update schema to v0.14

front-matter · May 16, 2024 · affc22c · affc22c
1 parent 429c4df
commit affc22c
Show file tree

Hide file tree

Showing 19 changed files with 645 additions and 94 deletions.
diff --git a/commonmeta/crossref_utils.py b/commonmeta/crossref_utils.py
@@ -228,6 +228,8 @@ def insert_citation_list(metadata, xml):
 
     citation_list = etree.SubElement(xml, "citation_list")
     for ref in metadata.references:
+        if ref.get("id", None) is None:
+            continue
         citation = etree.SubElement(
             citation_list, "citation", {"key": ref.get("key", None)}
         )
@@ -245,10 +247,10 @@ def insert_citation_list(metadata, xml):
             etree.SubElement(citation, "cYear").text = ref.get("publicationYear")
         if ref.get("title", None) is not None:
             etree.SubElement(citation, "article_title").text = ref.get("title")
-        if ref.get("doi", None) is not None:
-            etree.SubElement(citation, "doi").text = doi_from_url(ref.get("doi"))
-        if ref.get("url", None) is not None:
-            etree.SubElement(citation, "unstructured_citation").text = ref.get("url")
+        if ref.get("id", None) is not None:
+            etree.SubElement(citation, "doi").text = doi_from_url(ref.get("id"))
+        if ref.get("unstructured", None) is not None:
+            etree.SubElement(citation, "unstructured_citation").text = ref.get("unstructured")
     return xml
 
 

diff --git a/commonmeta/readers/crossref_xml_reader.py b/commonmeta/readers/crossref_xml_reader.py
@@ -392,15 +392,12 @@ def crossref_reference(reference: Optional[dict]) -> Optional[dict]:
     doi = parse_attributes(reference.get("doi", None))
     unstructured = reference.get("unstructured_citation", None)
     if isinstance(unstructured, dict):
-        url = unstructured.get("u", None)
         text = unstructured.get("font", None) or unstructured.get("#text", None)
     else:
-        url = reference.get("url", None)
         text = reference.get("unstructured_citation", None)
     metadata = {
         "key": reference.get("key", None),
-        "doi": normalize_doi(doi) if doi else None,
-        "url": normalize_url(url) if url else None,
+        "id": normalize_doi(doi) if doi else None,
         "contributor": reference.get("author", None),
         "title": reference.get("article_title", None),
         "publisher": reference.get("publisher", None),
@@ -411,7 +408,7 @@ def crossref_reference(reference: Optional[dict]) -> Optional[dict]:
         "lastPage": reference.get("last_page", None),
         "containerTitle": reference.get("journal_title", None),
         "edition": None,
-        "unstructured": sanitize(text) if text and doi is None else None,
+        "unstructured": sanitize(text) if text else None,
     }
     return compact(metadata)
 

diff --git a/commonmeta/readers/csl_reader.py b/commonmeta/readers/csl_reader.py
@@ -70,7 +70,7 @@ def read_csl(data: dict, **kwargs) -> Commonmeta:
         descriptions = [
             {
                 "description": sanitize(str(meta.get("abstract"))),
-                "descriptionType": "Abstract",
+                "type": "Abstract",
             }
         ]
     else:

diff --git a/commonmeta/readers/datacite_xml_reader.py b/commonmeta/readers/datacite_xml_reader.py
@@ -93,7 +93,7 @@ def format_subject(subject):
                 {
                     "subject": subject.get("#text", None),
                     "subjectScheme": subject.get("subjectScheme", None),
-                    "lang": subject.get("xml:lang", None),
+                    "language": subject.get("xml:lang", None),
                 }
             )
         return None

diff --git a/commonmeta/readers/inveniordm_reader.py b/commonmeta/readers/inveniordm_reader.py
@@ -127,9 +127,9 @@ def map_reference(reference):
         identifier = reference.get("relatedIdentifier", None)
         identifier_type = reference.get("relatedIdentifierType", None)
         if identifier and identifier_type == "DOI":
-            reference["doi"] = normalize_doi(identifier)
+            reference["id"] = normalize_doi(identifier)
         elif identifier and identifier_type == "URL":
-            reference["url"] = normalize_url(identifier)
+            reference["id"] = normalize_url(identifier)
         reference = py_.omit(
             reference,
             [

diff --git a/commonmeta/readers/json_feed_reader.py b/commonmeta/readers/json_feed_reader.py
@@ -102,7 +102,7 @@ def read_json_feed_item(data: Optional[dict], **kwargs) -> Commonmeta:
     description = meta.get("summary", None)
     if description is not None:
         descriptions = [
-            {"description": sanitize(description), "descriptionType": "Abstract"}
+            {"description": sanitize(description), "type": "Abstract"}
         ]
     else:
         descriptions = None
@@ -165,13 +165,12 @@ def get_reference(reference: dict) -> Optional[dict]:
             return None
         try:
             if reference.get("doi", None) and validate_doi(reference.get("doi")):
-                doi = normalize_doi(reference.get("doi"))
+                id_ = normalize_doi(reference.get("doi"))
                 return compact(
                     {
-                        "doi": doi,
+                        "id": id_,
                         "title": reference.get("title", None),
                         "publicationYear": reference.get("publicationYear", None),
-                        "url": reference.get("url", None),
                     }
                 )
 
@@ -185,7 +184,7 @@ def get_reference(reference: dict) -> Optional[dict]:
                 if response.status_code in [404]:
                     return None
                 return {
-                    "url": reference.get("url"),
+                    "id": reference.get("url"),
                 }
         except Exception as error:
             print(error)