def parse(input):
program = []
lines = [rstring.strip_spaces(i) for i in rstring.split(input, '\n')]
labels = get_labels(lines)
for line in lines:
line = [i for i in rstring.split(line, ' ') if i]
if not line:
continue
ins, args = line[0].upper(), [convert_arg(i, labels) for i in line[1:]]
if ins[-1] == ':':
continue
elif ins == "COPY":
val = Copy(args[0])
elif ins == "CONST":
val = Const(args[0])
elif ins == "CALL":
val = Call(args[0], args[1:])
elif ins == "JUMP":
val = Jump(args[0])
elif ins == "RETURN":
val = Return(args)
elif ins == "PICK":
val = Pick(args[0], args[1], args[2])
elif ins in Binop.classes:
val = Binop.get_cls(ins)(args[0], args[1])
else:
raise Exception("Unparsable instruction %s" % ins)
program.append(val)
return program[:]
def splitter(statement):
values = [];
_values = [];
p = 0;
m = False;
if("," in statement):
values = rstring.split(statement, ",")
#values = statement.split(","); #strip the ( and )
m = True;
#for value in values:
# print value
if(m == True):
for value in values:
p+=1;
if value.find("(") != -1:
if value == values[0]:
f1 = value
f0, f1 = rstring.split(f1, "(")
_values.append(f1)
elif value.startswith("("):
value = value[1:]
_values.append(value);
elif value.endswith(")"):
value = value[:-1]
_values.append(value);
else:
_values.append(value)
else:
_values.append(statement);
return _values
def check_split(value, sub, *args, **kwargs):
result = kwargs['res']
assert split(value, sub, *args) == result
list_result = [list(i) for i in result]
assert split(list(value), sub, *args) == list_result
assert split(buffer(value), sub, *args) == result
def check_split(value, sub, *args, **kwargs):
result = kwargs['res']
assert split(value, sub, *args) == result
list_result = [list(i) for i in result]
assert split(list(value), sub, *args) == list_result
assert split(buffer(value), sub, *args) == result
def remove_const(name):
tmplt_start = name.find("<")
tmplt_stop = name.rfind(">")
if 0 <= tmplt_start and 0 <= tmplt_stop:
# only replace const qualifying the class name, not in the template parameters
return "".join([x.strip(" ") for x in rstring.split(name[:tmplt_start], "const")])+\
name[tmplt_start:tmplt_stop]+\
"".join([x.strip(" ") for x in rstring.split(name[tmplt_stop:], "const")])
else:
return "".join([x.strip(" ") for x in rstring.split(name, "const")])
def fn():
res = True
res = res and split('a//b//c//d', '//') == ['a', 'b', 'c', 'd']
res = res and split('a//b//c//d', '//', 2) == ['a', 'b', 'c//d']
res = res and split(u'a//b//c//d', u'//') == [u'a', u'b', u'c', u'd']
res = res and split(u'endcase test', u'test') == [u'endcase ', u'']
res = res and rsplit('a|b|c|d', '|', 2) == ['a|b', 'c', 'd']
res = res and rsplit('a//b//c//d', '//') == ['a', 'b', 'c', 'd']
res = res and rsplit(u'a|b|c|d', u'|') == [u'a', u'b', u'c', u'd']
res = res and rsplit(u'a|b|c|d', u'|', 2) == [u'a|b', u'c', u'd']
res = res and rsplit(u'a//b//c//d', u'//') == [u'a', u'b', u'c', u'd']
return res
def descr_split(self, space, w_sep=None, maxsplit=-1):
res = []
value = self._val(space)
if space.is_none(w_sep):
res = split(value, maxsplit=maxsplit)
return self._newlist_unwrapped(space, res)
by = self._op_val(space, w_sep)
if len(by) == 0:
raise oefmt(space.w_ValueError, "empty separator")
res = split(value, by, maxsplit)
return self._newlist_unwrapped(space, res)
def descr_split(self, space, w_sep=None, maxsplit=-1):
res = []
value = self._val(space)
if space.is_none(w_sep):
res = split(value, maxsplit=maxsplit)
return self._newlist_unwrapped(space, res)
by = self._op_val(space, w_sep)
if len(by) == 0:
raise oefmt(space.w_ValueError, "empty separator")
res = split(value, by, maxsplit)
return self._newlist_unwrapped(space, res)
def test_split():
assert split("", 'x') == ['']
assert split("a", "a", 1) == ['', '']
assert split(" ", " ", 1) == ['', '']
assert split("aa", "a", 2) == ['', '', '']
assert split('a|b|c|d', '|') == ['a', 'b', 'c', 'd']
assert split('a|b|c|d', '|', 2) == ['a', 'b', 'c|d']
assert split('a//b//c//d', '//') == ['a', 'b', 'c', 'd']
assert split('a//b//c//d', '//', 2) == ['a', 'b', 'c//d']
assert split('endcase test', 'test') == ['endcase ', '']
py.test.raises(ValueError, split, 'abc', '')
def parse_bytecode_file(bytecode_file):
"""Parse a file of bytecode.
