Resource type eguide

cds_migrator_kit/rdm/records/transform/config.py

@@ -8,14 +8,15 @@
 """CDS-RDM transform config module."""
 
 # filters out PIDs which we don't migrate
-PIDS_SCHEMES_TO_DROP = ["HAL"]
+PIDS_SCHEMES_TO_DROP = []
 # validates allowed schemes
 PIDS_SCHEMES_ALLOWED = ["DOI"]
 
 # stores the identifiers found in PIDs field in the alternative identifiers instead
 PID_SCHEMES_TO_STORE_IN_IDENTIFIERS = [
     "ARXIV",
     "HDL",
+    "HAL"
     "HANDLE",
     "URN",
     "INIS",
@@ -25,7 +26,6 @@
 
 IDENTIFIERS_SCHEMES_TO_DROP = [
     "SPIRES",
-    "HAL",
     "OSTI",
     "SLAC",
     "PROQUEST",

cds_migrator_kit/rdm/records/transform/models/hr.py

@@ -35,6 +35,7 @@ class HrModel(CdsOverdo):
         "100__m",
         "300__a",  # number of pages
         "591__b",  #
+        "6531_9",  # keyword scheme
         "700__m",
         "7870_r",  # detailed description of record relation (2862345)
         "8564_8",

cds_migrator_kit/rdm/records/transform/xml_processing/rules/base.py

@@ -350,19 +350,20 @@ def identifiers(self, key, value):
     https://github.com/CERNDocumentServer/cds-migrator-kit/issues/21
     """
     id_value = StringValue(value.get("a", "")).parse()
-    scheme = StringValue(value.get("9", "")).parse()
+    original_scheme = StringValue(value.get("9", "")).parse()
+    scheme = original_scheme.lower()
     related_works = self.get("related_identifiers", [])
-    if scheme.upper() in IDENTIFIERS_SCHEMES_TO_DROP:
+    if original_scheme.upper() in IDENTIFIERS_SCHEMES_TO_DROP:
         raise IgnoreKey("identifiers")
     # drop oai harvest info
     if id_value.startswith("oai:inspirehep.net"):
         raise IgnoreKey("identifiers")
-    if scheme.lower() == "arxiv":
+    if scheme == "arxiv":
         id_value = id_value.replace("oai:arXiv.org:", "arXiv:")
-    if scheme.lower() == "cern annual report":
+    if scheme == "cern annual report":
         additional_descriptions = self.get("additional_descriptions", [])
         new_desc = {
-            "description": f"{scheme} {id_value}",
+            "description": f"{original_scheme} {id_value}",
             "type": {"id": "series-information"},
         }
         additional_descriptions.append(new_desc)
@@ -377,34 +378,36 @@ def identifiers(self, key, value):
         self["related_identifiers"] = related_works
         raise IgnoreKey("identifiers")
 
-    is_aleph_number = scheme.lower() == "cercer" or not scheme and "CERCER" in id_value
+    is_aleph_number = scheme == "cercer" or not scheme and "CERCER" in id_value
+
     if is_aleph_number:
         scheme = "aleph"
-    if scheme.lower() == "cds":
+    elif scheme == "cds":
         scheme = "cds"
-    if scheme.lower() == "inspire":
+    elif scheme == "inspire":
         validate_inspire_identifier(id_value, key)
 
-    rel_id = {"scheme": scheme.lower(), "identifier": id_value}
-    if scheme.lower() == "admbul":
-        legacy_scheme = scheme
+    rel_id = {"scheme": scheme, "identifier": id_value}
+
+    if scheme == "admbul":
         scheme = "other"
-        rel_id = {"scheme": scheme, "identifier": f"{legacy_scheme}_{id_value}"}
-    if scheme.lower() == "agendamaker":
+        rel_id = {"scheme": scheme, "identifier": f"{original_scheme}_{id_value}"}
+    if scheme == "agendamaker":
         indico_id = get_new_indico_id(id_value)
         scheme = "indico"
         rel_id = {"scheme": scheme, "identifier": str(indico_id)}
-    if scheme.lower() == "zentralblatt math":
+    if scheme == "zentralblatt math":
         scheme = "url"
         rel_id = {
             "scheme": scheme,
             "identifier": f"https://zbmath.org/?q=an:{id_value}",
         }
+
     if id_value:
         if rel_id["scheme"] in RDM_RECORDS_RELATED_IDENTIFIERS_SCHEMES:
             rel_id.update(
                 {
-                    "relation_type": {"id": "isreferencedby"},
+                    "relation_type": {"id": "isvariantformof"},
                     "resource_type": {"id": "publication-other"},
                 }
             )
@@ -459,7 +462,7 @@ def _pids(self, key, value):
         else:
             new_id.update(
                 {
-                    "relation_type": {"id": "isversionof"},
+                    "relation_type": {"id": "isvariantformof"},
                     "resource_type": {"id": qualifier},
                 }
             )
@@ -779,6 +782,10 @@ def related_identifiers_787(self, key, value):
         recid = recid.replace("https://cds.cern.ch/record/", "")
 
     relation_map = {
+        "periodical": {
+            "relation_type": {"id": "ispublishedin"},
+            "resource_type": {"id": "publication-periodical"},
+        },
         "issue": {
             "relation_type": {"id": "ispublishedin"},
             "resource_type": {"id": "publication-periodicalissue"},

cds_migrator_kit/rdm/records/transform/xml_processing/rules/hr.py

@@ -74,10 +74,11 @@ def additional_desc(self, key, value):
     raise IgnoreKey("additional_descriptions_hr")
 
