pyspiral 0.6.6__cp312-abi3-manylinux_2_17_x86_64.manylinux2014_x86_64.whl

spiral/dataset.py

@@ -0,0 +1,255 @@
+from typing import Any
+
+import pyarrow as pa
+import pyarrow.compute as pc
+import pyarrow.dataset as ds
+
+from spiral.scan import Scan
+from spiral.snapshot import Snapshot
+
+
+class Dataset(ds.Dataset):
+    def __init__(self, snapshot: Snapshot):
+        self._snapshot = snapshot
+        self._table = snapshot.table
+        self._schema: pa.Schema = self._snapshot.schema().to_arrow()
+
+        # We don't actually initialize a Dataset, we just implement enough of the API
+        # to fool both DuckDB and Polars.
+        # super().__init__()
+        self._last_scan = None
+
+    @property
+    def schema(self) -> pa.Schema:
+        return self._schema
+
+    def count_rows(
+        self,
+        filter: pc.Expression | None = None,
+        batch_size: int | None = None,
+        batch_readahead: int | None = None,
+        fragment_readahead: int | None = None,
+        fragment_scan_options: ds.FragmentScanOptions | None = None,
+        use_threads: bool = True,
+        memory_pool: pa.MemoryPool = None,
+    ):
+        return self.scanner(
+            None,
+            filter,
+            batch_size,
+            batch_readahead,
+            fragment_readahead,
+            fragment_scan_options,
+            use_threads,
+            memory_pool,
+        ).count_rows()
+
+    def filter(self, expression: pc.Expression) -> "Dataset":
+        raise NotImplementedError("filter not implemented")
+
+    def get_fragments(self, filter: pc.Expression | None = None):
+        """TODO(ngates): perhaps we should return ranges as per our split API?"""
+        raise NotImplementedError("get_fragments not implemented")
+
+    def head(
+        self,
+        num_rows: int,
+        columns: list[str] | None = None,
+        filter: pc.Expression | None = None,
+        batch_size: int | None = None,
+        batch_readahead: int | None = None,
+        fragment_readahead: int | None = None,
+        fragment_scan_options: ds.FragmentScanOptions | None = None,
+        use_threads: bool = True,
+        memory_pool: pa.MemoryPool = None,
+    ):
+        return self.scanner(
+            columns,
+            filter,
+            batch_size,
+            batch_readahead,
+            fragment_readahead,
+            fragment_scan_options,
+            use_threads,
+            memory_pool,
+        ).head(num_rows)
+
+    def join(
+        self,
+        right_dataset,
+        keys,
+        right_keys=None,
+        join_type=None,
+        left_suffix=None,
+        right_suffix=None,
+        coalesce_keys=True,
+        use_threads=True,
+    ):
+        raise NotImplementedError("join not implemented")
+
+    def join_asof(self, right_dataset, on, by, tolerance, right_on=None, right_by=None):
+        raise NotImplementedError("join_asof not implemented")
+
+    def replace_schema(self, schema: pa.Schema) -> "Dataset":
+        raise NotImplementedError("replace_schema not implemented")
+
+    def scanner(
+        self,
+        columns: list[str] | None = None,
+        filter: pc.Expression | None = None,
+        batch_size: int | None = None,
+        batch_readahead: int | None = None,
+        fragment_readahead: int | None = None,
+        fragment_scan_options: ds.FragmentScanOptions | None = None,
+        use_threads: bool = True,
+        memory_pool: pa.MemoryPool = None,
+    ) -> "TableScanner":
+        from spiral.substrait_ import SubstraitConverter
+
+        # Extract the substrait expression so we can convert it to a Spiral expression
+        if filter is not None:
+            filter = SubstraitConverter(self._table, self._schema, self._table.key_schema.to_arrow()).convert(
+                filter.to_substrait(self._schema, allow_arrow_extensions=True),
+            )
+
+        scan = (
+            self._table.spiral.scan(
+                {c: self._table[c] for c in columns},
+                where=filter,
+                asof=self._snapshot.asof,
+            )
+            if columns
+            else self._table.spiral.scan(
+                self._table,
+                where=filter,
+                asof=self._snapshot.asof,
+            )
+        )
