commonmeta-py 0.117__tar.gz → 0.119__tar.gz

{commonmeta_py-0.117 → commonmeta_py-0.119}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: commonmeta-py
-Version: 0.117
+Version: 0.119
 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
@@ -36,7 +36,7 @@ Requires-Dist: pyyaml>=5.4
 Requires-Dist: requests-toolbelt>=1.0.0
 Requires-Dist: requests>=2.31.0
 Requires-Dist: requests>=2.32.3
-Requires-Dist: setuptools>=70.3.0
+Requires-Dist: setuptools<81,>=70.3.0
 Requires-Dist: simplejson~=3.18
 Requires-Dist: types-beautifulsoup4<5,>=4.11
 Requires-Dist: types-dateparser~=1.1

{commonmeta_py-0.117 → commonmeta_py-0.119}/commonmeta/__init__.py

@@ -10,7 +10,7 @@ commonmeta-py is a Python library to convert scholarly metadata
 """
 
 __title__ = "commonmeta-py"
-__version__ = "0.117"
+__version__ = "0.119"
 __author__ = "Martin Fenner"
 __license__ = "MIT"
 

{commonmeta_py-0.117 → commonmeta_py-0.119}/commonmeta/doi_utils.py

@@ -342,7 +342,6 @@ def is_rogue_scholar_doi(doi: str, ra: str = "crossref") -> bool:
 
 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 ""

{commonmeta_py-0.117 → commonmeta_py-0.119}/commonmeta/file_utils.py

@@ -44,16 +44,6 @@ def download_file(url: str) -> bytes:
     resp = requests.get(url, stream=True)
     resp.raise_for_status()
     return resp.content
-    # # Progress bar
-    # total = int(resp.headers.get("content-length", 0))
-
-    # buf = io.BytesIO()
-    # with tqdm(total=total, unit="B", unit_scale=True, desc="downloading") as bar:
-    #     for chunk in resp.iter_content(chunk_size=8192):
-    #         if chunk:
-    #             buf.write(chunk)
-    #             bar.update(len(chunk))
-    # return buf.getvalue()
 
 
 def write_file(filename: str, output: bytes) -> None:

{commonmeta_py-0.117 → commonmeta_py-0.119}/commonmeta/writers/crossref_xml_writer.py

@@ -1,6 +1,7 @@
 """Crossref XML writer for commonmeta-py"""
 
 import io
+import logging
 from datetime import datetime
 from time import time
 from typing import Optional
@@ -18,6 +19,8 @@ from ..constants import Commonmeta
 from ..doi_utils import doi_from_url, validate_doi
 from ..utils import validate_url
 
+logger = logging.getLogger(__name__)
+
 POSTED_CONTENT_TYPES = [
     "preprint",
     "working_paper",
@@ -342,20 +345,25 @@ def write_crossref_xml(metadata: Commonmeta) -> Optional[str]:
 
     data = convert_crossref_xml(metadata)
     if data is None:
+        logger.error(f"Could not convert metadata to Crossref XML: {metadata.id}")
         return None
+
+    # Use the marshmallow schema to dump the data
     schema = CrossrefXMLSchema()
     crossref_xml = schema.dump(data)
 
-    # Ensure the order of fields in the XML matches the expected order
+    # Ensure consistent field ordering through the defined mapping
     field_order = [MARSHMALLOW_MAP.get(k, k) for k in list(data.keys())]
     crossref_xml = {k: crossref_xml[k] for k in field_order if k in crossref_xml}
+
     # Convert to XML
     return unparse_xml(crossref_xml, dialect="crossref")
 
 
-def write_crossref_xml_list(metalist):
+def write_crossref_xml_list(metalist) -> Optional[str]:
     """Write crossref_xml list"""
     if metalist is None or not metalist.is_valid:
+        logger.error("Invalid metalist provided for Crossref XML generation")
         return None
 
     schema = CrossrefXMLSchema()
@@ -380,15 +388,17 @@ def push_crossref_xml_list(metalist, login_id: str, login_passwd: str) -> bytes:
     """Push crossref_xml list to Crossref API, returns the API response."""
 
