I have strings made up of Boolean terms and equations, like so
x=1 AND (x=2 OR x=3) AND NOT (x=4 AND x=5) AND (x=5) AND y=1
I would like to break up
I suppose you could do something like this:
operators = ["AND NOT", "AND"]
sepChar = ":"
yourInputString = yourInputString.replace("(","").replace(")","") # remove the parenthesis
# Replace your operators with the separator character
for op in operators:
yourInputString = yourInputString.replace(op,sepChar)
# output of your string so far
# yourInputString
# 'x=1 : x=2 OR x=3 : x=4 : x=5 : x=5 : y=1'
# Create a list with the separator character
operationsList = youtInputString.split(sepChar)
# operationsList
# ['x=1', 'x=2 OR x=3', 'x=4', 'x=5', 'x=5', 'y=1']
# For the second result, let's do another operation list:
operators2 = ["OR"]
output = []
# Loop to find the other operators
for op in operationsList:
for operator in operators2:
if operator in op:
op = op.split(operator)
output.append(op)
# output:
# [['x=1'], ['x=2', 'x=3'], ['x=4'], ['x=5'], ['x=5'],['y=1']]
In this case, I used ":" as separation character, but you can change it according to your needs. Please let me know if this helps!
Edit
For a parenthesis nesting approach, I came with something brilliant:
import re
operators = ["AND NOT","AND","OR"]
# Substitute parenthesis
yourInputString = yourInputString.replace("(","[").replace(")","]")
# yourInputString
# "[x=1 AND [x=2 OR x=3] AND NOT [x=4 AND x=5] AND [x=5] AND y=1]"
# Replace your operators
for op in operators:
yourInputString = yourInputString(op,",")
# yourInputString
# "[x=1 , [x=2 , x=3] , [x=4 , x=5] , [x=5] , y=1]"
# Find matches like x = 5 and substitue with 'x = 5'
compiler = re.compile(r"[xyz]{1}=\d")
matches = compiler.findall(yourInputString)
# matches
# ['x=1', 'x=2', 'x=3', 'x=4', 'x=5', 'x=5', 'y=1']
# Convert the list into unique outputs
matches = list(set(matches))
# matches
# ['x=1', 'x=2', 'x=3', 'x=4', 'x=5', 'y=1']
# Replace your matches to add quotes to each element
for match in matches:
yourInputString = yourInputString.replace(match,f"'{match}'")
# yourInputString
# "['x=1' , ['x=2' , 'x=3'] , ['x=4' , 'x=5'] , ['x=5'] , 'y=1']"
# Here is the special move, convert your text into list
myList = eval(yourInputString)
# myList
# ['x=1', ['x=2', 'x=3'], ['x=4', 'x=5'], ['x=5'], 'y=1']
Let me know if that helped! Best!