Created
March 6, 2018 23:34
-
-
Save purpleP/5c48273c71893fc39c80ac4afb52536f to your computer and use it in GitHub Desktop.
split
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
class split: | |
def __init__(self, delimiter, sequence): | |
""" | |
Break a sequence on particular elements. | |
Return an iterator over chunks. | |
Arguments: | |
delimiter if a function, it returns True on chunk separators; | |
otherwise, it is the value of chunk separator. | |
sequence original sequence; | |
keepdelims whether or not to keep delimiters in chunks | |
""" | |
self.delimiter = delimiter(x) if callable(delimiter) else partial(eq, delimiter) | |
self.sequence = iter(sequence) | |
self.active = OrderedDict() | |
self.id = 0 | |
self.last_yielded_subgen_id = 0 | |
def __iter__(self): | |
return self | |
def subgen(self, id, item, buffered): | |
if self.delimiter(item): | |
return | |
yield item | |
buffered = self.active[id][1] | |
while True: | |
if buffered: | |
yield from (buffered.popleft() for i in range(len(buffered))) | |
elif id not in self.active: | |
return | |
else: | |
try: | |
item = next(seq) | |
except StopIteration: | |
self.active.pop(id) | |
return | |
else: | |
is_delim = self.delimiter(item) | |
if is_delim: | |
if self.active: | |
self.active.popitem(last=False) | |
else: | |
if self.active: | |
self.active[0][1].append(item) | |
else: | |
yield item | |
def __next__(self): | |
if self.active: | |
yield self.active[min(self.active)][0] | |
else: | |
try: | |
item = next(self.sequence) | |
except StopIteration: | |
return | |
else: | |
buffer = deque() | |
self.id += 1 | |
subg = self.subgen(id, item, buffer) | |
self.active[id] = subg, buffer | |
yield subg |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment