esgvoc 0.3.0__py3-none-any.whl → 0.4.0__py3-none-any.whl

esgvoc/core/db/project_ingestion.py

@@ -1,21 +1,22 @@
 import logging
 from pathlib import Path
 
-import esgvoc.core.constants
-from esgvoc.core.data_handler import JsonLdResource
-from esgvoc.core.db.connection import DBConnection
-from esgvoc.core.service.data_merger import DataMerger
-from esgvoc.core.db.models.mixins import TermKind
 from pydantic import BaseModel
+from sqlalchemy import text
 
+import esgvoc.core.constants
 import esgvoc.core.db.connection as db
-from esgvoc.core.db.connection import read_json_file
+import esgvoc.core.service as service
+from esgvoc.core.data_handler import JsonLdResource
+from esgvoc.core.db.connection import DBConnection, read_json_file
+from esgvoc.core.db.models.mixins import TermKind
 from esgvoc.core.db.models.project import Collection, Project, PTerm
-import  esgvoc.core.service as service
-
+from esgvoc.core.exceptions import EsgvocDbError
+from esgvoc.core.service.data_merger import DataMerger
 
 _LOGGER = logging.getLogger("project_ingestion")
 
+
 def infer_term_kind(json_specs: dict) -> TermKind:
     if esgvoc.core.constants.PATTERN_JSON_KEY in json_specs:
         return TermKind.PATTERN
@@ -25,15 +26,16 @@ def infer_term_kind(json_specs: dict) -> TermKind:
         return TermKind.PLAIN
 
 
-def ingest_metadata_project(connection:DBConnection,git_hash):
+def ingest_metadata_project(connection: DBConnection, git_hash):
     with connection.create_session() as session:
-        project = Project(id=str(connection.file_path.stem), git_hash=git_hash,specs={})
-        session.add(project)    
+        project = Project(id=str(connection.file_path.stem), git_hash=git_hash, specs={})
+        session.add(project)
         session.commit()
 
-###############################
+
 def get_data_descriptor_id_from_context(collection_context: dict) -> str:
-    data_descriptor_url = collection_context[esgvoc.core.constants.CONTEXT_JSON_KEY][esgvoc.core.constants.DATA_DESCRIPTOR_JSON_KEY]
+    data_descriptor_url = collection_context[esgvoc.core.constants.CONTEXT_JSON_KEY]\
+                                            [esgvoc.core.constants.DATA_DESCRIPTOR_JSON_KEY] # noqa E211
     return Path(data_descriptor_url).name
 
 
@@ -50,40 +52,40 @@ def instantiate_project_term(universe_term_json_specs: dict,
 def ingest_collection(collection_dir_path: Path,
                       project: Project,
                       project_db_session) -> None:
-
-
     collection_id = collection_dir_path.name
     collection_context_file_path = collection_dir_path.joinpath(esgvoc.core.constants.CONTEXT_FILENAME)
     try:
         collection_context = read_json_file(collection_context_file_path)
         data_descriptor_id = get_data_descriptor_id_from_context(collection_context)
     except Exception as e:
-        msg = f'Unable to read project context file {collection_context_file_path}. Abort.'
+        msg = f'unable to read project context file {collection_context_file_path}'
         _LOGGER.fatal(msg)
-        raise RuntimeError(msg) from e
+        raise EsgvocDbError(msg) from e
     # [KEEP]
     collection = Collection(
         id=collection_id,
         context=collection_context,
         project=project,
         data_descriptor_id=data_descriptor_id,
-        term_kind="") # we ll know it only when we ll add a term (hypothesis all term have the same kind in a collection
+        term_kind="")  # We ll know it only when we ll add a term
+                       # (hypothesis all term have the same kind in a collection) # noqa E116
     term_kind_collection = None
 
     for term_file_path in collection_dir_path.iterdir():
         _LOGGER.debug(f"found term path : {term_file_path}")
-        if term_file_path.is_file() and term_file_path.suffix==".json": 
+        if term_file_path.is_file() and term_file_path.suffix == ".json":
             try:
-                json_specs = DataMerger(data=JsonLdResource(uri =str(term_file_path)),
+                locally_avail = {"https://espri-mod.github.io/mip-cmor-tables":
+                                 service.current_state.universe.local_path}
+                json_specs = DataMerger(data=JsonLdResource(uri=str(term_file_path)),
                                         # locally_available={"https://espri-mod.github.io/mip-cmor-tables":".cache/repos/WCRP-universe"}).merge_linked_json()[-1]
-                                        locally_available={"https://espri-mod.github.io/mip-cmor-tables":service.current_state.universe.local_path}).merge_linked_json()[-1]
-
+                                        locally_available=locally_avail).merge_linked_json()[-1]
                 term_kind = infer_term_kind(json_specs)
                 term_id = json_specs["id"]
 
                 if term_kind_collection is None:
                     term_kind_collection = term_kind
-                
+
             except Exception as e:
                 _LOGGER.warning(f'Unable to read term {term_file_path}. Skip.\n{str(e)}')
                 continue
@@ -105,51 +107,63 @@ def ingest_collection(collection_dir_path: Path,
         collection.term_kind = term_kind_collection
     project_db_session.add(collection)
 
+
 def ingest_project(project_dir_path: Path,
                    project_db_file_path: Path,
-                   git_hash : str
+                   git_hash: str
                    ):
     try:
         project_connection = db.DBConnection(project_db_file_path)
     except Exception as e:
-        msg = f'Unable to read project SQLite file at {project_db_file_path}. Abort.'
+        msg = f'unable to read project SQLite file at {project_db_file_path}'
         _LOGGER.fatal(msg)
-        raise RuntimeError(msg) from e
-        
+        raise EsgvocDbError(msg) from e
+
     with project_connection.create_session() as project_db_session:
+        project_specs_file_path = project_dir_path.joinpath(esgvoc.core.constants.PROJECT_SPECS_FILENAME)
         try:
-            project_specs_file_path = project_dir_path.joinpath(esgvoc.core.constants.PROJECT_SPECS_FILENAME)
             project_json_specs = read_json_file(project_specs_file_path)
             project_id = project_json_specs[esgvoc.core.constants.PROJECT_ID_JSON_KEY]
         except Exception as e:
-            msg = f'Unable to read project specs file  {project_specs_file_path}. Abort.'
+            msg = f'unable to read project specs file  {project_specs_file_path}'
             _LOGGER.fatal(msg)
-            raise RuntimeError(msg) from e
-        
-        project = Project(id=project_id, specs=project_json_specs,git_hash=git_hash)
+            raise EsgvocDbError(msg) from e
+
+        project = Project(id=project_id, specs=project_json_specs, git_hash=git_hash)
         project_db_session.add(project)
-        
 
         for collection_dir_path in project_dir_path.iterdir():
-            if collection_dir_path.is_dir() and (collection_dir_path / "000_context.jsonld").exists(): #TODO maybe put that in settings
+            # TODO maybe put that in settings
+            if collection_dir_path.is_dir() and (collection_dir_path / "000_context.jsonld").exists():
                 _LOGGER.debug(f"found collection dir : {collection_dir_path}")
                 try:
                     ingest_collection(collection_dir_path,
                                       project,
                                       project_db_session)
                 except Exception as e:
-                    msg = f'Unexpected error while ingesting collection {collection_dir_path}. Abort.'
+                    msg = f'unexpected error while ingesting collection {collection_dir_path}'
                     _LOGGER.fatal(msg)
-                    raise RuntimeError(msg) from e
+                    raise EsgvocDbError(msg) from e
         project_db_session.commit()
 
-
-
-
-
-
-
-
-
-
-
+        # Well, the following instructions are not data duplication. It is more building an index.
+        # Read: https://sqlite.org/fts5.html
+        try:
+            sql_query = 'INSERT INTO pterms_fts5(pk, id, specs, kind, collection_pk) ' + \
+                        'SELECT pk, id, specs, kind, collection_pk FROM pterms;'  # noqa: S608
+            project_db_session.exec(text(sql_query))  # type: ignore
+        except Exception as e:
+            msg = f'unable to insert rows into pterms_fts5 table for {project_db_file_path}'
+            _LOGGER.fatal(msg)
+            raise EsgvocDbError(msg) from e
+        project_db_session.commit()
+        try:
+            sql_query = 'INSERT INTO pcollections_fts5(pk, id, data_descriptor_id, context, ' + \
+                         'project_pk, term_kind) SELECT pk, id, data_descriptor_id, context, ' + \
+                         'project_pk, term_kind FROM collections;'  # noqa: S608
+            project_db_session.exec(text(sql_query))  # type: ignore
+        except Exception as e:
+            msg = f'unable to insert rows into pcollections_fts5 table for {project_db_file_path}'
+            _LOGGER.fatal(msg)
+            raise EsgvocDbError(msg) from e
+        project_db_session.commit()

esgvoc/core/db/universe_ingestion.py

@@ -1,20 +1,22 @@
 import logging
 from pathlib import Path
 
-import esgvoc.core.constants
-from esgvoc.core.data_handler import JsonLdResource
-from esgvoc.core.service.data_merger import DataMerger
+from sqlalchemy import text
 from sqlmodel import Session, select
 
+import esgvoc.core.constants
 import esgvoc.core.db.connection as db
+import esgvoc.core.service as service
+from esgvoc.core.data_handler import JsonLdResource
 from esgvoc.core.db.connection import read_json_file
 from esgvoc.core.db.models.mixins import TermKind
-from esgvoc.core.db.models.universe import UDataDescriptor, UTerm, Universe
-from esgvoc.core.db.models.universe import universe_create_db
-import esgvoc.core.service as service
+from esgvoc.core.db.models.universe import UDataDescriptor, Universe, UTerm, universe_create_db
+from esgvoc.core.exceptions import EsgvocDbError
+from esgvoc.core.service.data_merger import DataMerger
 
 _LOGGER = logging.getLogger(__name__)
 
+
 def infer_term_kind(json_specs: dict) -> TermKind:
     if esgvoc.core.constants.PATTERN_JSON_KEY in json_specs:
         return TermKind.PATTERN
@@ -32,25 +34,48 @@ def ingest_universe(universe_repo_dir_path: Path, universe_db_file_path: Path) -
         _LOGGER.fatal(msg)
         raise IOError(msg) from e
 
-    for data_descriptor_dir_path in universe_repo_dir_path.iterdir(): 
-        if data_descriptor_dir_path.is_dir() and (data_descriptor_dir_path / "000_context.jsonld").exists(): # TODO maybe put that in setting
+    for data_descriptor_dir_path in universe_repo_dir_path.iterdir():
+        if data_descriptor_dir_path.is_dir() and \
+           (data_descriptor_dir_path / "000_context.jsonld").exists():  # TODO may be put that in setting
             try:
                 ingest_data_descriptor(data_descriptor_dir_path, connection)
             except Exception as e:
-                msg = f'Unexpected error while processing data descriptor {data_descriptor_dir_path}. Abort.'
+                msg = f'unexpected error while processing data descriptor {data_descriptor_dir_path}'
                 _LOGGER.fatal(msg)
-                raise RuntimeError(msg) from e
-        
-def ingest_metadata_universe(connection,git_hash):
+                raise EsgvocDbError(msg) from e
+
+    with connection.create_session() as session:
+        # Well, the following instructions are not data duplication. It is more building an index.
+        # Read: https://sqlite.org/fts5.html
+        try:
+            sql_query = 'INSERT INTO uterms_fts5(pk, id, specs, kind, data_descriptor_pk) ' + \
+                        'SELECT pk, id, specs, kind, data_descriptor_pk FROM uterms;'  # noqa: S608
+            session.exec(text(sql_query))  # type: ignore
+        except Exception as e:
+            msg = f'unable to insert rows into uterms_fts5 table for {universe_db_file_path}'
+            _LOGGER.fatal(msg)
+            raise EsgvocDbError(msg) from e
+        session.commit()
+        try:
+            sql_query = 'INSERT INTO udata_descriptors_fts5(pk, id, universe_pk, context, term_kind) ' + \
+                        'SELECT pk, id, universe_pk, context, term_kind FROM udata_descriptors;'  # noqa: S608
+            session.exec(text(sql_query))  # type: ignore
+        except Exception as e:
+            msg = f'unable to insert rows into udata_descriptors_fts5 table for {universe_db_file_path}'
+            _LOGGER.fatal(msg)
+            raise EsgvocDbError(msg) from e
+        session.commit()
+
+
+def ingest_metadata_universe(connection, git_hash):
     with connection.create_session() as session:
         universe = Universe(git_hash=git_hash)
-        session.add(universe)    
+        session.add(universe)
         session.commit()
 
