commonmeta-py 0.126__tar.gz → 0.128__tar.gz

{commonmeta_py-0.126 → commonmeta_py-0.128}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: commonmeta-py
-Version: 0.126
+Version: 0.128
 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-0.126 → commonmeta_py-0.128}/commonmeta/__init__.py

@@ -10,7 +10,7 @@ commonmeta-py is a Python library to convert scholarly metadata
 """
 
 __title__ = "commonmeta-py"
-__version__ = "0.126"
+__version__ = "0.128"
 __author__ = "Martin Fenner"
 __license__ = "MIT"
 
@@ -96,6 +96,7 @@ from .utils import (
     normalize_url,
     pages_as_string,
     replace_curie,
+    string_to_slug,
     to_csl,
     validate_orcid,
     validate_ror,

{commonmeta_py-0.126 → commonmeta_py-0.128}/commonmeta/utils.py

@@ -128,6 +128,57 @@ FOS_MAPPINGS = {
     "Other humanities": "http://www.oecd.org/science/inno/38235147.pdf?6.5",
 }
 
+FOS_TO_STRING_MAPPINGS = {
+    "Natural sciences": "naturalSciences",
+    "Mathematics": "mathematics",
+    "Computer and information sciences": "computerAndInformationSciences",
+    "Physical sciences": "physicalSciences",
+    "Chemical sciences": "chemicalSciences",
+    "Earth and related environmental sciences": "earthAndRelatedEnvironmentalSciences",
+    "Biological sciences": "biologicalSciences",
+    "Other natural sciences": "otherNaturalSciences",
+    "Engineering and technology": "engineeringAndTechnology",
+    "Civil engineering": "civilEngineering",
+    "Electrical engineering, electronic engineering, information engineering": "electricalEngineering",
+    "Mechanical engineering": "mechanicalEngineering",
+    "Chemical engineering": "chemicalEngineering",
+    "Materials engineering": "materialsEngineering",
+    "Medical engineering": "medicalEngineering",
+    "Environmental engineering": "environmentalEngineering",
+    "Environmental biotechnology": "environmentalBiotechnology",
+    "Industrial biotechnology": "industrialBiotechnology",
+    "Nano technology": "nanoTechnology",
+    "Other engineering and technologies": "otherEngineeringAndTechnologies",
+    "Medical and health sciences": "medicalAndHealthSciences",
+    "Basic medicine": "basicMedicine",
+    "Clinical medicine": "clinicalMedicine",
+    "Health sciences": "healthSciences",
+    "Health biotechnology": "healthBiotechnology",
+    "Other medical sciences": "otherMedicalSciences",
+    "Agricultural sciences": "agriculturalSciences",
+    "Agriculture, forestry, and fisheries": "agricultureForestryAndFisheries",
+    "Animal and dairy science": "animalAndDairyScience",
+    "Veterinary science": "veterinaryScience",
+    "Agricultural biotechnology": "agriculturalBiotechnology",
+    "Other agricultural sciences": "otherAgriculturalSciences",
+    "Social science": "socialScience",
+    "Psychology": "psychology",
+    "Economics and business": "economicsAndBusiness",
+    "Educational sciences": "educationalSciences",
+    "Sociology": "sociology",
+    "Law": "law",
+    "Political science": "politicalScience",
+    "Social and economic geography": "socialAndEconomicGeography",
+    "Media and communications": "mediaAndCommunications",
+    "Other social sciences": "otherSocialSciences",
+    "Humanities": "humanities",
+    "History and archaeology": "historyAndArchaeology",
+    "Languages and literature": "languagesAndLiterature",
+    "Philosophy, ethics and religion": "philosophyEthicsAndReligion",
+    "Arts (arts, history of arts, performing arts, music)": "artsArtsHistoryOfArtsPerformingArtsMusic",
+    "Other humanities": "otherHumanities",
+}
+
 
 def normalize_id(pid: Optional[str], **kwargs) -> Optional[str]:
     """Check for valid DOI or HTTP(S) URL"""
@@ -1274,6 +1325,21 @@ def subjects_as_string(subjects):
     return ", ".join(keywords)
 
 
+def string_to_slug(text: str) -> str:
+    """Makes a string lowercase and removes non-alphanumeric characters"""
+
+    # Remove optional FOS (Fields of Science) prefix
+    text = text.removeprefix("FOS: ")
+
+    # Convert to lowercase and keep only letters and numbers
+    result = ""
+    for char in text:
+        if char.isalnum():
+            result += char.lower()
+
+    return result
+
+
 # def reverse():
 #       return { 'citation': wrap(related_identifiers).select do |ri|
 #                         ri['relationType'] == 'IsReferencedBy'

{commonmeta_py-0.126 → commonmeta_py-0.128}/commonmeta/writers/inveniordm_writer.py

@@ -1,7 +1,6 @@
 """InvenioRDM writer for commonmeta-py"""
 
 import logging
-import re
 from time import time
 from typing import Dict, Optional
 
@@ -18,13 +17,14 @@ from ..constants import (
     Commonmeta,
 )
 from ..date_utils import get_iso8601_date
-from ..doi_utils import doi_as_url, doi_from_url, normalize_doi
+from ..doi_utils import doi_from_url, normalize_doi
 from ..utils import (
     FOS_MAPPINGS,
     get_language,
     id_from_url,
     normalize_url,
     pages_as_string,
+    string_to_slug,
     validate_orcid,
     validate_ror,
 )
@@ -399,28 +399,17 @@ def push_inveniordm(metadata: Commonmeta, host: str, token: str, **kwargs) -> Di
             "doi": doi,
         }
 
