commonmeta-py 0.101__py3-none-any.whl → 0.103__py3-none-any.whl

commonmeta/__init__.py

@@ -10,11 +10,50 @@ commonmeta-py is a Python library to convert scholarly metadata
 """
 
 __title__ = "commonmeta-py"
-__version__ = "0.101"
+__version__ = "0.103"
 __author__ = "Martin Fenner"
 __license__ = "MIT"
 
 # ruff: noqa: F401
+from .author_utils import (
+    authors_as_string,
+    cleanup_author,
+    get_affiliations,
+    get_authors,
+    get_one_author,
+    is_personal_name,
+)
+from .base_utils import (
+    compact,
+    parse_attributes,
+    presence,
+    sanitize,
+    unwrap,
+    wrap,
+)
+from .date_utils import (
+    get_date_from_crossref_parts,
+    get_date_from_date_parts,
+    get_date_from_unix_timestamp,
+    get_date_parts,
+    get_iso8601_date,
+    strip_milliseconds,
+)
+from .doi_utils import (
+    crossref_api_url,
+    crossref_xml_api_url,
+    datacite_api_url,
+    decode_doi,
+    doi_as_url,
+    doi_from_url,
+    doi_resolver,
+    encode_doi,
+    get_doi_ra,
+    is_rogue_scholar_doi,
+    normalize_doi,
+    validate_doi,
+    validate_prefix,
+)
 from .metadata import Metadata, MetadataList
 from .readers import (
     cff_reader,
@@ -26,23 +65,15 @@ from .readers import (
     inveniordm_reader,
     json_feed_reader,
     kbase_reader,
+    openalex_reader,
     ris_reader,
     schema_org_reader,
 )
-from .writers import (
-    bibtex_writer,
-    citation_writer,
-    commonmeta_writer,
-    csl_writer,
-    datacite_writer,
-    ris_writer,
-    schema_org_writer,
-)
 from .utils import (
     dict_to_spdx,
+    extract_curie,
     extract_url,
     extract_urls,
-    extract_curie,
     from_csl,
     from_json_feed,
     from_schema_org,
@@ -53,8 +84,8 @@ from .utils import (
     normalize_id,
     normalize_ids,
     normalize_orcid,
-    normalize_url,
     normalize_ror,
+    normalize_url,
     pages_as_string,
     replace_curie,
     to_csl,
@@ -62,42 +93,12 @@ from .utils import (
     validate_ror,
     validate_url,
 )
-from .author_utils import (
-    authors_as_string,
-    cleanup_author,
-    get_affiliations,
-    get_authors,
-    get_one_author,
-    is_personal_name,
-)
-from .base_utils import (
-    wrap,
-    unwrap,
-    compact,
-    presence,
-    parse_attributes,
-    sanitize,
-)
-from .date_utils import (
-    get_date_from_crossref_parts,
-    get_date_from_date_parts,
-    get_date_from_unix_timestamp,
-    get_date_parts,
-    get_iso8601_date,
-    strip_milliseconds,
-)
-from .doi_utils import (
-    crossref_api_url,
-    crossref_xml_api_url,
-    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,
+from .writers import (
+    bibtex_writer,
+    citation_writer,
+    commonmeta_writer,
+    csl_writer,
+    datacite_writer,
+    ris_writer,
+    schema_org_writer,
 )

commonmeta/base_utils.py

@@ -1,4 +1,5 @@
 """Base utilities for commonmeta-py"""
+
 import html
 from os import path
 import re

commonmeta/constants.py

@@ -1,6 +1,6 @@
 """Constants for commonmeta-py"""
 
-from typing import Optional, TypedDict, List
+from typing import List, Optional, TypedDict
 
 
 class Commonmeta(TypedDict):
@@ -464,6 +464,30 @@ CM_TO_SO_TRANSLATIONS = {
     "Presentation": "PresentationDigitalDocument",
 }
 
