def reset(self):
"""Clear collected data, and prepare to collect more."""
# A dictionary mapping filenames to dicts with line number keys,
# or mapping filenames to dicts with line number pairs as keys.
self.data = {}
self.plugin_data = {}
# A cache of the results from should_trace, the decision about whether
# to trace execution in a file. A dict of filename to (filename or
# None).
if env.PYPY:
import __pypy__ # pylint: disable=import-error
# Alex Gaynor said:
# should_trace_cache is a strictly growing key: once a key is in
# it, it never changes. Further, the keys used to access it are
# generally constant, given sufficient context. That is to say, at
# any given point _trace() is called, pypy is able to know the key.
# This is because the key is determined by the physical source code
# line, and that's invariant with the call site.
#
# This property of a dict with immutable keys, combined with
# call-site-constant keys is a match for PyPy's module dict,
# which is optimized for such workloads.
#
# This gives a 20% benefit on the workload described at
# https://bitbucket.org/pypy/pypy/issue/1871/10x-slower-than-cpython-under-coverage
self.should_trace_cache = __pypy__.newdict("module")
else:
self.should_trace_cache = {}
# Our active Tracers.
self.tracers = []
def reset(self):
"""Clear collected data, and prepare to collect more."""
# A dictionary mapping filenames to dicts with line number keys,
# or mapping filenames to dicts with line number pairs as keys.
self.data = {}
self.plugin_data = {}
# A cache of the results from should_trace, the decision about whether
# to trace execution in a file. A dict of filename to (filename or
# None).
if env.PYPY:
import __pypy__ # pylint: disable=import-error
# Alex Gaynor said:
# should_trace_cache is a strictly growing key: once a key is in
# it, it never changes. Further, the keys used to access it are
# generally constant, given sufficient context. That is to say, at
# any given point _trace() is called, pypy is able to know the key.
# This is because the key is determined by the physical source code
# line, and that's invariant with the call site.
#
# This property of a dict with immutable keys, combined with
# call-site-constant keys is a match for PyPy's module dict,
# which is optimized for such workloads.
#
# This gives a 20% benefit on the workload described at
# https://bitbucket.org/pypy/pypy/issue/1871/10x-slower-than-cpython-under-coverage
self.should_trace_cache = __pypy__.newdict("module")
else:
self.should_trace_cache = {}
# Our active Tracers.
self.tracers = []
def test_bug_materialize_huge_dict(self):
import __pypy__
d = __pypy__.newdict("instance")
for i in range(100):
d[str(i)] = i
assert len(d) == 100
for key in d:
assert d[key] == int(key)
def reset(self):
"""Clear collected data, and prepare to collect more."""
# A dictionary mapping file names to dicts with line number keys (if not
# branch coverage), or mapping file names to dicts with line number
# pairs as keys (if branch coverage).
self.data = {}
# A dict mapping contexts to data dictionaries.
self.contexts = {}
self.contexts[None] = self.data
# A dictionary mapping file names to file tracer plugin names that will
# handle them.
self.file_tracers = {}
# The .should_trace_cache attribute is a cache from file names to
# coverage.FileDisposition objects, or None. When a file is first
# considered for tracing, a FileDisposition is obtained from
# Coverage.should_trace. Its .trace attribute indicates whether the
# file should be traced or not. If it should be, a plugin with dynamic
# file names can decide not to trace it based on the dynamic file name
# being excluded by the inclusion rules, in which case the
# FileDisposition will be replaced by None in the cache.
if env.PYPY:
import __pypy__ # pylint: disable=import-error
# Alex Gaynor said:
# should_trace_cache is a strictly growing key: once a key is in
# it, it never changes. Further, the keys used to access it are
# generally constant, given sufficient context. That is to say, at
# any given point _trace() is called, pypy is able to know the key.
# This is because the key is determined by the physical source code
# line, and that's invariant with the call site.
#
# This property of a dict with immutable keys, combined with
# call-site-constant keys is a match for PyPy's module dict,
# which is optimized for such workloads.
#
# This gives a 20% benefit on the workload described at
# https://bitbucket.org/pypy/pypy/issue/1871/10x-slower-than-cpython-under-coverage
self.should_trace_cache = __pypy__.newdict("module")
else:
self.should_trace_cache = {}
# Our active Tracers.
self.tracers = []
self._clear_data()
def reset(self):
"""Clear collected data, and prepare to collect more."""
