Kent Johnson wrote:
> You might want to look at doing this with pyparsing, I think it will
> make it easier to get the data out vs just recognizing the correct pattern.
Here is a pyparsing version that correctly recognizes all of your
patterns and returns a (possibly nested) Python list in case of a match.
Note that this version will parse lists that are nested arbitrarily
deeply. If you don't want that you will have to define two kinds of
lists, a singly-nested list and a non-nested list.
Kent
from pyparsing import *
List = Forward()
T = Literal('true').setParseAction( lambda s,l,t: [ True ] )
F = Literal('false').setParseAction( lambda s,l,t: [ False ] )
String = QuotedString('"')
Number = Word(nums).setParseAction( lambda s,l,t: [ int(t[0]) ] )
List << Literal('{').suppress() +
delimitedList(T|F|String|Number|Group(List)) + Literal('}').suppress()
def IsASList(s):
# AppleScript lists are bracked by curly braces with items separate
by commas
# Each item is an alphanumeric label(?) or a string enclosed by
# double quotes or a list itself
# e.g. {2, True, "hello"}
try:
parsed = List.parseString(s)
return parsed.asList()
except Exception, e:
return None
sample_strs = [
'{}', # Empty list
'{a}', # Should not match
'{a, b, c}', # Should not match
'{"hello"}',
'{"hello", "kitty"}',
'{true}',
'{false}',
'{true, false}',
'{9}',
'{9,10, 11}',
'{93214, true, false, "hello", "kitty"}',
'{{1, 2, 3}}', # This matches
'{{1, 2, "cat"}, 1}', # This matches
# These don't match:
'{{1,2,3},1,{4,5,6},2}',
'{1, {2, 3, 4}, 3}',
'{{1, 2, 3}, {4, 5, 6}, 1}',
'{1, {1, 2, 3}}', # Should match but doesn't
'{93214, true, false, "hello", "kitty", {1, 2, 3}}', # Should match
but doesn't
'{label: "hello", value: false, num: 2}', # AppleScript dictionary
- should not match
]
for sample in sample_strs:
result = IsASList(sample)
print 'Is AppleScript List: %s; String: %s' % (bool(result), sample)
if result:
print result
_______________________________________________
Tutor maillist - Tutor@python.org
http://mail.python.org/mailman/listinfo/tutor
