From 660ba7a584fae5b5d8bb1095614f0104c9d89049 Mon Sep 17 00:00:00 2001
From: Ryan Kingsbury <rkingsbury@users.noreply.github.com>
Date: Wed, 31 Jul 2024 11:56:21 -0400
Subject: [PATCH] Fix Ion formula parsing bug; add more special formulas
 (#3942)

* fix Ion parsing bug introduced by commit
https://github.com/materialsproject/pymatgen/commit/b4a70eef7666743459a6e242a0efc18762ff3b49

* Ion: special handling of CH4, NH4, N3-, SCN-, formate, oxalate

* pre-commit auto-fixes

* Element / Species - add n_electrons

* Revert "Element / Species - add n_electrons"

This reverts commit 97ea1807302fb1dbaa34f012ef07d509dcc541ce.

---------

Co-authored-by: pre-commit-ci[bot] <66853113+pre-commit-ci[bot]@users.noreply.github.com>
---
 src/pymatgen/core/ion.py | 35 +++++++++++++++++++++++++++++++++--
 tests/core/test_ion.py   |  9 ++++++++-
 2 files changed, 41 insertions(+), 3 deletions(-)

diff --git a/src/pymatgen/core/ion.py b/src/pymatgen/core/ion.py
index c3d7cf3271c..52408713463 100644
--- a/src/pymatgen/core/ion.py
+++ b/src/pymatgen/core/ion.py
@@ -173,9 +173,10 @@ def get_reduced_formula_and_factor(
         el_amt_dict = {k: int(round(v)) for k, v in comp.get_el_amt_dict().items()}
         formula, factor = reduce_formula(el_amt_dict, iupac_ordering=iupac_ordering)
 
-        if (self.composition.get("H") and self.composition.get("O")) is not None:
+        # This line checks specifically that the contains an equal amount of O and H. When that is the case,
+        # they should be displayed as "OH" rather than "HO".
+        if self.composition.get("H") == self.composition.get("O"):
             formula = formula.replace("HO", "OH")
-
         if nH2O > 0:
             formula += f".{nH2O}H2O"
 
@@ -187,6 +188,13 @@ def get_reduced_formula_and_factor(
         elif formula == "H2CO":
             formula = "CH3COOH"
             factor /= 2
+        # phosphoric acid system
+        elif formula == "PH3O4":
+            formula = "H3PO4"
+        elif formula == "PHO4":
+            formula = "HPO4"
+        elif formula == "P(HO2)2":
+            formula = "H2PO4"
         # acetate
         elif formula == "H3(CO)2":
             formula = "CH3COO"
@@ -205,6 +213,29 @@ def get_reduced_formula_and_factor(
         elif formula == "O" and factor % 3 == 0:
             formula = "O3"
             factor /= 3
+        # ammonia
+        elif formula == "H4N":
+            formula = "NH4"
+        elif formula == "H3N":
+            formula = "NH3"
+        # methane
+        elif formula == "H4C":
+            formula = "CH4"
+        # thiocyanate
+        elif formula == "CSN":
+            formula = "SCN"
+        # triiodide, nitride, an phosphide
+        elif formula in ["I", "N", "P"] and self.charge == -1:
+            formula += "3"
+            factor /= 3
+        # formate # codespell:ignore
+        elif formula == "HCOO":
+            formula = "HCO2"
+        # oxalate
+        elif formula == "CO2":
+            formula = "C2O4"
+            factor *= 2
+        # diatomic gases
         elif formula in {"O", "N", "F", "Cl", "H"} and factor % 2 == 0:
             formula += "2"
             factor /= 2
diff --git a/tests/core/test_ion.py b/tests/core/test_ion.py
index f501287ed6d..5e5f5482dfb 100644
--- a/tests/core/test_ion.py
+++ b/tests/core/test_ion.py
@@ -46,6 +46,7 @@ def test_charge_from_formula(self):
         assert Ion.from_formula("SO42-").charge == -1
         assert Ion.from_formula("SO4--").charge == -2
         assert Ion.from_formula("SO4[--]").charge == -2
+        assert Ion.from_formula("N3-").charge == -1
 
         assert Ion.from_formula("Na[+-+]").charge == 1
 
@@ -59,19 +60,25 @@ def test_special_formulas(self):
             ("O3", "O3(aq)"),
             ("O2", "O2(aq)"),
             ("N2", "N2(aq)"),
+            ("NaOH", "NaOH(aq)"),
             ("H4O4", "H2O2(aq)"),
             ("OH-", "OH[-1]"),
+            ("H2PO4-", "H2PO4[-1]"),
             ("CH3COO-", "CH3COO[-1]"),
             ("CH3COOH", "CH3COOH(aq)"),
             ("CH3OH", "CH3OH(aq)"),
             ("H4CO", "CH3OH(aq)"),
+            ("CH4", "CH4(aq)"),
+            ("NH4+", "NH4[+1]"),
+            ("NH3", "NH3(aq)"),
+            ("N3-", "N3[-1]"),
+            ("HCOO-", "HCO2[-1]"),
             ("C2H6O", "C2H5OH(aq)"),
             ("C3H8O", "C3H7OH(aq)"),
             ("C4H10O", "C4H9OH(aq)"),
             ("Fe(OH)4+", "Fe(OH)4[+1]"),
             ("Zr(OH)4", "Zr(OH)4(aq)"),
         ]
-
         for tup in special_formulas:
             assert Ion.from_formula(tup[0]).reduced_formula == tup[1]