa7d,), # Myanmar Sign Pao Karen T..Myanmar Sign Tai Laing T
|
||||
(0x0aab0, 0x0aab0,), # Tai Viet Mai Kang
|
||||
(0x0aab2, 0x0aab4,), # Tai Viet Vowel I ..Tai Viet Vowel U
|
||||
(0x0aab7, 0x0aab8,), # Tai Viet Mai Khit ..Tai Viet Vowel Ia
|
||||
(0x0aabe, 0x0aabf,), # Tai Viet Vowel Am ..Tai Viet Tone Mai Ek
|
||||
(0x0aac1, 0x0aac1,), # Tai Viet Tone Mai Tho
|
||||
(0x0aaeb, 0x0aaef,), # Meetei Mayek Vowel Sign ..Meetei Mayek Vowel Sign
|
||||
(0x0aaf5, 0x0aaf6,), # Meetei Mayek Vowel Sign ..Meetei Mayek Virama
|
||||
(0x0abe3, 0x0abea,), # Meetei Mayek Vowel Sign ..Meetei Mayek Vowel Sign
|
||||
(0x0abec, 0x0abed,), # Meetei Mayek Lum Iyek ..Meetei Mayek Apun Iyek
|
||||
(0x0d7b0, 0x0d7ff,), # Hangul Jungseong O-yeo ..(nil)
|
||||
(0x0fb1e, 0x0fb1e,), # Hebrew Point Judeo-spanish Varika
|
||||
(0x0fe00, 0x0fe0f,), # Variation Selector-1 ..Variation Selector-16
|
||||
(0x0fe20, 0x0fe2f,), # Combining Ligature Left ..Combining Cyrillic Titlo
|
||||
(0x0feff, 0x0feff,), # Zero Width No-break Space
|
||||
(0x0ffa0, 0x0ffa0,), # Halfwidth Hangul Filler
|
||||
(0x0fff0, 0x0fffb,), # (nil) ..Interlinear Annotation T
|
||||
(0x101fd, 0x101fd,), # Phaistos Disc Sign Combining Oblique Stroke
|
||||
(0x102e0, 0x102e0,), # Coptic Epact Thousands Mark
|
||||
(0x10376, 0x1037a,), # Combining Old Permic Let..Combining Old Permic Let
|
||||
(0x10a01, 0x10a03,), # Kharoshthi Vowel Sign I ..Kharoshthi Vowel Sign Vo
|
||||
(0x10a05, 0x10a06,), # Kharoshthi Vowel Sign E ..Kharoshthi Vowel Sign O
|
||||
(0x10a0c, 0x10a0f,), # Kharoshthi Vowel Length ..Kharoshthi Sign Visarga
|
||||
(0x10a38, 0x10a3a,), # Kharoshthi Sign Bar Abov..Kharoshthi Sign Dot Belo
|
||||
(0x10a3f, 0x10a3f,), # Kharoshthi Virama
|
||||
(0x10ae5, 0x10ae6,), # Manichaean Abbreviation ..Manichaean Abbreviation
|
||||
(0x10d24, 0x10d27,), # Hanifi Rohingya Sign Har..Hanifi Rohingya Sign Tas
|
||||
(0x10d69, 0x10d6d,), # Garay Vowel Sign E ..Garay Consonant Nasaliza
|
||||
(0x10eab, 0x10eac,), # Yezidi Combining Hamza M..Yezidi Combining Madda M
|
||||
(0x10efa, 0x10eff,), # Arabic Double Vertical B..Arabic Small Low Word Ma
|
||||
(0x10f46, 0x10f50,), # Sogdian Combining Dot Be..Sogdian Combining Stroke
|
||||
(0x10f82, 0x10f85,), # Old Uyghur Combining Dot..Old Uyghur Combining Two
|
||||
(0x11000, 0x11002,), # Brahmi Sign Candrabindu ..Brahmi Sign Visarga
|
||||
(0x11038, 0x11046,), # Brahmi Vowel Sign Aa ..Brahmi Virama
|
||||
(0x11070, 0x11070,), # Brahmi Sign Old Tamil Virama
|
||||
(0x11073, 0x11074,), # Brahmi Vowel Sign Old Ta..Brahmi Vowel Sign Old Ta
|
||||
(0x1107f, 0x11082,), # Brahmi Number Joiner ..Kaithi Sign Visarga
|
||||
(0x110b0, 0x110ba,), # Kaithi Vowel Sign Aa ..Kaithi Sign Nukta
|
||||
(0x110c2, 0x110c2,), # Kaithi Vowel Sign Vocalic R
|
||||
(0x11100, 0x11102,), # Chakma Sign Candrabindu ..Chakma Sign Visarga
|
||||
(0x11127, 0x11134,), # Chakma Vowel Sign A ..Chakma Maayyaa
|
||||
(0x11145, 0x11146,), # Chakma Vowel Sign Aa ..Chakma Vowel Sign Ei
|
||||
(0x11173, 0x11173,), # Mahajani Sign Nukta
|
||||
(0x11180, 0x11182,), # Sharada Sign Candrabindu..Sharada Sign Visarga
|
||||
(0x111b3, 0x111c0,), # Sharada Vowel Sign Aa ..Sharada Sign Virama
|
||||
(0x111c9, 0x111cc,), # Sharada Sandhi Mark ..Sharada Extra Short Vowe
|
||||
(0x111ce, 0x111cf,), # Sharada Vowel Sign Prish..Sharada Sign Inverted Ca
|
||||
(0x1122c, 0x11237,), # Khojki Vowel Sign Aa ..Khojki Sign Shadda
|
||||
(0x1123e, 0x1123e,), # Khojki Sign Sukun
|
||||
(0x11241, 0x11241,), # Khojki Vowel Sign Vocalic R
|
||||
(0x112df, 0x112ea,), # Khudawadi Sign Anusvara ..Khudawadi Sign Virama
|
||||
(0x11300, 0x11303,), # Grantha Sign Combining A..Grantha Sign Visarga
|
||||
(0x1133b, 0x1133c,), # Combining Bindu Below ..Grantha Sign Nukta
|
||||
(0x1133e, 0x11344,), # Grantha Vowel Sign Aa ..Grantha Vowel Sign Vocal
|
||||
(0x11347, 0x11348,), # Grantha Vowel Sign Ee ..Grantha Vowel Sign Ai
|
||||
(0x1134b, 0x1134d,), # Grantha Vowel Sign Oo ..Grantha Sign Virama
|
||||
(0x11357, 0x11357,), # Grantha Au Length Mark
|
||||
