From e194d8118f871cfb55bfca5c0721aa8926156f48 Mon Sep 17 00:00:00 2001
From: Jeremy A Gray <jeremy.a.gray@gmail.com>
Date: Sat, 23 Sep 2023 11:48:00 -0500
Subject: [PATCH] fix(parser): handle decimal subscripts

Translate a Unicode decimal point in a subscript as a text decimal
point.  Use `.` as the decimal point operator and `..` as the hydrate
operator.  Add zinc nitrate example from bjodah/chempy#207.

Signed-off-by: Jeremy A Gray <jeremy.a.gray@gmail.com>
---
 chempy/util/parsing.py            |  8 ++++---
 chempy/util/tests/test_parsing.py | 38 +++++++++++++++++++++++++++++++
 2 files changed, 43 insertions(+), 3 deletions(-)

diff --git a/chempy/util/parsing.py b/chempy/util/parsing.py
index 0313545c..b4f89bb9 100644
--- a/chempy/util/parsing.py
+++ b/chempy/util/parsing.py
@@ -95,7 +95,7 @@ def _get_formula_parser():
                  | '{' formula '}'
                  | '[' formula ']' ) count prime charge?
         formula :: term+
-        hydrate :: '.' count? formula
+        hydrate :: '..' count? formula
         state :: '(' ( 's' | 'l' | 'g' | 'aq' | 'cr' ) ')'
         compound :: count formula hydrate? state?
 
@@ -600,9 +600,11 @@ def formula_to_latex(formula, prefixes=None, infixes=None, **kwargs):
     )
 
 
-_unicode_sub = {}
+_unicode_sub = {
+    ".": ".",
+}
 
-for k, v in enumerate("₀₁₂₃₄₅₆₇₈₉"):
+for k, v in enumerate("₀₁₂₃₄₅₆₇₈₉."):
     _unicode_sub[str(k)] = v
 
 _unicode_sup = {
diff --git a/chempy/util/tests/test_parsing.py b/chempy/util/tests/test_parsing.py
index 67386278..12ebffa8 100644
--- a/chempy/util/tests/test_parsing.py
+++ b/chempy/util/tests/test_parsing.py
@@ -11,6 +11,7 @@
     parsing_library,
     to_reaction,
 )
+
 from ..testing import requires
 
 
@@ -625,6 +626,22 @@ def test_formula_to_latex_caged(species, latex):
         ("[Fe(H2O)6][Fe(CN)6]..19H2O(aq)", r"[Fe(H₂O)₆][Fe(CN)₆]·19H₂O(aq)"),
         ("[Fe(CN)6]-3", r"[Fe(CN)₆]³⁻"),
         ("[Fe(CN)6]-3(aq)", r"[Fe(CN)₆]³⁻(aq)"),
+        (
+            "Ca2.832Fe0.6285Mg5.395(CO3)6",
+            r"Ca₂.₈₃₂Fe₀.₆₂₈₅Mg₅.₃₉₅(CO₃)₆",
+        ),
+        (
+            "Ca2.832Fe0.6285Mg5.395(CO3)6(s)",
+            r"Ca₂.₈₃₂Fe₀.₆₂₈₅Mg₅.₃₉₅(CO₃)₆(s)",
+        ),
+        (
+            "Ca2.832Fe0.6285Mg5.395(CO3)6..8H2O(s)",
+            r"Ca₂.₈₃₂Fe₀.₆₂₈₅Mg₅.₃₉₅(CO₃)₆·8H₂O(s)",
+        ),
+        (
+            "Zn(NO3)2..6H2O",
+            r"Zn(NO₃)₂·6H₂O",
+        ),
     ],
 )
 @requires(parsing_library)
@@ -692,8 +709,29 @@ def test_formula_to_unicode_caged(species, unicode):
         ),
         ("[Fe(CN)6]-3", r"[Fe(CN)<sub>6</sub>]<sup>3-</sup>"),
         ("[Fe(CN)6]-3(aq)", r"[Fe(CN)<sub>6</sub>]<sup>3-</sup>(aq)"),
+        (
+            "Ca2.832Fe0.6285Mg5.395(CO3)6",
+            r"Ca<sub>2.832</sub>Fe<sub>0.6285</sub>Mg<sub>5.395</sub>(CO<sub>3</sub>)<sub>6</sub>",
+        ),
+        (
+            "Ca2.832Fe0.6285Mg5.395(CO3)6(s)",
+            r"Ca<sub>2.832</sub>Fe<sub>0.6285</sub>Mg<sub>5.395</sub>(CO<sub>3</sub>)<sub>6</sub>(s)",
+        ),
+        (
+            "Ca2.832Fe0.6285Mg5.395(CO3)6..8H2O(s)",
+            r"Ca<sub>2.832</sub>Fe<sub>0.6285</sub>Mg<sub>5.395</sub>(CO<sub>3</sub>)<sub>6</sub>&sdot;8H<sub>2</sub>O(s)",
+        ),
+        (
+            "Ca2.832Fe0.6285Mg5.395(CO3)6..8H2O(s)",
+            r"Ca<sub>2.832</sub>Fe<sub>0.6285</sub>Mg<sub>5.395</sub>(CO<sub>3</sub>)<sub>6</sub>&sdot;8H<sub>2</sub>O(s)",
+        ),
+        (
+            "Zn(NO3)2..6H2O",
+            r"Zn(NO<sub>3</sub>)<sub>2</sub>&sdot;6H<sub>2</sub>O",
+        ),
     ],
 )
+
 @requires(parsing_library)
 def test_formula_to_html(species, html):
     assert formula_to_html(species) == html