Python sys.intern() Examples

def load_build(self):
        stack = self.stack
        state = stack.pop()
        inst = stack[-1]
        setstate = getattr(inst, "__setstate__", None)
        if setstate is not None:
            setstate(state)
            return
        slotstate = None
        if isinstance(state, tuple) and len(state) == 2:
            state, slotstate = state
        if state:
            inst_dict = inst.__dict__
            intern = sys.intern
            for k, v in state.items():
                if type(k) is str:
                    inst_dict[intern(k)] = v
                else:
                    inst_dict[k] = v
        if slotstate:
            for k, v in slotstate.items():
                setattr(inst, k, v) 

def test_removed_3_0(self):
        """Test for names removed in 3.0."""
        before, after = before_and_after((3, 0))
        for name, suggs in {
                'StandardError': [STDERR_REMOVED_MSG],
                'apply': [APPLY_REMOVED_MSG],
                'basestring': [],
                'buffer': [BUFFER_REMOVED_MSG],
                'cmp': [CMP_REMOVED_MSG],
                'coerce': [],
                'execfile': [],
                'file': ["'filter' (builtin)"],
                'intern': ["'iter' (builtin)", "'sys.intern'"],
                'long': [LONG_REMOVED_MSG],
                'raw_input': ["'input' (builtin)"],
                'reduce': ["'reduce' from functools (not imported)"],
                'reload': [RELOAD_REMOVED_MSG],
                'unichr': [],
                'unicode': ["'code' (local)"],
                'xrange': ["'range' (builtin)"],
                }.items():
            self.runs(name, before)
            self.throws(name, NAMEERROR, suggs, after) 

def load_build(self):
        stack = self.stack
        state = stack.pop()
        inst = stack[-1]
        setstate = getattr(inst, "__setstate__", None)
        if setstate is not None:
            setstate(state)
            return
        slotstate = None
        if isinstance(state, tuple) and len(state) == 2:
            state, slotstate = state
        if state:
            inst_dict = inst.__dict__
            intern = sys.intern
            for k, v in state.items():
                if type(k) is str:
                    inst_dict[intern(k)] = v
                else:
                    inst_dict[k] = v
        if slotstate:
            for k, v in slotstate.items():
                setattr(inst, k, v) 

def silent_intern(x):
    """
    Perform sys.intern() on the passed argument and return the result.
    If the input is ineligible (e.g. a unicode string) the original argument is
    returned and no exception is thrown.
    """
    try:
        return sys.intern(x)
    except TypeError:
        return x



# From Dinu C. Gherman,
# Python Cookbook, second edition, recipe 6.17, p. 277.
# Also:
# http://aspn.activestate.com/ASPN/Cookbook/Python/Recipe/68205
# ASPN: Python Cookbook: Null Object Design Pattern

#TODO??? class Null(object): 

def load_build(self):
        stack = self.stack
        state = stack.pop()
        inst = stack[-1]
        setstate = getattr(inst, "__setstate__", None)
        if setstate is not None:
            setstate(state)
            return
        slotstate = None
        if isinstance(state, tuple) and len(state) == 2:
            state, slotstate = state
        if state:
            inst_dict = inst.__dict__
            intern = sys.intern
            for k, v in state.items():
                if type(k) is str:
                    inst_dict[intern(k)] = v
                else:
                    inst_dict[k] = v
        if slotstate:
            for k, v in slotstate.items():
                setattr(inst, k, v) 

def readwarnings(warningsfile):
    prog = re.compile(PATTERN)
    try:
        f = open(warningsfile)
    except IOError as msg:
        sys.stderr.write("can't open: %s\n" % msg)
        return
    warnings = {}
    while 1:
        line = f.readline()
        if not line:
            break
        m = prog.match(line)
        if not m:
            if line.find("division") >= 0:
                sys.stderr.write("Warning: ignored input " + line)
            continue
        filename, lineno, what = m.groups()
        list = warnings.get(filename)
        if list is None:
            warnings[filename] = list = []
        list.append((int(lineno), sys.intern(what)))
    f.close()
    return warnings 

def MD5collect(signatures):
    """
    Collects a list of signatures into an aggregate signature.

    signatures - a list of signatures
    returns - the aggregate signature
    """
    if len(signatures) == 1:
        return signatures[0]
    else:
        return MD5signature(string.join(signatures, ', '))



# Wrap the intern() function so it doesn't throw exceptions if ineligible
# arguments are passed. The intern() function was moved into the sys module in
# Python 3. 

def silent_intern(x):
    """
    Perform intern() on the passed argument and return the result.
    If the input is ineligible (e.g. a unicode string) the original argument is
    returned and no exception is thrown.
    """
    try:
        return sys.intern(x)
    except TypeError:
        return x



