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

spiral/tables/debug/manifests.py

@@ -0,0 +1,70 @@
+from spiral import datetime_
+from spiral.core.table import TableScan
+from spiral.core.table.manifests import FragmentManifest
+from spiral.tables.debug.metrics import _format_bytes
+
+
+def display_manifests(scan: TableScan):
+    """Display all manifests in a scan."""
+    if len(scan.table_ids()) != 1:
+        raise NotImplementedError("Multiple table scans are not supported.")
+    table_id = scan.table_ids()[0]
+
+    key_space_manifest: FragmentManifest = scan.key_space_scan(table_id).manifest
+    _table_of_fragments(
+        key_space_manifest,
+        title="Key Space manifest",
+    )
+
+    for column_group in scan.column_groups():
+        column_group_manifest: FragmentManifest = scan.column_group_scan(column_group).manifest
+        _table_of_fragments(
+            column_group_manifest,
+            title=f"Column Group manifest for {str(column_group)}",
+        )
+
+
+def _table_of_fragments(manifest: FragmentManifest, title: str):
+    """Display fragments in a formatted table."""
+    # Calculate summary statistics
+    total_size = sum(fragment.size_bytes for fragment in manifest)
+    total_metadata_size = sum(len(fragment.format_metadata or b"") for fragment in manifest)
+    fragment_count = len(manifest)
+    avg_size = total_size / fragment_count if fragment_count > 0 else 0
+
+    # Print title and summary
+    print(f"\n\n{title}")
+    print(
+        f"{fragment_count} fragments, "
+        f"total: {_format_bytes(total_size)}, "
+        f"avg: {_format_bytes(int(avg_size))}, "
+        f"metadata: {_format_bytes(total_metadata_size)}"
+    )
+    print("=" * 120)
+
+    # Print header
+    print(
+        f"{'ID':<30} {'Size (Metadata)':<20} {'Format':<10} {'Key Span':<10} "
+        f"{'Level':<5} {'Committed At':<20} {'Compacted At':<20}"
+    )
+    print("=" * 120)
+
+    # Print each fragment
+    for fragment in manifest:
+        committed_str = str(datetime_.from_timestamp_micros(fragment.committed_at)) if fragment.committed_at else "N/A"
+        compacted_str = str(datetime_.from_timestamp_micros(fragment.compacted_at)) if fragment.compacted_at else "N/A"
+
+        size_with_metadata = (
+            f"{_format_bytes(fragment.size_bytes)} ({_format_bytes(len(fragment.format_metadata or b''))})"
+        )
+        key_span = f"{fragment.key_span.begin}..{fragment.key_span.end}"
+
+        print(
+            f"{fragment.id:<30} "
+            f"{size_with_metadata:<20} "
+            f"{str(fragment.format):<10} "
+            f"{key_span:<10} "
+            f"{str(fragment.level):<5} "
+            f"{committed_str:<20} "
+            f"{compacted_str:<20}"
+        )