The argument should be the text of the original file, with
mnemonic bytecodes. The result will be a rcsp.box.ProgramBox
object.
"""
from rcsp.box import CodeBox, ProgramBox
bytecode = []
# Split bytecode into individual strings.
# Throw away comments and whitespace.
for line_ in bytecode_file.split('\n'):
if DEBUG:
line = line_.strip()
else:
line = rstring.strip_spaces(line_)
if line.startswith('#'):
continue
else:
if DEBUG:
for code in line.split():
bytecode.append(code)
else:
bytecode.extend(rstring.split(line))
# Parse bytecodes into numeric opcodes.
functions = {} # Dict of str names -> CodeBox objects
counter = 0
while counter < len(bytecode):
opcodes, strings, integers, bools = [], [], [], []
name = '' # Name of each function which is parsed.
code = bytecode[counter]
# Parse a list of functions.
if code == 'DEF':
counter += 1 # Skip DEF.
name = bytecode[counter]
counter += 1 # Skip name of function.
code = bytecode[counter]
# TODO: Enable nested functions.
while code != 'ENDDEF':
# Handle general instructions.
if code in opcode_mnemonics():
opcodes.append(opcode(code))
# Handle literals.
else:
if code.isdigit():
integers.append(int(code))
opcodes.append(len(integers) - 1)
elif code == 'True' or code == 'False':
bools.append(bool(code))
opcodes.append(len(bools) - 1)
else:
strings.append(code)
opcodes.append(len(strings) - 1)
counter += 1
code = bytecode[counter]
functions[name] = CodeBox(opcodes, strings, integers, bools)
# Ignore ENDDEF
counter += 1
return ProgramBox(functions)
def test_split_unicode():
assert split(u"", u"x") == [u""]
assert split(u"a", u"a", 1) == [u"", u""]
assert split(u" ", u" ", 1) == [u"", u""]
assert split(u"aa", u"a", 2) == [u"", u"", u""]
assert split(u"a|b|c|d", u"|") == [u"a", u"b", u"c", u"d"]
assert split(u"a|b|c|d", u"|", 2) == [u"a", u"b", u"c|d"]
assert split(u"a//b//c//d", u"//") == [u"a", u"b", u"c", u"d"]
assert split(u"endcase test", u"test") == [u"endcase ", u""]
py.test.raises(ValueError, split, u"abc", u"")
def test_split_unicode():
assert split(u"", u'x') == [u'']
assert split(u"a", u"a", 1) == [u'', u'']
assert split(u" ", u" ", 1) == [u'', u'']
assert split(u"aa", u"a", 2) == [u'', u'', u'']
assert split(u'a|b|c|d', u'|') == [u'a', u'b', u'c', u'd']
assert split(u'a|b|c|d', u'|', 2) == [u'a', u'b', u'c|d']
assert split(u'a//b//c//d', u'//') == [u'a', u'b', u'c', u'd']
assert split(u'endcase test', u'test') == [u'endcase ', u'']
py.test.raises(ValueError, split, u'abc', u'')
def test_split_unicode():
assert split(u"", u'x') == [u'']
assert split(u"a", u"a", 1) == [u'', u'']
assert split(u" ", u" ", 1) == [u'', u'']
assert split(u"aa", u"a", 2) == [u'', u'', u'']
assert split(u'a|b|c|d', u'|') == [u'a', u'b', u'c', u'd']
assert split(u'a|b|c|d', u'|', 2) == [u'a', u'b', u'c|d']
assert split(u'a//b//c//d', u'//') == [u'a', u'b', u'c', u'd']
assert split(u'endcase test', u'test') == [u'endcase ', u'']
py.test.raises(ValueError, split, u'abc', u'')
