Merge pull request #1247 from dimitri-yatsenko/master

Fix error message when deleting without delete privilege

Author: ttngu207

datajoint/autopopulate.py

@@ -100,7 +100,7 @@ def make(self, key):
 
         1. Fetch data from tables above in the dependency hierarchy, restricted by the given key.
         2. Compute secondary attributes based on the fetched data.
-        3. Insert the new tuples into the current table.
+        3. Insert the new tuple(s) into the current table.
 
         The method can be implemented either as:
         (a) Regular method: All three steps are performed in a single database transaction.
@@ -146,7 +146,8 @@ def make(self, key):
         ):
             # user must implement `make`
             raise NotImplementedError(
-                "Subclasses of AutoPopulate must implement the method `make` or (`make_fetch` + `make_compute` + `make_insert`)"
+                "Subclasses of AutoPopulate must implement the method `make` "
+                "or (`make_fetch` + `make_compute` + `make_insert`)"
             )
 
         # User has implemented `_fetch`, `_compute`, and `_insert` methods instead
@@ -265,9 +266,8 @@ def populate(
             self.connection.schemas[self.target.database].jobs if reserve_jobs else None
         )
 
-        # define and set up signal handler for SIGTERM:
         if reserve_jobs:
-
+            # Define a signal handler for SIGTERM
             def handler(signum, frame):
                 logger.info("Populate terminated by SIGTERM")
                 raise SystemExit("SIGTERM received")

datajoint/blob.py

@@ -140,7 +140,7 @@ def read_blob(self, n_bytes=None):
                 "S": self.read_struct,  # matlab struct array
                 "C": self.read_cell_array,  # matlab cell array
                 # basic data types
-                "\xFF": self.read_none,  # None
+                "\xff": self.read_none,  # None
                 "\x01": self.read_tuple,  # a Sequence (e.g. tuple)
                 "\x02": self.read_list,  # a MutableSequence (e.g. list)
                 "\x03": self.read_set,  # a Set
@@ -401,7 +401,7 @@ def read_none(self):
 
     @staticmethod
     def pack_none():
-        return b"\xFF"
+        return b"\xff"
 
     def read_tuple(self):
         return tuple(

datajoint/condition.py

@@ -1,4 +1,4 @@
-""" methods for generating SQL WHERE clauses from datajoint restriction conditions """
+"""methods for generating SQL WHERE clauses from datajoint restriction conditions"""
 
 import collections
 import datetime

datajoint/preview.py

@@ -1,4 +1,4 @@
-""" methods for generating previews of query expression results in python command line and Jupyter """
+"""methods for generating previews of query expression results in python command line and Jupyter"""
 
 from .settings import config
 

datajoint/table.py

@@ -137,7 +137,7 @@ def alter(self, prompt=True, context=None):
         sql, external_stores = alter(self.definition, old_definition, context)
         if not sql:
             if prompt:
-                logger.warn("Nothing to alter.")
+                logger.warning("Nothing to alter.")
         else:
             sql = "ALTER TABLE {tab}\n\t".format(
                 tab=self.full_table_name
@@ -520,7 +520,13 @@ def cascade(table):
                 try:
                     delete_count = table.delete_quick(get_count=True)
                 except IntegrityError as error:
-                    match = foreign_key_error_regexp.match(error.args[0]).groupdict()
+                    match = foreign_key_error_regexp.match(error.args[0])
+                    if match is None:
+                        raise DataJointError(
+                            "Cascading deletes failed because the error message is missing foreign key information."
+                            "Make sure you have REFERENCES privilege to all dependent tables."
+                        ) from None
+                    match = match.groupdict()
                     # if schema name missing, use table
                     if "`.`" not in match["child"]:
                         match["child"] = "{}.{}".format(
@@ -643,7 +649,7 @@ def cascade(table):
         # Confirm and commit
         if delete_count == 0:
             if safemode:
-                logger.warn("Nothing to delete.")
+                logger.warning("Nothing to delete.")
             if transaction:
                 self.connection.cancel_transaction()
         elif not transaction:
@@ -653,12 +659,12 @@ def cascade(table):
                 if transaction:
                     self.connection.commit_transaction()
                 if safemode:
-                    logger.info("Deletes committed.")
+                    logger.info("Delete committed.")
             else:
                 if transaction:
                     self.connection.cancel_transaction()
                 if safemode:
-                    logger.warn("Deletes cancelled")
+                    logger.warning("Delete cancelled")
         return delete_count
 
     def drop_quick(self):
@@ -726,11 +732,6 @@ def size_on_disk(self):
         ).fetchone()
         return ret["Data_length"] + ret["Index_length"]
 
-    def show_definition(self):
-        raise AttributeError(
-            "show_definition is deprecated. Use the describe method instead."
-        )
-
     def describe(self, context=None, printout=False):
         """
         :return:  the definition string for the query using DataJoint DDL.

datajoint/utils.py

@@ -147,3 +147,5 @@ def parse_sql(filepath):
                     if line.endswith(delimiter):
                         yield " ".join(statement)
                         statement = []
+        if statement:
+            yield " ".join(statement)

docs/src/concepts/data-model.md

@@ -54,7 +54,7 @@ columns (often called attributes).
   A collection of base relations with their attributes, domain constraints, uniqueness
   constraints, and referential constraints is called a schema.
 