spiral/tables/debug/metrics.py

@@ -0,0 +1,56 @@
+from typing import Any
+
+
+def display_metrics(metrics: dict[str, Any]) -> None:
+    """Display metrics in a formatted table."""
+    print(
+        f"{'Metric':<40} {'Type':<10} {'Count':<8} {'Avg':<12} {'Min':<12} "
+        f"{'Max':<12} {'P95':<12} {'P99':<12} {'StdDev':<12}"
+    )
+    print("=" * 140)
+
+    for metric_name, data in sorted(metrics.items()):
+        metric_type = data["type"]
+        count = data["count"]
+        avg = _format_value(data["avg"], metric_type, metric_name)
+        min_val = _format_value(data["min"], metric_type, metric_name)
+        max_val = _format_value(data["max"], metric_type, metric_name)
+        p95 = _format_value(data["p95"], metric_type, metric_name)
+        p99 = _format_value(data["p99"], metric_type, metric_name)
+        stddev = _format_value(data["stddev"], metric_type, metric_name)
+
+        print(
+            f"{metric_name:<40} {metric_type:<10} {count:<8} {avg:<12} {min_val:<12} "
+            f"{max_val:<12} {p95:<12} {p99:<12} {stddev:<12}"
+        )
+
+
+def _format_duration(nanoseconds: float) -> str:
+    """Convert nanoseconds to human-readable duration."""
+    if nanoseconds >= 1_000_000_000:
+        return f"{nanoseconds / 1_000_000_000:.2f}s"
+    elif nanoseconds >= 1_000_000:
+        return f"{nanoseconds / 1_000_000:.2f}ms"
+    elif nanoseconds >= 1_000:
+        return f"{nanoseconds / 1_000:.2f}μs"
+    else:
+        return f"{nanoseconds:.0f}ns"
+
+
+def _format_bytes(bytes_value: float) -> str:
+    """Convert bytes to human-readable size."""
+    for unit in ["B", "KB", "MB", "GB"]:
+        if bytes_value < 1024:
+            return f"{bytes_value:.1f}{unit}"
+        bytes_value /= 1024
+    return f"{bytes_value:.1f}TB"
+
+
+def _format_value(value: float, metric_type: str, metric_name: str) -> str:
+    """Format a value based on metric type and name."""
+    if metric_type == "timer" or "duration" in metric_name:
+        return _format_duration(value)
+    elif "bytes" in metric_name:
+        return _format_bytes(value)
+    else:
+        return f"{value:,.0f}"

spiral/{debug.py → tables/debug/scan.py}

@@ -1,8 +1,8 @@
 from datetime import datetime
 
-from spiral.core.core import TableScan
-from spiral.core.manifests import FragmentFile, FragmentManifest
-from spiral.core.spec import Key, KeyRange
+from spiral.core.table import TableScan
+from spiral.core.table.manifests import FragmentFile, FragmentManifest
+from spiral.core.table.spec import Key
 from spiral.types_ import Timestamp
 
 
@@ -30,7 +30,7 @@ def show_scan(scan: TableScan):
         for i in range(len(cg_manifest)):
             fragment_file = cg_manifest[i]
             key_points.add(fragment_file.key_extent.min)
-        key_points.add(fragment_file.key_extent.max)
+            key_points.add(fragment_file.key_extent.max)
 
     # Make sure split points exist in all key points.
     for s in splits[:-1]:  # Don't take the last end.
@@ -44,9 +44,7 @@ def show_scan(scan: TableScan):
         show_manifest(cg_scan.manifest, scope=".".join(cg.path[1:]), key_points=key_points, splits=splits)
 
 
-def show_manifest(
-    manifest: FragmentManifest, scope: str = None, key_points: list[Key] = None, splits: list[KeyRange] = None
-):
+def show_manifest(manifest: FragmentManifest, scope: str = None, key_points: list[Key] = None, splits: list = None):
     try:
         import matplotlib.patches as patches
         import matplotlib.pyplot as plt
@@ -157,10 +155,9 @@ def _get_fragment_legend(manifest_file: FragmentFile):
             f"key_min: {manifest_file.key_extent.min}",
             f"key_max: {manifest_file.key_extent.max}",
             f"format: {manifest_file.format}",
-            f"level: {manifest_file.fs_level}",
+            f"level: {manifest_file.level}",
             f"committed_at: {_format_timestamp(manifest_file.committed_at)}",
             f"compacted_at: {_format_timestamp(manifest_file.compacted_at)}",
-            f"fs_id: {manifest_file.fs_id}",
             f"ks_id: {manifest_file.ks_id}",
         ]
     )

spiral/tables/maintenance.py

@@ -0,0 +1,12 @@
+from spiral.core.table import TableMaintenance
+
+
+class Maintenance:
+    """Spiral table maintenance."""
+
+    def __init__(self, maintenance: TableMaintenance):
+        self._maintenance = maintenance
+
+    def flush_wal(self):
+        """Flush the write-ahead log."""
+        self._maintenance.flush_wal()

