zopen: explicit binary/text mode , and explicit encoding as UTF-8

src/pymatgen/apps/borg/hive.py

@@ -443,7 +443,7 @@ 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") as file:
                 return json.load(file)["history"]
         except Exception:
             return None

src/pymatgen/core/structure.py

@@ -2994,7 +2994,7 @@ def to(self, filename: PathLike = "", fmt: FileFormats = "", **kwargs) -> str:
 
             geom_in = AimsGeometryIn.from_structure(self)
             if filename:
-                with zopen(filename, mode="w") as file:
+                with zopen(filename, mode="wt") as file:
                     file.write(geom_in.get_header(filename))
                     file.write(geom_in.content)
                     file.write("\n")
@@ -4009,7 +4009,7 @@ def from_file(cls, filename: PathLike) -> Self | None:
         """
         filename = str(filename)
 
-        with zopen(filename) as file:
+        with zopen(filename, mode="rt") as file:
             contents = file.read()
         fname = filename.lower()
         if fnmatch(fname, "*.xyz*"):

src/pymatgen/io/cif.py

@@ -1761,5 +1761,5 @@ def write_file(
         mode: Literal["w", "a", "wt", "at"] = "w",
     ) -> None:
         """Write the CIF file."""
-        with zopen(filename, mode=mode) as file:
+        with zopen(filename, mode=mode) as file:  # DEBUG: bad default value
             file.write(str(self))

src/pymatgen/io/common.py

@@ -526,7 +526,7 @@ def __getitem__(self, item):
             f"No parser defined for {item}. Contents are returned as a string.",
             UserWarning,
         )
-        with zopen(fpath, "rt") as f:
+        with zopen(fpath, mode="rt") as f:
             return f.read()
 
     def get_files_by_name(self, name: str) -> dict[str, Any]:

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") 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/feff/inputs.py

@@ -246,7 +246,7 @@ def header_string_from_file(filename: str = "feff.inp"):
         Returns:
             Reads header string.
         """
-        with zopen(filename, mode="r") as file:
+        with zopen(filename, mode="rt") as file:
             lines = file.readlines()
             feff_header_str = []
             ln = 0

src/pymatgen/io/feff/outputs.py

@@ -70,7 +70,7 @@ def from_file(cls, feff_inp_file: str = "feff.inp", ldos_file: str = "ldos") ->
             dos_index = 1
             begin = 0
 
-            with zopen(pot_inp, mode="r") as potfile:
+            with zopen(pot_inp, mode="rt") as potfile:
                 for line in potfile:
                     if len(pot_read_end.findall(line)) > 0:
                         break
@@ -95,7 +95,7 @@ def from_file(cls, feff_inp_file: str = "feff.inp", ldos_file: str = "ldos") ->
             dicts = Potential.pot_dict_from_str(pot_string)
             pot_dict = dicts[0]
 
-        with zopen(f"{ldos_file}00.dat", mode="r") as file:
+        with zopen(f"{ldos_file}00.dat", mode="rt") as file:
             lines = file.readlines()
         e_fermi = float(lines[0].split()[4])
 
@@ -172,7 +172,7 @@ def charge_transfer_from_file(feff_inp_file, ldos_file):
             pot_inp = re.sub(r"feff.inp", r"pot.inp", feff_inp_file)
             pot_readstart = re.compile(".*iz.*lmaxsc.*xnatph.*xion.*folp.*")
             pot_readend = re.compile(".*ExternalPot.*switch.*")
-            with zopen(pot_inp, mode="r") as potfile:
+            with zopen(pot_inp, mode="rt") as potfile:
                 for line in potfile:
                     if len(pot_readend.findall(line)) > 0:
                         break

src/pymatgen/io/fiesta.py

@@ -214,7 +214,7 @@ def __init__(self, filename):
         """
         self.filename = filename
 
-        with zopen(filename) as file:
+        with zopen(filename, mode="rt") as file:
             basis_set = file.read()
 
         self.data = self._parse_file(basis_set)
@@ -533,7 +533,7 @@ def write_file(self, filename: str | Path) -> None:
         Args:
             filename: Filename.
         """
-        with zopen(filename, mode="w") as file:
+        with zopen(filename, mode="wt") as file:
             file.write(str(self))
 
     def as_dict(self):
@@ -712,7 +712,7 @@ def from_file(cls, filename: str | Path) -> Self:
         Returns:
             FiestaInput object
         """
-        with zopen(filename) as file:
+        with zopen(filename, mode="rt") as file:
             return cls.from_str(file.read())
 