     input = write_crossref_xml_list(metalist)
+    if not input:
+        logger.error("Failed to generate XML for upload")
+        return "{}"
 
     # Convert string to bytes if necessary
     if isinstance(input, str):
         input = input.encode("utf-8")
 
-    # The filename displayed in the Crossref admin interface, using the current UNIX timestamp
+    # The filename displayed in the Crossref admin interface
     filename = f"{int(time())}"
 
-    # Create multipart form data
     multipart_data = MultipartEncoder(
         fields={
             "fname": (filename, io.BytesIO(input), "application/xml"),
@@ -398,38 +408,32 @@ def push_crossref_xml_list(metalist, login_id: str, login_passwd: str) -> bytes:
         }
     )
 
-    # Set up the request
     post_url = "https://doi.crossref.org/servlet/deposit"
     headers = {"Content-Type": multipart_data.content_type}
+    resp = requests.post(post_url, data=multipart_data, headers=headers, timeout=10)
+    resp.raise_for_status()
+
+    # Parse the response
+    response = parse_xml(resp.content)
+    status = py_.get(response, "html.body.h2")
+    if status == "SUCCESS":
+        items = []
+        for item in metalist.items:
+            items.append(
+                {
+                    "doi": item.id,
+                    "updated": datetime.now().isoformat("T", "seconds"),
+                    "status": "submitted",
+                }
+            )
 
-    try:
-        # Send the request
-        resp = requests.post(post_url, data=multipart_data, headers=headers, timeout=10)
-        resp.raise_for_status()
-
-        # Parse the response
-        response = parse_xml(resp.content)
-        status = py_.get(response, "html.body.h2")
-        if status == "SUCCESS":
-            items = []
-            for item in metalist.items:
-                items.append(
-                    {
-                        "doi": item.id,
-                        "updated": datetime.now().isoformat("T", "seconds"),
-                        "status": "submitted",
-                    }
-                )
-
-            # orjson has different options
-            return json.dumps(items, option=json.OPT_INDENT_2)
-
-        # if there is an error
-        message = py_.get(response, "html.body.p")
-        raise CrossrefError(f"Error uploading batch: {message}")
+        # Return JSON response
+        return json.dumps(items, option=json.OPT_INDENT_2)
 
-    except requests.exceptions.RequestException as e:
-        raise CrossrefError(f"Error uploading batch: {str(e)}") from e
+    # Handle error response
+    message = py_.get(response, "html.body.p")
+    logger.error(f"Crossref API error: {message}")
+    return "{}"
 
 
 def get_attributes(obj, **kwargs) -> dict:
@@ -539,15 +543,16 @@ def get_institution(obj) -> Optional[dict]:
 def get_titles(obj) -> Optional[dict]:
     """get titles"""
 
-    title = {}
+    titles = {}
     for t in wrap(py_.get(obj, "titles", [])):
         if isinstance(t, str):
-            title["title"] = t
+            titles["title"] = t
         elif isinstance(t, dict) and t.get("titleType", None) == "Subtitle":
-            title["subtitle"] = t.get("title", None)
-        elif isinstance(title, dict):
-            title["title"] = t.get("title", None)
-    return title
+            titles["subtitle"] = t.get("title", None)
+        elif isinstance(t, dict):
+            titles["title"] = t.get("title", None)
+
+    return titles if titles else None
 
 
 def get_contributors(obj) -> Optional[dict]:

{commonmeta_py-0.117 → commonmeta_py-0.119}/commonmeta/writers/inveniordm_writer.py

@@ -1,8 +1,9 @@
 """InvenioRDM writer for commonmeta-py"""
 
+import logging
 import re
 from time import time
-from typing import Optional
+from typing import Dict, Optional
 from urllib.parse import urlparse
 
 import orjson as json
@@ -15,6 +16,7 @@ from ..constants import (
     COMMUNITY_TRANSLATIONS,
     CROSSREF_FUNDER_ID_TO_ROR_TRANSLATIONS,
     INVENIORDM_IDENTIFIER_TYPES,
+    Commonmeta,
 )
 from ..date_utils import get_iso8601_date
 from ..doi_utils import doi_from_url, normalize_doi
@@ -28,6 +30,7 @@ from ..utils import (
     validate_ror,
 )
 
