Add ZVAL to potcar_summary_stats.json; save space by using bz2 compression instead of gz for potcar_summary_stats.json

Author: esoteric-ephemera

pymatgen/io/vasp/inputs.py

@@ -1689,7 +1689,7 @@ class PotcarSingle:
     )
 
     # used for POTCAR validation
-    potcar_summary_stats = loadfn(f"{module_dir}/potcar_summary_stats.json.gz")
+    potcar_summary_stats = loadfn(f"{module_dir}/potcar_summary_stats.json.bz2")
 
     def __init__(self, data: str, symbol: str | None = None) -> None:
         """
@@ -2369,22 +2369,26 @@ def __repr__(self) -> str:
 def _gen_potcar_summary_stats(
     append: bool = False,
     vasp_psp_dir: str | None = None,
-    summary_stats_filename: str = f"{module_dir}/potcar_summary_stats.json.gz",
+    summary_stats_filename: str = f"{module_dir}/potcar_summary_stats.json.bz2",
 ):
     """
     This function solely intended to be used for PMG development to regenerate the
-    potcar_summary_stats.json.gz file used to validate POTCARs
+    potcar_summary_stats.json.bz2 file used to validate POTCARs
 
-    THIS FUNCTION IS DESTRUCTIVE. It will completely overwrite your potcar_summary_stats.json.gz.
+    THIS FUNCTION IS DESTRUCTIVE. It will completely overwrite your potcar_summary_stats.json.bz2.
 
     Args:
-        append (bool): Change whether data is appended to the existing potcar_summary_stats.json.gz,
+        append (bool): Change whether data is appended to the existing potcar_summary_stats.json.bz2,
             or if a completely new file is generated. Defaults to False.
         PMG_VASP_PSP_DIR (str): Change where this function searches for POTCARs
             defaults to the PMG_VASP_PSP_DIR environment variable if not set. Defaults to None.
         summary_stats_filename (str): Name of the output summary stats file. Defaults to
-            '<pymatgen_install_dir>/io/vasp/potcar_summary_stats.json.gz'.
+            '<pymatgen_install_dir>/io/vasp/potcar_summary_stats.json.bz2'.
     """
+
+    if not os.path.isfile(summary_stats_filename):
+        dumpfn({func: {} for func in PotcarSingle.functional_dir}, summary_stats_filename)
+
     func_dir_exist: dict[str, str] = {}
     vasp_psp_dir = vasp_psp_dir or SETTINGS.get("PMG_VASP_PSP_DIR")
     for func in PotcarSingle.functional_dir:
@@ -2420,6 +2424,7 @@ def _gen_potcar_summary_stats(
                     "LEXCH": psp.LEXCH,
                     "VRHFIN": psp.VRHFIN.replace(" ", ""),
                     "symbol": psp.symbol,
+                    "ZVAL": psp.ZVAL,
                     **psp._summary_stats,
                 }
             )

pymatgen/io/vasp/potcar_summary_stats.json.bz2

@@ -1249,7 +1249,7 @@ def test_from_directory(self):
 def test_potcar_summary_stats() -> None:
     from pymatgen.io.vasp.inputs import module_dir
 
-    potcar_summary_stats = loadfn(f"{module_dir}/potcar_summary_stats.json.gz")
+    potcar_summary_stats = loadfn(f"{module_dir}/potcar_summary_stats.json.bz2")
 
     assert len(potcar_summary_stats) == 16
     n_potcars_per_functional = {
@@ -1278,9 +1278,9 @@ def test_potcar_summary_stats() -> None:
 
 
 def test_gen_potcar_summary_stats(tmp_path: Path, monkeypatch: MonkeyPatch) -> None:
-    """Regenerate the potcar_summary_stats.json.gz file used to validate POTCARs with scrambled POTCARs."""
+    """Regenerate the potcar_summary_stats.json.bz2 file used to validate POTCARs with scrambled POTCARs."""
     psp_path = f"{TEST_FILES_DIR}/fake_potcar_library/"
-    summ_stats_file = f"{tmp_path}/fake_potcar_summary_stats.json.gz"
+    summ_stats_file = f"{tmp_path}/fake_potcar_summary_stats.json.bz2"
     _gen_potcar_summary_stats(append=False, vasp_psp_dir=psp_path, summary_stats_filename=summ_stats_file)
 
     # only checking for two directories to save space, fake POTCAR library is big