Garmelon/bowl
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions

Filter out control characters

Browse source
This commit is contained in:
Joscha 2019-06-12 16:12:53 +00:00
parent 8b0740778c
commit 50e5b594ad
1 changed files with 11 additions and 6 deletions
Download patch file Download diff file Expand all files Collapse all files

17
cheuph/euphoria/euph_renderer.py
View file

@ -1,4 +1,5 @@
import unicodedata import unicodedata
from typing import Set
from ..cursor_rendering import CursorRenderer from ..cursor_rendering import CursorRenderer
from ..element import Message, RenderedMessage from ..element import Message, RenderedMessage
@ -22,6 +23,7 @@ class EuphRenderer(CursorRenderer):
def __init__(self, def __init__(self,
nick: str, nick: str,
replace_wide_unicode: bool = True, replace_wide_unicode: bool = True,
replace_character_categories: Set[str] = {"Cf"},
unicode_placeholder: str = "<EFBFBD>", unicode_placeholder: str = "<EFBFBD>",
# Meta settings # Meta settings
show_year: bool = False, show_year: bool = False,
@ -45,6 +47,7 @@ class EuphRenderer(CursorRenderer):
self.nick = nick self.nick = nick
self._replace_wide_unicode = replace_wide_unicode self._replace_wide_unicode = replace_wide_unicode
self._replace_character_categories = replace_character_categories
self._unicode_placeholder = unicode_placeholder self._unicode_placeholder = unicode_placeholder
# Meta settings # Meta settings
self._show_year = show_year self._show_year = show_year
@ -77,16 +80,18 @@ class EuphRenderer(CursorRenderer):
return width return width
def _filter_unicode(self, text: str) -> str: def _is_wide(self, char: str) -> bool:
if not self._replace_wide_unicode: return unicodedata.east_asian_width(char) not in self.NORMAL_WIDTH
return text
def _filter_unicode(self, text: str) -> str:
new_chars = [] new_chars = []
for char in text: for char in text:
if unicodedata.east_asian_width(char) in self.NORMAL_WIDTH: if self._replace_wide_unicode and self._is_wide(char):
new_chars.append(char)
else:
new_chars.append(self._unicode_placeholder) new_chars.append(self._unicode_placeholder)
elif unicodedata.category(char) in self._replace_character_categories:
pass
else:
new_chars.append(char)
return "".join(new_chars) return "".join(new_chars)