-
Notifications
You must be signed in to change notification settings - Fork 87
Commit
This commit does not belong to any branch on this repository, and may belong to a fork outside of the repository.
awards: added subjects and orgs, updated mappings
- Loading branch information
1 parent
b61f971
commit 83b7979
Showing
11 changed files
with
777 additions
and
72 deletions.
There are no files selected for viewing
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| Original file line number | Diff line number | Diff line change |
|---|---|---|
| @@ -0,0 +1,68 @@ | ||
| # -*- coding: utf-8 -*- | ||
| # | ||
| # Copyright (C) 2024 CERN. | ||
| # | ||
| # Invenio-RDM-Records is free software; you can redistribute it and/or modify | ||
| # it under the terms of the MIT License; see LICENSE file for more details. | ||
|
|
||
| """Search dumpers for subject hierarchy support.""" | ||
|
|
||
| from invenio_records.dumpers import SearchDumperExt | ||
|
|
||
|
|
||
| class SubjectHierarchyDumperExt(SearchDumperExt): | ||
| """Search dumper extension for subject hierarchy support. | ||
| It parses the values of the `subjects` field in the document, builds hierarchical | ||
| parent notations, and adds entries to the `hierarchy` field for each subject in award. | ||
| This dumper needs to be placed after the RelationDumper for subjects as it relies | ||
| on dereferenced subjects with scheme, subject, and props. | ||
| """ | ||
|
|
||
| def __init__(self, splitchar=","): | ||
| """Constructor. | ||
| :param splitchar: string to use to combine subject ids in hierarchy | ||
| """ | ||
| super().__init__() | ||
| self._splitchar = splitchar | ||
|
|
||
| def dump(self, record, data): | ||
| """Dump the data to secondary storage (OpenSearch-like).""" | ||
| awards = data.get("metadata", {}).get("funding", []) | ||
|
|
||
| def build_hierarchy(parents_str, current_subject_id): | ||
| """Build the hierarchy by progressively combining parent notations.""" | ||
| parents = parents_str.split(self._splitchar) # Split the parent notations | ||
| hierarchy = [] | ||
| current_hierarchy = parents[0] # Start with the top-level parent | ||
|
|
||
| hierarchy.append(current_hierarchy) | ||
| for parent in parents[1:]: | ||
| current_hierarchy = f"{current_hierarchy}{self._splitchar}{parent}" | ||
| hierarchy.append(current_hierarchy) | ||
|
|
||
| hierarchy.append( | ||
| f"{current_hierarchy}{self._splitchar}{current_subject_id}" | ||
| ) | ||
| return hierarchy | ||
|
|
||
| for award in awards: | ||
| subjects = award.get("award", {}).get("subjects", []) | ||
| for subject in subjects: | ||
| parents = subject.get("props", {}).get("parents", "") | ||
| current_subject_id = subject.get("id", "") | ||
| if parents and current_subject_id: | ||
| subject_hierarchy = build_hierarchy(parents, current_subject_id) | ||
| subject.setdefault("props", {})["hierarchy"] = subject_hierarchy | ||
|
|
||
| data["metadata"] = data.get("metadata", {}) | ||
|
|
||
| def load(self, data, record_cls): | ||
| """Load the data from secondary storage (OpenSearch-like). | ||
| This is run against the parent too (for some reason), so presence of any | ||
| field cannot be assumed. | ||
| """ | ||
| pass |
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Oops, something went wrong.