Python fonttools:检查字体是否支持多代码点表情符号
Python fonttools: Check if font supports multi codepoint emoji
我正在尝试检查 Python 3.x 中的字体是否具有多代码点表情符号的字形,例如“♂️”、“”或“” ]
对于像“”或“”这样的单一代码点表情符号,我可以通过以下代码使用 Python fonttols
:
来验证它们的支持
from fontTools.ttLib import TTFont
def __isEmojiSupportedByFont(emoji: str) -> bool:
font = TTFont(r"C:\Windows\Fonts\seguiemj.ttf")
emojiCodepoint = ord(str) # Only works for single codepoint emoji
for table in font['cmap'].tables:
for char_code, glyph_name in table.cmap.items():
if char_code == emojiCodepoint:
return True
return False
由于 cmp
只有单个代码点表情符号,我该如何为多代码点表情符号执行此操作?
要检查多代码点表情符号,我必须 "query" GSUB
Lookup List。
检查 python 中的字体是否支持表情符号的更简单方法是使用 HarfBuzz or more exact harfpy。
我想到的解决办法是:
from uharfbuzz import Face, Font, Buffer, ot_font_set_funcs, shape
def __isEmojiSupportedByFont(self, emoji: str) -> bool:
# Load font:
with open(r"C:\Windows\Fonts\seguiemj.ttf", 'rb') as fontfile:
self.fontdata = fontfile.read()
# Load font (has to be done for call):
face = Face(self.fontdata)
font = Font(face)
upem = face.upem
font.scale = (upem, upem)
ot_font_set_funcs(font)
# Create text buffer:
buf = Buffer()
buf.add_str(emoji)
buf.guess_segment_properties()
# Shape text:
features = {"kern": True, "liga": True}
shape(font, buf, features)
# Remove all variant selectors:
while len(infos) > 0 and infos[-1].codepoint == 3:
infos = infos[:-1]
# Filter empty:
if len(infos) <= 0:
return False
# Remove uncombined, ending with skin tone like "":
lastCp = infos[-1].codepoint
if lastCp == 1076 or lastCp == 1079 or lastCp == 1082 or lastCp == 1085 or lastCp == 1088:
return False
# If there is a code point 0 or 3 => Emoji not fully supported by font:
return all(info.codepoint != 0 and info.codepoint != 3 for info in infos)
感谢khaledhosny and justvanrossum over on GitHub/fonttols!
我正在尝试检查 Python 3.x 中的字体是否具有多代码点表情符号的字形,例如“♂️”、“”或“” ]
对于像“”或“”这样的单一代码点表情符号,我可以通过以下代码使用 Python fonttols
:
from fontTools.ttLib import TTFont
def __isEmojiSupportedByFont(emoji: str) -> bool:
font = TTFont(r"C:\Windows\Fonts\seguiemj.ttf")
emojiCodepoint = ord(str) # Only works for single codepoint emoji
for table in font['cmap'].tables:
for char_code, glyph_name in table.cmap.items():
if char_code == emojiCodepoint:
return True
return False
由于 cmp
只有单个代码点表情符号,我该如何为多代码点表情符号执行此操作?
要检查多代码点表情符号,我必须 "query" GSUB
Lookup List。
检查 python 中的字体是否支持表情符号的更简单方法是使用 HarfBuzz or more exact harfpy。
我想到的解决办法是:
from uharfbuzz import Face, Font, Buffer, ot_font_set_funcs, shape
def __isEmojiSupportedByFont(self, emoji: str) -> bool:
# Load font:
with open(r"C:\Windows\Fonts\seguiemj.ttf", 'rb') as fontfile:
self.fontdata = fontfile.read()
# Load font (has to be done for call):
face = Face(self.fontdata)
font = Font(face)
upem = face.upem
font.scale = (upem, upem)
ot_font_set_funcs(font)
# Create text buffer:
buf = Buffer()
buf.add_str(emoji)
buf.guess_segment_properties()
# Shape text:
features = {"kern": True, "liga": True}
shape(font, buf, features)
# Remove all variant selectors:
while len(infos) > 0 and infos[-1].codepoint == 3:
infos = infos[:-1]
# Filter empty:
if len(infos) <= 0:
return False
# Remove uncombined, ending with skin tone like "":
lastCp = infos[-1].codepoint
if lastCp == 1076 or lastCp == 1079 or lastCp == 1082 or lastCp == 1085 or lastCp == 1088:
return False
# If there is a code point 0 or 3 => Emoji not fully supported by font:
return all(info.codepoint != 0 and info.codepoint != 3 for info in infos)
感谢khaledhosny and justvanrossum over on GitHub/fonttols!