def identify_type_of_statement(code_statement_list):
if is_class_statement(code_statement_list):
return line_type_dict.get(6)
method_check = is_method_statement(code_statement_list)
if method_check != -1:
return line_type_dict.get(method_check)
expression_or_field_declaration_check = expression_or_field_delcaration(
code_statement_list)
if expression_or_field_declaration_check != -1:
return line_type_dict.get(expression_or_field_declaration_check)
def test_Processing_Statement6(self):
input_code_statement = 'protected void doGet(HttpServletRequest request, HttpServletResponse response) throws ServletException, IOException'
input_word_tokens = get_list_of_words_from_statement(
input_code_statement)
actual_output_dict = parse_java_code_line(input_word_tokens)
self.assertFalse(actual_output_dict.get('left_side_expression'))
self.assertFalse(actual_output_dict.get('right_side_expression'))
self.assertEqual(input_code_statement,
actual_output_dict.get('statement'))
self.assertEqual(line_type_dict.get(2),
actual_output_dict.get('statement_type'))
self.assertFalse(actual_output_dict.get('java_data_types'))
self.assertTrue(actual_output_dict.get('java_return_types'))
self.assertEqual(['void'], actual_output_dict.get('java_return_types'))
self.assertTrue(actual_output_dict.get('access_modifiers'))
self.assertEqual(['protected'],
actual_output_dict.get('access_modifiers'))
self.assertFalse(actual_output_dict.get('inheritance_type'))
self.assertTrue(actual_output_dict.get('exception_type'))
self.assertEqual(['throws'], actual_output_dict.get('exception_type'))
self.assertTrue(actual_output_dict.get('exceptions_and_inheritances'))
self.assertEqual(['ServletException', 'IOException'],
actual_output_dict.get('exceptions_and_inheritances'))
self.assertFalse(actual_output_dict.get('unknown'))
def test_Processing_Statement5(self):
input_code_statement = 'super();'
input_word_tokens = get_list_of_words_from_statement(
input_code_statement)
actual_output_dict = parse_java_code_line(input_word_tokens)
self.assertFalse(actual_output_dict.get('left_side_expression'))
self.assertFalse(actual_output_dict.get('right_side_expression'))
self.assertEqual(input_code_statement,
actual_output_dict.get('statement'))
self.assertEqual(line_type_dict.get(3),
actual_output_dict.get('statement_type'))
self.assertFalse(actual_output_dict.get('java_data_types'))
self.assertFalse(actual_output_dict.get('java_return_types'))
self.assertFalse(actual_output_dict.get('access_modifiers'))
self.assertFalse(actual_output_dict.get('inheritance_type'))
self.assertFalse(actual_output_dict.get('exceptions_and_inheritances'))
self.assertFalse(actual_output_dict.get('unknown'))
def test_Processing_Statement3(self):
input_code_statement = 'private static final long serialVersionUID = 1L;'
input_word_tokens = get_list_of_words_from_statement(
input_code_statement)
actual_output_dict = parse_java_code_line(input_word_tokens)
self.assertTrue(actual_output_dict.get('left_side_expression'))
self.assertEqual('serialVersionUID',
actual_output_dict.get('left_side_expression'))
self.assertTrue(actual_output_dict.get('right_side_expression'))
self.assertEqual('1L;',
actual_output_dict.get('right_side_expression'))
self.assertEqual(input_code_statement,
actual_output_dict.get('statement'))
self.assertEqual(line_type_dict.get(1),
actual_output_dict.get('statement_type'))
self.assertTrue(actual_output_dict.get('java_data_types'))
self.assertEqual(['long'], actual_output_dict.get('java_data_types'))
self.assertFalse(actual_output_dict.get('java_return_types'))
self.assertTrue(actual_output_dict.get('access_modifiers'))
self.assertEqual(['private'],
actual_output_dict.get('access_modifiers'))
self.assertFalse(actual_output_dict.get('inheritance_type'))
self.assertFalse(actual_output_dict.get('exceptions_and_inheritances'))
self.assertTrue(actual_output_dict.get('unknown'))
self.assertEqual(['static', 'final'],
actual_output_dict.get('unknown'))
def test_Processing_Statement2(self):
input_code_statement = 'public class CustomerFlightDetails extends HttpServlet'
input_word_tokens = get_list_of_words_from_statement(
input_code_statement)
actual_output_dict = parse_java_code_line(input_word_tokens)
self.assertFalse(actual_output_dict.get('right_side_expression'))
self.assertFalse(actual_output_dict.get('left_side_expression'))
self.assertEqual(input_code_statement,
actual_output_dict.get('statement'))
self.assertEqual(line_type_dict.get(6),
actual_output_dict.get('statement_type'))
self.assertFalse(actual_output_dict.get('java_data_types'))
self.assertFalse(actual_output_dict.get('java_return_types'))
self.assertTrue(actual_output_dict.get('access_modifiers'))
self.assertEqual(['public'],
actual_output_dict.get('access_modifiers'))
self.assertTrue(actual_output_dict.get('inheritance_type'))
self.assertEqual(['extends'],
actual_output_dict.get('inheritance_type'))
self.assertTrue(actual_output_dict.get('exceptions_and_inheritances'))
