Reapply zopen explicit UTF-8 encoding, enable optional EncodingWarning PEP 597 in tests

.github/workflows/test.yml

@@ -54,8 +54,9 @@ jobs:
     runs-on: ${{ matrix.config.os }}
 
     env:
-      PMG_MAPI_KEY: ${{ secrets.PMG_MAPI_KEY }}
       MPLBACKEND: Agg  # non-interactive backend for matplotlib
+      PMG_MAPI_KEY: ${{ secrets.PMG_MAPI_KEY }}
+      PYTHONWARNDEFAULTENCODING: "true"  # PEP 597: Enable optional EncodingWarning
 
     steps:
       - name: Check out repo

dev_scripts/potcar_scrambler.py

@@ -124,7 +124,7 @@ def scramble_single_potcar(self, potcar: PotcarSingle) -> str:
         return scrambled_potcar_str
 
     def to_file(self, filename: str) -> None:
-        with zopen(filename, mode="wt") as file:
+        with zopen(filename, mode="wt", encoding="utf-8") as file:
             file.write(self.scrambled_potcars_str)
 
     @classmethod

pyproject.toml

@@ -246,10 +246,11 @@ docstring-code-format = true
 [tool.pytest.ini_options]
 addopts = "--durations=30 --quiet -r xXs --color=yes --import-mode=importlib"
 filterwarnings = [
-    # NOTE: the last matching option is used
-    "ignore::Warning",               # Ignore all Warning
-    "default::FutureWarning",        # Show FutureWarnings
-    "default::DeprecationWarning",   # Show DeprecationWarnings
+    # NOTE: the LAST matching option would be used
+    "ignore::UserWarning",                                              # Ignore UserWarning
+    "error:We strongly encourage explicit `encoding`:EncodingWarning",  # Mark `zopen` EncodingWarning as error
+    # TODO: remove the following filter once `monty.io` dropped custom EncodingWarning
+    "error:We strongly encourage explicit `encoding`:monty.io.EncodingWarning",
     # TODO: pybtex (perhaps some others) emits the following warnings
     'ignore:pkg_resources is deprecated as an API:DeprecationWarning',
     'ignore:distutils Version classes are deprecated:DeprecationWarning',

src/pymatgen/apps/borg/hive.py

@@ -445,7 +445,7 @@ def _get_transformation_history(path: PathLike):
     """Check for a transformations.json* file and return the history."""
     if trans_json := glob(f"{path!s}/transformations.json*"):
         try:
-            with zopen(trans_json[0]) as file:
+            with zopen(trans_json[0], mode="rt", encoding="utf-8") as file:
                 return json.load(file)["history"]
         except Exception:
             return None

src/pymatgen/apps/borg/queen.py

@@ -103,12 +103,12 @@ def save_data(self, filename: PathLike) -> None:
                 that if the filename ends with gz or bz2, the relevant gzip
                 or bz2 compression will be applied.
         """
-        with zopen(filename, mode="wt") as file:
+        with zopen(filename, mode="wt", encoding="utf-8") as file:
             json.dump(list(self._data), file, cls=MontyEncoder)
 
     def load_data(self, filename: PathLike) -> None:
         """Load assimilated data from a file."""
-        with zopen(filename, mode="rt") as file:
+        with zopen(filename, mode="rt", encoding="utf-8") as file:
             self._data = json.load(file, cls=MontyDecoder)
 
 

src/pymatgen/core/structure.py

@@ -2953,15 +2953,15 @@ def to(self, filename: PathLike = "", fmt: FileFormats = "", **kwargs) -> str:
         elif fmt == "json" or fnmatch(filename.lower(), "*.json*"):
             json_str = json.dumps(self.as_dict())
             if filename:
-                with zopen(filename, mode="wt") as file:
+                with zopen(filename, mode="wt", encoding="utf-8") as file:
                     file.write(json_str)
             return json_str
         elif fmt == "xsf" or fnmatch(filename.lower(), "*.xsf*"):
             from pymatgen.io.xcrysden import XSF
 
             res_str = XSF(self).to_str()
             if filename:
-                with zopen(filename, mode="wt", encoding="utf8") as file:
+                with zopen(filename, mode="wt", encoding="utf-8") as file:
                     file.write(res_str)
             return res_str
         elif (
@@ -2987,15 +2987,15 @@ def to(self, filename: PathLike = "", fmt: FileFormats = "", **kwargs) -> str:
             yaml.dump(self.as_dict(), str_io)
             yaml_str = str_io.getvalue()
             if filename:
-                with zopen(filename, mode="wt") as file:
+                with zopen(filename, mode="wt", encoding="utf-8") as file:
                     file.write(yaml_str)
             return yaml_str
         elif fmt == "aims" or fnmatch(filename, "geometry.in"):
             from pymatgen.io.aims.inputs import AimsGeometryIn
 
