ingestify 0.3.3__py3-none-any.whl → 0.4.0__py3-none-any.whl

ingestify/infra/store/dataset/sqlalchemy/{mapping.py → tables.py}

@@ -1,5 +1,4 @@
 import datetime
-from dataclasses import is_dataclass, asdict
 from pathlib import Path
 from typing import Optional
 
@@ -15,33 +14,31 @@ from sqlalchemy import (
     String,
     Table,
     TypeDecorator,
-    Boolean,
 )
-from sqlalchemy.orm import registry, relationship
 
-from ingestify.domain import Selector, Identifier, DataSpecVersionCollection
-from ingestify.domain.models import Dataset, File, Revision
+from sqlalchemy.dialects.postgresql import JSONB
+
+from ingestify.domain import Identifier, DataSpecVersionCollection, Selector
 from ingestify.domain.models.dataset.dataset import DatasetState
-from ingestify.domain.models.ingestion.ingestion_job_summary import (
-    IngestionJobSummary,
-)
-from ingestify.domain.models.task.task_summary import TaskSummary, Operation, TaskStatus
+from ingestify.domain.models.ingestion.ingestion_job_summary import IngestionJobState
+
+from ingestify.domain.models.task.task_summary import Operation, TaskState
 from ingestify.domain.models.timing import Timing
 from ingestify.domain.models.dataset.revision import RevisionState
 
 
-def JSONType(serializer=None, deserializer=None):
+def JSONType(serializer=None, deserializer=None, base_type=JSON):
     class _JsonType(TypeDecorator):
         cache_ok = True
-        impl = JSON
+        impl = base_type
 
         def process_bind_param(self, value, dialect):
-            if serializer is not None:
+            if serializer and value is not None:
                 return serializer(value)
             return value
 
         def process_result_value(self, value, dialect):
-            if deserializer is not None:
+            if deserializer and value is not None:
                 return deserializer(value)
             return value
 
@@ -106,7 +103,7 @@ class RevisionStateString(TypeDecorator):
 
     def process_result_value(self, value, dialect):
         if not value:
-            return value
+            return RevisionState.PENDING_VALIDATION
 
         return RevisionState[value]
 
@@ -124,20 +121,31 @@ class OperationString(TypeDecorator):
         return Operation[value]
 
 
-class TaskStatusString(TypeDecorator):
+class TaskStateString(TypeDecorator):
     impl = String(255)
 
-    def process_bind_param(self, value: TaskStatus, dialect):
+    def process_bind_param(self, value: TaskState, dialect):
         return value.value
 
     def process_result_value(self, value, dialect):
         if not value:
             return value
 
-        return TaskStatus[value]
+        return TaskState[value]
+
+
+class IngestionJobStateString(TypeDecorator):
+    impl = String(255)
+
+    def process_bind_param(self, value: IngestionJobState, dialect):
+        return value.value
+
+    def process_result_value(self, value, dialect):
+        if not value:
+            return value
 
+        return IngestionJobState[value]
 
-mapper_registry = registry()
 
 metadata = MetaData()
 
@@ -146,14 +154,19 @@ dataset_table = Table(
     metadata,
     Column("bucket", String(255), default=None),
     Column("dataset_id", String(255), primary_key=True),
-    Column("provider", String(255)),
-    Column("dataset_type", String(255)),
+    Column("provider", String(255), index=True),
+    Column("dataset_type", String(255), index=True),
     Column("state", DatasetStateString),
     Column("name", String(255)),
-    Column("identifier", JSONType(deserializer=lambda item: Identifier(**item))),
+    Column(
+        "identifier",
+        # Use JSONB when available
+        JSON().with_variant(JSONB(), "postgresql"),
+    ),
     Column("metadata", JSON),
     Column("created_at", TZDateTime(6)),
     Column("updated_at", TZDateTime(6)),
+    Column("last_modified_at", TZDateTime(6)),
 )
 
 revision_table = Table(
@@ -193,40 +206,7 @@ file_table = Table(
     ),
 )
 
