opteryx-catalog 0.4.4__py3-none-any.whl

opteryx_catalog/catalog/manifest.py

@@ -0,0 +1,23 @@
+from __future__ import annotations
+
+from dataclasses import dataclass
+from dataclasses import field
+from typing import Dict
+
+
+@dataclass
+class DataFile:
+    file_path: str
+    file_format: str = "PARQUET"
+    record_count: int = 0
+    file_size_in_bytes: int = 0
+    partition: Dict[str, object] = field(default_factory=dict)
+    lower_bounds: Dict[int, bytes] | None = None
+    upper_bounds: Dict[int, bytes] | None = None
+
+
+@dataclass
+class ManifestEntry:
+    snapshot_id: int
+    data_file: DataFile
+    status: str = "added"  # 'added' | 'deleted'

opteryx_catalog/catalog/metadata.py

@@ -0,0 +1,81 @@
+from __future__ import annotations
+
+from dataclasses import dataclass
+from dataclasses import field
+from typing import Any
+from typing import List
+from typing import Optional
+
+
+@dataclass
+class Snapshot:
+    snapshot_id: int
+    timestamp_ms: int
+    author: Optional[str] = None
+    # Indicates whether this snapshot was created by a user (True) or internally (False)
+    user_created: Optional[bool] = None
+    # Monotonic sequence number for writes
+    sequence_number: Optional[int] = None
+    manifest_list: Optional[str] = None
+    # Operation metadata
+    operation_type: Optional[str] = None  # e.g., 'append', 'overwrite', 'compact'
+    parent_snapshot_id: Optional[int] = None
+    schema_id: Optional[str] = None
+    # Commit message for the snapshot
+    commit_message: Optional[str] = None
+    # Summary metrics (store zeros when not applicable)
+    summary: dict = field(
+        default_factory=lambda: {
+            "added-data-files": 0,
+            "added-files-size": 0,
+            "added-records": 0,
+            "deleted-data-files": 0,
+            "deleted-files-size": 0,
+            "deleted-records": 0,
+            "total-data-files": 0,
+            "total-files-size": 0,
+            "total-records": 0,
+        }
+    )
+
+
+@dataclass
+class DatasetMetadata:
+    dataset_identifier: str
+    format_version: int = 2
+    location: str = ""
+    schema: Any = None
+    properties: dict = field(default_factory=dict)
+    # Table-level created/updated metadata
+    timestamp_ms: Optional[int] = None
+    author: Optional[str] = None
+    description: Optional[str] = None
+    describer: Optional[str] = None
+    sort_orders: List[dict] = field(default_factory=list)
+    # Maintenance policy: retention settings grouped under a single block
+    maintenance_policy: dict = field(
+        default_factory=lambda: {
+            "retained-snapshot-count": None,
+            "retained-snapshot-age-days": None,
+            "compaction-policy": "performance",
+        }
+    )
+    # Compaction policy lives under maintenance_policy as 'compaction-policy'
+    snapshots: List[Snapshot] = field(default_factory=list)
+    current_snapshot_id: Optional[int] = None
+    # Schema management: schemas are stored in a subcollection in Firestore.
+    # `schemas` contains dicts with keys: schema_id, columns (list of {id,name,type}).
+    # Each schema dict may also include `timestamp-ms` and `author`.
+    schemas: List[dict] = field(default_factory=list)
+    current_schema_id: Optional[str] = None
+
+    def current_snapshot(self) -> Optional[Snapshot]:
+        if self.current_snapshot_id is None:
+            return self.snapshots[-1] if self.snapshots else None
+        for s in self.snapshots:
+            if s.snapshot_id == self.current_snapshot_id:
+                return s
+        return None
+
+
+# Dataset terminology: TableMetadata renamed to DatasetMetadata

