add(ship): new models and transformation rules

cds_migrator_kit/rdm/migration_config.py

@@ -551,7 +551,7 @@ def resolve_record_pid(pid):
         "label": "EP approval",  # shown in UI buttons/headings
         "referee_group": "cds-ph-ep-publication",  # CERN e-group slug
         "report_number": {
-            "prefix": "CERN-TH-EP",  # literal prefix, e.g. "CERN-EP"
+            "prefix": "CERN-EP",  # literal prefix, e.g. "CERN-EP"
             "include_year": True,  # append the current year after prefix
             "counter_digits": 3,  # zero-padding width, e.g. 3 → "001"
         },
@@ -606,4 +606,14 @@ def resolve_record_pid(pid):
             "counter_digits": 3,
         },
     },
+    "7277793b-5fce-458a-a3c4-e05a6cc43c69": {
+        # ship
+        "label": "EP approval",  # shown in UI buttons/headings
+        "referee_group": "cds-ph-ep-publications-referee-non-lhc",  # CERN e-group slug
+        "report_number": {
+            "prefix": "CERN-EP",  # literal prefix, e.g. "CERN-EP"
+            "include_year": True,  # append the current year after prefix
+            "counter_digits": 3,  # zero-padding width, e.g. 3 → "001"
+        },
+    },
 }

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

@@ -15,10 +15,11 @@
     # "035__z",  # oai harvest tag
     "037__c",  # arxiv subject
     "100__m",  # email of contributor
-    # "245__9",  # Provenance of title
+    "245__9",  # Provenance of title
     # "270__m",  # Contact email
     "300__a",  # number of pages
-    # "520__9",  # Provenance of the description
+    "500__9",  # Provenance of the note
+    "520__9",  # Provenance of the description
     # "540__3",  # Material of the license
     # "540__9",  # Also material of the license
     # "542__3",  # Also material of the license

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

@@ -0,0 +1,49 @@
+# -*- coding: utf-8 -*-
+#
+# Copyright (C) 2026 CERN.
+#
+# CDS-RDM is free software; you can redistribute it and/or modify it under
+# the terms of the MIT License; see LICENSE file for more details.
+
+"""CDS-RDM SHIP research model."""
+
+from cds_migrator_kit.rdm.records.transform.models._config import IGNORE_SYSTEM_KEYS
+from cds_migrator_kit.rdm.records.transform.models.research import (
+    ResearchModel,
+    research_model,
+)
+
+
+class SHIPResearchModel(ResearchModel):
+    """Translation model for SHIP records."""
+
+    __query__ = (
+        "((980__.a:NOTE OR 980__.a:Note OR 980__.a:ConferencePaper) AND 690C_.a:SHiP) OR "
+        "980__.a:SHiPPUBDRAFTFINAL OR 980__.a:SHiP_Papers OR "
+        "(980__.a:INTNOTE AND 693__.e:SHiP) "
+        "-980__:DELETED -980__.a:DUMMY"
+    )
+
+    __ignore_keys__ = IGNORE_SYSTEM_KEYS | {
+        "100__v",  # complete affiliation
+        "0247_9",  # provenance of the DOI
+        "035__h",  # oai identifiers
+        "035__d",  # oai identifiers
+        "035__t",  # oai identifiers
+        "035__u",  # oai identifiers
+        "035__m",  # oai identifiers
+        "110__u",  # Confirmed with SIS
+        "270__m",  # document contact email
+        "540__3",  # material of license
+        "542__3",  # copyright material
+        "700__v",  # complete affiliation
+        "773__o",  # Duplicate meeting title
+        "8564_z",  # automatic process with EP value:Stamped by WebSubmit
+        "903__s",  # public
+    }
+
+
+ship_research_model = SHIPResearchModel(
+    bases=(research_model,),
+    entry_point_group="cds_migrator_kit.migrator.rdm.rules.ship",
+)