-
-mapper_registry.map_imperatively(
-    Dataset,
-    dataset_table,
-    properties={
-        "revisions": relationship(
-            Revision,
-            backref="dataset",
-            order_by=revision_table.c.revision_id,
-            lazy="selectin",
-            cascade="all, delete-orphan",
-        ),
-    },
-)
-
-mapper_registry.map_imperatively(
-    Revision,
-    revision_table,
-    properties={
-        "modified_files": relationship(
-            File,
-            order_by=file_table.c.file_id,
-            primaryjoin="and_(Revision.revision_id==File.revision_id, Revision.dataset_id==File.dataset_id)",
-            lazy="selectin",
-            cascade="all, delete-orphan",
-        )
-    },
-)
-
-
-mapper_registry.map_imperatively(File, file_table)
-
-
-ingestion_job_summary = Table(
+ingestion_job_summary_table = Table(
     "ingestion_job_summary",
     metadata,
     Column("ingestion_job_summary_id", String(255), primary_key=True),
@@ -238,18 +218,25 @@ ingestion_job_summary = Table(
     Column(
         "data_spec_versions",
         JSONType(
-            serializer=lambda data_spec_versions: data_spec_versions.to_dict(),
+            serializer=lambda data_spec_versions: {
+                key: list(value) for key, value in data_spec_versions.items()
+            },
             deserializer=lambda data_spec_versions: DataSpecVersionCollection.from_dict(
                 data_spec_versions
             ),
         ),
     ),
     Column(
-        "selector", JSONType(serializer=lambda selector: selector.filtered_attributes)
+        "selector",
+        JSONType(
+            serializer=lambda selector: selector.filtered_attributes,
+            deserializer=lambda selector: Selector(**selector),
+        ),
     ),
     Column("started_at", TZDateTime(6)),
-    Column("finished_at", TZDateTime(6)),
+    Column("ended_at", TZDateTime(6)),
     # Some task counters
+    Column("state", IngestionJobStateString),
     Column("successful_tasks", Integer),
     Column("ignored_successful_tasks", Integer),
     Column("skipped_datasets", Integer),
@@ -258,7 +245,10 @@ ingestion_job_summary = Table(
         "timings",
         JSONType(
             serializer=lambda timings: [
-                timing.model_dump(mode="json") for timing in timings
+                # Timing is probably already a dictionary. Load it into Timing first, so it can be dumped
+                # in json mode
+                Timing.model_validate(timing).model_dump(mode="json")
+                for timing in timings
             ],
             deserializer=lambda timings: [
                 Timing.model_validate(timing) for timing in timings
@@ -299,12 +289,13 @@ task_summary_table = Table(
     Column("persisted_file_count", Integer),
     Column("bytes_retrieved", Integer),
     Column("last_modified", TZDateTime(6)),
-    Column("status", TaskStatusString),
+    Column("state", TaskStateString),
     Column(
         "timings",
         JSONType(
             serializer=lambda timings: [
-                timing.model_dump(mode="json") for timing in timings
+                Timing.model_validate(timing).model_dump(mode="json")
+                for timing in timings
             ],
             deserializer=lambda timings: [
                 Timing.model_validate(timing) for timing in timings
@@ -316,21 +307,54 @@ task_summary_table = Table(
     # Column("state", RevisionStateString, default=RevisionState.PENDING_VALIDATION),
     # Column("source", JSONType()),
 )
-
-
-mapper_registry.map_imperatively(
-    IngestionJobSummary,
-    ingestion_job_summary,
-    properties={
-        "task_summaries": relationship(
-            TaskSummary,
-            backref="ingestion_job_summary",
-            # order_by=task_summary_table.c.revision_id,
-            lazy="selectin",
-            cascade="all, delete-orphan",
-        ),
-    },
-)
-
-
-mapper_registry.map_imperatively(TaskSummary, task_summary_table)
+#
+#
+# mapper_registry = registry()
+#
+# mapper_registry.map_imperatively(
+#     Dataset,
+#     dataset_table,
+#     properties={
+#         "revisions": relationship(
+#             Revision,
+#             backref="dataset",
+#             order_by=revision_table.c.revision_id,
+#             lazy="selectin",
+#             cascade="all, delete-orphan",
+#         ),
+#     },
+# )
+#
+# mapper_registry.map_imperatively(
+#     Revision,
+#     revision_table,
+#     properties={
+#         "modified_files": relationship(
+#             File,
+#             order_by=file_table.c.file_id,
+#             primaryjoin="and_(Revision.revision_id==File.revision_id, Revision.dataset_id==File.dataset_id)",
+#             lazy="selectin",
+#             cascade="all, delete-orphan",
+#         )
+#     },
+# )
+#
+#
+# mapper_registry.map_imperatively(File, file_table)
+#
+# mapper_registry.map_imperatively(
+#     IngestionJobSummary,
+#     ingestion_job_summary,
+#     properties={
+#         "task_summaries": relationship(
+#             TaskSummary,
+#             backref="ingestion_job_summary",
+#             # order_by=task_summary_table.c.revision_id,
+#             lazy="selectin",
+#             cascade="all, delete-orphan",
+#         ),
+#     },
+# )
+#
+#
+# mapper_registry.map_imperatively(TaskSummary, task_summary_table)

