Merge branches 'master' and 'process_tracker_python-143' of https://github.com/OpenDataAlex/process_tracker_python into process_tracker_python-143

Author: Alex Meadows

dbscripts/mysql_process_tracker.sql

@@ -74,7 +74,7 @@ create table extract_filetype_lkup
 (
 	extract_filetype_id int auto_increment
 		primary key,
-	extract_filetype_code varchar(5) not null,
+	extract_filetype_code varchar(25) not null,
 	extract_filetype varchar(75) not null,
 	delimiter_char char null,
 	quote_char char null,

dbscripts/postgresql_process_tracker.sql

@@ -251,7 +251,7 @@ create table extract_filetype_lkup
 	extract_filetype_id serial not null
 		constraint extract_filetype_lkup_pk
 			primary key,
-	extract_filetype_code varchar(5) not null,
+	extract_filetype_code varchar(25) not null,
 	extract_filetype varchar(75) not null,
 	delimiter_char char,
 	quote_char char,

process_tracker/models/extract.py

@@ -74,7 +74,7 @@ class ExtractFileType(Base):
         primary_key=True,
         nullable=False,
     )
-    extract_filetype_code = Column(String(5), nullable=False)
+    extract_filetype_code = Column(String(25), nullable=False)
     extract_filetype = Column(String(75), nullable=False, unique=True)
     delimiter_char = Column(String(1), nullable=True)
     quote_char = Column(String(1), nullable=True)

process_tracker/process_tracker.py

@@ -79,6 +79,7 @@ def __init__(
         ProcessTracker is the primary engine for tracking data integration processes.
         :param process_name: Name of the process being tracked.
         :param process_run_name: Optional name of the process run.
+        :param process_type: Type of process the process_name is.  Optional if process already exists.
         :param actor_name: Name of the person or environment runnning the process.
         :param tool_name: Name of the tool used to run the process.
         :param sources: A single source name or list of source names for the given process. If source_objects is set,
@@ -164,17 +165,15 @@ def __init__(
                 self.logger.error(error_msg)
                 raise Exception(error_msg)
         else:
-            if process_name is None or process_type is None:
-                error_msg = "process_name and process_type must be set."
+            if process_name is None is None:
+                error_msg = "process_name must be set."
                 self.logger.error(error_msg)
                 raise Exception(error_msg)
 
             self.actor = self.data_store.get_or_create_item(
                 model=Actor, actor_name=actor_name
             )
-            self.process_type = self.data_store.get_or_create_item(
-                model=ProcessType, process_type_name=process_type
-            )
+
             self.tool = self.data_store.get_or_create_item(
                 model=Tool, tool_name=tool_name
             )
@@ -188,13 +187,27 @@ def __init__(
                     model=ScheduleFrequency, schedule_frequency_name=schedule_frequency
                 )
 
-            self.process = self.data_store.get_or_create_item(
-                model=Process,
-                process_name=process_name,
-                process_type_id=self.process_type.process_type_id,
-                process_tool_id=self.tool.tool_id,
-                schedule_frequency_id=self.schedule_frequency.schedule_frequency_id,
-            )
+            if process_type is None:
+
+                self.process = self.data_store.get_or_create_item(
+                    model=Process, process_name=process_name, create=False
+                )
+
+                self.process_type = self.process.process_type
+
+            else:
+
+                self.process_type = self.data_store.get_or_create_item(
+                    model=ProcessType, process_type_name=process_type
+                )
+
+                self.process = self.data_store.get_or_create_item(
+                    model=Process,
+                    process_name=process_name,
+                    process_type_id=self.process_type.process_type_id,
+                    process_tool_id=self.tool.tool_id,
+                    schedule_frequency_id=self.schedule_frequency.schedule_frequency_id,
+                )
 
             # Dataset types should be loaded before source and target because they are also used there.
 

tests/test_process_tracker.py

@@ -2292,7 +2292,7 @@ def test_determine_process_targets(self):
     def test_ensure_nulls_caught_on_instantiation(self):
         """
         With the adding of the ability of have a process_tracking_id we have to allow for nulled values for process_name
-        and process_type.  If ProcessTracker is instantiated with either (or both) being null, an exception should be
+        .  If ProcessTracker is instantiated with process_name being null, an exception should be
         raised.
         :return:
         """
@@ -2301,6 +2301,20 @@ def test_ensure_nulls_caught_on_instantiation(self):
 
             ProcessTracker()
 
-        return self.assertTrue(
-            "process_name and process_type must be set." in str(context.exception)
+        return self.assertTrue("process_name must be set." in str(context.exception))
+
+    def test_ensure_process_type_returned_with_given_process_name(self):
+        """Ensuring that if just the process name is passed, the process type will be retrieved for that given process"""
+
+        self.process_tracker.change_run_status("completed")
+
+        test_process = ProcessTracker(
+            process_name="Testing Process Tracking Initialization",
+            actor_name="UnitTesting",
+            tool_name="Spark",
         )
+
+        given_result = test_process.process_type.process_type_name
+        expected_result = "Extract"
+
+        return self.assertEqual(expected_result, given_result)