def rawwcharp2unicoden(wcp, maxlen):
b = UnicodeBuilder(maxlen)
i = 0
while i < maxlen and rffi.cast(lltype.Signed, wcp[i]) != 0:
b.append(code_to_unichr(wcp[i]))
i += 1
return assert_str0(b.build())
def get(self, ch, errorchar):
space = self.space
# get the character from the mapping
if self.mapping_w is not None:
w_ch = self.mapping_w[ord(ch)]
else:
try:
w_ch = space.getitem(self.w_mapping, space.newint(ord(ch)))
except OperationError as e:
if not e.match(space, space.w_LookupError):
raise
return errorchar
if space.isinstance_w(w_ch, space.w_unicode):
# Charmap may return a unicode string
return space.unicode_w(w_ch)
elif space.isinstance_w(w_ch, space.w_int):
# Charmap may return a number
x = space.int_w(w_ch)
if not 0 <= x <= 0x10FFFF:
raise oefmt(space.w_TypeError,
"character mapping must be in range(0x110000)")
return code_to_unichr(x)
elif space.is_w(w_ch, space.w_None):
# Charmap may return None
return errorchar
raise oefmt(space.w_TypeError,
"character mapping must return integer, None or str")
def lookup(self, space, name):
try:
code = self._lookup(name.upper())
except KeyError:
msg = space.mod(space.wrap("undefined character name '%s'"), space.wrap(name))
raise OperationError(space.w_KeyError, msg)
return space.wrap(code_to_unichr(code))
def get(self, ch, errorchar):
space = self.space
# get the character from the mapping
if self.mapping_w is not None:
w_ch = self.mapping_w[ord(ch)]
else:
try:
w_ch = space.getitem(self.w_mapping, space.newint(ord(ch)))
except OperationError as e:
if not e.match(space, space.w_LookupError):
raise
return errorchar
if space.isinstance_w(w_ch, space.w_unicode):
# Charmap may return a unicode string
return space.unicode_w(w_ch)
elif space.isinstance_w(w_ch, space.w_int):
# Charmap may return a number
x = space.int_w(w_ch)
if not 0 <= x <= 0x10FFFF:
raise oefmt(space.w_TypeError,
"character mapping must be in range(0x110000)")
return code_to_unichr(x)
elif space.is_w(w_ch, space.w_None):
# Charmap may return None
return errorchar
raise oefmt(space.w_TypeError,
"character mapping must return integer, None or unicode")
def rawwcharp2unicoden(wcp, maxlen):
b = UnicodeBuilder(maxlen)
i = 0
while i < maxlen and rffi.cast(lltype.Signed, wcp[i]) != 0:
b.append(code_to_unichr(wcp[i]))
i += 1
return assert_str0(b.build())
def lookup(self, space, name):
try:
code = self._lookup(name.upper())
except KeyError:
msg = space.mod(space.newtext("undefined character name '%s'"),
space.newtext(name))
raise OperationError(space.w_KeyError, msg)
return space.newunicode(code_to_unichr(code))
def lookup(self, space, name):
try:
code = self._lookup(name.upper(), with_named_sequence=True)
except KeyError:
msg = space.mod(space.newtext("undefined character name '%s'"),
space.newtext(name))
raise OperationError(space.w_KeyError, msg)
# The code may be a named sequence
sequence = self._lookup_named_sequence(code)
if sequence is not None:
# named sequences only contain UCS2 codes, no surrogates &co.
return space.newunicode(sequence)
return space.newunicode(code_to_unichr(code))
def decode_escape_sequence_unicode(self, i, builder):
# at this point we are just after the 'u' of the \u1234 sequence.
start = i
i += 4
hexdigits = self.getslice(start, i)
try:
val = int(hexdigits, 16)
if val & 0xfc00 == 0xd800:
# surrogate pair
val = self.decode_surrogate_pair(i, val)
i += 6
except ValueError:
self._raise("Invalid \uXXXX escape (char %d)", i-1)
return # help the annotator to know that we'll never go beyond
# this point
#
uchr = runicode.code_to_unichr(val) # may be a surrogate pair again
utf8_ch = unicodehelper.encode_utf8(self.space, uchr)
builder.append(utf8_ch)
return i
def decode_escape_sequence_unicode(self, i, builder):
# at this point we are just after the 'u' of the \u1234 sequence.
start = i
i += 4
hexdigits = self.getslice(start, i)
try:
val = int(hexdigits, 16)
if val & 0xfc00 == 0xd800:
# surrogate pair
val = self.decode_surrogate_pair(i, val)
i += 6
except ValueError:
self._raise("Invalid \uXXXX escape (char %d)", i - 1)
return # help the annotator to know that we'll never go beyond
# this point
#
uchr = runicode.code_to_unichr(val) # may be a surrogate pair again
utf8_ch = unicodehelper.encode_utf8(self.space, uchr)
builder.append(utf8_ch)
return i
class Charmap_Decode:
def __init__(self, space, w_mapping):
self.space = space
self.w_mapping = w_mapping
# fast path for all the stuff in the encodings module
if space.isinstance_w(w_mapping, space.w_tuple):
self.mapping_w = space.fixedview(w_mapping)
else:
self.mapping_w = None
def get(self, ch, errorchar):
space = self.space
# get the character from the mapping
if self.mapping_w is not None:
w_ch = self.mapping_w[ord(ch)]
else:
try:
w_ch = space.getitem(self.w_mapping, space.newint(ord(ch)))
except OperationError, e:
if not e.match(space, space.w_LookupError):
raise
return errorchar
if space.isinstance_w(w_ch, space.w_unicode):
# Charmap may return a unicode string
return space.unicode_w(w_ch)
elif space.isinstance_w(w_ch, space.w_int):
# Charmap may return a number
x = space.int_w(w_ch)
if not 0 <= x <= 0x10FFFF:
raise oefmt(space.w_TypeError,
"character mapping must be in range(0x110000)")
return code_to_unichr(x)
elif space.is_w(w_ch, space.w_None):
# Charmap may return None
return errorchar
raise oefmt(space.w_TypeError,
"character mapping must return integer, None or unicode")
def decode_escape_sequence_unicode(self, i, builder):
# at this point we are just after the 'u' of the \u1234 sequence.
start = i
i += 4
hexdigits = self.getslice(start, i)
try:
val = int(hexdigits, 16)
if sys.maxunicode > 65535 and 0xd800 <= val <= 0xdfff:
# surrogate pair
if self.ll_chars[i] == '\\' and self.ll_chars[i + 1] == 'u':
val = self.decode_surrogate_pair(i, val)
i += 6
except ValueError:
raise DecoderError("Invalid \\uXXXX escape", i - 1)
#
uchr = runicode.code_to_unichr(val) # may be a surrogate pair again
utf8_ch = unicodehelper.encode_utf8(self.space,
uchr,
allow_surrogates=True)
builder.append(utf8_ch)
return i
def f(c):
return ord(code_to_unichr(c)[0])
def f(c):
return code_to_unichr(c) + u''