commonmeta-py 0.31__py3-none-any.whl → 0.33__py3-none-any.whl

commonmeta/__init__.py

@@ -10,7 +10,7 @@ commonmeta-py is a Python library to convert scholarly metadata
 """
 
 __title__ = "commonmeta-py"
-__version__ = "0.31"
+__version__ = "0.33"
 __author__ = "Martin Fenner"
 __license__ = "MIT"
 

commonmeta/constants.py

@@ -1,4 +1,5 @@
 """Constants for commonmeta-py"""
+
 from typing import Optional, TypedDict, List
 
 
@@ -585,3 +586,29 @@ COMMONMETA_CONTRIBUTOR_ROLES = [
     "Maintainer",
     "Other",
 ]
+
+INVENIORDM_IDENTIFIER_TYPES = {
+    "Ark": "ark",
+    "ArXiv": "arxiv",
+    "Bibcode": "ads",
+    "CrossrefFunderID": "crossreffunderid",
+    "DOI": "doi",
+    "EAN13": "ean13",
+    "EISSN": "eissn",
+    "GRID": "grid",
+    "Handle": "handle",
+    "IGSN": "igsn",
+    "ISBN": "isbn",
+    "ISNI": "isni",
+    "ISSN": "issn",
+    "ISTC": "istc",
+    "LISSN": "lissn",
+    "LSID": "lsid",
+    "PMID": "pmid",
+    "PURL": "purl",
+    "UPC": "upc",
+    "URL": "url",
+    "URN": "urn",
+    "W3ID": "w3id",
+    "Other": "other",
+}

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 @@ UNKNOWN_INFORMATION = {
 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):
@@ -1106,3 +1124,16 @@ def timer_func(func):
         return value
 
     return function_timer
+
+
+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

@@ -1,12 +1,13 @@
 """InvenioRDM writer for commonmeta-py"""
 
 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
-from ..utils import get_language, validate_orcid
+from ..constants import CM_TO_INVENIORDM_TRANSLATIONS, INVENIORDM_IDENTIFIER_TYPES
+from ..utils import get_language, validate_orcid, id_from_url, FOS_MAPPINGS
 
 
 def write_inveniordm(metadata):
@@ -22,7 +23,9 @@ def write_inveniordm(metadata):
     identifiers = [
         {
             "identifier": i.get("identifier", None),
-            "scheme": i.get("identifierType", None),
+            "scheme": INVENIORDM_IDENTIFIER_TYPES.get(
+                i.get("identifierType", None), "other"
+            ),
         }
         for i in wrap(metadata.identifiers)
         if i.get("id", None) != metadata.id
@@ -70,7 +73,7 @@ def write_inveniordm(metadata):
                             "type": {"id": "updated"},
                         }
                     ],
-                    "subjects": subjects,
+                    "subjects": presence(subjects),
                     "description": parse_attributes(
                         metadata.descriptions, content="description", first=True
                     ),
@@ -114,25 +117,57 @@ def to_inveniordm_creator(creator: dict) -> dict:
     elif creator.get("name", None):
         name = creator.get("name", None)
 
-    return {
-        "person_or_org": compact(
+    return compact(
+        {
+            "person_or_org": compact(
+                {
+                    "name": name,
+                    "given_name": creator.get("givenName", None),
+                    "family_name": creator.get("familyName", None),
+                    "type": _type.lower() + "al" if _type else None,
+                    "identifiers": format_identifier(creator.get("id", None)),
+                }
+            ),
+            "affiliations": to_inveniordm_affiliations(creator),
+        }
+    )
+
+
+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(
             {
-                "name": name,
-                "given_name": creator.get("givenName", None),
-                "family_name": creator.get("familyName", None),
-                "type": _type.lower() + "al" if _type else None,
-                "identifiers": format_identifier(creator.get("id", None)),
-                "affiliation": creator.get("affiliations", None),
+                "id": id_,
+                "subject": subject,
             }
         )
-    }
-
-
-def to_inveniordm_subject(subject: dict) -> dict:
-    """Convert subjects to inveniordm subjects"""
     return compact(
         {
-            "id": subject.get("id", None),
-            "subject": subject.get("subject", None),
+            "subject": sub.get("subject"),
         }
     )
+
+
+def to_inveniordm_affiliations(creator: dict) -> Optional[list]:
+    """Convert affiliations to inveniordm affiliations.
+    Returns None if creator is not a person."""
+
+    def format_affiliation(affiliation):
+        return compact(
+            {
+                "id": id_from_url(affiliation.get("id", None)),
+                "name": affiliation.get("name", None),
+            }
+        )
+
+    if creator.get("type", None) != "Person":
+        return None
+
+    return compact(
+        [format_affiliation(i) for i in wrap(creator.get("affiliations", None))]
+    )