# From Dinu C. Gherman,
# Python Cookbook, second edition, recipe 6.17, p. 277.
# Also:
# http://aspn.activestate.com/ASPN/Cookbook/Python/Recipe/68205
# ASPN: Python Cookbook: Null Object Design Pattern

# TODO(1.5):
#class Null(object): 

def InternObject(obj):
    """Copies and interns strings in a recursive object."""
    obj_cls = obj.__class__
    if obj_cls is str:
        return sys.intern(obj)

    if obj_cls is str:
        return sys.intern(str(obj))

    if obj_cls is dict:
        result = {}
        for k, v in list(obj.items()):
            k = InternObject(k)
            v = InternObject(v)
            result[k] = v

        return result

    if obj_cls is list:
        return [InternObject(x) for x in obj]

    return obj 

def silent_intern(x):
    """
    Perform sys.intern() on the passed argument and return the result.
    If the input is ineligible (e.g. a unicode string) the original argument is
    returned and no exception is thrown.
    """
    try:
        return sys.intern(x)
    except TypeError:
        return x



# From Dinu C. Gherman,
# Python Cookbook, second edition, recipe 6.17, p. 277.
# Also:
# http://aspn.activestate.com/ASPN/Cookbook/Python/Recipe/68205
# ASPN: Python Cookbook: Null Object Design Pattern

#TODO??? class Null(object): 

def read_phones(path, dialect, sr = None):
    output = []
    with open(path,'r') as file_handle:
        if dialect == 'buckeye':
            header_pattern = re.compile("#\r{0,1}\n")
            line_pattern = re.compile("\s+\d{3}\s+")
            label_pattern = re.compile(" {0,1};| {0,1}\+")
            f = header_pattern.split(file_handle.read())[1]
            flist = f.splitlines()
            begin = 0.0
            for l in flist:
                line = line_pattern.split(l.strip())
                end = float(line[0])
                label = sys.intern(label_pattern.split(line[1])[0])
                output.append(BaseAnnotation(label, begin, end))
                begin = end

        else:
            raise(NotImplementedError)
    return output 

def test_prefix_preservation(self):
        b = """x =   intern(  a  )"""
        a = """import sys\nx =   sys.intern(  a  )"""
        self.check(b, a)

        b = """y = intern("b" # test
              )"""
        a = """import sys\ny = sys.intern("b" # test
              )"""
        self.check(b, a)

        b = """z = intern(a+b+c.d,   )"""
        a = """import sys\nz = sys.intern(a+b+c.d,   )"""
        self.check(b, a) 

def __setitem__(self, key, value):
        """If key is in table, update it. Otherwise, extend the array to make
        room. This uses additive resizing not multiplicative, since the number
        of keys is not likely to change frequently during a run, so do not abuse
        it.
        Raises an error if you try to change the type of the value stored for
        that key--if you need to do this, you must delete the key first.
        """
        val_type = type(value)
        if 'Tensor' in str(val_type):
            self.tensors[key] = value
            return
        if val_type not in self.types:
            raise TypeError('SharedTable does not support type ' + str(type(value)))
        if val_type == str:
            value = sys.intern(value)
        if key in self.idx:
            idx, typ = self.idx[key]
            if typ != val_type:
                raise TypeError(
                    (
                        'Cannot change stored type for {key} from '
                        + '{v1} to {v2}. You need to del the key first'
                        + ' if you need to change value types.'
                    ).format(key=key, v1=typ, v2=val_type)
                )
            self.arrays[typ][idx] = value
        else:
            raise KeyError(
                'Cannot add more keys to the shared table as '
                'they will not be synced across processes.'
            ) 

def parse_parts(self, parts):
        parsed = []
        sep = self.sep
        altsep = self.altsep
        drv = root = ''
        it = reversed(parts)
        for part in it:
            if not part:
                continue
            if altsep:
                part = part.replace(altsep, sep)
            drv, root, rel = self.splitroot(part)
            if sep in rel:
                for x in reversed(rel.split(sep)):
                    if x and x != '.':
                        parsed.append(sys.intern(x))
            else:
                if rel and rel != '.':
                    parsed.append(sys.intern(rel))
            if drv or root:
                if not drv:
                    # If no drive is present, try to find one in the previous
                    # parts. This makes the result of parsing e.g.
                    # ("C:", "/", "a") reasonably intuitive.
                    for part in it:
                        if not part:
                            continue
                        if altsep:
                            part = part.replace(altsep, sep)
                        drv = self.splitroot(part)[0]
                        if drv:
                            break
                break
        if drv or root:
            parsed.append(drv + root)
        parsed.reverse()
        return drv, root, parsed 

def test_unchanged(self):
        s = """intern(a=1)"""
        self.unchanged(s)

        s = """intern(f, g)"""
        self.unchanged(s)

        s = """intern(*h)"""
        self.unchanged(s)

        s = """intern(**i)"""
        self.unchanged(s)