+        self._last_scan = scan
+
+        return TableScanner(scan)
+
+    def sort_by(self, sorting, **kwargs):
+        raise NotImplementedError("sort_by not implemented")
+
+    def take(
+        self,
+        indices: pa.Array | Any,
+        columns: list[str] | None = None,
+        filter: pc.Expression | None = None,
+        batch_size: int | None = None,
+        batch_readahead: int | None = None,
+        fragment_readahead: int | None = None,
+        fragment_scan_options: ds.FragmentScanOptions | None = None,
+        use_threads: bool = True,
+        memory_pool: pa.MemoryPool = None,
+    ):
+        return self.scanner(
+            columns,
+            filter,
+            batch_size,
+            batch_readahead,
+            fragment_readahead,
+            fragment_scan_options,
+            use_threads,
+            memory_pool,
+        ).take(indices)
+
+    def to_batches(
+        self,
+        columns: list[str] | None = None,
+        filter: pc.Expression | None = None,
+        batch_size: int | None = None,
+        batch_readahead: int | None = None,
+        fragment_readahead: int | None = None,
+        fragment_scan_options: ds.FragmentScanOptions | None = None,
+        use_threads: bool = True,
+        memory_pool: pa.MemoryPool = None,
+    ):
+        return self.scanner(
+            columns,
+            filter,
+            batch_size,
+            batch_readahead,
+            fragment_readahead,
+            fragment_scan_options,
+            use_threads,
+            memory_pool,
+        ).to_batches()
+
+    def to_table(
+        self,
+        columns=None,
+        filter: pc.Expression | None = None,
+        batch_size: int | None = None,
+        batch_readahead: int | None = None,
+        fragment_readahead: int | None = None,
+        fragment_scan_options: ds.FragmentScanOptions | None = None,
+        use_threads: bool = True,
+        memory_pool: pa.MemoryPool = None,
+    ):
+        return self.scanner(
+            columns,
+            filter,
+            batch_size,
+            batch_readahead,
+            fragment_readahead,
+            fragment_scan_options,
+            use_threads,
+            memory_pool,
+        ).to_table()
+
+
+class TableScanner(ds.Scanner):
+    """A PyArrow Dataset Scanner that reads from a Spiral Table."""
+
+    def __init__(
+        self,
+        scan: Scan,
+        key_table: pa.Table | pa.RecordBatchReader | None = None,
+    ):
+        self._scan = scan
+        self._schema = scan.schema
+        self.key_table = key_table
+
+        # We don't actually initialize a Dataset, we just implement enough of the API
+        # to fool both DuckDB and Polars.
+        # super().__init__()
+
+    @property
+    def schema(self):
+        return self._schema
+
+    def count_rows(self):
+        # TODO(ngates): is there a faster way to count rows?
+        return sum(len(batch) for batch in self.to_reader())
+
+    def head(self, num_rows: int):
+        """Return the first `num_rows` rows of the dataset."""
+        reader = self.to_reader()
+        batches = []
+        row_count = 0
+        for batch in reader:
+            if row_count + len(batch) > num_rows:
+                batches.append(batch.slice(0, num_rows - row_count))
+                break
+            row_count += len(batch)
+            batches.append(batch)
+        return pa.Table.from_batches(batches, schema=reader.schema)
+
+    def scan_batches(self):
+        raise NotImplementedError("scan_batches not implemented")
+
+    def take(self, indices):
+        # TODO(ngates): can we defer take until after we've constructed the scan?
+        #  Or should this we delay constructing the Spiral Table.scan?
+        raise NotImplementedError("take not implemented")
+
+    def to_batches(self):
+        return self.to_reader()
+
+    def to_reader(self):
+        return self._scan.to_record_batches(key_table=self.key_table)
+
+    def to_table(self):
+        return self.to_reader().read_all()

spiral/datetime_.py

@@ -0,0 +1,27 @@
+import warnings
+from datetime import UTC, datetime, timedelta, tzinfo
+
+_THE_EPOCH = datetime.fromtimestamp(0, tz=UTC)
+
+
+def local_tz() -> tzinfo:
+    """Determine this machine's local timezone."""
