commonmeta-py 0.27__tar.gz → 0.65__tar.gz

{commonmeta_py-0.27 → commonmeta_py-0.65}/PKG-INFO

@@ -1,19 +1,20 @@
 Metadata-Version: 2.1
 Name: commonmeta-py
-Version: 0.27
+Version: 0.65
 Summary: Library for conversions to/from the Commonmeta scholarly metadata format
 Home-page: https://python.commonmeta.org
 License: MIT
 Keywords: science,metadata,commonmeta,bibtex,csl,crossref,datacite
 Author: Martin Fenner
 Author-email: martin@front-matter.io
-Requires-Python: >=3.9,<4.0.0
+Requires-Python: >=3.9,<4.0
 Classifier: License :: OSI Approved :: MIT License
 Classifier: Programming Language :: Python :: 3
 Classifier: Programming Language :: Python :: 3.9
 Classifier: Programming Language :: Python :: 3.10
 Classifier: Programming Language :: Python :: 3.11
 Classifier: Programming Language :: Python :: 3.12
+Classifier: Programming Language :: Python :: 3.13
 Requires-Dist: PyYAML (>=6.0,<7.0)
 Requires-Dist: anyio (>=4.2.0,<5.0.0)
 Requires-Dist: asyncclick (>=8.1.7.1,<9.0.0.0)
@@ -27,23 +28,21 @@ Requires-Dist: click (>=8.1.7,<9.0.0)
 Requires-Dist: datacite (>=1.1,<2.0)
 Requires-Dist: dateparser (>=1.1.7,<2.0.0)
 Requires-Dist: docutils (>=0.19,<0.20)
+Requires-Dist: edtf (>=5.0.0,<6.0.0)
 Requires-Dist: furl (>=2.1.3,<3.0.0)
 Requires-Dist: httpx (>=0.27,<0.28)
 Requires-Dist: jsonschema (>=4.21,<5.0)
-Requires-Dist: jupyterlab (>=4.0.9,<5.0.0)
-Requires-Dist: jupyterlab-quarto (>=0.2.8,<0.3.0)
 Requires-Dist: lxml (>=4.8)
 Requires-Dist: nameparser (>=1.1.2,<2.0.0)
 Requires-Dist: nbstripout (>=0.6,<0.7)
 Requires-Dist: nh3 (>=0.2.14,<0.3.0)
 Requires-Dist: orjson (>=3.9.14,<4.0.0)
 Requires-Dist: orjsonl (>=1.0.0,<2.0.0)
-Requires-Dist: pikepdf (>=8.14.0,<9.0.0)
+Requires-Dist: pikepdf (>=8.14,<10.0)
 Requires-Dist: pycountry (>=23.12.11,<24.0.0)
 Requires-Dist: pydash (>=7.0,<8.0)
 Requires-Dist: pyjwt (>=2.8.0,<3.0.0)
 Requires-Dist: python-dateutil (>=2.8.2,<3.0.0)
-Requires-Dist: quartodoc (>=0.7.1,<0.8.0)
 Requires-Dist: setuptools (>=70.0,<71.0)
 Requires-Dist: simplejson (>=3.18,<4.0)
 Requires-Dist: sphinx-autodoc-typehints (>=1.19,<2.0)

{commonmeta_py-0.27 → commonmeta_py-0.65}/commonmeta/__init__.py

@@ -10,7 +10,7 @@ commonmeta-py is a Python library to convert scholarly metadata
 """
 
 __title__ = "commonmeta-py"
-__version__ = "0.27"
+__version__ = "0.65"
 __author__ = "Martin Fenner"
 __license__ = "MIT"
 
@@ -54,7 +54,6 @@ from .utils import (
     validate_orcid,
     validate_url,
     get_language,
-    encode_doi,
     name_to_fos,
     from_json_feed,
 )
@@ -88,9 +87,12 @@ from .doi_utils import (
     doi_from_url,
     doi_as_url,
     doi_resolver,
+    decode_doi,
+    encode_doi,
     datacite_api_url,
     get_doi_ra,
     normalize_doi,
     validate_doi,
     validate_prefix,
+    is_rogue_scholar_doi,
 )

