commonmeta-py 0.124__py3-none-any.whl → 0.125__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__ = "0.124"
+__version__ = "0.125"
 __author__ = "Martin Fenner"
 __license__ = "MIT"
 

commonmeta/metadata.py

@@ -476,8 +476,9 @@ class MetadataList:
         elif to == "datacite":
             raise ValueError("Datacite not yet supported for metadata lists")
         elif to == "inveniordm":
+            kwargs = {"legacy_key": self.legacy_key}
             response = push_inveniordm_list(
-                self, host=self.host, token=self.token, legacy_key=self.legacy_key
+                self, host=self.host, token=self.token, **kwargs
             )
             return response
         else:

commonmeta/schema_utils.py

@@ -8,7 +8,9 @@ import xmlschema
 from jsonschema import Draft202012Validator, ValidationError
 
 
-def json_schema_errors(instance: Dict[str, Any], schema: str = "commonmeta") -> Optional[str]:
+def json_schema_errors(
+    instance: Dict[str, Any], schema: str = "commonmeta"
+) -> Optional[str]:
     """validate against JSON schema"""
     schema_map = {
         "commonmeta": "commonmeta_v0.16",
@@ -31,7 +33,9 @@ def json_schema_errors(instance: Dict[str, Any], schema: str = "commonmeta") ->
         return error.message
 
 
-def xml_schema_errors(instance: Union[str, bytes], schema: str = "crossref_xml") -> Optional[Union[bool, Exception]]:
+def xml_schema_errors(
+    instance: Union[str, bytes], schema: str = "crossref_xml"
+) -> Optional[Union[bool, Exception]]:
     """validate against XML schema"""
     schema_map = {
         "crossref_xml": "crossref5.4.0",

commonmeta/writers/crossref_xml_writer.py

@@ -385,7 +385,9 @@ def write_crossref_xml_list(metalist) -> Optional[str]:
     return unparse_xml_list(crossref_xml_list, dialect="crossref", head=head)
 
 
-def push_crossref_xml_list(metalist, login_id: str, login_passwd: str, legacy_key:str=None) -> bytes:
+def push_crossref_xml_list(
+    metalist, login_id: str, login_passwd: str, legacy_key: str = None
+) -> bytes:
     """Push crossref_xml list to Crossref API, returns the API response."""
 
     input = write_crossref_xml_list(metalist)
@@ -426,28 +428,21 @@ def push_crossref_xml_list(metalist, login_id: str, login_passwd: str, legacy_ke
     items = []
     for item in metalist.items:
         record = {
-                "doi": item.id,
-                "updated": datetime.now().isoformat("T", "seconds"),
-                "status": "submitted",
-            }
+            "doi": item.id,
+            "updated": datetime.now().isoformat("T", "seconds"),
+            "status": "submitted",
+        }
 
         # update rogue-scholar legacy record if legacy_key is provided
         if is_rogue_scholar_doi(item.id, ra="crossref") and legacy_key is not None:
-             record["uuid"] = py_.get(item, "identifiers.0.identifier")
-             record = update_legacy_record(record, legacy_key=legacy_key, field="doi")
+            record["uuid"] = py_.get(item, "identifiers.0.identifier")
+            record = update_legacy_record(record, legacy_key=legacy_key, field="doi")
         items.append(record)
 
     # Return JSON response
     return json.dumps(items, option=json.OPT_INDENT_2)
 
 
-
-
-
-
-
-
-
 def get_attributes(obj, **kwargs) -> dict:
     """Get root attributes"""
     return compact(

commonmeta/writers/inveniordm_writer.py

@@ -4,7 +4,6 @@ import logging
 import re
 from time import time
 from typing import Dict, Optional
-from urllib.parse import urlparse
 
 import orjson as json
 import pydash as py_
@@ -32,6 +31,7 @@ from ..utils import (
 
 logger = logging.getLogger(__name__)
 
