digichem-core 6.10.1__py3-none-any.whl → 6.10.3__py3-none-any.whl

digichem/__init__.py

@@ -20,7 +20,7 @@ from digichem.datas import get_resource
 # development = prerelease is not None
 # # The full version number of this package.
 # __version__ = "{}.{}.{}{}".format(major_version, minor_version, revision, "-pre.{}".format(prerelease) if development else "")
-__version__ = "6.10.1"
+__version__ = "6.10.3"
 _v_parts = __version__.split("-")[0].split(".")
 major_version = int(_v_parts[0])
 minor_version = int(_v_parts[1])
@@ -39,7 +39,7 @@ __author__ = [
 ]
 
 # Program date (when we were last updated). This is changed automatically.
-_last_updated_string = "28/05/2025"
+_last_updated_string = "09/06/2025"
 last_updated = datetime.strptime(_last_updated_string, "%d/%m/%Y")
 
 # The sys attribute 'frozen' is our flag, '_MEIPASS' is the dir location.

digichem/config/base.py

@@ -72,7 +72,7 @@ Possible options are:
         ),
         batoms = Options(help = "Beautiful Atoms/Blender specific options (only applies if engine == 'batoms'",
             blender = Option(help = "Path to the blender executable, in which beautiful atoms should be installed", default = "batoms-blender"),
-            cpus = Option(help = "The number of CPUs/threads to use. This option is overridden if running in a calculation environemnt (where it uses the same number of CPUs as the calculation did)", type = int, default = 1),
+            cpus = Option(help = "The number of CPUs/threads to use. This option is overridden if running in a calculation environment (where it uses the same number of CPUs as the calculation did)", type = int, default = 1),
             render_samples = Option(help = "The number of render samples (or passes) to use. Higher values result in higher image quality and greater render times", type = int, default = 32),
             perspective = Option(help = "The perspective mode", choices = ["orthographic", "perspective"], default = "perspective"),
             stacking = Option(help = "The number of image copies to composite together to avoid transparency artifacts", type = int, default = 10)

digichem/image/render.py

@@ -247,7 +247,6 @@ class Batoms_renderer(Render_maker):
             # "--render-samples", f"{samples}",
             "--perspective", f"{self.perspective}",
             "--padding", f"{padding}",
-            "--rotations",
         ]
         for orientation, resolution, samples, mini_file_name in targets:
             args.extend([
@@ -258,9 +257,12 @@ class Batoms_renderer(Render_maker):
                 mini_file_name
             ])
 
-        # Add rotations.
-        for rotation in self.rotations:
-            args.append(json.dumps(rotation))
+        if len(self.rotations) > 0:
+            args.append("--rotations")
+
+            # Add rotations.
+            for rotation in self.rotations:
+                args.append(json.dumps(rotation))
         
         return args
     

digichem/misc/io.py

@@ -6,6 +6,7 @@ import os
 import shutil
 import sys
 import warnings
+import itertools
 from uuid import uuid4
 import hashlib
 
@@ -320,3 +321,13 @@ class Safe_path():
         """
         # Close our file.
         self.close()
+
+def dir_size(target):
+    """
+    Calculate the total used file space of a directory and all contents.
+    """
+    bytes = 0
+    for path in itertools.chain(Path(target).rglob("*"), [Path(target)]):
+        bytes += path.stat().st_size
+    
+    return bytes

digichem/parse/cclib.py

@@ -156,15 +156,49 @@ class Cclib_parser(File_parser_abc):
             headers = next(reader)
 
