From 7f5779fa9d0a9016c3737237996cd27d5a8b1d71 Mon Sep 17 00:00:00 2001 From: Yang Cen <159225399+BubbleCal@users.noreply.github.com> Date: Sat, 26 Sep 2026 15:44:44 +0800 Subject: [PATCH] feat(mv): refresh native duplicate pairs in partition units --- rust/lancedb/src/materialized_view.rs | 81 +++- .../src/materialized_view/duplicate_pairs.rs | 422 ++++++++++++++++++ .../src/materialized_view/grouped_units.rs | 50 ++- .../src/materialized_view/partitioned.rs | 132 ++++++ rust/lancedb/src/materialized_view/query.rs | 78 +++- rust/lancedb/src/materialized_view/refresh.rs | 21 +- rust/lancedb/src/remote/table.rs | 1 + .../table/datafusion/udtf/duplicate_pairs.rs | 2 +- rust/lancedb/tests/duplicate_pairs.rs | 61 +++ 9 files changed, 822 insertions(+), 26 deletions(-) create mode 100644 rust/lancedb/src/materialized_view/duplicate_pairs.rs create mode 100644 rust/lancedb/src/materialized_view/partitioned.rs diff --git a/rust/lancedb/src/materialized_view.rs b/rust/lancedb/src/materialized_view.rs index 430750a00..c2185eafa 100644 --- a/rust/lancedb/src/materialized_view.rs +++ b/rust/lancedb/src/materialized_view.rs @@ -9,8 +9,11 @@ //! query this version cannot maintain reads back as unrefreshable, not as a //! plain table. Queries, indexes and search work on the view unchanged. +mod duplicate_pairs; mod grouped; mod grouped_units; +mod partitioned; +pub use duplicate_pairs::DuplicatePairsView; pub use grouped::IVF_PARTITION; /// Refreshing a view grouped by [`IVF_PARTITION`] in units, one per index /// partition, so the work can be spread over several processes. The caller @@ -74,6 +77,10 @@ pub use grouped_units::{ GroupedRefreshPlan, WrittenUnit, commit_grouped_refresh, plan_grouped_refresh, write_grouped_unit, }; +pub use partitioned::{ + PartitionedRefreshPlan, WrittenPartition, commit_partitioned_refresh, plan_partitioned_refresh, + write_refresh_partition, +}; mod query; pub mod refresh; @@ -146,18 +153,23 @@ const COLUMN_DEFINITIONS_META_KEY: &str = "lancedb::column_definitions"; /// The newest layout this version reads under [`DEFINITION_META_KEY`]: /// `{"format": N, "query": ""}`, the query as -/// [`MaterializedViewDefinition::to_sql`] renders it. Format 2 is a query -/// with `GROUP BY`; every other query is written as format 1, so a reader -/// that predates grouping reports a grouped view as unrefreshable rather -/// than failing to parse it. A reader refuses a newer format rather than +/// [`MaterializedViewDefinition::to_sql`] renders it. Format 3 identifies a +/// native duplicate-pair source, format 2 a query with `GROUP BY`, and +/// format 1 an ordinary query. A reader refuses a newer format rather than /// guess at it. The layout also carries `"kind": "query"`, which readers /// older than the format number report as an unrefreshable view instead of /// failing to read the metadata. -pub const DEFINITION_FORMAT: u64 = 2; +pub const DEFINITION_FORMAT: u64 = 3; /// The format `definition` is written in; see [`DEFINITION_FORMAT`]. fn format_of(definition: &MaterializedViewDefinition) -> u64 { - if definition.is_grouped() { 2 } else { 1 } + if definition.duplicate_pairs.is_some() { + 3 + } else if definition.is_grouped() { + 2 + } else { + 1 + } } /// Legacy `kind` tag of the structured layout written before @@ -300,6 +312,8 @@ pub fn read_staging(metadata: &HashMap) -> Result, /// Name of the source table, in the same database as the view. pub source_table: String, /// Namespace path holding the source table; empty is the root namespace. @@ -498,6 +512,7 @@ pub fn read_definition(metadata: &HashMap) -> Result, ) -> Result { + if definition.duplicate_pairs.is_some() { + return duplicate_pairs::plan(source_schema, definition); + } let filter = definition .filter .as_deref() @@ -712,6 +730,7 @@ pub(crate) fn plan( } let definition = MaterializedViewDefinition { + duplicate_pairs: None, source_table: definition.source_table.clone(), source_namespace: definition.source_namespace.clone(), lateral: definition.lateral.clone(), @@ -1145,6 +1164,11 @@ impl PreparedDeclaration { /// read: the column the view projects it to, if any, otherwise an /// internal projection added here, named by [`input_column_name`]. pub fn input_column(&mut self, source_column: &str) -> Result { + if self.definition.duplicate_pairs.is_some() { + return Err(Error::InvalidInput { + message: "native pair views have no per-source-row inputs".into(), + }); + } // A grouped view's rows are groups; no source row carries a value into one. if self.definition.is_grouped() { return Err(Error::InvalidInput { @@ -1245,6 +1269,11 @@ impl PreparedDeclaration { columns: Vec<(usize, ArrowField)>, bindings: &[FunctionBinding], ) -> Result { + if self.definition.duplicate_pairs.is_some() { + return Err(Error::InvalidInput { + message: "computed columns on native pair views are