        s = """intern()"""
        self.unchanged(s) 

def __init__(self, nnbrs, min_nbrs=1, min_sim=0, center=True, aggregate='weighted-average'):
        self.nnbrs = nnbrs
        self.min_nbrs = min_nbrs
        self.min_sim = min_sim
        self.center = center
        self.aggregate = intern(aggregate) 

def __setstate__(self, state):
        self.__dict__.update(state)
        self.aggregate = intern(self.aggregate)
        mkl = matrix.mkl_ops()
        self._mkl_m_ = mkl.SparseM.from_csr(self.rating_matrix_) if mkl else None 

def parse_parts(self, parts):
        if _py2:
            parts = _py2_fsencode(parts)
        parsed = []
        sep = self.sep
        altsep = self.altsep
        drv = root = ''
        it = reversed(parts)
        for part in it:
            if not part:
                continue
            if altsep:
                part = part.replace(altsep, sep)
            drv, root, rel = self.splitroot(part)
            if sep in rel:
                for x in reversed(rel.split(sep)):
                    if x and x != '.':
                        parsed.append(intern(x))
            else:
                if rel and rel != '.':
                    parsed.append(intern(rel))
            if drv or root:
                if not drv:
                    # If no drive is present, try to find one in the previous
                    # parts. This makes the result of parsing e.g.
                    # ("C:", "/", "a") reasonably intuitive.
                    for part in it:
                        drv = self.splitroot(part)[0]
                        if drv:
                            break
                break
        if drv or root:
            parsed.append(drv + root)
        parsed.reverse()
        return drv, root, parsed 

def parse_parts(self, parts):
        if six.PY2:
            parts = _py2_fsencode(parts)
        parsed = []
        sep = self.sep
        altsep = self.altsep
        drv = root = ''
        it = reversed(parts)
        for part in it:
            if not part:
                continue
            if altsep:
                part = part.replace(altsep, sep)
            drv, root, rel = self.splitroot(part)
            if sep in rel:
                for x in reversed(rel.split(sep)):
                    if x and x != '.':
                        parsed.append(intern(x))
            else:
                if rel and rel != '.':
                    parsed.append(intern(rel))
            if drv or root:
                if not drv:
                    # If no drive is present, try to find one in the previous
                    # parts. This makes the result of parsing e.g.
                    # ("C:", "/", "a") reasonably intuitive.
                    for part in it:
                        if not part:
                            continue
                        if altsep:
                            part = part.replace(altsep, sep)
                        drv = self.splitroot(part)[0]
                        if drv:
                            break
                break
        if drv or root:
            parsed.append(drv + root)
        parsed.reverse()
        return drv, root, parsed 

def test_unchanged(self):
        s = """intern(a=1)"""
        self.unchanged(s)

        s = """intern(f, g)"""
        self.unchanged(s)

        s = """intern(*h)"""
        self.unchanged(s)

        s = """intern(**i)"""
        self.unchanged(s)

        s = """intern()"""
        self.unchanged(s) 

def __init__(self, opt, data_loader=None, cands=None, shared=None, **kwargs):
        # self.data is a list of episodes
        # each episode is a tuple of entries
        # each entry is a tuple of values for the action/observation table
        if shared:
            self.image_loader = shared.get('image_loader', None)
            self.data = shared.get('data', [])
            self.cands = shared.get('cands', None)
        else:
            self.image_loader = ImageLoader(opt)
            self.data = []
            self._load(data_loader, opt['datafile'])
            self.cands = None if cands is None else set(sys.intern(c) for c in cands)
        self.addedCands = []
        self.copied_cands = False 

def __setitem__(self, key, value):
        """
        If key is in table, update it. Otherwise, extend the array to make room.

        This uses additive resizing not multiplicative, since the number
        of keys is not likely to change frequently during a run, so do not
        abuse it.

        Raises an error if you try to change the type of the value stored for
        that key -- if you need to do this, you must delete the key first.
        """
        val_type = type(value)
        if 'Tensor' in str(val_type):
            self.tensors[key] = value
            return
        if val_type not in self.types:
            raise TypeError('SharedTable does not support type ' + str(type(value)))
        if val_type == str:
            value = sys.intern(value)
        if key in self.idx:
            idx, typ = self.idx[key]
            if typ != val_type:
                raise TypeError(
                    (
                        'Cannot change stored type for {key} from '
                        + '{v1} to {v2}. You need to del the key first'
                        + ' if you need to change value types.'
                    ).format(key=key, v1=typ, v2=val_type)
                )
            self.arrays[typ][idx] = value
        else:
            raise KeyError(
                'Cannot add more keys to the shared table as '
                'they will not be synced across processes.'
            ) 

def test_unchanged(self):
        s = """intern(a=1)"""
        self.unchanged(s)

        s = """intern(f, g)"""
        self.unchanged(s)

        s = """intern(*h)"""
        self.unchanged(s)

        s = """intern(**i)"""
        self.unchanged(s)

        s = """intern()"""
        self.unchanged(s) 

def test(self):
        b = """x = intern(a)"""
        a = """import sys\nx = sys.intern(a)"""
        self.check(b, a)

        b = """z = intern(a+b+c.d,)"""
        a = """import sys\nz = sys.intern(a+b+c.d,)"""
        self.check(b, a)

        b = """intern("y%s" % 5).replace("y", "")"""
        a = """import sys\nsys.intern("y%s" % 5).replace("y", "")"""
        self.check(b, a)

