@nshiab/simple-data-analysis-core 2.0.8 → 2.1.0

package/script/methods/findCycles.js

@@ -0,0 +1,369 @@
+"use strict";
+var __createBinding = (this && this.__createBinding) || (Object.create ? (function(o, m, k, k2) {
+    if (k2 === undefined) k2 = k;
+    var desc = Object.getOwnPropertyDescriptor(m, k);
+    if (!desc || ("get" in desc ? !m.__esModule : desc.writable || desc.configurable)) {
+      desc = { enumerable: true, get: function() { return m[k]; } };
+    }
+    Object.defineProperty(o, k2, desc);
+}) : (function(o, m, k, k2) {
+    if (k2 === undefined) k2 = k;
+    o[k2] = m[k];
+}));
+var __setModuleDefault = (this && this.__setModuleDefault) || (Object.create ? (function(o, v) {
+    Object.defineProperty(o, "default", { enumerable: true, value: v });
+}) : function(o, v) {
+    o["default"] = v;
+});
+var __importStar = (this && this.__importStar) || (function () {
+    var ownKeys = function(o) {
+        ownKeys = Object.getOwnPropertyNames || function (o) {
+            var ar = [];
+            for (var k in o) if (Object.prototype.hasOwnProperty.call(o, k)) ar[ar.length] = k;
+            return ar;
+        };
+        return ownKeys(o);
+    };
+    return function (mod) {
+        if (mod && mod.__esModule) return mod;
+        var result = {};
+        if (mod != null) for (var k = ownKeys(mod), i = 0; i < k.length; i++) if (k[i] !== "default") __createBinding(result, mod, k[i]);
+        __setModuleDefault(result, mod);
+        return result;
+    };
+})();
+var __importDefault = (this && this.__importDefault) || function (mod) {
+    return (mod && mod.__esModule) ? mod : { "default": mod };
+};
+Object.defineProperty(exports, "__esModule", { value: true });
+exports.default = findCycles;
+const getGraphEdgeIdColumn_js_1 = __importDefault(require("../helpers/getGraphEdgeIdColumn.js"));
+const getGraphWeightColumn_js_1 = __importDefault(require("../helpers/getGraphWeightColumn.js"));
+const graphRouteResultSchema_js_1 = __importDefault(require("../helpers/graphRouteResultSchema.js"));
+const graphRouteResultSelect_js_1 = __importDefault(require("../helpers/graphRouteResultSelect.js"));
+const prepareGraphTemporalSql_js_1 = __importStar(require("../helpers/prepareGraphTemporalSql.js"));
+const prepareGraphStarts_js_1 = __importDefault(require("../helpers/prepareGraphStarts.js"));
+const prepareGraphTraversal_js_1 = __importStar(require("../helpers/prepareGraphTraversal.js"));
+const queueGraphResult_js_1 = __importDefault(require("../helpers/queueGraphResult.js"));
+const quoteIdentifier_js_1 = __importDefault(require("../helpers/quoteIdentifier.js"));
+const validateGraphTemporalEvents_js_1 = __importDefault(require("../helpers/validateGraphTemporalEvents.js"));
+const validateGraphRouteResultSchema_js_1 = __importDefault(require("../helpers/validateGraphRouteResultSchema.js"));
+function findCycles(simpleTable, sourceColumn, targetColumn, edgeId, startNodes, options = {}) {
+    if (typeof sourceColumn !== "string") {
+        throw new TypeError("findCycles() sourceColumn must be a string.");
+    }
+    if (typeof targetColumn !== "string") {
+        throw new TypeError("findCycles() targetColumn must be a string.");
+    }
+    if (typeof edgeId !== "string") {
+        throw new TypeError("findCycles() edgeId must be a string.");
+    }
+    const preparedStarts = (0, prepareGraphStarts_js_1.default)(startNodes, "findCycles()", "startNodes");
+    if (options === null || typeof options !== "object" || Array.isArray(options)) {
+        throw new TypeError("findCycles() options must be an object.");
+    }
+    if (options.direction !== undefined &&
