Michael Spencer wrote:
> Here's a small update to the generator that allows optional handling of the
> head
> and the tail:
>
> def chunker(s, chunk_size=3, sentry=".", keep_first = False, keep_last =
> False):
> buffer=[]
> sentry_count = 0
>
> for item in s:
> buffer.append(item)
> if item == sentry:
> sentry_count += 1
> if sentry_count < chunk_size:
> if keep_first:
> yield buffer
> else:
> yield buffer
> del buffer[:buffer.index(sentry)+1]
>
> if keep_last:
> while buffer:
> yield buffer
> del buffer[:buffer.index(sentry)+1]
And here's a (probably) more efficient version, using a deque as a
buffer:
from itertools import islice
from collections import deque
def chunker(seq, sentry='.', chunk_size=3, keep_first=False,
keep_last=False):
def format_chunks(chunks):
return [' '.join(chunk) for chunk in chunks]
iterchunks = itersplit(seq,sentry)
buf = deque()
for chunk in islice(iterchunks, chunk_size-1):
buf.append(chunk)
if keep_first:
yield format_chunks(buf)
for chunk in iterchunks:
buf.append(chunk)
yield format_chunks(buf)
buf.popleft()
if keep_last:
while buf:
yield format_chunks(buf)
buf.popleft()
def itersplit(seq, sentry='.'):
# split the iterable `seq` on each `sentry`
buf = []
for x in seq:
if x != sentry:
buf.append(x)
else:
yield buf
buf = []
if buf:
yield buf
s = " this . is a . test to . check if it . works . well . it looks .
like ."
for p in chunker(s.split(), keep_last=True, keep_first=True):
print p
George
--
http://mail.python.org/mailman/listinfo/python-list