+    tz = datetime.now().astimezone().tzinfo
+    if tz is None:
+        raise ValueError("Could not determine this machine's local timezone.")
+    return tz
+
+
+def timestamp_micros(instant: datetime) -> int:
+    """The number of microseconds between the epoch and the given instant."""
+    if instant.tzinfo is None:
+        warnings.warn("assuming timezone-naive datetime is local time", stacklevel=2)
+        instant = instant.replace(tzinfo=local_tz())
+    return (instant - _THE_EPOCH) // timedelta(microseconds=1)
+
+
+def from_timestamp_micros(ts: int) -> datetime:
+    """Convert a timestamp in microseconds to a datetime."""
+    if ts < 0:
+        raise ValueError("Timestamp must be non-negative")
+    return _THE_EPOCH + timedelta(microseconds=ts)

spiral/debug/manifests.py

@@ -0,0 +1,87 @@
+from rich.console import Console
+from rich.table import Table
+
+from spiral import datetime_
+from spiral.core.table import Scan
+from spiral.core.table.manifests import FragmentManifest
+from spiral.core.table.spec import ColumnGroup
+from spiral.debug.metrics import _format_bytes
+
+
+def display_scan_manifests(scan: Scan):
+    """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 = scan.key_space_state(table_id).manifest
+    column_group_manifests = [
+        (column_group, scan.column_group_state(column_group).manifest) for column_group in scan.column_groups()
+    ]
+
+    display_manifests(key_space_manifest, column_group_manifests)
+
+
+def display_manifests(
+    key_space_manifest: FragmentManifest, column_group_manifests: list[tuple[ColumnGroup, FragmentManifest]]
+):
+    _table_of_fragments(
+        key_space_manifest,
+        title="Key Space manifest",
+    )
+
+    for column_group, column_group_manifest in column_group_manifests:
+        _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
+    console = Console()
+    console.print(f"\n\n{title}")
+    console.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)}"
+    )
+
+    # Create rich table
+    table = Table(title=None, show_header=True, header_style="bold")
+    table.add_column("ID", style="cyan", no_wrap=True)
+    table.add_column("Size (Metadata)", justify="right")
+    table.add_column("Format", justify="center")
+    table.add_column("Key Span", justify="center")
+    table.add_column("Level", justify="center")
+    table.add_column("Committed At", justify="center")
+    table.add_column("Compacted At", justify="center")
+
+    # Add each fragment as a row
+    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}"
+
+        table.add_row(
+            fragment.id,
+            size_with_metadata,
+            str(fragment.format),
+            key_span,
+            str(fragment.level),
+            committed_str,
+            compacted_str,
+        )
+
+    console.print(table)

spiral/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/scan.py

@@ -0,0 +1,266 @@
+from datetime import datetime
+
+from spiral.core.table import Scan
+from spiral.core.table.manifests import FragmentFile, FragmentManifest
+from spiral.core.table.spec import Key
+from spiral.types_ import Timestamp
+
+
+def show_scan(scan: Scan):
+    """Displays a scan in a way that is useful for debugging."""
+    table_ids = scan.table_ids()
+    if len(table_ids) > 1:
+        raise NotImplementedError("Multiple table scan is not supported.")
+    table_id = table_ids[0]
+    column_groups = scan.column_groups()
+
+    splits = scan.splits()
+    key_space_state = scan.key_space_state(table_id)
+
+    # Collect all key bounds from all manifests. This makes sure all visualizations are aligned.
+    key_points = set()
+    key_space_manifest = key_space_state.manifest
+    for i in range(len(key_space_manifest)):
+        fragment_file = key_space_manifest[i]
+        key_points.add(fragment_file.key_extent.min)
+        key_points.add(fragment_file.key_extent.max)
+    for cg in column_groups:
+        cg_scan = scan.column_group_state(cg)
+        cg_manifest = cg_scan.manifest
+        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)
+
+    # Make sure split points exist in all key points.
+    for s in splits[:-1]:  # Don't take the last end.
