Merge pull request #12 from nlesc-nano/devel

Data-CAT 0.1.1

CHANGELOG.rst

@@ -6,6 +6,13 @@ All notable changes to this project will be documented in this file.
 This project adheres to `Semantic Versioning <http://semver.org/>`_.
 
 
+0.1.1
+*****
+
+* Introduced a proper logger (see https://github.com/nlesc-nano/CAT/issues/46 and
+  https://github.com/nlesc-nano/CAT/pull/47).
+
+
 [Unreleased]
 ************
 

README.rst

@@ -3,7 +3,7 @@
 
 
 ##############
-Data-CAT 0.1.0
+Data-CAT 0.1.1
 ##############
 
 Data-CAT is a databasing framework for the Compound Attachment Tools package (CAT_).

dataCAT/__init__.py

@@ -9,7 +9,7 @@
 from .__version__ import __version__
 
 from .database import Database
-from .database_functions import (mol_to_file, df_to_mongo_dict)
+from .database_functions import (df_to_mongo_dict)
 
 
 __version__ = __version__
@@ -18,5 +18,5 @@
 
 __all__ = [
     'Database',
-    'mol_to_file', 'df_to_mongo_dict'
+    'df_to_mongo_dict'
 ]

dataCAT/__version__.py

@@ -1 +1 @@
-__version__ = '0.1.0'
+__version__ = '0.1.1'

dataCAT/create_database.py

@@ -35,7 +35,7 @@
 import pandas as pd
 from pymongo import MongoClient, ASCENDING
 
-from CAT.utils import get_time
+from CAT.logger import logger
 
 __all__: List[str] = []
 
@@ -62,16 +62,15 @@ def _create_csv(path: str,
 
     # Check if the database exists and has the proper keys; create it if it does not
     if not isfile(path):
-        msg = get_time() + '{}_database.csv not found in {}, creating {} database'
-        print(msg.format(database, path, database))
+        msg = f'{database}_database.csv not found in {path}, creating {database} database'
+        logger.info(msg)
 
         if database == 'ligand':
             _create_csv_lig(path)
         elif database == 'QD':
             _create_csv_qd(path)
         else:
-            err = "'{}' is not an accepated value for the 'database' argument"
-            raise ValueError(err.format(database))
+            raise ValueError(f"'{database}' is not an accepated value for the 'database' argument")
     return path
 
 

dataCAT/database.py

@@ -34,6 +34,7 @@
 from rdkit.Chem import Mol
 from scm.plams import (Settings, Molecule)
 
+from CAT.logger import logger
 from CAT.mol_utils import from_rdmol
 from .database_functions import (
     df_to_mongo_dict, even_index, from_pdb_array, sanitize_yaml_settings, as_pdb_array
@@ -355,12 +356,14 @@ def __setitem__(self, key: Immutable,
                     if not isinstance(value, pd.DataFrame):
                         raise KeyError
                     super().__setitem__('df', value)
+
                 except KeyError:
-                    err = ("Instance of 'pandas.DataFrame' or 'CAT.Database.DF' expected;"
-                           " observed type: '{}'")
-                    raise TypeError(err.format(value.__class__.__name__))
+                    raise TypeError("Instance of 'pandas.DataFrame' or 'CAT.Database.DF' expected;"
+                                    " observed type: '{value.__class__.__name__}'")
+
             elif key == 'df':
                 super().__setitem__('df', value)
+
             else:
                 self['df'].__setitem__(key, value)
 
@@ -382,8 +385,7 @@ def _parse_database(self, database: str) -> Tuple[str, Callable]:
             path = self.csv_qd
             open_csv = self.OpenCsvQd
         else:
-            err = "database={}; accepted values for database are 'ligand' and 'QD'"
-            raise ValueError(err.format(database))
+            raise ValueError(f"database={database}; accepted values for are 'ligand' and 'QD'")
         return path, open_csv
 
     def update_mongodb(self, database: Union[str, Dict[str, pd.DataFrame]] = 'ligand',
@@ -421,7 +423,7 @@ def update_mongodb(self, database: Union[str, Dict[str, pd.DataFrame]] = 'ligand
 
         """
         if self.mongodb is None:
-            raise ValueError
+            raise ValueError('Database.Mongodb is None')
 
         # Open the MongoDB database
         client = MongoClient(**self.mongodb)
@@ -864,16 +866,17 @@ def hdf5_availability(self, timeout: float = 5.0,
             Raised if **max_attempts** is exceded.
 
