def fn(_):
s = StringBuilder()
s.append("a")
s.append("abc")
s.append_slice("abc", 1, 2)
s.append_multiple_char('d', 4)
return s.build()
def func():
s = StringBuilder()
s.append("a")
s.append("abc")
s.append_slice("abc", 1, 2)
s.append_multiple_char('d', 4)
return s.build()
def test_string_builder():
s = StringBuilder()
s.append("a")
s.append("abc")
s.append("a")
s.append_slice("abc", 1, 2)
s.append_multiple_char('d', 4)
assert s.build() == "aabcabdddd"
def test_string_builder():
s = StringBuilder()
s.append("a")
s.append("abc")
s.append("a")
s.append_slice("abc", 1, 2)
s.append_multiple_char('d', 4)
assert s.build() == "aabcabdddd"
def str_zfill__String_ANY(space, w_self, w_width):
input = w_self._value
width = space.int_w(w_width)
num_zeros = width - len(input)
if num_zeros <= 0:
# cannot return w_self, in case it is a subclass of str
return space.wrap(input)
builder = StringBuilder(width)
if len(input) > 0 and (input[0] == '+' or input[0] == '-'):
builder.append(input[0])
start = 1
else:
start = 0
builder.append_multiple_char('0', num_zeros)
builder.append_slice(input, start, len(input))
return space.wrap(builder.build())
def str_zfill__String_ANY(space, w_self, w_width):
input = w_self._value
width = space.int_w(w_width)
num_zeros = width - len(input)
if num_zeros <= 0:
# cannot return w_self, in case it is a subclass of str
return space.wrap(input)
builder = StringBuilder(width)
if len(input) > 0 and (input[0] == '+' or input[0] == '-'):
builder.append(input[0])
start = 1
else:
start = 0
builder.append_multiple_char('0', num_zeros)
builder.append_slice(input, start, len(input))
return space.wrap(builder.build())
def descr_repr(self, space):
res = StringBuilder()
res.append("array(")
concrete = self.get_concrete()
dtype = concrete.find_dtype()
if not concrete.find_size():
res.append('[]')
if len(self.shape) > 1:
# An empty slice reports its shape
res.append(", shape=(")
self_shape = str(self.shape)
res.append_slice(str(self_shape), 1, len(self_shape) - 1)
res.append(')')
else:
concrete.to_str(space, 1, res, indent=' ')
if (dtype is not space.fromcache(interp_dtype.W_Float64Dtype) and
dtype is not space.fromcache(interp_dtype.W_Int64Dtype)) or \
not self.find_size():
res.append(", dtype=" + dtype.name)
res.append(")")
return space.wrap(res.build())
def descr_repr(self, space):
res = StringBuilder()
res.append("array(")
concrete = self.get_concrete_or_scalar()
dtype = concrete.find_dtype()
if not concrete.size:
res.append('[]')
if len(self.shape) > 1:
# An empty slice reports its shape
res.append(", shape=(")
self_shape = str(self.shape)
res.append_slice(str(self_shape), 1, len(self_shape) - 1)
res.append(')')
else:
concrete.to_str(space, 1, res, indent=' ')
if (dtype is not interp_dtype.get_dtype_cache(space).w_float64dtype and
not (dtype.kind == interp_dtype.SIGNEDLTR and
dtype.itemtype.get_element_size() == rffi.sizeof(lltype.Signed)) or
not self.size):
res.append(", dtype=" + dtype.name)
res.append(")")
return space.wrap(res.build())
def descr_repr(self, space):
res = StringBuilder()
res.append("array(")
concrete = self.get_concrete_or_scalar()
dtype = concrete.find_dtype()
if not concrete.size:
res.append('[]')
if len(self.shape) > 1:
# An empty slice reports its shape
res.append(", shape=(")
self_shape = str(self.shape)
res.append_slice(str(self_shape), 1, len(self_shape) - 1)
res.append(')')
else:
concrete.to_str(space, 1, res, indent=' ')
if (dtype is not interp_dtype.get_dtype_cache(space).w_float64dtype
and not (dtype.kind == interp_dtype.SIGNEDLTR
and dtype.itemtype.get_element_size() == rffi.sizeof(
lltype.Signed)) or not self.size):
res.append(", dtype=" + dtype.name)
res.append(")")
return space.wrap(res.build())
def _string_replace(space, input, sub, by, maxsplit):
if maxsplit == 0:
return space.wrap(input)
if not sub:
upper = len(input)
if maxsplit > 0 and maxsplit < upper + 2:
upper = maxsplit - 1
assert upper >= 0
try:
result_size = ovfcheck(upper * len(by))
result_size = ovfcheck(result_size + upper)
result_size = ovfcheck(result_size + len(by))
remaining_size = len(input) - upper
result_size = ovfcheck(result_size + remaining_size)
except OverflowError:
raise OperationError(space.w_OverflowError,
space.wrap("replace string is too long")
)
builder = StringBuilder(result_size)