(0x11362, 0x11363,), # Grantha Vowel Sign Vocal..Grantha Vowel Sign Vocal
|
||||
(0x11366, 0x1136c,), # Combining Grantha Digit ..Combining Grantha Digit
|
||||
(0x11370, 0x11374,), # Combining Grantha Letter..Combining Grantha Letter
|
||||
(0x113b8, 0x113c0,), # Tulu-tigalari Vowel Sign..Tulu-tigalari Vowel Sign
|
||||
(0x113c2, 0x113c2,), # Tulu-tigalari Vowel Sign Ee
|
||||
(0x113c5, 0x113c5,), # Tulu-tigalari Vowel Sign Ai
|
||||
(0x113c7, 0x113ca,), # Tulu-tigalari Vowel Sign..Tulu-tigalari Sign Candr
|
||||
(0x113cc, 0x113d0,), # Tulu-tigalari Sign Anusv..Tulu-tigalari Conjoiner
|
||||
(0x113d2, 0x113d2,), # Tulu-tigalari Gemination Mark
|
||||
(0x113e1, 0x113e2,), # Tulu-tigalari Vedic Tone..Tulu-tigalari Vedic Tone
|
||||
(0x11435, 0x11446,), # Newa Vowel Sign Aa ..Newa Sign Nukta
|
||||
(0x1145e, 0x1145e,), # Newa Sandhi Mark
|
||||
(0x114b0, 0x114c3,), # Tirhuta Vowel Sign Aa ..Tirhuta Sign Nukta
|
||||
(0x115af, 0x115b5,), # Siddham Vowel Sign Aa ..Siddham Vowel Sign Vocal
|
||||
(0x115b8, 0x115c0,), # Siddham Vowel Sign E ..Siddham Sign Nukta
|
||||
(0x115dc, 0x115dd,), # Siddham Vowel Sign Alter..Siddham Vowel Sign Alter
|
||||
(0x11630, 0x11640,), # Modi Vowel Sign Aa ..Modi Sign Ardhacandra
|
||||
(0x116ab, 0x116b7,), # Takri Sign Anusvara ..Takri Sign Nukta
|
||||
(0x1171d, 0x1172b,), # Ahom Consonant Sign Medi..Ahom Sign Killer
|
||||
(0x1182c, 0x1183a,), # Dogra Vowel Sign Aa ..Dogra Sign Nukta
|
||||
(0x11930, 0x11935,), # Dives Akuru Vowel Sign A..Dives Akuru Vowel Sign E
|
||||
(0x11937, 0x11938,), # Dives Akuru Vowel Sign A..Dives Akuru Vowel Sign O
|
||||
(0x1193b, 0x1193e,), # Dives Akuru Sign Anusvar..Dives Akuru Virama
|
||||
(0x11940, 0x11940,), # Dives Akuru Medial Ya
|
||||
(0x11942, 0x11943,), # Dives Akuru Medial Ra ..Dives Akuru Sign Nukta
|
||||
(0x119d1, 0x119d7,), # Nandinagari Vowel Sign A..Nandinagari Vowel Sign V
|
||||
(0x119da, 0x119e0,), # Nandinagari Vowel Sign E..Nandinagari Sign Virama
|
||||
(0x119e4, 0x119e4,), # Nandinagari Vowel Sign Prishthamatra E
|
||||
(0x11a01, 0x11a0a,), # Zanabazar Square Vowel S..Zanabazar Square Vowel L
|
||||
(0x11a33, 0x11a39,), # Zanabazar Square Final C..Zanabazar Square Sign Vi
|
||||
(0x11a3b, 0x11a3e,), # Zanabazar Square Cluster..Zanabazar Square Cluster
|
||||
(0x11a47, 0x11a47,), # Zanabazar Square Subjoiner
|
||||
(0x11a51, 0x11a5b,), # Soyombo Vowel Sign I ..Soyombo Vowel Length Mar
|
||||
(0x11a8a, 0x11a99,), # Soyombo Final Consonant ..Soyombo Subjoiner
|
||||
(0x11b60, 0x11b67,), # Sharada Vowel Sign Oe ..Sharada Vowel Sign Candr
|
||||
(0x11c2f, 0x11c36,), # Bhaiksuki Vowel Sign Aa ..Bhaiksuki Vowel Sign Voc
|
||||
(0x11c38, 0x11c3f,), # Bhaiksuki Vowel Sign E ..Bhaiksuki Sign Virama
|
||||
(0x11c92, 0x11ca7,), # Marchen Subjoined Letter..Marchen Subjoined Letter
|
||||
(0x11ca9, 0x11cb6,), # Marchen Subjoined Letter..Marchen Sign Candrabindu
|
||||
(0x11d31, 0x11d36,), # Masaram Gondi Vowel Sign..Masaram Gondi Vowel Sign
|
||||
(0x11d3a, 0x11d3a,), # Masaram Gondi Vowel Sign E
|
||||
(0x11d3c, 0x11d3d,), # Masaram Gondi Vowel Sign..Masaram Gondi Vowel Sign
|
||||
(0x11d3f, 0x11d45,), # Masaram Gondi Vowel Sign..Masaram Gondi Virama
|
||||
(0x11d47, 0x11d47,), # Masaram Gondi Ra-kara
|
||||
(0x11d8a, 0x11d8e,), # Gunjala Gondi Vowel Sign..Gunjala Gondi Vowel Sign
|
||||
(0x11d90, 0x11d91,), # Gunjala Gondi Vowel Sign..Gunjala Gondi Vowel Sign
|
||||
(0x11d93, 0x11d97,), # Gunjala Gondi Vowel Sign..Gunjala Gondi Virama
|
||||
(0x11ef3, 0x11ef6,), # Makasar Vowel Sign I ..Makasar Vowel Sign O
|
||||
(0x11f00, 0x11f01,), # Kawi Sign Candrabindu ..Kawi Sign Anusvara
|
||||
(0x11f03, 0x11f03,), # Kawi Sign Visarga
|
||||
(0x11f34, 0x11f3a,), # Kawi Vowel Sign Aa ..Kawi Vowel Sign Vocalic
|
||||
(0x11f3e, 0x11f42,), # Kawi Vowel Sign E ..Kawi Conjoiner
|
||||
(0x11f5a, 0x11f5a,), # Kawi Sign Nukta
|
||||
(0x13430, 0x13440,), # Egyptian Hieroglyph Vert..Egyptian Hieroglyph Mirr
|
||||
(0x13447, 0x13455,), # Egyptian Hieroglyph Modi..Egyptian Hieroglyph Modi
|
||||
(0x1611e, 0x1612f,), # Gurung Khema Vowel Sign ..Gurung Khema Sign Tholho
