invenio-vocabularies 4.4.0__py2.py3-none-any.whl → 5.0.0__py2.py3-none-any.whl

invenio_vocabularies/contrib/funders/mappings/os-v2/funders/funder-v2.0.0.json

@@ -0,0 +1,140 @@
+{
+  "settings": {
+    "analysis": {
+      "char_filter": {
+        "strip_special_chars": {
+          "type": "pattern_replace",
+          "pattern": "[\\p{Punct}\\p{S}]",
+          "replacement": ""
+        }
+      },
+      "analyzer": {
+        "accent_edge_analyzer": {
+          "tokenizer": "standard",
+          "type": "custom",
+          "char_filter": ["strip_special_chars"],
+          "filter": [
+            "lowercase",
+            "asciifolding",
+            "edgegrams"
+          ]
+        },
+        "accent_analyzer": {
+          "tokenizer": "standard",
+          "type": "custom",
+          "char_filter": ["strip_special_chars"],
+          "filter": [
+            "lowercase",
+            "asciifolding"
+          ]
+        }
+      },
+      "filter": {
+        "lowercase": {
+          "type": "lowercase",
+          "preserve_original": true
+        },
+        "asciifolding": {
+          "type": "asciifolding",
+          "preserve_original": true
+        },
+        "edgegrams": {
+          "type": "edge_ngram",
+          "min_gram": 2,
+          "max_gram": 20
+        }
+      }
+    }
+  },
+  "mappings": {
+    "dynamic_templates": [
+      {
+        "i18n_title": {
+          "path_match": "title.*",
+          "match_mapping_type": "string",
+          "mapping": {
+            "type": "text",
+            "analyzer": "accent_edge_analyzer",
+            "search_analyzer": "accent_analyzer"
+          }
+        }
+      }
+    ],
+    "dynamic": "strict",
+    "properties": {
+      "$schema": {
+        "type": "keyword",
+        "index": "false"
+      },
+      "created": {
+        "type": "date"
+      },
+      "updated": {
+        "type": "date"
+      },
+      "indexed_at": {
+        "type": "date"
+      },
+      "uuid": {
+        "type": "keyword"
+      },
+      "version_id": {
+        "type": "integer"
+      },
+      "identifiers": {
+        "properties": {
+          "identifier": {
+            "type": "keyword"
+          },
+          "scheme": {
+            "type": "keyword"
+          }
+        }
+      },
+      "name_sort": {
+        "type": "keyword"
+      },
+      "name": {
+        "type": "text",
+        "analyzer": "accent_edge_analyzer",
+        "search_analyzer": "accent_analyzer",
+        "copy_to": "name_sort"
+      },
+      "country": {
+        "type": "text"
+      },
+      "country_name": {
+        "type": "text"
+      },
+      "location_name": {
+        "type": "text"
+      },
+      "acronym": {
+        "type": "text",
+        "analyzer": "accent_edge_analyzer",
+        "search_analyzer": "accent_analyzer"
+      },
+      "status": {
+        "type": "keyword"
+      },
+      "aliases": {
+        "type": "text",
+        "analyzer": "accent_edge_analyzer",
+        "search_analyzer": "accent_analyzer"
+      },
+      "types": {
+        "type": "keyword"
+      },
+      "id": {
+        "type": "keyword"
+      },
+      "title": {
+        "type": "object",
+        "dynamic": "true"
+      },
+      "tags": {
+        "type": "keyword"
+      }
+    }
+  }
+}

invenio_vocabularies/contrib/names/config.py

@@ -28,12 +28,14 @@ class NamesSearchOptions(SearchOptions):
 
     suggest_parser_cls = SuggestQueryParser.factory(
         fields=[
-            "name^100",
-            "family_name^100",
             "given_name^100",
+            "name^70",
+            "family_name^50",
             "identifiers.identifier^20",
-            "affiliations.name^10",
+            "affiliations.name^20",
         ],
+        type="most_fields",  # https://www.elastic.co/guide/en/elasticsearch/reference/current/query-dsl-multi-match-query.html#multi-match-types
+        fuzziness="AUTO",
     )
 
     sort_default = "bestmatch"

invenio_vocabularies/contrib/names/mappings/os-v1/names/name-v2.0.0.json

@@ -0,0 +1,150 @@
+{
+  "settings": {
+    "analysis": {
+      "char_filter": {
+        "strip_special_chars": {
+          "type": "pattern_replace",
+          "pattern": "[\\p{Punct}\\p{S}]",
+          "replacement": ""
+        }
+      },
+      "analyzer": {
+        "accent_edge_analyzer": {
+          "tokenizer": "standard",
+          "type": "custom",
+          "char_filter": ["strip_special_chars"],
+          "filter": [
+            "lowercase",
+            "asciifolding",
+            "edgegrams"
+          ]
+        },
+        "accent_analyzer": {
+          "tokenizer": "standard",
+          "type": "custom",
+          "char_filter": ["strip_special_chars"],
+          "filter": [
+            "lowercase",
+            "asciifolding"
+          ]
+        }
+      },
+      "normalizer": {
+        "accent_normalizer": {
+          "type": "custom",
+          "char_filter": ["strip_special_chars"],
+          "filter": [
+            "lowercase",
+            "asciifolding"
+          ]
+        }
+      },
+      "filter": {
+        "lowercase": {
+          "type": "lowercase",
+          "preserve_original": true
+        },
+        "asciifolding": {
+          "type": "asciifolding",
+          "preserve_original": true
+        },
+        "edgegrams": {
+          "type": "edge_ngram",
+          "min_gram": 2,
+          "max_gram": 20
+        }
+      }
+    }
+  },
+  "mappings": {
+    "dynamic": "strict",
+    "properties": {
+      "$schema": {
+        "type": "keyword",
+        "index": "false"
+      },
+      "created": {
+        "type": "date"
+      },
+      "updated": {
+        "type": "date"
+      },
+      "indexed_at": {
+        "type": "date"
+      },
+      "uuid": {
+        "type": "keyword"
+      },
+      "version_id": {
+        "type": "integer"
+      },
+      "id": {
+        "type": "keyword"
+      },
+      "tags": {
+        "type": "keyword"
+      },
+      "name_sort": {
+        "type": "keyword"
+      },
+      "name": {
+        "type": "text",
+        "analyzer": "accent_edge_analyzer",
+        "search_analyzer": "accent_analyzer",
+        "copy_to": "name_sort"
+      },
+      "given_name": {
+        "type": "text",
+        "analyzer": "accent_edge_analyzer",
+        "search_analyzer": "accent_analyzer"
+      },
+      "family_name": {
+        "type": "text"
+      },
+      "identifiers": {
+        "properties": {
+          "identifier": {
+            "type": "keyword",
+            "normalizer": "accent_normalizer"
+          },
+          "scheme": {
+            "type": "keyword"
+          }
+        }
+      },
+      "affiliations": {
+        "type": "object",
+        "properties": {
+          "@v": {
+            "type": "keyword"
+          },
+          "id": {
+            "type": "keyword"
+          },
+          "name": {
+            "type": "text",
+            "analyzer": "accent_edge_analyzer",
+            "search_analyzer": "accent_analyzer"
+          }
+        }
+      },
+      "pid": {
+        "type": "object",
+        "properties": {
+          "pk": {
+            "type": "integer"
+          },
+          "pid_type": {
+            "type": "keyword"
+          },
+          "obj_type": {
+            "type": "keyword"
+          },
+          "status": {
+            "type": "keyword"
+          }
+        }
+      }
+    }
+  }
+}

invenio_vocabularies/contrib/names/mappings/os-v2/names/name-v2.0.0.json

@@ -0,0 +1,150 @@
+{
+  "settings": {
+    "analysis": {
+      "char_filter": {
+        "strip_special_chars": {
+          "type": "pattern_replace",
+          "pattern": "[\\p{Punct}\\p{S}]",
+          "replacement": ""
+        }
+      },
+      "analyzer": {
+        "accent_edge_analyzer": {
+          "tokenizer": "standard",
+          "type": "custom",
+          "char_filter": ["strip_special_chars"],
+          "filter": [
+            "lowercase",
+            "asciifolding",
+            "edgegrams"
+          ]
+        },
+        "accent_analyzer": {
+          "tokenizer": "standard",
+          "type": "custom",
+          "char_filter": ["strip_special_chars"],
+          "filter": [
+            "lowercase",
+            "asciifolding"
+          ]
+        }
+      },
+      "normalizer": {
+        "accent_normalizer": {
+          "type": "custom",
+          "char_filter": ["strip_special_chars"],
+          "filter": [
+            "lowercase",
+            "asciifolding"
+          ]
+        }
+      },
+      "filter": {
+        "lowercase": {
+          "type": "lowercase",
+          "preserve_original": true
+        },
+        "asciifolding": {
+          "type": "asciifolding",
+          "preserve_original": true
+        },
+        "edgegrams": {
+          "type": "edge_ngram",
+          "min_gram": 2,
+          "max_gram": 20
+        }
+      }
+    }
+  },
+  "mappings": {
+    "dynamic": "strict",
+    "properties": {
+      "$schema": {
+        "type": "keyword",
+        "index": "false"
+      },
+      "created": {
+        "type": "date"
+      },
+      "updated": {
+        "type": "date"
+      },
+      "indexed_at": {
+        "type": "date"
+      },
+      "uuid": {
+        "type": "keyword"
+      },
+      "version_id": {
+        "type": "integer"
+      },
+      "id": {
+        "type": "keyword"
+      },
+      "tags": {
+        "type": "keyword"
+      },
+      "name_sort": {
+        "type": "keyword"
+      },
+      "name": {
+        "type": "text",
+        "analyzer": "accent_edge_analyzer",
+        "search_analyzer": "accent_analyzer",
+        "copy_to": "name_sort"
+      },
+      "given_name": {
+        "type": "text",
+        "analyzer": "accent_edge_analyzer",
+        "search_analyzer": "accent_analyzer"
+      },
+      "family_name": {
+        "type": "text"
+      },
+      "identifiers": {
+        "properties": {
+          "identifier": {
+            "type": "keyword",
+            "normalizer": "accent_normalizer"
+          },
+          "scheme": {
+            "type": "keyword"
+          }
+        }
+      },
+      "affiliations": {
+        "type": "object",
+        "properties": {
+          "@v": {
+            "type": "keyword"
+          },
+          "id": {
+            "type": "keyword"
+          },
+          "name": {
+            "type": "text",
+            "analyzer": "accent_edge_analyzer",
+            "search_analyzer": "accent_analyzer"
+          }
+        }
+      },
+      "pid": {
+        "type": "object",
+        "properties": {
+          "pk": {
+            "type": "integer"
+          },
+          "pid_type": {
+            "type": "keyword"
+          },
+          "obj_type": {
+            "type": "keyword"
+          },
+          "status": {
+            "type": "keyword"
+          }
+        }
+      }
+    }
+  }
+}

invenio_vocabularies/contrib/names/names.py

@@ -49,6 +49,7 @@ record_type = RecordTypeFactory(
     },
     schema_version="1.0.0",
     schema_path="local://names/name-v1.0.0.json",
+    index_name="names-name-v2.0.0",
     record_relations=name_relations,
     record_dumper=SearchDumper(
         model_fields={"pid": ("id", str)},

invenio_vocabularies/contrib/subjects/config.py

@@ -2,6 +2,7 @@
 #
 # Copyright (C) 2021 CERN.
 # Copyright (C) 2021 Northwestern University.
+# Copyright (C) 2024 University of Münster.
 #
 # Invenio-Vocabularies is free software; you can redistribute it and/or
 # modify it under the terms of the MIT License; see LICENSE file for more
@@ -9,13 +10,19 @@
 
 """Subjects configuration."""
 
+from flask import current_app
 from invenio_i18n import lazy_gettext as _
 from invenio_records_resources.services import SearchOptions
 from invenio_records_resources.services.records.components import DataComponent
+from werkzeug.local import LocalProxy
 
 from ...services.components import PIDComponent
 from ...services.querystr import FilteredSuggestQueryParser
 
+subject_schemes = LocalProxy(
+    lambda: current_app.config["VOCABULARIES_SUBJECTS_SCHEMES"]
+)
+
 
 class SubjectsSearchOptions(SearchOptions):
     """Search options."""
@@ -23,9 +30,8 @@ class SubjectsSearchOptions(SearchOptions):
     suggest_parser_cls = FilteredSuggestQueryParser.factory(
         filter_field="scheme",
         fields=[  # suggest fields
-            "subject^100",
-            "subject._2gram",
-            "subject._3gram",
+            "title.*^100",
+            "synonyms^20",
         ],
     )
 

invenio_vocabularies/contrib/subjects/datastreams.py

@@ -0,0 +1,55 @@
+# -*- coding: utf-8 -*-
+#
+# Copyright (C) 2024 University of Münster.
+#
+# Invenio-Vocabularies is free software; you can redistribute it and/or
+# modify it under the terms of the MIT License; see LICENSE file for more
+# details.
+
+"""Names datastreams, transformers, writers and readers."""
+
+from invenio_access.permissions import system_identity
+from invenio_i18n import lazy_gettext as _
+
+from ...datastreams.writers import ServiceWriter
+from .mesh.datastreams import VOCABULARIES_DATASTREAM_READERS as mesh_readers
+from .mesh.datastreams import VOCABULARIES_DATASTREAM_TRANSFORMERS as mesh_transformers
+from .mesh.datastreams import VOCABULARIES_DATASTREAM_WRITERS as mesh_writers
+
+
+class SubjectsServiceWriter(ServiceWriter):
+    """Subjects Service Writer."""
+
+    def __init__(self, *args, **kwargs):
+        """Constructor."""
+        service_or_name = kwargs.pop("service_or_name", "subjects")
+        super().__init__(service_or_name=service_or_name, *args, **kwargs)
+
+    def _entry_id(self, entry):
+        """Get the id from an entry."""
+        return entry["id"]
+
+
+VOCABULARIES_DATASTREAM_READERS = {**mesh_readers}
+"""Subjects Data Streams readers."""
+
+VOCABULARIES_DATASTREAM_TRANSFORMERS = {**mesh_transformers}
+"""Subjects Data Streams transformers."""
+
+VOCABULARIES_DATASTREAM_WRITERS = {
+    "subjects-service": SubjectsServiceWriter,
+    **mesh_writers,
+}
+"""Subjects Data Streams writers."""
+
+DATASTREAM_CONFIG = {
+    "readers": [
+        {"type": "yaml"},
+    ],
+    "writers": [
+        {
+            "type": "subjects-service",
+        }
+    ],
+}
+"""Data Stream configuration."""

invenio_vocabularies/contrib/subjects/jsonschemas/subjects/subject-v1.0.0.json

@@ -25,6 +25,18 @@
     "subject": {
       "description": "Human readable label.",
       "type": "string"
+    },
+    "title": {
+      "description": "Human readable label in different languages.",
+      "$ref": "local://vocabularies/definitions-v1.0.0.json#/title"
+    },
+    "synonyms": {
+      "description": "Synonyms of the subject label.",
+      "type": "array",
+      "items": {
+        "type": "string"
+      },
+      "uniqueItems": true
     }
   }
 }

invenio_vocabularies/contrib/subjects/mappings/os-v1/subjects/subject-v1.0.0.json

@@ -1,5 +1,16 @@
 {
   "mappings": {
+    "dynamic_templates": [
+      {
+        "i18n_title": {
+          "path_match": "title.*",
+          "match_mapping_type": "string",
+          "mapping": {
+            "type": "search_as_you_type"
+          }
+        }
+      }
+    ],
     "dynamic": "strict",
     "properties": {
       "$schema": {
@@ -56,6 +67,13 @@
           }
         }
       },
+      "title": {
+        "type": "object",
+        "dynamic": "true"
+      },
+      "synonyms": {
+        "type": "text"
+      },
       "tags": {
         "type": "keyword"
       }

invenio_vocabularies/contrib/subjects/mappings/os-v2/subjects/subject-v1.0.0.json

@@ -1,5 +1,16 @@
 {
   "mappings": {
+    "dynamic_templates": [
+      {
+        "i18n_title": {
+          "path_match": "title.*",
+          "match_mapping_type": "string",
+          "mapping": {
+            "type": "search_as_you_type"
+          }
+        }
+      }
+    ],
     "dynamic": "strict",
     "properties": {
       "$schema": {
@@ -56,6 +67,13 @@
           }
         }
       },
+      "title": {
+        "type": "object",
+        "dynamic": "true"
+      },
+      "synonyms": {
+        "type": "text"
+      },
       "tags": {
         "type": "keyword"
       }

invenio_vocabularies/contrib/subjects/mappings/v7/subjects/subject-v1.0.0.json

@@ -1,5 +1,16 @@
 {
   "mappings": {
+    "dynamic_templates": [
+      {
+        "i18n_title": {
+          "path_match": "title.*",
+          "match_mapping_type": "string",
+          "mapping": {
+            "type": "search_as_you_type"
+          }
+        }
+      }
+    ],
     "dynamic": "strict",
     "properties": {
       "$schema": {
@@ -56,6 +67,13 @@
           }
         }
       },
+      "title": {
+        "type": "object",
+        "dynamic": "true"
+      },
+      "synonyms": {
+        "type": "text"
+      },
       "tags": {
         "type": "keyword"
       }