def str_split__String_String_ANY(space, w_self, w_by, w_maxsplit=-1):
maxsplit = space.int_w(w_maxsplit)
value = w_self._value
by = w_by._value
bylen = len(by)
if bylen == 0:
raise OperationError(space.w_ValueError, space.wrap("empty separator"))
res = split(value, by, maxsplit)
return space.newlist_str(res)
def str_split__String_String_ANY(space, w_self, w_by, w_maxsplit=-1):
maxsplit = space.int_w(w_maxsplit)
value = w_self._value
by = w_by._value
bylen = len(by)
if bylen == 0:
raise OperationError(space.w_ValueError, space.wrap("empty separator"))
res = split(value, by, maxsplit)
return space.newlist_str(res)
def unicode_split__Unicode_Unicode_ANY(space, w_self, w_delim, w_maxsplit):
self = w_self._value
delim = w_delim._value
maxsplit = space.int_w(w_maxsplit)
delim_len = len(delim)
if delim_len == 0:
raise OperationError(space.w_ValueError,
space.wrap('empty separator'))
parts = split(self, delim, maxsplit)
return space.newlist_unicode(parts)
def fn():
res = True
res = res and split("a//b//c//d", "//") == ["a", "b", "c", "d"]
res = res and split(" a\ta\na b") == ["a", "a", "a", "b"]
res = res and split("a//b//c//d", "//", 2) == ["a", "b", "c//d"]
res = res and split("abcd,efghi", ",") == ["abcd", "efghi"]
res = res and split(u"a//b//c//d", u"//") == [u"a", u"b", u"c", u"d"]
res = res and split(u"endcase test", u"test") == [u"endcase ", u""]
res = res and rsplit("a|b|c|d", "|", 2) == ["a|b", "c", "d"]
res = res and rsplit("a//b//c//d", "//") == ["a", "b", "c", "d"]
res = res and rsplit(u"a|b|c|d", u"|") == [u"a", u"b", u"c", u"d"]
res = res and rsplit(u"a|b|c|d", u"|", 2) == [u"a|b", u"c", u"d"]
res = res and rsplit(u"a//b//c//d", u"//") == [u"a", u"b", u"c", u"d"]
return res
def fn():
res = True
res = res and split('a//b//c//d', '//') == ['a', 'b', 'c', 'd']
res = res and split(' a\ta\na b') == ['a', 'a', 'a', 'b']
res = res and split('a//b//c//d', '//', 2) == ['a', 'b', 'c//d']
res = res and split('abcd,efghi', ',') == ['abcd', 'efghi']
res = res and split(u'a//b//c//d', u'//') == [u'a', u'b', u'c', u'd']
res = res and split(u'endcase test', u'test') == [u'endcase ', u'']
res = res and rsplit('a|b|c|d', '|', 2) == ['a|b', 'c', 'd']
res = res and rsplit('a//b//c//d', '//') == ['a', 'b', 'c', 'd']
res = res and rsplit(u'a|b|c|d', u'|') == [u'a', u'b', u'c', u'd']
res = res and rsplit(u'a|b|c|d', u'|', 2) == [u'a|b', u'c', u'd']
res = res and rsplit(u'a//b//c//d', u'//') == [u'a', u'b', u'c', u'd']
return res
def descr_expandtabs(self, space, tabsize=8):
value = self._val(space)
if not value:
return self._empty()
if self._use_rstr_ops(space, self):
splitted = value.split(self._chr('\t'))
else:
splitted = split(value, self._chr('\t'))
try:
ovfcheck(len(splitted) * tabsize)
except OverflowError:
raise oefmt(space.w_OverflowError, "new string is too long")
expanded = oldtoken = splitted.pop(0)
for token in splitted:
expanded += self._multi_chr(self._chr(' ')) * self._tabindent(oldtoken,
tabsize) + token
oldtoken = token
return self._new(expanded)