+
 def write_inveniordm(metadata):
     """Write inveniordm"""
     if metadata is None or metadata.write_errors is not None:
@@ -387,123 +387,161 @@ def write_inveniordm_list(metalist):
     return [write_inveniordm(item) for item in metalist.items]
 
 
-def push_inveniordm(
-        metadata: Commonmeta,
-        host: str,
-        token: str,
-        legacy_key: str
-    ) -> Dict:
+def push_inveniordm(metadata: Commonmeta, host: str, token: str, **kwargs) -> Dict:
     """Push record to InvenioRDM"""
 
-    record = {}
-    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)
-
-        # Remove InvenioRDM rid after storing it
-        # rid_index = None
-        # if hasattr(metadata, "identifiers") and metadata.identifiers:
-        #     for i, identifier in enumerate(metadata.identifiers):
-        #         if identifier.get("identifierType") == "RID" and identifier.get("identifier"):
-        #             record["id"] = identifier.get("identifier")
-        #             rid_index = i
-        #         elif identifier.get("identifierType") == "UUID" and identifier.get("identifier"):
-        #             record["uuid"] = identifier.get("identifier")
-
-        # # Remove the identifier if we found and processed it
-        # if rid_index is not None and hasattr(metadata, "identifiers"):
-        #     metadata.identifiers.pop(rid_index)
-
-        # Check if record already exists in InvenioRDM
-        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)
-
-            # Update draft record
-            record = update_draft_record(record, host, token, output)
-        else:
-            # Create draft record
-            record = create_draft_record(record, host, token, output)
-
-        # Publish draft record
-        record = publish_draft_record(record, host, token)
-
-        # Add record to blog community if blog community is specified and exists
-        if record.get("community_id", None) is not None:
-            record = add_record_to_community(
-                record, host, token, record["community_id"]
-            )
-
-        # Add record to subject area community if subject area community is specified and exists
-        # Subject area communities should exist for all subjects in the FOSMappings
-
-        if hasattr(metadata, "subjects"):
-            for subject in metadata.subjects:
-                subject_name = subject.get("subject", "")
-                slug = string_to_slug(subject_name)
-                if slug in COMMUNITY_TRANSLATIONS:
-                    slug = COMMUNITY_TRANSLATIONS[slug]
-
-                community_id = search_by_slug(slug, "topic", host, token)
-                if 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")
+        doi = normalize_doi(metadata.id)
+        if doi is None:
+            raise ValueError("no doi provided")
 
-        for identifier in wrap(related_identifiers):
-            if py_.get(identifier, "relation_type.id") == "ispartof":
-                parsed_url = urlparse(identifier.get("identifier", ""))
-                path_parts = parsed_url.path.split("/")
+        record = {
+            "doi": doi,
+        }
 
-                if (
-                    parsed_url.netloc == urlparse(host).netloc
-                    and len(path_parts) == 3
-                    and path_parts[1] == "communities"
+        # extract optional information needed but not upserted to the InvenioRDM API:
+        # rid is the InvenioRDM record id,
+        # uuid is the Rogue Scholar uuid,
+        # community_id is the id of the primary community of the record
+        if hasattr(metadata, "identifiers") and metadata.identifiers:
+            rid_index = None
+            uuid_index = None
+            for i, identifier in enumerate(metadata.identifiers):
+                if identifier.get("identifierType") == "RID" and identifier.get(
+                    "identifier"
+                ):
+                    record["id"] = identifier.get("identifier")
+                    rid_index = i
+                elif identifier.get("identifierType") == "UUID" and identifier.get(
+                    "identifier"
                 ):
-                    record = add_record_to_community(record, host, token, path_parts[2])
+                    record["uuid"] = identifier.get("identifier")
+                    uuid_index = i
+            if rid_index is not None:
+                metadata.identifiers.pop(rid_index)
+            if uuid_index is not None:
+                metadata.identifiers.pop(rid_index)
+
+        if hasattr(metadata, "relations") and metadata.relations:
+            community_index = None
+            for i, relation in enumerate(metadata.relations):
+                if relation.get("type") == "IsPartOf" and relation.get(
+                    "id", ""
+                ).startswith(f"https://{host}/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
+
+            if community_index is not None:
+                metadata.relations.pop(community_index)
+
+        # upsert record via the InvenioRDM API
+        record = upsert_record(metadata, host, token, record)
+
+        # optionally add record to InvenioRDM communities
+        record = add_record_to_communities(metadata, host, token, record)
+
+        # optionally update external services
+        record = update_external_services(metadata, host, token, record, **kwargs)
 
