add precommit config and fix problem (#35)

.github/workflows/doc.yml

@@ -18,13 +18,13 @@ jobs:
       uses: actions/setup-python@v2
       with:
         python-version: 3.8
-    
+
     - name: Install dependencies
       run: |
         pip install .
         pip install sphinx
         pip install jupyter-book
-    
+
     - name: Sphinx APIDoc
       run: |
         sphinx-apidoc -f -o jupyter-book/_api/ cp2kdata/ --separate

.pre-commit-config.yaml

@@ -0,0 +1,11 @@
+# See https://pre-commit.com for more information
+# See https://pre-commit.com/hooks.html for more hooks
+repos:
+-   repo: https://github.com/pre-commit/pre-commit-hooks
+    rev: v3.2.0
+    hooks:
+    -   id: trailing-whitespace
+        exclude: "^tests/.*$"
+#    -   id: end-of-file-fixer
+    -   id: check-yaml
+#    -   id: check-added-large-files

cp2kdata/block_parser/atomic_kind.py

@@ -28,7 +28,7 @@ def parse_atomic_kinds(output_file):
     for match in ATOMIC_KINDS_RE.finditer(output_file):
         atomic_kinds.append(match["atomic_kind"])
     if atomic_kinds:
-        # only return the last atomic kinds 
+        # only return the last atomic kinds
         return np.array(atomic_kinds[-num_atomic_kinds_list[-1]:], dtype=str)
     else:
         return None

cp2kdata/block_parser/cells.py

@@ -9,20 +9,20 @@
 ALL_CELL_RE = re.compile(
     r"""
     \s+CELL\|\sVector\sa\s\[angstrom\]:
-    \s+(?P<xx>[\s-]\d+\.\d+) 
-    \s+(?P<xy>[\s-]\d+\.\d+) 
+    \s+(?P<xx>[\s-]\d+\.\d+)
+    \s+(?P<xy>[\s-]\d+\.\d+)
     \s+(?P<xz>[\s-]\d+\.\d+)
     \s+\|a\|\s+=\s+\S+
     \n
     \s+CELL\|\sVector\sb\s\[angstrom\]:
-    \s+(?P<yx>[\s-]\d+\.\d+) 
-    \s+(?P<yy>[\s-]\d+\.\d+) 
+    \s+(?P<yx>[\s-]\d+\.\d+)
+    \s+(?P<yy>[\s-]\d+\.\d+)
     \s+(?P<yz>[\s-]\d+\.\d+)
     \s+\|b\|\s+=\s+\S+
     \n
     \s+CELL\|\sVector\sc\s\[angstrom\]:
-    \s+(?P<zx>[\s-]\d+\.\d+) 
-    \s+(?P<zy>[\s-]\d+\.\d+) 
+    \s+(?P<zx>[\s-]\d+\.\d+)
+    \s+(?P<zy>[\s-]\d+\.\d+)
     \s+(?P<zz>[\s-]\d+\.\d+)
     \s+\|c\|\s+=\s+\S+
     \n
@@ -45,7 +45,7 @@ def parse_all_cells(output_file):
         return np.array(all_cells, dtype=float)
     else:
         return None
-    
+
 ALL_MD_CELL_RE_V7 = re.compile(
     r"""
     \sCELL\sLNTHS\[bohr\]\s{13}=\s
@@ -75,22 +75,22 @@ def parse_all_cells(output_file):
     #skip three lines
     (.{80}\n){3}
     #parse angles
-    (\sMD\|\sCell\sangles\s\[deg\]\s{10} 
+    (\sMD\|\sCell\sangles\s\[deg\]\s{10}
     \s{2}(?P<alpha>\d\.\d{8}E(\+|\-)\d{2})
     \s{2}(?P<beta>\d\.\d{8}E(\+|\-)\d{2})
     \s{2}(?P<gamma>\d\.\d{8}E(\+|\-)\d{2}))?
     """,
     re.VERBOSE
 )
 
-def parse_all_md_cells(output_file: List[str], 
+def parse_all_md_cells(output_file: List[str],
                        cp2k_info: Cp2kInfo,
                        init_cell_info=None):
     # init_cell_info are used for npt_I parse.
     # because npt_I doesn't include angle info in MD| block
 
     # notice that the cell of step 0 is excluded from MD| block
-    
+
     # choose parser according to cp2k_info.version
     if cp2k_info.version in ['2023.1']:
         ALL_MD_CELL_RE = ALL_MD_CELL_RE_V2023

cp2kdata/block_parser/converge.py

@@ -17,7 +17,7 @@ def parse_e_f_converge(filename) -> ConvergeInfo:
     info_dict = regrep(
         filename=filename,
         reverse=True,
-        patterns={"converge": CONVERGE_PATTERN}, 
+        patterns={"converge": CONVERGE_PATTERN},
         terminate_on_match=True
         )
 
