xander/main
1
0
Fork 0
mirror of https://github.com/googlefonts/noto-emoji.git synced 2025-07-09 13:55:31 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

Add support for "narrow" python to emoji_builder.py

Browse source 
The code currently only works with wide builds since it does not take
UTF-16 surrogate pairs into account.
This commit is contained in:
Andrew Clemons 2017-03-09 21:48:18 +13:00
parent 701acb4282
commit 3ba53cba1d
1 changed files with 37 additions and 4 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

41
third_party/color_emoji/emoji_builder.py vendored
View file

@ -25,10 +25,36 @@ from os import path
from nototools import font_data from nototools import font_data
def myunichr(cp):
if sys.maxunicode < 0x10FFFF and cp > 0xFFFF:
return ("\\U" + hex(cp)[2:].zfill(8)).decode("unicode-escape")
return unichr(cp)
def myord(high, low):
return (ord(high) - 0xD800) * 0x400 + (ord(low) - 0xDC00) + 0x10000
def begins_with_surrogate(string):
return sys.maxunicode < 0x10FFFF and len(string) > 1 and (0xD800 <= ord(string[0]) <= 0xDBFF) and (0xDC00 <= ord(string[1]) <= 0xDFFF)
def get_glyph_name_from_gsub (string, font, cmap_dict): def get_glyph_name_from_gsub (string, font, cmap_dict):
ligatures = font['GSUB'].table.LookupList.Lookup[0].SubTable[0].ligatures ligatures = font['GSUB'].table.LookupList.Lookup[0].SubTable[0].ligatures
first_glyph = cmap_dict[ord (string[0])]
rest_of_glyphs = [cmap_dict[ord (ch)] for ch in string[1:]] if begins_with_surrogate(string):
first_glyph = cmap_dict[myord(string[0], string[1])]
string = string[2:]
else:
first_glyph = cmap_dict[ord (string[0])]
string = string[1:]
rest_of_glyphs = []
while (len(string) > 0):
if begins_with_surrogate(string):
rest_of_glyphs.append(cmap_dict[myord(string[0], string[1])])
string = string[2:]
else:
rest_of_glyphs.append(cmap_dict[ord (string[0])])
string = string[1:]
for ligature in ligatures[first_glyph]: for ligature in ligatures[first_glyph]:
if ligature.Component == rest_of_glyphs: if ligature.Component == rest_of_glyphs:
return ligature.LigGlyph return ligature.LigGlyph
@ -462,13 +488,13 @@ By default they are dropped.
if "_" in codes: if "_" in codes:
pieces = codes.split ("_") pieces = codes.split ("_")
cps = [int(code, 16) for code in pieces] cps = [int(code, 16) for code in pieces]
uchars = "".join ([unichr(cp) for cp in cps if not is_vs(cp)]) uchars = "".join ([myunichr(cp) for cp in cps if not is_vs(cp)])
else: else:
cp = int(codes, 16) cp = int(codes, 16)
if is_vs(cp): if is_vs(cp):
print "ignoring unexpected vs input %04x" % cp print "ignoring unexpected vs input %04x" % cp
continue continue
uchars = unichr(cp) uchars = myunichr(cp)
img_files[uchars] = img_file img_files[uchars] = img_file
if not img_files: if not img_files:
raise Exception ("No image files found in '%s'." % glb) raise Exception ("No image files found in '%s'." % glb)
@ -483,6 +509,13 @@ By default they are dropped.
except: except:
print "no cmap entry for %x" % ord(uchars) print "no cmap entry for %x" % ord(uchars)
raise ValueError("%x" % ord(uchars)) raise ValueError("%x" % ord(uchars))
elif len (uchars) == 2 and begins_with_surrogate(uchars):
cp = myord(uchars[0], uchars[1])
try:
glyph_name = unicode_cmap.cmap[cp]
except:
print "no cmap entry for %x" % cp
raise ValueError("%x" % ord(uchars))
else: else:
glyph_name = get_glyph_name_from_gsub (uchars, font, unicode_cmap.cmap) glyph_name = get_glyph_name_from_gsub (uchars, font, unicode_cmap.cmap)
glyph_id = font.getGlyphID (glyph_name) glyph_id = font.getGlyphID (glyph_name)