-        # 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
+        # extract optional information needed
+        # uuid is the Rogue Scholar uuid
+        # community_id is the id of the primary community of the record,
+        # in the case of Rogue Scholar the blog community
+
         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(
+                if identifier.get("identifierType") == "UUID" and identifier.get(
                     "identifier"
                 ):
                     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(uuid_index)
 
         if hasattr(metadata, "relations") and metadata.relations:
             community_index = None
@@ -434,6 +423,7 @@ def push_inveniordm(metadata: Commonmeta, host: str, token: str, **kwargs) -> Di
                         record["community"] = slug
                         record["community_id"] = community_id
                         community_index = i
+                        break
 
             if community_index is not None:
                 metadata.relations.pop(community_index)
@@ -496,8 +486,14 @@ def add_record_to_communities(
 ) -> dict:
     """Add record to one or more InvenioRDM communities"""
 
+    communities = get_record_communities(record, host, token)
+    community_ids = [c.get("id") for c in communities] if communities else []
+
     # Add record to primary community if primary community is specified
-    if record.get("community_id", None) is not None:
+    if (
+        record.get("community_id", None) is not None
+        and record.get("community_id") not in community_ids
+    ):
         record = add_record_to_community(record, host, token, record["community_id"])
 
     # Add record to subject area community if subject area community is specified
@@ -509,9 +505,8 @@ def add_record_to_communities(
             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:
+            if community_id and community_id not in community_ids:
                 record = add_record_to_community(record, host, token, community_id)
 
     # Add record to communities defined as IsPartOf relation in InvenioRDM RelatedIdentifiers
@@ -522,7 +517,7 @@ def add_record_to_communities(
             ).startswith(f"https://{host}/api/communities/"):
                 slug = identifier.get("identifier").split("/")[5]
                 community_id = search_by_slug(slug, "topic", host, token)
-                if community_id:
+                if community_id and community_id not in community_ids:
                     record = add_record_to_community(record, host, token, community_id)
 
     return record
@@ -664,8 +659,6 @@ def publish_draft_record(record, host, token):
             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["created"] = data.get("created", None)
         record["updated"] = data.get("updated", None)
         record["status"] = "published"
@@ -676,17 +669,39 @@ def publish_draft_record(record, host, token):
         return record
 
 
+def get_record_communities(record, host, token):
+    """Get record communities by id"""
+    headers = {
+        "Authorization": f"Bearer {token}",
+        "Content-Type": "application/json",
+    }
+    try:
+        response = requests.get(
+            f"https://{host}/api/records/{record['id']}/communities",
+            headers=headers,
+        )
+        response.raise_for_status()
+        data = response.json()
+        if py_.get(data, "hits.total", 0) > 0:
+            return py_.get(data, "hits.hits")
+        return None
+    except requests.exceptions.RequestException as e:
+        logger.error(f"Error getting communities: {str(e)}", exc_info=True)
+        return None
+
+
 def add_record_to_community(record, host, token, community_id):
-    """Add a record to a community in InvenioRDM"""
+    """Add a record to a community"""
     headers = {
         "Authorization": f"Bearer {token}",
         "Content-Type": "application/json",
     }
+    json = {"communities": [{"id": community_id}]}
     try:
         response = requests.post(
             f"https://{host}/api/records/{record['id']}/communities",
             headers=headers,
-            json={"id": community_id},
+            json=json,
         )
         response.raise_for_status()
         return record
@@ -744,13 +759,13 @@ def update_legacy_record(record, legacy_key: str, field: str = None) -> dict:
         return record
 
 
-def search_by_slug(slug: str, type_value: str, host: str, token: str) -> Optional[str]:
+def search_by_slug(slug: str, type: str, host: str, token: str) -> Optional[str]:
     """Search for a community by slug in InvenioRDM"""
     headers = {
         "Authorization": f"Bearer {token}",
         "Content-Type": "application/json",
     }
-    params = {"q": f"slug:{slug} AND type:{type_value}", "size": 1}
+    params = [("q", f"slug:{slug}"), ("type", type), ("type", "subject"), ("size", 1)]
     try:
         response = requests.get(
             f"https://{host}/api/communities", headers=headers, params=params
@@ -765,18 +780,5 @@ def search_by_slug(slug: str, type_value: str, host: str, token: str) -> Optiona
         return None
 
 
-def string_to_slug(text):
-    """makes a string lowercase and removes non-alphanumeric characters"""
-    # Replace spaces with hyphens
-    slug = re.sub(r"\s+", "-", text.lower())
-    # Remove special characters
-    slug = re.sub(r"[^a-z0-9-]", "", slug)
-    # Remove multiple consecutive hyphens
-    slug = re.sub(r"-+", "-", slug)
-    # Remove leading and trailing hyphens
-    slug = slug.strip("-")
-    return slug
-
-
 class InvenioRDMError(Exception):
     """Custom exception for InvenioRDM API errors"""

{commonmeta_py-0.126 → commonmeta_py-0.128}/pyproject.toml

@@ -1,6 +1,6 @@
 [project]
 name = "commonmeta-py"
-version = "0.126"
+version = "0.128"
 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"