+        key_points.add(s.end)
+    key_points = list(sorted(key_points))
+
+    show_manifest(key_space_manifest, scope="Key space", key_points=key_points, splits=splits)
+    for cg in scan.column_groups():
+        cg_scan = scan.column_group_state(cg)
+        # Skip table id from the start of the column group.
+        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 = None):
+    try:
+        import matplotlib.patches as patches
+        import matplotlib.pyplot as plt
+    except ImportError:
+        raise ImportError("matplotlib is required for debug")
+
+    total_fragments = len(manifest)
+
+    size_points = set()
+    for i in range(total_fragments):
+        manifest_file: FragmentFile = manifest[i]
+        size_points.add(manifest_file.size_bytes)
+    size_points = list(sorted(size_points))
+
+    if key_points is None:
+        key_points = set()
+
+        for i in range(total_fragments):
+            manifest_file: FragmentFile = manifest[i]
+
+            key_points.add(manifest_file.key_extent.min)
+            key_points.add(manifest_file.key_extent.max)
+
+        if splits is not None:
+            for split in splits[:-1]:
+                key_points.add(split.end)
+
+        key_points = list(sorted(key_points))
+
+    # Create figure and axis with specified size
+    fig, ax = plt.subplots(figsize=(12, 8))
+
+    # Plot each rectangle
+    for i in range(total_fragments):
+        manifest_file: FragmentFile = manifest[i]
+
+        left = key_points.index(manifest_file.key_extent.min)
+        right = key_points.index(manifest_file.key_extent.max)
+        height = size_points.index(manifest_file.size_bytes) + 1
+
+        color = _get_fragment_color(manifest_file, i, total_fragments)
+
+        # Create rectangle patch
+        rect = patches.Rectangle(
+            (left, 0),  # (x, y)
+            right - left,  # width
+            height,  # height
+            facecolor=color,  # fill color
+            edgecolor="black",  # border color
+            alpha=0.5,  # transparency
+            linewidth=1,  # border width
+            label=manifest_file.id,  # label for legend
+        )
+
+        ax.add_patch(rect)
+
+    # Set axis limits with some padding
+    ax.set_xlim(-0.5, len(key_points) - 1 + 0.5)
+    ax.set_ylim(-0.5, len(size_points) + 0.5)
+
+    # Create split markers on x-axis
+    if splits is not None:
+        split_positions = [key_points.index(split.end) for split in splits[:-1]]
+
+        # Add split markers at the bottom
+        for pos in split_positions:
+            ax.annotate("▲", xy=(pos, 0), ha="center", va="top", color="red", annotation_clip=False)
+
+    # Add grid
+    ax.grid(True, linestyle="--", alpha=0.7, zorder=0)
+
+    # Add labels and title
+    ax.set_title("Fragment Distribution" if scope is None else f"{scope} Fragment Distribution")
+    ax.set_xlabel("Key Index")
+    ax.set_ylabel("Size Index")
+
+    # Add legend
+    ax.legend(bbox_to_anchor=(1, 1), loc="upper left", fontsize="small")
+
+    # Adjust layout to prevent label cutoff
+    plt.tight_layout()
+
+    plot = FragmentManifestPlot(fig, ax, manifest)
+    fig.canvas.mpl_connect("motion_notify_event", plot.hover)
+
+    plt.show()
+
+
+def _get_fragment_color(manifest_file: FragmentFile, color_index, total_colors):
+    import matplotlib.cm as cm
+
+    if manifest_file.compacted_at is not None:
+        # Use a shade of gray for compacted fragments
+        # Vary the shade based on the index to distinguish different compacted fragments
+        gray_value = 0.3 + (0.5 * (color_index / total_colors))
+        return (gray_value, gray_value, gray_value)
+    else:
+        # Use viridis colormap for non-compacted fragments
+        return cm.viridis(color_index / total_colors)
+
+
+def _get_human_size(size_bytes: int) -> str:
+    # Convert bytes to a human-readable format
+    for unit in ["B", "KB", "MB", "GB", "TB"]:
+        if size_bytes < 1024:
+            return f"{size_bytes:.2f} {unit}"
+        size_bytes /= 1024
+    return f"{size_bytes:.2f} PB"
+
+