+        !["outgoing", "incoming", "both"].includes(options.direction)) {
+        throw new TypeError('findCycles() options.direction must be "outgoing", "incoming", or "both".');
+    }
+    if (options.weight !== undefined && typeof options.weight !== "string") {
+        throw new TypeError("findCycles() options.weight must be a string.");
+    }
+    if (options.outputTable !== undefined &&
+        typeof options.outputTable !== "string" &&
+        typeof options.outputTable !== "boolean") {
+        throw new TypeError("findCycles() options.outputTable must be a string or boolean.");
+    }
+    const direction = options.direction ?? "outgoing";
+    const temporalOptions = (0, prepareGraphTemporalSql_js_1.prepareGraphTemporalOptions)(options, direction, "findCycles()");
+    options = structuredClone(options);
+    const parameters = {
+        sourceColumn,
+        targetColumn,
+        edgeId,
+        startNodes: structuredClone(startNodes),
+        options,
+    };
+    return (0, queueGraphResult_js_1.default)(simpleTable, {
+        method: "findCycles()",
+        parameters,
+        outputTable: options.outputTable,
+        preflight: temporalOptions === undefined
+            ? undefined
+            : (input) => (0, validateGraphTemporalEvents_js_1.default)(input, temporalOptions, "findCycles()", parameters),
+        values: (schema) => {
+            validateFindCyclesInputs(schema, sourceColumn, targetColumn, edgeId, preparedStarts, options.weight);
+            const temporal = temporalOptions === undefined
+                ? undefined
+                : (0, prepareGraphTemporalSql_js_1.default)(schema, temporalOptions, "findCycles()");
+            return temporal === undefined
+                ? preparedStarts.values
+                : [temporal.gapParameter, ...preparedStarts.values];
+        },
+        buildSelect: (input, schema) => findCyclesSelect(input, schema, sourceColumn, targetColumn, edgeId, preparedStarts, direction, options.weight, temporalOptions),
+        outputSchema: (schema) => {
+            const validated = validateFindCyclesInputs(schema, sourceColumn, targetColumn, edgeId, preparedStarts, options.weight);
+            if (temporalOptions !== undefined) {
+                (0, prepareGraphTemporalSql_js_1.default)(schema, temporalOptions, "findCycles()");
+            }
+            return {
+                start: validated.nodeIdType,
+                ...(0, graphRouteResultSchema_js_1.default)(schema, validated.distanceType, "findCycles()"),
+            };
+        },
+    });
+}
+function validateFindCyclesInputs(schema, source, target, edgeId, starts, weight) {
+    const endpoints = (0, prepareGraphTraversal_js_1.validateGraphStarts)(schema, source, target, starts, "findCycles()", "startNodes");
+    const edgeIdColumn = (0, getGraphEdgeIdColumn_js_1.default)(schema, edgeId, "findCycles()");
+    const weightColumn = weight === undefined
+        ? undefined
+        : (0, getGraphWeightColumn_js_1.default)(schema, weight, "findCycles()");
+    (0, validateGraphRouteResultSchema_js_1.default)(schema, "findCycles()", ["start"]);
+    return {
+        distanceType: weightColumn?.distanceType ?? "BIGINT",
+        edgeIdType: edgeIdColumn.idType,
+        nodeIdType: endpoints.idType,
+    };
+}
+function findCyclesSelect(input, schema, source, target, edgeId, starts, direction, weight, temporalOptions) {
+    const prepared = (0, prepareGraphTraversal_js_1.default)(input, schema, source, target, starts, "findCycles()", "startNodes");
+    const edgeIdColumn = (0, getGraphEdgeIdColumn_js_1.default)(schema, edgeId, "findCycles()");