-        # optionally update rogue-scholar legacy record
-        if host == "rogue-scholar.org" and legacy_key is not None:
-            record = update_legacy_record(record, legacy_key=legacy_key, field="rid")
     except Exception as e:
-        logger.error(f"Unexpected error in push_inveniordm: {str(e)}", exc_info=True, extra={
-            "host": host,
-            "record_id": record.get("id")
-        })
+        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
 
 
-def push_inveniordm_list(metalist, host: str, token: str, legacy_key: str) -> list:
+def push_inveniordm_list(metalist, host: str, token: str, **kwargs) -> list:
     """Push inveniordm list to InvenioRDM, returns list of push results."""
 
     if metalist is None:
         return None
-    items = [push_inveniordm(item, host, token, legacy_key) for item in metalist.items]
+    items = [push_inveniordm(item, host, token, **kwargs) for item in metalist.items]
     return json.dumps(items, option=json.OPT_INDENT_2)
 
 
+def upsert_record(metadata: Commonmeta, host: str, token: str, record: dict) -> dict:
+    """Upsert InvenioRDM record, based on DOI"""
+
+    output = write_inveniordm(metadata)
+
+    # Check if record already exists in InvenioRDM
+    record["id"] = search_by_doi(doi_from_url(record.get("doi")), host, token)
+
+    if record["id"] is not None:
+        # Create draft record from published record
+        record = edit_published_record(record, host, token)
+
+        # Update draft record
+        record = update_draft_record(record, host, token, output)
+    else:
+        # Create draft record
+        record = create_draft_record(record, host, token, output)
+
+    # Publish draft record
+    record = publish_draft_record(record, host, token)
+
+    return record
+
+
+def add_record_to_communities(
+    metadata: Commonmeta, host: str, token: str, record: dict
+) -> dict:
+    """Add record to one or more InvenioRDM communities"""
+
+    # Add record to primary community if primary community is specified
+    if record.get("community_id", None) is not None:
+        record = add_record_to_community(record, host, token, record["community_id"])
+
+    # Add record to subject area community if subject area community is specified
+    # Subject area communities should exist for all OECD subject areas
+
+    if hasattr(metadata, "subjects"):
+        for subject in metadata.subjects:
+            subject_name = subject.get("subject", "")
+            slug = string_to_slug(subject_name)
+            if slug in COMMUNITY_TRANSLATIONS:
+                slug = COMMUNITY_TRANSLATIONS[slug]
+
+            community_id = search_by_slug(slug, "topic", host, token)
+            if community_id:
+                record = add_record_to_community(record, host, token, community_id)
+
+    # Add record to communities defined as IsPartOf relation in InvenioRDM RelatedIdentifiers
+    if hasattr(metadata, "related_identifiers") and metadata.related_identifiers:
+        for identifier in metadata.related_identifiers:
+            if py_.get(identifier, "relation_type.id") == "ispartof" and identifier.get(
+                "identifier", ""
+            ).startswith(f"https://{host}/api/communities/"):
+                slug = identifier.get("identifier").split("/")[5]
+                community_id = search_by_slug(slug, "topic", host, token)
+                if community_id:
+                    record = add_record_to_community(record, host, token, community_id)
+
+    return record
+
+
+def update_external_services(
+    metadata: Commonmeta, host: str, token: str, record: dict, **kwargs
+) -> dict:
+    """Update external services with changes in InvenioRDM"""
+
+    # optionally update rogue-scholar legacy record
+    if host == "rogue-scholar.org" and kwargs.get("legacy_key", None) is not None:
+        record = update_legacy_record(
+            record, legacy_key=kwargs.get("legacy_key"), field="rid"
+        )
+
+    return record
+
+
 def search_by_doi(doi, host, token) -> Optional[str]:
     """Search for a record by DOI in InvenioRDM"""
     headers = {
@@ -539,7 +577,9 @@ def create_draft_record(record, host, token, output):
             record["status"] = "failed_rate_limited"
             return record
         if response.status_code != 201:
-            logger.error(f"Failed to create draft record: {response.status_code} - {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()
@@ -570,7 +610,9 @@ def edit_published_record(record, host, token):
         record["status"] = "edited"
         return record
     except requests.exceptions.RequestException as e:
-        logger.error(f"Error creating draft from published record: {str(e)}", exc_info=True)
+        logger.error(
+            f"Error creating draft from published record: {str(e)}", exc_info=True
+        )
         record["status"] = "error_edit_published_record"
         return record
 