+# source: https://api.openalex.org/works?group_by=type
+OA_TO_CM_TRANSLATIONS = {
+    "article": "Article",
+    "book": "Book",
+    "book-chapter": "BookChapter",
+    "dataset": "Dataset",
+    "dissertation": "Dissertation",
+    "editorial": "Document",
+    "erratum": "Other",
+    "grant": "Grant",
+    "letter": "Article",
+    "libguides": "InteractiveResource",
+    "other": "Other",
+    "paratext": "Component",
+    "peer-review": "PeerReview",
+    "preprint": "Article",
+    "reference-entry": "Other",
+    "report": "Report",
+    "retraction": "Other",
+    "review": "Article",
+    "standard": "Standard",
+    "supplementary-materials": "Component",
+}
+
 SO_TO_DC_RELATION_TYPES = {
     "citation": "References",
     "isBasedOn": "IsSupplementedBy",
@@ -527,6 +551,16 @@ DC_TO_CM_CONTAINER_TRANSLATIONS = {
     "Series": "Series",
 }
 
+OA_TO_CM_CONTAINER_TRANLATIONS = {
+    "journal": "Journal",
+    "repository": "Repository",
+    "conference": "Proceedings",
+    "ebook platform": "Book",
+    "book series": "BookSeries",
+    "metadata": "DataRepository",
+    "Other": "Repository",
+}
+
 DATACITE_CONTRIBUTOR_TYPES = {
     "ContactPerson": "ContactPerson",
     "DataCollector": "DataCollector",

commonmeta/crossref_utils.py

@@ -1,16 +1,17 @@
 """Crossref utils module for commonmeta-py"""
 
-from lxml import etree
-from typing import Optional
-from datetime import datetime
-from dateutil.parser import parse
 import uuid
+from datetime import datetime
+from typing import Optional
+
 import pydash as py_
+from dateutil.parser import parse
 from furl import furl
+from lxml import etree
 
-from .constants import Commonmeta, ROR_TO_CROSSREF_FUNDER_ID_TRANSLATIONS
-from .utils import wrap, compact, normalize_orcid, normalize_id, validate_url
+from .constants import ROR_TO_CROSSREF_FUNDER_ID_TRANSLATIONS, Commonmeta
 from .doi_utils import doi_from_url, validate_doi
+from .utils import compact, normalize_id, normalize_orcid, validate_url, wrap
 
 
 def generate_crossref_xml(metadata: Commonmeta) -> Optional[str]:
@@ -229,11 +230,12 @@ def insert_citation_list(metadata, xml):
         return xml
 
     citation_list = etree.SubElement(xml, "citation_list")
-    for ref in metadata.references:
+    for i, ref in enumerate(metadata.references):
+        print(i)
         if ref.get("id", None) is None:
             continue
         citation = etree.SubElement(
-            citation_list, "citation", {"key": ref.get("key", None)}
+            citation_list, "citation", {"key": ref.get("key", f"ref{i + 1}")}
         )
         if ref.get("journal_title", None) is not None:
             etree.SubElement(citation, "journal_article").text = ref.get(
@@ -255,6 +257,7 @@ def insert_citation_list(metadata, xml):
             etree.SubElement(citation, "unstructured_citation").text = ref.get(
                 "unstructured"
             )
+        print(xml)
     return xml
 
 

commonmeta/date_utils.py

@@ -1,4 +1,5 @@
 """Date utils for commonmeta-py"""
+
 import datetime
 from datetime import datetime as dt
 from typing import Optional, Union

commonmeta/doi_utils.py

@@ -2,9 +2,10 @@
 
 import re
 from typing import Optional
+
+import base32_lib as base32
 import httpx
 from furl import furl
-import base32_lib as base32
 