             geom_in = AimsGeometryIn.from_structure(self)
             if filename:
-                with zopen(filename, mode="w") as file:
+                with zopen(filename, mode="wt", encoding="utf-8") as file:
                     file.write(geom_in.get_header(filename))
                     file.write(geom_in.content)
                     file.write("\n")
@@ -3010,7 +3010,7 @@ def to(self, filename: PathLike = "", fmt: FileFormats = "", **kwargs) -> str:
 
             res_str = ResIO.structure_to_str(self)
             if filename:
-                with zopen(filename, mode="wt", encoding="utf8") as file:
+                with zopen(filename, mode="wt", encoding="utf-8") as file:
                     file.write(res_str)
             return res_str
         elif fmt == "pwmat" or fnmatch(filename.lower(), "*.pwmat") or fnmatch(filename.lower(), "*.config"):
@@ -3173,7 +3173,7 @@ def from_file(
             return struct
 
         fname = os.path.basename(filename)
-        with zopen(filename, mode="rt", errors="replace") as file:
+        with zopen(filename, mode="rt", errors="replace", encoding="utf-8") as file:
             contents = file.read()
         if fnmatch(fname.lower(), "*.cif*") or fnmatch(fname.lower(), "*.mcif*"):
             return cls.from_str(
@@ -3919,7 +3919,7 @@ def to(self, filename: str = "", fmt: str = "") -> str | None:
         elif fmt == "json" or fnmatch(filename, "*.json*") or fnmatch(filename, "*.mson*"):
             json_str = json.dumps(self.as_dict())
             if filename:
-                with zopen(filename, mode="wt", encoding="utf8") as file:
+                with zopen(filename, mode="wt", encoding="utf-8") as file:
                     file.write(json_str)
             return json_str
         elif fmt in {"yaml", "yml"} or fnmatch(filename, "*.yaml*") or fnmatch(filename, "*.yml*"):
@@ -3928,7 +3928,7 @@ def to(self, filename: str = "", fmt: str = "") -> str | None:
             yaml.dump(self.as_dict(), str_io)
             yaml_str = str_io.getvalue()
             if filename:
-                with zopen(filename, mode="wt", encoding="utf8") as file:
+                with zopen(filename, mode="wt", encoding="utf-8") as file:
                     file.write(yaml_str)
             return yaml_str
         else:
@@ -4010,7 +4010,7 @@ def from_file(cls, filename: PathLike) -> Self | None:
         """
         filename = str(filename)
 
-        with zopen(filename) as file:
+        with zopen(filename, mode="rt", encoding="utf-8") as file:
             contents = file.read()
         fname = filename.lower()
         if fnmatch(fname, "*.xyz*"):

src/pymatgen/core/trajectory.py

@@ -467,7 +467,7 @@ def write_Xdatcar(
 
         xdatcar_str = "\n".join(lines) + "\n"
 
-        with zopen(filename, mode="wt") as file:
+        with zopen(filename, mode="wt", encoding="utf-8") as file:
             file.write(xdatcar_str)
 
     def as_dict(self) -> dict:

src/pymatgen/io/adf.py

@@ -645,7 +645,7 @@ def _parse_logfile(self, logfile):
         # The last non-empty line of the logfile must match the end pattern.
         # Otherwise the job has some internal failure. The TAPE13 part of the
         # ADF manual has a detailed explanation.
-        with zopen(logfile, mode="rt") as file:
+        with zopen(logfile, mode="rt", encoding="utf-8") as file:
             for line in reverse_readline(file):
                 if line == "":
                     continue

src/pymatgen/io/aims/inputs.py

@@ -133,7 +133,7 @@ def from_file(cls, filepath: str | Path) -> Self:
         Returns:
             AimsGeometryIn: The input object represented in the file
         """
-        with zopen(filepath, mode="rt") as in_file:
+        with zopen(filepath, mode="rt", encoding="utf-8") as in_file:
             content = in_file.read()
         return cls.from_str(content)
 
