MAINT: Explicitly pass the encoding when opening a file

Author: BvB93

conftest.py

@@ -54,7 +54,7 @@ def reload_qmflows() -> Generator[None, None, None]:
 def configure_plams_logger() -> "Generator[None, None, None]":
     """Remove the date/time prefix from the PLAMS logging output."""
     # Ensure the plams.config dict is populated by firing up plams.init once
-    with open(os.devnull, "w") as f1, tempfile.TemporaryDirectory() as f2:
+    with open(os.devnull, "w", encoding="utf8") as f1, tempfile.TemporaryDirectory() as f2:
         with contextlib.redirect_stdout(f1), InitRestart(f2):
             pass
 

src/qmflows/packages/_scm.py

@@ -58,7 +58,7 @@ def selected_atoms() -> None:
 
     def inithess() -> None:
         hess_path = get_tmpfile_name("ADF_hessian_")
-        hess_file = open(hess_path, "w")
+        hess_file = open(hess_path, "w", encoding="utf8")
         hess_file.write(" ".join(['{:.6f}'.format(v) for v in value]))
         settings.specific[package].geometry.inithess = hess_path.as_posix()
 

src/qmflows/parsers/_cp2k_basis_parser.py

@@ -92,5 +92,5 @@ def read_cp2k_basis(file: PathLike, *, allow_multiple_exponents: bool = False) -
         Whether to allow the parsing of basis sets consisting of multiple exponent sets.
 
     """
-    with open(file, "r") as f:
+    with open(file, "r", encoding="utf8") as f:
         return _read_basis(_BasisFileIter(f, start=1), allow_multiple_exponents)

src/qmflows/parsers/_cp2k_orbital_parser.py

@@ -90,7 +90,7 @@ def _find_mo_start(path: str | os.PathLike[str], unrestricted: bool) -> int | tu
         and a single integer otherwise.
 
     """
-    with open(path, "r") as f:
+    with open(path, "r", encoding="utf8") as f:
         # Find all headers, but skip restarts
         enumerator = enumerate((h.strip("MO| \n") for h in f), start=1)
         headers = [(i, h) for i, h in enumerator if "EIGENVALUES" in h]
@@ -153,7 +153,7 @@ def read_coefficients(
 
     j0 = 0
     j1 = 0
-    with open(path, "r") as f:
+    with open(path, "r", encoding="utf8") as f:
         iterator = filter(None, (i.strip("MO| \n") for i in islice(f, start, None)))
         for h in iterator:
             # Each MO pair is preceded by their indices,
@@ -192,8 +192,8 @@ def read_coefficients(
 
 def read_cp2k_number_of_orbitals(file_name: str | os.PathLike[str]) -> MO_metadata:
     """Extract the number of (occupied) orbitals and basis functions."""
-    with open(file_name, "r") as f:
-        kwargs: "dict[str, list[int]]" = defaultdict(list)
+    with open(file_name, "r", encoding="utf8") as f:
+        kwargs: defaultdict[str, list[int]] = defaultdict(list)
         for line in f:
             match = _ORBITAL_PATTERN.search(line)
             if match is None:

src/qmflows/parsers/cp2k.py

@@ -207,7 +207,7 @@ def read_cp2k_xyz(path: PathLike, dtype: DTypeLike = np.float64) -> NDArray[Any]
     Requires a CP2K ``*.xyz`` file.
 
     """
-    with open(path, 'r') as f:
+    with open(path, 'r', encoding="utf8") as f:
         n_atom = int(next(f))
         flat_iter = chain.from_iterable(_read_cp2k_xyz(f, n_atom))
         ret = np.fromiter(flat_iter, dtype=dtype)
@@ -238,7 +238,7 @@ def read_cp2k_table(
     **start**, **stop** and **step** can be used for specifiying the to-be parsed rows.
 
     """
-    with open(path, 'r') as f:
+    with open(path, 'r', encoding="utf8") as f:
         flat_iter = (i.split()[column] for i in islice(f, start, stop, step))
         return np.fromiter(flat_iter, dtype=dtype)
 
@@ -261,7 +261,7 @@ def read_cp2k_table_slc(
     **start**, **stop** and **step** can be used for specifiying the to-be parsed rows.
 