{commonmeta_py-0.27 → commonmeta_py-0.65}/commonmeta/base_utils.py

@@ -94,6 +94,7 @@ def parse_xml(string: Optional[str], **kwargs) -> Optional[Union[dict, list]]:
             "item",
             "citation",
             "program",
+            "related_item",
         }
 
     kwargs["attr_prefix"] = ""

{commonmeta_py-0.27 → commonmeta_py-0.65}/commonmeta/cli.py

@@ -5,8 +5,7 @@ import orjson as json
 
 from commonmeta import Metadata, MetadataList  # __version__
 from commonmeta.api_utils import update_ghost_post_via_api
-from commonmeta.doi_utils import validate_prefix
-from commonmeta.utils import encode_doi, decode_doi
+from commonmeta.doi_utils import validate_prefix, encode_doi, decode_doi
 from commonmeta.readers.json_feed_reader import (
     get_json_feed_item_uuid,
 )

{commonmeta_py-0.27 → commonmeta_py-0.65}/commonmeta/constants.py

@@ -1,4 +1,5 @@
 """Constants for commonmeta-py"""
+
 from typing import Optional, TypedDict, List
 
 
@@ -407,11 +408,32 @@ SO_TO_CM_TRANSLATIONS = {
     "DigitalDocument": "Document",
     "Dissertation": "Dissertation",
     "Instrument": "Instrument",
+    "MusicRecording": "Audiovisual",
+    "MusicAlbum": "Audiovisual",
     "NewsArticle": "Article",
     "Legislation": "LegalDocument",
+    "ProfilePage": "WebPage",
     "Report": "Report",
     "ScholarlyArticle": "JournalArticle",
     "SoftwareSourceCode": "Software",
+    "Video": "Audiovisual",
+    "WebSite": "WebPage",
+}
+
+# OpenGraph to schema.org mapping
+OG_TO_SO_TRANSLATIONS = {
+    "music.song": "MusicRecording",
+    "music.album": "MusicAlbum",
+    "music.playlist": "MusicPlaylist",
+    "music.radio_station": "RadioStation",
+    "video.movie": "Video",
+    "video.episode": "Video",
+    "video.tv_show": "Video",
+    "video.other": "Video",
+    "article": "Article",
+    "book": "Book",
+    "profile": "ProfilePage",
+    "website": "WebSite",
 }
 
 CM_TO_SO_TRANSLATIONS = {
@@ -585,3 +607,52 @@ 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",
+    "GUID": "guid",
+    "UUID": "uuid",
+    "Other": "other",
+}
+
+
+CROSSREF_FUNDER_ID_TO_ROR_TRANSLATIONS = {
+    "https://doi.org/10.13039/100000001": "https://ror.org/021nxhr62",
+    "https://doi.org/10.13039/501100000780": "https://ror.org/00k4n6c32",
+    "https://doi.org/10.13039/501100007601": "https://ror.org/00k4n6c32",
+    "https://doi.org/10.13039/501100001659": "https://ror.org/018mejw64",
+    "https://doi.org/10.13039/501100006390": "https://ror.org/019whta54",
+    "https://doi.org/10.13039/501100001711": "https://ror.org/00yjd3n13",
+    "https://doi.org/10.13039/501100003043": "https://ror.org/04wfr2810",
+}
+
+
+ROR_TO_CROSSREF_FUNDER_ID_TRANSLATIONS = {
+    "https://ror.org/021nxhr62": "https://doi.org/10.13039/100000001",
+    "https://ror.org/00k4n6c32": "https://doi.org/10.13039/501100000780",
+    "https://ror.org/018mejw64": "https://doi.org/10.13039/501100001659",
+    "https://ror.org/019whta54": "https://doi.org/10.13039/501100006390",
+    "https://ror.org/00yjd3n13": "https://doi.org/10.13039/501100001711",
+    "https://ror.org/04wfr2810": "https://doi.org/10.13039/501100003043",
+}

{commonmeta_py-0.27 → commonmeta_py-0.65}/commonmeta/crossref_utils.py

@@ -8,7 +8,7 @@ import uuid
 import pydash as py_
 from furl import furl
 
-from .constants import Commonmeta
+from .constants import Commonmeta, ROR_TO_CROSSREF_FUNDER_ID_TRANSLATIONS
 from .utils import wrap, compact, normalize_orcid, normalize_id, validate_url
 from .doi_utils import doi_from_url, validate_doi
 
