Use cached_get_entity_by

Summary

Replace Crawler._get_entity_by... by cached versions of pylib.

Please track on https://gitlab.indiscale.com/caosdb/customers/umg/management/-/issues/84

Test Environment

unit and int tests

Check List for the Author

Please, prepare your MR for a review. Be sure to write a summary and a focus and create gitlab comments for the reviewer. They should guide the reviewer through the changes, explain your changes and also point out open questions. For further good practices have a look at our review guidelines

• All automated tests pass
• Reference related issues
• Up-to-date CHANGELOG.md (or not necessary) no api change; internal refactoring
• Up-to-date JSON schema (or not necessary)
• Appropriate user and developer documentation (or not necessary)
  • How do I use the software? Assume "stupid" users.
  • How do I develop or debug the software? Assume novice developers.
• Annotations in code (Gitlab comments)
  • Intent of new code
  • Problems with old code
  • Why this implementation?

Check List for the Reviewer

• I understand the intent of this MR
• All automated tests pass
• Up-to-date CHANGELOG.md (or not necessary)
• Appropriate user and developer documentation (or not necessary)
• The test environment setup works and the intended behavior is reproducible in the test environment
• In-code documentation and comments are up-to-date.
• Check: Are there specifications? Are they satisfied?

For further good practices have a look at our review guidelines.

src/caoscrawler/crawl.py

@@ -38,6 +38,7 @@ import logging
 import os
 import sys
 import uuid
+from caosdb.cached import cached_get_entity_by
 import warnings
 import yaml
 
@@ -573,7 +574,7 @@ class Crawler(object):
                     del flat[i]
                 # 2. Can it be identified via a path?
                 elif record.path is not None:
-                    existing = self._get_entity_by_path(record.path)
+                    existing = cached_get_entity_by(path=record.path)
                     if existing is None:
                         to_be_inserted.append(record)
                         self.add_to_remote_missing_cache(record, identifiable)
@@ -728,7 +729,7 @@ class Crawler(object):
         parent_updates = db.Container()
 
         for entity in to_be_updated:
-            old_entity = Crawler._get_entity_by_id(entity.id)
+            old_entity = cached_get_entity_by(id=entity.id)
 
             # Check whether the parents have been changed and add them if missing
             # in the old entity:
@@ -757,28 +758,13 @@ class Crawler(object):
                             "mode. This might lead to a failure of inserts that follow.")
                 logger.info(parent_updates)
 
-    @staticmethod
-    def _get_entity_by_name(name):
-        return db.Entity(name=name).retrieve()
-
-    @staticmethod
-    def _get_entity_by_path(path):
-        try:
-            return db.execute_query(f"FIND FILE WHICH IS STORED AT '{path}'", unique=True)
-        except db.exceptions.EmptyUniqueQueryError:
-            return None
-
-    @staticmethod
-    def _get_entity_by_id(id):
-        return db.Entity(id=id).retrieve()
-
     @staticmethod
     def execute_inserts_in_list(to_be_inserted, securityMode,
                                 run_id: Optional[uuid.UUID] = None,
                                 unique_names=True):
         for record in to_be_inserted:
             for prop in record.properties:
-                entity = Crawler._get_entity_by_name(prop.name)
+                entity = cached_get_entity_by(name=prop.name)
                 _resolve_datatype(prop, entity)
         logger.debug("INSERT")
         logger.debug(to_be_inserted)
@@ -794,10 +780,10 @@ class Crawler(object):
         for record in rec_list:
             for parent in record.parents:
                 if parent.id is None:
-                    parent.id = Crawler._get_entity_by_name(parent.name).id
+                    parent.id = cached_get_entity_by(name=parent.name).id
             for prop in record.properties:
                 if prop.id is None:
-                    entity = Crawler._get_entity_by_name(prop.name)
+                    entity = cached_get_entity_by(name=prop.name)
                     prop.id = entity.id
                     _resolve_datatype(prop, entity)