Add new data processing utility

Issue:
https://github.com/genenetwork/gn-gemtext-threads/blob/main/topics/gn1-migration-to-gn2/partial-correlations.gmi

* gn3/data_helpers.py: New function (`partition_by`)
* tests/unit/test_data_helpers.py: Tests for new function

  Add a function that approximates Clojure's `partition-by` function, to help
  with processing the data in a more functional way.

2 files changed, 29 insertions, 1 deletions

diff --git a/gn3/data_helpers.py b/gn3/data_helpers.py
index d3f942b..b72fbc5 100644
--- a/gn3/data_helpers.py
+++ b/gn3/data_helpers.py
@@ -24,6 +24,21 @@ def partition_all(num: int, items: Sequence[Any]) -> Tuple[Tuple[Any, ...], ...]
         in reduce(
             __compute_start_stop__, iterations, tuple())])
 
+def partition_by(partition_fn, items):
+    """
+    Given a sequence `items`, return a tuple of tuples, each of which contain
+    the values in `items` partitioned such that the first item in each internal
+    tuple, when passed to `partition_function` returns True.
+
+    This is an approximation of Clojure's `partition-by` function.
+    """
+    def __partitioner__(accumulator, item):
+        if partition_fn(item):
+            return accumulator + ((item,),)
+        return accumulator[:-1] + (accumulator[-1] + (item,),)
+
+    return reduce(__partitioner__, items, tuple())
+
 def parse_csv_line(
         line: str, delimiter: str = ",",
         quoting: Optional[str] = '"') -> Tuple[str, ...]:
diff --git a/tests/unit/test_data_helpers.py b/tests/unit/test_data_helpers.py
index 39aea45..3f76344 100644
--- a/tests/unit/test_data_helpers.py
+++ b/tests/unit/test_data_helpers.py
@@ -4,7 +4,7 @@ Test functions in gn3.data_helpers
 
 from unittest import TestCase
 
-from gn3.data_helpers import partition_all, parse_csv_line
+from gn3.data_helpers import partition_by, partition_all, parse_csv_line
 
 class TestDataHelpers(TestCase):
     """
@@ -59,3 +59,16 @@ class TestDataHelpers(TestCase):
                     parse_csv_line(
                         line=line, delimiter=delimiter, quoting=quoting),
                     expected)
+
+    def test_partition_by(self):
+        for part_fn, items, expected in (
+                (lambda s: s.startswith("----"),
+                 ("------", "a", "b", "-----", "c", "----", "d", "e", "---",
+                  "f"),
+                 (("------", "a", "b"), ("-----", "c"),
+                  ("----", "d", "e", "---", "f"))),
+                (lambda x: (x % 2) == 0,
+                 (0, 1, 3, 2, 4, 5, 7, 6, 9, 1),
+                 ((0, 1, 3), (2,), (4, 5, 7), (6, 9, 1))),):
+            with self.subTest(items=items):
+                self.assertEqual(partition_by(part_fn, items), expected)