From 783f302c5d4729eb0b5fb6ba79180b7cd97764a5 Mon Sep 17 00:00:00 2001
From: Frederick Muriuki Muriithi
Date: Mon, 25 Oct 2021 19:12:24 +0300
Subject: Implement `partition_all` function

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_all)
* tests/unit/test_data_helpers.py: tests for function
  `gn3.data_helpers.partition_all`

  As part of migrating some functions that access the database, this commit
  extracts generic processes that can be accomplished on data, and implements
  the `partition_all` function, that is equivalent to Clojure's
  `partition-all` function.
---
 tests/unit/test_data_helpers.py | 37 +++++++++++++++++++++++++++++++++++++
 1 file changed, 37 insertions(+)
 create mode 100644 tests/unit/test_data_helpers.py

(limited to 'tests/unit/test_data_helpers.py')

diff --git a/tests/unit/test_data_helpers.py b/tests/unit/test_data_helpers.py
new file mode 100644
index 0000000..1eec3cc
--- /dev/null
+++ b/tests/unit/test_data_helpers.py
@@ -0,0 +1,37 @@
+"""
+Test functions in gn3.data_helpers
+"""
+
+from unittest import TestCase
+
+from gn3.data_helpers import partition_all
+
+class TestDataHelpers(TestCase):
+    """
+    Test functions in gn3.data_helpers
+    """
+
+    def test_partition_all(self):
+        """
+        Test that `gn3.data_helpers.partition_all` partitions sequences as expected.
+
+        Given:
+            - `num`: The number of items per partition
+            - `items`: A sequence of items
+        When:
+            - The arguments above are passed to the `gn3.data_helpers.partition_all`
+        Then:
+            - Return a new sequence with partitions, each of which has `num`
+              items in the same order as those in `items`, save for the last
+              partition which might have fewer items than `num`.
+        """
+        for count, items, expected in (
+                (1, [0, 1, 2, 3], ((0,), (1,), (2,), (3,))),
+                (3, (0, 1, 2, 3, 4, 5, 6, 7, 8, 9),
+                 ((0, 1, 2), (3, 4, 5), (6, 7, 8), (9, ))),
+                (4, [0, 1, 2, 3, 4, 5, 6, 7, 8, 9],
+                 ((0, 1, 2, 3), (4, 5, 6, 7), (8, 9))),
+                (13, [0, 1, 2, 3, 4, 5, 6, 7, 8, 9],
+                 ((0, 1, 2, 3, 4, 5, 6, 7, 8, 9), ))):
+            with self.subTest(n=count, items=items):
+                self.assertEqual(partition_all(count, items), expected)
-- 
cgit v1.2.3


From ff23701bbfd90799f04fdf21c482f113bb408e34 Mon Sep 17 00:00:00 2001
From: Frederick Muriuki Muriithi
Date: Mon, 1 Nov 2021 07:09:26 +0300
Subject: Parse single line from CSV file

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

* gn3/data_helpers.py: New function (parse_csv_line)
* tests/unit/test_data_helpers.py: Add tests for new function (parse_csv_line)

  Add a function to parse a single line from a CSV file.
---
 gn3/data_helpers.py             | 13 ++++++++++++-
 tests/unit/test_data_helpers.py | 26 +++++++++++++++++++++++++-
 2 files changed, 37 insertions(+), 2 deletions(-)

(limited to 'tests/unit/test_data_helpers.py')

diff --git a/gn3/data_helpers.py b/gn3/data_helpers.py
index f0d971e..741a885 100644
--- a/gn3/data_helpers.py
+++ b/gn3/data_helpers.py
@@ -5,7 +5,7 @@ data structures.
 
 from math import ceil
 from functools import reduce
-from typing import Any, Tuple, Sequence
+from typing import Any, Tuple, Sequence, Optional
 
 def partition_all(num: int, items: Sequence[Any]) -> Tuple[Tuple[Any, ...], ...]:
     """
@@ -23,3 +23,14 @@ def partition_all(num: int, items: Sequence[Any]) -> Tuple[Tuple[Any, ...], ...]
         tuple(items[start:stop]) for start, stop # type: ignore[has-type]
         in reduce(
             __compute_start_stop__, iterations, tuple())])
+
+def parse_csv_line(
+        line:str, delimiter: str = ",", quoting:Optional[str] = '"') -> Tuple[str, ...]:
+    """
+    Parses a line from a CSV file into a tuple of strings.
+
+    This is a migration of the `web.webqtl.utility.webqtlUtil.readLineCSV`
+    function in GeneNetwork1.
+    """
+    return tuple(
+        col.strip("{} \t\n".format(quoting)) for col in line.split(delimiter))
diff --git a/tests/unit/test_data_helpers.py b/tests/unit/test_data_helpers.py
index 1eec3cc..39aea45 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
+from gn3.data_helpers import partition_all, parse_csv_line
 
 class TestDataHelpers(TestCase):
     """
@@ -35,3 +35,27 @@ class TestDataHelpers(TestCase):
                  ((0, 1, 2, 3, 4, 5, 6, 7, 8, 9), ))):
             with self.subTest(n=count, items=items):
                 self.assertEqual(partition_all(count, items), expected)
+
+    def test_parse_csv_line(self):
+        """
+        Test parsing a single line from a CSV file
+
+        Given:
+            - `line`: a line read from a csv file
+            - `delimiter`: the expected delimiter in the csv file
+            - `quoting`: the quoting enclosing each column in the csv file
+        When:
+            - `line` is parsed with the `parse_csv_file` with the given
+               parameters
+        Then:
+            - return a tuple of the columns in the CSV file, without the
+              delimiter and quoting
+        """
+        for line, delimiter, quoting, expected in (
+                ('"this","is","a","test"', ",", '"', ("this", "is", "a", "test")),
+                ('"this","is","a","test"', ",", None, ('"this"', '"is"', '"a"', '"test"'))):
+            with self.subTest(line=line, delimiter=delimiter, quoting=quoting):
+                self.assertEqual(
+                    parse_csv_line(
+                        line=line, delimiter=delimiter, quoting=quoting),
+                    expected)
-- 
cgit v1.2.3