Merge pull request #10 from heikomuller/dev0.1.3

Dev0.1.3

changelog.md

@@ -1,20 +1,25 @@
 # Data Frame History Store - Changelog
 
-### 0.1.0 - 05-06-2020
+### 0.1.0 - 2020-05-06
 
 * Initial version. Support for snapshot archives in main-memory and on file system.
 
 
-### 0.1.1 - 06-16-2020
+### 0.1.1 - 2020-06-16
 
 * Allow different types of input documents (e.g., CSV files or Json)
 * External merge-sort for large CSV files.
 * Add managers for maintaining sets of archives
 
 
-### 0.1.2 - 06-25-2020
+### 0.1.2 - 2020-06-25
 
 * Proper handling of date/time objects by the default archive reader and writer
 * Optional arguments for Json encoder and decoder for persistent archives
 * Add encoder and decoder information to archive manager metadata
 * Simple command-line interface for persistent archive manager
+
+
+### 0.1.3 - 2020-10-05
+
+* Add archive manager that maintains descriptors in a relational database (\#8)

histore/__init__.py

@@ -6,4 +6,4 @@
 # file LICENSE for full license details.
 
 from histore.archive.base import Archive, PersistentArchive  # noqa: F401
-from histore.archive.manager.fs import PersistentArchiveManager  # noqa: F401
+from histore.archive.manager.persist import PersistentArchiveManager  # noqa: F401, E501

histore/archive/base.py

@@ -181,11 +181,7 @@ class histore.document.schema.Column.
                     origin = last_snapshot.version
             # Get a modified snapshot list where the last entry represents the
             # new snapshot.
-            snapshots = self.snapshots().append(
-                valid_time=valid_time,
-                description=description
-            )
-            version = snapshots.last_snapshot().version
+            version = self.snapshots().next_version()
             # Merge the new snapshot schema with the current archive schema.
             schema, matched_columns, unchanged_columns = self.schema().merge(
                 columns=doc.columns,
@@ -220,9 +216,15 @@ class histore.document.schema.Column.
             # for cleanup of temporary files.
             doc.close()
         # Commit all changes to the associated archive store.
-        self.store.commit(schema=schema, writer=writer, snapshots=snapshots)
+        snapshot = self.store.commit(
+            schema=schema,
+            writer=writer,
+            version=version,
+            valid_time=valid_time,
+            description=description
+        )
         # Return descriptor for the created snapshot.
-        return snapshots.last_snapshot()
+        return snapshot
 
     def diff(self, original_version, new_version):
         """Get provenance information representing the difference between two

histore/archive/manager/base.py

@@ -8,6 +8,10 @@
 """Abstract class for managers that maintain a set of archives."""
 
 from abc import ABCMeta, abstractmethod
+from typing import Dict, List, Optional, Union
+
+from histore.archive.base import Archive
+from histore.archive.manager.descriptor import ArchiveDescriptor
 
 
 class ArchiveManager(metaclass=ABCMeta):  # pragma: no cover
@@ -17,7 +21,7 @@ class ArchiveManager(metaclass=ABCMeta):  # pragma: no cover
     maintained in an archive descriptor.
     """
     @abstractmethod
-    def archives(self):
+    def archives(self) -> Dict[str, ArchiveDescriptor]:
         """Get dictionary of archive descriptors. The returned dictionary maps
         archive identifier to their descriptor.
 
@@ -27,7 +31,7 @@ def archives(self):
         """
         raise NotImplementedError()
 
-    def contains(self, identifier):
+    def contains(self, identifier: str) -> bool:
         """Returns True if an archive with the given identifier exists.
 
         Parameters
@@ -43,10 +47,12 @@ def contains(self, identifier):
 
     @abstractmethod
     def create(
-        self, name=None, description=None, primary_key=None, encoder=None,
-        decoder=None
-    ):
-        """Create a new archive object.
+        self, name: Optional[str] = None, description: Optional[str] = None,
+        primary_key: Optional[Union[List[str], str]] = None,
+        encoder: Optional[str] = None, decoder: Optional[str] = None
+    ) -> ArchiveDescriptor:
+        """Create a new archive object. Raises a ValueError if an archive with
+        the given name exists.
 
         Parameters
         ----------
@@ -67,11 +73,15 @@ def create(
         Returns
         -------
         histore.archive.manager.descriptor.ArchiveDescriptor
+
+        Raises
+        ------
+        ValueError
         """
         raise NotImplementedError()
 
     @abstractmethod
-    def delete(self, identifier):
+    def delete(self, identifier: str):
         """Delete the archive with the given identifier.
 
         Parameters
@@ -82,7 +92,7 @@ def delete(self, identifier):
         raise NotImplementedError()
 
     @abstractmethod
-    def get(self, identifier):
+    def get(self, identifier: str) -> Archive:
         """Get the archive that is associated with the given identifier. Raises
         a ValueError if the identifier is unknown.
 
@@ -101,7 +111,7 @@ def get(self, identifier):
         """
         raise NotImplementedError()
 
-    def get_by_name(self, name):
+    def get_by_name(self, name: str) -> ArchiveDescriptor:
         """Get descriptor for the archive with the given name. If no archive
         with that name exists None is returned.
 
@@ -119,7 +129,7 @@ def get_by_name(self, name):
                 return archive
         return None
 
-    def list(self):
+    def list(self) -> List[ArchiveDescriptor]:
         """Get the list of descriptors for the maintained archives.
 
         Returns
@@ -129,7 +139,7 @@ def list(self):
         return list(self.archives().values())
 
     @abstractmethod
-    def rename(self, identifier, name):
+    def rename(self, identifier: str, name: str):
         """Rename the specified archive. Raises a ValueError if the identifier
         is unknown or if an archive with the given name exist.
 

histore/archive/manager/db/__init__.py

@@ -0,0 +1,6 @@
+# This file is part of the History Store (histore).
+#
+# Copyright (C) 2018-2020 New York University.
+#
+# The History Store (histore) is released under the Revised BSD License. See
+# file LICENSE for full license details.