Merge pull request #384 from aperture-data/release-0.4.19

Release 0.4.19

Author: gsaluja9

aperturedb/BBoxDataCSV.py

@@ -15,7 +15,7 @@ class BBoxDataCSV(CSVParser.CSVParser):
     **ApertureDB BBox Data.**
 
     This class loads the Bounding Box Data which is present in a CSV file,
-    and converts it into a series of aperturedb queries.
+    and converts it into a series of ApertureDB queries.
 
     :::note Is backed by a CSV file with the following columns:
     ``IMG_KEY``, ``x_pos``, ``y_pos``, ``width``, ``height``, ``BBOX_PROP_NAME_1``, ... ``BBOX_PROP_NAME_N``, ``constraint_BBOX_PROP_NAME_1``

aperturedb/BlobDataCSV.py

@@ -13,7 +13,7 @@ class BlobDataCSV(CSVParser.CSVParser):
     """**ApertureDB Blob Data.**
 
     This class loads the Blob Data which is present in a CSV file,
-    and converts it into a series of aperturedb queries.
+    and converts it into a series of ApertureDB queries.
 
     :::note Is backed by a CSV file with the following columns:
     ``FILENAME``, ``PROP_NAME_1``, ... ``PROP_NAME_N``, ``constraint_PROP_NAME_1``

aperturedb/BlobNewestDataCSV.py

@@ -15,7 +15,7 @@ class BlobNewestDataCSV(CSVParser.CSVParser):
       Update an Entity which has an associated blob to the data in the CSV
       What this means is:
       - If it doesn't exist, add it.
-      - If it exsits and the blob hasn't changed, update it.
+      - If it exists and the blob hasn't changed, update it.
       - If it exists and the blob has changed, delete and re-add it.
 
        This means if these elements are part of a graph where they are linked by connections
@@ -29,15 +29,15 @@ class BlobNewestDataCSV(CSVParser.CSVParser):
        This class utilizes 3 conditionals
        - normal constraint_ to select the element
        - a series of updateif_ to determine if an update is necessary
-       - one or more prop_ and the assocaited updateif blob conditonals
+       - one or more prop_ and the associated updateif blob conditionals
          to determine if a update or an delete/add is appropriate
 
        Generated fields
         Format is: gen_<type>_name
 
         type:
         - blobsha1 - the sha1 for the blob is calculated
-        - blobsize - the length in bytes of the blob is calcualte
+        - blobsize - the length in bytes of the blob is calculate
         - insertdate - ISO Format of date ( this will always change! )
 
         the result is then used to identify if a blob has changed.
@@ -169,7 +169,7 @@ def filter_generated_constraints(self, return_generated=False):
                     filtered.append(key)
         return filtered
 
-    # creat generated constraints for specific index
+    # create generated constraints for specific index
     # match controls if constrain will be a positive selection (True) or negative(False)
     def create_generated_constraints(self, idx, match=True):
         constraints = {}
@@ -218,7 +218,7 @@ def getitem(self, idx):
         # process is; add if not existing ( # Pt 1 )
         # if existing
         # if blob checks pass ( or there are none ) - update metadata ( Pt 2 )
-        # if blobk check FAILS
+        # if blob check FAILS
         # delete ( Pt 3 )
         # re-add ( Pt 4 )
 

aperturedb/CSVParser.py

@@ -30,11 +30,11 @@ class CSVParser(Subscriptable):
     - **Dask Mode**: This mode is used when the CSV file is too big to fit in memory, or multiprocessing is desired.
         It reads the CSV file into a Dask DataFrame.
         In Dask mode the CSV file is read in chunks, and the operations are performed on each chunk.
-        The tricky bit is that the chunck size is not known till the loader is created, so the processing happens when ingest is called.
+        The tricky bit is that the chunk size is not known till the loader is created, so the processing happens when ingest is called.
         So the Data CSV has another signature, where the df is passed explicitly.
 
     Typically, the response_handler is application specific, and loading does not break
-    on errors in response_handlers, so the default behaviour is to log the error and continue.
+    on errors in response_handlers, so the default behavior is to log the error and continue.
     If you want to break on errors, set strict_response_validation to True.
     """
 

aperturedb/Configuration.py

@@ -4,7 +4,7 @@
 @dataclass(repr=False)
 class Configuration:
     """
-    **Configuration object for aperturedb sdk to be able to connect to ApertureDB**
+    **Configuration object for ApertureDB sdk to be able to connect to ApertureDB**
     """
     host: str
     port: int

aperturedb/ConnectionDataCSV.py

@@ -28,9 +28,9 @@ class ConnectionDataCSV(CSVParser):
 
     **ConnectionClass**: Arbitrary class name for the entity this would be saved as.
 
-    **``ClassName``@``PropertyName``**: This is a special combination of Class Name and Property Name that can uniquely identify an entity. ‘@’ is a delimeter, so should not be used in a property name.
+    **``ClassName``@``PropertyName``**: This is a special combination of Class Name and Property Name that can uniquely identify an entity. ‘@’ is a delimiter, so should not be used in a property name.
 