             # Check headers match.
-            if (headers[0] != "Duration / s" or 
-               headers[1] != "Memory Used (Real) / bytes" or
-               headers[2] != "Memory Used (Real) / %" or
-               headers[3] != "Memory Available  (Real) / bytes" or
-               headers[4] != "Memory Available (Real) / %" or
-               headers[9] != "CPU Usage / %" or
-               headers[15] != "Output Directory Available / bytes" or
-               headers[17] != "Scratch Directory Available / bytes"
+            if (headers[0] == "Duration / s" and 
+               headers[1] == "Memory Used (Real) / bytes" and
+               headers[2] == "Memory Used (Real) / %" and
+               headers[3] == "Memory Available  (Real) / bytes" and
+               headers[4] == "Memory Available (Real) / %" and
+               headers[9] == "CPU Usage / %" and
+               headers[15] == "Output Directory Available / bytes" and
+               headers[17] == "Scratch Directory Used / bytes" and
+               headers[18] == "Scratch Directory Available / bytes"
             ):
+                column_map = {
+                    "duration": 0,
+                    "memory_used": 1,
+                    "memory_used_percent": 2,
+                    "memory_available": 3,
+                    "memory_available_percent": 4,
+                    "cpu_used": 9,
+                    "output_available": 15,
+                    "scratch_used": 17,
+                    "scratch_available": 18
+                }
+            
+            elif (headers[0] == "Duration / s" and 
+               headers[1] == "Memory Used (Real) / bytes" and
+               headers[2] == "Memory Used (Real) / %" and
+               headers[3] == "Memory Available  (Real) / bytes" and
+               headers[4] == "Memory Available (Real) / %" and
+               headers[9] == "CPU Usage / %" and
+               headers[15] == "Output Directory Available / bytes" and
+               headers[17] == "Scratch Directory Available / bytes"
+            ):
+                column_map = {
+                    "duration": 0,
+                    "memory_used": 1,
+                    "memory_used_percent": 2,
+                    "memory_available": 3,
+                    "memory_available_percent": 4,
+                    "cpu_used": 9,
+                    "output_available": 15,
+                    "scratch_available": 17
+                }
+            
+            else:
                 raise Digichem_exception("wrong headers found in profile.csv file")
             
             # Then the body.
@@ -185,17 +219,19 @@ class Cclib_parser(File_parser_abc):
         # - cpu used
         # - output space
         # - scratch space
-        new_data = numpy.zeros((math.ceil(lines / factor), 8))
+        new_data = numpy.zeros((math.ceil(lines / factor), len(column_map)))
 
         # Now decimate.
-        for i, k in enumerate([0,1,2,3,4,9,15,17]):
+        for i, k in enumerate(column_map.values()):
             if factor > 1:
                 new_data[:, i] = signal.decimate(data[:, k], factor)
             else:
                 new_data[:, i] = data[:, k]
         
         
-        self.data.metadata['performance'] = new_data
+        self.data.metadata['performance'] = {
+            key: new_data[:, index] for index, key in enumerate(column_map)
+        }
         
         
     def parse_output_line(self, log_file, line):

digichem/parse/pyscf.py

@@ -1,9 +1,11 @@
 import hashlib
 import json
+from uuid import uuid4
 
 from cclib.bridge.cclib2pyscf import cclibfrommethods
 
 from digichem.parse.base import Parser_abc
+import digichem.log
 
 class Pyscf_parser(Parser_abc):
     """
@@ -17,9 +19,17 @@ class Pyscf_parser(Parser_abc):
 
     def _parse(self):
         self.data = cclibfrommethods(**self.methods)
-        # TODO: We need some way of generating a checksum
-        self.data._id = hashlib.sha1(json.dumps(dir(self.data), sort_keys = True).encode('utf-8')).hexdigest()
+        
+        try:
+            # Try to generate a checksum from metadata.
+            self.data._id = hashlib.sha1(json.dumps(self.data.metadata, sort_keys = True).encode('utf-8')).hexdigest()
+
+        except Exception:
+            # No luck, something in metadata must be unhashable.
+            digichem.log.get_logger().error("Unable to generate hash ID from calculation metadata, using random ID instead", exc_info = True)
+            # TODO: Think of a better way to do this.
+            self.data._id = hashlib.sha1(uuid4().hex.encode('utf-8')).hexdigest()
+        
         self.data.metadata['name'] = self.mol_name
         self.data._aux = {'methods': self.methods}
-            
             

digichem/result/metadata.py

@@ -679,8 +679,9 @@ class Performance(Result_object):
         memory_available = [],
         memory_available_percent = [],
         cpu_used = [],
-        output_space = [],
-        scratch_space = [],
+        output_available = [],
+        scratch_used = [],
+        scratch_available = [],
         memory_allocated = None,
         cpu_allocated = None,
     ):
@@ -690,11 +691,22 @@ class Performance(Result_object):
         self.memory_available = memory_available
         self.memory_available_percent = memory_available_percent
         self.cpu_used = cpu_used
-        self.output_space = output_space
-        self.scratch_space = scratch_space
+        self.output_available = output_available
+        self.scratch_used = scratch_used
+        self.scratch_available = scratch_available
 
         self.memory_allocated = memory_allocated if memory_allocated is not None else self.max_mem
         self.cpu_allocated = cpu_allocated if cpu_allocated is not None else math.ceil(max(cpu_used) / 100)
+
+    @property
+    def output_space(self):
+        warnings.warn("output_space is deprecated, use output_available instead", DeprecationWarning)
+        return self.output_available
+
+    @property
+    def scratch_space(self):
+        warnings.warn("scratch_space is deprecated, use scratch_available instead", DeprecationWarning)
+        return self.scratch_available
     