@@ -759,7 +759,7 @@ def from_file(cls, filename: str, label: str | None = None) -> Self:
         Returns:
             AimsSpeciesFile
         """
-        with zopen(filename, mode="rt") as file:
+        with zopen(filename, mode="rt", encoding="utf-8") as file:
             return cls(data=file.read(), label=label)
 
     @classmethod

src/pymatgen/io/cif.py

@@ -299,7 +299,7 @@ def from_file(cls, filename: PathLike) -> Self:
         Returns:
             CifFile
         """
-        with zopen(filename, mode="rt", errors="replace") as file:
+        with zopen(filename, mode="rt", errors="replace", encoding="utf-8") as file:
             return cls.from_str(file.read())
 
 
@@ -1760,9 +1760,9 @@ def cif_file(self) -> CifFile:
 
     def write_file(
         self,
-        filename: str | Path,
-        mode: Literal["w", "a", "wt", "at"] = "w",
+        filename: PathLike,
+        mode: Literal["wt", "at"] = "wt",
     ) -> None:
         """Write the CIF file."""
-        with zopen(filename, mode=mode) as file:
+        with zopen(filename, mode=mode, encoding="utf-8") as file:
             file.write(str(self))

src/pymatgen/io/common.py

@@ -354,7 +354,7 @@ def to_cube(self, filename, comment: str = ""):
             filename (str): Name of the cube file to be written.
             comment (str): If provided, this will be added to the second comment line
         """
-        with zopen(filename, mode="wt") as file:
+        with zopen(filename, mode="wt", encoding="utf-8") as file:
             file.write(f"# Cube file for {self.structure.formula} generated by Pymatgen\n")
             file.write(f"# {comment}\n")
             file.write(f"\t {len(self.structure)} 0.000000 0.000000 0.000000\n")
@@ -386,7 +386,7 @@ def from_cube(cls, filename: str | Path) -> Self:
         Args:
             filename (str): of the cube to read
         """
-        file = zopen(filename, mode="rt")
+        file = zopen(filename, mode="rt", encoding="utf-8")
 
         # skip header lines
         file.readline()
@@ -529,7 +529,7 @@ def __getitem__(self, item):
             f"No parser defined for {item}. Contents are returned as a string.",
             stacklevel=2,
         )
-        with zopen(fpath, "rt") as f:
+        with zopen(fpath, mode="rt", encoding="utf-8") as f:
             return f.read()
 
     def get_files_by_name(self, name: str) -> dict[str, Any]:

src/pymatgen/io/core.py

@@ -74,7 +74,7 @@ def write_file(self, filename: PathLike) -> None:
         Args:
             filename: The filename to output to, including path.
         """
-        with zopen(Path(filename), mode="wt") as file:
+        with zopen(Path(filename), mode="wt", encoding="utf-8") as file:
             file.write(self.get_str())
 
     @classmethod
@@ -102,7 +102,7 @@ def from_file(cls, path: PathLike) -> None:
         Returns:
             InputFile
         """
-        with zopen(Path(path), mode="rt") as file:
+        with zopen(Path(path), mode="rt", encoding="utf-8") as file:
             return cls.from_str(file.read())  # from_str not implemented
 
 
@@ -218,7 +218,7 @@ def write_input(
             if isinstance(contents, InputFile):
                 contents.write_file(file_path)
             else:
-                with zopen(file_path, mode="wt") as file:
+                with zopen(file_path, mode="wt", encoding="utf-8") as file:
                     file.write(str(contents))
 
         if zip_inputs:

src/pymatgen/io/cp2k/inputs.py

@@ -692,7 +692,7 @@ def _from_dict(cls, dct: dict):
     @classmethod
     def from_file(cls, filename: str | Path) -> Self:
         """Initialize from a file."""
-        with zopen(filename, mode="rt") as file:
+        with zopen(filename, mode="rt", encoding="utf-8") as file:
             txt = preprocessor(file.read(), os.path.dirname(file.name))
             return cls.from_str(txt)
 

src/pymatgen/io/cp2k/outputs.py

@@ -327,7 +327,7 @@ def parse_initial_structure(self):
         )
 
         coord_table = []
-        with zopen(self.filename, mode="rt") as file:
+        with zopen(self.filename, mode="rt", encoding="utf-8") as file:
             while True:
                 line = file.readline()
                 if re.search(r"Atom\s+Kind\s+Element\s+X\s+Y\s+Z\s+Z\(eff\)\s+Mass", line):
@@ -789,7 +789,7 @@ def parse_atomic_kind_info(self):
             except (TypeError, IndexError, ValueError):
                 atomic_kind_info[kind]["total_pseudopotential_energy"] = None
 