+logger = logging.getLogger(__name__)
 
 def write_inveniordm(metadata):
     """Write inveniordm"""
@@ -384,30 +387,35 @@ 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: Commonmeta,
+        host: str,
+        token: str,
+        legacy_key: str
+    ) -> Dict:
     """Push record to InvenioRDM"""
 
     record = {}
-    input = write_inveniordm(metadata)
+    output = write_inveniordm(metadata)
 
     try:
         # Remove IsPartOf relation with InvenioRDM community identifier after storing it
-        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/"):
-                    slug = relation.get("id").split("/")[5]
-                    community_id, _ = search_by_slug(slug, "blog", host, token)
-                    if community_id:
-                        record["community"] = slug
-                        record["community_id"] = community_id
-                        community_index = i
-
-            # Remove the relation if we found and processed it
-            if community_index is not None and hasattr(metadata, "relations"):
-                metadata.relations.pop(community_index)
+        # 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/"):
+        #             slug = relation.get("id").split("/")[5]
+        #             community_id, _ = search_by_slug(slug, "blog", host, token)
+        #             if community_id:
+        #                 record["community"] = slug
+        #                 record["community_id"] = community_id
+        #                 community_index = i
+
+        #     # Remove the relation if we found and processed it
+        #     if community_index is not None and hasattr(metadata, "relations"):
+        #         metadata.relations.pop(community_index)
 
         # Remove InvenioRDM rid after storing it
         # rid_index = None
@@ -431,10 +439,10 @@ def push_inveniordm(metadata, host: str, token: str, legacy_key: str):
             record = edit_published_record(record, host, token)
 
             # Update draft record
-            record = update_draft_record(record, host, token, input)
+            record = update_draft_record(record, host, token, output)
         else:
             # Create draft record
-            record = create_draft_record(record, host, token, input)
+            record = create_draft_record(record, host, token, output)
 
         # Publish draft record
         record = publish_draft_record(record, host, token)
@@ -450,7 +458,8 @@ def push_inveniordm(metadata, host: str, token: str, legacy_key: str):
 
         if hasattr(metadata, "subjects"):
             for subject in metadata.subjects:
-                slug = string_to_slug(subject.get("subject", ""))
+                subject_name = subject.get("subject", "")
+                slug = string_to_slug(subject_name)
                 if slug in COMMUNITY_TRANSLATIONS:
                     slug = COMMUNITY_TRANSLATIONS[slug]
 
@@ -477,7 +486,11 @@ def push_inveniordm(metadata, host: str, token: str, legacy_key: str):
         if host == "rogue-scholar.org" and legacy_key is not None:
             record = update_legacy_record(record, legacy_key)
     except Exception as e:
-        print(f"Unexpected error: {str(e)}")
+        logger.error(f"Unexpected error in push_inveniordm: {str(e)}", exc_info=True, extra={
+            "host": host,
+            "record_id": record.get("id")
+        })
+        record["status"] = "error"
 
     return record
 
@@ -504,15 +517,15 @@ def search_by_doi(doi, host, token) -> Optional[str]:
         )
         response.raise_for_status()
         data = response.json()
-        if py_.get(data, "hits.total") or 0 > 0:
+        if py_.get(data, "hits.total", 0) > 0:
             return py_.get(data, "hits.hits.0.id")
         return None
     except requests.exceptions.RequestException as e:
-        print(f"Error searching for DOI: {str(e)}")
+        logger.error(f"Error searching for DOI {doi}: {str(e)}", exc_info=True)
         return None
 
