Merge pull request #106 from casework/release-0.10.0

Release 0.10.0

Author: kchason

.github/workflows/cicd.yml

@@ -23,6 +23,8 @@ on:
   release:
     types:
       - published
+  schedule:
+    - cron: '15 5 * * TUE'
 
 jobs:
   build:
@@ -31,7 +33,7 @@ jobs:
     strategy:
       matrix:
         python-version: 
-          - '3.7'
+          - '3.8'
           - '3.11'
 
     steps:

.pre-commit-config.yaml

@@ -1,14 +1,14 @@
 repos:
   - repo: https://github.com/psf/black
-    rev: 22.10.0
+    rev: 23.1.0
     hooks:
       - id: black
   - repo: https://github.com/pycqa/flake8
-    rev: 5.0.4
+    rev: 6.0.0
     hooks:
       - id: flake8
   - repo: https://github.com/pycqa/isort
-    rev: 5.10.1
+    rev: 5.12.0
     hooks:
       - id: isort
         name: isort (python)

case_utils/__init__.py

@@ -11,6 +11,6 @@
 #
 # We would appreciate acknowledgement if the software is used.
 
-__version__ = "0.9.0"
+__version__ = "0.10.0"
 
 from . import local_uuid  # noqa: F401

case_utils/case_file/__init__.py

@@ -39,6 +39,7 @@
 
 DEFAULT_PREFIX = "http://example.org/kb/"
 
+
 # Shortcut syntax for defining an immutable named tuple is noted here:
 # https://docs.python.org/3/library/typing.html#typing.NamedTuple
 # via the "See also" box here: https://docs.python.org/3/library/collections.html#collections.namedtuple

case_utils/case_sparql_construct/__init__.py

@@ -15,7 +15,7 @@
 This script executes a SPARQL CONSTRUCT query, returning a graph of the generated triples.
 """
 
-__version__ = "0.2.4"
+__version__ = "0.2.5"
 
 import argparse
 import logging
@@ -98,10 +98,11 @@ def main() -> None:
     construct_query_result = in_graph.query(construct_query_object)
     _logger.debug("type(construct_query_result) = %r." % type(construct_query_result))
     _logger.debug("len(construct_query_result) = %d." % len(construct_query_result))
-    for (row_no, row) in enumerate(construct_query_result):
+    for row_no, row in enumerate(construct_query_result):
+        assert isinstance(row, tuple)
         if row_no == 0:
             _logger.debug("row[0] = %r." % (row,))
-        out_graph.add(row)
+        out_graph.add((row[0], row[1], row[2]))
 
     output_format = None
     if args.output_format is None:

case_utils/case_sparql_select/__init__.py

@@ -26,7 +26,7 @@
 Should a more complex query be necessary, an outer, wrapping SELECT query would let this script continue to function.
 """
 
-__version__ = "0.5.0"
+__version__ = "0.5.1"
 
 import argparse
 import binascii
@@ -86,26 +86,27 @@ def graph_and_query_to_data_frame(
     select_query_object = rdflib.plugins.sparql.processor.prepareQuery(
         select_query_text, initNs=nsdict
     )
-    for (row_no, row) in enumerate(_graph.query(select_query_object)):
+    for row_no, row in enumerate(_graph.query(select_query_object)):
+        assert isinstance(row, rdflib.query.ResultRow)
         tally = row_no + 1
         record = []
-        for (column_no, column) in enumerate(row):
+        for column_no, column in enumerate(row):
             if column is None:
                 column_value = ""
-            elif (
-                isinstance(column, rdflib.term.Literal)
-                and column.datatype == NS_XSD.hexBinary
-            ):
-                # Use hexlify to convert xsd:hexBinary to ASCII.
-                # The render to ASCII is in support of this script rendering results for website viewing.
-                # .decode() is because hexlify returns bytes.
-                column_value = binascii.hexlify(column.toPython()).decode()
+            elif isinstance(column, rdflib.term.Literal):
+                if column.datatype == NS_XSD.hexBinary:
+                    # Use hexlify to convert xsd:hexBinary to ASCII.
+                    # The render to ASCII is in support of this script rendering results for website viewing.
+                    # .decode() is because hexlify returns bytes.
+                    column_value = binascii.hexlify(column.toPython()).decode()
+                else:
+                    column_value = column.toPython()
             elif isinstance(column, rdflib.URIRef):
                 if use_prefixes:
                     column_value = graph.namespace_manager.qname(column.toPython())
                 else:
                     column_value = column.toPython()
-            else:
+            elif isinstance(column, rdflib.BNode):
                 column_value = column.toPython()
             if row_no == 0:
                 _logger.debug("row[0]column[%d] = %r." % (column_no, column_value))