+    const weightColumn = weight === undefined
+        ? undefined
+        : (0, getGraphWeightColumn_js_1.default)(schema, weight, "findCycles()");
+    const distanceType = weightColumn?.distanceType ?? "BIGINT";
+    const q = quoteIdentifier_js_1.default;
+    const edgeIdReference = `${q("edges")}.${q(edgeIdColumn.column)}`;
+    const typedEdgeId = `CAST(${edgeIdReference} AS ${edgeIdColumn.idType})`;
+    const edgeKey = edgeIdColumn.family === "string"
+        ? `ENCODE(${typedEdgeId})`
+        : typedEdgeId;
+    const edgeWeight = weightColumn === undefined
+        ? `CAST(1 AS ${distanceType})`
+        : `CAST(${q("edges")}.${q(weightColumn.column)} AS ${distanceType})`;
+    const stepType = `STRUCT(${q("edgeId")} ${edgeIdColumn.idType}, ${q("source")} ${prepared.endpoints.idType}, ${q("target")} ${prepared.endpoints.idType}, ${q("weight")} ${distanceType}, ${q("distance")} ${distanceType})`;
+    if (temporalOptions !== undefined) {
+        const temporal = (0, prepareGraphTemporalSql_js_1.default)(schema, temporalOptions, "findCycles()");
+        return temporalFindCyclesSelect(prepared, direction, temporal, typedEdgeId, edgeKey, edgeWeight, distanceType, stepType, input, edgeIdColumn);
+    }
+    const relations = prepared.relationNames([
+        "graph_start_values",
+        "graph_starts",
+        "graph_edges",
+        "graph_cycle_walks",
+        "graph_complete_cycles",
+        "graph_ranked_cycles",
+    ]);
+    const startValuesRelation = relations.graph_start_values;
+    const startsRelation = relations.graph_starts;
+    const edgesRelation = relations.graph_edges;
+    const walksRelation = relations.graph_cycle_walks;
+    const completeRelation = relations.graph_complete_cycles;
+    const rankedRelation = relations.graph_ranked_cycles;
+    const edgeFrom = `${q("edges")}.${q("__from")}`;
+    const edgeTo = `${q("edges")}.${q("__to")}`;
+    const edgeFromKey = `${q("edges")}.${q("__from_key")}`;
+    const edgeToKey = `${q("edges")}.${q("__to_key")}`;
+    const edgeIdentity = `${q("edges")}.${q("__edge_id")}`;
+    const edgeIdentityKey = `${q("edges")}.${q("__edge_key")}`;
+    const edgeCost = `${q("edges")}.${q("__weight")}`;
+    const walkDistance = `${q("walks")}.${q("distance")}`;
+    const candidateDistance = `CAST(${walkDistance} + ${edgeCost} AS ${distanceType})`;
+    return `WITH RECURSIVE ${startValuesRelation}(${q("start")}) AS (
+      VALUES ${prepared.startValues}
+    ), ${startsRelation} AS (
+      SELECT ${q("start")},
+        ${prepared.key(q("start"))} AS ${q("__start_key")}
+      FROM ${startValuesRelation}
+    ), ${edgesRelation} AS (
+      ${prepared.edges(direction, [
+        `${typedEdgeId} AS ${q("__edge_id")}`,
+        `${edgeKey} AS ${q("__edge_key")}`,
+        `${edgeWeight} AS ${q("__weight")}`,
+    ])}
+    ), ${walksRelation}(
+      ${q("start")}, ${q("__start_key")}, ${q("node")},
+      ${q("__node_key")}, ${q("__visited")}, ${q("__edge_keys")},
+      ${q("steps")}, ${q("distance")}, ${q("closed")}
+    ) AS (
+      SELECT ${q("starts")}.${q("start")},
+        ${q("starts")}.${q("__start_key")}, ${edgeTo}, ${edgeToKey},
+        CASE WHEN ${edgeFromKey} = ${edgeToKey}
+          THEN [${edgeFromKey}]
+          ELSE [${edgeFromKey}, ${edgeToKey}]
+        END,
+        [${edgeIdentityKey}],
+        [struct_pack(
+          ${q("edgeId")} := ${edgeIdentity},
+          ${q("source")} := ${edgeFrom},
+          ${q("target")} := ${edgeTo},
+          ${q("weight")} := ${edgeCost},
+          ${q("distance")} := ${edgeCost}
+        )]::${stepType}[],
+        ${edgeCost}, ${edgeFromKey} = ${edgeToKey}
