Coverage for /pythoncovmergedfiles/medio/medio/usr/local/lib/python3.8/site-packages/nbconvert/preprocessors/regexremove.py: 54%

13 statements  

« prev     ^ index     » next       coverage.py v7.2.7, created at 2023-07-01 06:54 +0000

1""" 

2Module containing a preprocessor that removes cells if they match 

3one or more regular expression. 

4""" 

5 

6# Copyright (c) IPython Development Team. 

7# Distributed under the terms of the Modified BSD License. 

8 

9import re 

10 

11from traitlets import List, Unicode 

12 

13from .base import Preprocessor 

14 

15 

16class RegexRemovePreprocessor(Preprocessor): 

17 """ 

18 Removes cells from a notebook that match one or more regular expression. 

19 

20 For each cell, the preprocessor checks whether its contents match 

21 the regular expressions in the ``patterns`` traitlet which is a list 

22 of unicode strings. If the contents match any of the patterns, the cell 

23 is removed from the notebook. 

24 

25 To modify the list of matched patterns, 

26 modify the patterns traitlet. For example, execute the following command 

27 to convert a notebook to html and remove cells containing only whitespace:: 

28 

29 jupyter nbconvert --RegexRemovePreprocessor.patterns="['\\s*\\Z']" mynotebook.ipynb 

30 

31 The command line argument 

32 sets the list of patterns to ``'\\s*\\Z'`` which matches an arbitrary number 

33 of whitespace characters followed by the end of the string. 

34 

35 See https://regex101.com/ for an interactive guide to regular expressions 

36 (make sure to select the python flavor). See 

37 https://docs.python.org/library/re.html for the official regular expression 

38 documentation in python. 

39 """ 

40 

41 patterns = List(Unicode(), default_value=[]).tag(config=True) 

42 

43 def check_conditions(self, cell): 

44 """ 

45 Checks that a cell matches the pattern. 

46 

47 Returns: Boolean. 

48 True means cell should *not* be removed. 

49 """ 

50 

51 # Compile all the patterns into one: each pattern is first wrapped 

52 # by a non-capturing group to ensure the correct order of precedence 

53 # and the patterns are joined with a logical or 

54 pattern = re.compile("|".join("(?:%s)" % pattern for pattern in self.patterns)) 

55 

56 # Filter out cells that meet the pattern and have no outputs 

57 return not pattern.match(cell.source) 

58 

59 def preprocess(self, nb, resources): 

60 """ 

61 Preprocessing to apply to each notebook. See base.py for details. 

62 """ 

63 # Skip preprocessing if the list of patterns is empty 

64 if not self.patterns: 

65 return nb, resources 

66 

67 # Filter out cells that meet the conditions 

68 nb.cells = [cell for cell in nb.cells if self.check_conditions(cell)] 

69 

70 return nb, resources