|
||||
(0x16af0, 0x16af4,), # Bassa Vah Combining High..Bassa Vah Combining High
|
||||
(0x16b30, 0x16b36,), # Pahawh Hmong Mark Cim Tu..Pahawh Hmong Mark Cim Ta
|
||||
(0x16f4f, 0x16f4f,), # Miao Sign Consonant Modifier Bar
|
||||
(0x16f51, 0x16f87,), # Miao Sign Aspiration ..Miao Vowel Sign Ui
|
||||
(0x16f8f, 0x16f92,), # Miao Tone Right ..Miao Tone Below
|
||||
(0x16fe4, 0x16fe4,), # Khitan Small Script Filler
|
||||
(0x16ff0, 0x16ff1,), # Vietnamese Alternate Rea..Vietnamese Alternate Rea
|
||||
(0x1bc9d, 0x1bc9e,), # Duployan Thick Letter Se..Duployan Double Mark
|
||||
(0x1bca0, 0x1bca3,), # Shorthand Format Letter ..Shorthand Format Up Step
|
||||
(0x1cf00, 0x1cf2d,), # Znamenny Combining Mark ..Znamenny Combining Mark
|
||||
(0x1cf30, 0x1cf46,), # Znamenny Combining Tonal..Znamenny Priznak Modifie
|
||||
(0x1d165, 0x1d169,), # Musical Symbol Combining..Musical Symbol Combining
|
||||
(0x1d16d, 0x1d182,), # Musical Symbol Combining..Musical Symbol Combining
|
||||
(0x1d185, 0x1d18b,), # Musical Symbol Combining..Musical Symbol Combining
|
||||
(0x1d1aa, 0x1d1ad,), # Musical Symbol Combining..Musical Symbol Combining
|
||||
(0x1d242, 0x1d244,), # Combining Greek Musical ..Combining Greek Musical
|
||||
(0x1da00, 0x1da36,), # Signwriting Head Rim ..Signwriting Air Sucking
|
||||
(0x1da3b, 0x1da6c,), # Signwriting Mouth Closed..Signwriting Excitement
|
||||
(0x1da75, 0x1da75,), # Signwriting Upper Body Tilting From Hip Joints
|
||||
(0x1da84, 0x1da84,), # Signwriting Location Head Neck
|
||||
(0x1da9b, 0x1da9f,), # Signwriting Fill Modifie..Signwriting Fill Modifie
|
||||
(0x1daa1, 0x1daaf,), # Signwriting Rotation Mod..Signwriting Rotation Mod
|
||||
(0x1e000, 0x1e006,), # Combining Glagolitic Let..Combining Glagolitic Let
|
||||
(0x1e008, 0x1e018,), # Combining Glagolitic Let..Combining Glagolitic Let
|
||||
(0x1e01b, 0x1e021,), # Combining Glagolitic Let..Combining Glagolitic Let
|
||||
(0x1e023, 0x1e024,), # Combining Glagolitic Let..Combining Glagolitic Let
|
||||
(0x1e026, 0x1e02a,), # Combining Glagolitic Let..Combining Glagolitic Let
|
||||
(0x1e08f, 0x1e08f,), # Combining Cyrillic Small Letter Byelorussian-ukr
|
||||
(0x1e130, 0x1e136,), # Nyiakeng Puachue Hmong T..Nyiakeng Puachue Hmong T
|
||||
(0x1e2ae, 0x1e2ae,), # Toto Sign Rising Tone
|
||||
(0x1e2ec, 0x1e2ef,), # Wancho Tone Tup ..Wancho Tone Koini
|
||||
(0x1e4ec, 0x1e4ef,), # Nag Mundari Sign Muhor ..Nag Mundari Sign Sutuh
|
||||
(0x1e5ee, 0x1e5ef,), # Ol Onal Sign Mu ..Ol Onal Sign Ikir
|
||||
(0x1e6e3, 0x1e6e3,), # Tai Yo Sign Ue
|
||||
(0x1e6e6, 0x1e6e6,), # Tai Yo Sign Au
|
||||
(0x1e6ee, 0x1e6ef,), # Tai Yo Sign Ay ..Tai Yo Sign Ang
|
||||
(0x1e6f5, 0x1e6f5,), # Tai Yo Sign Om
|
||||
(0x1e8d0, 0x1e8d6,), # Mende Kikakui Combining ..Mende Kikakui Combining
|
||||
(0x1e944, 0x1e94a,), # Adlam Alif Lengthener ..Adlam Nukta
|
||||
(0xe0000, 0xe0fff,), # (nil)
|
||||
),
|
||||
}
|
||||
656
venv/lib/python3.12/site-packages/wcwidth/textwrap.py
Normal file
656
venv/lib/python3.12/site-packages/wcwidth/textwrap.py
Normal file
@@ -0,0 +1,656 @@
|
||||
"""
|
||||
Sequence-aware text wrapping functions.
|
||||
|
||||
This module provides functions for wrapping text that may contain terminal escape sequences, with
|
||||
proper handling of Unicode grapheme clusters and character display widths.
|
||||
"""
|
||||
from __future__ import annotations
|
||||
|
||||
# std imports
|
||||
import re
|
||||
import secrets
|
||||
import textwrap
|
||||
|
||||
from typing import TYPE_CHECKING, NamedTuple
|
||||
|
||||
# local
|
||||
from .wcwidth import width as _width
|
||||
from .wcwidth import iter_sequences
|
||||
from .grapheme import iter_graphemes
|
||||
from .sgr_state import propagate_sgr as _propagate_sgr
|
||||
from .escape_sequences import ZERO_WIDTH_PATTERN
|
||||
|
||||
if TYPE_CHECKING: # pragma: no cover
|
||||
from typing import Any, Literal
|
||||
|
||||
|
||||
class _HyperlinkState(NamedTuple):
|
||||
"""State for tracking an open OSC 8 hyperlink across line breaks."""