+      FROM ${edgesRelation} AS ${q("edges")}
+      INNER JOIN ${startsRelation} AS ${q("starts")}
+        ON ${q("starts")}.${q("__start_key")} = ${edgeFromKey}
+      UNION ALL
+      SELECT ${q("walks")}.${q("start")},
+        ${q("walks")}.${q("__start_key")}, ${edgeTo}, ${edgeToKey},
+        list_append(${q("walks")}.${q("__visited")}, ${edgeToKey}),
+        list_append(${q("walks")}.${q("__edge_keys")}, ${edgeIdentityKey}),
+        list_append(${q("walks")}.${q("steps")}, struct_pack(
+          ${q("edgeId")} := ${edgeIdentity},
+          ${q("source")} := ${edgeFrom},
+          ${q("target")} := ${edgeTo},
+          ${q("weight")} := ${edgeCost},
+          ${q("distance")} := ${candidateDistance}
+        )), ${candidateDistance},
+        ${edgeToKey} = ${q("walks")}.${q("__start_key")}
+      FROM ${walksRelation} AS ${q("walks")}
+      INNER JOIN ${edgesRelation} AS ${q("edges")}
+        ON ${q("walks")}.${q("__node_key")} = ${edgeFromKey}
+      WHERE NOT ${q("walks")}.${q("closed")}
+        AND NOT list_contains(
+          ${q("walks")}.${q("__edge_keys")}, ${edgeIdentityKey}
+        )
+        AND (
+          ${edgeToKey} = ${q("walks")}.${q("__start_key")}
+          OR NOT list_contains(
+            ${q("walks")}.${q("__visited")}, ${edgeToKey}
+          )
+        )
+    ), ${completeRelation} AS (
+      SELECT DISTINCT ${q("start")}, ${q("__start_key")},
+        ${q("__edge_keys")}, ${q("steps")}
+      FROM ${walksRelation}
+      WHERE ${q("closed")}${direction === "both"
+        ? `
+        AND ${q("__edge_keys")} <= list_reverse(${q("__edge_keys")})`
+        : ""}
+    ), ${rankedRelation} AS (
+      SELECT ${q("start")}, ${q("__start_key")},
+        CAST(row_number() OVER (
+          PARTITION BY ${q("__start_key")}
+          ORDER BY ${q("__edge_keys")}) - 1
+          AS BIGINT) AS ${q("pathId")}, ${q("steps")}
+      FROM ${completeRelation}
+    )
+    ${(0, graphRouteResultSelect_js_1.default)(rankedRelation, input, edgeIdColumn, true)}`;
+}
+function temporalFindCyclesSelect(prepared, direction, temporal, typedEdgeId, edgeKey, edgeWeight, distanceType, stepType, input, edgeIdColumn) {
+    const q = quoteIdentifier_js_1.default;
+    const relations = prepared.relationNames([
+        "graph_start_values",
+        "graph_starts",
+        "graph_temporal_settings",
+        "graph_event_rows",
+        "graph_edges",
+        "graph_cycle_walks",
+        "graph_complete_cycles",
+        "graph_ranked_cycles",
+    ]);
+    const startValuesRelation = relations.graph_start_values;
+    const startsRelation = relations.graph_starts;
+    const settingsRelation = relations.graph_temporal_settings;
+    const eventRowsRelation = relations.graph_event_rows;
+    const edgesRelation = relations.graph_edges;
+    const walksRelation = relations.graph_cycle_walks;
+    const completeRelation = relations.graph_complete_cycles;
+    const rankedRelation = relations.graph_ranked_cycles;
+    const edgeFrom = `${q("edges")}.${q("__from")}`;
+    const edgeTo = `${q("edges")}.${q("__to")}`;
+    const edgeFromKey = `${q("edges")}.${q("__from_key")}`;
+    const edgeToKey = `${q("edges")}.${q("__to_key")}`;
+    const edgeIdentity = `${q("edges")}.${q("__edge_id")}`;
+    const edgeIdentityKey = `${q("edges")}.${q("__edge_key")}`;
+    const edgeCost = `${q("edges")}.${q("__weight")}`;
+    const walkDistance = `${q("walks")}.${q("distance")}`;
+    const candidateDistance = `CAST(${walkDistance} + ${edgeCost} AS ${distanceType})`;
+    const gap = `${q("settings")}.${q("__gap")}`;
+    const step = (distance) => `struct_pack(
+          ${q("edgeId")} := ${edgeIdentity},