ingestify/utils.py

@@ -1,34 +1,23 @@
-import abc
-import asyncio
-import inspect
 import logging
 import os
 import time
 import re
+import traceback
+from contextlib import contextmanager
 from multiprocessing import get_context, cpu_count, get_all_start_methods
 
 from datetime import datetime, timezone
 from string import Template
-from typing import (
-    Dict,
-    Generic,
-    Type,
-    TypeVar,
-    Tuple,
-    Optional,
-    Any,
-    Callable,
-    Awaitable,
-    List,
-    Iterable,
-)
+from typing import Dict, Tuple, Optional, Any, List
 
 import cloudpickle
+from pydantic import Field
 from typing_extensions import Self
 
 
 from itertools import islice
 
+from ingestify.domain.models.timing import Timing
 
 logger = logging.getLogger(__name__)
 
@@ -221,3 +210,46 @@ def try_number(s: str):
             return float(s)
         except ValueError:
             return s
+
+
+class HasTiming:
+    """Mixin to give Pydantic models ability to time actions."""
+
+    timings: List[Timing] = Field(default_factory=list)
+
+    @contextmanager
+    def record_timing(
+        self, description: str, metadata: Optional[dict] = None
+    ) -> Timing:
+        if not metadata:
+            metadata = {}
+
+        start = utcnow()
+        try:
+            result = None
+            yield
+        except Exception as e:
+            result = {
+                "type": type(e).__name__,
+                "message": str(e),
+                "traceback": traceback.format_exc(),
+            }
+            raise e
+        finally:
+            metadata = dict(result=result, **metadata)
+            self.timings.append(
+                Timing(
+                    name=description,
+                    started_at=start,
+                    ended_at=utcnow(),
+                    metadata=metadata,
+                )
+            )
+
+    def start_timing(self, name):
+        start = utcnow()
+
+        def finish():
+            self.timings.append(Timing(name=name, started_at=start, ended_at=utcnow()))
+
+        return finish

{ingestify-0.3.3.dist-info → ingestify-0.4.0.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: ingestify
-Version: 0.3.3
+Version: 0.4.0
 Summary: Data Ingestion Framework
 Author: Koen Vossen
 Author-email: info@koenvossen.nl
@@ -227,23 +227,23 @@ dataset_collection = store.get_dataset_collection(
 store.map(
     lambda dataset: (
         store
-        
-        # As it's related to https://github.com/PySport/kloppy the store can load files using kloppy
-        .load_with_kloppy(dataset)
-        
-        # Convert it into a polars dataframe using all columns in the original data and some more additional ones
-        .to_df(
-            "*", 
-            match_id=dataset.identifier.match_id,
-            competition_id=dataset.identifier.competition_id,
-            season_id=dataset.identifier.season_id, 
-            
+
+            # As it's related to https://github.com/PySport/kloppy the store can load files using kloppy
+            .load_with_kloppy(dataset)
+
+            # Convert it into a polars dataframe using all columns in the original data and some more additional ones
+            .to_df(
+            "*",
+            match_id=dataset.dataset_resource_id.match_id,
+            competition_id=dataset.dataset_resource_id.competition_id,
+            season_id=dataset.dataset_resource_id.season_id,
+
             engine="polars"
         )
-        
-        # Write to parquet format
-        .write_parquet(
-            f"/tmp/files/blaat/{dataset.identifier.match_id}.parquet"
+
+            # Write to parquet format
+            .write_parquet(
+            f"/tmp/files/blaat/{dataset.dataset_resource_id.match_id}.parquet"
         )
     ),
     dataset_collection,