# A dictionary mapping file names to dicts with line number keys (if not
# branch coverage), or mapping file names to dicts with line number
# pairs as keys (if branch coverage).
self.data = {}
# A dict mapping contexts to data dictionaries.
self.contexts = {}
self.contexts[None] = self.data
# A dictionary mapping file names to file tracer plugin names that will
# handle them.
self.file_tracers = {}
# The .should_trace_cache attribute is a cache from file names to
# coverage.FileDisposition objects, or None. When a file is first
# considered for tracing, a FileDisposition is obtained from
# Coverage.should_trace. Its .trace attribute indicates whether the
# file should be traced or not. If it should be, a plugin with dynamic
# file names can decide not to trace it based on the dynamic file name
# being excluded by the inclusion rules, in which case the
# FileDisposition will be replaced by None in the cache.
if env.PYPY:
import __pypy__ # pylint: disable=import-error
# Alex Gaynor said:
# should_trace_cache is a strictly growing key: once a key is in
# it, it never changes. Further, the keys used to access it are
# generally constant, given sufficient context. That is to say, at
# any given point _trace() is called, pypy is able to know the key.
# This is because the key is determined by the physical source code
# line, and that's invariant with the call site.
#
# This property of a dict with immutable keys, combined with
# call-site-constant keys is a match for PyPy's module dict,
# which is optimized for such workloads.
#
# This gives a 20% benefit on the workload described at
# https://bitbucket.org/pypy/pypy/issue/1871/10x-slower-than-cpython-under-coverage
self.should_trace_cache = __pypy__.newdict("module")
else:
self.should_trace_cache = {}
# Our active Tracers.
self.tracers = []
self._clear_data()
def _normalize_dict(_dict):
# Credit: Lin Cheng
# return the original dictionary if not running on PyPy
try:
from __pypy__ import strategy, newdict
except Exception:
return _dict
# return the original dictionary if already using ModuleDictStrategy
if strategy(_dict) == "ModuleDictStrategy":
return _dict
# create a new module dict
new_dict = newdict("module")
# copy over entries
for key, value in _dict.items():
new_dict[key] = value
return new_dict
def __init__(self):
self.flags = 0
self.open = []
self.groups = 1
self.groupdict = newdict("module")
self.lookbehind = 0
def namedtuple(typename, field_names, verbose=False, rename=False):
"""Returns a new subclass of tuple with named fields.
>>> Point = namedtuple('Point', ['x', 'y'])
>>> Point.__doc__ # docstring for the new class
'Point(x, y)'
>>> p = Point(11, y=22) # instantiate with positional args or keywords
>>> p[0] + p[1] # indexable like a plain tuple
33
>>> x, y = p # unpack like a regular tuple
>>> x, y
(11, 22)
>>> p.x + p.y # fields also accessable by name
33
>>> d = p._asdict() # convert to a dictionary
>>> d['x']
11
>>> Point(**d) # convert from a dictionary
Point(x=11, y=22)
>>> p._replace(x=100) # _replace() is like str.replace() but targets named fields
Point(x=100, y=22)
"""
# Validate the field names. At the user's option, either generate an error
# message or automatically replace the field name with a valid name.
if isinstance(field_names, basestring):
field_names = field_names.replace(',', ' ').split()
field_names = map(str, field_names)
if rename:
seen = set()
for index, name in enumerate(field_names):
if (not all(c.isalnum() or c=='_' for c in name)
or _iskeyword(name)
or not name
or name[0].isdigit()
or name.startswith('_')
or name in seen):
field_names[index] = '_%d' % index
seen.add(name)
for name in [typename] + field_names:
if not all(c.isalnum() or c=='_' for c in name):
raise ValueError('Type names and field names can only contain '
'alphanumeric characters and underscores: %r' % name)
if _iskeyword(name):
raise ValueError('Type names and field names cannot be a '
'keyword: %r' % name)
if name[0].isdigit():
raise ValueError('Type names and field names cannot start with '
'a number: %r' % name)
seen = set()
for name in field_names:
if name.startswith('_') and not rename:
raise ValueError('Field names cannot start with an underscore: '
'%r' % name)
if name in seen:
raise ValueError('Encountered duplicate field name: %r' % name)
seen.add(name)
# Fill-in the class template
class_definition = _class_template.format(
typename = typename,
field_names = tuple(field_names),
num_fields = len(field_names),
arg_list = repr(tuple(field_names)).replace("'", "")[1:-1],
repr_fmt = ', '.join(_repr_template.format(name=name)
for name in field_names),
field_defs = '\n'.join(_field_template.format(index=index, name=name)
for index, name in enumerate(field_names))
)
if verbose:
print class_definition
# Execute the template string in a temporary namespace and support
# tracing utilities by setting a value for frame.f_globals['__name__']
namespace = newdict('module')
namespace['__name__'] = 'namedtuple_%s' % typename
namespace['OrderedDict'] = OrderedDict
namespace['_property'] = property
namespace['_tuple'] = tuple
try:
exec class_definition in namespace
except SyntaxError as e:
raise SyntaxError(e.message + ':\n' + class_definition)
result = namespace[typename]
# For pickling to work, the __module__ variable needs to be set to the frame
# where the named tuple is created. Bypass this step in environments where
# sys._getframe is not defined (Jython for example) or sys._getframe is not
# defined for arguments greater than 0 (IronPython).
try:
result.__module__ = _sys._getframe(1).f_globals.get('__name__', '__main__')
except (AttributeError, ValueError):
pass
return result
def namedtuple(typename, field_names, verbose=False, rename=False):
"""Returns a new subclass of tuple with named fields.
>>> Point = namedtuple('Point', ['x', 'y'])
>>> Point.__doc__ # docstring for the new class
'Point(x, y)'
>>> p = Point(11, y=22) # instantiate with positional args or keywords
>>> p[0] + p[1] # indexable like a plain tuple
33
>>> x, y = p # unpack like a regular tuple
>>> x, y
(11, 22)
>>> p.x + p.y # fields also accessable by name
33
>>> d = p._asdict() # convert to a dictionary
>>> d['x']
11
>>> Point(**d) # convert from a dictionary
Point(x=11, y=22)
>>> p._replace(x=100) # _replace() is like str.replace() but targets named fields
Point(x=100, y=22)
"""
# Validate the field names. At the user's option, either generate an error
# message or automatically replace the field name with a valid name.
if isinstance(field_names, basestring):
field_names = field_names.replace(',', ' ').split()
field_names = map(str, field_names)
typename = str(typename)
if rename:
seen = set()
for index, name in enumerate(field_names):
if (not all(c.isalnum() or c=='_' for c in name)
or _iskeyword(name)
or not name
or name[0].isdigit()
or name.startswith('_')
or name in seen):
field_names[index] = '_%d' % index
seen.add(name)
for name in [typename] + field_names:
if type(name) != str:
raise TypeError('Type names and field names must be strings')
if not all(c.isalnum() or c=='_' for c in name):
raise ValueError('Type names and field names can only contain '
'alphanumeric characters and underscores: %r' % name)
if _iskeyword(name):
raise ValueError('Type names and field names cannot be a '
'keyword: %r' % name)
if name[0].isdigit():
raise ValueError('Type names and field names cannot start with '
'a number: %r' % name)
seen = set()
for name in field_names:
if name.startswith('_') and not rename:
raise ValueError('Field names cannot start with an underscore: '
'%r' % name)
if name in seen:
raise ValueError('Encountered duplicate field name: %r' % name)
seen.add(name)
# Fill-in the class template
class_definition = _class_template.format(
typename = typename,
field_names = tuple(field_names),
num_fields = len(field_names),
arg_list = repr(tuple(field_names)).replace("'", "")[1:-1],
repr_fmt = ', '.join(_repr_template.format(name=name)
for name in field_names),
field_defs = '\n'.join(_field_template.format(index=index, name=name)
for index, name in enumerate(field_names))
)
if verbose:
print class_definition
# Execute the template string in a temporary namespace and support
# tracing utilities by setting a value for frame.f_globals['__name__']
namespace = newdict('module')
namespace['__name__'] = 'namedtuple_%s' % typename
namespace['OrderedDict'] = OrderedDict
namespace['_property'] = property
namespace['_tuple'] = tuple
try:
exec class_definition in namespace
except SyntaxError as e:
raise SyntaxError(e.message + ':\n' + class_definition)
result = namespace[typename]
# For pickling to work, the __module__ variable needs to be set to the frame
# where the named tuple is created. Bypass this step in environments where
# sys._getframe is not defined (Jython for example) or sys._getframe is not
# defined for arguments greater than 0 (IronPython).
try:
result.__module__ = _sys._getframe(1).f_globals.get('__name__', '__main__')
except (AttributeError, ValueError):
pass
return result
def __init__(self):
self.flags = 0
self.open = []
self.groups = 1
self.groupdict = newdict("module")
self.lookbehind = 0
def common_value(seq):
cv = CommonValue()
for val in seq:
cv.present(val)
if cv._value is None:
break
return cv.value
# dict optimized for small numbers of keys
if is_pypy:
from __pypy__ import newdict
create_small_dict = lambda: newdict('instance')
else:
create_small_dict = dict
### string
def simplify_whitespace(s):
return ' '.join(s.split())
_re_word_split = re.compile(r'[^a-zA-Z_]+')
def find_nonnumeric_words(s):
words = _re_word_split.split(s)
def namedtuple(typename, field_names, verbose=False, rename=False):
"""Returns a new subclass of tuple with named fields.