+          ${q("source")} := ${edgeFrom},
+          ${q("target")} := ${edgeTo},
+          ${q("weight")} := ${edgeCost},
+          ${q("distance")} := ${distance}
+        )`;
+    return `WITH RECURSIVE ${settingsRelation} AS MATERIALIZED (
+      SELECT CAST(? AS HUGEINT) AS ${q("__gap")}
+    ), ${startValuesRelation}(${q("start")}) AS (
+      VALUES ${prepared.startValues}
+    ), ${startsRelation} AS (
+      SELECT ${q("start")},
+        ${prepared.key(q("start"))} AS ${q("__start_key")}
+      FROM ${startValuesRelation}
+    ), ${eventRowsRelation} AS MATERIALIZED (
+      ${prepared.edges(direction, [
+        `${typedEdgeId} AS ${q("__edge_id")}`,
+        `${edgeKey} AS ${q("__edge_key")}`,
+        `${edgeWeight} AS ${q("__weight")}`,
+        ...temporal.eventSelections("edges"),
+    ])}
+    ), ${edgesRelation} AS MATERIALIZED (
+      SELECT *
+      FROM ${eventRowsRelation} AS ${q("events")}
+      WHERE ${temporal.eventValidity("events")}
+    ), ${walksRelation}(
+      ${q("start")}, ${q("__start_key")}, ${q("node")},
+      ${q("__node_key")}, ${q("__visited")}, ${q("__event_ids")},
+      ${q("__edge_keys")}, ${q("steps")}, ${q("distance")},
+      ${q("closed")}, ${q("__event_id")}, ${q("__event_start")},
+      ${q("__event_end")}
+    ) AS (
+      SELECT ${q("starts")}.${q("start")},
+        ${q("starts")}.${q("__start_key")}, ${edgeTo}, ${edgeToKey},
+        CASE WHEN ${edgeFromKey} = ${edgeToKey}
+          THEN [${edgeFromKey}]
+          ELSE [${edgeFromKey}, ${edgeToKey}]
+        END,
+        [${q("edges")}.${q("__event_id")}], [${edgeIdentityKey}],
+        [${step(edgeCost)}]::${stepType}[], ${edgeCost},
+        ${edgeFromKey} = ${edgeToKey},
+        ${q("edges")}.${q("__event_id")},
+        ${q("edges")}.${q("__event_start")},
+        ${q("edges")}.${q("__event_end")}
+      FROM ${edgesRelation} AS ${q("edges")}
+      INNER JOIN ${startsRelation} AS ${q("starts")}
+        ON ${q("starts")}.${q("__start_key")} = ${edgeFromKey}
+      UNION ALL
+      SELECT ${q("walks")}.${q("start")},
+        ${q("walks")}.${q("__start_key")}, ${edgeTo}, ${edgeToKey},
+        list_append(${q("walks")}.${q("__visited")}, ${edgeToKey}),
+        list_append(${q("walks")}.${q("__event_ids")},
+          ${q("edges")}.${q("__event_id")}),
+        list_append(${q("walks")}.${q("__edge_keys")}, ${edgeIdentityKey}),
+        list_append(${q("walks")}.${q("steps")}, ${step(candidateDistance)}),
+        ${candidateDistance},
+        ${edgeToKey} = ${q("walks")}.${q("__start_key")},
+        ${q("edges")}.${q("__event_id")},
+        ${q("edges")}.${q("__event_start")},
+        ${q("edges")}.${q("__event_end")}
+      FROM ${walksRelation} AS ${q("walks")}
+      INNER JOIN ${edgesRelation} AS ${q("edges")}
+        ON ${q("walks")}.${q("__node_key")} = ${edgeFromKey}
+      CROSS JOIN ${settingsRelation} AS ${q("settings")}
+      WHERE NOT ${q("walks")}.${q("closed")}
+        AND NOT list_contains(${q("walks")}.${q("__event_ids")},
+          ${q("edges")}.${q("__event_id")})
+        AND (
+          ${edgeToKey} = ${q("walks")}.${q("__start_key")}
+          OR NOT list_contains(${q("walks")}.${q("__visited")}, ${edgeToKey})
+        )
+        AND ${temporal.transition("walks", "edges", direction, gap)}
+    ), ${completeRelation} AS (
+      SELECT DISTINCT ${q("start")}, ${q("__start_key")},
+        ${q("__edge_keys")}, ${q("steps")}
+      FROM ${walksRelation}
+      WHERE ${q("closed")}
+    ), ${rankedRelation} AS (
+      SELECT ${q("start")}, ${q("__start_key")},
+        CAST(row_number() OVER (
+          PARTITION BY ${q("__start_key")}