not supported".into(), + }); + } let invalid = |message: String| Error::InvalidInput { message }; if columns.is_empty() { return Err(invalid("at least one computed column is needed".into())); @@ -1451,6 +1480,7 @@ pub async fn prepare_declaration( limit: Option, ) -> Result { let definition = MaterializedViewDefinition { + duplicate_pairs: None, source_table: source.name().to_string(), source_namespace: source.namespace().to_vec(), lateral: None, @@ -1627,7 +1657,9 @@ async fn prepare_with( ), }); } - if !native.dataset.get().await?.manifest.uses_stable_row_ids() { + if definition.duplicate_pairs.is_none() + && !native.dataset.get().await?.manifest.uses_stable_row_ids() + { return Err(Error::InvalidInput { message: format!( "materialized views require stable row ids on the source table; \ @@ -1653,7 +1685,22 @@ async fn prepare_with( message: format!("view column name '{}' is reserved", reserved.output), }); } - let source_schema = resolved.schema().await?; + let source_schema = if let Some(pairs) = &definition.duplicate_pairs { + let ds = native + .dataset + .get() + .await? + .checkout_version(pairs.dataset_version) + .await?; + crate::table::datafusion::udtf::duplicate_pairs::plan_duplicate_pairs( + Arc::new(ds.clone()), + &pairs.config()?, + ) + .await?; + Arc::new(ArrowSchema::from(ds.schema())) + } else { + resolved.schema().await? + }; let source_metadata = source_schema.metadata().clone(); let Planned { definition, @@ -1670,11 +1717,13 @@ async fn prepare_with( None => source_schema.clone(), Some(unnest) => flattened_schema(&source_schema, &unnest)?, }; - fields.push(ArrowField::new( - SOURCE_ROW_ID_COLUMN, - DataType::UInt64, - false, - )); + if definition.duplicate_pairs.is_none() { + fields.push(ArrowField::new( + SOURCE_ROW_ID_COLUMN, + DataType::UInt64, + false, + )); + } // Only column-describing metadata comes along: structural declarations // describe how a table is written, and a view is written by refresh alone. let mut metadata: HashMap = HashMap::new(); @@ -2186,6 +2235,7 @@ mod tests { assert_eq!( view.definition(), &MaterializedViewDefinition { + duplicate_pairs: None, source_table: "people".into(), source_namespace: Vec::new(), projections: vec![ @@ -3235,6 +3285,7 @@ mod tests { fn definition(source_namespace: Vec) -> MaterializedViewDefinition { MaterializedViewDefinition { + duplicate_pairs: None, source_table: "people".to_string(), source_namespace, lateral: None, @@ -3321,8 +3372,8 @@ mod tests { #[test] fn a_newer_format_is_reported_not_guessed() { assert_eq!( - read(r#"{"format":3,"query":"SELECT name FROM people"}"#).unwrap(), - Some(StoredDefinition::Newer { format: "3".into() }) + read(r#"{"format":4,"query":"SELECT name FROM people"}"#).unwrap(), + Some(StoredDefinition::Newer { format: "4".into() }) ); assert_eq!( read(r#"{"kind":"join"}"#).unwrap(), diff --git a/rust/lancedb/src/materialized_view/duplicate_pairs.rs b/rust/lancedb/src/materialized_view/duplicate_pairs.rs new file mode 100644 index 000000000..c22cd1086 --- /dev/null +++ b/rust/lancedb/src/materialized_view/duplicate_pairs.rs @@ -0,0 +1,422 @@ +// SPDX-License-Identifier: Apache-2.0 +// SPDX-FileCopyrightText: Copyright The LanceDB Authors + +//! Native pair generation as partitioned materialized-view refresh work. + +use std::sync::Arc; + +use arrow_schema::{Schema, SchemaRef}; +use datafusion_execution::{SendableRecordBatchStream, TaskContext}; +use datafusion_physical_plan::ExecutionPlan; +use datafusion_sql::sqlparser::ast::{ + Expr, FunctionArg, FunctionArgExpr, TableFunctionArgs, Value, +}; +use futures::TryStreamExt; +use lance::Dataset; +use lance::dataset::transaction::Operation; +use lance::dataset::{InsertBuilder, WriteDestination, WriteMode, WriteParams}; +use lance_table::format::Fragment; +use serde::{Deserialize, Serialize}; + +use super::grouped_units::GroupedRefreshPlan; +use super::refresh::{ + RefreshMaterializedViewResult, ensure_incarnation, ensure_no_mem_wal, open_source, +}; +use super::{MaterializedViewDefinition, Planned, ViewProjection}; +use crate::table::Table; +use crate::table::datafusion::udtf::duplicate_pairs::{ + DUPLICATE_PAIRS_OPERATOR_VERSION, DuplicatePairTask, DuplicatePairsConfig, DuplicatePairsExec, + duplicate_pair_schema, plan_duplicate_pairs, +}; +use crate::{Error, Result}; + +pub(crate) const FUNCTION_NAME: &str = "vector_duplicate_pairs"; + +/// A native table-function source, pinned for the lifetime of the view. +#[derive(Debug, Clone, PartialEq, Eq, Serialize, Deserialize)] +#[serde(deny_unknown_fields)] +pub struct DuplicatePairsView { + pub dataset_version: u64, + pub column: String, + /// Validated numeric SQL spelling; execution and task identity use f32 bits. + pub distance_threshold: String, +} + +impl DuplicatePairsView { + pub(crate) fn config(&self) -> Result { + let threshold: f32 = self + .distance_threshold + .parse() + .map_err(|_| invalid("invalid pair threshold"))?; + if self.dataset_version == 0 || self.column.is_empty() || !threshold.is_finite() { + return Err(invalid( + "duplicate pairs require a positive snapshot, a column and a finite threshold", + )); + } + Ok(DuplicatePairsConfig { + dataset_version: self.dataset_version, + column: self.column.clone(), + distance_threshold: threshold, + }) + } +} + +fn invalid(message: impl Into) -> Error { + Error::InvalidInput { + message: message.into(), + } +} + +pub(super) fn source( + args: &TableFunctionArgs, +) -> Result<(Vec, String, DuplicatePairsView)> { + if args.settings.is_some() { + return Err(invalid("duplicate pairs do not accept function settings")); + } + let exprs = args + .args + .iter() + .map(|arg| match arg { + FunctionArg::Unnamed(FunctionArgExpr::Expr(expr)) => Ok(expr), + _ => Err(invalid( + "duplicate pairs require four positional literal arguments", + )), + }) + .collect::>>()?; + let [table, version, column, threshold] = exprs.as_slice() else { + return Err(invalid( + "vector_duplicate_pairs requires (table, dataset_version, column, distance_threshold)", + )); + }; + let string = |expr: &Expr| match expr { + Expr::Value(value) => match &value.value { + Value::SingleQuotedString(value) => Ok(value.clone()), + _ => Err(invalid("table and column must be string literals")), + }, + _ => Err(invalid("table and column must be string literals")), + }; + let table = string(table)?; + let plain = MaterializedViewDefinition::from_sql(&format!("SELECT * FROM {table}"))?; + if plain.duplicate_pairs.is_some() + || plain.lateral.is_some() + || plain.filter.is_some() + || plain.is_grouped() + || plain.limit.is_some() + { + return Err(invalid("duplicate pairs must name one source table")); + } + let dataset_version = match version { + Expr::Value(value) => match &value.value { + Value::Number(number, _) => number + .parse() + .map_err(|_| invalid("invalid source version"))?, + _ => return Err(invalid("source version must be an integer literal")), + }, + _ => return Err(invalid("source version must be an integer literal")), + }; + let config = DuplicatePairsView { + dataset_version, + column: string(column)?, + distance_threshold: threshold.to_string(), + }; + config.config()?; + Ok((plain.source_namespace, plain.source_table, config)) +} + +pub(super) fn check_shape(definition: &MaterializedViewDefinition) -> Result<()> { + let schema = duplicate_pair_schema(); + let projections = schema + .fields() + .iter() + .map(|field| ViewProjection { + output: field.name().clone(), + expression: field.name().clone(), + }) + .collect::>(); + if (!definition.selects_star() && definition.projections != projections) + || definition.filter.is_some() + || definition.limit.is_some() + || definition.lateral.is_some() + || definition.is_grouped() + { + return Err(invalid( + "a native pair view selects *, or row_id_a, row_id_b, distance, without other clauses", + )); + } + Ok(()) +} + +pub(super) fn plan( + source_schema: SchemaRef, + definition: &MaterializedViewDefinition, +) -> Result { + check_shape(definition)?; + let config = definition.duplicate_pairs.as_ref().expect("native source"); + config.config()?; + source_schema.field_with_name(&config.column)?; + let schema = duplicate_pair_schema(); + let projections = schema + .fields() + .iter() + .map(|field| ViewProjection { + output: field.name().clone(), + expression: field.name().clone(), + }) + .collect(); + let mut definition = definition.clone(); + let inputs = vec![config.column.clone()]; + definition.projections = projections; + Ok(Planned { + definition, + fields: schema.fields().iter().map(|f| f.as_ref().clone()).collect(), + lineage: Default::default(), + inputs, + }) +} + +/// A saved native refresh plan, including every physical partition identity. +#[derive(Debug, Clone, PartialEq, Eq, Serialize, Deserialize)] +#[serde(deny_unknown_fields)] +pub struct DuplicatePairsRefreshPlan { + pub snapshot: GroupedRefreshPlan, + pub source_uri: String, + pub definition_sql: String, + pub operator_version: u32, + pub threshold_bits: u32, + pub tasks: Vec, +} + +#[derive(Debug, Clone, Serialize, Deserialize)] +#[serde(deny_unknown_fields)] +pub struct WrittenPairsPartition { + pub(super) unit: u32, + pub(super) plan_id: String, + pub(super) task: DuplicatePairTask, + pub(super) fragments: Vec, + pub(super) rows: u64, +} + +impl DuplicatePairsRefreshPlan { + fn identity(&self) -> Result { + use sha2::{Digest, Sha256}; + let encoded = serde_json::to_vec(&( + &self.snapshot, + &self.source_uri, + &self.definition_sql, + self.operator_version, + self.threshold_bits, + )) + .map_err(|e| invalid(e.to_string()))?; + Ok(format!