+
 def ingest_data_descriptor(data_descriptor_path: Path,
                            connection: db.DBConnection) -> None:
-
-
     data_descriptor_id = data_descriptor_path.name
 
     context_file_path = data_descriptor_path.joinpath(esgvoc.core.constants.CONTEXT_FILENAME)
@@ -60,22 +85,24 @@ def ingest_data_descriptor(data_descriptor_path: Path,
         msg = f'Unable to read the context file {context_file_path} of data descriptor \
                {data_descriptor_id}. Skip.\n{str(e)}'
         _LOGGER.warning(msg)
-        return        
+        return
 
     with connection.create_session() as session:
+        # We ll know it only when we ll add a term (hypothesis all term have the same kind in a data_descriptor)
         data_descriptor = UDataDescriptor(id=data_descriptor_id,
-                                         context=context,
-                                         term_kind="") # we ll know it only when we ll add a term (hypothesis all term have the same kind in a data_descriptor)
+                                          context=context,
+                                          term_kind="")
         term_kind_dd = None
 
         _LOGGER.debug(f"add data_descriptor : {data_descriptor_id}")
         for term_file_path in data_descriptor_path.iterdir():
             _LOGGER.debug(f"found term path : {term_file_path}, {term_file_path.suffix}")
             if term_file_path.is_file() and term_file_path.suffix == ".json":
-                
                 try:
-                    json_specs=DataMerger(data=JsonLdResource(uri=str(term_file_path)),
-                                          locally_available={"https://espri-mod.github.io/mip-cmor-tables":service.current_state.universe.local_path}).merge_linked_json()[-1]
+                    locally_available = {"https://espri-mod.github.io/mip-cmor-tables":
+                                         service.current_state.universe.local_path}
+                    json_specs = DataMerger(data=JsonLdResource(uri=str(term_file_path)),
+                                            locally_available=locally_available).merge_linked_json()[-1]
                     term_kind = infer_term_kind(json_specs)
                     term_id = json_specs["id"]
 
@@ -83,7 +110,8 @@ def ingest_data_descriptor(data_descriptor_path: Path,
                         term_kind_dd = term_kind
 
                 except Exception as e:
-                    _LOGGER.warning(f'Unable to read term {term_file_path} for data descriptor {data_descriptor_path}. Skip.\n{str(e)}')
+                    _LOGGER.warning(f'Unable to read term {term_file_path} for data descriptor ' +
+                                    f'{data_descriptor_path}. Skip.\n{str(e)}')
                     continue
                 if term_id and json_specs and data_descriptor and term_kind:
                     _LOGGER.debug("adding {term_id}")
@@ -99,9 +127,10 @@ def ingest_data_descriptor(data_descriptor_path: Path,
         session.add(data_descriptor)
         session.commit()
 
+
 def get_universe_term(data_descriptor_id: str,
-                     term_id: str,
-                     universe_db_session: Session) -> tuple[TermKind, dict]:
+                      term_id: str,
+                      universe_db_session: Session) -> tuple[TermKind, dict]:
     statement = (
         select(UTerm)
         .join(UDataDescriptor)
@@ -113,9 +142,8 @@ def get_universe_term(data_descriptor_id: str,
 
 
 if __name__ == "__main__":
-    #ingest_universe(db.UNIVERSE_DIR_PATH, db.UNIVERSE_DB_FILE_PATH)
     import os
     root_dir = Path(str(os.getcwd())).parent.parent
     print(root_dir)
-    universe_create_db(root_dir /  Path(".cache/dbs/universe.sqlite"))
-    ingest_universe(root_dir / Path(".cache/repos/mip-cmor-tables"),root_dir /  Path(".cache/dbs/universe.sqlite"))
+    universe_create_db(root_dir / Path(".cache/dbs/universe.sqlite"))
+    ingest_universe(root_dir / Path(".cache/repos/mip-cmor-tables"), root_dir / Path(".cache/dbs/universe.sqlite"))

