def _check_valid_emoji_cps(sorted_seq_to_filepath, unicode_version):
"""Ensure all cps in these sequences are valid emoji cps or specific cps
used in forming emoji sequences. This is a 'pre-check' that reports
this specific problem."""
valid_cps = set(unicode_data.get_emoji())
if unicode_version is None or unicode_version >= unicode_data.PROPOSED_EMOJI_AGE:
valid_cps |= unicode_data.proposed_emoji_cps()
else:
valid_cps = set(cp for cp in valid_cps
if unicode_data.age(cp) <= unicode_version)
valid_cps.add(0x200d) # ZWJ
valid_cps.add(0x20e3) # combining enclosing keycap
valid_cps.add(0xfe0f) # variation selector (emoji presentation)
valid_cps.add(0xfe82b) # PUA value for unknown flag
valid_cps |= TAG_SET # used in subregion tag sequences
not_emoji = {}
for seq, fp in sorted_seq_to_filepath.iteritems():
for cp in seq:
if cp not in valid_cps:
if cp not in not_emoji:
not_emoji[cp] = []
not_emoji[cp].append(fp)
if len(not_emoji):
print('check valid emoji cps: %d non-emoji cp found' % len(not_emoji),
file=sys.stderr)
for cp in sorted(not_emoji):
fps = not_emoji[cp]
print('check valid emoji cps: %04x (in %d sequences)' %
(cp, len(fps)),
file=sys.stderr)
def _check_valid_emoji_cps(sorted_seq_to_filepath, unicode_version):
"""Ensure all cps in these sequences are valid emoji cps or specific cps
used in forming emoji sequences. This is a 'pre-check' that reports
this specific problem."""
valid_cps = set(unicode_data.get_emoji())
if unicode_version is None or unicode_version >= unicode_data.PROPOSED_EMOJI_AGE:
valid_cps |= unicode_data.proposed_emoji_cps()
else:
valid_cps = set(
cp for cp in valid_cps if unicode_data.age(cp) <= unicode_version)
valid_cps.add(0x200d) # ZWJ
valid_cps.add(0x20e3) # combining enclosing keycap
valid_cps.add(0xfe0f) # variation selector (emoji presentation)
valid_cps.add(0xfe82b) # PUA value for unknown flag
valid_cps |= TAG_SET # used in subregion tag sequences
not_emoji = {}
for seq, fp in sorted_seq_to_filepath.iteritems():
for cp in seq:
if cp not in valid_cps:
if cp not in not_emoji:
not_emoji[cp] = []
not_emoji[cp].append(fp)
if len(not_emoji):
print(
'check valid emoji cps: %d non-emoji cp found' % len(not_emoji),
file=sys.stderr)
for cp in sorted(not_emoji):
fps = not_emoji[cp]
print(
'check valid emoji cps: %04x (in %d sequences)' % (cp, len(fps)),
file=sys.stderr)
def _get_name(key_tuple):
CELL_PREFIX = '<td class="name">'
if len(key_tuple) != 1:
name = ''
else:
cp = key_tuple[0]
if cp in unicode_data.proposed_emoji_cps():
name = '(proposed) ' + unicode_data.proposed_emoji_name(cp)
else:
name = unicode_data.name(cp, '(error)')
return CELL_PREFIX + name
def _get_name(key_tuple):
CELL_PREFIX = '<td class="name">'
if len(key_tuple) != 1:
name = ''
else:
cp = key_tuple[0]
if cp in unicode_data.proposed_emoji_cps():
name = '(proposed) ' + unicode_data.proposed_emoji_name(cp)
else:
name = unicode_data.name(cp, '(error)')
return CELL_PREFIX + name
def _get_name(key_tuple, annotated_tuples):
CELL_PREFIX = '<td%s>' % ('' if annotated_tuples is None or key_tuple
not in annotated_tuples else ' class="aname"')
if len(key_tuple) != 1:
name = '(' + ' '.join('U+%04X' % cp for cp in key_tuple) + ')'
else:
cp = key_tuple[0]
if cp in unicode_data.proposed_emoji_cps():
name = '(proposed) ' + unicode_data.proposed_emoji_name(cp)
else:
name = unicode_data.name(cp, '(error)')
return CELL_PREFIX + name
def _check_valid_emoji(sorted_seqs):
"""Ensure all emoji are either valid emoji or specific chars."""
