我认为这正是您需要的;orderedMerge基于Gnibbler的代码,但添加了一个自定义键函数和一个唯一的参数import kyotocabinet
import collections
import heapq
class IterableCursor(kyotocabinet.Cursor, collections.Iterator):
def __init__(self, *args, **kwargs):
kyotocabinet.Cursor.__init__(self, *args, **kwargs)
collections.Iterator.__init__(self)
def next():
"Return (key,value) pair"
res = self.get(True)
if res is None:
raise StopIteration
else:
return res
def orderedMerge(*iterables, **kwargs):
"""Take a list of ordered iterables; return as a single ordered generator.
@param key: function, for each item return key value
(Hint: to sort descending, return negated key value)
@param unique: boolean, return only first occurrence for each key value?
"""
key = kwargs.get('key', (lambda x: x))
unique = kwargs.get('unique', False)
_heapify = heapq.heapify
_heapreplace = heapq.heapreplace
_heappop = heapq.heappop
_StopIteration = StopIteration
# preprocess iterators as heapqueue
h = []
for itnum, it in enumerate(map(iter, iterables)):
try:
next = it.next
data = next()
keyval = key(data)
h.append([keyval, itnum, data, next])
except _StopIteration:
pass
_heapify(h)
# process iterators in ascending key order
oldkeyval = None
while True:
try:
while True:
keyval, itnum, data, next = s = h[0] # get smallest-key value
# raises IndexError when h is empty
# if unique, skip duplicate keys
if unique and keyval==oldkeyval:
pass
else:
yield data
oldkeyval = keyval
# load replacement value from same iterator
s[2] = data = next() # raises StopIteration when exhausted
s[0] = key(data)
_heapreplace(h, s) # restore heap condition
except _StopIteration:
_heappop(h) # remove empty iterator
except IndexError:
return
那么你的功能可以作为
^{pr2}$
本文介绍了一个名为orderedMerge的函数,该函数能够接受多个已排序的迭代器并返回一个单一的有序生成器。此外,文中还提供了一个IterableCursor类,用于扩展Kyoto Cabinet库中的Cursor类以实现迭代器接口。
247

被折叠的 条评论
为什么被折叠?