esgvoc/core/exceptions.py

@@ -0,0 +1,33 @@
+class EsgvocException(Exception):
+    """
+    Class base of all ESGVOC errors.
+    """
+    pass
+
+
+class EsgvocNotFoundError(EsgvocException):
+    """
+    Represents the not found errors.
+    """
+    pass
+
+
+class EsgvocValueError(EsgvocException):
+    """
+    Represents value errors.
+    """
+    pass
+
+
+class EsgvocDbError(EsgvocException):
+    """
+    Represents errors relative to data base management.
+    """
+    pass
+
+
+class EsgvocNotImplementedError(EsgvocException):
+    """
+    Represents not implemented errors.
+    """
+    pass

{esgvoc-0.3.0.dist-info → esgvoc-0.4.0.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.3
 Name: esgvoc
-Version: 0.3.0
+Version: 0.4.0
 Summary: python library and CLI to interact with WCRP CVs
 Project-URL: Repository, https://github.com/ESGF/esgf-vocab
 Author-email: Sébastien Gardoll <sebastien@gardoll.fr>, Guillaume Levavasseur <guillaume.levavasseur@ipsl.fr>, Laurent Troussellier <laurent.troussellier@ipsl.fr>

{esgvoc-0.3.0.dist-info → esgvoc-0.4.0.dist-info}/RECORD

@@ -1,11 +1,11 @@
-esgvoc/__init__.py,sha256=D1rteIBXx1OIT6Jg9Yqo4pOud1VZTXZI8vrhJxm7Nvs,66
-esgvoc/api/__init__.py,sha256=Oe6ch-MhVnN886jQAJ-OuyCI1eO3BxOtB_zvdbkVTXk,2764
-esgvoc/api/_utils.py,sha256=pddSwnqYqLua0r2SXX6098OaCDxWJxaW7zlt2Xarl9o,2149
-esgvoc/api/project_specs.py,sha256=uX1zqvTC8Dj5bOegZQVMAqU1VOle01s_8ncPXvtp0J4,2328
-esgvoc/api/projects.py,sha256=E-Jt3vlu4vhPpVUixDGc7SHSj1HrNeIYz7n3cd9GhWI,42306
-esgvoc/api/report.py,sha256=rAqOwYTqmzMguONT54YzNU1i7ZtmjYaCRD0Yz7mJsOI,3511
-esgvoc/api/search.py,sha256=yV00GjvC9ZRodmfTp9HhOSk5OBsKq1s6ZNfpfxkbCwc,4208
-esgvoc/api/universe.py,sha256=oFgYXCwVZP4HSgdGXYMFmGolSah1uCmfCMWKhNTuhog,10581
+esgvoc/__init__.py,sha256=1U7uasmBR5VzekoxCEz4GBNgpPcsEU5BwY-QOSW37qA,66
+esgvoc/api/__init__.py,sha256=w68CdVRS553bDWezZoCTxIFq_vsP7mFluSoO4yUo_Uc,4130
+esgvoc/api/project_specs.py,sha256=a-hEL-tXsfvwFeSU5PBnQZq_tqB7L67wxpB1ACah-no,2330
+esgvoc/api/projects.py,sha256=y6qcBSuW22a4nDB9V8lU6PFUj1j2SOrj3xtu9FKVyS4,57466
+esgvoc/api/py.typed,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
+esgvoc/api/report.py,sha256=OlK5ApnaikMKmC6FyJ1uTSBeTezZe85yTCJwsk14uZE,3526
+esgvoc/api/search.py,sha256=Ss_-EvCQHZc6pBTDJzPUrOE_ErTcdqa-zmLkcBjsVkk,6667
+esgvoc/api/universe.py,sha256=8aEvkTHWv9PEWz9hw_JYDdjJBbHzizi_RdVg9Ua-ook,21830
 esgvoc/api/data_descriptors/__init__.py,sha256=6ldSy7x4rnol7ZykPBn9xtnKq1bT_d8G19LIyJnc_mw,3248
 esgvoc/api/data_descriptors/activity.py,sha256=HZIaFqOVeYKmMJd1B_ihbKTAAAr13wr8IFISZI_jdO8,620
