def run(self,
counting_conditions: counting_condition_dict=default_cc_dict,
average_calculation: bool=False,
poly_postprocessing: bool=True,
exp_postprocessing: bool=False,
extra_include_paths: path_list=()):
'''
Retrieves similarities for code clone detection. Those can be reused in
another bear to produce results.
Postprocessing may be done because small functions are less likely to
be clones at the same difference value than big functions which may
provide a better refactoring opportunity for the user.
:param counting_conditions: A comma seperated list of counting
conditions. Possible values are: used,
returned, is_condition, in_condition,
in_second_level_condition,
in_third_level_condition, is_assignee,
is_assigner, loop_content,
second_level_loop_content,
third_level_loop_content, is_param,
in_sum, in_product, in_binary_operation,
member_accessed.
Weightings can be assigned to each
condition due to providing a dict
value, i.e. having used weighted in
half as much as other conditions would
simply be: "used: 0.5, is_assignee".
Weightings default to 1 if unset.
:param average_calculation: If set to true the difference calculation
function will take the average of all
variable differences as the difference,
else it will normalize the function as a
whole and thus weighting in variables
dependent on their size.
:param poly_postprocessing: If set to true, the difference value of big
function pairs will be reduced using a
polynomial approach.
:param extra_include_paths: A list containing additional include paths.
:param exp_postprocessing: If set to true, the difference value of big
function pairs will be reduced using an
exponential approach.
'''
self.debug("Using the following counting conditions:")
for key, val in counting_conditions.items():
self.debug(" *", key.__name__, "(weighting: {})".format(val))
self.debug("Creating count matrices...")
count_matrices = get_count_matrices(
ClangCountVectorCreator(list(counting_conditions.keys()),
list(counting_conditions.values())),
list(self.file_dict.keys()),
lambda prog: self.debug("{:2.4f}%...".format(prog)),
self.section["files"].origin,
collect_dirs(extra_include_paths))
self.debug("Calculating differences...")
differences = []
function_count = len(count_matrices)
# Thats n over 2, hardcoded to simplify calculation
combination_length = function_count * (function_count-1) / 2
partial_get_difference = functools.partial(
get_difference,
count_matrices=count_matrices,
average_calculation=average_calculation,
poly_postprocessing=poly_postprocessing,
exp_postprocessing=exp_postprocessing)
for i, elem in enumerate(
map(partial_get_difference,
[(f1, f2) for f1, f2 in combinations(count_matrices, 2)])):
if i % 50 == 0:
self.debug("{:2.4f}%...".format(100*i/combination_length))
differences.append(elem)
yield HiddenResult(self, differences)
yield HiddenResult(self, count_matrices)
def run(self,
counting_conditions: counting_condition_dict = default_cc_dict,
average_calculation: bool = False,
poly_postprocessing: bool = True,
exp_postprocessing: bool = False,
extra_include_paths: path_list = ()):
'''
Retrieves similarities for code clone detection. Those can be reused in
another bear to produce results.
Postprocessing may be done because small functions are less likely to
be clones at the same difference value than big functions which may
provide a better refactoring opportunity for the user.
:param counting_conditions: A comma seperated list of counting
conditions. Possible values are: used,
returned, is_condition, in_condition,
in_second_level_condition,
in_third_level_condition, is_assignee,
is_assigner, loop_content,
second_level_loop_content,
third_level_loop_content, is_param,
in_sum, in_product, in_binary_operation,
member_accessed.
Weightings can be assigned to each
condition due to providing a dict
value, i.e. having used weighted in
half as much as other conditions would
simply be: "used: 0.5, is_assignee".
Weightings default to 1 if unset.
:param average_calculation: If set to true the difference calculation
function will take the average of all
variable differences as the difference,
else it will normalize the function as a
whole and thus weighting in variables
dependent on their size.
:param poly_postprocessing: If set to true, the difference value of big
function pairs will be reduced using a
polynomial approach.
:param extra_include_paths: A list containing additional include paths.
:param exp_postprocessing: If set to true, the difference value of big
function pairs will be reduced using an
exponential approach.
'''
self.debug("Using the following counting conditions:")
for key, val in counting_conditions.items():
self.debug(" *", key.__name__, "(weighting: {})".format(val))
self.debug("Creating count matrices...")
count_matrices = get_count_matrices(
ClangCountVectorCreator(list(counting_conditions.keys()),
list(counting_conditions.values())),
list(self.file_dict.keys()),
lambda prog: self.debug("{:2.4f}%...".format(prog)),
self.section["files"].origin, collect_dirs(extra_include_paths))
self.debug("Calculating differences...")
differences = []
function_count = len(count_matrices)
# Thats n over 2, hardcoded to simplify calculation
combination_length = function_count * (function_count - 1) / 2
partial_get_difference = functools.partial(
get_difference,
count_matrices=count_matrices,
average_calculation=average_calculation,
poly_postprocessing=poly_postprocessing,
exp_postprocessing=exp_postprocessing)
for i, elem in enumerate(
map(partial_get_difference,
[(f1, f2) for f1, f2 in combinations(count_matrices, 2)])):
if i % 50 == 0:
self.debug("{:2.4f}%...".format(100 * i / combination_length))
differences.append(elem)
yield HiddenResult(self, differences)
yield HiddenResult(self, count_matrices)