@@ -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
 
 
@@ -360,11 +362,18 @@ def insert_funding_references(metadata, xml):
             {"name": "funder_name"},
         )
         if funding_reference.get("funderIdentifier", None) is not None:
+            funder_identifier = funding_reference.get("funderIdentifier", None)
+
+            # translate ROR to Crossref funder ID until Crossref supports ROR
+            funder_identifier = ROR_TO_CROSSREF_FUNDER_ID_TRANSLATIONS.get(
+                funder_identifier, funder_identifier
+            )
+
             etree.SubElement(
                 funder_name,
                 "assertion",
                 {"name": "funder_identifier"},
-            ).text = funding_reference.get("funderIdentifier", None)
+            ).text = funder_identifier
         if funding_reference.get("awardNumber", None) is not None:
             etree.SubElement(
                 assertion,
@@ -440,9 +449,7 @@ def insert_item_number(metadata, xml):
     if metadata.identifiers is None:
         return xml
     for identifier in metadata.identifiers:
-        if identifier.get("identifier", None) is None:
-            continue
-        if identifier.get("identifierType", None) is not None:
+        if identifier.get("identifierType", None) == "UUID":
             # strip hyphen from UUIDs, as item_number can only be 32 characters long (UUIDv4 is 36 characters long)
             if identifier.get("identifierType", None) == "UUID":
                 identifier["identifier"] = identifier.get("identifier", "").replace(
@@ -454,9 +461,7 @@ def insert_item_number(metadata, xml):
                 {"item_number_type": identifier.get("identifierType", "").lower()},
             ).text = identifier.get("identifier", None)
         else:
-            etree.SubElement(xml, "item_number").text = identifier.get(
-                "identifier", None
-            )
+            continue
     return xml
 
 

{commonmeta_py-0.27 → commonmeta_py-0.65}/commonmeta/date_utils.py

@@ -3,6 +3,8 @@ import datetime
 from datetime import datetime as dt
 from typing import Optional, Union
 import dateparser
+from edtf import parse_edtf, DateAndTime, Date
+from edtf.parser.edtf_exceptions import EDTFParseException
 import pydash as py_
 
 from .base_utils import compact
@@ -191,3 +193,17 @@ def normalize_date_dict(data: dict) -> dict:
             "withdrawn": data.get("Withdrawn", None),
         }
     )
+
+
+def validate_edtf(iso8601_time: Optional[str]) -> Optional[str]:
+    """Validate EDTF string using edtf. Return None if invalid"""
+    if iso8601_time is None:
+        return None
+    try:
+        edtf = parse_edtf(iso8601_time)
+    except EDTFParseException as e:
+        print(e)
+        return None
+    if not isinstance(edtf, (DateAndTime, Date)):
+        return None
+    return edtf.isoformat()

{commonmeta_py-0.27 → commonmeta_py-0.65}/commonmeta/doi_utils.py

@@ -4,6 +4,7 @@ import re
 from typing import Optional
 import httpx
 from furl import furl
+import base32_lib as base32
 
 from .base_utils import compact
 
@@ -131,6 +132,34 @@ def get_doi_ra(doi) -> Optional[str]:
     return response.json()[0].get("RA", None)
 