valid_cps = set(unicode_data.get_emoji() | unicode_data.proposed_emoji_cps())
valid_cps.add(0x200d) # ZWJ
valid_cps.add(0x20e3) # combining enclosing keycap
valid_cps.add(0xfe0f) # variation selector (emoji presentation)
valid_cps.add(0xfe82b) # PUA value for unknown flag
not_emoji = set()
for seq in sorted_seqs:
for cp in seq:
if cp not in valid_cps:
not_emoji.add(cp)
if len(not_emoji):
print >> sys.stderr, '%d non-emoji found:' % len(not_emoji)
for cp in sorted(not_emoji):
print >> sys.stderr, '%04X' % cp
def _check_valid_emoji(sorted_seqs):
"""Ensure all emoji are either valid emoji or specific chars."""
valid_cps = set(unicode_data.get_emoji()
| unicode_data.proposed_emoji_cps())
valid_cps.add(0x200d) # ZWJ
valid_cps.add(0x20e3) # combining enclosing keycap
valid_cps.add(0xfe0f) # variation selector (emoji presentation)
valid_cps.add(0xfe82b) # PUA value for unknown flag
not_emoji = set()
for seq in sorted_seqs:
for cp in seq:
if cp not in valid_cps:
not_emoji.add(cp)
if len(not_emoji):
print >> sys.stderr, '%d non-emoji found:' % len(not_emoji)
for cp in sorted(not_emoji):
print >> sys.stderr, '%04X' % cp
def _check_valid_emoji_cps(sorted_seq_to_filepath, unicode_version):
"""Ensure all cps in these sequences are valid emoji cps or specific cps
used in forming emoji sequences. This is a 'pre-check' that reports
this specific problem."""
coverage_pass = True
valid_cps = set(unicode_data.get_emoji())
if unicode_version is None or unicode_version >= unicode_data.PROPOSED_EMOJI_AGE:
valid_cps |= unicode_data.proposed_emoji_cps()
else:
valid_cps = set(cp for cp in valid_cps
if unicode_data.age(cp) <= unicode_version)
valid_cps.add(0x200d) # ZWJ
valid_cps.add(0x20e3) # combining enclosing keycap
valid_cps.add(0xfe0f) # variation selector (emoji presentation)
valid_cps.add(0xfe82b) # PUA value for unknown flag
valid_cps |= TAG_SET # used in subregion tag sequences
not_emoji = {}
for seq, fp in sorted_seq_to_filepath.items():
for cp in seq:
if cp not in valid_cps:
if cp not in not_emoji:
not_emoji[cp] = []
not_emoji[cp].append(fp)
if len(not_emoji):
print(f'check valid emoji cps: {len(not_emoji)} non-emoji cp found',
file=sys.stderr)
for cp in sorted(not_emoji):
fps = not_emoji[cp]
print(
f'check the following cp: {cp} - {not_emoji.get(cp)[0]} (in {len(fps)} sequences)',
file=sys.stderr)
coverage_pass = False
if not coverage_pass:
exit(
"Please fix the problems metioned above or run: make BYPASS_SEQUENCE_CHECK='True'"
)
def _check_valid_emoji(sorted_seq_to_filepath):
"""Ensure all emoji are either valid emoji or specific chars."""
valid_cps = set(unicode_data.get_emoji()
| unicode_data.proposed_emoji_cps())
valid_cps.add(0x200d) # ZWJ
valid_cps.add(0x20e3) # combining enclosing keycap
valid_cps.add(0xfe0f) # variation selector (emoji presentation)
valid_cps.add(0xfe82b) # PUA value for unknown flag
not_emoji = {}
for seq, fp in sorted_seq_to_filepath.iteritems():
for cp in seq:
if cp not in valid_cps:
if cp not in not_emoji:
not_emoji[cp] = []
not_emoji[cp].append(fp)
if len(not_emoji):
print >> sys.stderr, '%d non-emoji found:' % len(not_emoji)
for cp in sorted(not_emoji):
print >> sys.stderr, '%04x (in %s)' % (cp, ', '.join(
not_emoji[cp]))