spiral/tables/scan.py

@@ -0,0 +1,193 @@
+from collections.abc import Iterator
+from typing import TYPE_CHECKING, Any
+
+import pyarrow as pa
+from datasets import DatasetInfo, Features
+
+from spiral.core.table import KeyRange, TableScan
+from spiral.core.table.spec import Schema
+from spiral.settings import CI, DEV
+
+if TYPE_CHECKING:
+    import dask.dataframe as dd
+    import pandas as pd
+    import polars as pl
+    from datasets import iterable_dataset
+
+
+class Scan:
+    """Scan object."""
+
+    def __init__(
+        self,
+        scan: TableScan,
+    ):
+        # NOTE(ngates): this API is a little weird. e.g. if the query doesn't define an asof, it is resolved
+        #  when we wrap it into a core.Scan. Should we expose a Query object in the Python API that's reusable
+        #  and will re-resolve the asof? Or should we just expose a scan that fixes the asof at construction time?
+        self._scan = scan
+
+    @property
+    def metrics(self) -> dict[str, Any]:
+        """Returns metrics about the scan."""
+        return self._scan.metrics()
+
+    @property
+    def schema(self) -> Schema:
+        """Returns the schema of the scan."""
+        return self._scan.schema()
+
+    def is_empty(self) -> bool:
+        """Check if the Spiral is empty for the given key range.
+
+        **IMPORTANT**: False negatives are possible, but false positives are not,
+            i.e. is_empty can return False and scan can return zero rows.
+        """
+        return self._scan.is_empty()
+
+    def to_record_batches(
+        self,
+        key_table: pa.Table | pa.RecordBatchReader | None = None,
+        batch_size: int | None = None,
+        batch_readahead: int | None = None,
+    ) -> pa.RecordBatchReader:
+        """Read as a stream of RecordBatches.
+
+        Args:
+            key_table: a table of keys to "take" (including aux columns for cell-push-down).
+                If None, the scan will be executed without a key table.
+            batch_size: the maximum number of rows per returned batch.
+                IMPORTANT: This is currently only respected when the key_table is used. If key table is a
+                    RecordBatchReader, the batch_size argument must be None, and the existing batching is respected.
+            batch_readahead: the number of batches to prefetch in the background.
+        """
+        if isinstance(key_table, pa.RecordBatchReader):
+            if batch_size is not None:
+                raise ValueError(
+                    "batch_size must be None when key_table is a RecordBatchReader, the existing batching is respected."
+                )
+        elif isinstance(key_table, pa.Table):
+            key_table = key_table.to_reader(max_chunksize=batch_size)
+
+        return self._scan.to_record_batches(key_table=key_table, batch_readahead=batch_readahead)
+
+    def to_table(
+        self,
+        key_table: pa.Table | pa.RecordBatchReader | None = None,
+    ) -> pa.Table:
+        """Read into a single PyArrow Table.
+
+        Args:
+            key_table: a table of keys to "take" (including aux columns for cell-push-down).
+                If None, the scan will be executed without a key table.
+        """
+        # NOTE: Evaluates fully on Rust side which improved debuggability.
+        if DEV and not CI and key_table is None:
+            rb = self._scan.to_record_batch()
+            return pa.Table.from_batches([rb])
+
+        return self.to_record_batches(key_table=key_table).read_all()
+
+    def to_dask(self) -> "dd.DataFrame":
+        """Read into a Dask DataFrame.
+
+        Requires the `dask` package to be installed.
+        """
+        import dask.dataframe as dd
+        import pandas as pd
+
+        def _read_key_range(key_range: KeyRange) -> pd.DataFrame:
+            # TODO(ngates): we need a way to preserve the existing asofs? Should we copy CoreScan instead of Query?
+            raise NotImplementedError()
+
+        # Fetch a set of partition ranges
+        return dd.from_map(_read_key_range, self.split())
+
+    def to_pandas(self) -> "pd.DataFrame":
+        """Read into a Pandas DataFrame.
+
+        Requires the `pandas` package to be installed.
+        """
+        return self.to_table().to_pandas()
+
+    def to_polars(self) -> "pl.DataFrame":
+        """Read into a Polars DataFrame.
+
+        Requires the `polars` package to be installed.
+        """
+        import polars as pl
+
+        # TODO(marko): This should support lazy dataframe.
+        return pl.from_arrow(self.to_record_batches())
+
+    def to_pytorch(
+        self,
+        batch_readahead: int | None = None,
+        shuffle_batch_size: int | None = None,
+        shuffle_pool_num_rows: int | None = None,
+    ) -> "iterable_dataset.IterableDataset":
+        """Returns an iterable dataset that can be used to build a PyTorch DataLoader.
+
+        Args:
+            batch_readahead: Number of batches to prefetch in the background.
+            shuffle_batch_size: read granularity of number of rows for a shuffled scan. If left as
+            None along with shuffle_pool_num_rows=None, shuffling is disabled.
+            shuffle_pool_num_rows: Pool size for shuffling batches.
+        """
+        from datasets.iterable_dataset import ArrowExamplesIterable, IterableDataset
+
+        def _generate_tables(**kwargs) -> Iterator[tuple[int, pa.Table]]:
+            if shuffle_batch_size is None and shuffle_pool_num_rows is None:
+                stream = self.to_record_batches(
+                    batch_readahead=batch_readahead,
+                )
+            else:
+                stream = self._scan.to_shuffled_record_batches(
+                    batch_readahead, shuffle_batch_size, shuffle_pool_num_rows
+                )
+
+            # This key is unused when training with IterableDataset.
+            # Default implementation returns shard id, e.g. parquet row group id.
+            for i, rb in enumerate(stream):
+                yield i, pa.Table.from_batches([rb], stream.schema)
+
+        def _hf_compatible_schema(schema: pa.Schema) -> pa.Schema:
+            """
+            Replace string-view columns in the schema with strings. We do use this converted schema
+            as Features in the returned Dataset.
+            Remove this method once we have https://github.com/huggingface/datasets/pull/7718
+            """
+            new_fields = [
+                pa.field(field.name, pa.string(), nullable=field.nullable, metadata=field.metadata)
+                if field.type == pa.string_view()
+                else field
+                for field in schema
+            ]
+            return pa.schema(new_fields)
+
+        # NOTE: generate_tables_fn type annotations are wrong, return type must be an iterable of tuples.
+        ex_iterable = ArrowExamplesIterable(generate_tables_fn=_generate_tables, kwargs={})
+        info = DatasetInfo(features=Features.from_arrow_schema(_hf_compatible_schema(self.schema.to_arrow())))
+        return IterableDataset(ex_iterable=ex_iterable, info=info)
+
+    def _split(self) -> list[KeyRange]:
+        # Splits the scan into a set of key ranges.
+        return self._scan.split()
+
+    def _debug(self):
+        # Visualizes the scan, mainly for debugging purposes.
+        from spiral.tables.debug.scan import show_scan
+
+        show_scan(self._scan)
+
+    def _dump_manifests(self):
+        # Print manifests in a human-readable format.
+        from spiral.tables.debug.manifests import display_manifests
+
+        display_manifests(self._scan)
+
+    def _dump_metrics(self):
+        # Print metrics in a human-readable format.
+        from spiral.tables.debug.metrics import display_metrics
+
+        display_metrics(self.metrics)

