Geek Answers Handbook

Python regex string extension

Suppose I have the following line:

trend  = '(A|B|C)_STRING'

I want to expand this:

A_STRING
B_STRING
C_STRING

The OR clause can be anywhere on the line. ISTRING_(A|B)_STRING_(C|D)

will expand to

STRING_A_STRING_C
STRING_B_STRING C
STRING_A_STRING_D
STRING_B_STRING_D

I also want to highlight the case of empty convention:

(|A_)STRING will expand to:

A_STRING
STRING

Here is what I have tried so far:

def expandOr(trend):
    parenBegin = trend.index('(') + 1
    parenEnd = trend.index(')')
    orExpression = trend[parenBegin:parenEnd]
    originalTrend = trend[0:parenBegin - 1]
    expandedOrList = []

    for oe in orExpression.split("|"):
        expandedOrList.append(originalTrend + oe)

But this obviously does not work.

Is there an easy way to do this with regex?

+4
source share
3 answers

This is a pretty clean path. You will be interested to know how this works :-)

def expander(s):
    import re
    from itertools import product
    pat = r"\(([^)]*)\)"
    pieces = re.split(pat, s)
    pieces = [piece.split("|") for piece in pieces]
    for p in product(*pieces):
        yield "".join(p)

Then:

for s in ('(A|B|C)_STRING',
          '(|A_)STRING',
          'STRING_(A|B)_STRING_(C|D)'):
    print s, "->"
    for t in expander(s):
        print "   ", t

displayed:

(A|B|C)_STRING ->
    A_STRING
    B_STRING
    C_STRING
(|A_)STRING ->
    STRING
    A_STRING
STRING_(A|B)_STRING_(C|D) ->
    STRING_A_STRING_C
    STRING_A_STRING_D
    STRING_B_STRING_C
    STRING_B_STRING_D
+3
source

I would do this to extract groups:

def extract_groups(trend):
    l_parens = [i for i,c in enumerate(trend) if c == '(']
    r_parens = [i for i,c in enumerate(trend) if c == ')']
    assert len(l_parens) == len(r_parens)
    return [trend[l+1:r].split('|') for l,r in zip(l_parens,r_parens)]

And then you can evaluate the product of these extracted groups using itertools.product:

expr = 'STRING_(A|B)_STRING_(C|D)'
from itertools import product
list(product(*extract_groups(expr)))
Out[92]: [('A', 'C'), ('A', 'D'), ('B', 'C'), ('B', 'D')]

, . re :)

#python3.3+
def _gen(it):
    yield from it

p = re.compile('\(.*?\)')

for tup in product(*extract_groups(trend)):
    gen = _gen(tup)
    print(p.sub(lambda x: next(gen),trend))

STRING_A_STRING_C
STRING_A_STRING_D
STRING_B_STRING_C
STRING_B_STRING_D

, re.sub, , , .

+1
import exrex
trend  = '(A|B|C)_STRING'
trend2 = 'STRING_(A|B)_STRING_(C|D)'

>>> list(exrex.generate(trend))
[u'A_STRING', u'B_STRING', u'C_STRING']

>>> list(exrex.generate(trend2))
[u'STRING_A_STRING_C', u'STRING_A_STRING_D', u'STRING_B_STRING_C', u'STRING_B_STRING_D']
+1
source

More articles:


All Articles