@@ -32,7 +32,7 @@ def parse_md_converge(filename):
     info_dict = regrep(
         filename=filename,
         reverse=True,
-        patterns={"converge": CONVERGE_PATTERN}, 
+        patterns={"converge": CONVERGE_PATTERN},
         terminate_on_match=False
         )
     #print(info_dict['converge'])

cp2kdata/block_parser/dipole.py

@@ -28,13 +28,13 @@ def parse_dipole_list(output_file):
 
 """
    Reference Point [Bohr]              0.00000000      0.00000000      0.00000000
-   Charges                                                                       
+   Charges
      Electronic=    864.00000000    Core=  -864.00000000    Total=     0.00000000
-   Dipole vectors are based on the periodic (Berry phase) operator.              
-   They are defined modulo integer multiples of the cell matrix [Debye].         
-   [X] [   46.55265580     0.00000000     0.00000000 ] [i]                       
-   [Y]=[    0.00000000    54.46353324     0.00000000 ]*[j]                       
-   [Z] [    0.00000000     0.00000000    54.47313965 ] [k]                       
-   Dipole moment [Debye]                                                         
+   Dipole vectors are based on the periodic (Berry phase) operator.
+   They are defined modulo integer multiples of the cell matrix [Debye].
+   [X] [   46.55265580     0.00000000     0.00000000 ] [i]
+   [Y]=[    0.00000000    54.46353324     0.00000000 ]*[j]
+   [Z] [    0.00000000     0.00000000    54.47313965 ] [k]
+   Dipole moment [Debye]
      X=   -0.07183634 Y=   -0.07690441 Z=    1.13302571     Total=     1.13790246
 """

cp2kdata/block_parser/errors_handle.py

@@ -10,7 +10,7 @@
 
 def parse_errors(output_file):
     errors_info = {}
-    
+
     for match in EXCEED_WALL_TIME_RE.finditer(output_file):
         #print(match)
         if match:

cp2kdata/block_parser/header_info.py

@@ -17,8 +17,8 @@ class Cp2kInfo:
 def parse_cp2k_info(filename) -> Cp2kInfo:
 
     cp2k_info = regrep(
-        filename=filename, 
-        patterns={"version": CP2K_INFO_VERSION_PATTERN}, 
+        filename=filename,
+        patterns={"version": CP2K_INFO_VERSION_PATTERN},
         terminate_on_match=True
         )
 
@@ -42,10 +42,10 @@ class GlobalInfo:
 
 def parse_global_info(filename) -> GlobalInfo:
     global_info = {}
-    
+
     global_info = regrep(
-        filename=filename, 
-        patterns={"run_type": GLOBAL_INFO_RUN_TYPE_PATTERN, 
+        filename=filename,
+        patterns={"run_type": GLOBAL_INFO_RUN_TYPE_PATTERN,
                   "print_level": GLOBAL_INFO_PRINT_LEVEL_PATTERN
                   },
         terminate_on_match=True
@@ -78,16 +78,16 @@ class DFTInfo:
 
 def parse_dft_info(filename) -> DFTInfo:
     dft_info = {}
-    
+
     dft_info = regrep(
-        filename=filename, 
+        filename=filename,
         patterns={
             "ks_type": DFT_INFO_KS_TYPE_PATTERN,
             "multiplicity": DFT_INFO_MULTIPLICITY_PATTERN
         },
         terminate_on_match=True
         )
-    
+
     if dft_info:
         return DFTInfo(ks_type=dft_info["ks_type"][0][0][0], multiplicity=dft_info["multiplicity"][0][0][0])
     else:
@@ -108,12 +108,12 @@ class MDInfo:
 
 def parse_md_info(filename):
     md_info = {}
-    
+
     md_info = regrep(
-        filename=filename, 
+        filename=filename,
         patterns={
             "ensemble_type": MD_INFO_ENSEMBLE_TYPE_PATTERN
-        }, 
+        },
         terminate_on_match=True
         )
 

cp2kdata/block_parser/md_xyz.py

@@ -81,21 +81,21 @@ def parse_pos_xyz_from_wannier(wannier_xyz_fiel):
 def parse_md_stress(stress_file):
     print(f"Parsing Stresses from {stress_file}")
     stresses_list = np.loadtxt(
-        stress_file, 
-        usecols=(2, 3, 4, 5, 6, 7, 8, 9, 10), 
+        stress_file,
+        usecols=(2, 3, 4, 5, 6, 7, 8, 9, 10),
         ndmin=2,
         dtype=np.float64
         )
-    
+
     numb_frames = stresses_list.shape[0]
 
     return stresses_list.reshape(numb_frames, 3, 3)
 
 def parse_md_cell(cell_file):
     print(f"Parsing Cells from {cell_file}")
     cells_list = np.loadtxt(
-        cell_file, 
-        usecols=(2, 3, 4, 5, 6, 7, 8, 9, 10), 
+        cell_file,
+        usecols=(2, 3, 4, 5, 6, 7, 8, 9, 10),
         ndmin=2,
         dtype=np.float64
         )