for i in range(upper):
builder.append(by)
builder.append(input[i])
builder.append(by)
builder.append_slice(input, upper, len(input))
else:
# First compute the exact result size
count = input.count(sub)
if count > maxsplit and maxsplit > 0:
count = maxsplit
diff_len = len(by) - len(sub)
try:
result_size = ovfcheck(diff_len * count)
result_size = ovfcheck(result_size + len(input))
except OverflowError:
raise OperationError(space.w_OverflowError,
space.wrap("replace string is too long")
)
builder = StringBuilder(result_size)
start = 0
sublen = len(sub)
while maxsplit != 0:
next = input.find(sub, start)
if next < 0:
break
builder.append_slice(input, start, next)
builder.append(by)
start = next + sublen
maxsplit -= 1 # NB. if it's already < 0, it stays < 0
builder.append_slice(input, start, len(input))
return space.wrap(builder.build())
def _string_replace(space, input, sub, by, maxsplit):
if maxsplit == 0:
return space.wrap(input)
if not sub:
upper = len(input)
if maxsplit > 0 and maxsplit < upper + 2:
upper = maxsplit - 1
assert upper >= 0
try:
result_size = ovfcheck(upper * len(by))
result_size = ovfcheck(result_size + upper)
result_size = ovfcheck(result_size + len(by))
remaining_size = len(input) - upper
result_size = ovfcheck(result_size + remaining_size)
except OverflowError:
raise OperationError(space.w_OverflowError,
space.wrap("replace string is too long"))
builder = StringBuilder(result_size)
for i in range(upper):
builder.append(by)
builder.append(input[i])
builder.append(by)
builder.append_slice(input, upper, len(input))
else:
# First compute the exact result size
count = input.count(sub)
if count > maxsplit and maxsplit > 0:
count = maxsplit
diff_len = len(by) - len(sub)
try:
result_size = ovfcheck(diff_len * count)
result_size = ovfcheck(result_size + len(input))
except OverflowError:
raise OperationError(space.w_OverflowError,
space.wrap("replace string is too long"))
builder = StringBuilder(result_size)
start = 0
sublen = len(sub)
while maxsplit != 0:
next = input.find(sub, start)
if next < 0:
break
builder.append_slice(input, start, next)
builder.append(by)
start = next + sublen
maxsplit -= 1 # NB. if it's already < 0, it stays < 0
builder.append_slice(input, start, len(input))
return space.wrap(builder.build())
def repr__String(space, w_str):
s = w_str._value
buf = StringBuilder(50)
quote = "'"
if quote in s and '"' not in s:
quote = '"'
buf.append(quote)
startslice = 0
for i in range(len(s)):
c = s[i]
use_bs_char = False # character quoted by backspace
if c == '\\' or c == quote:
bs_char = c
use_bs_char = True
elif c == '\t':
bs_char = 't'
use_bs_char = True
elif c == '\r':
bs_char = 'r'
use_bs_char = True
elif c == '\n':
bs_char = 'n'
use_bs_char = True
elif not '\x20' <= c < '\x7f':
n = ord(c)
if i != startslice:
buf.append_slice(s, startslice, i)
startslice = i + 1
buf.append('\\x')
buf.append("0123456789abcdef"[n>>4])
buf.append("0123456789abcdef"[n&0xF])
if use_bs_char:
if i != startslice:
buf.append_slice(s, startslice, i)
startslice = i + 1
buf.append('\\')
buf.append(bs_char)
if len(s) != startslice:
buf.append_slice(s, startslice, len(s))
buf.append(quote)
return space.wrap(buf.build())
def repr__String(space, w_str):
s = w_str._value
buf = StringBuilder(50)
quote = "'"
if quote in s and '"' not in s:
quote = '"'
buf.append(quote)
startslice = 0
for i in range(len(s)):
c = s[i]
use_bs_char = False # character quoted by backspace
if c == "\\" or c == quote:
bs_char = c
use_bs_char = True
elif c == "\t":
bs_char = "t"
use_bs_char = True
elif c == "\r":
bs_char = "r"
use_bs_char = True
elif c == "\n":
bs_char = "n"
use_bs_char = True
elif not "\x20" <= c < "\x7f":
n = ord(c)
if i != startslice:
buf.append_slice(s, startslice, i)
startslice = i + 1
buf.append("\\x")
buf.append("0123456789abcdef"[n >> 4])
buf.append("0123456789abcdef"[n & 0xF])
if use_bs_char:
if i != startslice:
buf.append_slice(s, startslice, i)
startslice = i + 1
buf.append("\\")
buf.append(bs_char)
if len(s) != startslice:
buf.append_slice(s, startslice, len(s))
buf.append(quote)
return space.wrap(buf.build())
def repr__String(space, w_str):
s = w_str._value
buf = StringBuilder(50)
quote = "'"
if quote in s and '"' not in s:
quote = '"'
buf.append(quote)
startslice = 0
for i in range(len(s)):
c = s[i]