opteryx_catalog/catalog/metastore.py

@@ -0,0 +1,68 @@
+from __future__ import annotations
+
+from typing import Any
+from typing import Iterable
+from typing import Optional
+
+
+class Metastore:
+    """Abstract catalog interface.
+
+    Implementations should provide methods to create, load and manage
+    datasets and views. Terminology in this project follows the mapping:
+    `catalog -> workspace -> collection -> dataset|view`.
+    Signatures are intentionally simple and similar to other catalog
+    implementations to ease future compatibility.
+    """
+
+    def load_dataset(self, identifier: str) -> "Table":
+        raise NotImplementedError()
+
+    def create_dataset(
+        self, identifier: str, schema: Any, properties: dict | None = None
+    ) -> "Table":
+        raise NotImplementedError()
+
+    def drop_dataset(self, identifier: str) -> None:
+        raise NotImplementedError()
+
+    def list_datasets(self, namespace: str) -> Iterable[str]:
+        raise NotImplementedError()
+
+
+class Dataset:
+    """Abstract dataset interface.
+
+    Minimal methods needed by the Opteryx engine and tests: access metadata,
+    list snapshots, append data, and produce a data scan object.
+    """
+
+    @property
+    def metadata(self) -> Any:
+        raise NotImplementedError()
+
+    def snapshots(self) -> Iterable[Any]:
+        raise NotImplementedError()
+
+    def snapshot(self, snapshot_id: Optional[int] = None) -> Optional[Any]:
+        """Return a specific snapshot by id or the current snapshot when
+        called with `snapshot_id=None`.
+        """
+        raise NotImplementedError()
+
+    def append(self, table):
+        """Append data (implementations can accept pyarrow.Table or similar)."""
+        raise NotImplementedError()
+
+    def scan(
+        self, row_filter=None, snapshot_id: Optional[int] = None, row_limit: Optional[int] = None
+    ) -> Any:
+        raise NotImplementedError()
+
+
+class View:
+    """Abstract view metadata representation."""
+
+    @property
+    def definition(self) -> str:
+        raise NotImplementedError()

opteryx_catalog/catalog/view.py

@@ -0,0 +1,12 @@
+from __future__ import annotations
+
+from dataclasses import dataclass
+from typing import Any
+
+
+@dataclass
+class View:
+    name: str
+    definition: str
+    properties: dict | None = None
+    metadata: Any | None = None

opteryx_catalog/exceptions.py

@@ -0,0 +1,38 @@
+"""Catalog-specific exceptions for opteryx_catalog.
+
+Exceptions mirror previous behavior (they subclass KeyError where callers
+may expect KeyError) but provide explicit types for tables, views and
+namespaces.
+"""
+
+
+class CatalogError(Exception):
+    """Base class for catalog errors."""
+
+
+class DatasetError(KeyError, CatalogError):
+    pass
+
+
+class DatasetAlreadyExists(DatasetError):
+    pass
+
+
+class DatasetNotFound(DatasetError):
+    pass
+
+
+class ViewError(KeyError, CatalogError):
+    pass
+
+
+class ViewAlreadyExists(ViewError):
+    pass
+
+
+class ViewNotFound(ViewError):
+    pass
+
+
+class CollectionAlreadyExists(KeyError, CatalogError):
+    pass

opteryx_catalog/iops/__init__.py

@@ -0,0 +1,6 @@
+from .base import FileIO
+from .base import InputFile
+from .base import OutputFile
+from .gcs import GcsFileIO
+
+__all__ = ["FileIO", "InputFile", "OutputFile", "GcsFileIO"]