-    **PROP_NAME_1 .. PROP_NAME_N**: Arbitraty property names.
+    **PROP_NAME_1 .. PROP_NAME_N**: Arbitrary property names.
 
     **constraint_PROP_NAME_1**: A equality check against a unique property to ensure duplicates are not inserted.
 

aperturedb/Connector.py

@@ -70,15 +70,15 @@ def valid(self) -> bool:
 
         # This triggers refresh if the session is about to expire.
         if session_age > self.session_token_ttl - \
-                int(os.getenv("SESSION_EXPIRTY_OFFSET_SEC", 10)):
+                int(os.getenv("SESSION_EXPIRY_OFFSET_SEC", 10)):
             return False
 
         return True
 
 
 class Connector(object):
     """
-    **Class to facilitate connections with an instance of aperturedb**
+    **Class to facilitate connections with an instance of ApertureDB**
 
     It lets the client execute any JSON query based on the [ApertureDB query language specification](/query_language/Overview/API%20Description)
 
@@ -91,7 +91,7 @@ class Connector(object):
         bool (use_ssl): Use SSL to encrypt communication with the database.
         bool (use_keepalive): Set keepalive on the connection with the database.
             This has two benefits: It reduces the chance of disconnection for a long-running query,
-            and it means that diconnections are detected sooner.
+            and it means that disconnections are detected sooner.
             Turn this off to reduce traffic on high-cost network connections.
         Configuration (config): Configuration object to use for connection.
     """

aperturedb/ConnectorRest.py

@@ -44,7 +44,7 @@
 
 class ConnectorRest(Connector):
     """
-    **Class to use aperturedb's REST interface**
+    **Class to use ApertureDB's REST interface**
 
     Args:
         str (host): Address of the host to connect to.
@@ -143,9 +143,9 @@ def _query(self, query, blob_array = [], try_resume=True):
 
         if tries == self.config.retry_max_attempts:
             raise Exception(
-                f"Could not query apertureDB {self.config} using REST.")
+                f"Could not query ApertureDB {self.config} using REST.")
         return (self.last_response, response_blob_array)
 
     def _connect(self):
-        logger.info("Connecting to aperturedb using REST")
+        logger.info("Connecting to ApertureDB using REST")
         self.connected = True

aperturedb/DaskManager.py

@@ -74,8 +74,8 @@ def process(df, host, port, use_ssl, session, connnector_type):
                 count += 1
                 metrics.times_arr.extend(loader.times_arr)
                 metrics.error_counter += loader.error_counter
-                metrics.suceeded_queries += loader.get_suceeded_queries()
-                metrics.suceeded_commands += loader.get_suceeded_commands()
+                metrics.succeeded_queries += loader.get_succeeded_queries()
+                metrics.succeeded_commands += loader.get_succeeded_commands()
 
             return metrics
 

aperturedb/DescriptorDataCSV.py

@@ -18,7 +18,7 @@ class DescriptorDataCSV(CSVParser.CSVParser):
     **ApertureDB Descriptor Data.**
 
     This class loads the Descriptor Data which is present in a CSV file,
-    and converts it into a series of aperturedb queries.
+    and converts it into a series of ApertureDB queries.
 
     :::note Is backed by a CSV file with the following columns, and a NumPy array file "npz" for the descriptors:
     ``filename``, ``index``, ``set``, ``label``, ``PROP_NAME_1``, ... ``PROP_NAME_N``, ``constraint_PROP_NAME_N``
@@ -30,11 +30,11 @@ class DescriptorDataCSV(CSVParser.CSVParser):
 
     **set**: The search space to restrict the knn search queries to.
 
-    **label**: Arbitraty name given to the label associated with this descriptor.
+    **label**: Arbitrary name given to the label associated with this descriptor.
 
     **PROP_NAME_1 .. PROP_NAME_N**: Arbitrarily assigned properties to this descriptor.
 
-    **constraint_PROP_NAME_1**: A constraint to enusre uniqueness when inserting this descriptor.
+    **constraint_PROP_NAME_1**: A constraint to ensure uniqueness when inserting this descriptor.
 
     Example CSV file::
 
@@ -56,7 +56,7 @@ class DescriptorDataCSV(CSVParser.CSVParser):
 
 
     :::info
-    In the above example, the index uniqely identiifes the actual np array from the many arrays in the npz file
+    In the above example, the index uniquely identifies the actual np array from the many arrays in the npz file
     which is same for line 1 and line 2. The UUID and constraint_UUID ensure that a Descriptor is inserted only once in the DB.
 
     Association of an entity to a Descriptor can be specified by first ingesting other Objects, then Descriptors and finally by