 
-@model.over("subjects", "(^6931_)|(^650[12_][7_])|(^653[12_]_)|(^695__)|(^694__)")
+@model.over("subjects", "(^6931_)|(^650[12_][7_])|(^653[12_]_)|(^695__)|(^694__)", override=True)
 @require(["a"])
 @for_each_value
 def hr_subjects(self, key, value):
+    keyword = value.get("a")
     if key == "6531_":
         keyword = value.get("a")
         if "," in keyword:
@@ -87,14 +88,17 @@ def hr_subjects(self, key, value):
                 _subjects.append({"subject": key})
             self["subjects"] = _subjects
             raise IgnoreKey("subjects")
-        else:
-            resource_type_map = {
-                "Presentation": {"id": "presentation"},
-            }
-            resource_type = resource_type_map.get(keyword)
-            if resource_type:
-                self["resource_type"] = resource_type
-            raise IgnoreKey("subjects")
+
+    resource_type_map = {
+        "Presentation": {"id": "presentation"},
+        "Mémos": {"id": "publication-memorandum"},
+        "Formulaires": {"id": "publication-form"},
+        "Form": {"id": "publication-form"},
+        "Modèles de documents": {"id": "publication-doctemplate"},
+    }
+    resource_type = resource_type_map.get(keyword)
+    if resource_type:
+        self["resource_type"] = resource_type
 
     subjects(self, key, value)
 
@@ -153,6 +157,8 @@ def resource_type(self, key, value):
         self["subjects"] = subjects
     if value == "administrativenote":
         raise IgnoreKey("resource_type")
+    if value == "cern-admin-e-guide" and self["resource_type"]:
+        raise IgnoreKey("resource_type")
     map = {
         "annualstats": {"id": "publication-report"},
         "cern-admin-e-guide": {"id": "publication-other"},

cds_migrator_kit/rdm/records/transform/xml_processing/rules/publications.py

@@ -45,15 +45,15 @@ def isbn(self, key, value):
             new_id = {
                 "identifier": _isbn,
                 "scheme": "isbn",
-                "relation_type": {"id": "isversionof"},
+                "relation_type": {"id": "isvariantformof"},
                 "resource_type": {"id": "publication-book"},
             }
         else:
             destination = "related_identifiers"
             new_id = {
                 "identifier": _isbn,
                 "scheme": "isbn",
-                "relation_type": {"id": "isversionof"},
+                "relation_type": {"id": "isvariantformof"},
                 "resource_type": {"id": "publication-book"},
             }
         ids = self.get(destination, [])

tests/cds-rdm/conftest.py

@@ -1472,6 +1472,16 @@ def relation_type_v(app, relation_type):
         },
     )
 
+    vocab = vocabulary_service.create(
+        system_identity,
+        {
+            "id": "isvariantformof",
+            "props": {"datacite": "Is variant form of"},
+            "title": {"en": "Is variant form of"},
+            "type": "relationtypes",
+        },
+    )
+
     Vocabulary.index.refresh()
 
     return vocab

tests/cds-rdm/test_thesis_migration.py

@@ -1,3 +1,3 @@
 # -*- coding: utf-8 -*-
 #
 # Copyright (C) 2025 CERN.
@@ -96,7 +96,7 @@
         {
             "identifier": "978-3-030-90375-6",
             "scheme": "isbn",
-            "relation_type": {"id": "isversionof", "title": {"en": "Is version of"}},
+            "relation_type": {"id": "isvariantformof", "title": {"en": "Is variant form of"}},
             "resource_type": {
                 "id": "publication-book",
                 "title": {
@@ -108,7 +108,7 @@
         {
             "identifier": "978-3-030-90376-3",
             "scheme": "isbn",
-            "relation_type": {"id": "isversionof", "title": {"en": "Is version of"}},
+            "relation_type": {"id": "isvariantformof", "title": {"en": "Is variant form of"}},
             "resource_type": {
                 "id": "publication-book",
                 "title": {
@@ -121,7 +121,7 @@
         {
             "identifier": "10.1007/978-3-030-90376-3",
             "scheme": "doi",
-            "relation_type": {"id": "isversionof", "title": {"en": "Is version of"}},
+            "relation_type": {"id": "isvariantformof", "title": {"en": "Is variant form of"}},
             "resource_type": {
                 "id": "publication",
                 "title": {"en": "Publication", "de": "Publikation"},
@@ -130,8 +130,8 @@
         {
             "identifier": "1807850",
             "relation_type": {
-                "id": "isreferencedby",
-                "title": {"de": "Wird referenziert von", "en": "Is referenced by"},
+                "id": "isvariantformof",
+                "title": {"en": "Is variant form of"},
             },
             "resource_type": {
                 "id": "publication-other",