def main():
parser = argparse.ArgumentParser(description='command line interface for map2annotation')
parser.add_argument('--type-mapping',dest='type_mapping_file')
parser.add_argument('--field-mapping', dest='field_mapping_file')
parser.add_argument('--project-list', dest='projects', help='project_nameA,project_nameB,...')
args = parser.parse_args()
if args.type_mapping_file is None and args.field_mapping_file is None:
print "error, required at least one mapping file to be indicated."
parser.print_help()
sys.exit(1)
project_list = common.get_project_list()
if args.projects:
arg_projects = args.projects.split(',')
project_list = [project for project in project_list if project in arg_projects]
pa2checker.revert_checker_source()
if not args.type_mapping_file is None:
type_mappings_to_rules(args.type_mapping_file)
if not args.field_mapping_file is None:
field_mappings_to_annotation(project_list, args.field_mapping_file)
for project in project_list:
run_anno_inference(project)
def main():
parser = argparse.ArgumentParser()
parser.add_argument("-c", "--cluster", type=str, help="path to the input json file that contains the clustering information.")
parser.add_argument("-d", "--dir", type=str, required=True, help="output folder.")
parser.add_argument("-p", "--plist", type=str, help="a comma separated list of projects to work with.")
parser.add_argument("-k", "--kernel", action="store_true", help="recompute kernel vectors.")
parser.add_argument("-g", "--graph", action="store_true", help="regenerate graphs.")
parser.add_argument("-s", "--sim", type=str, help="specify a subset of projects for finding similar programs in the list of projects.")
args = parser.parse_args()
common.mkdir(args.dir)
# determine which projects to consider
project_list = common.get_project_list()
if args.plist:
arg_projects = args.plist.split(',')
project_list = [project for project in project_list if project in arg_projects]
# determine if need to regerenate graphs
if args.graph:
for project in project_list:
generate_graphs(project)
print("\n***** Done with generating graphs. *****\n")
# determine if need to recompute the kernel vectors
if args.kernel:
for project in project_list:
generate_project_kernel(project, args.cluster)
print("\n***** Done with computing kernels. *****\n")
# check similarity
dot_method_map = get_method_map(project_list, False)
print("Done gathering all method-dot pairs.")
if args.sim:
project_sublist = args.sim.split(',')
for project in project_sublist:
if project not in project_list:
print("Skipping {0} since it is not in the list of projects.".format(project))
else:
print("Computing similar programs for {0}:".format(project))
result_file = os.path.join(common.WORKING_DIR, args.dir, project+"_result.txt")
kernel_file = os.path.join(common.WORKING_DIR, args.dir, project+"_kernel.txt")
json_file = os.path.join(common.WORKING_DIR, args.dir, project+"_result.json")
check_similarity(project, result_file, kernel_file, dot_method_map, json_file, args.cluster, min(5,len(project_list)))
else:
for project in project_list:
pl = list(project_list) # create a copy
pl.remove(project)
gather_kernels(pl, os.path.join(common.WORKING_DIR, args.dir, project+"_kernel.txt"))
print("Computing similar programs for {0}:".format(project))
result_file = os.path.join(common.WORKING_DIR, args.dir, project+"_result.txt")
kernel_file = os.path.join(common.WORKING_DIR, args.dir, project+"_kernel.txt")
json_file = os.path.join(common.WORKING_DIR, args.dir, project+"_result.json")
check_similarity(project, result_file, kernel_file, dot_method_map, json_file, args.cluster, min(5,len(project_list)))
print("\n***** Done with computing similar programs. *****\n")
def main():
kf = open("corpus_kernel.txt", "w")
for project in common.get_project_list():
print "Analyzing {}".format(project)
project_kernel_file = add_project_to_corpus(project)
with open(project_kernel_file, "r") as fi: kf.write(fi.read())
dtrace = get_dtrace_file_for_project(project)
if dtrace:
print "Generated {}".format(dtrace)
kf.close()
def main():
kf = open("corpus_kernel.txt", "w")
for project in common.get_project_list():
print "Analyzing {}".format(project)
project_kernel_file = add_project_to_corpus(project)