spiral/tables/snapshot.py

@@ -0,0 +1,78 @@
+from typing import TYPE_CHECKING
+
+from spiral.core.table import TableSnapshot
+from spiral.expressions import ExprLike
+from spiral.tables.scan import Scan
+from spiral.types_ import Timestamp
+
+if TYPE_CHECKING:
+    import duckdb
+    import polars as pl
+    import pyarrow.dataset
+
+    from spiral.tables import Tables
+    from spiral.tables.table import Table
+
+
+class Snapshot:
+    """Spiral table snapshot.
+
+    A snapshot represents a point-in-time view of a table.
+    """
+
+    def __init__(self, tables: "Tables", snapshot: TableSnapshot):
+        self._tables = tables
+        self._snapshot = snapshot
+
+    @property
+    def asof(self) -> Timestamp:
+        """Returns the asof timestamp of the snapshot."""
+        return self._snapshot.asof
+
+    @property
+    def client(self) -> "Tables":
+        """Returns the client used by the snapshot."""
+        return self._tables
+
+    @property
+    def table(self) -> "Table":
+        """Returns the table associated with the snapshot."""
+        from spiral.tables.table import Table
+
+        return Table(self._tables, self._snapshot.table)
+
+    def to_dataset(self) -> "pyarrow.dataset.Dataset":
+        """Returns a PyArrow Dataset representing the table."""
+        from .dataset import TableDataset
+
+        return TableDataset(self)
+
+    def to_polars(self) -> "pl.LazyFrame":
+        """Returns a Polars LazyFrame for the Spiral table."""
+        import polars as pl
+
+        return pl.scan_pyarrow_dataset(self.to_dataset())
+
+    def to_duckdb(self) -> "duckdb.DuckDBPyRelation":
+        """Returns a DuckDB relation for the Spiral table."""
+        import duckdb
+
+        return duckdb.from_arrow(self.to_dataset())
+
+    def scan(
+        self,
+        *projections: ExprLike,
+        where: ExprLike | None = None,
+        exclude_keys: bool = False,
+    ) -> Scan:
+        """Reads the snapshot. If projections are not provided, the entire table is read."""
+        if not projections:
+            # Use table as the default projection.
+            projections = [self._snapshot.table.__expr__]
+
+        return self._tables.scan(
+            *projections,
+            where=where,
+            asof=self._snapshot.asof,
+            exclude_keys=exclude_keys,
+        )

spiral/tables/table.py

@@ -0,0 +1,157 @@
+from datetime import datetime
+from typing import TYPE_CHECKING
+
+from spiral.core.table import Table as CoreTable
+from spiral.core.table.spec import Schema
+from spiral.expressions.base import Expr, ExprLike
+from spiral.settings import settings
+from spiral.tables.maintenance import Maintenance
+from spiral.tables.scan import Scan
+from spiral.tables.snapshot import Snapshot
+from spiral.tables.transaction import Transaction
+
+if TYPE_CHECKING:
+    from spiral.tables import Tables
+
+
+class Table(Expr):
+    """API for interacting with a SpiralDB's Table.
+
+    Different catalog implementations should ultimately construct a Table object.
+    """
+
+    # TODO(marko): Make identifier required.
+    def __init__(self, tables: "Tables", table: CoreTable, *, identifier: str | None = None):
+        super().__init__(table.__expr__)
+
+        self._tables = tables
+        self._table = table
+        self._identifier = identifier
+        self._key_schema = self._table.key_schema
+        self._key_columns = set(self._key_schema.names)
+
+    @property
+    def client(self) -> "Tables":
+        """Returns the client used by the table."""
+        return self._tables
+
+    @property
+    def table_id(self) -> str:
+        return self._table.id
+
+    @property
+    def identifier(self) -> str:
+        """Returns the fully qualified identifier of the table."""
+        return self._identifier or self._table.id
+
+    @property
+    def dataset(self) -> str | None:
+        """Returns the dataset of the table."""