{ingestify-0.3.3.dist-info → ingestify-0.4.0.dist-info}/RECORD

@@ -1,18 +1,18 @@
-ingestify/__init__.py,sha256=skDa1VfOP7IslAz1tXtfTAwPzohhFlzwGkD_1wV8m50,301
-ingestify/cmdline.py,sha256=bIuyPgGEw4wIglNzpG9zp7TsJozsP8NSVsCe4eAyWUg,7189
-ingestify/exceptions.py,sha256=wMMuajl4AkQRfW60TLN7btJmQaH8-lUczXyW_2g9kOU,143
+ingestify/__init__.py,sha256=pqbfmiQtpinnyWcferY68eDjMbrSslyzmNBk9XErzak,301
+ingestify/cmdline.py,sha256=oagUe-Jup1SU3s6jVl25f0cSG0wlNYhxFY-gGBwWmr0,7482
+ingestify/exceptions.py,sha256=izRzaLQmMy-4P8ZqGqVZyf4k6LFYOYqwYLuRaUH8BJw,187
 ingestify/main.py,sha256=Xr0VbGgstPO7doDX18xqk4lBb4W2sbGWtQuXZaARsHA,8763
 ingestify/server.py,sha256=OVrf_XtpAQIn88MzqQzShXgsA9_jbnqYvD8YPBjn3cs,2413
 ingestify/source_base.py,sha256=GXAFCoT11Zov9M2v-fqQr9gFCXbtVfEIEH32V7r2oE8,382
-ingestify/utils.py,sha256=HETGhAoUlutLG0cQR63nac2JbFei9gnktDHeBQoYWfU,5692
+ingestify/utils.py,sha256=6BqgEZjecLW_anqYP5WrFpi93bmdhF-EdrebEkm59Ds,6806
 ingestify/application/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-ingestify/application/dataset_store.py,sha256=5CZ2v_fjqhNyC8JdjE9O4huTwy3WtHhawyc8Gw4DeJ4,11646
-ingestify/application/ingestion_engine.py,sha256=PtMjKMpvfqB802G5zfKLzyamdH7qFOXl3x6_97y8w60,2288
-ingestify/application/loader.py,sha256=v8ZcpMDEml9k_uFPFqT4WaCjXED_OIpAr7g0Pz5Hp6Y,7153
+ingestify/application/dataset_store.py,sha256=JkAb1W0HaUgOwbohKntM4ttyrFXQ7df1uZSu2rbZllY,11680
+ingestify/application/ingestion_engine.py,sha256=4SAmPZDm3e2QA5jZvMrb6xz1eDDshKoSZDWH3TCe4Bo,2372
+ingestify/application/loader.py,sha256=2LpYSHvedsoe5wFsIkQv0xLcKcqtebwVOSPWapAypao,7566
 ingestify/application/secrets_manager.py,sha256=5qCbPfUvRGP1Xbq6xPkMfpgYl8uPzF_0NbiKeRY5zxU,1757
 ingestify/domain/__init__.py,sha256=M7_fVTJjQUx53P4UQUPhowRKPKsIIjx4JYZL1yjHKsM,46
 ingestify/domain/models/__init__.py,sha256=cjQmdSDFA-saXjdF1mLPNWILFHIFgdj20J_fC5FmFsI,770
-ingestify/domain/models/base.py,sha256=6jzzIqSkH1mPsXZ2OTXMj09S_IlvMOrOBHBJyWAKEjE,555
+ingestify/domain/models/base.py,sha256=4gKbREajxJHlS-VwKoosNtHVupZ4eDLKMqnJ4ib0aS8,184
 ingestify/domain/models/data_spec_version_collection.py,sha256=CAXlO4W2AOOWAPdPAuymqBHnJpiYtkr2z7fYFJ3HSCk,1372
 ingestify/domain/models/fetch_policy.py,sha256=d7K1TzliNJXxqaqzqEOQWLhvgIvmmqhUQEliXvSUcTs,1405
 ingestify/domain/models/sink.py,sha256=OBVfFMpB7puJmHg4q2KYx4qgoAnlmX8xKWYnPi8a9pc,178
@@ -20,16 +20,16 @@ ingestify/domain/models/source.py,sha256=sB3aqr2LfjIbtw7ODJpHnPj3RUeo7gYmTU7MXvf