opteryx_catalog/iops/base.py

@@ -0,0 +1,42 @@
+from __future__ import annotations
+
+from io import BytesIO
+from typing import BinaryIO
+
+
+class InputFile:
+    def __init__(self, location: str, content: bytes | None = None):
+        self.location = location
+        self._content = content
+
+    def open(self) -> BinaryIO:
+        if self._content is None:
+            raise FileNotFoundError(self.location)
+        return BytesIO(self._content)
+
+
+class OutputFile:
+    def __init__(self, location: str):
+        self.location = location
+
+    def create(self):
+        """Return a file-like object with a `write` method.
+
+        Implementations may return a buffer or a writer that persists on write/close.
+        """
+        raise NotImplementedError()
+
+
+class FileIO:
+    """Minimal FileIO abstraction used by the `opteryx_catalog` layer.
+
+    Concrete implementations should implement `new_input`, `new_output`, and
+    optionally `delete`/`exists`. The abstraction intentionally keeps only the
+    small surface needed by the catalog (read bytes, write bytes).
+    """
+
+    def new_input(self, location: str) -> InputFile:
+        return InputFile(location)
+
+    def new_output(self, location: str) -> OutputFile:
+        return OutputFile(location)

opteryx_catalog/iops/fileio.py

@@ -0,0 +1,125 @@
+from __future__ import annotations
+
+from io import BytesIO
+from typing import BinaryIO
+
+
+class InputFile:
+    def __init__(self, location: str, content: bytes | None = None):
+        self.location = location
+        self._content = content
+
+    def open(self) -> BinaryIO:
+        if self._content is None:
+            raise FileNotFoundError(self.location)
+        return BytesIO(self._content)
+
+
+class OutputFile:
+    def __init__(self, location: str):
+        self.location = location
+
+    def create(self):
+        """Return a file-like object with a `write` method.
+
+        Implementations may return a buffer or a writer that persists on write/close.
+        """
+        raise NotImplementedError()
+
+
+class FileIO:
+    """Minimal FileIO abstraction used by the `opteryx_catalog` layer.
+
+    Concrete implementations should implement `new_input`, `new_output`, and
+    optionally `delete`/`exists`. The abstraction intentionally keeps only the
+    small surface needed by the catalog (read bytes, write bytes).
+    """
+
+    def new_input(self, location: str) -> InputFile:
+        return InputFile(location)
+
+    def new_output(self, location: str) -> OutputFile:
+        return OutputFile(location)
+
+
+class _GcsAdapterOutputFile(OutputFile):
+    def __init__(self, location: str, gcs_fileio):
+        super().__init__(location)
+        self._location = location
+        self._gcs_fileio = gcs_fileio
+
+    def create(self):
+        """Return a writer whose `write(data)` uploads the data via the wrapped GCS FileIO.
+
+        We perform the upload on the first write and close the underlying stream
+        afterwards so callers that simply call `out.write(data)` (common pattern
+        in this codebase) will succeed.
+        """
+
+        class _Writer:
+            def __init__(self, location: str, gcs_fileio):
+                self._location = location
+                self._gcs_fileio = gcs_fileio
+                self._stream = None
+
+            def write(self, data: bytes | bytearray):
+                if self._stream is None:
+                    # Create underlying output stream (may be a GcsOutputStream,
+                    # DiscardOutputStream, or CaptureOutputStream depending on
+                    # the wrapped FileIO behaviour).
+                    out = self._gcs_fileio.new_output(self._location)
+                    self._stream = out.create()
+                # Underlying stream implements write/close semantics
+                self._stream.write(data)
+
+            def close(self):
+                if self._stream is not None:
+                    try:
+                        self._stream.close()
+                    except Exception:
+                        pass
+
+        return _Writer(self._location, self._gcs_fileio)
+
+
+class GcsFileIO(FileIO):
+    """GCS-backed FileIO adapter that wraps the existing GCS implementation.
+
+    This adapter delegates to `pyiceberg_firestore_gcs.fileio.gcs_fileio.GcsFileIO`
+    for actual network operations but exposes the small `opteryx_catalog.iops`
+    `FileIO` interface used by the catalog layer.
+    """
+
+    def __init__(self, properties=None):
+        # Lazy import to avoid pulling google libs unless used
+        from pyiceberg_firestore_gcs.fileio.gcs_fileio import GcsFileIO as _GcsImpl
+
+        self._impl = _GcsImpl(properties or {})
+
+    def new_input(self, location: str) -> InputFile:
+        # Read full bytes from the underlying InputFile and return an in-memory InputFile
+        impl_input = self._impl.new_input(location)
+        try:
+            stream = impl_input.open()
+            data = stream.read()
+            return InputFile(location, data)
+        except FileNotFoundError:
+            return InputFile(location, None)
+
+    def new_output(self, location: str) -> OutputFile:
+        return _GcsAdapterOutputFile(location, self._impl)
+
+    def delete(self, location: str) -> None:
+        return self._impl.delete(location)
+
+    def exists(self, location: str) -> bool:
+        try:
+            impl_in = self._impl.new_input(location)
+            # Some implementations provide `exists()`
+            if hasattr(impl_in, "exists"):
+                return impl_in.exists()
+            # Fallback: try to open
+            _ = impl_in.open()
+            return True
+        except Exception:
+            return False