 esgvoc/api/data_descriptors/area_label.py,sha256=sJqHuuLeXqDajZfEatAWX7Jot6I0xnCd1gvFJaA2s_M,161
@@ -41,38 +41,40 @@ esgvoc/api/data_descriptors/variable.py,sha256=WtWlYRO0NLPRn1qe7Dt84doJWZYNCvCCq
 esgvoc/api/data_descriptors/variant_label.py,sha256=FL8nz0BfvJgKFjMmfBgNyRb8jcHaLBDLPpOvr6mBx9A,155
 esgvoc/api/data_descriptors/vertical_label.py,sha256=g2t-38eE-FY4H_aHrOj-ScZSPHIX6m71oltLcRHOtqI,141
 esgvoc/apps/__init__.py,sha256=Kyq36qRjvTWN7gu4_iFaLOjNUYvW0k1xp8bvkgJlQ5w,269
+esgvoc/apps/py.typed,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 esgvoc/apps/drs/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-esgvoc/apps/drs/constants.py,sha256=kZxFo7Aa8DNy3WBq2j0FuZVEqOyxG53ZAkkjQaObE8s,95
-esgvoc/apps/drs/generator.py,sha256=2-l68Zp4XVzZ42a6x1GN5hHwqYDe--JaiVjfWIGgiBw,22996
-esgvoc/apps/drs/report.py,sha256=HywC7LXA7ER8VQu5g56izm5Z-zLxhoDekQJbhNUNkmI,17316
-esgvoc/apps/drs/validator.py,sha256=-hX5PEYeiuRyIwS6jsY9XRyvj-wPpdcUD8PJn31D9hE,14913
-esgvoc/cli/drs.py,sha256=ykisrZEOz3sl9rFuQehJfgOf4xsE9tKjPd_CmMWR08M,9133
-esgvoc/cli/get.py,sha256=NrNCb2nWftlPkdRmYysbMU_pVUksFTeYItCuVviAAqQ,5171
+esgvoc/apps/drs/constants.py,sha256=rVWq1QQwAFgISjvl3YzJDLLPNUPXHpqgv66spmjyPMQ,96
+esgvoc/apps/drs/generator.py,sha256=M0QMtpAaMU4E0142FPqdhix3n034CU_QaPuwvXsWtlA,22392
+esgvoc/apps/drs/report.py,sha256=ZRu5l6T-U-hqY7O3ZwAseYbWZPcJiMhJ2dpFKZJE3Gk,17371
+esgvoc/apps/drs/validator.py,sha256=yNijdOPhF9adgZbya5Ugvs13GbL4MvgQepCT38A66vM,13825
+esgvoc/cli/drs.py,sha256=PvVbLxef34A1IO600AFWOEWb5iLaWrBRHwwgMJ4u-PM,9237
+esgvoc/cli/get.py,sha256=zwLWkWOfAddK5onyRjWZ0zU909MtTDjEB_YrQtIwXqw,5242
 esgvoc/cli/install.py,sha256=zMssevZDrigrUlw1QHWITGUL1TvsHMZBQdYeNtHgWQA,433
 esgvoc/cli/main.py,sha256=kjB-yus-cmG9rOmVIPBhmjOr3tkwB13dHLcNqrdpYAM,483
 esgvoc/cli/status.py,sha256=hmpyrszrb5ke9l_1SgendPSeoXW1h-h7nH0zGFt_vUw,1357
 esgvoc/cli/valid.py,sha256=XrseGONeWR6gnnwZrRMJNjVBFQLT82Uzn5rHrjjM1Uk,7040
-esgvoc/core/constants.py,sha256=b9GoM3pTICki95gMCnUZbg4_mMiywKhJX5ME01pgwMs,431
+esgvoc/core/constants.py,sha256=i03VR29sQmg89DdQpGZ1fzBT-elT3-_S0bTNraGA6T4,432
 esgvoc/core/convert.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 esgvoc/core/data_handler.py,sha256=BmcD_dSvX5fCkUEGAQnadPTeuKA7IvgMmQtesMXKh5g,5004
+esgvoc/core/exceptions.py,sha256=hs2D1lRWYhFuXDRbApKyJmEZMs8HxTPlSGkDSpkeQiA,538
 esgvoc/core/logging.conf,sha256=GK52lsTu17CfC2tKiMAIvkuHkIt5tqPmkWv68COOilc,278
 esgvoc/core/logging_handler.py,sha256=VgRBWeW_xdC4HtXG0TleQFwoy_YbJR4wlpci_sFezK0,147
 esgvoc/core/repo_fetcher.py,sha256=Rg668F4NN60jd8Ydz9dXpJQxd2eQOgaO0Ziwm53mcaI,9823