 
@@ -730,7 +730,7 @@ def __init__(self, filename):
         """
         self.filename = filename
 
-        with zopen(filename) as file:
+        with zopen(filename, mode="rt") as file:
             data = file.read()
 
         chunks = re.split(r"GW Driver iteration", data)
@@ -821,7 +821,7 @@ def __init__(self, filename):
         """
         self.filename = filename
 
-        with zopen(filename) as file:
+        with zopen(filename, mode="rt") as file:
             log_bse = file.read()
 
         # self.job_info = self._parse_preamble(preamble)

src/pymatgen/io/gaussian.py

@@ -368,7 +368,7 @@ def from_file(cls, filename: str | Path) -> Self:
         Returns:
             GaussianInput object
         """
-        with zopen(filename, mode="r") as file:
+        with zopen(filename, mode="rt") as file:
             return cls.from_str(file.read())
 
     def get_zmatrix(self):
@@ -447,9 +447,9 @@ def para_dict_to_str(para, joiner=" "):
     def write_file(self, filename, cart_coords=False):
         """Write the input string into a file.
 
-        Option: see __str__ method
+        Option: see `__str__` method
         """
-        with zopen(filename, mode="w") as file:
+        with zopen(filename, mode="wt") as file:
             file.write(self.to_str(cart_coords))
 
     def as_dict(self):
@@ -1102,7 +1102,7 @@ def read_scan(self):
         data = {"energies": [], "coords": {}}
 
         # read in file
-        with zopen(self.filename, mode="r") as file:
+        with zopen(self.filename, mode="rt") as file:
             line = file.readline()
 
             while line != "":
@@ -1188,7 +1188,7 @@ def read_excitation_energies(self):
         transitions = []
 
         # read in file
-        with zopen(self.filename, mode="r") as file:
+        with zopen(self.filename, mode="rt") as file:
             line = file.readline()
             td = False
             while line != "":

src/pymatgen/io/lammps/generators.py

@@ -67,7 +67,7 @@ def get_input_set(self, structure: Structure | LammpsData | CombinedData) -> Lam
         data: LammpsData = LammpsData.from_structure(structure) if isinstance(structure, Structure) else structure
 
         # Load the template
-        with zopen(self.template, mode="r") as file:
+        with zopen(self.template, mode="rt") as file:
             template_str = file.read()
 
         # Replace all variables

src/pymatgen/io/lobster/inputs.py

@@ -642,7 +642,7 @@ def _get_potcar_symbols(POTCAR_input: PathLike) -> list[str]:
                 raise ValueError("Lobster only works with PAW! Use different POTCARs")
 
         # Warning about a bug in LOBSTER-4.1.0
-        with zopen(POTCAR_input, mode="r") as file:
+        with zopen(POTCAR_input, mode="rt") as file:
             data = file.read()
 
         if isinstance(data, bytes):

src/pymatgen/io/nwchem.py

@@ -391,7 +391,7 @@ def write_file(self, filename):
         Args:
             filename (str): Filename.
         """
-        with zopen(filename, mode="w") as file:
+        with zopen(filename, mode="wt") as file:
             file.write(str(self))
 
     def as_dict(self):
@@ -531,7 +531,7 @@ def from_file(cls, filename: str | Path) -> Self:
         Returns:
             NwInput object
         """
-        with zopen(filename) as file:
+        with zopen(filename, mode="rt") as file:
             return cls.from_str(file.read())
 
 
@@ -554,7 +554,7 @@ def __init__(self, filename):
         """
         self.filename = filename
 
-        with zopen(filename) as file:
+        with zopen(filename, mode="rt") as file:
             data = file.read()
 
         chunks = re.split(r"NWChem Input Module", data)

src/pymatgen/io/qchem/outputs.py

@@ -58,6 +58,7 @@ def __init__(self, filename: str):
         self.data["errors"] = []
         self.data["warnings"] = {}
         self.text = ""
+        # TODO: why not utf-8 encoding?
         with zopen(filename, mode="rt", encoding="ISO-8859-1") as file:
             self.text = file.read()
 
