Python string.partition() example

gistfile1.txt

# Demonstrates string.partition() to split a string by a sequence of delimiters.
# Not terribly useful, can do with regex pretty easily.

s = "apple AND banana AND cherry AND date OR elderberry BUT fig"
delims = [" AND "]*3 + [" OR ", " BUT "]

# [' AND ', ' AND ', ' AND ', ' OR ', ' BUT ']

def splitByDelimList(str, delimList):
    delims = delimList.copy()
    p = str.partition(delims.pop(0))
    print("p:\t", p)
    tokens = [p[0]]
    while p[2] and delims:
       p = p[2].partition(delims.pop(0))
       print("p:\t", p)
       tokens.append(p[0])
    else:
       # Get p[2] if no more delims
       tokens.append(p[2])
    return tokens

tokensByPartition = splitByDelimList(s, delims)

p:   ('apple', ' AND ', 'banana AND cherry AND date OR elderberry BUT fig')
p:   ('banana', ' AND ', 'cherry AND date OR elderberry BUT fig')
p:   ('cherry', ' AND ', 'date OR elderberry BUT fig')
p:   ('date', ' OR ', 'elderberry BUT fig')
p:   ('elderberry', ' BUT ', 'fig')

assert tokensByPartition == ["apple", "banana", "cherry", "date" , "elderberry", "fig"]

### Using regex
import re
regexDelims = '|'.join([re.escape(delim) for delim in delims])

print(regexDelims)
# \ AND\ |\ AND\ |\ AND\ |\ OR\ |\ BUT\ 

tokensRegex = re.split(regexDelims, s)
assert tokensRegex == tokensByPartition