From cc4bf0a58bfc50d506318b6017771b0375dd1921 Mon Sep 17 00:00:00 2001
From: Min-Hsueh Chiu <peter810601@gmail.com>
Date: Thu, 30 Jul 2026 15:29:40 -0700
Subject: [PATCH 1/2] fix htmlify_spacegroup and use pymatgen's
 unicodeify_spacegroup

---
 .../emmet/core/featurization/robocrys/util.py | 49 ++-----------------
 emmet-core/emmet/core/io/pymatgen.py          |  1 +
 .../tests/featurization/robocrys/test_util.py | 10 +++-
 3 files changed, 13 insertions(+), 47 deletions(-)

diff --git a/emmet-core/emmet/core/featurization/robocrys/util.py b/emmet-core/emmet/core/featurization/robocrys/util.py
index f01c773c68..e93fe990e1 100644
--- a/emmet-core/emmet/core/featurization/robocrys/util.py
+++ b/emmet-core/emmet/core/featurization/robocrys/util.py
@@ -21,7 +21,7 @@
 from collections import defaultdict
 from typing import TYPE_CHECKING
 
-from emmet.core.io.pymatgen import Element, Species, get_el_sp, latexify_spacegroup
+from emmet.core.io.pymatgen import Element, Species, get_el_sp
 
 if TYPE_CHECKING:
     from pathlib import Path
@@ -215,51 +215,10 @@ def superscript_number(string):
     return string
 
 
-def unicodeify_spacegroup(spacegroup_symbol: str) -> str:
-    """Formats a spacegroup using unicode symbols.
-
-    E.g. Fd-3m -> Fd̅3m
-
-    Args:
-        spacegroup_symbol: A spacegroup symbol.
-
-    Returns:
-        The unicode formatted spacegroup symbol.
-    """
-    subscript_unicode_map = {
-        0: "₀",
-        1: "₁",
-        2: "₂",
-        3: "₃",
-        4: "₄",
-        5: "₅",
-        6: "₆",
-        7: "₇",
-        8: "₈",
-        9: "₉",
-    }
-
-    symbol = latexify_spacegroup(spacegroup_symbol)
-
-    for number, unicode_number in subscript_unicode_map.items():
-        symbol = symbol.replace("$_{" + str(number) + "}$", unicode_number)
-
-    overline = "\u0305"  # u"\u0304" (macron) is also an option
-    for char, rep in {
-        "$\\overline{": overline,
-        "$": "",
-        "{": "",
-        "}": "",
-    }.items():
-        symbol = symbol.replace(char, rep)
-
-    return symbol
-
-
 def htmlify_spacegroup(spacegroup_symbol: str) -> str:
     """Formats a spacegroup using unicode symbols.
 
-    E.g. P-42_1m -> P̅42<sub>1</sub>m
+    E.g. P-42_1m -> P4̅2<sub>1</sub>m
 
     Args:
         spacegroup_symbol: A spacegroup symbol.
@@ -268,8 +227,8 @@ def htmlify_spacegroup(spacegroup_symbol: str) -> str:
         The html formatted spacegroup symbol.
     """
     overline = "\u0305"  # u"\u0304" (macron) is also an option
-    symbol = re.sub(r"_(\d+)", r"<sub>\1</sub>", spacegroup_symbol)
-    symbol = re.sub(r"-(\d)", rf"{overline}\1", symbol)
+    symbol = re.sub(r"_(\d)", r"<sub>\1</sub>", spacegroup_symbol)
+    symbol = re.sub(r"-(\d)", rf"\1{overline}", symbol)
     return symbol
 
 
diff --git a/emmet-core/emmet/core/io/pymatgen.py b/emmet-core/emmet/core/io/pymatgen.py
index c898406672..ff3d62c54a 100644
--- a/emmet-core/emmet/core/io/pymatgen.py
+++ b/emmet-core/emmet/core/io/pymatgen.py
@@ -18,6 +18,7 @@
     "htmlify": "util.string",
     "latexify": "util.string",
     "latexify_spacegroup": "util.string",
+    "unicodeify_spacegroup": "util.string",
     "unicodeify": "util.string",
     "Lattice": "core.lattice",
     "Specie": "core.periodic_table",
diff --git a/emmet-core/tests/featurization/robocrys/test_util.py b/emmet-core/tests/featurization/robocrys/test_util.py
index 1b2de881a2..20d221301a 100644
--- a/emmet-core/tests/featurization/robocrys/test_util.py
+++ b/emmet-core/tests/featurization/robocrys/test_util.py
@@ -88,12 +88,18 @@ def test_get_formatted_el():
 
 def test_unicodeify_spacegroup():
     spg_symbol = unicodeify_spacegroup("P-42_1m")
-    assert spg_symbol == "P̅42₁m"
+    assert spg_symbol == "P4̅2₁m"
+
+    spg_symbol2 = unicodeify_spacegroup("P2_12_12_1")
+    assert spg_symbol2 == "P2₁2₁2₁"
 
 
 def test_htmlify_spacegroup():
     spg_symbol = htmlify_spacegroup("P-42_1m")
-    assert spg_symbol == "P̅42<sub>1</sub>m"
+    assert spg_symbol == "P4̅2<sub>1</sub>m"
+
+    spg_symbol2 = htmlify_spacegroup("P2_12_12_1")
+    assert spg_symbol2 == "P2<sub>1</sub>2<sub>1</sub>2<sub>1</sub>"
 
 
 def test_load_condense_structure_json(test_condensed_structures):

From 107cca640457cdb62dca940c65af0a0bc38fb2cf Mon Sep 17 00:00:00 2001
From: Min-Hsueh Chiu <peter810601@gmail.com>
Date: Thu, 30 Jul 2026 15:39:09 -0700
Subject: [PATCH 2/2] add back unicodeify_spacegroup

---
 emmet-core/emmet/core/featurization/robocrys/util.py | 4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

diff --git a/emmet-core/emmet/core/featurization/robocrys/util.py b/emmet-core/emmet/core/featurization/robocrys/util.py
index e93fe990e1..40e78396b1 100644
--- a/emmet-core/emmet/core/featurization/robocrys/util.py
+++ b/emmet-core/emmet/core/featurization/robocrys/util.py
@@ -21,11 +21,13 @@
 from collections import defaultdict
 from typing import TYPE_CHECKING
 
-from emmet.core.io.pymatgen import Element, Species, get_el_sp
+from emmet.core.io.pymatgen import Element, Species, get_el_sp, unicodeify_spacegroup
 
 if TYPE_CHECKING:
     from pathlib import Path
 
+__all__ = ["unicodeify_spacegroup"]
+
 
 def _get_common_formulas() -> dict[str, str]:
     """Retrieve common formula information from stored data."""