@@ -2951,6 +2952,7 @@ def nbo_parser(filename: str) -> dict[str, list[pd.DataFrame]]:
         RuntimeError: If a section cannot be found.
     """
     # Open the lines
+    # TODO: why not utf-8 encoding?
     with zopen(filename, mode="rt", encoding="ISO-8859-1") as file:
         lines = file.readlines()
 

src/pymatgen/io/res.py

@@ -249,7 +249,7 @@ def _parse_str(cls, source: str) -> Res:
     def _parse_file(cls, filename: str | Path) -> Res:
         """Parse the res file as a file."""
         self = cls()
-        with zopen(filename, mode="r") as file:
+        with zopen(filename, mode="rt") as file:
             self.source = file.read()
             return self._parse_txt()
 
@@ -335,7 +335,7 @@ def string(self) -> str:
 
     def write(self, filename: str) -> None:
         """Write the res data to a file."""
-        with zopen(filename, mode="w") as file:
+        with zopen(filename, mode="wt") as file:
             file.write(str(self))
 
 

src/pymatgen/io/template.py

@@ -52,7 +52,7 @@ def get_input_set(
         self.filename = str(filename)
 
         # Load the template
-        with zopen(self.template, mode="r") as file:
+        with zopen(self.template, mode="rt") as file:
             template_str = file.read()
 
         # Replace all variables

src/pymatgen/io/vasp/outputs.py

@@ -5394,7 +5394,7 @@ def __init__(
         self.occu_tol = occu_tol
         self.separate_spins = separate_spins
 
-        with zopen(filename, mode="r") as file:
+        with zopen(filename, mode="rt") as file:
             self.ispin = int(file.readline().split()[-1])
 
             # Remove useless header information

src/pymatgen/io/zeopp.py

@@ -146,7 +146,7 @@ def from_file(cls, filename: str | Path) -> Self:
         Returns:
             ZeoCssr object.
         """
-        with zopen(filename, mode="r") as file:
+        with zopen(filename, mode="rt") as file:
             return cls.from_str(file.read())
 
 
@@ -200,7 +200,7 @@ def from_file(cls, filename: str | Path) -> Self:
         Returns:
             XYZ object
         """
-        with zopen(filename) as file:
+        with zopen(filename, mode="rt") as file:
             return cls.from_str(file.read())
 
     def __str__(self) -> str:

tests/electronic_structure/test_dos.py

@@ -108,7 +108,7 @@ class TestCompleteDos(TestCase):
     def setUp(self):
         with open(f"{TEST_DIR}/complete_dos.json") as file:
             self.dos = CompleteDos.from_dict(json.load(file))
-        with zopen(f"{TEST_DIR}/pdag3_complete_dos.json.gz") as file:
+        with zopen(f"{TEST_DIR}/pdag3_complete_dos.json.gz", mode="rt") as file:
             self.dos_pdag3 = CompleteDos.from_dict(json.load(file))
 
     def test_get_gap(self):

tests/io/qchem/test_utils.py

@@ -36,6 +36,7 @@ def test_process_parsed_hess(self):
             binary = file.read()
             data_132 = [struct.unpack("d", binary[ii * 8 : (ii + 1) * 8])[0] for ii in range(len(binary) // 8)]
 
+        # TODO: why not utf-8 encoding?
         with zopen(f"{TEST_DIR}/parse_hess/HESS", mode="rt", encoding="ISO-8859-1") as file:
             data_hess = file.readlines()
 

tests/io/vasp/test_outputs.py

@@ -2148,7 +2148,7 @@ def test_consistency(self):
         wder_ref = np.loadtxt(f"{VASP_OUT_DIR}/WAVEDERF.Si.gz", skiprows=1)
 
         def _check(wder):
-            with zopen(f"{VASP_OUT_DIR}/WAVEDERF.Si.gz") as file:
+            with zopen(f"{VASP_OUT_DIR}/WAVEDERF.Si.gz", mode="rt") as file:
                 first_line = [int(a) for a in file.readline().split()]
             assert wder.nkpoints == first_line[1]
             assert wder.nbands == first_line[2]