def _split(self, splitter, splits=-1):
return [StrObject(s) for s in split(self._s, splitter, splits)]
def test_split_None():
assert split("") == []
assert split(" a\ta\na b") == ["a", "a", "a", "b"]
assert split(" a a ", maxsplit=1) == ["a", "a "]
def split(self, splitter):
return [StrObject(s) for s in split(self._s, splitter)]
def test_split_None():
assert split("") == []
assert split(' a\ta\na b') == ['a', 'a', 'a', 'b']
assert split(" a a ", maxsplit=1) == ['a', 'a ']
def test_split_utf8():
assert split('', 'a', isutf8=1) == ['']
assert split('baba', 'a', isutf8=1) == ['b', 'b', '']
assert split('b b', isutf8=1) == ['b', 'b']
assert split('b\xe1\x9a\x80b', isutf8=1) == ['b', 'b']
def split(self, splitter, splits=-1):
if splits == -1:
return [BytesObject(s) for s in split(self._bs, splitter)]
else:
return [BytesObject(s) for s in split(self._bs, splitter, splits)]
def method_split(self, space, w_sep=None, limit=0):
if w_sep is None:
res_w = []
i = 0
limit -= 1
s = space.str_w(self)
while True:
while i < len(s):
if not s[i].isspace():
break
i += 1
else:
break
if limit == 0:
j = len(s)
else:
j = i + 1
while j < len(s) and not s[j].isspace():
j += 1
limit -= 1
res_w.append(space.newstr_fromstr(s[i:j]))
i = j + 1
return space.newarray(res_w)
elif space.is_kind_of(w_sep, space.w_string):
sep = space.str_w(w_sep)
return space.newarray([
space.newstr_fromstr(s) for s in split(space.str_w(self), sep, limit - 1)
])
elif space.is_kind_of(w_sep, space.w_regexp):
results_w = []
n = 0
last = 0
string = space.str_w(self)
ctx = w_sep.make_ctx(string)
w_match = w_sep.get_match_result(space, ctx, found=True)
while limit <= 0 or n + 1 < limit:
if not self.search_context(space, ctx):
break
elif ctx.match_start == ctx.match_end:
if ctx.match_start == ctx.end:
break
results_w.append(space.newstr_fromstr(string[last]))
last = ctx.match_end + 1
else:
results_w.append(space.newstr_fromstr(string[last:ctx.match_start]))
for num in xrange(1, w_match.size(), 1):
begin, end = w_match.get_span(num)
begin += last
end += last
assert begin >= 0
assert end >= 0
results_w.append(space.newstr_fromstr(string[begin:end]))
last = ctx.match_end
n += 1
ctx.reset(last)
if len(string) > last:
results_w.append(space.newstr_fromstr(string[last:]))
if limit < 0 or len(results_w) < limit:
results_w.append(space.newstr_fromstr(""))
return space.newarray(results_w)
else:
raise space.error(
space.w_TypeError,
"wrong argument type %s (expected Regexp)" %
space.obj_to_s(space.getclass(w_sep))
)
def split(a, b):
affirm(rt.count(b) > 0, u"separator can't be empty")
v = rt.vector()
for s in rstring.split(rt.name(a), rt.name(b)):
v = rt.conj(v, rt.wrap(s))
return v
def _split(self, splitter, splits):
return [BytesObject(s) for s in split(self._bs, splitter, splits)]
def method_split(self, space, w_sep=None, limit=0):
if w_sep is None:
res_w = []
i = 0
limit -= 1
s = space.str_w(self)
while True:
while i < len(s):
if not s[i].isspace():
break
i += 1
else:
break
if limit == 0:
j = len(s)
else:
j = i + 1
while j < len(s) and not s[j].isspace():
j += 1
limit -= 1
res_w.append(space.newstr_fromstr(s[i:j]))
i = j + 1
return space.newarray(res_w)
elif space.is_kind_of(w_sep, space.w_string):
sep = space.str_w(w_sep)
if sep:
return space.newarray([
space.newstr_fromstr(s)
for s in split(space.str_w(self), sep, limit - 1)
])
else:
if limit:
raise space.error(
space.w_NotImplementedError,
"String#split with empty string and limit")
return space.newarray([
space.newstr_fromstr(
self.strategy.getitem(self.str_storage, i))
for i in xrange(self.length())
])
elif space.is_kind_of(w_sep, space.w_regexp):
results_w = []
n = 0
last = 0
string = space.str_w(self)
ctx = w_sep.make_ctx(string)
w_match = w_sep.get_match_result(space, ctx, string, found=True)
while limit <= 0 or n + 1 < limit:
if not self.search_context(space, ctx):
break
elif ctx.match_start == ctx.match_end:
if ctx.match_start == ctx.end:
break
results_w.append(space.newstr_fromstr(string[last]))
last = ctx.match_end + 1
else:
results_w.append(
space.newstr_fromstr(string[last:ctx.match_start]))
for num in xrange(1, w_match.size(), 1):
begin, end = w_match.get_span(num)
begin += last
end += last
if begin >= 0 and end >= 0:
results_w.append(
space.newstr_fromstr(string[begin:end]))
last = ctx.match_end
n += 1
ctx.reset(last)
if len(string) > last:
results_w.append(space.newstr_fromstr(string[last:]))
if limit < 0 or len(results_w) < limit:
results_w.append(space.newstr_fromstr(""))
return space.newarray(results_w)
else:
raise space.error(
space.w_TypeError, "wrong argument type %s (expected Regexp)" %
(space.obj_to_s(space.getclass(w_sep))))
def split(self, splitter):
return [BytesObject(s) for s in split(self._bs, splitter)]
def split(self, splitter):
return [StrObject(s) for s in split(self._s, splitter)]
def str_split__String_None_ANY(space, w_self, w_none, w_maxsplit=-1):
maxsplit = space.int_w(w_maxsplit)
value = w_self._value
res = split(value, maxsplit=maxsplit)
return space.newlist_str(res)
def _split(self, splitter, splits=-1):
return [StrObject(s) for s in split(self._s, splitter, splits)]
def test_split_None():
assert split("") == []
assert split(' a\ta\na b') == ['a', 'a', 'a', 'b']
assert split(" a a ", maxsplit=1) == ['a', 'a ']
def split(a, b):
affirm(rt.count(b) > 0, u"separator can't be empty")
v = rt.vector()
for s in rstring.split(rt.name(a), rt.name(b)):
v = rt.conj(v, rt.wrap(s))
return v
def _split(self, splitter, splits):
return [BytesObject(s) for s in split(self._bs, splitter, splits)]
def split(self, splitter, splits=-1):
if splits == -1:
return [StrObject(s) for s in split(self._s, splitter)]
else:
return [StrObject(s) for s in split(self._s, splitter, splits)]
def String_split(self, sep, maxsplit):
out = []
m = maxsplit.value if maxsplit else -1
for s in split(self.string, sep.string, m):
out.append(String(s))
return space.List(out)
def split(self, splitter):
return [BytesObject(s) for s in split(self._bs, splitter)]