opteryx_catalog/iops/gcs.py

@@ -0,0 +1,225 @@
+"""
+Optimized GCS FileIO for opteryx_catalog.iops
+
+Adapted from pyiceberg_firestore_gcs.fileio.gcs_fileio to provide a fast
+HTTP-backed GCS implementation without depending on pyiceberg types.
+"""
+
+import io
+import logging
+import os
+import urllib.parse
+from typing import Callable
+from typing import Union
+
+import requests
+from google.auth.transport.requests import Request
+from requests.adapters import HTTPAdapter
+
+from .base import FileIO
+from .base import InputFile
+from .base import OutputFile
+
+logger = logging.getLogger(__name__)
+
+
+def _get_storage_credentials():
+    from google.cloud import storage
+
+    if os.environ.get("STORAGE_EMULATOR_HOST"):
+        from google.auth.credentials import AnonymousCredentials
+
+        storage_client = storage.Client(credentials=AnonymousCredentials())
+    else:
+        storage_client = storage.Client()
+    return storage_client._credentials
+
+
+class _GcsInputStream(io.BytesIO):
+    def __init__(
+        self, path: str, session: requests.Session, access_token_getter: Callable[[], str]
+    ):
+        # Strip gs://
+        if path.startswith("gs://"):
+            path = path[5:]
+        bucket = path.split("/", 1)[0]
+        object_full_path = urllib.parse.quote(path[(len(bucket) + 1) :], safe="")
+        url = f"https://storage.googleapis.com/{bucket}/{object_full_path}"
+
+        access_token = access_token_getter()
+        headers = {"Accept-Encoding": "identity"}
+        if access_token:
+            headers["Authorization"] = f"Bearer {access_token}"
+
+        response = session.get(
+            url,
+            headers=headers,
+            timeout=30,
+        )
+
+        if response.status_code != 200:
+            raise FileNotFoundError(
+                f"Unable to read '{path}' - status {response.status_code}: {response.text}"
+            )
+
+        super().__init__(response.content)
+
+
+class _GcsOutputStream(io.BytesIO):
+    def __init__(
+        self, path: str, session: requests.Session, access_token_getter: Callable[[], str]
+    ):
+        super().__init__()
+        self._path = path
+        self._session = session
+        self._access_token_getter = access_token_getter
+        self._closed = False
+
+    def close(self):
+        if self._closed:
+            return
+
+        path = self._path
+        if path.startswith("gs://"):
+            path = path[5:]
+
+        bucket = path.split("/", 1)[0]
+        url = f"https://storage.googleapis.com/upload/storage/v1/b/{bucket}/o"
+
+        data = self.getvalue()
+        object_name = path[(len(bucket) + 1) :]
+
+        token = self._access_token_getter()
+        headers = {
+            "Content-Type": "application/octet-stream",
+            "Content-Length": str(len(data)),
+        }
+        if token:
+            headers["Authorization"] = f"Bearer {token}"
+
+        response = self._session.post(
+            url,
+            params={"uploadType": "media", "name": object_name},
+            headers=headers,
+            data=data,
+            timeout=60,
+        )
+
+        if response.status_code not in (200, 201):
+            raise IOError(
+                f"Failed to write '{self._path}' - status {response.status_code}: {response.text}"
+            )
+
+        self._closed = True
+        super().close()
+
+
+class _GcsInputFile(InputFile):
+    def __init__(
+        self, location: str, session: requests.Session, access_token_getter: Callable[[], str]
+    ):
+        # read entire bytes via optimized session
+        try:
+            stream = _GcsInputStream(location, session, access_token_getter)
+            data = stream.read()
+            super().__init__(location, data)