{commonmeta_py-0.31.dist-info → commonmeta_py-0.33.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: commonmeta-py
-Version: 0.31
+Version: 0.33
 Summary: Library for conversions to/from the Commonmeta scholarly metadata format
 Home-page: https://python.commonmeta.org
 License: MIT

{commonmeta_py-0.31.dist-info → commonmeta_py-0.33.dist-info}/RECORD

@@ -1,10 +1,10 @@
-commonmeta/__init__.py,sha256=FFfOmC3JZbNBVQtBjbddrKFTgL3cPfQIpScMhdA3qZk,1779
+commonmeta/__init__.py,sha256=2iZDueWNzIzIbOQjnBw80FTSqsczN0N6HAFrBEDRI8Q,1779
 commonmeta/api_utils.py,sha256=-ZHGVZZhJqnjnsLtp4-PoeHYbDqL0cQme7W70BEjo4U,2677
 commonmeta/author_utils.py,sha256=zBIPTgP5n7Zx57xomJ2h7x0dvC0AV8gJ2gPoYeDy5Lo,8348
 commonmeta/base_utils.py,sha256=0t6fr9XGeeTBoMlKSAMI7p_EmKsA6wYRW0roEBXVcc8,3722
 commonmeta/cli.py,sha256=0IJF1SQ1sKPg7M0Gb8fpX2nBps-G0L13o01__M6c5Z0,6104
-commonmeta/constants.py,sha256=L9WeJL6e5G_PlSmmjYFBCILGfVeLlLrkujGBH-Yy-rA,15885
-commonmeta/crossref_utils.py,sha256=uffkjbs3732yCzD7hEA5lZ9ZZ648Mftl_n0GGcnEPHc,21918
+commonmeta/constants.py,sha256=fB2oMjnPYCJG3Zx6080u0R0ujmXkPRLGSgYOulWyOFw,16411
+commonmeta/crossref_utils.py,sha256=xyS8jFXO8unzumCC6YXK45kzz16PQAAOkWUHgjqawAo,22063
 commonmeta/date_utils.py,sha256=amF3E0ZJlh8yY5eY3aVXQyAO1x2WuZHJXw-ajOEcdUQ,5808
 commonmeta/doi_utils.py,sha256=Dt6K9ADD2ga2WNsOzfX9f29gnubhn7xqeKL7U5pEpBs,8209
 commonmeta/metadata.py,sha256=dqqk4IW-_OwtS_PVs0i7AuxrkNqOYjJCqhQJ2X-I1DQ,12398
@@ -19,7 +19,7 @@ commonmeta/readers/csl_reader.py,sha256=5V_sHSJwcAWJmhB8SYk199nB96BWYX1Sq9vkQ3iE
 commonmeta/readers/datacite_reader.py,sha256=CdOtxhthrakBoQMsLTdPx6sUCmqtEWo5ICYE6ZsWDdo,12026
 commonmeta/readers/datacite_xml_reader.py,sha256=nhnO92fZihr1HZlbXjyem-HJXc9_DWLgJ2zeltuPMIg,13041
 commonmeta/readers/inveniordm_reader.py,sha256=ejhpj4KX6bJU79lKrkTQeG3AATw0h2DdNdieNlx5j0w,7521
-commonmeta/readers/json_feed_reader.py,sha256=_rOAIGhBoEwmNbGGlYixEzVHhUszVNlzmwkjqFQY1kw,13946
+commonmeta/readers/json_feed_reader.py,sha256=YUJlZ7P44HEb-VKZHGr84ePGmHTVnfco_K36koooKnQ,13917
 commonmeta/readers/kbase_reader.py,sha256=NpIK-_fh5QFN4Q_ArqcrnH4tS5zR1gqbPew6VEjrUbs,6764
 commonmeta/readers/ris_reader.py,sha256=v6qOd-i2OcMTEFy5RGd3MlYthJcYSU6yzmZ5yHDzmII,3677
 commonmeta/readers/schema_org_reader.py,sha256=xyWzO2XAWlI2pYVl2EbVRsUmfiWXEwP64CHRBQNRN-M,16835
