commonmeta-py 0.111__tar.gz → 0.113__tar.gz

{commonmeta_py-0.111 → commonmeta_py-0.113}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: commonmeta-py
-Version: 0.111
+Version: 0.113
 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-0.111 → commonmeta_py-0.113}/commonmeta/__init__.py

@@ -10,7 +10,7 @@ commonmeta-py is a Python library to convert scholarly metadata
 """
 
 __title__ = "commonmeta-py"
-__version__ = "0.111"
+__version__ = "0.113"
 __author__ = "Martin Fenner"
 __license__ = "MIT"
 

{commonmeta_py-0.111 → commonmeta_py-0.113}/commonmeta/doi_utils.py

@@ -302,19 +302,101 @@ def datacite_api_sample_url(number: int = 1, **kwargs) -> str:
     return f"https://api.datacite.org/dois?random=true&page[size]={number}"
 
 
-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",  # not managed by Front Matter
+def is_rogue_scholar_doi(doi: str, ra: str = "crossref") -> bool:
+    """Check if a DOI is from Rogue Scholar with specific registration agency"""
+    rogue_scholar_crossref_prefixes = [
+        "10.13003",
         "10.53731",
         "10.54900",
-        "10.57689",  # not managed by Front Matter
-        "10.58079",  # not managed by Front Matter
+        "10.57689",
+        "10.59347",
         "10.59348",
         "10.59349",
         "10.59350",
         "10.63485",
         "10.64000",
+    ]
+    rogue_scholar_datacite_prefixes = [
+        "10.5438",
+        "10.34732",  # not managed by Front Matter
+        "10.57689",  # not managed by Front Matter
+        "10.58079",  # not managed by Front Matter
+        "10.60804",
         "10.71938",  # not managed by Front Matter
+        # "10.83132",
     ]
+
+    prefix = validate_prefix(doi)
+    if not prefix:
+        return False
+
+    is_crossref = prefix in rogue_scholar_crossref_prefixes
+    is_datacite = prefix in rogue_scholar_datacite_prefixes
+
+    if ra == "crossref":
+        return is_crossref
+    elif ra == "datacite":
+        return is_datacite
+    return is_crossref or is_datacite
+
+
+def generate_wordpress_doi(prefix: str, slug: str, guid: str) -> str:
+    """Generate a DOI from a WordPress GUID and slug"""
+    import re
+
+    if not prefix or not guid:
+        return ""
+
+    pattern = re.compile(r"p=(\d+)$")
+    matched = pattern.search(guid)
+
+    if not matched:
+        return ""
+
+    doi = f"https://doi.org/{prefix}/{slug}.{matched.group(1)}"
+    return doi
+
+
+def generate_doi_from_guid(prefix: str, guid: str) -> str:
+    """Validates a GUID that is a DOI"""
+    import base32_lib as base32
+
+    if not prefix:
+        return ""
+
+    doi = normalize_doi(guid)
+    if not doi:
+        return ""
+
+    p = validate_prefix(doi)
+    if not p or p != prefix:
+        return ""
+
+    suffix = doi.split("/")[-1]
+
+    try:
+        number = base32.decode(suffix, checksum=True)
+        if number != 0:
+            return doi
+    except (ValueError, IndexError):
+        pass
+
+    return ""
+
+
+def generate_substack_doi(prefix: str, guid: str) -> str:
+    """Generate a DOI from a Substack GUID"""
+    import base32_lib as base32
+
+    if not prefix or not guid:
+        return ""
+
+    try:
+        i = int(guid)
+    except ValueError:
+        return ""
+
+    # encode the number using base32 with length=4, split_every=8, and checksum=True
+    suffix = base32.encode(i, length=4, split_every=8, checksum=True)
+    doi = f"https://doi.org/{prefix}/{suffix}"
+    return doi

{commonmeta_py-0.111 → commonmeta_py-0.113}/commonmeta/metadata.py

@@ -490,7 +490,9 @@ class MetadataList:
         elif to == "datacite":
             raise ValueError("Datacite not yet supported for metadata lists")
         elif to == "inveniordm":
-            response = push_inveniordm_list(self, host=self.host, token=self.token, legacy_key=self.legacy_key)
+            response = push_inveniordm_list(
+                self, host=self.host, token=self.token, legacy_key=self.legacy_key
+            )
             return response
         else:
             raise ValueError("No valid output format found")

{commonmeta_py-0.111 → commonmeta_py-0.113}/commonmeta/readers/jsonfeed_reader.py

@@ -13,6 +13,9 @@ from ..date_utils import get_date_from_unix_timestamp
 from ..doi_utils import (
     doi_from_url,
     encode_doi,
+    generate_doi_from_guid,
+    generate_substack_doi,
+    generate_wordpress_doi,
     is_rogue_scholar_doi,
     normalize_doi,
     validate_doi,
@@ -55,13 +58,39 @@ def read_jsonfeed(data: Optional[dict], **kwargs) -> Commonmeta:
         "archive_url", None
     ):
         url = normalize_url(meta.get("archive_url", None))
-    _id = normalize_doi(read_options.get("doi", None) or meta.get("doi", None)) or url
-    _type = "BlogPost"
 