+        if self._identifier is None:
+            return None
+        _, dataset, _ = self._identifier.split(".")
+        return dataset
+
+    @property
+    def name(self) -> str | None:
+        """Returns the name of the table."""
+        if self._identifier is None:
+            return None
+        _, _, name = self._identifier.split(".")
+        return name
+
+    @property
+    def last_modified_at(self) -> int:
+        return self._table.get_wal(asof=None).last_modified_at
+
+    def __str__(self):
+        return self.identifier
+
+    def __repr__(self):
+        return f'Table("{self.identifier}")'
+
+    def __getitem__(self, item: str) -> Expr:
+        from spiral import expressions as se
+
+        if item in self._key_columns:
+            return se.key(name=item)
+
+        return super().__getitem__(item)
+
+    def select(self, *paths: str, exclude: list[str] = None) -> "Expr":
+        # Override an expression select in the root column group to split between keys and columns.
+        if exclude is not None:
+            if set(exclude) & self._key_columns:
+                raise ValueError(
+                    "Cannot use 'exclude' arg with key columns. Use 'exclude_keys' and an explicit select of keys."
+                )
+
+        key_paths = set(paths) & self._key_columns
+        other_paths = set(paths) - key_paths
+        if not key_paths:
+            return super().select(*paths, exclude=exclude)
+
+        from spiral import expressions as se
+
+        return se.merge(se.pack({key: se.key(key) for key in key_paths}), super().select(*other_paths, exclude=exclude))
+
+    @property
+    def key_schema(self) -> Schema:
+        """Returns the key schema of the table."""
+        return self._key_schema
+
+    @property
+    def schema(self) -> Schema:
+        """Returns the FULL schema of the table.
+
+        NOTE: This can be expensive for large tables.
+        """
+        return self._table.get_schema(asof=None)
+
+    def scan(
+        self,
+        *projections: ExprLike,
+        where: ExprLike | None = None,
+        asof: datetime | int | None = None,
+        exclude_keys: bool = False,
+    ) -> Scan:
+        """Reads the table. If projections are not provided, the entire table is read."""
+        if not projections:
+            projections = [self]
+
+        return self._tables.scan(*projections, where=where, asof=asof, exclude_keys=exclude_keys)
+
+    def write(
+        self,
+        expr: ExprLike,
+        *,
+        partition_size_bytes: int | None = None,
+    ) -> None:
+        """Write an item to the table inside a single transaction.
+
+        :param expr: The expression to write. Must evaluate to a struct array.
+        :param partition_size_bytes: The maximum partition size in bytes.
+        """
+        with self.txn() as txn:
+            txn.write(
+                expr,
+                partition_size_bytes=partition_size_bytes,
+            )
+
+    def snapshot(self, asof: datetime | int | None = None) -> Snapshot:
+        """Returns a snapshot of the table at the given timestamp."""
+        if isinstance(asof, datetime):
+            asof = int(asof.timestamp() * 1_000_000)
+        return Snapshot(self._tables, self._table.get_snapshot(asof=asof))
+
+    def txn(self) -> Transaction:
+        """Begins a new transaction. Transaction must be committed for writes to become visible.
+
+        IMPORTANT: While transaction can be used to atomically write data to the table,
+             it is important that the primary key columns are unique within the transaction.
+        """
+        return Transaction(self._tables._spiral.open_transaction(self._table, settings().file_format))
+
+    def maintenance(self) -> Maintenance:
+        """Access maintenance operations for a table."""
+        return Maintenance(self._tables._spiral.open_maintenance(self._table, settings().file_format))