 from .base_utils import compact
 
@@ -71,8 +72,12 @@ def doi_from_url(url: Optional[str]) -> Optional[str]:
             f.path.segments[-1] in ["fetchobject.action"]
             and f.args.get("uri", None) is not None
         ):
-            f.path = f.args.get("uri")
-    path = str(f.path)
+            uri = f.args.get("uri")
+            if uri is not None:
+                f.path.segments.clear()
+                f.path.segments.append(uri)
+
+    path = str(f.path).replace("%2F", "/")
     match = re.search(
         r"(10\.\d{4,5}/.+)\Z",
         path,
@@ -86,9 +91,12 @@ def short_doi_as_doi(doi: Optional[str]) -> Optional[str]:
     """Resolve a short DOI"""
     if doi is None:
         return None
-    response = httpx.head(doi_as_url(doi), timeout=10)
+    doi_url = doi_as_url(doi)
+    if doi_url is None:
+        return None
+    response = httpx.head(doi_url, timeout=10)
     if response.status_code != 301:
-        return doi_as_url(doi)
+        return doi_url
     return response.headers.get("Location")
 
 
@@ -106,7 +114,10 @@ def normalize_doi(doi: Optional[str], **kwargs) -> Optional[str]:
     doi_str = validate_doi(doi)
     if not doi_str:
         return None
-    return doi_resolver(doi, **kwargs) + doi_str.lower()
+    resolver = doi_resolver(doi, **kwargs)
+    if resolver is None:
+        return None
+    return resolver + doi_str.lower()
 
 
 def doi_resolver(doi, **kwargs):
@@ -144,13 +155,14 @@ def encode_doi(prefix, number: Optional[int] = None, checksum: bool = True) -> s
 def decode_doi(doi: str, checksum: bool = True) -> int:
     """Decode a DOI to a number"""
     try:
-        doi = validate_doi(doi)
-        if doi is None:
+        validated_doi = validate_doi(doi)
+        if validated_doi is None:
             return 0
-        suffix = doi.split("/", maxsplit=1)[1]
+        suffix = validated_doi.split("/", maxsplit=1)[1]
         if checksum:
             number = base32.decode(suffix, checksum=True)
-        number = base32.decode(suffix)
+        else:
+            number = base32.decode(suffix)
         return number
     except ValueError:
         return 0
@@ -183,6 +195,9 @@ def crossref_api_query_url(query: dict) -> str:
     rows = min(int(query.get("rows", 20)), 1000)
     queries = []
     filters = []
+    _query = None
+    _filter = None
+
     if query.get("query", None) is not None:
         queries += [query.get("query")]
     for key, value in query.items():
@@ -193,7 +208,8 @@ def crossref_api_query_url(query: dict) -> str:
             "query.container-title",
         ]:
             queries += [f"{key}:{value}"]
-        _query = ",".join(queries) if len(queries) > 0 else None
+    if queries:
+        _query = ",".join(queries)
 
     for key, value in query.items():
         if key in [
@@ -207,8 +223,10 @@ def crossref_api_query_url(query: dict) -> str:
             "has-license",
         ]:
             filters += [f"{key}:{value}"]
-        _filter = ",".join(filters) if len(filters) > 0 else None
-    f.args = compact({"rows": rows, "query": _query, "filter": _filter})
+    if filters:
+        _filter = ",".join(filters)
+
+    f.args.update(compact({"rows": rows, "query": _query, "filter": _filter}))
 
     return f.url
 
@@ -284,6 +302,16 @@ def datacite_api_sample_url(number: int = 1, **kwargs) -> str:
     return f"https://api.datacite.org/dois?random=true&page[size]={number}"
 
 
+def openalex_api_url(doi: str, **kwargs) -> str:
+    """Return the OpenAlex API URL for a given DOI"""
+    return f"https://api.openalex.org/works/{doi}"
+
+
+def openalex_api_sample_url(number: int = 1, **kwargs) -> str:
+    """Return the OpenAlex API URL for a sample of dois"""
+    return f"https://api.openalex.org/works?sample={number}"
+
+
 def is_rogue_scholar_doi(doi: str) -> bool:
     """Return True if DOI is from Rogue Scholar"""
     prefix = validate_prefix(doi)
@@ -298,5 +326,5 @@ def is_rogue_scholar_doi(doi: str) -> bool:
         "10.59350",
         "10.63485",
         "10.64000",
-        "10.71938", # not managed by Front Matter
+        "10.71938",  # not managed by Front Matter
     ]