Merge pull request #201 from eriknw/diff

Add `itertoolz.diff` to yield elements that differ between sequences.

doc/source/api.rst

@@ -15,6 +15,7 @@ Itertoolz
    concatv
    cons
    count
+   diff
    drop
    first
    frequencies

doc/source/tips-and-tricks.rst

@@ -102,3 +102,25 @@ a few of these recipes.
      'location': 'Oakland',
      'name': 'Matthew',
      'person_id': 2}]
+
+* .. function:: areidentical(\*seqs)
+
+  Determine if sequences are identical element-wise.
+  This lazily evaluates the sequences and stops as soon as the result
+  is determined.
+
+  ::
+
+    from toolz import diff
+
+    def areidentical(*seqs):
+        return not any(diff(*seqs, default=object()))
+
+
+  Example:
+
+   >>> areidentical([1, 2, 3], (1, 2, 3))
+   True
+
+   >>> areidentical([1, 2, 3], [1, 2])
+   False

toolz/itertoolz.py

@@ -12,7 +12,7 @@
            'first', 'second', 'nth', 'last', 'get', 'concat', 'concatv',
            'mapcat', 'cons', 'interpose', 'frequencies', 'reduceby', 'iterate',
            'sliding_window', 'partition', 'partition_all', 'count', 'pluck',
-           'join', 'tail')
+           'join', 'tail', 'diff')
 
 
 def remove(predicate, seq):
@@ -815,3 +815,43 @@ def join(leftkey, leftseq, rightkey, rightseq,
             if key not in seen_keys:
                 for match in matches:
                     yield (match, right_default)
+
+
+def diff(*seqs, **kwargs):
+    """ Return those items that differ between sequences
+
+    >>> list(diff([1, 2, 3], [1, 2, 10, 100]))
+    [(3, 10)]
+
+    Shorter sequences may be padded with a ``default`` value:
+
+    >>> list(diff([1, 2, 3], [1, 2, 10, 100], default=None))
+    [(3, 10), (None, 100)]
+
+    A ``key`` function may also be applied to each item to use during
+    comparisons:
+
+    >>> list(diff(['apples', 'bananas'], ['Apples', 'Oranges'], key=str.lower))
+    [('bananas', 'Oranges')]
+    """
+    N = len(seqs)
+    if N == 1 and isinstance(seqs[0], list):
+        seqs = seqs[0]
+        N = len(seqs)
+    if N < 2:
+        raise TypeError('Too few sequences given (min 2 required)')
+    default = kwargs.get('default', no_default)
+    if default is no_default:
+        iters = zip(*seqs)
+    else:
+        iters = zip_longest(*seqs, fillvalue=default)
+    key = kwargs.get('key', None)
+    if key is None:
+        for items in iters:
+            if items.count(items[0]) != N:
+                yield items
+    else:
+        for items in iters:
+            vals = tuple(map(key, items))
+            if vals.count(vals[0]) != N:
+                yield items

toolz/tests/test_itertoolz.py

@@ -10,7 +10,8 @@
                              rest, last, cons, frequencies,
                              reduceby, iterate, accumulate,
                              sliding_window, count, partition,
-                             partition_all, take_nth, pluck, join)
+                             partition_all, take_nth, pluck, join,
+                             diff)
 from toolz.compatibility import range, filter
 from operator import add, mul
 
@@ -403,3 +404,34 @@ def test_outer_join():
     expected = set([(2, 2), (1, None), (None, 3)])
 
     assert result == expected
+
+
+def test_diff():
+    assert raises(TypeError, lambda: list(diff()))
+    assert raises(TypeError, lambda: list(diff([1, 2])))
+    assert raises(TypeError, lambda: list(diff([1, 2], 3)))
+    assert list(diff([1, 2], (1, 2), iter([1, 2]))) == []
+    assert list(diff([1, 2, 3], (1, 10, 3), iter([1, 2, 10]))) == [
+        (2, 10, 2), (3, 3, 10)]
+    assert list(diff([1, 2], [10])) == [(1, 10)]
+    assert list(diff([1, 2], [10], default=None)) == [(1, 10), (2, None)]
+    # non-variadic usage
+    assert raises(TypeError, lambda: list(diff([])))
+    assert raises(TypeError, lambda: list(diff([[]])))
+    assert raises(TypeError, lambda: list(diff([[1, 2]])))
+    assert raises(TypeError, lambda: list(diff([[1, 2], 3])))
+    assert list(diff([(1, 2), (1, 3)])) == [(2, 3)]
+
+    data1 = [{'cost': 1, 'currency': 'dollar'},
+             {'cost': 2, 'currency': 'dollar'}]
+
+    data2 = [{'cost': 100, 'currency': 'yen'},
+             {'cost': 300, 'currency': 'yen'}]
+
+    conversions = {'dollar': 1, 'yen': 0.01}
+
+    def indollars(item):
+        return conversions[item['currency']] * item['cost']
+
+    list(diff(data1, data2, key=indollars)) == [
+        ({'cost': 2, 'currency': 'dollar'}, {'cost': 300, 'currency': 'yen'})]