From d365acf5153f635af01429507b006326be66013e Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Henrik=20tom=20W=C3=B6rden?= <h.tomwoerden@indiscale.com>
Date: Tue, 4 Aug 2020 09:12:07 +0000
Subject: [PATCH] ENH: properly treat lists of references
---
src/caosadvancedtools/crawler.py | 41 +++++++++++++++++++---------
unittests/test_crawler.py | 47 ++++++++++++++++++++++++++++++++
2 files changed, 75 insertions(+), 13 deletions(-)
create mode 100644 unittests/test_crawler.py
diff --git a/src/caosadvancedtools/crawler.py b/src/caosadvancedtools/crawler.py
index 7e69ed33..fa6fa5ad 100644
--- a/src/caosadvancedtools/crawler.py
+++ b/src/caosadvancedtools/crawler.py
@@ -541,6 +541,33 @@ carefully and if the changes are ok, click on the following link:
logger.debug("Retrieving entities from CaosDB...")
identifiables.retrieve(unique=True, raise_exception_on_error=False)
+ @staticmethod
+ def create_query_for_identifiable(ident):
+ """
+ uses the properties of ident to create a query that can determine
+ whether the required record already exists.
+ """
+ # TODO multiple parents are ignored! Sufficient?
+ if len(ident.get_parents()) == 0:
+ raise ValueError("The identifiable must have at least one parent.")
+ query_string = "FIND Record " + ident.get_parents()[0].name
+ query_string += " WITH "
+ if ident.name is not None:
+ query_string += "name='{}' AND".format(ident.name)
+
+ for p in ident.get_properties():
+ if p.datatype is not None and p.datatype.startswith("LIST<"):
+ for v in p.value:
+ query_string += ("references "
+ + str(v.id if isinstance(v, db.Entity)
+ else v)
+ + " AND ")
+ else:
+ query_string += ("'" + p.name + "'='" + str(get_value(p))
+ + "' AND ")
+ # remove the last AND
+ return query_string[:-4]
+
@staticmethod
def find_existing(entity):
"""searches for an entity that matches the identifiable in CaosDB
@@ -548,19 +575,7 @@ carefully and if the changes are ok, click on the following link:
Characteristics of the identifiable like, properties, name or id are
used for the match.
"""
-
- # TODO multiple parents are ignored! Sufficient?
- query_string = "FIND Record " + entity.get_parents()[0].name
- query_string += " WITH "
- if entity.name is not None:
- query_string += "name='{}' AND".format(entity.name)
-
- for p in entity.get_properties():
- query_string += ("'" + p.name + "'='" + str(get_value(p))
- + "' AND ")
- # remove the last AND
- query_string = query_string[:-4]
-
+ query_string = Crawler.create_query_for_identifiable(entity)
logger.debug(query_string)
q = db.Query(query_string)
# the identifiable should identify an object uniquely. Thus the query
diff --git a/unittests/test_crawler.py b/unittests/test_crawler.py
new file mode 100644
index 00000000..f603031e
--- /dev/null
+++ b/unittests/test_crawler.py
@@ -0,0 +1,47 @@
+#!/usr/bin/env python
+# encoding: utf-8
+#
+# This file is a part of the CaosDB Project.
+#
+# Copyright (C) 2020 Indiscale GmbH <info@indiscale.com>
+# Copyright (C) 2020 Henrik tom Wörden <h.tomwoerden@indiscale.com>
+#
+# This program is free software: you can redistribute it and/or modify
+# it under the terms of the GNU Affero General Public License as
+# published by the Free Software Foundation, either version 3 of the
+# License, or (at your option) any later version.
+#
+# This program is distributed in the hope that it will be useful,
+# but WITHOUT ANY WARRANTY; without even the implied warranty of
+# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+# GNU Affero General Public License for more details.
+#
+# You should have received a copy of the GNU Affero General Public License
+# along with this program. If not, see <https://www.gnu.org/licenses/>.
+#
+
+import re
+import unittest
+
+import caosdb as db
+from caosadvancedtools.crawler import Crawler
+
+
+class CrawlerTest(unittest.TestCase):
+ def test_ident_query(self):
+ ident = db.Record(name="coolrec")
+ self.assertRaises(ValueError, Crawler.create_query_for_identifiable,
+ ident)
+ ident.add_parent(name="RT")
+ qs = Crawler.create_query_for_identifiable(ident)
+ assert qs == "FIND Record RT WITH name='coolrec'"
+ ident.add_property(name="p", value=5)
+ qs = Crawler.create_query_for_identifiable(ident)
+ assert qs == "FIND Record RT WITH name='coolrec' AND'p'='5' "
+
+ ident = db.Record()
+ ident.add_parent(name="RT")
+ ident.add_property(name="p", value=[2345, db.Record(id=234567)],
+ datatype=db.LIST("RT2"))
+ qs = Crawler.create_query_for_identifiable(ident)
+ assert qs == "FIND Record RT WITH references 2345 AND references 234567 "
--
GitLab