|
||||
|
||||
url: str # hyperlink target URL
|
||||
params: str # id=xxx and other key=value pairs separated by :
|
||||
terminator: str # BEL (\x07) or ST (\x1b\\)
|
||||
|
||||
|
||||
# Hyperlink parsing: captures (params, url, terminator)
|
||||
_HYPERLINK_OPEN_RE = re.compile(r'\x1b]8;([^;]*);([^\x07\x1b]*)(\x07|\x1b\\)')
|
||||
|
||||
|
||||
def _parse_hyperlink_open(seq: str) -> _HyperlinkState | None:
|
||||
"""Parse OSC 8 open sequence, return state or None."""
|
||||
if (m := _HYPERLINK_OPEN_RE.match(seq)):
|
||||
return _HyperlinkState(url=m.group(2), params=m.group(1), terminator=m.group(3))
|
||||
return None
|
||||
|
||||
|
||||
def _make_hyperlink_open(url: str, params: str, terminator: str) -> str:
|
||||
"""Generate OSC 8 open sequence."""
|
||||
return f'\x1b]8;{params};{url}{terminator}'
|
||||
|
||||
|
||||
def _make_hyperlink_close(terminator: str) -> str:
|
||||
"""Generate OSC 8 close sequence."""
|
||||
return f'\x1b]8;;{terminator}'
|
||||
|
||||
|
||||
class SequenceTextWrapper(textwrap.TextWrapper):
|
||||
"""
|
||||
Sequence-aware text wrapper extending :class:`textwrap.TextWrapper`.
|
||||
|
||||
This wrapper properly handles terminal escape sequences and Unicode grapheme clusters when
|
||||
calculating text width for wrapping.
|
||||
|
||||
This implementation is based on the SequenceTextWrapper from the 'blessed' library, with
|
||||
contributions from Avram Lubkin and grayjk.
|
||||
|
||||
The key difference from the blessed implementation is the addition of grapheme cluster support
|
||||
via :func:`~.iter_graphemes`, providing width calculation for ZWJ emoji sequences, VS-16 emojis
|
||||
and variations, regional indicator flags, and combining characters.
|
||||
|
||||
OSC 8 hyperlinks are handled specially: when a hyperlink must span multiple lines, each line
|
||||
receives complete open/close sequences with a shared ``id`` parameter, ensuring terminals
|
||||
treat the fragments as a single hyperlink for hover underlining. If the original hyperlink
|
||||
already has an ``id`` parameter, it is preserved; otherwise, one is generated.
|
||||
"""
|
||||
|
||||
def __init__(self, width: int = 70, *,
|
||||
control_codes: Literal['parse', 'strict', 'ignore'] = 'parse',
|
||||
tabsize: int = 8,
|
||||
ambiguous_width: int = 1,
|
||||
**kwargs: Any) -> None:
|
||||
"""
|
||||
Initialize the wrapper.
|
||||
|
||||
:param width: Maximum line width in display cells.
|
||||
:param control_codes: How to handle control sequences (see :func:`~.width`).
|
||||
:param tabsize: Tab stop width for tab expansion.
|
||||
:param ambiguous_width: Width to use for East Asian Ambiguous (A) characters.
|
||||
:param kwargs: Additional arguments passed to :class:`textwrap.TextWrapper`.
|
||||
"""
|
||||
super().__init__(width=width, **kwargs)
|
||||
self.control_codes = control_codes
|
||||
self.tabsize = tabsize
|
||||
self.ambiguous_width = ambiguous_width
|
||||
|
||||
@staticmethod
|
||||
def _next_hyperlink_id() -> str:
|
||||
"""Generate unique hyperlink id as 8-character hex string."""
|
||||
return secrets.token_hex(4)
|
||||
|
||||
def _width(self, text: str) -> int:
|
||||
"""Measure text width accounting for sequences."""
|
||||
return _width(text, control_codes=self.control_codes, tabsize=self.tabsize,
|
||||
ambiguous_width=self.ambiguous_width)
|
||||
|
||||
def _strip_sequences(self, text: str) -> str:
|
||||
"""Strip all terminal sequences from text."""
|
||||
result = []
|
||||
for segment, is_seq in iter_sequences(text):
|
||||
if not is_seq:
|
||||
result.append(segment)
|
||||
return ''.join(result)
|
||||
|
||||
def _extract_sequences(self, text: str) -> str:
|
||||
"""Extract only terminal sequences from text."""
|
||||
result = []
|
||||
for segment, is_seq in iter_sequences(text):
|
||||
if is_seq:
|
||||
result.append(segment)
|
||||
return ''.join(result)
|
||||
|
||||
def _split(self, text: str) -> list[str]: # pylint: disable=too-many-locals
|
||||
r"""
|
||||
Sequence-aware variant of :meth:`textwrap.TextWrapper._split`.
|
||||
|
||||
This method ensures that terminal escape sequences don't interfere with the text splitting
|
||||
logic, particularly for hyphen-based word breaking. It builds a position mapping from
|
||||
stripped text to original text, calls the parent's _split on stripped text, then maps chunks
|
||||
back.
|
||||
|
||||
OSC hyperlink sequences are treated as word boundaries::
|
||||
|
||||
>>> wrap('foo \x1b]8;;https://example.com\x07link\x1b]8;;\x07 bar', 6)
|
||||
['foo', '\x1b]8;;https://example.com\x07link\x1b]8;;\x07', 'bar']
|
||||
|
||||
Both BEL (``\x07``) and ST (``\x1b\\``) terminators are supported.