cp2kdata/block_parser/mulliken.py

@@ -30,7 +30,7 @@
         \s+(?P<kind>\d+)
         \s+(?P<alpha>[\s-]\d+\.\d+)
         \s+(?P<net_charge>[\s-]\d+\.\d+)
-        
+
     )+
     """,
     re.VERBOSE
@@ -67,7 +67,7 @@ def parse_mulliken_pop_list(output_file, DFTInfo):
                         "net_charge": float(net_charge),
                     }
                 )
-            mulliken_pop_list.append(mulliken_pop)      
+            mulliken_pop_list.append(mulliken_pop)
 
     if  mulliken_pop_list:
         return  mulliken_pop_list

cp2kdata/block_parser/stress.py

@@ -6,17 +6,17 @@
     (\sSTRESS\sTENSOR\s\[GPa\]
     \n
     \s+X\s+Y\s+Z\s*\n
-    \s+X 
-    \s+(?P<xx>[\s-]\d+\.\d+) 
-    \s+(?P<xy>[\s-]\d+\.\d+) 
+    \s+X
+    \s+(?P<xx>[\s-]\d+\.\d+)
+    \s+(?P<xy>[\s-]\d+\.\d+)
     \s+(?P<xz>[\s-]\d+\.\d+)\n
     \s+Y
-    \s+(?P<yx>[\s-]\d+\.\d+) 
-    \s+(?P<yy>[\s-]\d+\.\d+) 
+    \s+(?P<yx>[\s-]\d+\.\d+)
+    \s+(?P<yy>[\s-]\d+\.\d+)
     \s+(?P<yz>[\s-]\d+\.\d+)\n
-    \s+Z 
-    \s+(?P<zx>[\s-]\d+\.\d+) 
-    \s+(?P<zy>[\s-]\d+\.\d+) 
+    \s+Z
+    \s+(?P<zx>[\s-]\d+\.\d+)
+    \s+(?P<zy>[\s-]\d+\.\d+)
     \s+(?P<zz>[\s-]\d+\.\d+)\n
     |# or another pattern used in v8.1
     \s+STRESS\|\sAnalytical\sstress\stensor\s\[GPa\]\s*\n

cp2kdata/cell.py

@@ -7,9 +7,9 @@
 
 class Cp2kCell:
     def __init__(
-        self, 
-        cell_param: npt.NDArray[np.float64], 
-        grid_point: npt.NDArray[np.int_] = None, 
+        self,
+        cell_param: npt.NDArray[np.float64],
+        grid_point: npt.NDArray[np.int_] = None,
         grid_spacing_matrix: npt.NDArray[np.float64] = None
         ):
         """
@@ -32,21 +32,21 @@ def __init__(
         if isinstance(cell_param, float):
             self.cell_matrix = np.array(
                 [
-                    [cell_param, 0, 0], 
-                    [0, cell_param, 0], 
+                    [cell_param, 0, 0],
+                    [0, cell_param, 0],
                     [0, 0, cell_param]
                 ]
             )
             print("input cell_param is a float, the cell is assumed to be cubic")
         elif cell_param.shape == (3,):
             self.cell_matrix = np.array(
                 [
-                    [cell_param[0], 0, 0], 
-                    [0, cell_param[1], 0], 
+                    [cell_param[0], 0, 0],
+                    [0, cell_param[1], 0],
                     [0, 0, cell_param[2]]
                 ]
             )
-            print("the length of input cell_param is 3, " 
+            print("the length of input cell_param is 3, "
                   "the cell is assumed to be orthorhombic")
         elif cell_param.shape == (6,):
             self.cell_matrix = cellpar_to_cell(cell_param)
@@ -55,12 +55,12 @@ def __init__(
                   "which will be converted to cell matrix")
         elif cell_param.shape == (3, 3):
             self.cell_matrix = cell_param
-            print("input cell_param is a matrix with shape of (3,3), " 
+            print("input cell_param is a matrix with shape of (3,3), "
                   "the cell is read as is")
         else:
             raise ValueError("The input cell_param is not supported")
-        
-        
+
+
         if (grid_point is None) and (grid_spacing_matrix is None):
             self.grid_point = None
             self.grid_spacing_matrix = None
@@ -74,7 +74,7 @@ def __init__(
         elif (grid_point is not None) and (grid_spacing_matrix is not None):
             self.grid_point = np.array(grid_point)
             self.grid_spacing_matrix = np.array(grid_spacing_matrix)
-        
+
         if grid_point is not None:
             self.grid_point = self.grid_point.astype(int)
 
@@ -83,7 +83,7 @@ def __init__(
 
     def copy(self):
         return deepcopy(self)
-        
+
     def get_volume(self):
         return np.linalg.det(self.cell_matrix)
 
@@ -92,14 +92,13 @@ def get_dv(self):
             return np.linalg.det(self.grid_spacing_matrix)
         except LinAlgError as ae:
             print("No grid point information is available")
-    
+
     def get_cell_param(self):
         return self.cell_param
 
     def get_cell_angles(self):
         return self.cell_param[3:]
-    
+
     def get_cell_lengths(self):
         return self.cell_param[:3]
 
-