standardize_formula: parse super and subscripts in ion formulae

CHANGELOG.md

@@ -5,7 +5,20 @@ All notable changes to this project will be documented in this file.
 The format is based on [Keep a Changelog](https://keepachangelog.com/en/1.0.0/),
 and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0.html).
 
-## Unreleased
+## [1.0.3] - 2024-07-20
+
+### Fixed
+
+- `standardize_formula`: Fix incorrect display of additional formulas, including methane which
+  was shown as "H4C(aq)", other tri-anions (N3-, P3-), and a variety of haloacetic acids. For
+  example, tricholoracetic acid was previously shown as `'C2Cl3O2[-1]'` but will now display
+  as `'CCl3COO[-1]'`.
+
+### Added
+
+- `standardize_formula`: `pyEQL` can now parse ion formulas that contain unicode superscript
+  or subscript characters, which makes input even more flexible. For example, `"PO₄³⁻"` and `"Co²⁺"`
+  will now standardize correctly to `"PO4[-3]"` and `"Co[+2]"`, respectively.
 
 ### Changed
 

docs/chemistry.md

@@ -23,7 +23,8 @@ Here are some examples:
 | Sodium Sulfate  |      "Na2(SO4)" or "Na2SO4"       |    "Na(SO4)(aq)"    |
 | Sodium Ion      | "Na+", "Na+1", "Na1+", or "Na[+]" |      "Na[+1]"       |
 | Magnesium Ion   |    "Mg+2", "Mg++", or "Mg[++]"    |      "Mg[+2]"       |
-| Methanol        |          "CH3OH", "CH4O"          |    "'CH3OH(aq)'"    |
+| Methanol        |          "CH3OH", "CH4O"          |     "CH3OH(aq)"     |
+| Phosphate Ion   |         "PO4-3", "PO₄³⁻"          |      "PO4[-3]"      |
 
 Specifically, `standardize_formula` uses `Ion.from_formula(<formula>).reduced_formla` (shown in the right hand column
 of the table) to identify solutes. Notice that for charged species, the charges are always placed inside square brackets
@@ -33,6 +34,11 @@ by `(aq)` to disambiguate them from solids.
 ```{important}
 **When writing multivalent ion formulas, it is strongly recommended that you put the charge number AFTER the + or -
 sign** (e.g., type "Mg+2" NOT "Mg2+"). The latter formula is ambiguous - it could mean $Mg_2^+$ or $Mg^{+2}$ and it will be processed incorrectly into `Mg[+0.5]`
+
+There is **one exception** to the rule above. If you really want to list the charge number
+first , you can use unicode superscript characters (e.g., "Co²⁺"), and `pyEQL` will understand
+these regardless of the order of the `+` and the `2`. So you can write "Co²⁺" and it will be
+correctly standardized to `Co[+2]`
 ```
 
 (manual-testing)=

src/pyEQL/utils.py

@@ -60,6 +60,18 @@ def standardize_formula(formula: str):
         be enclosed in square brackets to remove any ambiguity in the meaning of the formula. For example, 'Na+',
         'Na+1', and 'Na[+]' will all standardize to "Na[+1]"
     """
+    # fix permuted sign and charge number (e.g. Co2+)
+    for str, rep in zip(["²⁺", "³⁺", "⁴⁺", "²⁻", "³⁻", "⁴⁻"], ["+2", "+3", "+4", "-2", "-3", "-4"]):
+        formula = formula.replace(str, rep)
+
+    # replace superscripts with non superscripts
+    for char, rep in zip("⁻⁺⁰¹²³⁴⁵⁶⁷⁸⁹", "-+0123456789"):
+        formula = formula.replace(char, rep)
+
+    # replace subscripts with non subscripts
+    for char, rep in zip("₀₁₂₃₄₅₆₇₈₉", "0123456789"):
+        formula = formula.replace(char, rep)
+
     sform = Ion.from_formula(formula).reduced_formula
 