-        with zopen(self.filename, mode="rt") as file:
+        with zopen(self.filename, mode="rt", encoding="utf-8") as file:
             j = -1
             lines = file.readlines()
             for k, line in enumerate(lines):
@@ -1010,7 +1010,7 @@ def parse_mo_eigenvalues(self):
         eigenvalues = []
         efermi = []
 
-        with zopen(self.filename, mode="rt") as file:
+        with zopen(self.filename, mode="rt", encoding="utf-8") as file:
             lines = iter(file.readlines())
             for line in lines:
                 try:
@@ -1349,7 +1349,7 @@ def parse_hyperfine(self, hyperfine_filename=None):
             else:
                 return None
 
-        with zopen(hyperfine_filename, mode="rt") as file:
+        with zopen(hyperfine_filename, mode="rt", encoding="utf-8") as file:
             lines = [line for line in file.read().split("\n") if line]
 
         hyperfine = [[] for _ in self.ionic_steps]
@@ -1370,7 +1370,7 @@ def parse_gtensor(self, gtensor_filename=None):
             else:
                 return None
 
-        with zopen(gtensor_filename, mode="rt") as file:
+        with zopen(gtensor_filename, mode="rt", encoding="utf-8") as file:
             lines = [line for line in file.read().split("\n") if line]
 
         data = {}
@@ -1407,7 +1407,7 @@ def parse_chi_tensor(self, chi_filename=None):
             else:
                 return None
 
-        with zopen(chi_filename, mode="rt") as file:
+        with zopen(chi_filename, mode="rt", encoding="utf-8") as file:
             lines = [line for line in file.read().split("\n") if line]
 
         data = {k: [] for k in "chi_soft chi_local chi_total chi_total_ppm_cgs PV1 PV2 PV3 ISO ANISO".split()}
@@ -1554,7 +1554,7 @@ def read_table_pattern(
             row_pattern, or a dict in case that named capturing groups are defined by
             row_pattern.
         """
-        with zopen(self.filename, mode="rt") as file:
+        with zopen(self.filename, mode="rt", encoding="utf-8") as file:
             if strip:
                 lines = file.readlines()
                 text = "".join(
@@ -1691,7 +1691,7 @@ def parse_pdos(dos_file=None, spin_channel=None, total=False):
     """
     spin = Spin(spin_channel) if spin_channel else Spin.down if "BETA" in os.path.split(dos_file)[-1] else Spin.up
 
-    with zopen(dos_file, mode="rt") as file:
+    with zopen(dos_file, mode="rt", encoding="utf-8") as file:
         lines = file.readlines()
         kind = re.search(r"atomic kind\s(.*)\sat iter", lines[0]) or re.search(r"list\s(\d+)\s(.*)\sat iter", lines[0])
         kind = kind.groups()[0]

src/pymatgen/io/cp2k/utils.py

@@ -80,7 +80,7 @@ def preprocessor(data: str, dir: str = ".") -> str:  # noqa: A002
             raise ValueError(f"length of inc should be 2, got {len(inc)}")
         inc = inc[1].strip("'")
         inc = inc.strip('"')
-        with zopen(os.path.join(dir, inc)) as file:
+        with zopen(os.path.join(dir, inc), mode="rt", encoding="utf-8") as file:
             data = re.sub(rf"{incl}", file.read(), data)
     variable_sets = re.findall(r"(@SET.+)", data, re.IGNORECASE)
     for match in variable_sets:

src/pymatgen/io/cssr.py

@@ -57,7 +57,7 @@ def write_file(self, filename):
         Args:
             filename (str): Filename to write to.
         """
-        with zopen(filename, mode="wt") as file:
+        with zopen(filename, mode="wt", encoding="utf-8") as file:
             file.write(str(self) + "\n")
 
     @classmethod
@@ -98,5 +98,5 @@ def from_file(cls, filename: str | Path) -> Self:
         Returns:
             Cssr object.
         """
-        with zopen(filename, mode="rt") as file:
+        with zopen(filename, mode="rt", encoding="utf-8") as file:
             return cls.from_str(file.read())

src/pymatgen/io/exciting/inputs.py

@@ -172,7 +172,7 @@ def from_file(cls, filename: str | Path) -> Self:
         Returns:
             ExcitingInput
         """
-        with zopen(filename, mode="rt") as file:
+        with zopen(filename, mode="rt", encoding="utf-8") as file:
             data = file.read().replace("\n", "")
         return cls.from_str(data)