|
||||
"""
|
||||
# pylint: disable=too-many-locals,too-many-branches
|
||||
# Build a mapping from stripped text positions to original text positions.
|
||||
#
|
||||
# Track where each character ENDS so that sequences between characters
|
||||
# attach to the following text (not preceding text). This ensures sequences
|
||||
# aren't lost when whitespace is dropped.
|
||||
#
|
||||
# char_end[i] = position in original text right after the i-th stripped char
|
||||
char_end: list[int] = []
|
||||
stripped_text = ''
|
||||
original_pos = 0
|
||||
prev_was_hyperlink_close = False
|
||||
|
||||
for segment, is_seq in iter_sequences(text):
|
||||
if not is_seq:
|
||||
# Conditionally insert space after hyperlink close to force word boundary
|
||||
if prev_was_hyperlink_close and segment and not segment[0].isspace():
|
||||
stripped_text += ' '
|
||||
char_end.append(original_pos)
|
||||
for char in segment:
|
||||
original_pos += 1
|
||||
char_end.append(original_pos)
|
||||
stripped_text += char
|
||||
prev_was_hyperlink_close = False
|
||||
else:
|
||||
is_hyperlink_close = segment.startswith(('\x1b]8;;\x1b\\', '\x1b]8;;\x07'))
|
||||
|
||||
# Conditionally insert space before OSC sequences to artificially create word
|
||||
# boundary, but *not* before hyperlink close sequences, to ensure hyperlink is
|
||||
# terminated on the same line.
|
||||
if (segment.startswith('\x1b]') and stripped_text and not
|
||||
stripped_text[-1].isspace()):
|
||||
if not is_hyperlink_close:
|
||||
stripped_text += ' '
|
||||
char_end.append(original_pos)
|
||||
|
||||
# Escape sequences advance position but don't add to stripped text
|
||||
original_pos += len(segment)
|
||||
prev_was_hyperlink_close = is_hyperlink_close
|
||||
|
||||
# Add sentinel for final position
|
||||
char_end.append(original_pos)
|
||||
|
||||
# Use parent's _split on the stripped text
|
||||
# pylint: disable-next=protected-access
|
||||
stripped_chunks = textwrap.TextWrapper._split(self, stripped_text)
|
||||
|
||||
# Handle text that contains only sequences (no visible characters).
|
||||
# Return the sequences as a single chunk to preserve them.
|
||||
if not stripped_chunks and text:
|
||||
return [text]
|
||||
|
||||
# Map the chunks back to the original text with sequences
|
||||
result: list[str] = []
|
||||
stripped_pos = 0
|
||||
num_chunks = len(stripped_chunks)
|
||||
|
||||
for idx, chunk in enumerate(stripped_chunks):
|
||||
chunk_len = len(chunk)
|
||||
|
||||
# Start is where previous character ended (or 0 for first chunk)
|
||||
start_orig = 0 if stripped_pos == 0 else char_end[stripped_pos - 1]
|
||||
|
||||
# End is where next character starts. For last chunk, use sentinel
|
||||
# to include any trailing sequences.
|
||||
if idx == num_chunks - 1:
|
||||
end_orig = char_end[-1] # sentinel includes trailing sequences
|
||||
else:
|
||||
end_orig = char_end[stripped_pos + chunk_len - 1]
|
||||
|
||||
# Extract the corresponding portion from the original text
|
||||
# Skip empty chunks (from virtual spaces inserted at OSC boundaries)
|
||||
if start_orig != end_orig:
|
||||
result.append(text[start_orig:end_orig])
|
||||
stripped_pos += chunk_len
|
||||
|
||||
return result
|
||||
|
||||
def _wrap_chunks(self, chunks: list[str]) -> list[str]: # pylint: disable=too-many-branches
|
||||
"""
|
||||
Wrap chunks into lines using sequence-aware width.
|
||||
|
||||
Override TextWrapper._wrap_chunks to use _width instead of len. Follows stdlib's algorithm:
|
||||
greedily fill lines, handle long words. Also handle OSC hyperlink processing. When
|
||||
hyperlinks span multiple lines, each line gets complete open/close sequences with matching
|
||||
id parameters for hover underlining continuity per OSC 8 spec.
|
||||
"""
|
||||
# pylint: disable=too-many-branches,too-many-statements,too-complex,too-many-locals
|
||||
# pylint: disable=too-many-nested-blocks
|
||||
# the hyperlink code in particular really pushes the complexity rating of this method.
|
||||
# preferring to keep it "all in one method" because of so much local state and manipulation.
|
||||
if not chunks:
|
||||
return []
|
||||
|
||||
if self.max_lines is not None:
|
||||
if self.max_lines > 1:
|
||||
indent = self.subsequent_indent
|
||||
else:
|
||||
indent = self.initial_indent
|
||||
if (self._width(indent)
|
||||
+ self._width(self.placeholder.lstrip())
|
||||
> self.width):
|
||||
raise ValueError("placeholder too large for max width")
|
||||
|
||||
lines: list[str] = []
|
||||
is_first_line = True
|
||||
|
||||
hyperlink_state: _HyperlinkState | None = None
|
||||
# Track the id we're using for the current hyperlink continuation
|
||||
current_hyperlink_id: str | None = None
|
||||
|
||||
# Arrange in reverse order so items can be efficiently popped
|
||||
chunks = list(reversed(chunks))
|
||||
|
||||
while chunks:
|
||||
current_line: list[str] = []
|
||||
current_width = 0
|
||||
|
||||
# Get the indent and available width for current line
|
||||
indent = self.initial_indent if is_first_line else self.subsequent_indent
|
||||
line_width = self.width - self._width(indent)
|
||||
|
||||
# If continuing a hyperlink from previous line, prepend open sequence
|
||||
if hyperlink_state is not None:
|
||||
open_seq = _make_hyperlink_open(
|
||||
hyperlink_state.url, hyperlink_state.params, hyperlink_state.terminator)
|
||||
chunks[-1] = open_seq + chunks[-1]
|
||||
|
||||
# Drop leading whitespace (except at very start)
|
||||
# When dropping, transfer any sequences to the next chunk.
|
||||
# Only drop if there's actual whitespace text, not if it's only sequences.
|
||||
stripped = self._strip_sequences(chunks[-1])
|
||||
if self.drop_whitespace and lines and stripped and not stripped.strip():
|
||||
sequences = self._extract_sequences(chunks[-1])
|
||||
del chunks[-1]
|
||||
if sequences and chunks:
|
||||
chunks[-1] = sequences + chunks[-1]
|
||||
|
||||
# Greedily add chunks that fit
|
||||
while chunks:
|
||||
chunk = chunks[-1]
|
||||
chunk_width = self._width(chunk)
|
||||
|
||||
if current_width + chunk_width <= line_width:
|
||||
current_line.append(chunks.pop())
|
||||
current_width += chunk_width
|
||||
else:
|
||||
break
|
||||
|
||||
# Handle chunk that's too long for any line
|
||||
if chunks and self._width(chunks[-1]) > line_width:
|
||||
self._handle_long_word(
|
||||
chunks, current_line, current_width, line_width
|
||||
)
|
||||
current_width = self._width(''.join(current_line))
|
||||
# Remove any empty chunks left by _handle_long_word
|
||||
while chunks and not chunks[-1]:
|
||||
del chunks[-1]
|
||||
|
||||
# Drop trailing whitespace
|
||||
# When dropping, transfer any sequences to the previous chunk.
|
||||
# Only drop if there's actual whitespace text, not if it's only sequences.
|
||||
stripped_last = self._strip_sequences(current_line[-1]) if current_line else ''
|
||||
if (self.drop_whitespace and current_line and
|
||||
stripped_last and not stripped_last.strip()):
|
||||
sequences = self._extract_sequences(current_line[-1])
|
||||
current_width -= self._width(current_line[-1])
|
||||
del current_line[-1]
|
||||
if sequences and current_line:
|
||||
current_line[-1] = current_line[-1] + sequences
|
||||
|
||||
if current_line:
|
||||
# Check whether this is a normal append or max_lines
|
||||
# truncation. Matches stdlib textwrap precedence:
|
||||
# normal if max_lines not set, not yet reached, or no
|
||||
# remaining visible content that would need truncation.
|
||||
no_more_content = (
|
||||
not chunks or
|
||||
self.drop_whitespace and
|
||||
len(chunks) == 1 and
|
||||
not self._strip_sequences(chunks[0]).strip()
|
||||
)
|
||||
if (self.max_lines is None or
|
||||
len(lines) + 1 < self.max_lines or
|
||||
no_more_content
|
||||
and current_width <= line_width):
|
||||
line_content = ''.join(current_line)
|
||||
|
||||
# Track hyperlink state through this line's content
|
||||
new_state = self._track_hyperlink_state(line_content, hyperlink_state)
|
||||
|
||||
# If we end inside a hyperlink, append close sequence
|
||||
if new_state is not None:
|
||||
# Ensure we have an id for continuation
|
||||
if current_hyperlink_id is None:
|
||||
if 'id=' in new_state.params:
|
||||
current_hyperlink_id = new_state.params
|
||||
elif new_state.params:
|
||||
# Prepend id to existing params (per OSC 8 spec, params can have
|
||||
# multiple key=value pairs separated by :)
|
||||
current_hyperlink_id = (
|
||||
f'id={self._next_hyperlink_id()}:{new_state.params}')
|
||||
else:
|
||||
current_hyperlink_id = f'id={self._next_hyperlink_id()}'
|
||||
line_content += _make_hyperlink_close(new_state.terminator)
|
||||
|
||||
# Also need to inject the id into the opening
|
||||
# sequence if it didn't have one
|
||||
if 'id=' not in new_state.params:
|
||||
# Find and replace the original open sequence with one that has id
|
||||
old_open = _make_hyperlink_open(
|
||||
new_state.url, new_state.params, new_state.terminator)
|
||||
new_open = _make_hyperlink_open(
|
||||
new_state.url, current_hyperlink_id, new_state.terminator)
|
||||
line_content = line_content.replace(old_open, new_open, 1)
|
||||
|
||||
# Update state for next line, using computed id
|
||||
hyperlink_state = _HyperlinkState(
|
||||
new_state.url, current_hyperlink_id, new_state.terminator)
|
||||
else:
|
||||
hyperlink_state = None
|
||||
current_hyperlink_id = None # Reset id when hyperlink closes
|
||||
|
||||
# Strip trailing whitespace when drop_whitespace is enabled
|
||||
# (matches CPython #140627 fix behavior)
|
||||
if self.drop_whitespace:
|
||||
line_content = line_content.rstrip()
|
||||
lines.append(indent + line_content)
|
||||
is_first_line = False
|
||||
else:
|
||||
# max_lines reached with remaining content —
|
||||
# pop chunks until placeholder fits, then break.
|
||||
placeholder_w = self._width(self.placeholder)
|
||||
while current_line:
|
||||
last_text = self._strip_sequences(current_line[-1])
|
||||
if (last_text.strip()
|
||||
and current_width + placeholder_w <= line_width):
|
||||
line_content = ''.join(current_line)
|
||||
new_state = self._track_hyperlink_state(
|
||||
line_content, hyperlink_state)
|
||||
if new_state is not None:
|
||||
line_content += _make_hyperlink_close(
|
||||
new_state.terminator)
|
||||
lines.append(indent + line_content + self.placeholder)
|
||||
break
|
||||
current_width -= self._width(current_line[-1])
|
||||
del current_line[-1]
|
||||
else:
|
||||
if lines:
|
||||
prev_line = self._rstrip_visible(lines[-1])
|
||||
if (self._width(prev_line) + placeholder_w
|
||||
<= self.width):
|
||||
lines[-1] = prev_line + self.placeholder
|
||||
break
|
||||
lines.append(indent + self.placeholder.lstrip())
|
||||
break
|
||||
|
||||
return lines
|
||||
|
||||
def _track_hyperlink_state(
|
||||
self, text: str,
|
||||
state: _HyperlinkState | None) -> _HyperlinkState | None:
|
||||
"""
|
||||
Track hyperlink state through text.
|
||||
|
||||
:param text: Text to scan for hyperlink sequences.
|
||||
:param state: Current state or None if outside hyperlink.
|
||||
:returns: Updated state after processing text.
|
||||
"""
|
||||
for segment, is_seq in iter_sequences(text):
|
||||
if is_seq:
|
||||
parsed_link = _parse_hyperlink_open(segment)
|
||||
if parsed_link is not None and parsed_link.url: # has URL = open
|
||||
state = parsed_link
|
||||
elif segment.startswith(('\x1b]8;;\x1b\\', '\x1b]8;;\x07')): # close
|
||||
state = None
|
||||
return state
|
||||
|
||||
def _handle_long_word(self, reversed_chunks: list[str],
|
||||
cur_line: list[str], cur_len: int,
|
||||
width: int) -> None:
|
||||
"""
|
||||
Sequence-aware :meth:`textwrap.TextWrapper._handle_long_word`.