+        except FileNotFoundError:
+            super().__init__(location, None)
+
+
+class _GcsOutputFile(OutputFile):
+    def __init__(
+        self, location: str, session: requests.Session, access_token_getter: Callable[[], str]
+    ):
+        super().__init__(location)
+        self._location = location
+        self._session = session
+        self._access_token_getter = access_token_getter
+
+    def create(self):
+        return _GcsOutputStream(self._location, self._session, self._access_token_getter)
+
+
+class GcsFileIO(FileIO):
+    """Optimized HTTP-backed GCS FileIO.
+
+    Implements a blackhole/capture pattern for manifest files and exposes
+    `new_input`, `new_output`, `delete`, `exists`.
+    """
+
+    def __init__(self):
+        # Track manifest paths and captured manifests
+        self.manifest_paths: list[str] = []
+        self.captured_manifests: list[tuple[str, bytes]] = []
+
+        # Prepare requests session and set up credential refresh helper (token may expire)
+        self._credentials = _get_storage_credentials()
+        self._access_token = None
+
+        def _refresh_credentials():
+            try:
+                if not self._credentials.valid:
+                    req = Request()
+                    self._credentials.refresh(req)
+                self._access_token = self._credentials.token
+            except Exception as e:
+                logger.warning("Failed to refresh GCS credentials: %s", e)
+                self._access_token = None
+
+        self._refresh_credentials = _refresh_credentials
+
+        def get_access_token():
+            # Refresh credentials on demand to avoid using expired tokens
+            self._refresh_credentials()
+            return self._access_token
+
+        self.get_access_token = get_access_token
+
+        self._session = requests.session()
+        adapter = HTTPAdapter(pool_connections=100, pool_maxsize=100)
+        self._session.mount("https://", adapter)
+
+    def new_input(self, location: str) -> InputFile:
+        return _GcsInputFile(location, self._session, self.get_access_token)
+
+    def new_output(self, location: str) -> OutputFile:
+        logger.info(f"new_output -> {location}")
+
+        return _GcsOutputFile(location, self._session, self.get_access_token)
+
+    def delete(self, location: Union[str, InputFile, OutputFile]) -> None:
+        if isinstance(location, (InputFile, OutputFile)):
+            location = location.location
+
+        path = location
+        if path.startswith("gs://"):
+            path = path[5:]
+
+        bucket = path.split("/", 1)[0]
+        object_full_path = urllib.parse.quote(path[(len(bucket) + 1) :], safe="")
+        url = f"https://storage.googleapis.com/storage/v1/b/{bucket}/o/{object_full_path}"
+
+        token = self.get_access_token()
+        headers = {}
+        if token:
+            headers["Authorization"] = f"Bearer {token}"
+        response = self._session.delete(url, headers=headers, timeout=10)
+
+        if response.status_code not in (204, 404):
+            raise IOError(f"Failed to delete '{location}' - status {response.status_code}")
+
+    def exists(self, location: str) -> bool:
+        path = location
+        if path.startswith("gs://"):
+            path = path[5:]
+
+        bucket = path.split("/", 1)[0]
+        object_full_path = urllib.parse.quote(path[(len(bucket) + 1) :], safe="")
+        url = f"https://storage.googleapis.com/{bucket}/{object_full_path}"
+
+        token = self.get_access_token()
+        headers = {}
+        if token:
+            headers["Authorization"] = f"Bearer {token}"
+        response = self._session.head(url, headers=headers, timeout=10)
+        return response.status_code == 200