         """
-        warning = "OSWarning: '{}' is currently unavailable; repeating attempt in {:.0f} seconds"
+        err = f"'{self.hdf5}' is currently unavailable; repeating attempt in {timeout:.0f} seconds"
         i = max_attempts or np.inf
 
         while i:
             try:
                 with h5py.File(self.hdf5, 'r+') as _:
                     return None  # the .hdf5 file can safely be opened
             except OSError as ex:  # the .hdf5 file cannot be safely opened yet
-                print((warning).format(self.hdf5, timeout))
+                logger.warn(err)
                 error = ex
                 sleep(timeout)
             i -= 1
-        raise error
+
+        raise error.__class__(error)

dataCAT/database_functions.py

@@ -44,58 +44,12 @@
 from rdkit.Chem import Mol
 
 from CAT.utils import get_template
+from CAT.logger import logger
 from CAT.mol_utils import from_rdmol
 
 __all__ = ['mol_to_file', 'df_to_mongo_dict']
 
 
-def mol_to_file(mol_list: Iterable[Molecule],
-                path: Optional[str] = None,
-                overwrite: bool = False,
-                mol_format: Collection[str] = ('xyz', 'pdb')) -> None:
-    """Export all molecules in **mol_list** to .pdb and/or .xyz files.
-
-    Parameters
-    ----------
-    mol_list: |list|_ [|plams.Molecule|_]
-        An iterable consisting of PLAMS molecules.
-
-    path : str
-        Optional: The path to the directory where the molecules will be stored.
-        Defaults to the current working directory if ``None``.
-
-    overwrite : bool
-        If previously generated files can be overwritten or not.
-
-    mol_format : |list|_ [|str|_]
-        A list of strings with the to-be exported file types.
-        Accepted values are ``"xyz"`` and/or ``"pdb"``.
-
-    """
-    # Set the export path
-    path = path or getcwd()
-    assert isdir(path)
-
-    if not mol_format:
-        return None
-
-    if overwrite:  # Export molecules while allowing for file overriding
-        for mol in mol_list:
-            mol_path = join(path, mol.properties.name)
-            if 'pdb' in mol_format:
-                molkit.writepdb(mol, mol_path + '.pdb')
-            if 'xyz' in mol_format:
-                mol.write(mol_path + '.xyz')
-
-    else:  # Export molecules without allowing for file overriding
-        for mol in mol_list:
-            mol_path = join(path, mol.properties.name)
-            if 'pdb' in mol_format and not isfile(mol_path + '.pdb'):
-                molkit.writepdb(mol, mol_path + '.pdb')
-            if 'xyz' in mol_format and not isfile(mol_path + '.xyz'):
-                mol.write(mol_path + '.xyz')
-
-
 Immutable = Union[str, int, float, frozenset, tuple]  # Immutable objects
 
 
@@ -154,9 +108,8 @@ def _get_dict(idx: Sequence[Immutable],
         return ret
 
     if not (isinstance(df.index, pd.MultiIndex) and isinstance(df.columns, pd.MultiIndex)):
-        raise TypeError(
-            "DataFrame.index and DataFrame.columns should be instances of pandas.MultiIndex"
-        )
+        raise TypeError("DataFrame.index and DataFrame.columns should be "
+                        "instances of pandas.MultiIndex")
 
     idx_names = df.index.names
     if as_gen: