commonmeta-py 0.17.1__tar.gz → 0.17.3__tar.gz

{commonmeta_py-0.17.1 → commonmeta_py-0.17.3}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: commonmeta-py
-Version: 0.17.1
+Version: 0.17.3
 Summary: Library for conversions to/from the Commonmeta scholarly metadata format
 Home-page: https://python.commonmeta.org
 License: MIT

{commonmeta_py-0.17.1 → commonmeta_py-0.17.3}/commonmeta/author_utils.py

@@ -108,6 +108,9 @@ def get_one_author(author, **kwargs):
         else:
             given_name = None
             family_name = None
+  
+    # support various keys for affiliations
+    affiliations = author.get("affiliation", None) or author.get("affiliations", None)
 
     # return author in commonmeta format, using name vs. given/family name
     # depending on type
@@ -119,7 +122,7 @@ def get_one_author(author, **kwargs):
             "name": name if _type == "Organization" else None,
             "givenName": given_name if _type == "Person" else None,
             "familyName": family_name if _type == "Person" else None,
-            "affiliation": presence(get_affiliations(wrap(author.get("affiliation", None)))
+            "affiliations": presence(get_affiliations(wrap(affiliations))
             ),
         }
     )

{commonmeta_py-0.17.1 → commonmeta_py-0.17.3}/commonmeta/crossref_utils.py

@@ -131,8 +131,12 @@ def insert_crossref_contributors(metadata, xml):
     ]
     for num, contributor in enumerate(con):
         contributor_role = (
-            "author" if contributor.get("contributorRoles") == ["Author"] else "editor"
+            "author" if "Author" in contributor.get("contributorRoles") else None
         )
+        if contributor_role is None:
+            contributor_role = (
+                "editor" if "Editor" in contributor.get("contributorRoles") else None
+            )
         sequence = "first" if num == 0 else "additional"
         if (
             contributor.get("type", None) == "Organization"
@@ -153,7 +157,7 @@ def insert_crossref_contributors(metadata, xml):
                 {"contributor_role": contributor_role, "sequence": sequence},
             )
             person_name = insert_crossref_person(contributor, person_name)
-        elif contributor.get("affiliation", None) is not None:
+        elif contributor.get("affiliations", None) is not None:
             anonymous = etree.SubElement(
                 contributors,
                 "anonymous",
@@ -176,18 +180,17 @@ def insert_crossref_person(contributor, xml):
     if contributor.get("familyName", None) is not None:
         etree.SubElement(xml, "surname").text = contributor.get("familyName")
 
-    if contributor.get("affiliation", None) is not None:
+    if contributor.get("affiliations", None) is not None:
         affiliations = etree.SubElement(xml, "affiliations")
         institution = etree.SubElement(affiliations, "institution")
-        if py_.get(contributor, "affiliation.0.name") is not None:
+        if py_.get(contributor, "affiliations.0.name") is not None:
             etree.SubElement(institution, "institution_name").text = py_.get(
-                contributor, "affiliation.0.name"
+                contributor, "affiliations.0.name"
             )
-        if py_.get(contributor, "affiliation.0.id") is not None:
+        if py_.get(contributor, "affiliations.0.id") is not None:
             etree.SubElement(
                 institution, "institution_id", {"type": "ror"}
-            ).text = py_.get(contributor, "affiliation.0.id")
-
+            ).text = py_.get(contributor, "affiliations.0.id")
     orcid = normalize_orcid(contributor.get("id", None))
     if orcid is not None:
         etree.SubElement(xml, "ORCID").text = orcid
@@ -196,13 +199,13 @@ def insert_crossref_person(contributor, xml):
 
 def insert_crossref_anonymous(contributor, xml):
     """Insert crossref anonymous"""
-    if contributor.get("affiliation", None) is None:
+    if contributor.get("affiliations", None) is None:
         return xml
     affiliations = etree.SubElement(xml, "affiliations")
     institution = etree.SubElement(affiliations, "institution")
-    if py_.get(contributor, "affiliation.0.name") is not None:
+    if py_.get(contributor, "affiliations.0.name") is not None:
         etree.SubElement(institution, "institution_name").text = py_.get(
-            contributor, "affiliation.0.name"
+            contributor, "affiliations.0.name"
         )
     return xml
 

{commonmeta_py-0.17.1 → commonmeta_py-0.17.3}/commonmeta/readers/crossref_reader.py

@@ -65,6 +65,8 @@ def read_crossref(data: Optional[dict], **kwargs) -> Commonmeta:
     _id = doi_as_url(doi)
     _type = CR_TO_CM_TRANSLATIONS.get(meta.get("type", None)) or "Other"
 
+    archive_locations = wrap(meta.get("archive", None))
+    
     if meta.get("author", None):
         contributors = get_authors(wrap(meta.get("author")), via="crossref")
     else:
@@ -89,7 +91,15 @@ def read_crossref(data: Optional[dict], **kwargs) -> Commonmeta:
             or py_.get(meta, "created.date-time")
         }
     )
-
+    identifiers = []
+    identifiers.append(
+        compact(
+            {
+                "identifier": _id,
+                "identifierType": "DOI",
+            }
+        )
+    )
     license_ = meta.get("license", None)
     if license_ is not None:
         license_ = normalize_cc_url(license_[0].get("URL", None))
@@ -133,27 +143,26 @@ def read_crossref(data: Optional[dict], **kwargs) -> Commonmeta:
         "id": _id,
         "type": _type,
         # recommended and optional properties
-        "url": url,
+        "additionalType": None,
+        "archiveLocations": presence(archive_locations),
+        "container": presence(container),
         "contributors": presence(contributors),
-        "titles": presence(titles),
-        "publisher": presence(publisher),
         "date": presence(date),
-        "additionalType": None,
-        "subjects": presence(subjects),
+        "descriptions": presence(descriptions),
+        "files": presence(files),
+        "fundingReferences": presence(funding_references),
+        "geoLocations": None,
+        "identifiers": identifiers,
         "language": meta.get("language", None),
-        "identifiers": None,
-        "sizes": None,
-        "formats": None,
-        "version": meta.get("version", None),
         "license": license_,
-        "descriptions": descriptions,
-        "geoLocations": None,
-        "fundingReferences": presence(funding_references),
+        "provider": "Crossref",
+        "publisher": presence(publisher),
         "references": presence(references),
         "relations": presence(relations),
-        "files": presence(files),
-        "container": presence(container),
-        "provider": "Crossref",
+        "subjects": presence(subjects),
+        "titles": presence(titles),
+        "url": url,
+        "version": meta.get("version", None),
     } | read_options
 
 

{commonmeta_py-0.17.1 → commonmeta_py-0.17.3}/commonmeta/readers/datacite_reader.py

@@ -84,6 +84,15 @@ def read_datacite(data: dict, **kwargs) -> Commonmeta:
     files = [get_file(i) for i in wrap(meta.get("content_url"))]
     
     identifiers = get_identifiers(wrap(meta.get("alternateIdentifiers", None)))
+    identifiers.append(
+        compact(
+            {
+                "identifier": normalize_doi(_id),
+                "identifierType": "DOI",
+            }
+        )
+    )
+    
     references = get_references(
         wrap(meta.get("relatedItems", None) or meta.get("relatedIdentifiers", None))
     )
@@ -104,28 +113,26 @@ def read_datacite(data: dict, **kwargs) -> Commonmeta:
         # required properties
         "id": _id,
         "type": _type,
-        "doi": doi_from_url(_id),
-        "url": normalize_url(meta.get("url", None)),
-        "contributors": presence(contributors),
-        "titles": titles,
-        "publisher": publisher,
-        "date": compact(date),
         # recommended and optional properties
         "additionalType": additional_type,
-        "subjects": presence(subjects),
-        "language": meta.get("language", None),
+        "container": presence(container),
+        "contributors": presence(contributors),
+        "date": compact(date),
+        "descriptions": presence(descriptions),
+        "files": presence(files),
+        "fundingReferences": presence(meta.get("fundingReferences", None)),
+        "geoLocations": presence(geo_locations),
         "identifiers": presence(identifiers),
-        "version": meta.get("version", None),
+        "language": meta.get("language", None),
         "license": presence(license_),
-        "descriptions": descriptions,
-        "geoLocations": presence(geo_locations),
-        "fundingReferences": presence(meta.get("fundingReferences", None)),
+        "provider": "DataCite",
+        "publisher": publisher,
         "references": presence(references),
         "relations": presence(relations),
-        # other properties
-        "files": presence(files),
-        "container": presence(container),
-        "provider": "DataCite",
+        "subjects": presence(subjects),
+        "titles": presence(titles),
+        "url": normalize_url(meta.get("url", None)),
+        "version": meta.get("version", None),
     } | read_options
 
 
@@ -176,11 +183,16 @@ def get_references(references: list) -> list:
         """map_reference"""
         identifier = reference.get("relatedIdentifier", None)
         identifier_type = reference.get("relatedIdentifierType", None)
+        if identifier_type == "DOI":
+            id_ = normalize_doi(identifier)
+        elif identifier_type == "URL":
+            id_ = normalize_url(identifier)
+        else:
+            id_ = identifier
         return compact(
             {
                 "key": f"ref{index + 1}",
-                "doi": normalize_doi(identifier) if identifier_type == "DOI" else None,
-                "url": normalize_url(identifier) if identifier_type == "URL" else None,
+                "id": id_,
             }
         )
 
@@ -214,7 +226,8 @@ def get_relations(relations: list) -> list:
 
     def map_relation(relation):
         """map_relation"""
-        identifier = relation.get("relatedIdentifier", None)
+        
+        identifier = normalize_doi(relation.get("relatedIdentifier", None)) or relation.get("relatedIdentifier", None)
         relation_type = relation.get("relationType", None)
         return compact(
             {

{commonmeta_py-0.17.1 → commonmeta_py-0.17.3}/commonmeta/readers/datacite_xml_reader.py

@@ -35,16 +35,13 @@ def read_datacite_xml(data: dict, **kwargs) -> Commonmeta:
 
     doi = parse_attributes(meta.get("identifier", None))
     _id = doi_as_url(doi) if doi else None
-    #         identifiers = Array.wrap(meta.dig('alternateIdentifiers', 'alternateIdentifier')).map do |r|
-    #           if r['__content__'].present?
-    #             { 'identifierType' => get_identifier_type(r['alternateIdentifierType']),
-    #               'identifier' => r['__content__'] }
-    #           end
-    #         end.compact
 
     resource__typegeneral = py_.get(meta, "resourceType.resourceTypeGeneral")
     _type = DC_TO_CM_TRANSLATIONS.get(resource__typegeneral, "Other")
     additional_type = py_.get(meta, "resourceType.#text")
+    
+    identifiers = wrap(py_.get(meta, "alternateIdentifiers.alternateIdentifier"))
+    identifiers = get_xml_identifiers(identifiers)
 
     def format_title(title):
         """format_title"""
@@ -218,7 +215,7 @@ def read_datacite_xml(data: dict, **kwargs) -> Commonmeta:
         "additionalType": presence(additional_type),
         "subjects": presence(subjects),
         "language": meta.get("language", None),
-        "identifiers": presence(meta.get("alternateIdentifiers", None)),
+        "identifiers": identifiers,
         "version": meta.get("version", None),
         "license": presence(license_),
         "descriptions": presence(descriptions),
@@ -239,6 +236,43 @@ def read_datacite_xml(data: dict, **kwargs) -> Commonmeta:
     } | read_options
 
 
+def get_xml_identifiers(identifiers: list) -> list:
+    """get_identifiers"""
+    
+    def is_identifier(identifier):
+        """supported identifier types"""
+        return identifier.get("alternateIdentifierType", None) in [
+                "ARK",
+                "arXiv",
+                "Bibcode",
+                "DOI",
+                "Handle",
+                "ISBN",
+                "ISSN",
+                "PMID",
+                "PMCID",
+                "PURL",
+                "URL",
+                "URN",
+                "Other"
+            ]
+        
+    def format_identifier(identifier):
+        """format_identifier"""
+
+        if is_identifier(identifier):
+            type_ = identifier.get("alternateIdentifierType")
+        else:
+            type_ = "Other"
+            
+        return compact(
+            {
+                "identifier": identifier.get("#text", None),
+                "identifierType": type_,
+            }
+        )
+    return [format_identifier(i) for i in identifiers]
+    
 def get_xml_references(references: list) -> list:
     """get_xml_references"""
 

{commonmeta_py-0.17.1 → commonmeta_py-0.17.3}/commonmeta/resources/commonmeta_v0.13.json

@@ -248,7 +248,6 @@
               "$ref": "#/definitions/contributorRole"
             },
             "type": "array",
-            "minItems": 1,
             "uniqueItems": true
           }
         }
@@ -333,7 +332,6 @@
         },
         "required": ["url"]
       },
-      "minItems": 1,
       "uniqueItems": true
     },
     "fundingReferences": {

{commonmeta_py-0.17.1 → commonmeta_py-0.17.3}/commonmeta/writers/commonmeta_writer.py

@@ -27,6 +27,7 @@ def write_commonmeta(metadata):
         data,
         {
             "additional_type": "additionalType",
+            "archive_locations": "archiveLocations",
             "geo_locations": "geoLocations",
             "funding_references": "fundingReferences",
         },

{commonmeta_py-0.17.1 → commonmeta_py-0.17.3}/commonmeta/writers/datacite_writer.py

@@ -3,7 +3,7 @@ import orjson as json
 from typing import Optional, Union
 
 from ..base_utils import wrap, compact
-from ..doi_utils import doi_from_url
+from ..doi_utils import doi_from_url, normalize_doi
 from ..constants import (
     CM_TO_BIB_TRANSLATIONS,
     CM_TO_CSL_TRANSLATIONS,
@@ -19,6 +19,14 @@ def write_datacite(metadata: Commonmeta) -> Optional[Union[str, dict]]:
     """Write datacite. Make sure JSON Schema validates before writing"""
     if metadata.write_errors is not None:
         return "{}"
+    
+    alternate_identifiers = [
+        {
+            "alternateIdentifier": i.get("identifier", None),
+            "alternateIdentifierType": i.get("identifierType", None),
+        }
+        for i in wrap(metadata.identifiers) if i.get("id", None) != metadata.id
+    ]
 
     creators = [
         to_datacite_creator(i)
@@ -33,7 +41,7 @@ def write_datacite(metadata: Commonmeta) -> Optional[Union[str, dict]]:
     related_identifiers = [
         to_datacite_related_identifier(i)
         for i in wrap(metadata.references)
-        if i.get("doi", None) or i.get("url", None)
+        if i.get("id", None)
     ]
 
     resource__typegeneral = CM_TO_DC_TRANSLATIONS.get(metadata.type, "Other")
@@ -114,6 +122,7 @@ def write_datacite(metadata: Commonmeta) -> Optional[Union[str, dict]]:
             "dates": dates,
             "language": metadata.language,
             "types": types,
+            "alternateIdentifiers": alternate_identifiers,
             "relatedIdentifiers": related_identifiers,
             "version": metadata.version,
             "rightsList": license_,
@@ -151,7 +160,7 @@ def to_datacite_creator(creator: dict) -> dict:
             "familyName": creator.get("familyName", None),
             "nameType": _type + "al" if _type else None,
             "nameIdentifiers": name_identifiers,
-            "affiliation": creator.get("affiliation", None),
+            "affiliation": creator.get("affiliations", None),
         }
     )
 
@@ -170,8 +179,8 @@ def to_datacite_titles(titles: list) -> list:
 
 def to_datacite_related_identifier(reference: dict) -> dict:
     """Convert reference to datacite related_identifier"""
-    _id = reference.get("id", None)
-    url = reference.get("url", None)
+    _id = normalize_doi(reference.get("id", None))
+    url = reference.get("id", None)
     return compact(
         {
             "relatedIdentifier": _id if _id else url,

{commonmeta_py-0.17.1 → commonmeta_py-0.17.3}/pyproject.toml

@@ -1,6 +1,6 @@
 [tool.poetry]
 name="commonmeta-py"
-version="0.17.1"
+version="0.17.3"
 repository = "https://github.com/front-matter/commonmeta-py"
 homepage = "https://python.commonmeta.org"
 documentation = "https://python.commonmeta.org"

{commonmeta_py-0.17.1 → commonmeta_py-0.17.3}/commonmeta/metadata.py

@@ -80,26 +80,26 @@ class Metadata:
         self.id = meta.get("id")  # pylint: disable=C0103
         self.type = meta.get("type")
         # recommended and optional properties
-        self.url = meta.get("url")
+        self.additional_type = meta.get("additionalType")
+        self.archive_locations = meta.get("archiveLocations")
+        self.container = meta.get("container")
         self.contributors = meta.get("contributors")
-        self.titles = meta.get("titles")
-        self.publisher = meta.get("publisher")
         self.date = meta.get("date")
-        self.additional_type = meta.get("additionalType")
-        self.subjects = meta.get("subjects")
-        self.language = meta.get("language")
-        self.identifiers = meta.get("identifiers")
-        self.relations = meta.get("relations")
-        self.version = meta.get("version")
-        self.license = meta.get("license")
         self.descriptions = meta.get("descriptions")
-        self.geo_locations = meta.get("geoLocations")
-        self.funding_references = meta.get("fundingReferences")
-        self.references = meta.get("references")
         self.files = meta.get("files")
-        self.container = meta.get("container")
+        self.funding_references = meta.get("fundingReferences")
+        self.geo_locations = meta.get("geoLocations")
+        self.identifiers = meta.get("identifiers")
+        self.language = meta.get("language")
+        self.license = meta.get("license")
         self.provider = meta.get("provider")
-        self.archive_locations = meta.get("archiveLocations")
+        self.publisher = meta.get("publisher")
+        self.references = meta.get("references")
+        self.relations = meta.get("relations")
+        self.subjects = meta.get("subjects")
+        self.titles = meta.get("titles")
+        self.url = meta.get("url")
+        self.version = meta.get("version")
         # other properties
         self.date_created = meta.get("date_created")
         self.date_registered = meta.get("date_registered")