def __getcharmaps__():
f = open(get_from_cache('AdobeSourceSansDevanagariGlyphOrderAndAliasDB.txt', URL), 'r')
glyphnames = []
for line in f:
glyphnames += [re.sub(r'\s+', ' ', line).split()]
return [type('Charmap', (object,),
dict(glyphnames=glyphnames,
common_name='Unencoded Glyphs',
short_name='unencoded-glyphs',
native_name=''))]
def __getcharmaps__():
content = open(get_from_cache('Blocks.txt', UNIDATA_URL), 'r').read()
regex = re.compile('^([\da-f]+)..([\da-f]+);\s*(.*)$', re.I | re.U)
for line in content.split('\n'):
m = regex.match(line.strip())
# 100000..10FFFF; Supplementary Private Use Area-B
if not m:
continue
glyphlist = '0x%s-0x%s' % (m.group(1), m.group(2))
unicodes = Extension.convert_to_list_of_unicodes(glyphlist)
yield type('Charmap', (object,),
dict(glyphs=unicodes,
common_name=u'Unicode Block %s' % m.group(3),
native_name=''))
def __getcharsets__():
f = open(get_from_cache("AdobeSourceSansDevanagariGlyphOrderAndAliasDB.txt", URL), "r")
glyphnames = []
for line in f:
glyphnames += [re.sub(r"\s+", " ", line).split()]
return [
type(
"Charset",
(object,),
dict(
glyphnames=glyphnames, common_name="Unencoded Glyphs", short_name="unencoded-glyphs", native_name=""
),
)
]
def __getcharsets__():
f = open(
get_from_cache('AdobeSourceSansDevanagariGlyphOrderAndAliasDB.txt',
URL), 'r')
glyphnames = []
for line in f:
glyphnames += [re.sub(r'\s+', ' ', line).split()]
return [
type(
'Charset', (object, ),
dict(glyphnames=glyphnames,
common_name='Unencoded Glyphs',
short_name='unencoded-glyphs',
native_name=''))
]
def __getcharsets__():
content = open(get_from_cache('Blocks.txt', UNIDATA_URL), 'r', encoding='utf-8').read()
regex = re.compile('^([\da-f]+)..([\da-f]+);\s*(.*)$', re.I | re.U)
for line in content.split('\n'):
m = regex.match(line.strip())
# 100000..10FFFF; Supplementary Private Use Area-B
if not m:
continue
glyphlist = '0x%s-0x%s' % (m.group(1), m.group(2))
unicodes = Extension.convert_to_list_of_unicodes(glyphlist)
yield type('Charset', (object,),
dict(glyphs=unicodes,
common_name=u'Unicode Block %s' % m.group(3),
native_name='',
short_name=unicodedata.normalize('NFKD', u'uni-{}'.format(m.group(3).lower().replace(' ', '-')))))
def get_codepoints():
""" Return all XML <scanning-codepoints> in received XML """
# response = requests.get(EXTENSIS_LANG_XML)
# if response.status_code != 200:
# return []
path = get_from_cache('languages.xml', EXTENSIS_LANG_XML)
try:
xml_content = open(path, 'r').read()
except IOError:
logging.error('Could not read languages.xml from cache')
xml_content = ''
content = re.sub('<!--.[^>]*-->', '', xml_content)
doc = etree.fromstring(content.lstrip('`'))
return doc.findall('.//scanning-codepoints')
def get_codepoints():
""" Return all XML <scanning-codepoints> in received XML """
# response = requests.get(EXTENSIS_LANG_XML)
# if response.status_code != 200:
# return []
path = get_from_cache("languages.xml", EXTENSIS_LANG_XML)
try:
xml_content = open(path, "r").read()
except IOError:
logging.error("Could not read languages.xml from cache")
xml_content = ""
content = re.sub("<!--.[^>]*-->", "", xml_content)
doc = etree.fromstring(content.lstrip("`"))
return doc.findall(".//scanning-codepoints")
def get_codepoints():
""" Return all XML <scanning-codepoints> in received XML """
# response = requests.get(EXTENSIS_LANG_XML)
# if response.status_code != 200:
# return []
path = get_from_cache('languages.xml', EXTENSIS_LANG_XML)
try:
xml_content = open(path, 'r').read()
except IOError:
logging.error('Could not read languages.xml from cache')
xml_content = ''
content = re.sub('<!--.[^>]*-->', '', xml_content)
doc = etree.fromstring(content.lstrip('`').encode("utf-8"))
return doc.findall('.//scanning-codepoints')
