handle oecd fos classification

commonmeta/__init__.py

@@ -10,7 +10,7 @@
 """
 
 __title__ = "commonmeta-py"
-__version__ = "0.32"
+__version__ = "0.33"
 __author__ = "Martin Fenner"
 __license__ = "MIT"
 

commonmeta/crossref_utils.py

@@ -112,9 +112,11 @@ def insert_group_title(metadata, xml):
  """Insert group title"""
  if metadata.subjects is None or len(metadata.subjects) == 0:
  return xml
- etree.SubElement(xml, "group_title").text = metadata.subjects[0].get(
- "subject", None
- )
+ group_title = metadata.subjects[0].get("subject", None)
+ # strip optional FOS (Field of Science) prefix
+ if group_title.startswith("FOS: "):
+ group_title = group_title[5:]
+ etree.SubElement(xml, "group_title").text = group_title
  return xml
 
 

commonmeta/readers/json_feed_reader.py

@@ -114,7 +114,10 @@ def read_json_feed_item(data: Optional[dict], **kwargs) -> Commonmeta:
  if category is not None:
  subjects = [name_to_fos(py_.human_case(category))]
  else:
- subjects = None
+ subjects = []
+ tags = wrap(py_.get(meta, "tags", None))
+ if tags is not None:
+ subjects += wrap([format_subject(i) for i in tags])
  references = get_references(wrap(meta.get("reference", None)))
  funding_references = get_funding_references(meta)
  relations = get_relations(wrap(meta.get("relationships", None)))
@@ -414,13 +417,10 @@ def get_json_feed_blog_slug(id: str):
  return py_.get(post, "blog.slug", None)
 
 
-def get_json_feed_blog_slug(id: str):
- """get JSON Feed item by id and return blog slug"""
- if id is None:
+def format_subject(subject: str) -> Optional[dict]:
+ """format subject"""
+ if subject is None or not isinstance(subject, str):
  return None
- url = f"https://api.rogue-scholar.org/posts/#{id}"
- response = httpx.get(url, timeout=10)
- if response.status_code != 200:
- return None
- post = response.json()
- return py_.get(post, "blog.slug", None)
+ return {
+ "subject": subject,
+ }

commonmeta/utils.py

@@ -77,6 +77,57 @@
 HTTP_SCHEME = "http://"
 HTTPS_SCHEME = "https://"
 
+FOS_MAPPINGS = {
+ "Natural sciences": "http://www.oecd.org/science/inno/38235147.pdf?1",
+ "Mathematics": "http://www.oecd.org/science/inno/38235147.pdf?1.1",
+ "Computer and information sciences": "http://www.oecd.org/science/inno/38235147.pdf?1.2",
+ "Physical sciences": "http://www.oecd.org/science/inno/38235147.pdf?1.3",
+ "Chemical sciences": "http://www.oecd.org/science/inno/38235147.pdf?1.4",
+ "Earth and related environmental sciences": "http://www.oecd.org/science/inno/38235147.pdf?1.5",
+ "Biological sciences": "http://www.oecd.org/science/inno/38235147.pdf?1.6",
+ "Other natural sciences": "http://www.oecd.org/science/inno/38235147.pdf?1.7",
+ "Engineering and technology": "http://www.oecd.org/science/inno/38235147.pdf?2",
+ "Civil engineering": "http://www.oecd.org/science/inno/38235147.pdf?2.1",
+ "Electrical engineering, electronic engineering, information engineering": "http://www.oecd.org/science/inno/38235147.pdf?2.2",
+ "Mechanical engineering": "http://www.oecd.org/science/inno/38235147.pdf?2.3",
+ "Chemical engineering": "http://www.oecd.org/science/inno/38235147.pdf?2.4",
+ "Materials engineering": "http://www.oecd.org/science/inno/38235147.pdf?2.5",
+ "Medical engineering": "http://www.oecd.org/science/inno/38235147.pdf?2.6",
+ "Environmental engineering": "http://www.oecd.org/science/inno/38235147.pdf?2.7",
+ "Environmental biotechnology": "http://www.oecd.org/science/inno/38235147.pdf?2.8",
+ "Industrial biotechnology": "http://www.oecd.org/science/inno/38235147.pdf?2.9",
+ "Nano technology": "http://www.oecd.org/science/inno/38235147.pdf?2.10",
+ "Other engineering and technologies": "http://www.oecd.org/science/inno/38235147.pdf?2.11",
+ "Medical and health sciences": "http://www.oecd.org/science/inno/38235147.pdf?3",
+ "Basic medicine": "http://www.oecd.org/science/inno/38235147.pdf?3.1",
+ "Clinical medicine": "http://www.oecd.org/science/inno/38235147.pdf?3.2",
+ "Health sciences": "http://www.oecd.org/science/inno/38235147.pdf?3.3",
+ "Health biotechnology": "http://www.oecd.org/science/inno/38235147.pdf?3.4",
+ "Other medical sciences": "http://www.oecd.org/science/inno/38235147.pdf?3.5",
+ "Agricultural sciences": "http://www.oecd.org/science/inno/38235147.pdf?4",
+ "Agriculture, forestry, and fisheries": "http://www.oecd.org/science/inno/38235147.pdf?4.1",
+ "Animal and dairy science": "http://www.oecd.org/science/inno/38235147",
+ "Veterinary science": "http://www.oecd.org/science/inno/38235147",
+ "Agricultural biotechnology": "http://www.oecd.org/science/inno/38235147",
+ "Other agricultural sciences": "http://www.oecd.org/science/inno/38235147",
+ "Social science": "http://www.oecd.org/science/inno/38235147.pdf?5",
+ "Psychology": "http://www.oecd.org/science/inno/38235147.pdf?5.1",
+ "Economics and business": "http://www.oecd.org/science/inno/38235147.pdf?5.2",
+ "Educational sciences": "http://www.oecd.org/science/inno/38235147.pdf?5.3",
+ "Sociology": "http://www.oecd.org/science/inno/38235147.pdf?5.4",
+ "Law": "http://www.oecd.org/science/inno/38235147.pdf?5.5",
+ "Political science": "http://www.oecd.org/science/inno/38235147.pdf?5.6",
+ "Social and economic geography": "http://www.oecd.org/science/inno/38235147.pdf?5.7",
+ "Media and communications": "http://www.oecd.org/science/inno/38235147.pdf?5.8",
+ "Other social sciences": "http://www.oecd.org/science/inno/38235147.pdf?5.9",
+ "Humanities": "http://www.oecd.org/science/inno/38235147.pdf?6",
+ "History and archaeology": "http://www.oecd.org/science/inno/38235147.pdf?6.1",
+ "Languages and literature": "http://www.oecd.org/science/inno/38235147.pdf?6.2",
+ "Philosophy, ethics and religion": "http://www.oecd.org/science/inno/38235147.pdf?6.3",
+ "Arts (arts, history of arts, performing arts, music)": "http://www.oecd.org/science/inno/38235147.pdf?6.4",
+ "Other humanities": "http://www.oecd.org/science/inno/38235147.pdf?6.5",
+}
+
 
 def normalize_id(pid: Optional[str], **kwargs) -> Optional[str]:
  """Check for valid DOI or HTTP(S) URL"""
@@ -982,45 +1033,12 @@ def subjects_as_string(subjects):
 
 def name_to_fos(name: str) -> Optional[dict]:
  """Convert name to Fields of Science (OECD) subject"""
- # # first find subject in Fields of Science (OECD)
- # fos = JSON.load(File.read(File.expand_path('../../resources/oecd/fos-mappings.json',
- # __dir__))).fetch('fosFields')
-
- # subject = fos.find { |l| l['fosLabel'] == name || 'FOS: ' + l['fosLabel'] == name }
-
- # if subject
- # return [{
- # 'subject': sanitize(name).downcase
- # },
- # {
- # 'subject': 'FOS: ' + subject['fosLabel'],
- # 'subjectScheme': 'Fields of Science and Technology (FOS)',
- # 'schemeUri': 'http://www.oecd.org/science/inno/38235147.pdf'
- # }]
- # end
 
- # # if not found, look in Fields of Research (Australian and New Zealand Standard Research Classification)
- # # and map to Fields of Science. Add an extra entry for the latter
- # fores = JSON.load(File.read(File.expand_path('../../resources/oecd/for-mappings.json',
- # __dir__)))
- # for_fields = fores.fetch('forFields')
- # for_disciplines = fores.fetch('forDisciplines')
-
- # subject = for_fields.find { |l| l['forLabel'] == name } ||
- # for_disciplines.find { |l| l['forLabel'] == name }
-
- # if subject
- # [{
- # 'subject': sanitize(name).downcase
- # },
- # {
- # 'subject': 'FOS: ' + subject['fosLabel'],
- # 'subjectScheme': 'Fields of Science and Technology (FOS)',
- # 'schemeUri': 'http://www.oecd.org/science/inno/38235147.pdf'
- # }]
- # else
-
- return {"subject": name.strip()}
+ subject = name.strip()
+ fos_subject = FOS_MAPPINGS.get(name, None)
+ if fos_subject is not None:
+ return {"subject": f"FOS: {subject}"}
+ return {"subject": subject}
 
 
 def encode_doi(prefix):
@@ -1112,10 +1130,10 @@ def id_from_url(url: Optional[str]) -> Optional[str]:
  """Return a ID from a URL"""
  if url is None:
  return None
- 
+
  f = furl(url)
  # check for allowed scheme if string is a URL
  if f.host is not None and f.scheme not in ["http", "https", "ftp"]:
  return None
- 
+
  return str(f.path).strip("/")

commonmeta/writers/inveniordm_writer.py

@@ -3,11 +3,11 @@
 import orjson as json
 from typing import Optional
 
-from ..base_utils import compact, wrap, parse_attributes
+from ..base_utils import compact, wrap, parse_attributes, presence
 from ..date_utils import get_iso8601_date
 from ..doi_utils import doi_from_url
 from ..constants import CM_TO_INVENIORDM_TRANSLATIONS, INVENIORDM_IDENTIFIER_TYPES
-from ..utils import get_language, validate_orcid, id_from_url
+from ..utils import get_language, validate_orcid, id_from_url, FOS_MAPPINGS
 
 
 def write_inveniordm(metadata):
@@ -73,7 +73,7 @@ def write_inveniordm(metadata):
  "type": {"id": "updated"},
  }
  ],
- "subjects": subjects,
+ "subjects": presence(subjects),
  "description": parse_attributes(
  metadata.descriptions, content="description", first=True
  ),
@@ -133,12 +133,22 @@ def format_identifier(id):
  )
 
 
-def to_inveniordm_subject(subject: dict) -> dict:
- """Convert subjects to inveniordm subjects"""
+def to_inveniordm_subject(sub: dict) -> Optional[dict]:
+ """Convert subject to inveniordm subject"""
+ if sub.get("subject", None) is None:
+ return None
+ if sub.get("subject").startswith("FOS: "):
+ subject = sub.get("subject")[5:]
+ id_ = FOS_MAPPINGS.get(subject, None)
+ return compact(
+ {
+ "id": id_,
+ "subject": subject,
+ }
+ )
  return compact(
  {
- "id": subject.get("id", None),
- "subject": subject.get("subject", None),
+ "subject": sub.get("subject"),
  }
  )
 

pyproject.toml

@@ -1,6 +1,6 @@
 [tool.poetry]
 name="commonmeta-py"
-version="0.32"
+version="0.33"
 repository = "https:/front-matter/commonmeta-py"
 homepage = "https://python.commonmeta.org"
 documentation = "https://python.commonmeta.org"