("{:x}", Sha256::digest(encoded))) + } +} + +async fn open(view: &Table) -> Result<(Dataset, MaterializedViewDefinition, Arc)> { + let native = view + .as_native() + .ok_or_else(|| invalid("native pair refresh requires a local view"))?; + native.dataset.ensure_mutable()?; + native.dataset.reload().await?; + let view_ds = native.dataset.get().await?.as_ref().clone(); + let Some(super::StoredDefinition::Query(definition)) = + super::read_definition(&view_ds.schema().metadata)? + else { + return Err(invalid("view does not carry a supported definition")); + }; + let config = definition + .duplicate_pairs + .as_ref() + .ok_or_else(|| invalid("not a native pair view"))? + .config()?; + let source = Arc::new( + open_source(view, &definition, None) + .await? + .checkout_version(config.dataset_version) + .await?, + ); + ensure_no_mem_wal(&source, "source table", &definition.source_table).await?; + let planned = plan(Arc::new(Schema::from(source.schema())), &definition)?; + let expected = duplicate_pair_schema(); + let physical = Schema::from(view_ds.schema()); + if physical.fields().len() != expected.fields().len() + || physical + .fields() + .iter() + .zip(expected.fields()) + .any(|(a, b)| { + a.name() != b.name() + || a.data_type() != b.data_type() + || a.is_nullable() != b.is_nullable() + }) + { + return Err(invalid("native pair view schema changed since creation")); + } + Ok((view_ds, planned.definition, source)) +} + +pub(super) async fn plan_refresh( + view: &Table, + pinned: Option, +) -> Result { + let (view_ds, definition, source) = open(view).await?; + let config = definition + .duplicate_pairs + .as_ref() + .expect("native") + .config()?; + if pinned.is_some_and(|v| v != config.dataset_version) { + return Err(invalid( + "refresh source version differs from the native pair view's fixed snapshot", + )); + } + let tasks = plan_duplicate_pairs(source.clone(), &config).await?; + let units = u32::try_from(tasks.len()).map_err(|_| invalid("too many index partitions"))?; + let incarnation = view_ds + .schema() + .metadata + .get(super::INCARNATION_META_KEY) + .cloned() + .ok_or_else(|| invalid("native pair view has no incarnation"))?; + Ok(DuplicatePairsRefreshPlan { + snapshot: GroupedRefreshPlan { + units, + source_version: config.dataset_version, + view_version: view_ds.version().version, + incarnation, + }, + source_uri: source.uri().to_string(), + definition_sql: definition.to_sql(), + operator_version: DUPLICATE_PAIRS_OPERATOR_VERSION, + threshold_bits: config.distance_threshold.to_bits(), + tasks, + }) +} + +async fn open_planned( + view: &Table, + plan: &DuplicatePairsRefreshPlan, +) -> Result<(Dataset, MaterializedViewDefinition, Arc)> { + let (view_ds, definition, source) = open(view).await?; + ensure_incarnation(&view_ds, Some(&plan.snapshot.incarnation), view.name()).await?; + let config = definition + .duplicate_pairs + .as_ref() + .expect("native") + .config()?; + if source.uri() != plan.source_uri + || source.version().version != plan.snapshot.source_version + || definition.to_sql() != plan.definition_sql + || config.distance_threshold.to_bits() != plan.threshold_bits + || plan.operator_version != DUPLICATE_PAIRS_OPERATOR_VERSION + || plan.tasks.len() != plan.snapshot.units as usize + { + return Err(invalid( + "native pair task belongs to a different snapshot, configuration or operator", + )); + } + Ok((view_ds, definition, source)) +} + +pub(super) async fn write_unit( + view: &Table, + unit: u32, + plan: &DuplicatePairsRefreshPlan, +) -> Result { + let (view_ds, definition, source) = open_planned(view, plan).await?; + let task = plan + .tasks + .get(unit as usize) + .ok_or_else(|| invalid("pair partition is outside the plan"))? + .clone(); + let config = definition + .duplicate_pairs + .as_ref() + .expect("native") + .config()?; + let exec = DuplicatePairsExec::try_new(source, config, vec![task.clone()])?; + let stream = exec.execute(0, Arc::new(TaskContext::default()))?; + let rows = Arc::new(std::sync::atomic::AtomicU64::new(0)); + let count = rows.clone(); + let stream = stream.inspect_ok(move |batch| { + count.fetch_add( + batch.num_rows() as u64, + std::sync::atomic::Ordering::Relaxed, + ); + }); + let stream: SendableRecordBatchStream = Box::pin( + datafusion_physical_plan::stream::RecordBatchStreamAdapter::new( + duplicate_pair_schema(), + stream, + ), + ); + let txn = InsertBuilder::new(WriteDestination::Dataset(Arc::new(view_ds))) + .with_params(&WriteParams { + mode: WriteMode::Append, + ..Default::default() + }) + .execute_uncommitted_stream(stream) + .await?; + let Operation::Append { fragments } = txn.operation else { + return Err(invalid( + "native pair partition did not stage append fragments", + )); + }; + Ok(WrittenPairsPartition { + unit, + plan_id: plan.identity()?, + task, + fragments, + rows: rows.load(std::sync::atomic::Ordering::Relaxed), + }) +} + +pub(super) async fn commit( + view: &Table, + plan: &DuplicatePairsRefreshPlan, + units: Vec, + expected: Option<&str>, +) -> Result { + let (_, definition, source) = open_planned(view, plan).await?; + let config = definition + .duplicate_pairs + .as_ref() + .expect("native") + .config()?; + if plan_duplicate_pairs(source.clone(), &config).await? != plan.tasks { + return Err(invalid( + "pair plan does not cover the pinned index partitions exactly", + )); + } + let identity = plan.identity()?; + let mut ordered = vec![None; plan.snapshot.units as usize]; + for written in units { + if written.plan_id != identity + || plan.tasks.get(written.unit as usize) != Some(&written.task) + { + return Err(invalid("pair partition receipt belongs to another plan")); + } + let slot = ordered + .get_mut(written.unit as usize) + .ok_or_else(|| invalid("unknown pair partition receipt"))?; + if slot.is_some() { + return Err(invalid("duplicate pair partition receipt")); + } + *slot = Some(written); + } + let units = ordered + .into_iter() + .collect::>>() + .ok_or_else(|| invalid("missing pair partition receipt"))?; + let rows = units.iter().map(|u| u.rows).sum(); + let fragments = units.into_iter().flat_map(|u| u.fragments).collect(); + super::grouped_units::commit_fragments( + view, + &plan.snapshot, + &definition, + source.manifest.timestamp_nanos, + fragments, + rows, + expected, + ) + .await +} diff --git a/rust/lancedb/src/materialized_view/grouped_units.rs b/rust/lancedb/src/materialized_view/grouped_units.rs index 44bbd7381..7f408be4d 100644 --- a/rust/lancedb/src/materialized_view/grouped_units.rs +++ b/rust/lancedb/src/materialized_view/grouped_units.rs @@ -53,6 +53,7 @@ const PROBE_ROWS: usize = 256; /// How a grouped view can be refreshed in units. #[derive(Debug, Clone, PartialEq, Eq, Serialize, Deserialize)] +#[serde(deny_unknown_fields)] pub struct GroupedRefreshPlan { /// Units `0..units`: unit `p` before the last holds index partition /// `p`'s groups; the last holds the rows the index cannot place (null or @@ -177,6 +178,7 @@ pub async fn plan_grouped_refresh( /// accounted for has to be refusable. Travels to whoever commits, so it /// serializes, but its fields are not a caller's to write. #[derive(Debug, Clone, Serialize, Deserialize)] +#[serde(deny_unknown_fields)] pub struct WrittenUnit { unit: u32, plan: GroupedRefreshPlan, @@ -491,10 +493,38 @@ pub async fn commit_grouped_refresh( plan: &GroupedRefreshPlan, units: Vec, expected_incarnation: Option<&str>, +) -> Result { + let grouped = open_planned(view, plan).await?; + let units = complete_set(view.name(), plan, units)?; + let rows_written = units.iter().map(|unit| unit.rows).sum(); + let new_fragments = units.into_iter().flat_map(|unit| unit.fragments).collect(); + commit_fragments( + view, + plan, + &grouped.definition, + grouped.source.manifest.timestamp_nanos, + new_fragments, + rows_written, + expected_incarnation, + ) + .await +} + +/// The common all-or-nothing unit sink, shared by grouped and native views. +#[allow(clippy::too_many_arguments)] +pub(super) async fn commit_fragments( + view: &Table, + plan: &GroupedRefreshPlan, + definition: &MaterializedViewDefinition, + source_ts: u128, + new_fragments: Vec, + rows_written: u64, + expected_incarnation: Option<&str>, ) -> Result { let view_native = view.as_native().ok_or_else(|| Error::NotSupported { message: "materialized views are supported only on local tables".into(), })?; + view_native.dataset.ensure_mutable()?; let lock = refresh_lock(view_native.dataset.get().await?.uri()); let _guard = lock.lock().await; if let Some(expected) = expected_incarnation @@ -508,10 +538,17 @@ pub async fn commit_grouped_refresh( ), }); } - let grouped = open_planned(view, plan).await?; - let source_ts = grouped.source.manifest.timestamp_nanos; - - let ds = Arc::new(grouped.view_ds); + view_native.dataset.reload().await?; + let ds = view_native.dataset.get().await?.as_ref().clone(); + ensure_incarnation(&ds, Some(&plan.incarnation), view.name()).await?; + if super::read_definition(&ds.schema().metadata)? + != Some(super::StoredDefinition::Query(definition.clone())) + { + return Err(Error::InvalidInput { + message: "view definition changed while its units were written".into(), + }); + } + let ds = Arc::new(ds); if ds.version().version != plan.view_version { return Err(Error::Runtime { message: format!