+def _maybe_truncate(text, max_length: int = 30) -> str:
+    text = str(text)
+    if len(text) <= max_length:
+        return text
+
+    half_length = (max_length - 3) // 2
+    return text[:half_length] + "..." + text[-half_length:]
+
+
+def _get_fragment_legend(manifest_file: FragmentFile):
+    return "\n".join(
+        [
+            f"id: {manifest_file.id}",
+            f"size: {_get_human_size(manifest_file.size_bytes)} ({manifest_file.size_bytes} bytes)",
+            f"key_span: {manifest_file.key_span}",
+            f"key_min: {_maybe_truncate(manifest_file.key_extent.min)}",
+            f"key_max: {_maybe_truncate(manifest_file.key_extent.max)}",
+            f"format: {manifest_file.format}",
+            f"level: {manifest_file.level}",
+            f"committed_at: {_format_timestamp(manifest_file.committed_at)}",
+            f"compacted_at: {_format_timestamp(manifest_file.compacted_at)}",
+            f"ks_id: {manifest_file.ks_id}",
+        ]
+    )
+
+
+def _format_timestamp(ts: Timestamp | None) -> str:
+    # Format timestamp or show None
+    if ts is None:
+        return "None"
+    try:
+        return datetime.fromtimestamp(ts / 1e6).strftime("%Y-%m-%d %H:%M:%S")
+    except ValueError:
+        return str(ts)
+
+
+class FragmentManifestPlot:
+    def __init__(self, fig, ax, manifest: FragmentManifest):
+        self.fig = fig
+        self.ax = ax
+        self.manifest = manifest
+
+        # Position the annotation in the bottom right corner
+        self.annotation = ax.annotate(
+            "",
+            xy=(0.98, 0.02),  # Position in axes coordinates
+            xycoords="axes fraction",
+            bbox=dict(boxstyle="round,pad=0.5", fc="white", ec="gray", alpha=0.8),
+            ha="right",  # Right-align text
+            va="bottom",  # Bottom-align text
+            visible=False,
+        )
+        self.highlighted_rect = None
+        self.highlighted_legend = None
+
+    def hover(self, event):
+        if event.inaxes != self.ax:
+            # Check if we're hovering over the legend
+            legend = self.ax.get_legend()
+            if legend and legend.contains(event)[0]:
+                # Find which legend item we're hovering over
+                for i, legend_text in enumerate(legend.get_texts()):
+                    if legend_text.contains(event)[0]:
+                        manifest_file = self.manifest[i]
+                        self._show_legend(manifest_file, i, legend_text)
+                        return
+            self._hide_legend()
+            return
+
+        # Check rectangles in the main plot
+        for i, rect in enumerate(self.ax.patches):
+            if rect.contains(event)[0]:
+                manifest_file = self.manifest[i]
+                self._show_legend(manifest_file, i, rect)
+                return
+
+        self._hide_legend()
+
+    def _show_legend(self, manifest_file, index, highlight_obj):
+        import matplotlib.patches as patches
+
+        # Update tooltip text
+        self.annotation.set_text(_get_fragment_legend(manifest_file))
+        self.annotation.set_visible(True)
+
+        # Handle highlighting
+        if isinstance(highlight_obj, patches.Rectangle):
+            # Highlighting rectangle in main plot
+            if self.highlighted_rect and self.highlighted_rect != highlight_obj:
+                self.highlighted_rect.set_alpha(0.5)
+            highlight_obj.set_alpha(0.8)
+            self.highlighted_rect = highlight_obj
+        else:
+            # Highlighting legend text
+            if self.highlighted_rect:
+                self.highlighted_rect.set_alpha(0.5)
+            # Find and highlight corresponding rectangle
+            rect = self.ax.patches[index]
+            rect.set_alpha(0.8)
+            self.highlighted_rect = rect
+
+        self.fig.canvas.draw_idle()
+
+    def _hide_legend(self):
+        if self.annotation.get_visible():
+            self.annotation.set_visible(False)
+            if self.highlighted_rect:
+                self.highlighted_rect.set_alpha(0.5)
+            self.fig.canvas.draw_idle()