spiral/tables/transaction.py

@@ -0,0 +1,52 @@
+from typing import TYPE_CHECKING
+
+from spiral.core.table import TableTransaction
+
+if TYPE_CHECKING:
+    from spiral.expressions.base import ExprLike
+
+
+class Transaction:
+    """Spiral table transaction.
+
+    IMPORTANT: While transaction can be used to atomically write data to the table,
+            it is important that the primary key columns are unique within the transaction.
+    """
+
+    def __init__(self, transaction: TableTransaction):
+        self._transaction = transaction
+
+    @property
+    def status(self) -> str:
+        """The status of the transaction."""
+        return self._transaction.status
+
+    def __enter__(self):
+        return self
+
+    def __exit__(self, exc_type, exc_value, traceback):
+        if exc_type is None:
+            self._transaction.commit()
+        else:
+            self._transaction.abort()
+
+    def write(self, expr: "ExprLike", *, partition_size_bytes: int | None = None):
+        """Write an item to the table inside a single transaction.
+
+        :param expr: The expression to write. Must evaluate to a struct array.
+        :param partition_size_bytes: The maximum partition size in bytes.
+            If not provided, the default partition size is used.
+        """
+        from spiral import expressions as se
+
+        expr = se.lift(expr)
+
+        self._transaction.write(expr.__expr__, partition_size_bytes=partition_size_bytes)
+
+    def commit(self):
+        """Commit the transaction."""
+        self._transaction.commit()
+
+    def abort(self):
+        """Abort the transaction."""
+        self._transaction.abort()