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

Shortcuts on this page

r m x   toggle line displays

j k   next/prev highlighted chunk

0   (zero) top of page

1   (one) first highlighted chunk

45 statements  

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"""This fuzzer script targets the pandas replace function with variety of inputs and edge cases.""" 

27 

28import sys 

29import atheris 

30import pandas as pd 

31 

32 

33def TestOneInput(data): 

34 fdp = atheris.FuzzedDataProvider(data) 

35 

36 try: 

37 num_rows = fdp.ConsumeIntInRange(3, 30) 

38 num_columns = fdp.ConsumeIntInRange(3, 30) 

39 col_names = [fdp.ConsumeString(fdp.ConsumeIntInRange(1, 20)) for _ in range(num_columns)] 

40 

41 df_content = {} 

42 for col_name in col_names: 

43 if fdp.ConsumeBool(): 

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

45 elif fdp.ConsumeBool(): 

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

47 elif fdp.ConsumeBool(): 

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

49 elif fdp.ConsumeBool(): 

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

51 else: 

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

53 df = pd.DataFrame(df_content) 

54 

55 to_replace = fdp.ConsumeIntInRange(1, 100) if fdp.ConsumeBool else [fdp.ConsumeIntInRange(1, 100), 

56 fdp.ConsumeIntInRange(1, 100)] 

57 value = fdp.ConsumeIntInRange(101, 200) 

58 inplace = fdp.ConsumeBool() 

59 limit = fdp.ConsumeIntInRange(1, num_rows - 1) if fdp.ConsumeBool() else None 

60 regex = fdp.ConsumeBool() 

61 method = fdp.PickValueInList(['pad', 'ffill', 'bfill', 'backfill', fdp.ConsumeString(20), None]) 

62 

63 df.replace( 

64 to_replace=to_replace, 

65 value=value, 

66 inplace=inplace, 

67 limit=limit, 

68 regex=regex, 

69 method=method 

70 ) 

71 

72 except ( 

73 TypeError, # If to_replace and value have different length 

74 ValueError # If method is not in ['pad', 'ffill', 'bfill', 'backfill'] 

75 ): 

76 pass 

77 

78 

79def main(): 

80 atheris.Setup(sys.argv, TestOneInput) 

81 atheris.instrument_all() 

82 atheris.Fuzz() 

83 

84 

85if __name__ == "__main__": 

86 main()