Move calc_id into job.py

changelog.txt

@@ -33,6 +33,7 @@ Changed
  - Tests are run with ``xfail_strict = True`` (#850).
  - Detection of an invalid config will raise an error rather than a debug log (#855).
  - The package namespace has been flattened so that most functionality is directly available in the ``signac`` namespace (#756, #868).
+ - The ``calc_id`` function has been moved from the ``hashing`` module to the ``job`` module (#873).
 
 Removed
 +++++++

signac/job.py

@@ -4,11 +4,12 @@
 """Job class defined here."""
 
 import errno
+import hashlib
+import json
 import logging
 import os
 import shutil
 from copy import deepcopy
-from json import JSONDecodeError
 from threading import RLock
 from typing import FrozenSet
 
@@ -18,15 +19,38 @@
     json_attr_dict_validator,
 )
 from ._synced_collections.errors import KeyTypeError
+from ._synced_collections.utils import SyncedCollectionJSONEncoder
 from ._utility import _mkdir_p
 from .errors import DestinationExistsError, JobsCorruptedError
 from .h5store import H5StoreManager
-from .hashing import calc_id
 from .sync import sync_jobs
 
 logger = logging.getLogger(__name__)
 
 
+def calc_id(statepoint):
+    """Calculate and return a hash value for the given statepoint.
+
+    The hash is computed as an MD5 checksum of the input data. The input data
+    is first encoded as JSON, with dictionary keys sorted to ensure the hash
+    is reproducible.
+
+    Parameters
+    ----------
+    statepoint : dict
+        A JSON-encodable mapping.
+
+    Returns
+    -------
+    str
+        Encoded hash in hexadecimal format.
+    """
+    blob = json.dumps(statepoint, cls=SyncedCollectionJSONEncoder, sort_keys=True)
+    m = hashlib.md5()
+    m.update(blob.encode())
+    return m.hexdigest()
+
+
 # Note: All children of _StatePointDict will be of its parent type because they
 # share a backend and the SyncedCollection registry parses the classes in order
 # of registration. _If_ we need more control over this, that process can be
@@ -203,7 +227,7 @@ def load(self, job_id):
         """
         try:
             data = self._load_from_resource()
-        except JSONDecodeError:
+        except json.JSONDecodeError:
             raise JobsCorruptedError([job_id])
 
         if calc_id(data) != job_id:

signac/project.py

@@ -39,8 +39,7 @@
 )
 from .filterparse import _add_prefix, _root_keys, parse_filter
 from .h5store import H5StoreManager
-from .hashing import calc_id
-from .job import Job
+from .job import Job, calc_id
 from .schema import ProjectSchema
 from .sync import sync_projects
 from .version import SCHEMA_VERSION, __version__

tests/test_project.py

@@ -35,7 +35,7 @@
     StatepointParsingError,
     WorkspaceError,
 )
-from signac.hashing import calc_id
+from signac.job import calc_id
 from signac.linked_view import _find_all_links
 from signac.project import JobsCursor, Project  # noqa: F401
 from signac.schema import ProjectSchema