 ingestify/domain/models/timing.py,sha256=TvvH6Szo61CD8wCP7Awyc45CXga5lKqvoW2U-0TRHlA,388
 ingestify/domain/models/dataset/__init__.py,sha256=i1kswluvWjw0xn4OUByRt7yeRvNHu1mauevv-Vmayx4,630
 ingestify/domain/models/dataset/collection.py,sha256=E2utQ6oyaFFrfQFMiwP9J_I7Wm21z0sRvE4Zc3QEs20,1310
-ingestify/domain/models/dataset/collection_metadata.py,sha256=gI5cb9M0QRsheIr2jA71wOyWfI5lGx5ES2Qw7rbDIoA,371
-ingestify/domain/models/dataset/dataset.py,sha256=ReL50BXNaJVU29OB5_9CQEI7BekWsgi1t3AR7e5jENc,2743
+ingestify/domain/models/dataset/collection_metadata.py,sha256=u2H3XZ-6NMfuAcVD_mb7jEc1IkS1MgQahDIe5CWHjtc,458
+ingestify/domain/models/dataset/dataset.py,sha256=STew8_zCBro_x_u03JrjMvq8yqUDaNndlOlolf9osdM,3332
 ingestify/domain/models/dataset/dataset_repository.py,sha256=kUjiqW58kOUOli1gZCLR5xw4dBX0bqI1UJsf16hgNsQ,812
 ingestify/domain/models/dataset/dataset_state.py,sha256=O95mea5N34HDXw7XsYzxHna4FVk_T-ZNUDezkvt7VzY,220
 ingestify/domain/models/dataset/events.py,sha256=58VacQejQt-WPh9BywP4st5McauM3gXBQo0kaDnSekY,481
-ingestify/domain/models/dataset/file.py,sha256=1oj03zKdkO_9F85LuDcihbB0Kr3suf12KZNGHpVo3w0,4144
+ingestify/domain/models/dataset/file.py,sha256=1Thdv6A1YmC1UfutaRf2q3FGHQYO0SWEptCxur6Ahfs,4144
 ingestify/domain/models/dataset/file_collection.py,sha256=yaQmqFlmbajLCkU5QnjgqCvKzvVEZJrXVvinx5UGHcM,1193
 ingestify/domain/models/dataset/file_repository.py,sha256=9EQprch9isAH2pbK7e7tfOKl6ulip4Ij1kBCTbO_rTc,1721
 ingestify/domain/models/dataset/identifier.py,sha256=EJYsxt0OS_43Y989DZQq8U9NjwmtvnHGYGMe6-hOBlI,575
-ingestify/domain/models/dataset/revision.py,sha256=O_1HG2S2EmYdWqI2K282S_D-d6IhRh_f4Q3wV8MEhkk,1311
+ingestify/domain/models/dataset/revision.py,sha256=jBjMqYXDbvt_VAIwL_db09jcH4W8JPRKsXJb4JCniuM,1447
 ingestify/domain/models/dataset/selector.py,sha256=kEGpU8pIyjZ0zwE9n2uo_NY5xrNanWiTTgapyMAUEsw,1039
 ingestify/domain/models/event/__init__.py,sha256=OdPTpE9bj5QqdGmrYqRTLPX1f-LR9GWJYlGMPPEsuL8,138
 ingestify/domain/models/event/_old_event.py,sha256=RktgCAj9SMdtqkAc_bOwoghEb2Z6m4r5_xWXin9wqx4,472
@@ -39,15 +39,15 @@ ingestify/domain/models/event/event_bus.py,sha256=iseourbCwdUg-ODM5bM_u6cageJmce
 ingestify/domain/models/event/publisher.py,sha256=TOAawYYiPQCLR2Gm17LumMEzeapMDYcAYeklLFmwqAY,620
 ingestify/domain/models/event/subscriber.py,sha256=tP1ZFSvpJWKUITnATYekRxJzepz85UY7egBTMiP-dwg,1039