@@ -57,7 +57,7 @@ commonmeta/resources/styles/modern-language-association.csl,sha256=HI2iU4krze1aH
 commonmeta/resources/styles/vancouver.csl,sha256=lun3_i2oTilgsANk4LjFao2UDPQlGj_hgFgKAWC_DF8,12878
 commonmeta/schema_utils.py,sha256=Ep8suJgqtgDAvbjVkQxwzAY1MqwwqPwNRKDTMAxMQTg,915
 commonmeta/translators.py,sha256=RpGJtKNLjmz41VREZDY7KyyE2eXOi8j7m-da4jHmknI,1362
-commonmeta/utils.py,sha256=qJOEnjKbpLGPEhc2n_VGB0ifRohE_zWT1VtyUv8_OFY,39463
+commonmeta/utils.py,sha256=TjspdiI9g6WEcbvEiUOc6ARV7j_PHAdY2nRrEHrNXQs,42310
 commonmeta/writers/__init__.py,sha256=47-snms6xBHkoEXKYV1DBtH1npAtlVtvY29Z4Zr45qI,45
 commonmeta/writers/bibtex_writer.py,sha256=s3hIJIgWvSG7TAriZMRQEAyuitw6ebwWSI1YcYFQ-do,4971
 commonmeta/writers/citation_writer.py,sha256=RjaNh9EALxq6gfODLRWVJxGxPArGd6ZiHUlkYnCT6MA,2355
@@ -65,11 +65,11 @@ commonmeta/writers/commonmeta_writer.py,sha256=2qlttCfYpGhfVjrYkjzbIra7AywssRLT3
 commonmeta/writers/crossref_xml_writer.py,sha256=0Ds494RnXfdfjWw5CLX1kwV2zP7gqffdVqO-X74Uc6c,492
 commonmeta/writers/csl_writer.py,sha256=rlCeShkvC6ui9By0yVfNCMay_JfaZ4AooUPOPg-g-2M,2819
 commonmeta/writers/datacite_writer.py,sha256=G7Lr0aZ4sAEdbfXe3dG4Y6AyGUKA9UWr_iiaQRDnV24,6233
-commonmeta/writers/inveniordm_writer.py,sha256=rreqnyZOq-XE51SkmAWGYrQ6OaNvIYblcQVVUivcYyc,4725
+commonmeta/writers/inveniordm_writer.py,sha256=c4Z-s_fME_Kke4Wc5Hv2GhwxecxhOiThjHYSLpTONTs,5804
 commonmeta/writers/ris_writer.py,sha256=AcnCszS3WY9lF594NbFBtLylsA8ownnYp_XLQJ84Ios,2093
 commonmeta/writers/schema_org_writer.py,sha256=5j002uCNLdlScZMNQmPjodcVWqaBh2z38zL1H4lo2hY,5741
-commonmeta_py-0.31.dist-info/LICENSE,sha256=746hEF2wZCKkcckk5-_DcBLtHewfaEMS4iXTlA1PVwk,1074
-commonmeta_py-0.31.dist-info/METADATA,sha256=zJ8DGELyt5duoMd6t7UebZE83w6clxAAXZEJt9sKQic,8331
-commonmeta_py-0.31.dist-info/WHEEL,sha256=sP946D7jFCHeNz5Iq4fL4Lu-PrWrFsgfLXbbkciIZwg,88
-commonmeta_py-0.31.dist-info/entry_points.txt,sha256=vbcDw3_2lMTKdcAL2VUF4DRYRpKuzXVYLMCdgKVf88U,49
-commonmeta_py-0.31.dist-info/RECORD,,
+commonmeta_py-0.33.dist-info/LICENSE,sha256=746hEF2wZCKkcckk5-_DcBLtHewfaEMS4iXTlA1PVwk,1074
+commonmeta_py-0.33.dist-info/METADATA,sha256=G7zkJ6L1biUiEGKgUMYY1a1xTdzRdxApaKjPZR22tSA,8331
+commonmeta_py-0.33.dist-info/WHEEL,sha256=sP946D7jFCHeNz5Iq4fL4Lu-PrWrFsgfLXbbkciIZwg,88
+commonmeta_py-0.33.dist-info/entry_points.txt,sha256=vbcDw3_2lMTKdcAL2VUF4DRYRpKuzXVYLMCdgKVf88U,49
+commonmeta_py-0.33.dist-info/RECORD,,