     """
-    with open(path, 'r') as f:
+    with open(path, 'r', encoding="utf8") as f:
         clm_slc = slice(column_start, column_stop, column_step)
         row_slc = islice(f, row_start, row_stop, row_step)
         flat_iter = chain.from_iterable(i.split()[clm_slc] for i in row_slc)
@@ -300,7 +300,7 @@ def read_cp2k_pressure(
     major, _ = get_cp2k_version(path)
 
     # Read the pressures
-    with open(path, 'r') as f:
+    with open(path, 'r', encoding="utf8") as f:
         iterator = _get_pressure_iter(major, f)
         return np.fromiter(islice(iterator, start, stop, step), dtype=dtype)
 
@@ -313,7 +313,7 @@ def get_cp2k_version(out_file: PathLike) -> CP2KVersion:
 
     Returns :code:`(0, 0)` if the versions cannot be identified.
     """
-    with open(out_file, 'r') as f:
+    with open(out_file, 'r', encoding="utf8") as f:
         for i in f:
             i = i.strip()
             if i.startswith("CP2K| version string:"):

src/qmflows/parsers/utils.py

@@ -98,7 +98,7 @@ def try_search_pattern(
 ) -> None | str:
     """Search for an specific pattern in  a file."""
     try:
-        with open(file_name, 'r') as f:
+        with open(file_name, 'r', encoding="utf8") as f:
             for line in f:
                 if re.search(pat, line):
                     return line

src/qmflows/test_utils.py

@@ -195,7 +195,7 @@ def _read_result_file(result: Result, extension: str, max_line: int = 100) -> No
     iterator = (os.path.join(root, i) for i in os.listdir(root)
                 if os.path.splitext(i)[1] == extension)
     for i in iterator:
-        with open(i, "r") as f:
+        with open(i, "r", encoding="utf8") as f:
             ret_list = f.readlines()
             ret = "..." if len(ret_list) > max_line else ""
             ret += "".join(ret_list[-max_line:])

src/qmflows/utils.py

@@ -123,6 +123,8 @@ def file_to_context(file: int | PathLike | IO[Any],
     """
     # path-like object
     try:
+        if "encoding" not in kwargs:
+            kwargs["encoding"] = "utf8"
         return open(file, **kwargs)  # type: ignore
 
     # a file-like object (hopefully)
@@ -148,7 +150,8 @@ def init_restart(
 
     """
     is_init: bool = config.init
-    with open(os.devnull, 'w') as f, redirect_stdout(f):  # Temporary supress printing
+    # Temporary supress printing
+    with open(os.devnull, 'w', encoding="utf8") as f, redirect_stdout(f):
         init(path, folder)
 
     # Parse variables

test/test_special_keywords.py

@@ -294,6 +294,6 @@ def test_cp2k_mm_keywords():
     s.specific.cp2k.force_eval.mm.forcefield.parm_file_name = basename(
         s.specific.cp2k.force_eval.mm.forcefield.parm_file_name)
 
-    with open(PATH / 'cp2k_mm_special_keyword.yaml', 'rb') as f:
+    with open(PATH / 'cp2k_mm_special_keyword.yaml', 'r', encoding="utf8") as f:
         ref = yaml2Settings(f)
     assertion.eq(s.specific, ref)

test/test_utils.py

@@ -98,9 +98,9 @@ def test_validate_status() -> None:
         validate_status(result)
     msg = str(rec.value)
 
-    with open(root / "cp2k_opt.out", "r") as f:
+    with open(root / "cp2k_opt.out", "r", encoding="utf8") as f:
         out_ref = textwrap.indent("".join(f.readlines()[-100:]), 4 * " ")
-    with open(root / "cp2k_opt.err", "r") as f:
+    with open(root / "cp2k_opt.err", "r", encoding="utf8") as f:
         err_ref = textwrap.indent("".join(f.readlines()[-100:]), 4 * " ")
 
     assertion.contains(msg, out_ref)