quick-fix exotic branch swapping in find_isomorphs

CHANGELOG.md

@@ -9,7 +9,7 @@
 - Added setuptools to required_installs to support pip installation beyond `pip 25.0` (94646ad)
 - Added pyproject.toml to support pip installation beyond `pip 25.0` (94646ad)
 - Added CITATION.bib to allow for even easier citation of glycowork (a64f694)
-- Reworked user interface of the `glycoworkGUI`
+- Reworked user interface of the `glycoworkGUI` (77bbfa3)
 
 ### Changed 🔄
 - Bumped minimum supported Python version to 3.9 (3.8 is no longer supported, see https://devguide.python.org/versions/) (4960c5c)

glycowork/motif/processing.py

@@ -186,7 +186,7 @@ def find_isomorphs(glycan: str # Glycan in IUPAC-condensed format
   temp = set()
   # Starting branch swapped with next side branch again to also include double branch swapped isomorphs
   for k in out_list:
-    temp.add(re.sub(r'^(.*?)\[((?:[^\[\]]|\[[^\[\]]*\])*)\]', r'\2[\1]', k, 1))
+    temp.add(re.sub(r'^(.*?)\[((?:[^\[\]]|\[[^\[\]]*\])*?)\]((?:\[[^\[\]]*\])*?)([A-Z][a-z0-9]*[A-Z]?[a-z0-9]*\([ab?][1-2]-[1-9?]\))', r'\2[\1]\3\4', k, 1))
     if k.count('[') > 1 and k.index('[') > 0 and find_nth(k, '[', 2) > k.index(']') and (find_nth(k, ']', 2) < find_nth(k, '[', 3) or k.count('[') == 2):
       temp.add(re.sub(r'^(.*?)\[(.*?)\](.*?)\[(.*?)\]', r'\4[\1[\2]\3]', k, 1))
   out_list.update(temp)

tests/test_core_functions.py

@@ -741,6 +741,7 @@ def test_canonicalize_iupac():
     assert canonicalize_iupac("Gal(b1-4)GlcNAc(b1-2)Man(a1-3)[Gal(b1-4)GlcNAc(b1-2)Man(a1-6)][Xyl(b1-2)]Man(b1-4)GlcNAc(b1-4)[Fuc(a1-6)][Fuc(a1-3)]GlcNAc") == "Gal(b1-4)GlcNAc(b1-2)Man(a1-3)[Gal(b1-4)GlcNAc(b1-2)Man(a1-6)][Xyl(b1-2)]Man(b1-4)GlcNAc(b1-4)[Fuc(a1-3)][Fuc(a1-6)]GlcNAc"
     assert canonicalize_iupac("Gal(b1-4)GlcNAc(b1-2)[Gal(b1-4)GlcNAc(b1-6)]Man(a1-6)[Gal(b1-4)GlcNAc(b1-2)[Gal(b1-4)GlcNAc(b1-4)]Man(a1-3)]Man(b1-4)GlcNAc(b1-4)[Fuc(a1-6)]GlcNAc") == "Gal(b1-4)GlcNAc(b1-2)[Gal(b1-4)GlcNAc(b1-4)]Man(a1-3)[Gal(b1-4)GlcNAc(b1-2)[Gal(b1-4)GlcNAc(b1-6)]Man(a1-6)]Man(b1-4)GlcNAc(b1-4)[Fuc(a1-6)]GlcNAc"
     assert canonicalize_iupac("Galβ1–4GlcNAcβ1–2(Fucα1–3(Galβ1–4)GlcNAcβ1–4)Manα1–3(Galβ1–4GlcNAcβ1–2(Galβ1–4GlcNAcβ1–6)Manα1–6)Manβ1–4GlcNAcβ1–4GlcNAc") == "Gal(b1-4)GlcNAc(b1-2)[Fuc(a1-3)[Gal(b1-4)]GlcNAc(b1-4)]Man(a1-3)[Gal(b1-4)GlcNAc(b1-2)[Gal(b1-4)GlcNAc(b1-6)]Man(a1-6)]Man(b1-4)GlcNAc(b1-4)GlcNAc"
+    assert canonicalize_iupac("Fuc(a1-3)[Gal(b1-4)]GlcNAc(b1-2)[GlcNAc(b1-4)]Man(a1-3)[Man(a1-3)[Man(a1-6)]Man(a1-6)]Man(b1-4)GlcNAc(b1-4)GlcNAc") == "Fuc(a1-3)[Gal(b1-4)]GlcNAc(b1-2)[GlcNAc(b1-4)]Man(a1-3)[Man(a1-3)[Man(a1-6)]Man(a1-6)]Man(b1-4)GlcNAc(b1-4)GlcNAc"
     # Test other nomenclatures
     assert canonicalize_iupac("DManpa1-6DManpb1-4DGlcpNAcb1-4[LFucpa1-6]DGlcpNAcb1-OH") == "Man(a1-6)Man(b1-4)GlcNAc(b1-4)[Fuc(a1-6)]GlcNAc"
     assert canonicalize_iupac("Neup5Aca2-3DGalpb1-4DGlcpNAcb1-3DGalpb1-3DGalpb1-4DGlcpb1-OH") == "Neu5Ac(a2-3)Gal(b1-4)GlcNAc(b1-3)Gal(b1-3)Gal(b1-4)Glc"