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

@@ -743,6 +743,7 @@ def resource_type(self, key, value):
         "slide": {"id": "presentation"},
         "faser_papers": {"id": "publication-article"},
         "demsuppliers": {"id": "other"},
+        "ship_papers": {"id": "publication-article"},
         "lhcf_papers": {"id": "publication-article"},
         "lhcf_proc": {"id": "publication-conferenceproceeding"},
         "lhcf_reports": {"id": "publication-report"},

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

@@ -0,0 +1,58 @@
+# -*- coding: utf-8 -*-
+#
+# Copyright (C) 2026 CERN.
+#
+# CDS-RDM is free software; you can redistribute it and/or modify it under
+# the terms of the MIT License; see LICENSE file for more details.
+
+"""CDS-RDM SHIP research rules."""
+
+from dojson.errors import IgnoreKey
+from dojson.utils import for_each_value
+
+from cds_migrator_kit.errors import UnexpectedValue
+from cds_migrator_kit.transform.xml_processing.quality.parsers import StringValue
+
+from ...models.ship import ship_research_model as model
+from .faser_publication import spokesperson
+
+model.over("request_reviewers", "(^905__|^906__)", override=True)(spokesperson)
+
+
+@model.over("document_type", "^594__")
+def document_type(self, key, value):
+    """Confirmed with SIS, we can ignore this since the record already has a resource type."""
+    document_type = value.get("a").strip().lower()
+    if document_type and document_type not in [
+        "int",
+        "conferencepaper",
+        "note",
+    ]:
+        raise UnexpectedValue(f"Invalid document type: {document_type}")
+    raise IgnoreKey("document_type")
+
+
+@model.over("related_identifiers", "(^78502|^78002)")
+@for_each_value
+def related_works(self, key, value):
+    """Translates related identifiers."""
+    description = StringValue(value.get("i")).parse().strip().lower()
+    recid = value.get("w")
+    report_number = value.get("r")
+    rel_ids = self.get("related_identifiers", [])
+    if "superseded by" == description:
+        relation_type = "isobsoletedby"
+    elif "supersedes" == description:
+        relation_type = "obsoletes"
+    else:
+        raise UnexpectedValue(f"Invalid relation type: {description}")
+    new_id = {
+        "identifier": recid,
+        "scheme": "cds",
+        "relation_type": {"id": relation_type},
+        "resource_type": {"id": "other"},
+    }
+    if new_id not in rel_ids:
+        return new_id
+
+    raise IgnoreKey("related_identifiers")

setup.cfg

@@ -78,6 +78,7 @@ cds_migrator_kit.migrator.models =
     lhcf = cds_migrator_kit.rdm.records.transform.models.lhcf:lhcf_model
     antares = cds_migrator_kit.rdm.records.transform.models.antares:antares_research_model
     lcd = cds_migrator_kit.rdm.records.transform.models.lcd:lcd_research_model
+    ship = cds_migrator_kit.rdm.records.transform.models.ship:ship_research_model
     research_comm_model = cds_migrator_kit.rdm.records.transform.models.research_committee:research_comm_model
     fap = cds_migrator_kit.rdm.records.transform.models.fap:fap_model
     ssn = cds_migrator_kit.rdm.records.transform.models.summer_student_report:sspn_model
@@ -126,6 +127,11 @@ cds_migrator_kit.migrator.rdm.rules.research =
     base = cds_migrator_kit.transform.xml_processing.rules.base
     base_records = cds_migrator_kit.rdm.records.transform.xml_processing.rules.base
     research = cds_migrator_kit.rdm.records.transform.xml_processing.rules.research
+cds_migrator_kit.migrator.rdm.rules.ship =
+    base = cds_migrator_kit.transform.xml_processing.rules.base
+    base_records = cds_migrator_kit.rdm.records.transform.xml_processing.rules.base
+    research = cds_migrator_kit.rdm.records.transform.xml_processing.rules.research
+    ship = cds_migrator_kit.rdm.records.transform.xml_processing.rules.ship
 cds_migrator_kit.migrator.rdm.rules.small_exp =
     base = cds_migrator_kit.transform.xml_processing.rules.base
     base_records = cds_migrator_kit.rdm.records.transform.xml_processing.rules.base