pyspiral 0.2.5__cp310-abi3-macosx_11_0_arm64.whl → 0.4.0__cp310-abi3-macosx_11_0_arm64.whl

spiral/project.py

@@ -1,26 +1,18 @@
-from typing import TYPE_CHECKING, Any
-
-import pyarrow as pa
-
-from spiral import Table
-from spiral.api.tables import CreateTable, FindTable
-from spiral.core.core import Table as CoreTable
-from spiral.core.metastore import PyMetastore
-from spiral.core.spec import Schema
-from spiral.types_ import Uri
+from typing import TYPE_CHECKING
 
 if TYPE_CHECKING:
-    from spiral.catalog import Spiral
+    from spiral.client import Spiral
+    from spiral.iceberg import Iceberg
+    from spiral.indexes import Indexes
+    from spiral.tables import Tables
 
 
 class Project:
-    def __init__(self, spiral_db: "Spiral", id: str, name: str | None = None):
-        self._spiral_db = spiral_db
+    def __init__(self, spiral: "Spiral", id: str, name: str | None = None):
+        self._spiral = spiral
         self._id = id
         self._name = name
 
-        self._api = self._spiral_db.config.api
-
     def __str__(self):
         return self._id
 
@@ -35,103 +27,20 @@ class Project:
     def name(self) -> str:
         return self._name or self._id
 
-    def list_table_names(self) -> list[(str, str)]:
-        """List tuples of (dataset, table) names in the project."""
-        return [(t.dataset, t.table) for t in self._api.table.list(FindTable.Request(project_id=self.id))]
-
-    def list_tables(self) -> list[Table]:
-        """List tables in the project."""
-        return [
-            Table(
-                CoreTable(
-                    PyMetastore.http(
-                        table_id=t.id,
-                        root_uri=t.metadata.root_uri,
-                        key_schema=Schema.from_arrow(t.metadata.key_schema),
-                        base_url=self._api.base_url + "/metastore/",
-                        token_provider=self._spiral_db.config.authn.token,
-                    ),
-                ),
-                name=f"{self.id}.{t.dataset}.{t.table}",
-            )
-            for t in self._api.table.list(FindTable.Request(project_id=self.id))
-        ]
-
-    def create_table(
-        self,
-        identifier: str,
-        *,
-        key_schema: pa.Schema | Any,
-        uri: Uri | None = None,
-        exist_ok: bool = False,
-    ) -> Table:
-        """Create a new table in the project."""
-        dataset, table = self._parse_identifier(identifier)
-
-        if not isinstance(key_schema, pa.Schema):
-            key_schema = pa.schema(key_schema)
-
-        res = self._api.table.create(
-            CreateTable.Request(
-                project_id=self.id,
-                dataset=dataset,
-                table=table,
-                key_schema=key_schema,
-                root_uri=uri,
-                exist_ok=exist_ok,
-            )
-        )
-
-        # Must have the same schema as provided, even if the table already exists.
-        expected_key_schema = res.table.metadata.key_schema
-        if key_schema != expected_key_schema:
-            raise ValueError(f"Table already exists with different key schema: {expected_key_schema} != {key_schema}")
-        if uri and res.table.metadata.root_uri != uri:
-            raise ValueError(f"Table already exists with different root URI: {res.table.metadata.root_uri} != {uri}")
-
-        # Set up a metastore backed by SpiralDB
-        metastore = PyMetastore.http(
-            table_id=res.table.id,
-            root_uri=res.table.metadata.root_uri,
-            key_schema=Schema.from_arrow(res.table.metadata.key_schema),
-            base_url=self._api.base_url + "/metastore/",
-            token_provider=self._spiral_db.config.authn.token,
-        )
-
-        return Table(CoreTable(metastore), name=f"{self.id}.{res.table.dataset}.{res.table.table}")
+    @property
+    def tables(self) -> "Tables":
+        from spiral.tables import Tables
 
-    def table(self, identifier: str) -> Table:
-        """Open a table with a `dataset.table` identifier, or `table` name using the `default` dataset."""
-        dataset, table = self._parse_identifier(identifier)
+        return Tables(self._spiral._api, self._spiral._core, project_id=self.id)
 