-esgvoc/core/db/__init__.py,sha256=gjAT_lUJtPqxsc8WnwbG_sxDqSIFAlG8vEKxdGyH82w,150
-esgvoc/core/db/connection.py,sha256=dhnCy1mwytUUvt149WHk7eYW0KSP64IaF3kMvKOQSJE,877
-esgvoc/core/db/project_ingestion.py,sha256=c7sgl91ScPfB4n05OR6HbtDqxNELv0jTiFf77S7tqc4,6327
-esgvoc/core/db/universe_ingestion.py,sha256=kH9TryeHbahLMaF1BFfOzrakWkcllIi9KWz90IKAphI,5215
+esgvoc/core/db/__init__.py,sha256=fszGxJfRUa6uuuogrdh8_ExtdyMLZSaaVawpdgXzqKM,113
+esgvoc/core/db/connection.py,sha256=AIFo0IWznu0Alk0SK_4bqp6FL5ZqSezNrfc_AlM9Z14,882
+esgvoc/core/db/project_ingestion.py,sha256=M0Yruh7w--Q9JyRnbLynoPiVfmufp8b6h5UuUeNnnPA,7687
+esgvoc/core/db/universe_ingestion.py,sha256=vPNr_svmduX3JKuLA_-SQMTxO2FWMqCNyCWkPSDznNE,6522
 esgvoc/core/db/models/mixins.py,sha256=S4_6iuKf1kYLdUXAgqRKSTXs8H9I--43MKlEq4F-dm4,445
-esgvoc/core/db/models/project.py,sha256=tuVcwNOkv0fQLFojpQCWacpnM7ZIX3eMDq6Mnko5OI0,2284
-esgvoc/core/db/models/universe.py,sha256=_WwuqrLGrheLbSOXaFN-2rWmHmeEGseO5sN400p6BuY,2202
+esgvoc/core/db/models/project.py,sha256=hkDCPJNo3wGt-UMOfujeQYPgju_aH1oExDAnIgoe96M,4369
+esgvoc/core/db/models/universe.py,sha256=vrR1TMD9ZI6RSGRi-qnLEKHD2Qk6Mh3qz8gciPgsELQ,4199
 esgvoc/core/service/__init__.py,sha256=hveqCB4oC6gKDf_L-wZxu9iBz7RiY4x9OeJGP6S5xtU,1534
 esgvoc/core/service/data_merger.py,sha256=GNFp5DTV2jlBVJZNpILngi6jCbUvVGcqka4EMWKj_Os,3456
 esgvoc/core/service/esg_voc.py,sha256=5G0P4_xmQzoI_RG_agpq-yHoYYZx220P27v2nPrpyNs,2420
 esgvoc/core/service/state.py,sha256=f1Pb11yYRAcLyK93zJ60i5l-mifDXP8_81tJQtMAvPo,10622
 esgvoc/core/service/configuration/config_manager.py,sha256=K-gU3Kd-eJMunxDKOk4x72CRcyJ50IZXLfqQgyI9zTs,8282
 esgvoc/core/service/configuration/setting.py,sha256=WJgo9ZjZJrTGR9WEBhp1d7ab0Yb2Y6XmnO1oImTPc2s,3042
-esgvoc-0.3.0.dist-info/METADATA,sha256=nIkD0iIw2LFnD7DTYzWIml_af3Rx5Io6KkCFKmADoZE,2165
-esgvoc-0.3.0.dist-info/WHEEL,sha256=C2FUgwZgiLbznR-k0b_5k3Ai_1aASOXDss3lzCUsUug,87
-esgvoc-0.3.0.dist-info/entry_points.txt,sha256=ZXufSC7Jlx1lb52U6Buv9IitJMcqAAXOerR2V9DaIto,48
-esgvoc-0.3.0.dist-info/licenses/LICENSE.txt,sha256=rWJoZt3vach8ZNdLq-Ee5djzCMFnJ1gIfBeJU5RIop4,21782
-esgvoc-0.3.0.dist-info/RECORD,,
+esgvoc-0.4.0.dist-info/METADATA,sha256=rDbK18ahBLJtPMTi00NI64tEhNn8ulPlfvMoJ4TBIlc,2165
+esgvoc-0.4.0.dist-info/WHEEL,sha256=C2FUgwZgiLbznR-k0b_5k3Ai_1aASOXDss3lzCUsUug,87
+esgvoc-0.4.0.dist-info/entry_points.txt,sha256=ZXufSC7Jlx1lb52U6Buv9IitJMcqAAXOerR2V9DaIto,48
+esgvoc-0.4.0.dist-info/licenses/LICENSE.txt,sha256=rWJoZt3vach8ZNdLq-Ee5djzCMFnJ1gIfBeJU5RIop4,21782
+esgvoc-0.4.0.dist-info/RECORD,,

