def __str__(self):
def info(node, depth = 0):
prefix = ' ' * depth
if isstring(node): return prefix + node
return prefix + node.info(), [info(n, depth+1) for n in node.children]
lines = info(self.root)
return '\n'.join(flatten(lines))
def extract_regex(regex, text):
"""Extract a list of strings from the given text using the following rules:
* if the regex contains a named group called "extract" that will be returned
* if the regex contains multiple numbered groups, all those will be returned (flattened)
* if the regex doesn't contain any group the entire regex matching is returned
Adapted from Scrapy code.
"""
if isinstance(regex, basestring):
regex = re.compile(regex)
try:
strings = [regex.search(text).group('extract')] # named group
except:
strings = regex.findall(text) # full regex or numbered groups
return flatten(strings)
def _rewriteNode(self, parnode):
children = flatten(self.rewrite(c) for c in parnode.children)
return (parnode.start, parnode.end), parnode.expr_name, children # pos, type, children
