commonmeta-py 0.137__py3-none-any.whl → 0.139__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__ = "0.137"
+__version__ = "0.139"
 __author__ = "Martin Fenner"
 __license__ = "MIT"
 

commonmeta/doi_utils.py

@@ -315,6 +315,7 @@ def is_rogue_scholar_doi(doi: str, ra: str = "crossref") -> bool:
         "10.59350",
         "10.63485",
         "10.64000",
+        "10.64395",
     ]
     rogue_scholar_datacite_prefixes = [
         "10.5438",

commonmeta/metadata.py

@@ -355,13 +355,14 @@ class MetadataList:
             raise ValueError("No input found")
         if isinstance(dct, dict):
             meta = dct
+        elif isinstance(dct, list):
+            meta = {"items": dct}
         elif isinstance(dct, (str, bytes)):
             if path.exists(dct):
                 with open(dct, encoding="utf-8") as file:
                     dct = file.read()
             self.via = kwargs.get("via", None) or find_from_format(string=dct)
             meta = self.get_metadata_list(dct)
-
         self.id = meta.get("id", None)
         self.type = meta.get("type", None)
         self.title = meta.get("title", None)
@@ -392,12 +393,15 @@ class MetadataList:
     def get_metadata_list(self, string) -> list:
         if string is None or not isinstance(string, (str, bytes)):
             raise ValueError("No input found")
+        if self.via in [
+            "inveniordm",
+        ]:
+            return {"items": json.loads(string)}
         if self.via in [
             "commonmeta",
             "crossref",
             "csl",
             "datacite",
-            "inveniordm",
             "jsonfeed",
             "openalex",
             "schema_org",

commonmeta/readers/inveniordm_reader.py

@@ -1,5 +1,7 @@
 """InvenioRDM reader for Commonmeta"""
 
+from typing import Optional
+
 import requests
 from furl import furl
 from pydash import py_
@@ -12,8 +14,9 @@ from ..constants import (
     Commonmeta,
 )
 from ..date_utils import strip_milliseconds
-from ..doi_utils import doi_as_url, doi_from_url
+from ..doi_utils import doi_as_url, doi_from_url, is_rogue_scholar_doi
 from ..utils import (
+    dict_to_fos,
     dict_to_spdx,
     from_inveniordm,
     get_language,
@@ -40,7 +43,15 @@ def read_inveniordm(data: dict, **kwargs) -> Commonmeta:
     meta = data
     read_options = kwargs or {}
 
-    url = normalize_url(py_.get(meta, "links.self_html"))
+    url = normalize_url(py_.get(meta, "links.self_html")) or next(
+        (
+            normalize_url(identifier.get("identifier"))
+            for identifier in wrap(py_.get(meta, "metadata.identifiers", []))
+            if identifier.get("scheme") == "url"
+            and identifier.get("identifier", None) is not None
+        ),
+        None,
+    )
     _id = (
         doi_as_url(meta.get("doi", None))
         or doi_as_url(py_.get(meta, "pids.doi.identifier"))
@@ -67,10 +78,22 @@ def read_inveniordm(data: dict, **kwargs) -> Commonmeta:
     #     titles += [{"title": sanitize("bla")} for i in wrap(additional_titles)]
 
     date: dict = {}
-    date["published"] = py_.get(meta, ("metadata.publication_date"))
-    if date["published"]:
-        date["published"] = date["published"].split("/")[0]
-    date["updated"] = strip_milliseconds(meta.get("updated", None))
+    date["published"] = next(
+        (
+            i.get("date")
+            for i in wrap(py_.get(meta, "metadata.dates", []))
+            if py_.get(i, "type.id") == "issued" and i.get("date", None) is not None
+        ),
+        None,
+    ) or py_.get(meta, ("metadata.publication_date"))
+    date["updated"] = next(
+        (
+            i.get("date")
+            for i in wrap(py_.get(meta, "metadata.dates", []))
+            if py_.get(i, "type.id") == "updated" and i.get("date", None) is not None
+        ),
+        None,
+    ) or strip_milliseconds(meta.get("updated", None))
     f = furl(url)
     if f.host == "zenodo.org":
         container = compact(
@@ -89,25 +112,31 @@ def read_inveniordm(data: dict, **kwargs) -> Commonmeta:
                 {
                     "type": "Periodical",
                     "title": container.get("title", None),
-                    "identifier": issn,
+                    "identifier": issn if issn else None,
                     "identifierType": "ISSN" if issn else None,
+                    "platform": py_.get(meta, "custom_fields.rs:generator", None),
                 }
             )
-    license_ = py_.get(meta, "metadata.rights[0].id") or py_.get(
-        meta, "metadata.license.id"
-    )
-    if license_:
-        license_ = dict_to_spdx({"id": license_})
     descriptions = format_descriptions(
         [
             py_.get(meta, "metadata.description"),
             py_.get(meta, "metadata.notes"),
         ]
     )
+    identifiers = py_.compact(
+        [format_identifier(i) for i in wrap(py_.get(meta, "metadata.identifiers"))]
+    )
     language = py_.get(meta, "metadata.language") or py_.get(
         meta, "metadata.languages[0].id"
     )
-    subjects = [name_to_fos(i) for i in wrap(py_.get(meta, "metadata.keywords"))]
+    license_ = py_.get(meta, "metadata.rights[0].id") or py_.get(
+        meta, "metadata.license.id"
+    )
+    if license_:
+        license_ = dict_to_spdx({"id": license_})
+    subjects = [dict_to_fos(i) for i in wrap(py_.get(meta, "metadata.subjects"))] or [
+        name_to_fos(i) for i in wrap(py_.get(meta, "metadata.keywords"))
+    ]
 
