Fix incorrect reduction of dimers/polymers in standardize_formula

src/pyEQL/utils.py

@@ -7,6 +7,7 @@
 """
 
 import logging
+import re
 from collections import UserDict
 from functools import lru_cache
 from typing import Any
@@ -76,6 +77,12 @@ def standardize_formula(formula: str):
     for char in [r"‑", r"‐", r"‒", r"–", r"—", r"−"]:  # noqa: RUF001
         formula = formula.replace(char, "-")
 
+    # Do not modify any dimers etc (Phreeqc reports a small amount of
+    # "(CO2)2" in a water solution with C(4), for example.
+    _POLYMER_RE = re.compile(r"^\([A-Za-z0-9+-]+\)\d+$")
+    if _POLYMER_RE.match(formula):
+        return formula
+
     sform = Ion.from_formula(formula).reduced_formula
 
     # TODO - manual formula adjustments. May be implemented upstream in pymatgen in the future

tests/test_utils.py

@@ -62,6 +62,10 @@ def test_standardize_formula():
     assert standardize_formula("(NH4)2SO4") == "(NH4)2SO4(aq)"
     assert standardize_formula("NH4SO4-") == "NH4SO4[-1]"
 
+    # Polymers should be left intact
+    assert standardize_formula("(CO2)2") == "(CO2)2"
+    assert standardize_formula("(H2O)3") == "(H2O)3"
+
 
 def test_formula_dict():
     """