 
     @classmethod
@@ -705,6 +717,21 @@ class Performance(Result_object):
         :param parser: Output data parser.
         :return: A populated Performance object.
         """
+        return self(
+            duration = parser.data.metadata['performance']['duration'].tolist(),
+            memory_used = parser.data.metadata['performance']['memory_used'].tolist(),
+            memory_allocated = Memory(parser.data.metadata['memory_available']) if "memory_available" in parser.data.metadata else None,
+            memory_used_percent = parser.data.metadata['performance']['memory_used_percent'].tolist(),
+            memory_available = parser.data.metadata['performance']['memory_available'].tolist(),
+            memory_available_percent = parser.data.metadata['performance']['memory_available_percent'].tolist(),
+            cpu_used = parser.data.metadata['performance']['cpu_used'].tolist(),
+            cpu_allocated = parser.data.metadata.get('num_cpu', None),
+            output_available = parser.data.metadata['performance']['output_available'].tolist(),
+            scratch_used = parser.data.metadata['performance']['scratch_used'].tolist() if 'scratch_used' in parser.data.metadata['performance'] else [0] * len(parser.data.metadata['performance']['duration']),
+            scratch_available = parser.data.metadata['performance']['scratch_available'].tolist()
+        )
+    
+
         return self(
             duration = parser.data.metadata['performance'][:, 0].tolist(),
             memory_used = parser.data.metadata['performance'][:, 1].tolist(),
@@ -788,8 +815,9 @@ class Performance(Result_object):
         memory_available_percent = [0.0] * len(data['values'])
         cpu_used = [0.0] * len(data['values'])
         cpu_allocated = data['cpu_allocated']
-        output_space = [0.0] * len(data['values'])
-        scratch_space = [0.0] * len(data['values'])
+        output_available = [0.0] * len(data['values'])
+        scratch_used = [0.0] * len(data['values'])
+        scratch_available = [0.0] * len(data['values'])
 
         for i, value in enumerate(data['values']):
             duration[i] = value['duration']['value']
@@ -798,8 +826,10 @@ class Performance(Result_object):
             memory_available[i] = value['memory_available']['value']
             memory_available_percent[i] = value['memory_available_percent']['value']
             cpu_used[i] = value['cpu_used']['value']
-            output_space[i] = value['output_space']['value']
-            scratch_space[i] = value['scratch_space']['value']
+            output_available[i] = value['output_space']['value']
+            if 'scratch_used' in value:
+                scratch_used[i] = value['scratch_used']['value']
+            scratch_available[i] = value['scratch_space']['value']
         
         return self(
             duration = duration,
@@ -810,8 +840,9 @@ class Performance(Result_object):
             memory_available_percent = memory_available_percent,
             cpu_used = cpu_used,
             cpu_allocated = cpu_allocated,
-            output_space = output_space,
-            scratch_space = scratch_space
+            output_available = output_available,
+            scratch_used = scratch_used,
+            scratch_available = scratch_available
         )
 
     
@@ -871,6 +902,10 @@ class Performance(Result_object):
                         "units": "bytes",
                         "value": self.output_space[i]
                     },
+                    'scratch_used': {
+                        "units": "bytes",
+                        "value": self.scratch_used[i]
+                    },
                     'scratch_space': {
                         "units": "bytes",
                         "value": self.scratch_space[i]

digichem/test/conftest.py

@@ -1,4 +1,9 @@
 import numpy
+import os
+from pathlib import Path
 
 # Set numpy errors (not sure why this isn't the default...)
 numpy.seterr(invalid = 'raise', divide = 'raise')
+
+# Expand path to include mocks.
+os.environ["PATH"] = str(Path(__file__).parent / "mock") + os.pathsep + os.environ["PATH"]