     references = get_references(wrap(py_.get(meta, "metadata.related_identifiers")))
     relations = get_relations(wrap(py_.get(meta, "metadata.related_identifiers")))
@@ -119,6 +148,9 @@ def read_inveniordm(data: dict, **kwargs) -> Commonmeta:
                 "type": "IsVersionOf",
             }
         )
+
+    content = py_.get(meta, "custom_fields.rs:content_html")
+    image = py_.get(meta, "custom_fields.rs:image")
     files = [get_file(i) for i in wrap(meta.get("files"))]
 
     return {
@@ -135,6 +167,7 @@ def read_inveniordm(data: dict, **kwargs) -> Commonmeta:
             # recommended and optional properties
             # "additional_type": additional_type,
             "subjects": presence(subjects),
+            "identifiers": presence(identifiers),
             "language": get_language(language),
             "version": py_.get(meta, "metadata.version"),
             "license": presence(license_),
@@ -143,10 +176,12 @@ def read_inveniordm(data: dict, **kwargs) -> Commonmeta:
             "fundingReferences": presence(funding_references),
             "references": presence(references),
             "relations": presence(relations),
+            "content": presence(content),
+            "image": presence(image),
+            "files": presence(files),
             # other properties
-            "files": files,
             "container": container,
-            "provider": "DataCite",
+            "provider": "Crossref" if is_rogue_scholar_doi(_id) else "Datacite",
         },
         **read_options,
     }
@@ -258,3 +293,27 @@ def format_descriptions(descriptions: list) -> list:
         for index, i in enumerate(descriptions)
         if i
     ]
+
+
+def format_identifier(identifier: dict) -> Optional[dict]:
+    """format_identifier. scheme url is stored as url metadata."""
+    if (
+        identifier.get("identifier", None) is None
+        or identifier.get("scheme", None) is None
+        or identifier.get("scheme") == "url"
+    ):
+        return None
+
+    scheme = identifier.get("scheme")
+    if scheme == "doi":
+        identifier_type = "DOI"
+    elif scheme == "uuid":
+        identifier_type = "UUID"
+    elif scheme == "guid":
+        identifier_type = "GUID"
+    else:
+        identifier_type = None
+    return {
+        "identifier": identifier.get("identifier"),
+        "identifierType": identifier_type,
+    }

commonmeta/utils.py

@@ -1367,6 +1367,15 @@ def name_to_fos(name: str) -> Optional[dict]:
     return {"subject": subject}
 
 
+def dict_to_fos(dct: dict) -> Optional[dict]:
+    """Convert dict to Fields of Science (OECD) subject"""
+    if not isinstance(dct, dict):
+        return None
+    if dct.get("subject", None) is not None:
+        return name_to_fos(dct["subject"])
+    return None
+
+
 def from_curie(id: Optional[str]) -> Optional[str]:
     """from CURIE"""
     if id is None:

commonmeta/writers/crossref_xml_writer.py

@@ -452,7 +452,9 @@ def push_crossref_xml_list(
             if uuid:
                 record["uuid"] = uuid
                 record = update_legacy_record(
-                    record, legacy_key=legacy_key, field="doi"
+                    # record, legacy_key=legacy_key, field="doi"
+                    record,
+                    legacy_key=legacy_key,
                 )
         items.append(record)
 

commonmeta/writers/inveniordm_writer.py

@@ -382,9 +382,16 @@ def to_inveniordm_funding(funding: dict) -> Optional[dict]:
 
 def write_inveniordm_list(metalist):
     """Write InvenioRDM list"""
+
     if metalist is None:
         return None
-    return [write_inveniordm(item) for item in metalist.items]
+
+    def write_item(item):
+        """write inveniordm item for inveniordm list"""
+
+        return write_inveniordm(item)
+
+    return [write_item(item) for item in metalist.items]
 
