From 221c773daea839ecf0e50c196484bb91e3a6db33 Mon Sep 17 00:00:00 2001
From: Muriithi Frederick Muriuki
Date: Wed, 1 Sep 2021 06:18:20 +0300
Subject: Implement parsing of genotype labels

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

* gn3/db/genotypes.py: parse genotype labels
* tests/unit/db/test_genotypes.py: test that genotype labels are parsed
  correctly

  As part of parsing the genotype files into usable python data structures,
  this commit adds a function to parse the label lines (beginning with "@")
  into the appropriate values.
---
 tests/unit/db/test_genotypes.py | 17 +++++++++++++++++
 1 file changed, 17 insertions(+)
 create mode 100644 tests/unit/db/test_genotypes.py

(limited to 'tests/unit/db')

diff --git a/tests/unit/db/test_genotypes.py b/tests/unit/db/test_genotypes.py
new file mode 100644
index 0000000..0264764
--- /dev/null
+++ b/tests/unit/db/test_genotypes.py
@@ -0,0 +1,17 @@
+"""Tests gn3.db.genotypes"""
+from unittest import TestCase
+from gn3.db.genotypes import parse_genotype_labels
+
+class TestGenotypes(TestCase):
+    """Tests for functions in `gn3.db.genotypes`."""
+
+    def test_parse_genotype_labels(self):
+        self.assertEqual(
+            parse_genotype_labels([
+                "@name: test_group\t", "@filler: test_filler    ",
+                "@type:test_type", "@mat:test_mat   \t", "@pat:test_pat ",
+                "@het: test_het ", "@unk: test_unk", "@other: test_other",
+                "@brrr: test_brrr "]),
+        (("group", "test_group"), ("filler", "test_filler"),
+         ("type", "test_type"), ("mat", "test_mat"), ("pat", "test_pat"),
+         ("het", "test_het"), ("unk", "test_unk")))
-- 
cgit v1.2.3