>>> Point = namedtuple('Point', 'x y')
>>> Point.__doc__ # docstring for the new class
'Point(x, y)'
>>> p = Point(11, y=22) # instantiate with positional args or keywords
>>> p[0] + p[1] # indexable like a plain tuple
33
>>> x, y = p # unpack like a regular tuple
>>> x, y
(11, 22)
>>> p.x + p.y # fields also accessable by name
33
>>> d = p._asdict() # convert to a dictionary
>>> d['x']
11
>>> Point(**d) # convert from a dictionary
Point(x=11, y=22)
>>> p._replace(x=100) # _replace() is like str.replace() but targets named fields
Point(x=100, y=22)
"""
# Parse and validate the field names. Validation serves two purposes,
# generating informative error messages and preventing template injection attacks.
if isinstance(field_names, basestring):
field_names = field_names.replace(',', ' ').split() # names separated by whitespace and/or commas
field_names = tuple(map(str, field_names))
if rename:
names = list(field_names)
seen = set()
for i, name in enumerate(names):
if (not all(c.isalnum() or c=='_' for c in name) or _iskeyword(name)
or not name or name[0].isdigit() or name.startswith('_')
or name in seen):
names[i] = '_%d' % i
seen.add(name)
field_names = tuple(names)
for name in (typename,) + field_names:
if not all(c.isalnum() or c=='_' for c in name):
raise ValueError('Type names and field names can only contain alphanumeric characters and underscores: %r' % name)
if _iskeyword(name):
raise ValueError('Type names and field names cannot be a keyword: %r' % name)
if name[0].isdigit():
raise ValueError('Type names and field names cannot start with a number: %r' % name)
seen_names = set()
for name in field_names:
if name.startswith('_') and not rename:
raise ValueError('Field names cannot start with an underscore: %r' % name)
if name in seen_names:
raise ValueError('Encountered duplicate field name: %r' % name)
seen_names.add(name)
# Create and fill-in the class template
numfields = len(field_names)
argtxt = repr(field_names).replace("'", "")[1:-1] # tuple repr without parens or quotes
reprtxt = ', '.join('%s=%%r' % name for name in field_names)
template = '''class %(typename)s(tuple):
'%(typename)s(%(argtxt)s)' \n
__slots__ = () \n
_fields = %(field_names)r \n
def __new__(_cls, %(argtxt)s):
'Create new instance of %(typename)s(%(argtxt)s)'
return _tuple.__new__(_cls, (%(argtxt)s)) \n
@classmethod
def _make(cls, iterable, new=tuple.__new__, len=len):
'Make a new %(typename)s object from a sequence or iterable'
result = new(cls, iterable)
if len(result) != %(numfields)d:
raise TypeError('Expected %(numfields)d arguments, got %%d' %% len(result))
return result \n
def __repr__(self):
'Return a nicely formatted representation string'
return '%(typename)s(%(reprtxt)s)' %% self \n
def _asdict(self):
'Return a new OrderedDict which maps field names to their values'
return OrderedDict(zip(self._fields, self)) \n
__dict__ = property(_asdict) \n
def _replace(_self, **kwds):
'Return a new %(typename)s object replacing specified fields with new values'
result = _self._make(map(kwds.pop, %(field_names)r, _self))
if kwds:
raise ValueError('Got unexpected field names: %%r' %% kwds.keys())
return result \n
def __getnewargs__(self):
'Return self as a plain tuple. Used by copy and pickle.'
return tuple(self) \n\n''' % locals()
for i, name in enumerate(field_names):
template += " %s = _property(lambda self: self[%d], doc='Alias for field number %d')\n" % (name, i, i)
if verbose:
print template
# Execute the template string in a temporary namespace and
# support tracing utilities by setting a value for frame.f_globals['__name__']
namespace = newdict('module')
namespace['OrderedDict'] = OrderedDict
namespace['_property'] = property
namespace['_tuple'] = tuple
namespace['__name__'] = 'namedtuple_%s' % typename
try:
exec template in namespace
except SyntaxError, e:
raise SyntaxError(e.message + ':\n' + template)
def magic_dict(**kwargs):
import __pypy__
res = __pypy__.newdict('module')
res.update(kwargs)
return res