From 5143f8b6b1ec39fea8da5df1afa743a576a057fd Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Henrik=20tom=20W=C3=B6rden?= <henrik@trineo.org>
Date: Mon, 3 Jun 2019 09:33:14 +0200
Subject: [PATCH] MAINT minor and comments
---
src/caosadvancedtools/cfood.py | 34 ++++++++++++++++++++++++++++------
1 file changed, 28 insertions(+), 6 deletions(-)
diff --git a/src/caosadvancedtools/cfood.py b/src/caosadvancedtools/cfood.py
index 05cf6f1c..617a8c7a 100644
--- a/src/caosadvancedtools/cfood.py
+++ b/src/caosadvancedtools/cfood.py
@@ -38,13 +38,24 @@ ENTITIES = {}
def get_value(prop):
+ """returns the value of a Property
+
+ If the value is an Entity itself, its id is returned instead
+ """
+
if not isinstance(prop.value, db.Entity):
return prop.value
else:
- return str(prop.value.id)
+ return prop.value.id
def get_entity(name):
+ """implements a mini cache of RecordTypes
+
+ If and only if a RecordType (identified by its name) is not in the
+ dictionary, it is retrieved from CaosDB.
+ """
+
if name not in ENTITIES:
ent = db.Entity(name=name)
ent.retrieve()
@@ -63,6 +74,9 @@ class AbstractCFood(object):
self.use_cache = use_cache
self.access = access
+ if self.use_cache:
+ self.identifiable_cache = Cache()
+
def treat_match(self, crawled_file, match):
print(crawled_file)
@@ -81,8 +95,9 @@ class AbstractCFood(object):
if self.use_cache:
identifiable_cache = Cache()
identifier = Cache.hash_entity(identifiable)
- print(identifier)
- cached_id = identifiable_cache.check_existing(identifier)
+ cached_id = self.identifiable_cache.check_existing(identifier)
+
+ # retrieve entity for the cached id
if cached_id is not None:
existing = db.execute_query("FIND {}".format(cached_id),
@@ -151,18 +166,25 @@ class AbstractCFood(object):
@staticmethod
def find_existing(entity):
+ """searches for an entity that matches the identifiable in CaosDB
+
+ Characteristics of the identifiable like, properties, name or id are
+ used for the match.
+ """
+
if entity.name is None:
+ # TODO multiple parents are ignored! Sufficient?
query_string = "FIND Record " + entity.get_parents()[0].name
- #import IPython
- # IPython.embed()
query_string += " with " + " and ".join(
["'" + p.name + "'='"
- + get_value(p) + "'" for p in entity.get_properties()])
+ + str(get_value(p)) + "'" for p in entity.get_properties()])
else:
query_string = "FIND '{}'".format(entity.name)
print(query_string)
q = db.Query(query_string)
+ # the identifiable should identify an object uniquely. Thus the query
+ # is using the unique keyword
try:
r = q.execute(unique=True)
except TransactionError as er:
--
GitLab