@@ -616,12 +658,14 @@ def publish_draft_record(record, host, token):
             record["status"] = "failed_rate_limited"
             return record
         if response.status_code != 202:
-            logger.error(f"Failed to publish draft record: {response.status_code} - {response.json()}")
+            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")
-        record["doi"] =  doi_as_url(py_.get(data, "pids.doi.identifier")),
+        record["doi"] = (doi_as_url(py_.get(data, "pids.doi.identifier")),)
         record["created"] = data.get("created", None)
         record["updated"] = data.get("updated", None)
         record["status"] = "published"
@@ -651,7 +695,7 @@ def add_record_to_community(record, host, token, community_id):
         return record
 
 
-def update_legacy_record(record, legacy_key: str, field:str=None) -> dict:
+def update_legacy_record(record, legacy_key: str, field: str = None) -> dict:
     """Update corresponding record in Rogue Scholar legacy database."""
 
     legacy_host = "bosczcmeodcrajtcaddf.supabase.co"
@@ -678,7 +722,7 @@ def update_legacy_record(record, legacy_key: str, field:str=None) -> dict:
             }
         else:
             print(f"nothing to update for id {record.get('uuid')}")
-            return record # nothing to update
+            return record  # nothing to update
 
         request_url = f"https://{legacy_host}/rest/v1/posts?id=eq.{record['uuid']}"
         headers = {
@@ -700,7 +744,7 @@ def update_legacy_record(record, legacy_key: str, field:str=None) -> dict:
         return record
 
 
-def search_by_slug(slug, type_value, host, token) -> Optional[str]:
+def search_by_slug(slug: str, type_value: str, host: str, token: str) -> Optional[str]:
     """Search for a community by slug in InvenioRDM"""
     headers = {
         "Authorization": f"Bearer {token}",

{commonmeta_py-0.124.dist-info → commonmeta_py-0.125.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: commonmeta-py
-Version: 0.124
+Version: 0.125
 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-0.124.dist-info → commonmeta_py-0.125.dist-info}/RECORD