self.assertEqual(['HttpServlet'],
actual_output_dict.get('exceptions_and_inheritances'))
self.assertFalse(actual_output_dict.get('unknown'))
def test_processing_statement19(self):
input_code_statement_list = ['s', '=', '"Hello"', ';']
actual_output = identify_type_of_statement(input_code_statement_list)
expected_output = line_type_dict.get(5)
self.assertEqual(actual_output, expected_output, \
"Did not get the expected output for method 'identify_type_of_statement' " \
"\nActual output is {} \nExpected output is {}".format(actual_output, expected_output))
def test_field_declaration9(self):
input_code_statement_list = ['int', '[]', 'a;']
actual_output = identify_type_of_statement(input_code_statement_list)
expected_output = line_type_dict.get(1)
self.assertEqual(actual_output, expected_output, \
"Did not get the expected output for method 'identify_type_of_statement' " \
"\nActual output is {} \nExpected output is {}".format(actual_output, expected_output))
def test_method_invocation5(self):
input_code_statement_list = ['person', '=doGet(name);']
actual_output = identify_type_of_statement(input_code_statement_list)
expected_output = line_type_dict.get(3)
self.assertEqual(actual_output, expected_output, \
"Did not get the expected output for method 'identify_type_of_statement' " \
"\nActual output is {} \nExpected output is {}".format(actual_output, expected_output))
def test_class_check2(self):
input_code_statement_list = ['public', 'class', 'SampleClass']
actual_output = identify_type_of_statement(input_code_statement_list)
expected_output = line_type_dict.get(6)
self.assertEqual(actual_output, expected_output, \
"Did not get the expected output for method 'identify_type_of_statement' " \
"\nActual output is {} \nExpected output is {}".format(actual_output, expected_output))
def test_method_declaration2(self):
input_code_statement_list = [
'public', 'void', 'doGet(String', 'name){'
]
actual_output = identify_type_of_statement(input_code_statement_list)
expected_output = line_type_dict.get(2)
self.assertEqual(actual_output, expected_output, \
"Did not get the expected output for method 'identify_type_of_statement' " \
"\nActual output is {} \nExpected output is {}".format(actual_output, expected_output))
def get_type_of_line():
print(
"What does this line number signify? Please select one of the below options"
)
for key in line_type_dict:
print(str(key) + ". " + line_type_dict.get(key))
line_type_option = int(raw_input())
if line_type_option == 1 or line_type_option == 2:
return line_type_option
else:
print("Sorry. Incorrect option provided. Please retry")
get_type_of_line()
def test_Processing_Statement1(self):
input_code_statement = 'String url = "jdbc:mysql://localhost:3306/airline";'
input_word_tokens = get_list_of_words_from_statement(
input_code_statement)
actual_output_dict = parse_java_code_line(input_word_tokens)
self.assertEqual('"jdbc:mysql://localhost:3306/airline";',
actual_output_dict.get('right_side_expression'))
self.assertEqual('url', actual_output_dict.get('left_side_expression'))
self.assertEqual(input_code_statement,
actual_output_dict.get('statement'))
self.assertEqual(line_type_dict.get(1),
actual_output_dict.get('statement_type'))
self.assertTrue(actual_output_dict.get('java_data_types'))
self.assertFalse(actual_output_dict.get('java_return_types'))
self.assertFalse(actual_output_dict.get('access_modifiers'))
self.assertFalse(actual_output_dict.get('inheritance_type'))
self.assertFalse(actual_output_dict.get('exceptions_and_inheritances'))
self.assertFalse(actual_output_dict.get('unknown'))
def parse_java_code_line(code_statement_in_word_tokens):
#0. Extract the type of statement
type_of_statement = identify_type_of_statement(
code_statement_in_word_tokens)
#2. Extract all access modifiers
access_modifiers_identified = [
token for token in code_statement_in_word_tokens
if is_access_modifier(token)
]
#3. Extract all java data types
data_types_identified = [
token for token in code_statement_in_word_tokens if is_data_type(token)
]
#4. Extract all return types (Do this only for method declaration statements)
return_types_identified = []
if type_of_statement == line_type_dict.get(2):
return_types_identified = [
token for token in code_statement_in_word_tokens
if is_return_type_keyword(token)
]
#5. Extract all inheritance tokens
inheritance_keywords_identified = [
token for token in code_statement_in_word_tokens
if is_inheritance_keyword(token)
]
#6. Extract all exception tokens
exception_keywords_identified = [
token for token in code_statement_in_word_tokens
if is_exception_keyword(token)
]
#7. Extract user_defined_data_types such as class or interface or enum
user_defined_data_type_type_identified = [
token for token in code_statement_in_word_tokens
if is_user_data_type_keyword(token)
]
#8. If a user defined data type is present, the retrieve the token that immediately follows it.