 ingestify/domain/models/ingestion/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-ingestify/domain/models/ingestion/ingestion_job.py,sha256=U6B62c7NGeHBAjmKhgOa4uHeul34xyR66WtWaPSRNTU,12276
-ingestify/domain/models/ingestion/ingestion_job_summary.py,sha256=e8wULXsKAGNGrOV4dyiRcFlAfYCWcLa2iqJKNMwirlk,4270
+ingestify/domain/models/ingestion/ingestion_job.py,sha256=H9jfbbWFZw73nxMOW0480LgSHV-o4sA5IcvpUZmFpS4,13140
+ingestify/domain/models/ingestion/ingestion_job_summary.py,sha256=Xvmtu0BwE9C7FxBl6D8tN49I6--E_RngcMfWeme4DPA,4499
 ingestify/domain/models/ingestion/ingestion_plan.py,sha256=KAvITBMQt3zmMFokESQJyp3rMuz1Hxr6msfZK1_faZM,648
 ingestify/domain/models/resources/__init__.py,sha256=ZuY9DPRfwk-aLB3Lj6DYP_NqMkcQfcYjZp4VejTtcbU,46
 ingestify/domain/models/resources/dataset_resource.py,sha256=NRnN029ct3P_Eg2d9Unb1t7A12Ksv_emBGhoe9DpPwM,3118
 ingestify/domain/models/task/__init__.py,sha256=BdlyIPvE07Xax_IzLgO9DUw0wsz9OZutxnxdDNyRlys,79
 ingestify/domain/models/task/set.py,sha256=04txDYgS5rotXofD9TqChKdW0VZIYshrkfPIpXtlhW4,430
 ingestify/domain/models/task/task.py,sha256=OwLZQi9GGe0O8m1dKvJdN2Rham5oilI49KyKc5uV20A,161
-ingestify/domain/models/task/task_summary.py,sha256=ovzqKPstngRVzVA_JboQMluq5uQjKVJDsWNNcfcadhU,3774
+ingestify/domain/models/task/task_summary.py,sha256=T9BSGhOZjKCPfym34VUdBXuMy0o6E832GAI4WMtjGao,3181
 ingestify/domain/services/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 ingestify/domain/services/identifier_key_transformer.py,sha256=y4GS9u9Ej1MO2jUhAxWbifp0mrE_MqTHvVVcoQzSKb4,4034
 ingestify/domain/services/transformers/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
@@ -55,7 +55,7 @@ ingestify/domain/services/transformers/kloppy_to_pandas.py,sha256=NcN6nTBGVn9gz-
 ingestify/infra/__init__.py,sha256=V0hpLzPVTcOHRVh0gguF6FT30YIgEOUd5v87xUHkfZ4,88
 ingestify/infra/fetch/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 ingestify/infra/fetch/http.py,sha256=ldaXy6alBbI9z63H97lXfYZNT0ZCBkTac1W6-acNjjY,4127
-ingestify/infra/serialization/__init__.py,sha256=LwfmRoO4qykZkJZXxVPSKpwoVIkg9qzXa7Egut9JjL4,1772
+ingestify/infra/serialization/__init__.py,sha256=UqXWJmKTp7Mi58ZyDASGguPFlqdVWVUbm_sg9GWx9eI,702
 ingestify/infra/sink/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 ingestify/infra/sink/postgresql.py,sha256=SxuM3LntfYcpCriUpqJhMvgAf0s9cohXf6WkxSEDYDY,1816
 ingestify/infra/source/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