-**Domain constraints:** 
+**Domain constraints:**
   Each attribute (column) in a table is associated with a specific attribute domain (or
   datatype, a set of possible values), ensuring that the data entered is valid.
   Attribute domains may not include relations, which keeps the data model
@@ -68,13 +68,13 @@ columns (often called attributes).
   One key in a relation is designated as the primary key used for referencing its elements.
 
 **Referential constraints:**
-  Associations among data are established by means of referential constraints with the 
+  Associations among data are established by means of referential constraints with the
   help of foreign keys.
   A referential constraint on relation A referencing relation B allows only those
   entities in A whose foreign key attributes match the key attributes of an entity in B.
 
 **Declarative queries:**
-  Data queries are formulated through declarative, as opposed to imperative, 
+  Data queries are formulated through declarative, as opposed to imperative,
   specifications of sought results.
   This means that query expressions convey the logic for the result rather than the
   procedure for obtaining it.
@@ -106,7 +106,7 @@ clarity, efficiency, workflow management, and precise and flexible data
 queries. By enforcing entity normalization,
 simplifying dependency declarations, offering a rich query algebra, and visualizing
 relationships through schema diagrams, DataJoint makes relational database programming
-more intuitive and robust for complex data pipelines. 
+more intuitive and robust for complex data pipelines.
 
 The model has emerged over a decade of continuous development of complex data
 pipelines for neuroscience experiments ([Yatsenko et al.,
@@ -123,7 +123,7 @@ DataJoint comprises:
 + a schema [definition](../design/tables/declare.md) language
 + a data [manipulation](../manipulation/index.md) language
 + a data [query](../query/principles.md) language
-+ a [diagramming](../design/diagrams.md) notation for visualizing relationships between 
++ a [diagramming](../design/diagrams.md) notation for visualizing relationships between
 modeled entities
 
 The key refinement of DataJoint over other relational data models and their

docs/src/concepts/teamwork.md

@@ -60,33 +60,33 @@ division of labor among team members, leading to greater efficiency and better s
 ### Scientists
 
 Design and conduct experiments, collecting data.
-They interact with the data pipeline through graphical user interfaces designed by 
+They interact with the data pipeline through graphical user interfaces designed by
 others.
 They understand what analysis is used to test their hypotheses.
 
 ### Data scientists
 
-Have the domain expertise and select and implement the processing and analysis 
+Have the domain expertise and select and implement the processing and analysis
 methods for experimental data.
-Data scientists are in charge of defining and managing the data pipeline using 
-DataJoint's data model, but they may not know the details of the underlying 
+Data scientists are in charge of defining and managing the data pipeline using
+DataJoint's data model, but they may not know the details of the underlying
 architecture.
-They interact with the pipeline using client programming interfaces directly from 
+They interact with the pipeline using client programming interfaces directly from
 languages such as MATLAB and Python.
 
-The bulk of this manual is written for working data scientists, except for System 
+The bulk of this manual is written for working data scientists, except for System
 Administration.
 
 ### Data engineers
 
 Work with the data scientists to support the data pipeline.
-They rely on their understanding of the DataJoint data model to configure and 
-administer the required IT resources such as database servers, data storage 
+They rely on their understanding of the DataJoint data model to configure and
+administer the required IT resources such as database servers, data storage
 servers, networks, cloud instances, [Globus](https://globus.org) endpoints, etc.
-Data engineers can provide general solutions such as web hosting, data publishing, 
+Data engineers can provide general solutions such as web hosting, data publishing,
 interfaces, exports and imports.
 
-The System Administration section of this tutorial contains materials helpful in 
+The System Administration section of this tutorial contains materials helpful in
 accomplishing these tasks.
 
 DataJoint is designed to delineate a clean boundary between **data science** and **data

docs/src/design/integrity.md

@@ -1,7 +1,7 @@
 # Data Integrity
 
-The term **data integrity** describes guarantees made by the data management process 
-that prevent errors and corruption in data due to technical failures and human errors 
+The term **data integrity** describes guarantees made by the data management process
+that prevent errors and corruption in data due to technical failures and human errors
 arising in the course of continuous use by multiple agents.
 DataJoint pipelines respect the following forms of data integrity: **entity
 integrity**, **referential integrity**, and **group integrity** as described in more

docs/src/design/tables/customtype.md

@@ -49,9 +49,9 @@ attribute type in a datajoint table class:
 import datajoint as dj
 
 class GraphAdapter(dj.AttributeAdapter):
-    
+
     attribute_type = 'longblob'   # this is how the attribute will be declared
-    
+
     def put(self, obj):
         # convert the nx.Graph object  into an edge list
         assert isinstance(obj, nx.Graph)
@@ -60,7 +60,7 @@ class GraphAdapter(dj.AttributeAdapter):
     def get(self, value):
         # convert edge list back into an nx.Graph
         return nx.Graph(value)
-    
+
 
 # instantiate for use as a datajoint type
 graph = GraphAdapter()
@@ -75,6 +75,6 @@ class Connectivity(dj.Manual):
     definition = """
     conn_id : int
     ---
-    conn_graph = null : <graph>  # a networkx.Graph object 
+    conn_graph = null : <graph>  # a networkx.Graph object
     """
 ```