|
||||
|
||||
This method ensures that word boundaries are not broken mid-sequence, and respects grapheme
|
||||
cluster boundaries when breaking long words.
|
||||
"""
|
||||
if width < 1:
|
||||
space_left = 1
|
||||
else:
|
||||
space_left = width - cur_len
|
||||
|
||||
chunk = reversed_chunks[-1]
|
||||
|
||||
if self.break_long_words:
|
||||
break_at_hyphen = False
|
||||
hyphen_end = 0
|
||||
|
||||
# Handle break_on_hyphens: find last hyphen within space_left
|
||||
if self.break_on_hyphens:
|
||||
# Strip sequences to find hyphen in logical text
|
||||
stripped = self._strip_sequences(chunk)
|
||||
if len(stripped) > space_left:
|
||||
# Find last hyphen in the portion that fits
|
||||
hyphen_pos = stripped.rfind('-', 0, space_left)
|
||||
if hyphen_pos > 0 and any(c != '-' for c in stripped[:hyphen_pos]):
|
||||
# Map back to original position including sequences
|
||||
hyphen_end = self._map_stripped_pos_to_original(chunk, hyphen_pos + 1)
|
||||
break_at_hyphen = True
|
||||
|
||||
# Break at grapheme boundaries to avoid splitting multi-codepoint characters
|
||||
if break_at_hyphen:
|
||||
actual_end = hyphen_end
|
||||
else:
|
||||
actual_end = self._find_break_position(chunk, space_left)
|
||||
# If no progress possible (e.g., wide char exceeds line width),
|
||||
# force at least one grapheme to avoid infinite loop.
|
||||
# Only force when cur_line is empty; if line has content,
|
||||
# appending nothing is safe and the line will be committed.
|
||||
if actual_end == 0 and not cur_line:
|
||||
actual_end = self._find_first_grapheme_end(chunk)
|
||||
cur_line.append(chunk[:actual_end])
|
||||
reversed_chunks[-1] = chunk[actual_end:]
|
||||
|
||||
elif not cur_line:
|
||||
cur_line.append(reversed_chunks.pop())
|
||||
|
||||
def _map_stripped_pos_to_original(self, text: str, stripped_pos: int) -> int:
|
||||
"""Map a position in stripped text back to original text position."""
|
||||
stripped_idx = 0
|
||||
original_idx = 0
|
||||
|
||||
for segment, is_seq in iter_sequences(text):
|
||||
if is_seq:
|
||||
original_idx += len(segment)
|
||||
elif stripped_idx + len(segment) > stripped_pos:
|
||||
# Position is within this segment
|
||||
return original_idx + (stripped_pos - stripped_idx)
|
||||
else:
|
||||
stripped_idx += len(segment)
|
||||
original_idx += len(segment)
|
||||
|
||||
# Caller guarantees stripped_pos < total stripped chars, so we always
|
||||
# return from within the loop. This line satisfies the type checker.
|
||||
return original_idx # pragma: no cover
|
||||
|
||||
def _find_break_position(self, text: str, max_width: int) -> int:
|
||||
"""Find string index in text that fits within max_width cells."""
|
||||
idx = 0
|
||||
width_so_far = 0
|
||||
|
||||
while idx < len(text):
|
||||
char = text[idx]
|
||||
|
||||
# Skip escape sequences (they don't add width)
|
||||
if char == '\x1b':
|
||||
match = ZERO_WIDTH_PATTERN.match(text, idx)
|
||||
if match:
|
||||
idx = match.end()
|
||||
continue
|
||||
|
||||
# Get grapheme (use start= to avoid slice allocation)
|
||||
grapheme = next(iter_graphemes(text, start=idx))
|
||||
|
||||
grapheme_width = self._width(grapheme)
|
||||
if width_so_far + grapheme_width > max_width:
|
||||
return idx # Found break point
|
||||
|
||||
width_so_far += grapheme_width
|
||||
idx += len(grapheme)
|
||||
|
||||
# Caller guarantees chunk_width > max_width, so a grapheme always
|
||||
# exceeds and we return from within the loop. Type checker requires this.
|
||||
return idx # pragma: no cover
|
||||
|
||||
def _find_first_grapheme_end(self, text: str) -> int:
|
||||
"""Find the end position of the first grapheme."""
|
||||
return len(next(iter_graphemes(text)))
|
||||
|
||||
def _rstrip_visible(self, text: str) -> str:
|
||||
"""Strip trailing visible whitespace, preserving trailing sequences."""
|
||||
segments = list(iter_sequences(text))
|
||||
last_vis = -1
|
||||
for i, (segment, is_seq) in enumerate(segments):
|
||||
if not is_seq and segment.rstrip():
|
||||
last_vis = i
|
||||
if last_vis == -1:
|
||||
return ''
|
||||
result = []
|
||||
for i, (segment, is_seq) in enumerate(segments):
|
||||
if i < last_vis:
|
||||
result.append(segment)
|
||||
elif i == last_vis:
|
||||
result.append(segment.rstrip())
|
||||
elif is_seq:
|
||||
result.append(segment)
|
||||
return ''.join(result)
|
||||
|
||||
|
||||
def wrap(text: str, width: int = 70, *,
|
||||
control_codes: Literal['parse', 'strict', 'ignore'] = 'parse',
|
||||
tabsize: int = 8,
|
||||
expand_tabs: bool = True,
|
||||
replace_whitespace: bool = True,
|
||||
ambiguous_width: int = 1,
|
||||
initial_indent: str = '',
|
||||
subsequent_indent: str = '',
|
||||
fix_sentence_endings: bool = False,
|
||||
break_long_words: bool = True,
|
||||
break_on_hyphens: bool = True,
|
||||
drop_whitespace: bool = True,
|
||||
max_lines: int | None = None,
|
||||
placeholder: str = ' [...]',
|
||||
propagate_sgr: bool = True) -> list[str]:
|
||||
r"""
|
||||
Wrap text to fit within given width, returning a list of wrapped lines.
|
||||
|
||||
Like :func:`textwrap.wrap`, but measures width in display cells rather than
|
||||
characters, correctly handling wide characters, combining marks, and terminal
|
||||
escape sequences.