( @@ -523,11 +560,8 @@ pub async fn commit_grouped_refresh( ), }); } - let units = complete_set(view.name(), plan, units)?; let removed_fragment_ids: Vec = ds.get_fragments().iter().map(|f| f.id() as u64).collect(); // Fragment ids are assigned at commit; the units' fragments all carry 0. - let rows_written = units.iter().map(|unit| unit.rows).sum(); - let new_fragments = units.into_iter().flat_map(|unit| unit.fragments).collect(); let transaction = Transaction::new( plan.view_version, Operation::Update { @@ -566,7 +600,7 @@ pub async fn commit_grouped_refresh( committed, plan.source_version, source_ts, - Some(&grouped.definition), + Some(definition), expected_incarnation, ) .await?; diff --git a/rust/lancedb/src/materialized_view/partitioned.rs b/rust/lancedb/src/materialized_view/partitioned.rs new file mode 100644 index 000000000..5bdd88f0d --- /dev/null +++ b/rust/lancedb/src/materialized_view/partitioned.rs @@ -0,0 +1,132 @@ +// SPDX-License-Identifier: Apache-2.0 +// SPDX-FileCopyrightText: Copyright The LanceDB Authors + +//! Shared plan/write/commit surface for materialized views with independent units. + +use serde::{Deserialize, Serialize}; + +use super::duplicate_pairs::{self, DuplicatePairsRefreshPlan, WrittenPairsPartition}; +use super::{GroupedRefreshPlan, RefreshMaterializedViewResult, StoredDefinition, WrittenUnit}; +use crate::table::Table; +use crate::{Error, Result}; + +/// Serializable work description consumed by a host's existing job workers. +/// The grouped variant preserves the previous saved-plan representation. +#[derive(Debug, Clone, PartialEq, Eq, Serialize, Deserialize)] +#[serde(untagged)] +pub enum PartitionedRefreshPlan { + DuplicatePairs(DuplicatePairsRefreshPlan), + Grouped(GroupedRefreshPlan), +} + +impl PartitionedRefreshPlan { + /// The shared source snapshot and destination generation fence. + pub fn snapshot(&self) -> &GroupedRefreshPlan { + match self { + Self::DuplicatePairs(plan) => &plan.snapshot, + Self::Grouped(plan) => plan, + } + } + /// Number of independent units in this immutable plan. + pub fn units(&self) -> u32 { + self.snapshot().units + } +} + +/// One completed unit's uncommitted fragments. Failed attempts produce no receipt. +#[derive(Debug, Clone, Serialize, Deserialize)] +#[serde(untagged)] +pub enum WrittenPartition { + DuplicatePairs(WrittenPairsPartition), + Grouped(WrittenUnit), +} + +impl WrittenPartition { + /// Number of pair or grouped rows staged by this unit. + pub fn rows(&self) -> u64 { + match self { + Self::DuplicatePairs(unit) => unit.rows, + Self::Grouped(unit) => unit.rows(), + } + } + /// Uncommitted output files, retained only after task completion. + pub fn fragments(&self) -> &[lance_table::format::Fragment] { + match self { + Self::DuplicatePairs(unit) => &unit.fragments, + Self::Grouped(unit) => unit.fragments(), + } + } +} + +/// Plan native pair or indexed grouped work; return `None` for ordinary views. +/// `pinned`, when supplied, must match a native view's declared source version. +pub async fn plan_partitioned_refresh( + view: &Table, + pinned: Option, +) -> Result> { + if let Some(StoredDefinition::Query(definition)) = + super::read_definition(view.schema().await?.metadata())? + && definition.duplicate_pairs.is_some() + { + return duplicate_pairs::plan_refresh(view, pinned) + .await + .map(|p| Some(PartitionedRefreshPlan::DuplicatePairs(p))); + } + super::plan_grouped_refresh(view, pinned) + .await + .map(|plan| plan.map(PartitionedRefreshPlan::Grouped)) +} + +/// Stream one unit into uncommitted fragments. Persist the returned receipt only +/// on success. A failed or interrupted call must be retried from the unit's start. +pub async fn write_refresh_partition( + view: &Table, + unit: u32, + plan: &PartitionedRefreshPlan, +) -> Result { + match plan { + PartitionedRefreshPlan::DuplicatePairs(plan) => { + duplicate_pairs::write_unit(view, unit, plan) + .await + .map(WrittenPartition::DuplicatePairs) + } + PartitionedRefreshPlan::Grouped(plan) => super::write_grouped_unit(view, unit, plan) + .await + .map(WrittenPartition::Grouped), + } +} + +/// Publish a complete set of unit receipts through the common MV commit sink. +/// `expected` fences the destination incarnation. No partial set is publishable. +pub async fn commit_partitioned_refresh( + view: &Table, + plan: &PartitionedRefreshPlan, + units: Vec, + expected: Option<&str>, +) -> Result { + let foreign = || Error::InvalidInput { + message: "refresh receipt does not match the plan kind".into(), + }; + match plan { + PartitionedRefreshPlan::DuplicatePairs(plan) => { + let units = units + .into_iter() + .map(|unit| match unit { + WrittenPartition::DuplicatePairs(unit) => Ok(unit), + _ => Err(foreign()), + }) + .collect::>>()?; + duplicate_pairs::commit(view, plan, units, expected).await + } + PartitionedRefreshPlan::Grouped(plan) => { + let units = units + .into_iter() + .map(|unit| match unit { + WrittenPartition::Grouped(unit) => Ok(unit), + _ => Err(foreign()), + }) + .collect::>>()?; + super::commit_grouped_refresh(view, plan, units, expected).await + } + } +} diff --git a/rust/lancedb/src/materialized_view/query.rs b/rust/lancedb/src/materialized_view/query.rs index c1a987b2c..7dd407315 100644 --- a/rust/lancedb/src/materialized_view/query.rs +++ b/rust/lancedb/src/materialized_view/query.rs @@ -264,7 +264,29 @@ fn extract(query: &Query) -> Result { }; let mut from = select.from.iter(); + let mut duplicate_pairs = None; let (source_namespace, source_table) = match from.next().map(|f| &f.relation) { + Some(TableFactor::Table { + name, + args: Some(args), + alias: None, + with_hints, + version: None, + with_ordinality: false, + partitions, + json_path: None, + sample: None, + index_hints, + .. + }) if name.to_string() == super::duplicate_pairs::FUNCTION_NAME + && with_hints.is_empty() + && partitions.is_empty() + && index_hints.is_empty() => + { + let (namespace, table, config) = super::duplicate_pairs::source(args)?; + duplicate_pairs = Some(config); + (namespace, table) + } Some(TableFactor::Table { args: Some(_), .. }) => { return Err(invalid( "a view reads a table; a Function in FROM position follows it: \ @@ -416,6 +438,7 @@ fn extract(query: &Query) -> Result { }; let definition = MaterializedViewDefinition { + duplicate_pairs, source_table, source_namespace, lateral, @@ -424,6 +447,9 @@ fn extract(query: &Query) -> Result { group_by, limit, }; + if definition.duplicate_pairs.is_some() { + super::duplicate_pairs::check_shape(&definition)?; + } check_grouping(&definition)?; Ok(definition) } @@ -483,7 +509,18 @@ pub fn render(definition: &MaterializedViewDefinition) -> String { .chain(std::iter::once(&definition.source_table)) .map(|part| ident_sql(part)) .collect(); - sql.push_str(&table.join(".")); + if let Some(native) = &definition.duplicate_pairs { + sql.push_str(&format!( + "{}('{}', {}, '{}', {})", + super::duplicate_pairs::FUNCTION_NAME, + table.join(".").replace('\'', "''"), + native.dataset_version, + native.column.replace('\'', "''"), + native.distance_threshold + )); + } else { + sql.push_str(&table.join(".")); + } if let Some(lateral) = &definition.lateral { match &lateral.source { LateralSource::Unnest { column } => { @@ -511,6 +548,45 @@ pub fn render(definition: &MaterializedViewDefinition) -> String { mod tests { use super::*; + #[test] + fn native_pairs_are_a_table_source_with_literal_snapshot_arguments() { + for threshold in ["4", "4.0", "-1", "0.05"] { + let sql = + format!("SELECT * FROM vector_duplicate_pairs('images', 3, 'phash', {threshold})"); + let definition = parse(&sql).unwrap(); + assert_eq!(definition.source_table, "images"); + assert!(definition.lateral.is_none()); + assert_eq!( + definition.duplicate_pairs.as_ref().unwrap().dataset_version, + 3 + ); + assert_eq!(parse(&render(&definition)).unwrap(), definition); + let metadata = std::collections::HashMap::from([( + super::super::DEFINITION_META_KEY.to_string(), + definition.to_json().unwrap(), + )]); + assert_eq!( + super::super::read_definition(&metadata).unwrap(), + Some(super::super::StoredDefinition::Query(definition)) + ); + } + for sql in [ + "SELECT row_id_a FROM vector_duplicate_pairs('images', 3, 'phash', 4)", + "SELECT * FROM vector_duplicate_pairs('images', 0, 'phash', 4)", + "SELECT * FROM vector_duplicate_pairs('images', 3, 'phash', 1e100)", + "SELECT * FROM vector_duplicate_pairs('images', 3, 'phash', cutoff)", + "SELECT * FROM vector_duplicate_pairs('images', 3, 'phash', 4) LIMIT 1", + "SELECT * FROM vector_duplicate_pairs('images', 3, 'phash', 4) WHERE distance < 2", + "SELECT * FROM vector_duplicate_pairs('images', 3, 'phash', 4) AS p", + "SELECT * FROM vector_duplicate_pairs('images', 3, 'phash', 4), f(phash) AS p", + ] { + assert!( + parse(sql).is_err(), + "accepted unsupported native view: {sql}" + ); + } + } + #[test] fn a_query_round_trips_through_its_canonical_form() { for (sql, canonical) in [ diff --git a/rust/lancedb/src/materialized_view/refresh.rs b/rust/lancedb/src/materialized_view/refresh.rs index 5e9fe13e3..07754af76 100644 --- a/rust/lancedb/src/materialized_view/refresh.rs +++ b/rust/lancedb/src/materialized_view/refresh.rs @@ -117,6 +117,23 @@ pub(crate) async fn execute_refresh( pinned: Option, expected_incarnation: Option<&str>, ) -> Result { + // Native table functions use the same partition writer and commit sink in + // local execution; Sophon drives these units through its job registry. + if let Some(super::StoredDefinition::Query(definition)) = + super::read_definition(view.schema().await?.metadata())? + && definition.duplicate_pairs.is_some() + { + let plan = super::plan_partitioned_refresh(view, pinned) + .await? + .ok_or_else(|| Error::Runtime { + message: "native pair view has no partition plan".into(), + })?; + let mut units = Vec::with_capacity(plan.units() as usize); + for unit in 0..plan.units() { + units.push(super::write_refresh_partition(view, unit, &plan).await?); + } + return super::commit_partitioned_refresh(view, &plan, units, expected_incarnation).await; + } let view_native = view.as_native().ok_or_else(|| Error::NotSupported { message: "materialized views are supported only on local tables".into(), })?; @@ -728,7 +745,7 @@ pub(super) async fn open_source( message: "materialized views are supported only on local tables".into(), })?; let dataset = native.dataset.get().await?.as_ref().clone(); - if !dataset.manifest.uses_stable_row_ids() { + if definition.duplicate_pairs.is_none() && !dataset.manifest.uses_stable_row_ids() { return Err(Error::InvalidInput { message: format!