def backslashreplace_errors(space, w_exc):
check_exception(space, w_exc)
if space.isinstance_w(w_exc, space.w_UnicodeEncodeError):
obj = space.realunicode_w(space.getattr(w_exc, space.wrap('object')))
start = space.int_w(space.getattr(w_exc, space.wrap('start')))
w_end = space.getattr(w_exc, space.wrap('end'))
end = space.int_w(w_end)
builder = UnicodeBuilder()
pos = start
while pos < end:
oc = ord(obj[pos])
num = hex(oc)
if (oc >= 0x10000):
builder.append(u"\\U")
zeros = 8
elif (oc >= 0x100):
builder.append(u"\\u")
zeros = 4
else:
builder.append(u"\\x")
zeros = 2
lnum = len(num)
nb = zeros + 2 - lnum # num starts with '0x'
if nb > 0:
builder.append_multiple_char(u'0', nb)
builder.append_slice(unicode(num), 2, lnum)
pos += 1
return space.newtuple([space.wrap(builder.build()), w_end])
else:
raise oefmt(space.w_TypeError,
"don't know how to handle %T in error callback", w_exc)
class W_UnicodeBuilder(W_Root):
def __init__(self, space, size):
if size < 0:
self.builder = UnicodeBuilder()
else:
self.builder = UnicodeBuilder(size)
@unwrap_spec(size=int)
def descr__new__(space, w_subtype, size=-1):
return W_UnicodeBuilder(space, size)
@unwrap_spec(s=unicode)
def descr_append(self, space, s):
self.builder.append(s)
@unwrap_spec(s=unicode, start=int, end=int)
def descr_append_slice(self, space, s, start, end):
if not 0 <= start <= end <= len(s):
raise oefmt(space.w_ValueError, "bad start/stop")
self.builder.append_slice(s, start, end)
def descr_build(self, space):
w_s = space.newunicode(self.builder.build())
# after build(), we can continue to append more strings
# to the same builder. This is supported since
# 2ff5087aca28 in RPython.
return w_s
def descr_len(self, space):
if self.builder is None:
raise oefmt(space.w_ValueError, "no length of built builder")
return space.newint(self.builder.getlength())
def backslashreplace_errors(space, w_exc):
check_exception(space, w_exc)
if space.isinstance_w(w_exc, space.w_UnicodeEncodeError):
obj = space.realunicode_w(space.getattr(w_exc, space.wrap('object')))
start = space.int_w(space.getattr(w_exc, space.wrap('start')))
w_end = space.getattr(w_exc, space.wrap('end'))
end = space.int_w(w_end)
builder = UnicodeBuilder()
pos = start
while pos < end:
oc = ord(obj[pos])
num = hex(oc)
if (oc >= 0x10000):
builder.append(u"\\U")
zeros = 8
elif (oc >= 0x100):
builder.append(u"\\u")
zeros = 4
else:
builder.append(u"\\x")
zeros = 2
lnum = len(num)
nb = zeros + 2 - lnum # num starts with '0x'
if nb > 0:
builder.append_multiple_char(u'0', nb)
builder.append_slice(unicode(num), 2, lnum)
pos += 1
return space.newtuple([space.wrap(builder.build()), w_end])
else:
raise oefmt(space.w_TypeError,
"don't know how to handle %T in error callback", w_exc)
def func():
s = UnicodeBuilder(32)
s.append(u'a')
s.append(u'abc')
s.append(u'abcdef')
s.append_slice(u'abc', 1, 2)
s.append_multiple_char(u'u', 40)
return s.build()
def func():
s = UnicodeBuilder(32)
s.append(u'a')
s.append(u'abc')
s.append(u'abcdef')
s.append_slice(u'abc', 1, 2)
s.append_multiple_char(u'u', 40)
return s.build()
def test_unicode_builder():
s = UnicodeBuilder()