use_bs_char = False # character quoted by backspace
if c == '\\' or c == quote:
bs_char = c
use_bs_char = True
elif c == '\t':
bs_char = 't'
use_bs_char = True
elif c == '\r':
bs_char = 'r'
use_bs_char = True
elif c == '\n':
bs_char = 'n'
use_bs_char = True
elif not '\x20' <= c < '\x7f':
n = ord(c)
if i != startslice:
buf.append_slice(s, startslice, i)
startslice = i + 1
buf.append('\\x')
buf.append("0123456789abcdef"[n>>4])
buf.append("0123456789abcdef"[n&0xF])
if use_bs_char:
if i != startslice:
buf.append_slice(s, startslice, i)
startslice = i + 1
buf.append('\\')
buf.append(bs_char)
if len(s) != startslice:
buf.append_slice(s, startslice, len(s))
buf.append(quote)
return space.wrap(buf.build())
def string_escape_encode(s, quote):
buf = StringBuilder(len(s) + 2)
buf.append(quote)
startslice = 0
for i in range(len(s)):
c = s[i]
use_bs_char = False # character quoted by backspace
if c == '\\' or c == quote:
bs_char = c
use_bs_char = True
elif c == '\t':
bs_char = 't'
use_bs_char = True
elif c == '\r':
bs_char = 'r'
use_bs_char = True
elif c == '\n':
bs_char = 'n'
use_bs_char = True
elif not '\x20' <= c < '\x7f':
n = ord(c)
if i != startslice:
buf.append_slice(s, startslice, i)
startslice = i + 1
buf.append('\\x')
buf.append("0123456789abcdef"[n>>4])
buf.append("0123456789abcdef"[n&0xF])
if use_bs_char:
if i != startslice:
buf.append_slice(s, startslice, i)
startslice = i + 1
buf.append('\\')
buf.append(bs_char)
if len(s) != startslice:
buf.append_slice(s, startslice, len(s))
buf.append(quote)
return buf.build()
def string_escape_encode(s, quote):
buf = StringBuilder(len(s) + 2)
buf.append(quote)
startslice = 0
for i in range(len(s)):
c = s[i]
use_bs_char = False # character quoted by backspace
if c == '\\' or c == quote:
bs_char = c
use_bs_char = True
elif c == '\t':
bs_char = 't'
use_bs_char = True
elif c == '\r':
bs_char = 'r'
use_bs_char = True
elif c == '\n':
bs_char = 'n'
use_bs_char = True
elif not '\x20' <= c < '\x7f':
n = ord(c)
if i != startslice:
buf.append_slice(s, startslice, i)
startslice = i + 1
buf.append('\\x')
buf.append("0123456789abcdef"[n >> 4])
buf.append("0123456789abcdef"[n & 0xF])
if use_bs_char:
if i != startslice:
buf.append_slice(s, startslice, i)
startslice = i + 1
buf.append('\\')
buf.append(bs_char)
if len(s) != startslice:
buf.append_slice(s, startslice, len(s))
buf.append(quote)
return buf.build()
def PyString_DecodeEscape(space, s, recode_encoding):
"""
Unescape a backslash-escaped string. If recode_encoding is non-zero,
the string is UTF-8 encoded and should be re-encoded in the
specified encoding.
"""
builder = StringBuilder(len(s))
ps = 0
end = len(s)
while 1:
ps2 = ps
while ps < end and s[ps] != '\\':
if recode_encoding and ord(s[ps]) & 0x80:
w, ps = decode_utf8(space, s, ps, end, recode_encoding)
builder.append(w)
ps2 = ps
else:
ps += 1
if ps > ps2:
builder.append_slice(s, ps2, ps)
if ps == end:
break
ps += 1
if ps == end:
raise_app_valueerror(space, 'Trailing \\ in string')
prevps = ps
ch = s[ps]
ps += 1
# XXX This assumes ASCII!
if ch == '\n':
pass
elif ch == '\\':
builder.append('\\')
elif ch == "'":
builder.append("'")
elif ch == '"':
builder.append('"')
elif ch == 'b':
builder.append("\010")
elif ch == 'f':
builder.append('\014') # FF
elif ch == 't':
builder.append('\t')
elif ch == 'n':
builder.append('\n')
elif ch == 'r':
builder.append('\r')
elif ch == 'v':
builder.append('\013') # VT
elif ch == 'a':
builder.append('\007') # BEL, not classic C
elif ch in '01234567':
# Look for up to two more octal digits
span = ps
span += (span < end) and (s[span] in '01234567')
span += (span < end) and (s[span] in '01234567')
octal = s[prevps : span]
# emulate a strange wrap-around behavior of CPython:
# \400 is the same as \000 because 0400 == 256
num = int(octal, 8) & 0xFF
builder.append(chr(num))
ps = span
elif ch == 'x':
if ps+2 <= end and isxdigit(s[ps]) and isxdigit(s[ps + 1]):
hexa = s[ps : ps + 2]
num = int(hexa, 16)
builder.append(chr(num))
ps += 2
else:
raise_app_valueerror(space, 'invalid \\x escape')
# ignored replace and ignore for now
else:
# this was not an escape, so the backslash
# has to be added, and we start over in
# non-escape mode.
builder.append('\\')
ps -= 1
assert ps >= 0
continue
# an arbitry number of unescaped UTF-8 bytes may follow.
buf = builder.build()
return buf