 
 def push_inveniordm(metadata: Commonmeta, host: str, token: str, **kwargs) -> Dict:
@@ -727,6 +734,7 @@ def update_legacy_record(record, legacy_key: str, field: str = None) -> dict:
                 "indexed_at": now,
                 "indexed": "true",
                 "archived": "true",
+                "registered": "false",
             }
         elif record.get("doi", None) is not None:
             output = {
@@ -734,10 +742,12 @@ def update_legacy_record(record, legacy_key: str, field: str = None) -> dict:
                 "indexed_at": now,
                 "indexed": "true",
                 "archived": "true",
+                "registered": "false",
             }
         else:
-            print(f"nothing to update for id {record.get('uuid')}")
-            return record  # nothing to update
+            output = {
+                "registered": "true",
+            }
 
         request_url = f"https://{legacy_host}/rest/v1/posts?id=eq.{record['uuid']}"
         headers = {

{commonmeta_py-0.137.dist-info → commonmeta_py-0.139.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: commonmeta-py
-Version: 0.137
+Version: 0.139
 Summary: Library for conversions to/from the Commonmeta scholarly metadata format
 Project-URL: Homepage, https://python.commonmeta.org
 Project-URL: Repository, https://github.com/front-matter/commonmeta-py

{commonmeta_py-0.137.dist-info → commonmeta_py-0.139.dist-info}/RECORD

@@ -1,16 +1,16 @@
-commonmeta/__init__.py,sha256=dHiaWJo_FPXFLyxr8wGWSwgUCHKUZAewRgsiCTu54rA,2118
+commonmeta/__init__.py,sha256=0LNsQxOEovE9g84On2Y4q4nCnYHQcXN6TkJDbyChwcM,2118
 commonmeta/api_utils.py,sha256=P8LMHHYiF4OTi97_5k4KstcBreooMkOAKZ4ebxsAv4o,2691
 commonmeta/author_utils.py,sha256=3lYW5s1rOUWNTKs1FP6XLfEUY3yCLOe_3L_VdJTDMp0,8585
 commonmeta/base_utils.py,sha256=-MGy9q2uTiJEkPWQUYOJMdq-3tRpNnvBwlLjvllQ5g8,11164
 commonmeta/cli.py,sha256=kBDSn7hL29I_ICn8XKFFEaIWl_ZVE_KrNWpzfar9v3g,8639
 commonmeta/constants.py,sha256=wSTEUiHeRdXLwjXEQD9AU2hxFyEKi5OTX2iHOKO6nF0,19844
 commonmeta/date_utils.py,sha256=H2cCobX0JREIUOT_cCigGd3MG7prGiQpXk1m4ZNrFwU,6318
-commonmeta/doi_utils.py,sha256=uB5Zxr5ezo-5Pp_M_FCGM7jwuZ8ylRBtS1WHOCCLpsU,11491
+commonmeta/doi_utils.py,sha256=0g53aGwYCLHmZZBpRBnxTO39IsF3fcDltEWbRMBY4HE,11511
 commonmeta/file_utils.py,sha256=eFYDWyR8Gr722nvFmp542hCm-TGmO_q4ciZ85IPHpjA,2893
-commonmeta/metadata.py,sha256=90aTe47d071wHxwcNsOqU5lSVPKP8wAPnPHhddj3Fuo,18443
+commonmeta/metadata.py,sha256=xh5RNy9f7uKu5AjoPKyLqHGx149tGFy3IZwrf-fYHzg,18597
 commonmeta/schema_utils.py,sha256=zn3gqAHciUOQmrw9okR68weFs-yqPPyORFt-Zl1D3Lw,1924
 commonmeta/translators.py,sha256=CBMK4jrXRmGZiAhCh6wsJjhbDJWbcsda8UvXFXxccAw,1363
-commonmeta/utils.py,sha256=1Q6vh1mhQRTcPsEEymAPPJxBgDfNOR1ZXF_UaaW9ZoM,53612
+commonmeta/utils.py,sha256=L84hESseuBbnY2iEjuBb9y2reUPmoX29R1hmlli8NW0,53877
 commonmeta/readers/__init__.py,sha256=vOf7UsOKNoh_ZCuyexxhAmPMt8wjB-pF_CfpWRaN8pk,45
 commonmeta/readers/bibtex_reader.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 commonmeta/readers/cff_reader.py,sha256=HMFK6QIg_XIlhmYIWL4EfIyuidYl5L_0TAwyG78XPlU,6244
@@ -21,7 +21,7 @@ commonmeta/readers/crossref_xml_reader.py,sha256=A2iAFT2IbhTNcfL-Dx4xO2SFSNOu_HN
 commonmeta/readers/csl_reader.py,sha256=OxzC2AZKfv43BCah4XGYvlK_LUK-5mxXFcjdzB5vv_o,3216
 commonmeta/readers/datacite_reader.py,sha256=4b_AP8m_aOUNVnVB0nU9j4-a8WTpmYJA8QPr5v35qyw,12219
 commonmeta/readers/datacite_xml_reader.py,sha256=nsPc7JBbIKgx6Yaauq8vmhUE-o6K0t_MAuExv6FO2AU,13205
-commonmeta/readers/inveniordm_reader.py,sha256=DtSloEZDu8bL-QLQAqAW1aDsS6ESTDZyhme379IekjY,8502
+commonmeta/readers/inveniordm_reader.py,sha256=0zJABZMfncWDjhilFNkcxE7-hx2Ug_37RbksSkAJ_w4,10514
 commonmeta/readers/jsonfeed_reader.py,sha256=rrWsYfvgji0SW0wgvyT-eQ7J-nFraP6CXe1bWH0nx84,16134
 commonmeta/readers/kbase_reader.py,sha256=0Y9cHRNs_7kHyocN4IESXbgmXJiq4TXoxvGeUYGml1s,6896
 commonmeta/readers/openalex_reader.py,sha256=4HUkBsut_iUjhUcC5c1GHgxnKsYQc-fgY43QILgVZEg,12826
@@ -77,14 +77,14 @@ commonmeta/writers/__init__.py,sha256=47-snms6xBHkoEXKYV1DBtH1npAtlVtvY29Z4Zr45q
 commonmeta/writers/bibtex_writer.py,sha256=doAdyl1NEp60mPkHPo3GMH8B-HA6MzLAdlyNsIecTzU,4972
 commonmeta/writers/citation_writer.py,sha256=qs_4X3BjrSqHexmJFPvPDTp0mRIqzb0F70_Wuc7S9x0,2343
 commonmeta/writers/commonmeta_writer.py,sha256=QpfyhG__7o_XpsOTCPWxGymO7YKwZi2LQh8Zic44bdc,1365
-commonmeta/writers/crossref_xml_writer.py,sha256=nyNgnyluzd9jZ6jysrSg_TpMNOQuVjfMo7pN0HUb3c0,34832
+commonmeta/writers/crossref_xml_writer.py,sha256=1DQNnjU_9TSz2YuBQprKK_3ostCBikZUn9OVhov78B8,34905
 commonmeta/writers/csl_writer.py,sha256=4gDYs1EzK4_L2UIRTfs25wgHmYRwdRP2zmfxF9387oU,2779
 commonmeta/writers/datacite_writer.py,sha256=bcinpwhq7XnVthKHH8-sdXA34dSlvFH4ImYH768iaQU,6428
-commonmeta/writers/inveniordm_writer.py,sha256=tiuq9JEkz02l615yVe9wUcJQqiIPJLUqNDyofEE8Aus,26726
+commonmeta/writers/inveniordm_writer.py,sha256=Q28Ogj5M8nP6FuOLcJOO8Vrm6jHRoYxCEyAcT3FjzA4,26882
 commonmeta/writers/ris_writer.py,sha256=3SdyEvMRaPRP1SV1MB-MXBlunE7x6og7RF1zuWtetPc,2094
 commonmeta/writers/schema_org_writer.py,sha256=s18_x0ReXwAGBoEAwp2q-HCgFQ-h5qRg6JyAlqCoSFE,5871
-commonmeta_py-0.137.dist-info/METADATA,sha256=2AJlNYHWys5ZdUp3TT5_DZPa65pFTj-t2ohmJAedj1U,7656
-commonmeta_py-0.137.dist-info/WHEEL,sha256=qtCwoSJWgHk21S1Kb4ihdzI2rlJ1ZKaIurTj_ngOhyQ,87
-commonmeta_py-0.137.dist-info/entry_points.txt,sha256=U4w4BoRuS3rN5t5Y-uYSyOeU5Lh_VRVMS9OIDzIgw4w,50
-commonmeta_py-0.137.dist-info/licenses/LICENSE,sha256=wsIvxF9Q9GC9vA_s79zTWP3BkXJdfUNRmALlU8GbW1s,1074
-commonmeta_py-0.137.dist-info/RECORD,,
+commonmeta_py-0.139.dist-info/METADATA,sha256=-oF4TP5OQTDBUQYQJaBDfCKje5jKjtUlP3ludFAESJ4,7656
+commonmeta_py-0.139.dist-info/WHEEL,sha256=qtCwoSJWgHk21S1Kb4ihdzI2rlJ1ZKaIurTj_ngOhyQ,87
+commonmeta_py-0.139.dist-info/entry_points.txt,sha256=U4w4BoRuS3rN5t5Y-uYSyOeU5Lh_VRVMS9OIDzIgw4w,50
+commonmeta_py-0.139.dist-info/licenses/LICENSE,sha256=wsIvxF9Q9GC9vA_s79zTWP3BkXJdfUNRmALlU8GbW1s,1074
+commonmeta_py-0.139.dist-info/RECORD,,