     # TODO - manual formula adjustments. May be implemented upstream in pymatgen in the future
@@ -81,15 +93,49 @@ def standardize_formula(formula: str):
     # thiocyanate
     elif sform == "CSN[-1]":
         sform = "SCN[-1]"
-    # triiodide
+    # triiodide, nitride, an phosphide
     elif sform == "I[-0.33333333]":
         sform = "I3[-1]"
+    elif sform == "N[-0.33333333]":
+        sform = "N3[-1]"
+    elif sform == "P[-0.33333333]":
+        sform = "P3[-1]"
     # formate
     elif sform == "HCOO[-1]":
         sform = "HCO2[-1]"
     # oxalate
     elif sform == "CO2[-1]":
         sform = "C2O4[-2]"
+    # triflate
+    elif sform == "CS(OF)3[-1]":
+        sform = "CF3SO3[-1]"
+    # haloacetic acids of F, Cl, Br, I
+    elif sform == "C2Cl3O2[-1]":
+        sform = "CCl3COO[-1]"
+    elif sform == "C2O2F3[-1]":
+        sform = "CF3COO[-1]"
+    elif sform == "C2I3O2[-1]":
+        sform = "CI3COO[-1]"
+    elif sform == "C2Br3O2[-1]":
+        sform = "CBr3COO[-1]"
+
+    # Cl+F
+    elif sform == "C2Cl2O2F[-1]":
+        sform = "CFCl2COO[-1]"
+    elif sform == "C2Cl(OF)2[-1]":
+        sform = "CF2ClCOO[-1]"
+
+    # Cl+Br
+    elif sform == "C2Br(ClO)2[-1]":
+        sform = "CBrCl2COO[-1]"
+    elif sform == "C2Br2ClO2[-1]":
+        sform = "CBr2ClCOO[-1]"
+
+    # Cl+I
+    elif sform == "C2I(ClO)2[-1]":
+        sform = "CICl2COO[-1]"
+    elif sform == "C2I2ClO2[-1]":
+        sform = "CI2ClCOO[-1]"
 
     # TODO - consider adding recognition of special formulas like MeOH for methanol or Cit for citrate
     return sform

tests/test_utils.py

@@ -26,12 +26,32 @@ def test_standardize_formula():
     assert standardize_formula("H2PO4-") == "H2PO4[-1]"
     assert standardize_formula("SCN-") == "SCN[-1]"
     assert standardize_formula("I3-") == "I3[-1]"
+    assert standardize_formula("N3-") == "N3[-1]"
+    assert standardize_formula("P3-") == "P3[-1]"
     assert standardize_formula("HCOO-") == "HCO2[-1]"
     assert standardize_formula("CO2-1") == "C2O4[-2]"
     assert standardize_formula("C2O4--") == "C2O4[-2]"
     assert standardize_formula("H3PO4") == "H3PO4(aq)"
     assert standardize_formula("H2SO4") == "H2SO4(aq)"
     assert standardize_formula("HClO4") == "HClO4(aq)"
+    assert standardize_formula("CF3SO3-") == "CF3SO3[-1]"
+    # superscripts, subscripts, and permuted sign/charge number
+    assert standardize_formula("PO₄³⁻") == "PO4[-3]"
+    assert standardize_formula("Co²⁺") == "Co[+2]"
+    # haloacetic acids
+    assert standardize_formula("CCl3COO-") == "CCl3COO[-1]"
+    assert standardize_formula("CF3COO-") == "CF3COO[-1]"
+    assert standardize_formula("CI3COO-") == "CI3COO[-1]"
+    assert standardize_formula("CBr3COO-") == "CBr3COO[-1]"
+    # Cl+F
+    assert standardize_formula("CCl2FCOO-") == "CFCl2COO[-1]"
+    assert standardize_formula("CClF2COO-") == "CF2ClCOO[-1]"
+    # Cl+I
+    assert standardize_formula("CCl2ICOO-") == "CICl2COO[-1]"
+    assert standardize_formula("CClI2COO-") == "CI2ClCOO[-1]"
+    # Cl+Br
+    assert standardize_formula("CBrCl2COO-") == "CBrCl2COO[-1]"
+    assert standardize_formula("CBr2ClCOO-") == "CBr2ClCOO[-1]"
 
 
 def test_formula_dict():