+          ORDER BY ${q("__edge_keys")}) - 1
+          AS BIGINT) AS ${q("pathId")}, ${q("steps")}
+      FROM ${completeRelation}
+    )
+    ${(0, graphRouteResultSelect_js_1.default)(rankedRelation, input, edgeIdColumn, true)}`;
+}

package/script/methods/fuzzyClean.d.ts.map

@@ -1 +1 @@
-{"version":3,"file":"fuzzyClean.d.ts","sourceRoot":"","sources":["../../src/methods/fuzzyClean.ts"],"names":[],"mappings":"AACA,OAAO,KAAK,WAAW,MAAM,yBAAyB,CAAC;AAMvD,MAAM,CAAC,OAAO,UAAU,UAAU,CAChC,KAAK,EAAE,WAAW,EAClB,MAAM,EAAE,MAAM,EACd,SAAS,EAAE,MAAM,EACjB,SAAS,EAAE,MAAM,EACjB,OAAO,GAAE;IACP,MAAM,CAAC,EACH,OAAO,GACP,eAAe,GACf,kBAAkB,GAClB,iBAAiB,CAAC;IACtB,QAAQ,CAAC,EACL,YAAY,GACZ,eAAe,GACf,gBAAgB,GAChB,aAAa,GACb,UAAU,CAAC;IACf,qBAAqB,CAAC,EAAE,MAAM,CAAC;CAC3B,GACL,IAAI,CAYN"}
+{"version":3,"file":"fuzzyClean.d.ts","sourceRoot":"","sources":["../../src/methods/fuzzyClean.ts"],"names":[],"mappings":"AAEA,OAAO,KAAK,WAAW,MAAM,yBAAyB,CAAC;AASvD,MAAM,CAAC,OAAO,UAAU,UAAU,CAChC,KAAK,EAAE,WAAW,EAClB,MAAM,EAAE,MAAM,EACd,SAAS,EAAE,MAAM,EACjB,SAAS,EAAE,MAAM,EACjB,OAAO,GAAE;IACP,MAAM,CAAC,EACH,OAAO,GACP,eAAe,GACf,kBAAkB,GAClB,iBAAiB,CAAC;IACtB,QAAQ,CAAC,EACL,YAAY,GACZ,eAAe,GACf,gBAAgB,GAChB,aAAa,GACb,UAAU,CAAC;IACf,qBAAqB,CAAC,EAAE,MAAM,CAAC;CAC3B,GACL,IAAI,CAWN"}

package/script/methods/fuzzyClean.js

@@ -5,14 +5,15 @@ var __importDefault = (this && this.__importDefault) || function (mod) {
 Object.defineProperty(exports, "__esModule", { value: true });
 exports.default = fuzzyClean;
 const quoteIdentifier_js_1 = __importDefault(require("../helpers/quoteIdentifier.js"));
+const node_api_1 = require("@duckdb/node-api");
 const mergeOptions_js_1 = __importDefault(require("../helpers/mergeOptions.js"));
 const queryDB_js_1 = __importDefault(require("../helpers/queryDB.js"));
 const queueOp_js_1 = __importDefault(require("../helpers/queueOp.js"));
 const buildFuzzyMatchSql_js_1 = __importDefault(require("../helpers/buildFuzzyMatchSql.js"));
+const selectFuzzyReplacements_js_1 = __importDefault(require("../helpers/selectFuzzyReplacements.js"));
 function fuzzyClean(table, column, newColumn, threshold, options = {}) {
-    // The clustering runs in JS over the fuzzy pairs read from the table, so
-    // fuzzyClean can't be expressed as a single SELECT over its input: it
-    // executes as a barrier.
+    // This implementation clusters fuzzy pairs in JS and writes the mapping
+    // back to DuckDB, so it executes as a barrier.
     options = structuredClone(options);
     (0, queueOp_js_1.default)(table, {
         kind: "barrier",
@@ -63,149 +64,29 @@ async function executeFuzzyClean(table, column, newColumn, threshold, options =
         }
         return;
     }
-    // Build count map from the pairs — no separate query needed.
-    const countMap = new Map();
-    for (const { left_value, left_cnt, right_value, right_cnt } of pairs) {
-        countMap.set(left_value, Number(left_cnt));
-        countMap.set(right_value, Number(right_cnt));
-    }
-    // Union-Find — only over values that actually participate in a pair.
-    const parent = new Map();
-    const find = (x) => {
-        if (!parent.has(x))
-            parent.set(x, x);
-        if (parent.get(x) !== x)
-            parent.set(x, find(parent.get(x)));
-        return parent.get(x);
-    };
-    const union = (a, b) => {
-        const ra = find(a);
-        const rb = find(b);
-        if (ra !== rb)
-            parent.set(ra, rb);
-    };
-    for (const v of countMap.keys())
-        find(v);
-    for (const { left_value, right_value } of pairs) {
-        union(left_value, right_value);
-    }
-    // Group values by their cluster root.
