Merge branch '7-test-stringology' into 'main'

Add tests for the stringology of vizitig

Closes #7

See merge request pydisk/examples/vizitig!5

vizitig/stringology.py

@@ -34,4 +34,4 @@ def get_canonical(kmer: str) -> str:
 
 def is_canonical(kmer: str) -> bool:
     rc = reverse_complement(kmer)
-    return kmer < rc
+    return kmer <= rc

vizitig/tests/test_stringology.py

+from pytest import mark
+from vizitig import stringology
+
+
+sequences_and_revcomp = [
+    ("ATCGTAGCTGATCG", "CGATCAGCTACGAT"),
+    ("ATCGTAGCTGATC", "GATCAGCTACGAT"),
+    ("ATCGTAGCTGAT", "ATCAGCTACGAT"),
+    ("ATCGTAGCTG", "CAGCTACGAT"),
+    ("AAAAAAAAAA","TTTTTTTTTT"),
+    ("ACTGCATATGCAGT", "ACTGCATATGCAGT")
+]
+
+kmers_and_canonical = [
+    ("CGATCAGCTACGAT", "ATCGTAGCTGATCG"),
+    ("ATCGTAGCTGATC", "ATCGTAGCTGATC"),
+    ("ATCGTAGCTGAT", "ATCAGCTACGAT"),
+    ("CAGCTACGAT", "ATCGTAGCTG"),
+    ("AAAAAAAAAA","AAAAAAAAAA"),
+    ("ACTGCATATGCAGT", "ACTGCATATGCAGT")
+]
+
+kmers = [
+    "CGATCAGCTACGAT",
+    "ATCGTAGCTGATC",
+    "ATCGTAGCTGAT", 
+    "CAGCTACGAT", 
+    "AAAAAAAAAA",
+    "ACTGCATATGCAGT"
+]
+
+@mark.parametrize("seq, rseq", sequences_and_revcomp)
+def test_reverse_complement1(seq, rseq):
+    assert stringology.reverse_complement(seq) == rseq
+
+def test_is_canonical1():
+    assert stringology.is_canonical('ACGT')
+
+def test_is_canonical2():
+    assert stringology.is_canonical('CGTA')
+
+def test_is_canonical3():
+    assert not stringology.is_canonical('TACG')
+
+def test_enum_kmer():
+    assert list(stringology.enum_kmer('ACTG', 1)) == [i for i in 'ACTG']
+
+def test_enum_canonical_kmer():
+    assert list(stringology.enum_canonical_kmer('ACTG', 2)) == ['AC', 'AG', 'CA']
+
+@mark.parametrize("kmer, c_kmer", kmers_and_canonical)
+def test_get_canonical1(kmer, c_kmer):
+    assert stringology.get_canonical(kmer) == c_kmer
+
+@mark.parametrize("kmer", kmers)
+def test_enum_kmer_returns_right_kmer_count(kmer):
+    for m in range(len(kmer)):
+        assert len(list(stringology.enum_kmer(kmer, m))) + m - 1 == len(kmer)
+
+@mark.parametrize("kmer", kmers)
+def test_enum_canonical_kmer_returns_right_kmer_count(kmer):
+    for m in range(len(kmer)):
+        assert len(list(stringology.enum_canonical_kmer(kmer, m))) + m - 1 == len(kmer)
+
+@mark.parametrize("kmer", kmers)
+def test_canonicality_of_enum_canonical_kmer(kmer):
+    for m in range(len(kmer)):
+        assert all(stringology.is_canonical(kmer2) for kmer2 in stringology.enum_canonical_kmer(kmer, m))
\ No newline at end of file