with open(project_kernel_file, "r") as fi:
kf.write(fi.read())
dtrace = get_dtrace_file_for_project(project)
if dtrace:
print "Generated {}".format(dtrace)
kf.close()
def main():
project_list = common.get_project_list()
parser = argparse.ArgumentParser()
parser.add_argument("-rc",
"--recompute_clusters",
action="store_true",
help="recompute clustering for selected projects")
parser.add_argument(
"-c",
"--cluster",
type=str,
help="path to the json file that contains clustering information")
parser.add_argument("-g",
"--graph",
action="store_true",
help="set to regenerate graphs from the programs")
parser.add_argument("-d",
"--dir",
type=str,
required=True,
help="The output directory")
parser.add_argument("-p",
"--projectset",
type=str,
help="A project set name to work on")
args = parser.parse_args()
if args.projectset:
project_list = common.get_corpus_set(args.projectset)
args.dir = os.path.abspath(
os.path.join(common.WORKING_DIR, 'results', args.dir))
if os.path.exists(args.dir):
rotate_log_dir(args.dir)
common.mkdir(args.dir)
common.set_output_dir(args.dir)
kernel_dir = os.path.join(args.dir, "kernel_directory")
common.mkdir(kernel_dir)
backend.run(project_list, args, kernel_dir)
print("\n********* END OF BACKEND **********\n")
frontend.run(project_list, args, kernel_dir)
collect_stray_output(project_list, args.dir)
sanity.check_run(project_list, args.dir)
def main():
project_list = common.get_project_list()
parser = argparse.ArgumentParser()
parser.add_argument("-rc", "--recompute_clusters", action="store_true", help="recompute clustering for selected projects")
parser.add_argument("-c", "--cluster", type=str, help="path to the json file that contains clustering information")
parser.add_argument("-g", "--graph", action="store_true", help="set to regenerate graphs from the programs")
parser.add_argument("-d", "--dir", type=str, required=True, help="The output directory")
parser.add_argument("-p", "--projects", type=str, help="A comma separated list of projects to work with.")
args = parser.parse_args()
if args.projects:
arg_projects = args.projects.split(',')
project_list = [project for project in project_list if project in arg_projects]
common.mkdir(args.dir)
kernel_dir = "kernel_directory"
common.mkdir(kernel_dir)
backend.run(project_list, args, kernel_dir)
print("\n********* END OF BACKEND **********\n")
frontend.run(project_list, args, kernel_dir)
INPUT: k_list_of_methods
OUTPUT: patch file for the ontology. Worst case: just add the 'best' implementation
found in the corpus as a blob to the ontology. Best case: generate an equivalent
flow-graph in the ontology.
"""
#print "TODO" # ALL
# if not os.path.isfile(daikon_jar):
# print "Downloading dependencies"
# cmd = ["./fetch_dependencies.sh"]
# run_command(cmd)
# print "Done."
if __name__ == '__main__':
corpus = common.get_project_list()
annotations = {"Sequence": ['java.util.List', 'java.util.LinkedHashSet']}
top_k = 3
if len(sys.argv) > 1:
annotations_file = sys.argv[1]
if len(sys.argv) > 2:
top_k = sys.argv[2]
with open(annotations_file, 'r') as f:
annotations.clear()
for line in f.readlines():
pair = [x.strip() for x in line.split(',')]
if len(pair) != 2:
print("Ignoring {}".format(line))
continue
if pair[0] not in annotations:
annotations[pair[0]] = []
import backend, common project_list = common.get_project_list() backend.run2(project_list)
"""
Close the loop and add the best implementation found in the previous
step back to the ontology.
INPUT: k_list_of_methods
OUTPUT: patch file for the ontology. Worst case: just add the 'best' implementation
found in the corpus as a blob to the ontology. Best case: generate an equivalent
flow-graph in the ontology.
"""
print "TODO" # ALL
# if not os.path.isfile(daikon_jar):
# print "Downloading dependencies"
# cmd = ["./fetch_dependencies.sh"]
# run_command(cmd)
# print "Done."
if __name__ == '__main__':
corpus = common.get_project_list()
if len(sys.argv)>1:
filtered_corpus = []
for arg in sys.argv[1:]:
if arg in corpus:
filtered_corpus += [arg]
print ("Filtered corpus contianing: {}".format(','.join(filtered_corpus)))
corpus = filtered_corpus
annotations = { "Sequence": ['java.util.List', 'java.util.LinkedHashSet'] }
main(corpus, annotations)
