Coverage for /pythoncovmergedfiles/medio/medio/src/fuzz_melt_map.py: 67%

1###### Coverage stub 

2import atexit 

3import coverage 

4cov = coverage.coverage(data_file='.coverage', cover_pylib=True) 

5cov.start() 

6# Register an exist handler that will print coverage 

7def exit_handler(): 

8 cov.stop() 

9 cov.save() 

10atexit.register(exit_handler) 

11####### End of coverage stub 

12#!/usr/bin/python3 

13# Copyright 2023 Google LLC 

14# 

15# Licensed under the Apache License, Version 2.0 (the "License"); 

16# you may not use this file except in compliance with the License. 

17# You may obtain a copy of the License at 

18# 

19# http://www.apache.org/licenses/LICENSE-2.0 

20# 

21# Unless required by applicable law or agreed to in writing, software 

22# distributed under the License is distributed on an "AS IS" BASIS, 

23# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. 

24# See the License for the specific language governing permissions and 

25# limitations under the License. 

26 

27"""This fuzzer script targets the pandas melt and map functions, creating a variety of DataFrames with mixed data 

28types and then transforming them using melting and mapping operations.""" 

29 

30import sys 

31import atheris 

32import pandas as pd 

33 

34 

35def TestOneInput(data): 

36 fdp = atheris.FuzzedDataProvider(data) 

37 

38 try: 

39 groups = { 

40 fdp.ConsumeString(10): fdp.ConsumeUnicodeNoSurrogates(10), 

41 fdp.ConsumeString(10): fdp.ConsumeUnicodeNoSurrogates(10) 

42 } 

43 

44 num_rows = fdp.ConsumeIntInRange(3, 30) 

45 num_columns = fdp.ConsumeIntInRange(3, 30) 

46 col_names = [fdp.ConsumeString(fdp.ConsumeIntInRange(1, 15)) for _ in range(num_columns)] 

47 

48 df_content = {} 

49 for col_name in col_names: 

50 if fdp.ConsumeBool(): 

51 df_content[col_name] = [fdp.ConsumeInt(10) for _ in range(num_rows)] 

52 elif fdp.ConsumeBool(): 

53 df_content[col_name] = [fdp.ConsumeString(10) for _ in range(num_rows)] 

54 elif fdp.ConsumeBool(): 

55 df_content[col_name] = [fdp.ConsumeIntInRange(0, 2100) for _ in range(num_rows)] 

56 elif fdp.ConsumeBool(): 

57 df_content[col_name] = [fdp.ConsumeFloat() for _ in range(num_rows)] 

58 else: 

59 df_content[col_name] = [fdp.ConsumeBool() for _ in range(num_rows)] 

60 

61 id_vars_data = [ 

62 col_names[fdp.ConsumeIntInRange(0, len(col_names) - 1)], 

63 col_names[fdp.ConsumeIntInRange(0, len(col_names) - 1)], 

64 col_names[fdp.ConsumeIntInRange(0, len(col_names) - 1)] 

65 ] 

66 if fdp.ConsumeBool(): 

67 id_vars_data.append(fdp.ConsumeString(fdp.ConsumeIntInRange(1, 15))) 

68 

69 df = pd.DataFrame(df_content) 

70 name = fdp.ConsumeString(20) 

71 df = pd.melt( 

72 df, 

73 id_vars=id_vars_data, 

74 value_vars=[ 

75 col_names[fdp.ConsumeIntInRange(0, len(col_names) - 1)], 

76 col_names[fdp.ConsumeIntInRange(0, len(col_names) - 1)] 

77 ], 

78 var_name='gf', value_name=fdp.ConsumeString(10) 

79 ) 

80 

81 local_var_name = 'gf' if fdp.ConsumeBool() else fdp.ConsumeString(10) 

82 df[name] = df[local_var_name].map(groups) 

83 except ( 

84 KeyError, # if `id_vars` are not in the frame. 

85 ValueError # if initial data from seed is empty and fdp produces empty data. 

86 ): 

87 pass 

88 

89 

90def main(): 

91 atheris.Setup(sys.argv, TestOneInput) 

92 atheris.instrument_all() 

93 atheris.Fuzz() 

94 

95 

96if __name__ == "__main__": 

97 main()