-        # TODO(ngates): why does the client _need_ this information? Can we defer it?
-        res = self._api.table.find(
-            FindTable.Request(
-                project_id=self.id,
-                dataset=dataset,
-                table=table,
-            )
-        )
-        if res.table is None:
-            raise ValueError(f"Table not found: {self.id}.{dataset}.{table}")
+    @property
+    def indexes(self) -> "Indexes":
+        from spiral.indexes.client import Indexes
 
-        # Set up a metastore backed by SpiralDB
-        metastore = PyMetastore.http(
-            table_id=res.table.id,
-            root_uri=res.table.metadata.root_uri,
-            key_schema=Schema.from_arrow(res.table.metadata.key_schema),
-            base_url=self._api.base_url + "/metastore/",
-            token_provider=self._spiral_db.config.authn.token,
-        )
+        return Indexes(self._spiral._api, self._spiral._core, project_id=self._id)
 
-        return Table(CoreTable(metastore), name=f"{self.id}.{res.table.dataset}.{res.table.table}")
+    @property
+    def iceberg(self) -> "Iceberg":
+        from spiral.iceberg import Iceberg
 
-    @staticmethod
-    def _parse_identifier(identifier: str) -> tuple[str, str]:
-        parts = identifier.split(".")
-        if len(parts) == 1:
-            return "default", parts[0]
-        elif len(parts) == 2:
-            return parts[0], parts[1]
-        else:
-            raise ValueError(f"Invalid table identifier: {identifier}")
+        return Iceberg(self._spiral, project_id=self._id)

spiral/{proto → protogen}/_/scandal/__init__.py

@@ -30,6 +30,31 @@ class Source(betterproto.Message):
     parquet: "MetadataParquet" = betterproto.message_field(10, group="metadata")
 
 
+@dataclass(eq=False, repr=False)
+class Metadata(betterproto.Message):
+    pass
+
+
+@dataclass(eq=False, repr=False)
+class MetadataParquet(betterproto.Message):
+    pass
+
+
+@dataclass(eq=False, repr=False)
+class Sink(betterproto.Message):
+    url: str = betterproto.string_field(1)
+
+
+@dataclass(eq=False, repr=False)
+class Connectivity(betterproto.Message):
+    """
+    Information about the client's perceived connectivity to a FileSystem.
+    """
+
+    unreachable: bool = betterproto.bool_field(1)
+    round_trip_time_us: Optional[int] = betterproto.int32_field(2, optional=True)
+
+
 @dataclass(eq=False, repr=False)
 class Fetch(betterproto.Message):
     """Let's make "fetch" happen."""
@@ -39,15 +64,19 @@ class Fetch(betterproto.Message):
 
 @dataclass(eq=False, repr=False)
 class FetchRequest(betterproto.Message):
+    """TODO(ngates): include projection expression."""
+
     uri: str = betterproto.string_field(1)
     """
-    A signed request to read an spfs://<fsid>/path?token=<jwt> URI.
-      * Declares the MIME types the client can read directly.
-      * Declares whether the client has connectivity to the FileSystem.
+    A signed request to read an
+     spfs://&lt;fsid&gt;/path?token=&lt;jwt&gt URI.
     """
 
     connectivity: "Connectivity" = betterproto.message_field(2)
+    """Declares whether the client has connectivity to the FileSystem."""
+
     accepts: List[str] = betterproto.string_field(3)
+    """Declares the MIME types the client can read directly."""
 
 
 @dataclass(eq=False, repr=False)
@@ -59,11 +88,6 @@ class FetchResponse(betterproto.Message):
     """
 
 
-@dataclass(eq=False, repr=False)
-class Sink(betterproto.Message):
-    url: str = betterproto.string_field(1)
-
-
 @dataclass(eq=False, repr=False)
 class Put(betterproto.Message):
     pass
@@ -80,42 +104,6 @@ class PutResponse(betterproto.Message):
     sinks: List["Sink"] = betterproto.message_field(1)
 