case_utils/local_uuid.py

@@ -15,7 +15,7 @@
 This library is a wrapper for uuid, provided to generate repeatable UUIDs if requested.
 """
 
-__version__ = "0.3.1"
+__version__ = "0.3.2"
 
 import logging
 import os
@@ -33,6 +33,9 @@
 
 
 def configure() -> None:
+    """
+    This function is part of setting up demo_uuid() to generate non-random UUIDs.  See demo_uuid() documentation for further setup notes.
+    """
     global DEMO_UUID_BASE
 
     if os.getenv("DEMO_UUID_REQUESTING_NONRANDOM") == "NONRANDOM_REQUESTED":
@@ -112,7 +115,10 @@ def demo_uuid() -> str:
 
     WARNING: This function was developed for use ONLY for reducing (but not eliminating) version-control edits to identifiers when generating sample data.  It creates UUIDs that are decidedly NOT random, and should remain consistent on repeated calls to the importing script.
 
-    To prevent accidental non-random UUID usage, an environment variable, CASE_DEMO_NONRANDOM_UUID_BASE, must be set to a string provided by the caller.  The variable's required value is the path to some directory.  The variable's recommended value is the equivalent of the Make variable "top_srcdir" - that is, the root directory of the containing Git repository, some parent of the current process's current working directory.
+    To prevent accidental non-random UUID usage, two setup steps need to be done before calling this function:
+
+    * An environment variable, CASE_DEMO_NONRANDOM_UUID_BASE, must be set to a string provided by the caller.  The variable's required value is the path to some directory.  The variable's recommended value is the equivalent of the Make variable "top_srcdir" - that is, the root directory of the containing Git repository, some parent of the current process's current working directory.
+    * The configure() function in this module must be called.
     """
     global DEMO_UUID_BASE
     global DEMO_UUID_COUNTER

case_utils/ontology/Makefile

@@ -29,8 +29,16 @@ all: \
 .PRECIOUS: \
   case-$(case_version).ttl
 
+$(case_srcdir)/.venv.done.log: \
+  $(top_srcdir)/.git_submodule_init.done.log
+	$(MAKE) \
+	  --directory $(case_srcdir) \
+	    .venv.done.log
+	touch -c $@
+	test -r $@
+
 case-$(case_version).ttl: \
-  $(top_srcdir)/.git_submodule_init.done.log \
+  $(case_srcdir)/.venv.done.log \
   $(RDF_TOOLKIT_JAR)
 	$(MAKE) \
 	  --directory $(case_srcdir)/tests \
@@ -47,10 +55,7 @@ case-$(case_version)-subclasses.ttl: \
 	# release is being made, that step will have been skipped.
 	# This recursive Make call guarantees the virtual environment is
 	# set up.
-	$(MAKE) \
-	  --directory $(case_srcdir)/tests \
-	    .venv.done.log
-	source $(case_srcdir)/tests/venv/bin/activate \
+	source $(case_srcdir)/venv/bin/activate \
 	  && python3 src/subclasses_ttl.py \
 	  __$@ \
 	 $<
@@ -70,11 +75,7 @@ clean:
 ontology_and_version_iris.txt: \
   src/ontology_and_version_iris.py \
   case-$(case_version)-subclasses.ttl
-	# Guarantee venv is built.  (Same rationale as in the subclasses.ttl recipe.)
-	$(MAKE) \
-	  --directory $(case_srcdir)/tests \
-	    .venv.done.log
-	source $(case_srcdir)/tests/venv/bin/activate \
+	source $(case_srcdir)/venv/bin/activate \
 	  && python3 src/ontology_and_version_iris.py \
 	    _$@ \
 	    case-*.ttl