mirrors/cpython
1
0
Fork 0
mirror of https://github.com/python/cpython.git synced 2025-09-27 02:39:58 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions 13

Issue #4615. Document how to use itertools for de-duping.

Browse source
This commit is contained in:
Raymond Hettinger 2009-01-02 21:39:07 +00:00
parent 80a50acbe9
commit ad9d96bc1a
2 changed files with 60 additions and 0 deletions
Download patch file Download diff file Expand all files Collapse all files

24
Doc/library/itertools.rst
View file

@ -606,3 +606,27 @@ which incur interpreter overhead.
return return
indices[i:] = [indices[i] + 1] * (r - i) indices[i:] = [indices[i] + 1] * (r - i)
yield tuple(pool[i] for i in indices) yield tuple(pool[i] for i in indices)
def unique_everseen(iterable, key=None):
"List unique elements, preserving order. Remember all elements ever seen."
# unique_everseen('AAAABBBCCDAABBB') --> A B C D
# unique_everseen('ABBCcAD', str.lower) --> A B C D
seen = set()
seen_add = seen.add
if key is None:
for element in iterable:
if element not in seen:
seen_add(element)
yield element
else:
for element in iterable:
k = key(element)
if k not in seen:
seen_add(k)
yield element
def unique_justseen(iterable, key=None):
"List unique elements, preserving order. Remember only the element just seen."
# unique_justseen('AAAABBBCCDAABBB') --> A B C D A B
# unique_justseen('ABBCcAD', str.lower) --> A B C A D
return map(next, map(itemgetter(1), groupby(iterable, key)))

36
Lib/test/test_itertools.py
View file

@ -1298,6 +1298,30 @@ Samuele
... indices[i:] = [indices[i] + 1] * (r - i) ... indices[i:] = [indices[i] + 1] * (r - i)
... yield tuple(pool[i] for i in indices) ... yield tuple(pool[i] for i in indices)
>>> def unique_everseen(iterable, key=None):
... "List unique elements, preserving order. Remember all elements ever seen."
... # unique_everseen('AAAABBBCCDAABBB') --> A B C D
... # unique_everseen('ABBCcAD', str.lower) --> A B C D
... seen = set()
... seen_add = seen.add
... if key is None:
... for element in iterable:
... if element not in seen:
... seen_add(element)
... yield element
... else:
... for element in iterable:
... k = key(element)
... if k not in seen:
... seen_add(k)
... yield element
>>> def unique_justseen(iterable, key=None):
... "List unique elements, preserving order. Remember only the element just seen."
... # unique_justseen('AAAABBBCCDAABBB') --> A B C D A B
... # unique_justseen('ABBCcAD', str.lower) --> A B C A D
... return map(next, map(itemgetter(1), groupby(iterable, key)))
This is not part of the examples but it tests to make sure the definitions This is not part of the examples but it tests to make sure the definitions
perform as purported. perform as purported.
@ -1360,6 +1384,18 @@ perform as purported.
>>> list(combinations_with_replacement('abc', 2)) >>> list(combinations_with_replacement('abc', 2))
[('a', 'a'), ('a', 'b'), ('a', 'c'), ('b', 'b'), ('b', 'c'), ('c', 'c')] [('a', 'a'), ('a', 'b'), ('a', 'c'), ('b', 'b'), ('b', 'c'), ('c', 'c')]
>>> list(unique_everseen('AAAABBBCCDAABBB'))
['A', 'B', 'C', 'D']
>>> list(unique_everseen('ABBCcAD', str.lower))
['A', 'B', 'C', 'D']
>>> list(unique_justseen('AAAABBBCCDAABBB'))
['A', 'B', 'C', 'D', 'A', 'B']
>>> list(unique_justseen('ABBCcAD', str.lower))
['A', 'B', 'C', 'A', 'D']
""" """
__test__ = {'libreftest' : libreftest} __test__ = {'libreftest' : libreftest}