-    # optionally generate a DOI if missing but a DOI prefix is provided
-    prefix = read_options.get("prefix", None) or py_.get(meta, "blog.prefix", None)
-    if doi_from_url(_id) is None and prefix is not None:
-        _id = encode_doi(prefix)
+    # generate DOI string for registration if not provided
+    _id = normalize_doi(read_options.get("doi", None) or meta.get("doi", None))
+    if _id is None:
+        if meta.get("guid") and py_.get(meta, "blog.doi_reg", False):
+            # Generate DOI based on blogging platform
+            generator = py_.get(meta, "blog.generator")
+            prefix = py_.get(meta, "blog.prefix")
+            slug = py_.get(meta, "blog.slug")
+            guid = meta.get("guid")
+
+            # Import these functions only when needed to avoid circular imports
+            if generator in ["WordPress", "WordPress.com"] and prefix and slug and guid:
+                _id = generate_wordpress_doi(prefix, slug, guid)
+            elif generator == "Substack" and prefix and guid:
+                _id = generate_substack_doi(prefix, guid)
+            elif prefix and guid:
+                _id = generate_doi_from_guid(prefix, guid)
+
+        # If still no DOI but prefix provided and not registered for DOI generation
+        elif py_.get(meta, "blog.prefix") and not py_.get(meta, "blog.doi_reg", False):
+            prefix = py_.get(meta, "blog.prefix")
+            _id = encode_doi(prefix)
+
+        # If override prefix is provided in read_options, use that
+        elif read_options.get("prefix"):
+            _id = encode_doi(read_options.get("prefix"))
+
+    # fall back to url if no DOI can be generated
+    if _id is None:
+        _id = url
+
+    _type = "BlogPost"
 
     if meta.get("authors", None):
         contributors = get_authors(from_jsonfeed(wrap(meta.get("authors"))))

{commonmeta_py-0.111 → commonmeta_py-0.113}/commonmeta/writers/inveniordm_writer.py

@@ -23,6 +23,7 @@ from ..utils import (
     get_language,
     id_from_url,
     normalize_url,
+    pages_as_string,
     validate_orcid,
     validate_ror,
 )
@@ -68,7 +69,7 @@ def write_inveniordm(metadata):
         ]
     )
     container = metadata.container if metadata.container else {}
-    journal = (
+    journal_title = (
         container.get("title", None)
         if _type not in ["inbook", "inproceedings"]
         and container.get("type") in ["Journal", "Periodical", "Blog"]
@@ -79,6 +80,10 @@ def write_inveniordm(metadata):
         if container.get("identifierType", None) == "ISSN"
         else None
     )
+    volume = container.get("volume", None)
+    issue = container.get("issue", None)
+    pages = pages_as_string(container)
+
     dates = []
     for date in metadata.date.keys():
         if metadata.date.get(date, None) is None:
@@ -141,7 +146,15 @@ def write_inveniordm(metadata):
             ),
             "custom_fields": compact(
                 {
-                    "journal:journal": compact({"title": journal, "issn": issn}),
+                    "journal:journal": compact(
+                        {
+                            "title": journal_title,
+                            "issn": issn,
+                            "volume": volume,
+                            "issue": issue,
+                            "pages": pages,
+                        }
+                    ),
                     "rs:content_html": presence(metadata.content),
                     "rs:image": presence(metadata.image),
                     "rs:generator": container.get("platform", None),
@@ -371,7 +384,7 @@ def write_inveniordm_list(metalist):
     return [write_inveniordm(item) for item in metalist.items]
 
 
-def push_inveniordm(metadata, host: str, token: str, legacy_key:str):
+def push_inveniordm(metadata, host: str, token: str, legacy_key: str):
     """Push record to InvenioRDM"""
 
     record = {}
@@ -382,8 +395,9 @@ def push_inveniordm(metadata, host: str, token: str, legacy_key:str):
         community_index = None
         if hasattr(metadata, "relations") and metadata.relations:
             for i, relation in enumerate(metadata.relations):
-                if (relation.get("type") == "IsPartOf" and
-                    relation.get("id", "").startswith("https://rogue-scholar.org/api/communities/")):
+                if relation.get("type") == "IsPartOf" and relation.get(
+                    "id", ""
+                ).startswith("https://rogue-scholar.org/api/communities/"):
                     slug = relation.get("id").split("/")[5]
                     community_id, _ = search_by_slug(slug, "blog", host, token)
                     if community_id:
@@ -413,7 +427,6 @@ def push_inveniordm(metadata, host: str, token: str, legacy_key:str):
         record["id"] = search_by_doi(doi_from_url(metadata.id), host, token)
 
         if record["id"] is not None:
-
             # Create draft record from published record
             record = edit_published_record(record, host, token)
 