 
+def encode_doi(prefix, number: Optional[int] = None, checksum: bool = True) -> str:
+    """Generate a DOI using the DOI prefix and a random base32 suffix"""
+    if isinstance(number, int):
+        suffix = base32.encode(number, split_every=5, checksum=checksum)
+    else:
+        suffix = base32.generate(length=10, split_every=5, checksum=True)
+    print("s", suffix)
+    return f"https://doi.org/{prefix}/{suffix}"
+
+
+def decode_doi(doi: str, checksum: bool = True) -> int:
+    """Decode a DOI to a number"""
+    try:
+        doi = validate_doi(doi)
+        if doi is None:
+            return 0
+        suffix = doi.split("/", maxsplit=1)[1]
+        print(suffix, checksum)
+        if checksum:
+            number = base32.decode(suffix, checksum=True)
+            print("n", number)
+        number = base32.decode(suffix)
+        print("nn", number)
+        return number
+    except ValueError:
+        return 0
+
+
 def get_crossref_member(member_id) -> Optional[dict]:
     """Return the Crossref member for a given member_id"""
     response = httpx.get("https://api.crossref.org/members/" + member_id, timeout=10)
@@ -263,10 +292,11 @@ def is_rogue_scholar_doi(doi: str) -> bool:
     """Return True if DOI is from Rogue Scholar"""
     prefix = validate_prefix(doi)
     return prefix in [
-        "10.34732",
+        "10.34732",  # not managed by Front Matter
         "10.53731",
         "10.54900",
-        "10.57689",
+        "10.57689",  # not managed by Front Matter
+        "10.58079",  # not managed by Front Matter
         "10.59348",
         "10.59349",
         "10.59350",

{commonmeta_py-0.27 → commonmeta_py-0.65}/commonmeta/metadata.py

@@ -101,6 +101,8 @@ class Metadata:
         self.titles = meta.get("titles")
         self.url = meta.get("url")
         self.version = meta.get("version")
+        self.content = meta.get("content")
+        self.image = meta.get("image")
         # other properties
         self.date_created = meta.get("date_created")
         self.date_registered = meta.get("date_registered")

{commonmeta_py-0.27 → commonmeta_py-0.65}/commonmeta/readers/crossref_reader.py

@@ -339,6 +339,8 @@ def get_container(meta: dict, issn: str) -> dict:
     )
     isbn = isbn["value"] if isbn else None
     container_title = parse_attributes(meta.get("container-title", None), first=True)
+    if not container_title and container_type in ["Periodical"]:
+        container_title = py_.get(meta, "institution.0.name")
     volume = meta.get("volume", None)
     issue = py_.get(meta, "journal-issue.issue")
     if meta.get("page", None):

{commonmeta_py-0.27 → commonmeta_py-0.65}/commonmeta/readers/csl_reader.py

@@ -1,9 +1,9 @@
 """CSL-JSON reader for commonmeta-py"""
-from ..utils import dict_to_spdx, from_csl, normalize_id, name_to_fos, encode_doi
+from ..utils import dict_to_spdx, from_csl, normalize_id, name_to_fos
 from ..base_utils import wrap, compact, sanitize, presence
 from ..author_utils import get_authors
 from ..date_utils import get_date_from_date_parts
-from ..doi_utils import get_doi_ra, doi_from_url
+from ..doi_utils import get_doi_ra, doi_from_url, encode_doi
 from ..constants import (
     CSL_TO_CM_TRANSLATIONS,
     Commonmeta,

{commonmeta_py-0.27 → commonmeta_py-0.65}/commonmeta/readers/inveniordm_reader.py

@@ -36,7 +36,6 @@ def get_inveniordm(pid: str, **kwargs) -> dict:
 
 def read_inveniordm(data: dict, **kwargs) -> Commonmeta:
     """read_inveniordm"""
-    print(data)
     meta = data
     read_options = kwargs or {}
 
@@ -49,7 +48,6 @@ def read_inveniordm(data: dict, **kwargs) -> Commonmeta:
     resource_type = py_.get(meta, "metadata.resource_type.type") or py_.get(
         meta, "metadata.resource_type.id"
     )
-    print(resource_type)
     _type = INVENIORDM_TO_CM_TRANSLATIONS.get(resource_type, "Other")
 
     contributors = py_.get(meta, "metadata.creators")
@@ -79,6 +77,7 @@ def read_inveniordm(data: dict, **kwargs) -> Commonmeta:
                 "title": "Zenodo",
             }
         )
+        publisher = {"name": "Zenodo"}
     else:
         container = py_.get(meta, "custom_fields.journal:journal")
         if container:
@@ -96,7 +95,6 @@ def read_inveniordm(data: dict, **kwargs) -> Commonmeta:
     )
     if license_:
         license_ = dict_to_spdx({"id": license_})
-    print(license_)
     descriptions = format_descriptions(
         [
             py_.get(meta, "metadata.description"),