 
-@dataclass(eq=False, repr=False)
-class Delete(betterproto.Message):
-    pass
-
-
-@dataclass(eq=False, repr=False)
-class DeleteRequest(betterproto.Message):
-    uri: str = betterproto.string_field(1)
-
-
-@dataclass(eq=False, repr=False)
-class DeleteResponse(betterproto.Message):
-    url: str = betterproto.string_field(1)
-    """Returns signed URL to delete the resource."""
-
-
-@dataclass(eq=False, repr=False)
-class Connectivity(betterproto.Message):
-    """
-    Information about the client's perceived connectivity to a FileSystem.
-    """
-
-    unreachable: bool = betterproto.bool_field(1)
-    round_trip_time_us: Optional[int] = betterproto.int32_field(2, optional=True)
-
-
-@dataclass(eq=False, repr=False)
-class Metadata(betterproto.Message):
-    pass
-
-
-@dataclass(eq=False, repr=False)
-class MetadataParquet(betterproto.Message):
-    pass
-
-
 class ScandalServiceStub(betterproto.ServiceStub):
     async def fetch(
         self,
@@ -151,23 +139,6 @@ class ScandalServiceStub(betterproto.ServiceStub):
             metadata=metadata,
         )
 
-    async def delete(
-        self,
-        delete_request: "DeleteRequest",
-        *,
-        timeout: Optional[float] = None,
-        deadline: Optional["Deadline"] = None,
-        metadata: Optional["MetadataLike"] = None
-    ) -> "DeleteResponse":
-        return await self._unary_unary(
-            "/scandal.ScandalService/Delete",
-            delete_request,
-            DeleteResponse,
-            timeout=timeout,
-            deadline=deadline,
-            metadata=metadata,
-        )
-
 
 class ScandalServiceBase(ServiceBase):
     async def fetch(self, fetch_request: "FetchRequest") -> "FetchResponse":
@@ -176,9 +147,6 @@ class ScandalServiceBase(ServiceBase):
     async def put(self, put_request: "PutRequest") -> "PutResponse":
         raise grpclib.GRPCError(grpclib.const.Status.UNIMPLEMENTED)
 
-    async def delete(self, delete_request: "DeleteRequest") -> "DeleteResponse":
-        raise grpclib.GRPCError(grpclib.const.Status.UNIMPLEMENTED)
-
     async def __rpc_fetch(
         self, stream: "grpclib.server.Stream[FetchRequest, FetchResponse]"
     ) -> None:
@@ -193,13 +161,6 @@ class ScandalServiceBase(ServiceBase):
         response = await self.put(request)
         await stream.send_message(response)
 
-    async def __rpc_delete(
-        self, stream: "grpclib.server.Stream[DeleteRequest, DeleteResponse]"
-    ) -> None:
-        request = await stream.recv_message()
-        response = await self.delete(request)
-        await stream.send_message(response)
-
     def __mapping__(self) -> Dict[str, grpclib.const.Handler]:
         return {
             "/scandal.ScandalService/Fetch": grpclib.const.Handler(
@@ -214,10 +175,4 @@ class ScandalServiceBase(ServiceBase):
                 PutRequest,
                 PutResponse,
             ),
-            "/scandal.ScandalService/Delete": grpclib.const.Handler(
-                self.__rpc_delete,
-                grpclib.const.Cardinality.UNARY_UNARY,
-                DeleteRequest,
-                DeleteResponse,
-            ),
         }

spiral/protogen/_/spiral/table/__init__.py

@@ -0,0 +1,22 @@
+# Generated by the protocol buffer compiler.  DO NOT EDIT!
+# sources: spiral/table/statistics.proto
+# plugin: python-betterproto
+# This file has been @generated
+
+from dataclasses import dataclass
+
+import betterproto
+
+
+@dataclass(eq=False, repr=False)
+class ApproximateSetMembership(betterproto.Message):
+    bloom_filter: "BloomFilter" = betterproto.message_field(
+        2, group="membership_strategy"
+    )
+
+
+@dataclass(eq=False, repr=False)
+class BloomFilter(betterproto.Message):
+    bit_vec: bytes = betterproto.bytes_field(1)
+    bitmap_bits: int = betterproto.uint64_field(2)
+    k_num: int = betterproto.uint32_field(3)