@@ -1,4 +1,4 @@
-commonmeta/__init__.py,sha256=pp3RcQ6mEgusaIHYnKMwYYMDh-6dGBRUhu2jP0ecdHw,2098
+commonmeta/__init__.py,sha256=kDEzO2vW7BmMnXyZBc8T6XAN6gxwn0MRTRDOeTYdME8,2098
 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
@@ -7,8 +7,8 @@ commonmeta/constants.py,sha256=wSTEUiHeRdXLwjXEQD9AU2hxFyEKi5OTX2iHOKO6nF0,19844
 commonmeta/date_utils.py,sha256=H2cCobX0JREIUOT_cCigGd3MG7prGiQpXk1m4ZNrFwU,6318
 commonmeta/doi_utils.py,sha256=cOogLatKg6qea2jgMd3yLALSTfaTNUgr-IkBXIK4xZw,11498
 commonmeta/file_utils.py,sha256=eFYDWyR8Gr722nvFmp542hCm-TGmO_q4ciZ85IPHpjA,2893
-commonmeta/metadata.py,sha256=_N9suKA10uiWU5-3a349x-H9VbhzEZ6rQ1PqXOCiinA,18408
-commonmeta/schema_utils.py,sha256=O6OxiySUrvnNJvslJLY86RFu2HldrZFi21OaLXnV3mA,1912
+commonmeta/metadata.py,sha256=90aTe47d071wHxwcNsOqU5lSVPKP8wAPnPHhddj3Fuo,18443
+commonmeta/schema_utils.py,sha256=zn3gqAHciUOQmrw9okR68weFs-yqPPyORFt-Zl1D3Lw,1924
 commonmeta/translators.py,sha256=CBMK4jrXRmGZiAhCh6wsJjhbDJWbcsda8UvXFXxccAw,1363
 commonmeta/utils.py,sha256=pJnh3EzOU1E2nutnAZsopY_NsUX6zYmxoj5bIYqqWvE,50574
 commonmeta/readers/__init__.py,sha256=vOf7UsOKNoh_ZCuyexxhAmPMt8wjB-pF_CfpWRaN8pk,45
@@ -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=cGrX9vacNwDdK7TbH1RWig68SH8hg5VusuqkI9gU1DY,33931
+commonmeta/writers/crossref_xml_writer.py,sha256=rcPOfrGxU4mX7_fFywYWDW2FFUoKW9wD-JzW8nX1ipI,33915
 commonmeta/writers/csl_writer.py,sha256=4gDYs1EzK4_L2UIRTfs25wgHmYRwdRP2zmfxF9387oU,2779
 commonmeta/writers/datacite_writer.py,sha256=bcinpwhq7XnVthKHH8-sdXA34dSlvFH4ImYH768iaQU,6428
-commonmeta/writers/inveniordm_writer.py,sha256=2CD2XYThHgZhUUeVVzZU6A_p6lOz7Xdt0Ij4Zy_E1PM,25772
+commonmeta/writers/inveniordm_writer.py,sha256=ARNssMUhwckAGwzz2ugJoLjVSTezbyLrK2c-utdmins,26795
 commonmeta/writers/ris_writer.py,sha256=3SdyEvMRaPRP1SV1MB-MXBlunE7x6og7RF1zuWtetPc,2094
 commonmeta/writers/schema_org_writer.py,sha256=s18_x0ReXwAGBoEAwp2q-HCgFQ-h5qRg6JyAlqCoSFE,5871
-commonmeta_py-0.124.dist-info/METADATA,sha256=t0hoWqdbSD8HDjdOpJtoxhjb9_coYI_z9wBMgN5VZIU,7656
-commonmeta_py-0.124.dist-info/WHEEL,sha256=qtCwoSJWgHk21S1Kb4ihdzI2rlJ1ZKaIurTj_ngOhyQ,87
-commonmeta_py-0.124.dist-info/entry_points.txt,sha256=U4w4BoRuS3rN5t5Y-uYSyOeU5Lh_VRVMS9OIDzIgw4w,50
-commonmeta_py-0.124.dist-info/licenses/LICENSE,sha256=wsIvxF9Q9GC9vA_s79zTWP3BkXJdfUNRmALlU8GbW1s,1074
-commonmeta_py-0.124.dist-info/RECORD,,
+commonmeta_py-0.125.dist-info/METADATA,sha256=x7HcPVeiOM03np_p5URA_xH84RGt-8HO7tF3oV7xoB4,7656
+commonmeta_py-0.125.dist-info/WHEEL,sha256=qtCwoSJWgHk21S1Kb4ihdzI2rlJ1ZKaIurTj_ngOhyQ,87
+commonmeta_py-0.125.dist-info/entry_points.txt,sha256=U4w4BoRuS3rN5t5Y-uYSyOeU5Lh_VRVMS9OIDzIgw4w,50
+commonmeta_py-0.125.dist-info/licenses/LICENSE,sha256=wsIvxF9Q9GC9vA_s79zTWP3BkXJdfUNRmALlU8GbW1s,1074
+commonmeta_py-0.125.dist-info/RECORD,,