@@ -443,9 +456,7 @@ def push_inveniordm(metadata, host: str, token: str, legacy_key:str):
 
                 community_id = search_by_slug(slug, "topic", host, token)
                 if community_id:
-                    record = add_record_to_community(
-                        record, host, token, community_id
-                    )
+                    record = add_record_to_community(record, host, token, community_id)
 
         # Add record to communities defined as IsPartOf relation in inveniordm metadata's RelatedIdentifiers
         related_identifiers = py_.get(input, "metadata.related_identifiers")
@@ -460,21 +471,19 @@ def push_inveniordm(metadata, host: str, token: str, legacy_key:str):
                     and len(path_parts) == 3
                     and path_parts[1] == "communities"
                 ):
-                    record = add_record_to_community(
-                        record, host, token, path_parts[2]
-                    )
+                    record = add_record_to_community(record, host, token, path_parts[2])
 
         # optionally update rogue-scholar legacy record
         if host == "rogue-scholar.org" and legacy_key is not None:
             record = update_legacy_record(record, legacy_key)
-
+        print("g", record)
     except Exception as e:
         raise InvenioRDMError(f"Unexpected error: {str(e)}")
 
     return record
 
 
-def push_inveniordm_list(metalist, host: str, token: str, legacy_key:str) -> list:
+def push_inveniordm_list(metalist, host: str, token: str, legacy_key: str) -> list:
     """Push inveniordm list to InvenioRDM, returns list of push results."""
 
     if metalist is None:
@@ -491,7 +500,9 @@ def search_by_doi(doi, host, token) -> Optional[str]:
     }
     params = {"q": f"doi:{doi}", "size": 1}
     try:
-        response = requests.get(f"https://{host}/api/records", headers=headers, params=params)
+        response = requests.get(
+            f"https://{host}/api/records", headers=headers, params=params
+        )
         response.raise_for_status()
         data = response.json()
         if py_.get(data, "hits.total") or 0 > 0:
@@ -508,14 +519,16 @@ def create_draft_record(record, host, token, input):
         "Content-Type": "application/json",
     }
     try:
-        response = requests.post(f"https://{host}/api/records", headers=headers, json=input)
+        response = requests.post(
+            f"https://{host}/api/records", headers=headers, json=input
+        )
         response.raise_for_status()
         data = response.json()
         return {
             "id": data.get("id", None),
             "created": data.get("created", None),
             "updated": data.get("updated", None),
-            "status": "updated"
+            "status": "updated",
         }
     except requests.exceptions.RequestException as e:
         raise InvenioRDMError(f"Error creating draft record: {str(e)}")
@@ -611,38 +624,37 @@ def update_legacy_record(record, legacy_key: str):
 
     if not legacy_key:
         return record, ValueError("no legacy key provided")
-
     if not record.get("uuid", None):
         return record, ValueError("no UUID provided")
-
-    now = f"{int(time())}"
-
     if not record.get("doi", None):
         return ValueError("no valid doi to update")
 
-    output = {
-            "doi": record["doi"],
+    now = f"{int(time())}"
+    if record.get("id", None) is not None:
+        output = {
+            "rid": record.get("id"),
+            "indexed_at": now,
+            "indexed": "true",
+            "archived": "true",
+        }
+    else:
+        output = {
+            "doi": record.get("doi"),
             "indexed_at": now,
             "indexed": "true",
-            "archived": "true"
+            "archived": "true",
         }
 
     request_url = f"https://{legacy_host}/rest/v1/posts?id=eq.{record['uuid']}"
-
     headers = {
         "Content-Type": "application/json",
         "apikey": legacy_key,
         "Authorization": f"Bearer {legacy_key}",
-        "Prefer": "return=minimal"
+        "Prefer": "return=minimal",
     }
 
     try:
-        response = requests.patch(
-            request_url,
-            json=output,
-            headers=headers,
-            timeout=30
-        )
+        response = requests.patch(request_url, json=output, headers=headers, timeout=30)
         response.raise_for_status()
         if response.status_code != 204:
             return record, Exception(f"Unexpected status code: {response.status_code}")
@@ -651,7 +663,7 @@ def update_legacy_record(record, legacy_key: str):
         return record
 
     except requests.exceptions.RequestException as e:
-        return record, e
+        raise InvenioRDMError(f"Error updating legacy record: {str(e)}")
 
 
 def search_by_slug(slug, type_value, host, token) -> Optional[str]:

{commonmeta_py-0.111 → commonmeta_py-0.113}/pyproject.toml

@@ -1,6 +1,6 @@
 [project]
 name = "commonmeta-py"
-version = "0.111"
+version = "0.113"
 description = "Library for conversions to/from the Commonmeta scholarly metadata format"
 authors = [{ name = "Martin Fenner", email = "martin@front-matter.io" }]
 requires-python = ">=3.9,<4.0"