( "source table '{}' does not have stable row ids; it is not the \ @@ -3674,6 +3691,7 @@ pub(crate) mod tests { let (_conn, _, view) = refreshed_doubled(vec![1, 2]).await; let replacement = crate::materialized_view::MaterializedViewDefinition { + duplicate_pairs: None, source_table: "src".into(), source_namespace: Vec::new(), projections: vec![ @@ -3715,6 +3733,7 @@ pub(crate) mod tests { let (_conn, _, view) = refreshed_doubled(vec![1, 2]).await; let narrower = crate::materialized_view::MaterializedViewDefinition { + duplicate_pairs: None, source_table: "src".into(), source_namespace: Vec::new(), projections: vec![crate::materialized_view::ViewProjection { diff --git a/rust/lancedb/src/remote/table.rs b/rust/lancedb/src/remote/table.rs index d6abfea9a..624340ffb 100644 --- a/rust/lancedb/src/remote/table.rs +++ b/rust/lancedb/src/remote/table.rs @@ -2140,6 +2140,7 @@ impl BaseTable for RemoteTable { let definition = match response.query { Some(query) => MaterializedViewDefinition::from_sql(&query)?, None => MaterializedViewDefinition { + duplicate_pairs: None, source_table: response.source_table, source_namespace: response.source_namespace, lateral: None, diff --git a/rust/lancedb/src/table/datafusion/udtf/duplicate_pairs.rs b/rust/lancedb/src/table/datafusion/udtf/duplicate_pairs.rs index eeb21112f..47a35cbd2 100644 --- a/rust/lancedb/src/table/datafusion/udtf/duplicate_pairs.rs +++ b/rust/lancedb/src/table/datafusion/udtf/duplicate_pairs.rs @@ -60,7 +60,7 @@ pub struct DuplicatePairsConfig { /// One worker input, never a row of source vectors. The complete task identity /// also includes the dataset URI/version, column, threshold and operator version. -#[derive(Debug, Clone, PartialEq, Eq)] +#[derive(Debug, Clone, PartialEq, Eq, serde::Serialize, serde::Deserialize)] pub struct DuplicatePairTask { pub segment_id: Uuid, pub partition_id: usize, diff --git a/rust/lancedb/tests/duplicate_pairs.rs b/rust/lancedb/tests/duplicate_pairs.rs index 4f3ed50f6..e63b20ecf 100644 --- a/rust/lancedb/tests/duplicate_pairs.rs +++ b/rust/lancedb/tests/duplicate_pairs.rs @@ -206,6 +206,67 @@ async fn sql_pairs_match_native_snapshot_and_partition_tasks() -> anyhow::Result ); let retry = ctx.sql(&sql).await?.collect().await?; assert_eq!(pairs(&retry), pairs(&actual)); + // The same table function can be maintained through the MV unit + // lifecycle. Staging attempts do not make any rows visible. + use lancedb::materialized_view::{ + MaterializedViewDefinition, commit_partitioned_refresh, plan_partitioned_refresh, + prepare_definition, write_refresh_partition, + }; + let view_name = format!("pairs_{}", threshold.to_bits()); + let view = prepare_definition(&table, MaterializedViewDefinition::from_sql(&sql)?) + .await? + .create(&view_name) + .await?; + assert_eq!(view.table().schema().await?.fields().len(), 3); + let plan = plan_partitioned_refresh(view.table(), Some(version)) + .await? + .unwrap(); + assert_eq!(plan.units() as usize, tasks.len()); + let plan = serde_json::from_slice(&serde_json::to_vec(&plan)?)?; + let first = write_refresh_partition(view.table(), 0, &plan).await?; + assert_eq!(view.table().count_rows(None).await?, 0); + assert!( + commit_partitioned_refresh( + view.table(), + &plan, + vec![first.clone(), first.clone()], + view.incarnation() + ) + .await + .is_err() + ); + // Lost receipt: its files remain unreferenced; the retry writes + // another attempt, of which only one receipt is ever committed. + drop(write_refresh_partition(view.table(), 0, &plan).await?); + let mut units = vec![first]; + for unit in 1..plan.units() { + units.push(write_refresh_partition(view.table(), unit, &plan).await?); + } + assert_eq!(view.table().count_rows(None).await?, 0); + let outcome = + commit_partitioned_refresh(view.table(), &plan, units.clone(), view.incarnation()) + .await?; + assert_eq!(outcome.rows_written as usize, pairs(&expected).len()); + assert!( + commit_partitioned_refresh(view.table(), &plan, units, view.incarnation()) + .await + .is_err() + ); + use lancedb::query::ExecutableQuery; + let written = view + .table() + .query() + .execute() + .await? + .try_collect::>() + .await?; + assert_eq!(pairs(&written), pairs(&expected)); + // Repeating a refresh replaces the view rather than appending. + view.refresh().execute().await?; + assert_eq!( + view.table().count_rows(None).await? as usize, + pairs(&expected).len() + ); assert!( DuplicatePairsExec::try_new( ds.clone(),