From efdb10e3c4ddb741a4b5b474d052ec8649ba8efc Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Henrik=20tom=20W=C3=B6rden?= <h.tomwoerden@indiscale.com>
Date: Wed, 31 Jan 2024 18:48:47 +0100
Subject: [PATCH] ENH: allow wildcard is_referenced_by
---
CHANGELOG.md | 2 ++
src/caoscrawler/identifiable_adapters.py | 19 ++++++++++++-------
2 files changed, 14 insertions(+), 7 deletions(-)
diff --git a/CHANGELOG.md b/CHANGELOG.md
index 8eeed54f..ff413461 100644
--- a/CHANGELOG.md
+++ b/CHANGELOG.md
@@ -10,6 +10,8 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
### Added ###
* 'transform' sections can be added to a CFood to apply functions to values stored in variables.
* default transform functions: submatch, split and replace.
+* `*` can now be used as a wildcard in the identifiables parameter file to denote
+ that any Record may reference the identified one.
### Changed ###
- If the `parents` key is used in a cfood at a lower level for a Record that
diff --git a/src/caoscrawler/identifiable_adapters.py b/src/caoscrawler/identifiable_adapters.py
index d9c9c00b..d0dfd752 100644
--- a/src/caoscrawler/identifiable_adapters.py
+++ b/src/caoscrawler/identifiable_adapters.py
@@ -219,18 +219,23 @@ identifiabel, identifiable and identified record) for a Record.
# separate class too
if prop.name.lower() == "is_referenced_by":
for givenrt in prop.value:
- rt_and_children = get_children_of_rt(givenrt)
found = False
- for rtname in rt_and_children:
- if (id(record) in referencing_entities
- and rtname in referencing_entities[id(record)]):
- identifiable_backrefs.extend(
- referencing_entities[id(record)][rtname])
+ if givenrt == "*":
+ for rt, rec in referencing_entities[id(record)].items():
+ identifiable_backrefs.extend(rec)
found = True
+ else:
+ rt_and_children = get_children_of_rt(givenrt)
+ for rtname in rt_and_children:
+ if (id(record) in referencing_entities
+ and (rtname in referencing_entities[id(record)])):
+ identifiable_backrefs.extend(
+ referencing_entities[id(record)][rtname])
+ found = True
if not found:
# TODO: is this the appropriate error?
raise NotImplementedError(
- f"The following record is missing an identifying property:"
+ f"The following record is missing an identifying property:\n"
f"RECORD\n{record}\nIdentifying PROPERTY\n{prop.name}"
)
continue
--
GitLab