@@ -64,8 +64,8 @@ ingestify/infra/source/wyscout.py,sha256=DxCzdkzYpVRHTfV9GpF8pe3FzwIk-WHYUlea6nO
 ingestify/infra/store/__init__.py,sha256=3dA6NWfB6FS5SFdQiSlJ0ZghBfnUAUuGIP5Vr4rkCqk,43
 ingestify/infra/store/dataset/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 ingestify/infra/store/dataset/sqlalchemy/__init__.py,sha256=Z5JHWGO_hwT6rO-ecMOOAmOKjFFJi449KZvJTQgt6vQ,52
-ingestify/infra/store/dataset/sqlalchemy/mapping.py,sha256=pyqxy7LAyRK2Mt6knaKYozXN07oNPYztU9x4DGDQD0U,9451
-ingestify/infra/store/dataset/sqlalchemy/repository.py,sha256=-eSR_F9tS9Hd3JNEpoJoDAb5RY38rFaKLMI3eBedjx8,7068
+ingestify/infra/store/dataset/sqlalchemy/repository.py,sha256=R7OJVC_dh5hGhaCvU_Ixyfb16Xyd-hxvm7n0zJ6KxDk,15857
+ingestify/infra/store/dataset/sqlalchemy/tables.py,sha256=FEMEkBiefozEoWCYMQnc4DD3ZsDeg3KaFs1c58A66ME,10314
 ingestify/infra/store/file/__init__.py,sha256=DuEekZa2pmDuRCFiulbgoGotN0wGv3OrRXSvokY0PhY,104
 ingestify/infra/store/file/dummy_file_repository.py,sha256=azUq9c43Mz9-GWk9j0E97BaqyUKu-ZMrcuaIednLq5E,723
 ingestify/infra/store/file/local_file_repository.py,sha256=1hhLqds5LlppJq2QBB0oN0Q98j6aXreCtYQYz3Q1P8g,819
@@ -80,8 +80,8 @@ ingestify/static/templates/wyscout/README.md,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRk
 ingestify/static/templates/wyscout/config.yaml.jinja2,sha256=0zQXuvJVwd0oL2OJsPMZ8sOvRbdfRbieSGLQ44ezmYc,379
 ingestify/static/templates/wyscout/query.py,sha256=wjAOMoKvhX-BzCRqEm1SJp6YAcF8Fsq7ddrOaOpAeOk,364
 ingestify/static/templates/wyscout/database/README.md,sha256=7IuzjKo7Pqkx5wkmOETRZDljVOslqfA3ALuHMONq5dg,32
-ingestify-0.3.3.dist-info/METADATA,sha256=ln_MGBlqm4wgPBldNv_VofJ4snw981jv667X4JOylmY,18832
-ingestify-0.3.3.dist-info/WHEEL,sha256=tZoeGjtWxWRfdplE7E3d45VPlLNQnvbKiYnx7gwAy8A,92
-ingestify-0.3.3.dist-info/entry_points.txt,sha256=czYYXeX2ul4zdeB6bKlz3HaUF7zyVVcj9E_sRNDisI0,53
-ingestify-0.3.3.dist-info/top_level.txt,sha256=Lwnjgns4KequS7KiicXhh6mLUvcdfjzLyPI4qf_s4A0,10
-ingestify-0.3.3.dist-info/RECORD,,
+ingestify-0.4.0.dist-info/METADATA,sha256=t02z0kStKbk2lECODDJieRK4Ev1TDKR0Z6G2DpUeeGM,18854
+ingestify-0.4.0.dist-info/WHEEL,sha256=tZoeGjtWxWRfdplE7E3d45VPlLNQnvbKiYnx7gwAy8A,92
+ingestify-0.4.0.dist-info/entry_points.txt,sha256=czYYXeX2ul4zdeB6bKlz3HaUF7zyVVcj9E_sRNDisI0,53
+ingestify-0.4.0.dist-info/top_level.txt,sha256=Lwnjgns4KequS7KiicXhh6mLUvcdfjzLyPI4qf_s4A0,10
+ingestify-0.4.0.dist-info/RECORD,,