# For e.g. Given a statement such as class SampleClass, the earlier step identified the 'class' token.
# In this step, we must retrieve 'SampleClass' token
user_defined_data_type_identified = []
for index, token in enumerate(code_statement_in_word_tokens):
for data_type_type in user_defined_data_type_type_identified:
if data_type_type == token:
user_defined_data_type_identified.append(
code_statement_in_word_tokens[index + 1])
break
#Goes with assumption that a line can have only one token such as class or interface
#9. Keyword markers = A dictionary of all the indices that has a token that we have identified so far.
# For e.g given a statement such as Class SampleClass => our dict will be {0:['class'], 1:['SampleClass']}
keywords_markers_dict = {}
for index, token in enumerate(code_statement_in_word_tokens):
if (token in access_modifiers_identified \
or token in data_types_identified \
or token in return_types_identified \
or token in inheritance_keywords_identified \
or token in exception_keywords_identified \
or token in user_defined_data_type_type_identified \
or token in user_defined_data_type_identified):
keywords_markers_dict[index] = token
#10. Identify inheritance and exception key words in the code statement
inheritance_marker_positions = []
exception_marker_positions = []
for key in sorted(keywords_markers_dict.iterkeys()):
keyword = keywords_markers_dict.get(key)
if keyword in inheritance_keywords_identified:
inheritance_marker_positions.append(key)
elif keyword in exception_keywords_identified:
exception_marker_positions.append(key)
exceptions_and_inheritances_identified = []
startedReading = False
for index, token in enumerate(code_statement_in_word_tokens):
if index in inheritance_marker_positions or index in exception_marker_positions:
startedReading = True
elif startedReading and token != ",":
exceptions_and_inheritances_identified.append(
token.replace(",", ""))
#11. The remaining are all user_defined
remaining_words_identified = []
for token in code_statement_in_word_tokens:
if(token.replace(",","") not in access_modifiers_identified \
and token.replace(",","") not in data_types_identified \
and token.replace(",","") not in return_types_identified \
and token.replace(",","") not in user_defined_data_type_type_identified \
and token.replace(",","") not in user_defined_data_type_identified \
and token.replace(",","") not in inheritance_keywords_identified \
and token.replace(",","") not in exception_keywords_identified \
and token.replace(",","") not in exceptions_and_inheritances_identified):
remaining_words_identified.append(token)
#12. If the type of statement is either a field declaration or processing statement,
# Then we must capture the left_hand_side and right hand side of '='
expression_list = []
if type_of_statement == line_type_dict.get(
1) or type_of_statement == line_type_dict.get(5):
expression_list = get_tokens_for_field_declaration_and_processing_statements(
remaining_words_identified)
left_hand_side_list = []
right_hand_side_list = []
remaining_words_filtered = []
if len(expression_list) > 0:
left_hand_side_list = expression_list[0]
right_hand_side_list = expression_list[1]
for token in remaining_words_identified:
if token not in expression_list and token not in '=':
remaining_words_filtered.append(token)
# print("Code => {}".format(" ".join(code_statement_in_word_tokens)))
# print("\tType of statement => {}".format(type_of_statement))
# print("\tLeft-side expression => {}".format(left_hand_side_list))
# print("\tRight-side expression => {}".format(right_hand_side_list))
# print("\tAccess modifiers => {}".format(access_modifiers_identified))
# print("\tJava Data Types identified => {}".format(data_types_identified))
# print("\tJava Return Types identified => {}".format(return_types_identified))
# print("\tUser Defined Data Type Type =>{}".format(user_defined_data_type_type_identified))
# print("\tUser Defined data type =>{}".format(user_defined_data_type_identified))
# print("\tInheritance keywords =>{}".format(inheritance_keywords_identified))
# print("\tException keywords =>{}".format(exception_keywords_identified))
# print("\tException and inheritances identified =>{}".format(exceptions_and_inheritances_identified))
# print("\tRemaining Words => {}".format(remaining_words_filtered))
parsed_line_dict = {}
parsed_line_dict["statement"] = " ".join(code_statement_in_word_tokens)
parsed_line_dict["statement_type"] = type_of_statement
parsed_line_dict["left_side_expression"] = left_hand_side_list
parsed_line_dict["right_side_expression"] = right_hand_side_list
parsed_line_dict["access_modifiers"] = access_modifiers_identified
parsed_line_dict["java_data_types"] = data_types_identified
parsed_line_dict["java_return_types"] = return_types_identified
parsed_line_dict[
"user_data_type_type"] = user_defined_data_type_type_identified
parsed_line_dict["user_data_type"] = user_defined_data_type_identified
parsed_line_dict["inheritance_type"] = inheritance_keywords_identified
parsed_line_dict["exception_type"] = exception_keywords_identified
parsed_line_dict[
"exceptions_and_inheritances"] = exceptions_and_inheritances_identified
parsed_line_dict["unknown"] = remaining_words_filtered
return parsed_line_dict