    # These should not be refactored 

def test_prefix_preservation(self):
        b = """x =   intern(  a  )"""
        a = """import sys\nx =   sys.intern(  a  )"""
        self.check(b, a)

        b = """y = intern("b" # test
              )"""
        a = """import sys\ny = sys.intern("b" # test
              )"""
        self.check(b, a)

        b = """z = intern(a+b+c.d,   )"""
        a = """import sys\nz = sys.intern(a+b+c.d,   )"""
        self.check(b, a) 

def parse_parts(self, parts):
        parsed = []
        sep = self.sep
        altsep = self.altsep
        drv = root = ''
        it = reversed(parts)
        for part in it:
            if not part:
                continue
            if altsep:
                part = part.replace(altsep, sep)
            drv, root, rel = self.splitroot(part)
            if sep in rel:
                for x in reversed(rel.split(sep)):
                    if x and x != '.':
                        parsed.append(sys.intern(x))
            else:
                if rel and rel != '.':
                    parsed.append(sys.intern(rel))
            if drv or root:
                if not drv:
                    # If no drive is present, try to find one in the previous
                    # parts. This makes the result of parsing e.g.
                    # ("C:", "/", "a") reasonably intuitive.
                    for part in it:
                        if not part:
                            continue
                        if altsep:
                            part = part.replace(altsep, sep)
                        drv = self.splitroot(part)[0]
                        if drv:
                            break
                break
        if drv or root:
            parsed.append(drv + root)
        parsed.reverse()
        return drv, root, parsed 

def parse_parts(self, parts):
        if six.PY2:
            parts = _py2_fsencode(parts)
        parsed = []
        sep = self.sep
        altsep = self.altsep
        drv = root = ''
        it = reversed(parts)
        for part in it:
            if not part:
                continue
            if altsep:
                part = part.replace(altsep, sep)
            drv, root, rel = self.splitroot(part)
            if sep in rel:
                for x in reversed(rel.split(sep)):
                    if x and x != '.':
                        parsed.append(intern(x))
            else:
                if rel and rel != '.':
                    parsed.append(intern(rel))
            if drv or root:
                if not drv:
                    # If no drive is present, try to find one in the previous
                    # parts. This makes the result of parsing e.g.
                    # ("C:", "/", "a") reasonably intuitive.
                    for part in it:
                        if not part:
                            continue
                        if altsep:
                            part = part.replace(altsep, sep)
                        drv = self.splitroot(part)[0]
                        if drv:
                            break
                break
        if drv or root:
            parsed.append(drv + root)
        parsed.reverse()
        return drv, root, parsed 

def testNoIntern(self):
        s = marshal.loads(marshal.dumps(self.strobj, 2))
        self.assertEqual(s, self.strobj)
        self.assertNotEqual(id(s), id(self.strobj))
        s2 = sys.intern(s)
        self.assertNotEqual(id(s2), id(s)) 

def testIntern(self):
        s = marshal.loads(marshal.dumps(self.strobj))
        self.assertEqual(s, self.strobj)
        self.assertEqual(id(s), id(self.strobj))
        s2 = sys.intern(s)
        self.assertEqual(id(s2), id(s)) 

def parse_parts(self, parts):
        parsed = []
        sep = self.sep
        altsep = self.altsep
        drv = root = ''
        it = reversed(parts)
        for part in it:
            if not part:
                continue
            if altsep:
                part = part.replace(altsep, sep)
            drv, root, rel = self.splitroot(part)
            if sep in rel:
                for x in reversed(rel.split(sep)):
                    if x and x != '.':
                        parsed.append(sys.intern(x))
            else:
                if rel and rel != '.':
                    parsed.append(sys.intern(rel))
            if drv or root:
                if not drv:
                    # If no drive is present, try to find one in the previous
                    # parts. This makes the result of parsing e.g.
                    # ("C:", "/", "a") reasonably intuitive.
                    for part in it:
                        if not part:
                            continue
                        if altsep:
                            part = part.replace(altsep, sep)
                        drv = self.splitroot(part)[0]
                        if drv:
                            break
                break
        if drv or root:
            parsed.append(drv + root)
        parsed.reverse()
        return drv, root, parsed