def check_gdef(self):
if self._skip('gdef'):
return
mark_glyphs = [cp for cp in self.target_chars if unicode_data.category(cp) == 'Mn']
if self._check_gdef_class_defs(mark_glyphs):
self._check_gdef_marks(mark_glyphs)
self._check_gdef_combining()
def check_gdef(self):
if self._skip('gdef'):
return
mark_glyphs = [cp for cp in self.target_chars if unicode_data.category(cp) == 'Mn']
if self._check_gdef_class_defs(mark_glyphs):
self._check_gdef_marks(mark_glyphs)
self._check_gdef_combining()
def _write_char_text(chars, filepath, chars_per_line):
text = [unichr(cp) for cp in chars
if not unicode_data.category(cp)[0] in ['M', 'C', 'Z']]
filename, _ = path.splitext(path.basename(filepath))
m = re.match(r'(.*)-(?:Regular|Bold|Italic|BoldItalic)', filename)
if m:
filename = m.group(1)
filename += '_chars.txt'
print 'writing file: %s' % filename
print '%d characters (of %d)' % (len(text), len(chars))
if chars_per_line > 0:
lines = []
for n in range(0, len(text), chars_per_line):
substr = text[n:n + chars_per_line]
lines.append(' '.join(cp for cp in substr))
text = '\n'.join(lines)
with codecs.open(filename, 'w', 'utf-8') as f:
f.write(text)
def accept_cp(cp): cat = unicode_data.category(cp) return cat[0] not in ['M', 'C', 'Z'] or cat == 'Co'
def sample_text_from_exemplar(exemplar):
exemplar = [
c for c in exemplar if unicode_data.category(c[0])[0] in 'LNPS'
]
exemplar = exemplar[:EXEMPLAR_CUTOFF_SIZE]
return ' '.join(exemplar)
def accept_cp(cp): cat = unicode_data.category(cp) return cat[0] not in ['M', 'C', 'Z'] or cat == 'Co'
def sample_text_from_exemplar(exemplar):
exemplar = [c for c in exemplar
if unicode_data.category(c[0])[0] in 'LNPS']
exemplar = exemplar[:EXEMPLAR_CUTOFF_SIZE]
return ' '.join(exemplar)
def accept(s): return len(s) > 1 or unicode_data.category(s)[0] in cat
def test_category(self):
"""Tests the category() method."""
self.assertEqual('Co', unicode_data.category(0xF0001))
self.assertEqual('Cn', unicode_data.category(0xE01F0))
def accept(s):
return len(s) > 1 or unicode_data.category(s)[0] in cat