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

2 files changed, 60 insertions, 0 deletions

diff --git a/Doc/library/itertools.rst b/Doc/library/itertools.rst
index e0a55bd..2bd18d0 100644
--- a/Doc/library/itertools.rst
+++ b/Doc/library/itertools.rst
@@ -687,3 +687,27 @@ which incur interpreter overhead.
                return
            indices[i:] = [indices[i] + 1] * (r - i)
            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 imap(next, imap(itemgetter(1), groupby(iterable, key)))
diff --git a/Lib/test/test_itertools.py b/Lib/test/test_itertools.py
index 6912ac7..029498a 100644
--- a/Lib/test/test_itertools.py
+++ b/Lib/test/test_itertools.py
@@ -1277,6 +1277,30 @@ Samuele
 ...         indices[i:] = [indices[i] + 1] * (r - i)
 ...         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 imap(next, imap(itemgetter(1), groupby(iterable, key)))
+
 This is not part of the examples but it tests to make sure the definitions
 perform as purported.
 
@@ -1339,6 +1363,18 @@ perform as purported.
 >>> list(combinations_with_replacement('abc', 2))
 [('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}