s.append(u'a')
s.append(u'abc')
s.append_slice(u'abcdef', 1, 2)
assert s.getlength() == len('aabcb')
s.append_multiple_char(u'd', 4)
assert s.build() == 'aabcbdddd'
assert isinstance(s.build(), unicode)
def f(n):
while n > 0:
jitdriver.jit_merge_point(n=n)
sb = UnicodeBuilder()
sb.append_slice(u"abcdefghij", 1, n)
sb.append_slice(u"abcdefghij", 0, n)
s = sb.build()
if len(s) != 2 * n - 1: raise ValueError
n -= 1
return n
def test_unicode_builder():
s = UnicodeBuilder()
s.append(u'a')
s.append(u'abc')
s.append_slice(u'abcdef', 1, 2)
assert s.getlength() == len('aabcb')
s.append_multiple_char(u'd', 4)
result = s.build()
assert result == 'aabcbdddd'
assert isinstance(result, unicode)
def test_unicode_builder():
s = UnicodeBuilder()
s.append(u"a")
s.append(u"abc")
s.append_slice(u"abcdef", 1, 2)
assert s.getlength() == len("aabcb")
s.append_multiple_char(u"d", 4)
result = s.build()
assert result == "aabcbdddd"
assert isinstance(result, unicode)
def f(n):
while n > 0:
jitdriver.jit_merge_point(n=n)
sb = UnicodeBuilder()
sb.append_slice(u"fOo!", 1, 3)
s = sb.build()
if len(s) != 2: raise ValueError
if s[0] != u"O": raise ValueError
if s[1] != u"o": raise ValueError
n -= 1
return n
def format(self):
lgt = len(self.fmt) + 4 * len(self.values_w) + 10
if do_unicode:
result = UnicodeBuilder(lgt)
else:
result = StringBuilder(lgt)
self.result = result
while True:
# fast path: consume as many characters as possible
fmt = self.fmt
i = i0 = self.fmtpos
while i < len(fmt):
if fmt[i] == '%':
break
i += 1
else:
result.append_slice(fmt, i0, len(fmt))
break # end of 'fmt' string
result.append_slice(fmt, i0, i)
self.fmtpos = i + 1
# interpret the next formatter
w_value = self.parse_fmt()
c = self.peekchr()
self.forward()
if c == '%':
self.std_wp(const('%'))
continue
if w_value is None:
w_value = self.nextinputvalue()
# dispatch on the formatter
# (this turns into a switch after translation)
for c1 in FORMATTER_CHARS:
if c == c1:
# 'c1' is an annotation constant here,
# so this getattr() is ok
do_fmt = getattr(self, 'fmt_' + c1)
do_fmt(w_value)
break
else:
self.unknown_fmtchar()
self.checkconsumed()
return result.build()
def format(self):
lgt = len(self.fmt) + 4 * len(self.values_w) + 10
if do_unicode:
result = UnicodeBuilder(lgt)
else:
result = StringBuilder(lgt)
self.result = result
while True:
# fast path: consume as many characters as possible
fmt = self.fmt
i = i0 = self.fmtpos
while i < len(fmt):
if fmt[i] == '%':
break
i += 1
else:
result.append_slice(fmt, i0, len(fmt))
break # end of 'fmt' string
result.append_slice(fmt, i0, i)
self.fmtpos = i + 1
# interpret the next formatter
w_value = self.parse_fmt()
c = self.peekchr()
self.forward()
if c == '%':
self.std_wp(const('%'))
continue
if w_value is None:
w_value = self.nextinputvalue()
# dispatch on the formatter
# (this turns into a switch after translation)
for c1 in FORMATTER_CHARS:
if c == c1:
# 'c1' is an annotation constant here,
# so this getattr() is ok
do_fmt = getattr(self, 'fmt_' + c1)
do_fmt(w_value)
break
else:
self.unknown_fmtchar()
self.checkconsumed()
return result.build()