 
-def create_draft_record(record, host, token, input):
+def create_draft_record(record, host, token, output):
     """Create a new draft record in InvenioRDM"""
     headers = {
         "Authorization": f"Bearer {token}",
@@ -520,23 +533,23 @@ def create_draft_record(record, host, token, input):
     }
     try:
         response = requests.post(
-            f"https://{host}/api/records", headers=headers, json=input
+            f"https://{host}/api/records", headers=headers, json=output
         )
         if response.status_code == 429:
             record["status"] = "failed_rate_limited"
             return record
         if response.status_code != 201:
-            print(response.json())
+            logger.error(f"Failed to create draft record: {response.status_code} - {response.json()}")
             record["status"] = "failed_create_draft"
             return record
         data = response.json()
-        record["id"]: data.get("id", None)
+        record["id"] = data.get("id", None)
         record["created"] = data.get("created", None)
         record["updated"] = data.get("updated", None)
         record["status"] = "draft"
         return record
     except requests.exceptions.RequestException as e:
-        print(f"Error creating draft record: {str(e)}")
+        logger.error(f"Error creating draft record: {str(e)}", exc_info=True)
         record["status"] = "error_draft"
         return record
 
@@ -557,7 +570,7 @@ def edit_published_record(record, host, token):
         record["status"] = "edited"
         return record
     except requests.exceptions.RequestException as e:
-        print(f"Error creating draft from published record: {str(e)}")
+        logger.error(f"Error creating draft from published record: {str(e)}", exc_info=True)
         record["status"] = "error_edit_published_record"
         return record
 
@@ -581,7 +594,7 @@ def update_draft_record(record, host, token, inveniordm_data):
         record["status"] = "updated"
         return record
     except requests.exceptions.RequestException as e:
-        print(f"Error updating draft record: {str(e)}")
+        logger.error(f"Error updating draft record: {str(e)}", exc_info=True)
         record["status"] = "error_update_draft_record"
         return record
 
@@ -604,8 +617,8 @@ def publish_draft_record(record, host, token):
             record["status"] = "failed_rate_limited"
             return record
         if response.status_code != 202:
-            print(response.json())
-            record["status"] = "failed_publish_draft"
+            logger.error(f"Failed to publish draft record: {response.status_code} - {response.json()}")
+            record["status"] = "error_publish_draft_record"
             return record
         data = response.json()
         record["uuid"] = py_.get(data, "metadata.identifiers.0.identifier")
@@ -614,7 +627,7 @@ def publish_draft_record(record, host, token):
         record["status"] = "published"
         return record
     except requests.exceptions.RequestException as e:
-        print(f"Error publishing draft record: {str(e)}")
+        logger.error(f"Error publishing draft record: {str(e)}", exc_info=True)
         record["status"] = "error_publish_draft_record"
         return record
 
@@ -634,7 +647,7 @@ def add_record_to_community(record, host, token, community_id):
         response.raise_for_status()
         return record
     except requests.exceptions.RequestException as e:
-        print(f"Error adding record to community: {str(e)}")
+        logger.error(f"Error adding record to community: {str(e)}", exc_info=True)
         return record
 
 
@@ -682,7 +695,7 @@ def update_legacy_record(record, legacy_key: str):
         return record
 
     except requests.exceptions.RequestException as e:
-        print(f"Error updating legacy record: {str(e)}")
+        logger.error(f"Error updating legacy record: {str(e)}", exc_info=True)
         record["status"] = "error_update_legacy_record"
         return record
 
@@ -700,11 +713,11 @@ def search_by_slug(slug, type_value, host, token) -> Optional[str]:
         )
         response.raise_for_status()
         data = response.json()
-        if py_.get(data, "hits.total") or 0 > 0:
+        if py_.get(data, "hits.total", 0) > 0:
             return py_.get(data, "hits.hits.0.id")
         return None
     except requests.exceptions.RequestException as e:
-        print(f"Error searching for community: {str(e)}")
+        logger.error(f"Error searching for community: {str(e)}", exc_info=True)
         return None
 
 

{commonmeta_py-0.117 → commonmeta_py-0.119}/pyproject.toml

@@ -1,6 +1,6 @@
 [project]
 name = "commonmeta-py"
-version = "0.117"
+version = "0.119"
 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"
@@ -52,7 +52,7 @@ dependencies = [
     "marshmallow-utils>=0.10.0",
     "xmlschema>=4.0.1",
     "requests-toolbelt>=1.0.0",
-    "setuptools>=70.3.0",
+    "setuptools>=70.3.0,<81",
 ]
 
 [project.urls]