|
||||
|
||||
:param text: Text to wrap, may contain terminal sequences.
|
||||
:param width: Maximum line width in display cells.
|
||||
:param control_codes: How to handle terminal sequences (see :func:`~.width`).
|
||||
:param tabsize: Tab stop width for tab expansion.
|
||||
:param expand_tabs: If True (default), tab characters are expanded
|
||||
to spaces using ``tabsize``.
|
||||
:param replace_whitespace: If True (default), each whitespace character
|
||||
is replaced with a single space after tab expansion. When False,
|
||||
control whitespace like ``\n`` has zero display width (unlike
|
||||
:func:`textwrap.wrap` which counts ``len()``), so wrap points
|
||||
may differ from stdlib for non-space whitespace characters.
|
||||
:param ambiguous_width: Width to use for East Asian Ambiguous (A)
|
||||
characters. Default is ``1`` (narrow). Set to ``2`` for CJK contexts.
|
||||
:param initial_indent: String prepended to first line.
|
||||
:param subsequent_indent: String prepended to subsequent lines.
|
||||
:param fix_sentence_endings: If True, ensure sentences are always
|
||||
separated by exactly two spaces.
|
||||
:param break_long_words: If True, break words longer than width.
|
||||
:param break_on_hyphens: If True, allow breaking at hyphens.
|
||||
:param drop_whitespace: If True (default), whitespace at the beginning
|
||||
and end of each line (after wrapping but before indenting) is dropped.
|
||||
Set to False to preserve whitespace.
|
||||
:param max_lines: If set, output contains at most this many lines, with
|
||||
``placeholder`` appended to the last line if the text was truncated.
|
||||
:param placeholder: String appended to the last line when text is
|
||||
truncated by ``max_lines``. Default is ``' [...]'``.
|
||||
:param propagate_sgr: If True (default), SGR (terminal styling) sequences
|
||||
are propagated across wrapped lines. Each line ends with a reset
|
||||
sequence and the next line begins with the active style restored.
|
||||
:returns: List of wrapped lines without trailing newlines.
|
||||
|
||||
SGR (terminal styling) sequences are propagated across wrapped lines
|
||||
by default. Each line ends with a reset sequence and the next line
|
||||
begins with the active style restored::
|
||||
|
||||
>>> wrap('\x1b[1;34mHello world\x1b[0m', width=6)
|
||||
['\x1b[1;34mHello\x1b[0m', '\x1b[1;34mworld\x1b[0m']
|
||||
|
||||
Set ``propagate_sgr=False`` to disable this behavior.
|
||||
|
||||
Like :func:`textwrap.wrap`, newlines in the input text are treated as
|
||||
whitespace and collapsed. To preserve paragraph breaks, wrap each
|
||||
paragraph separately::
|
||||
|
||||
>>> text = 'First line.\nSecond line.'
|
||||
>>> wrap(text, 40) # newline collapsed to space
|
||||
['First line. Second line.']
|
||||
>>> [line for para in text.split('\n')
|
||||
... for line in (wrap(para, 40) if para else [''])]
|
||||
['First line.', 'Second line.']
|
||||
|
||||
.. seealso::
|
||||
|
||||
:func:`textwrap.wrap`, :class:`textwrap.TextWrapper`
|
||||
Standard library text wrapping (character-based).
|
||||
|
||||
:class:`.SequenceTextWrapper`
|
||||
Class interface for advanced wrapping options.
|
||||
|
||||
.. versionadded:: 0.3.0
|
||||
|
||||
.. versionchanged:: 0.5.0
|
||||
Added ``propagate_sgr`` parameter (default True).
|
||||
|
||||
.. versionchanged:: 0.6.0
|
||||
Added ``expand_tabs``, ``replace_whitespace``, ``fix_sentence_endings``,
|
||||
``drop_whitespace``, ``max_lines``, and ``placeholder`` parameters.
|
||||
|
||||
Example::
|
||||
|
||||
>>> from wcwidth import wrap
|
||||
>>> wrap('hello world', 5)
|
||||
['hello', 'world']
|
||||
>>> wrap('中文字符', 4) # CJK characters (2 cells each)
|
||||
['中文', '字符']
|
||||
"""
|
||||
# pylint: disable=too-many-arguments,too-many-locals
|
||||
wrapper = SequenceTextWrapper(
|
||||
width=width,
|
||||
control_codes=control_codes,
|
||||
tabsize=tabsize,
|
||||
expand_tabs=expand_tabs,
|
||||
replace_whitespace=replace_whitespace,
|
||||
ambiguous_width=ambiguous_width,
|
||||
initial_indent=initial_indent,
|
||||
subsequent_indent=subsequent_indent,
|
||||
fix_sentence_endings=fix_sentence_endings,
|
||||
break_long_words=break_long_words,
|
||||
break_on_hyphens=break_on_hyphens,
|
||||
drop_whitespace=drop_whitespace,
|
||||
max_lines=max_lines,
|
||||
placeholder=placeholder,
|
||||
)
|
||||
lines = wrapper.wrap(text)
|
||||
|
||||
if propagate_sgr:
|
||||
lines = _propagate_sgr(lines)
|
||||
|
||||
return lines
|
||||
@@ -0,0 +1,21 @@
|
||||
"""
|
||||
Exports function list_versions() for unicode version level support.
|
||||
|
||||
This code generated by wcwidth/bin/update-tables.py on 2026-01-27 00:41:01 UTC.
|
||||
"""
|
||||
|
||||
from __future__ import annotations
|
||||
|
||||
|
||||
def list_versions() -> tuple[str, ...]:
|
||||
"""
|
||||
Return Unicode version levels supported by this module release.
|
||||
|
||||
.. versionchanged:: 0.5.0
|
||||
Now returns a single-element tuple containing only the latest version.
|
||||
|
||||
:returns: Supported Unicode version numbers in ascending sorted order.
|
||||
"""
|
||||
return (
|
||||
"17.0.0",
|
||||
)
|
||||
1030
venv/lib/python3.12/site-packages/wcwidth/wcwidth.py
Normal file
1030
venv/lib/python3.12/site-packages/wcwidth/wcwidth.py
Normal file
File diff suppressed because it is too large
Load Diff
Reference in New Issue
Block a user