esgvoc/api/_utils.py

@@ -1,53 +0,0 @@
-from typing import Iterable, MutableSequence
-
-from sqlmodel import Session
-
-import esgvoc.core.constants as api_settings
-import esgvoc.core.service as service
-from esgvoc.api.data_descriptors import DATA_DESCRIPTOR_CLASS_MAPPING
-from esgvoc.api.data_descriptors.data_descriptor import (DataDescriptor,
-                                                         DataDescriptorSubSet)
-from esgvoc.core.db.models.project import PTerm
-from esgvoc.core.db.models.universe import UTerm
-
-
-class APIException(Exception): ...
-
-
-def get_pydantic_class(data_descriptor_id_or_term_type: str) -> type[DataDescriptor]:
-    if data_descriptor_id_or_term_type in DATA_DESCRIPTOR_CLASS_MAPPING:
-        return DATA_DESCRIPTOR_CLASS_MAPPING[data_descriptor_id_or_term_type]
-    else:
-        raise RuntimeError(f"{data_descriptor_id_or_term_type} pydantic class not found")
-
-
-def get_universe_session() -> Session:
-    
-    UNIVERSE_DB_CONNECTION = service.current_state.universe.db_connection
-    if UNIVERSE_DB_CONNECTION:
-        return UNIVERSE_DB_CONNECTION.create_session()
-    else:
-        raise RuntimeError('universe connection is not initialized')
-
-
-def instantiate_pydantic_term(term: UTerm|PTerm,
-                              selected_term_fields: Iterable[str]|None) -> DataDescriptor:
-    type = term.specs[api_settings.TERM_TYPE_JSON_KEY]
-    if selected_term_fields:
-        subset = DataDescriptorSubSet(id=term.id, type=type)
-        for field in selected_term_fields:
-            setattr(subset, field, term.specs.get(field, None))
-        for field in DataDescriptorSubSet.MANDATORY_TERM_FIELDS:
-            setattr(subset, field, term.specs.get(field, None))
-        return subset
-    else:
-        term_class = get_pydantic_class(type)
-        return term_class(**term.specs)
-
-
-def instantiate_pydantic_terms(db_terms: Iterable[UTerm|PTerm],
-                               list_to_populate: MutableSequence[DataDescriptor],
-                               selected_term_fields: Iterable[str]|None) -> None:
-    for db_term in db_terms:
-        term = instantiate_pydantic_term(db_term, selected_term_fields)
-        list_to_populate.append(term)