-    const clusters = new Map();
-    for (const v of countMap.keys()) {
-        const root = find(v);
-        if (!clusters.has(root))
-            clusters.set(root, []);
-        clusters.get(root).push(v);
-    }
-    // Pick the canonical value for each cluster.
-    const replacement = new Map();
-    for (const members of clusters.values()) {
-        if (members.length === 1)
-            continue; // All pairs are already canonical — skip.
-        // Score sums and per-member max scores are computed lazily — only when
-        // actually needed as a primary criterion or tie-breaker.
-        //
-        // scoreSum: total similarity to all other cluster members (used by
-        //   "mostCentral" as primary, and as tie-breaker for all strategies).
-        // scoreMax: highest single pairwise score (used by "maxScore" as primary).
-        let scoreSum = null;
-        const getScoreSum = () => {
-            if (scoreSum === null) {
-                scoreSum = new Map(members.map((m) => [m, 0]));
-                for (const { left_value, right_value, score } of pairs) {
-                    if (scoreSum.has(left_value) && scoreSum.has(right_value)) {
-                        scoreSum.set(left_value, (scoreSum.get(left_value) ?? 0) + score);
-                        scoreSum.set(right_value, (scoreSum.get(right_value) ?? 0) + score);
-                    }
-                }
-            }
-            return scoreSum;
-        };
-        let scoreMax = null;
-        const getScoreMax = () => {
-            if (scoreMax === null) {
-                scoreMax = new Map(members.map((m) => [m, 0]));
-                for (const { left_value, right_value, score } of pairs) {
-                    if (scoreMax.has(left_value) && scoreMax.has(right_value)) {
-                        scoreMax.set(left_value, Math.max(scoreMax.get(left_value) ?? 0, score));
-                        scoreMax.set(right_value, Math.max(scoreMax.get(right_value) ?? 0, score));
-                    }
-                }
-            }
-            return scoreMax;
-        };
-        // Sum-based comparator: highest total similarity, then alphabetical.
-        const byScore = (a, b) => {
-            const sum = getScoreSum();
-            const sa = sum.get(a) ?? 0;
-            const sb = sum.get(b) ?? 0;
-            if (sa !== sb)
-                return sa > sb ? a : b;
-            return a <= b ? a : b; // alphabetical tie-break
-        };
-        // Max-based comparator: highest single-pair score, then sum, then alphabetical.
-        const byMaxScore = (a, b) => {
-            const mx = getScoreMax();
-            const ma = mx.get(a) ?? 0;
-            const mb = mx.get(b) ?? 0;
-            if (ma !== mb)
-                return ma > mb ? a : b;
-            return byScore(a, b); // sum then alphabetical tie-break
-        };
-        let canonical;
-        if (strategy === "longestString") {
-            canonical = members.reduce((a, b) => {
-                if (a.length !== b.length)
-                    return a.length > b.length ? a : b;
-                return byScore(a, b);
-            });
-        }
-        else if (strategy === "shortestString") {
-            canonical = members.reduce((a, b) => {
-                if (a.length !== b.length)
-                    return a.length < b.length ? a : b;
-                return byScore(a, b);
-            });
-        }
-        else if (strategy === "mostCommon") {
-            canonical = members.reduce((a, b) => {
-                const ca = countMap.get(a) ?? 0;
-                const cb = countMap.get(b) ?? 0;
-                if (ca !== cb)
-                    return ca > cb ? a : b;
-                return byScore(a, b);
-            });
-        }
-        else if (strategy === "mostCentral") {
-            // Most central string — highest total similarity to all other cluster members.
-            canonical = members.reduce((a, b) => byScore(a, b));
-        }
-        else {
-            // "maxScore": the string participating in the single highest-scoring pair.
-            canonical = members.reduce((a, b) => byMaxScore(a, b));
-        }
-        for (const m of members) {
-            if (m !== canonical)
-                replacement.set(m, canonical);
-        }
-    }
+    const replacement = (0, selectFuzzyReplacements_js_1.default)(pairs, strategy);
     if (replacement.size === 0)
         return;
-    // Use a VALUES-based CTE for the UPDATE so DuckDB can use a hash join
-    // instead of evaluating a potentially huge CASE WHEN expression.
-    const replacementEntries = [...replacement.entries()];
-    const valuesList = replacementEntries.map(() => "(?, ?)").join(",\n     ");
-    const values = replacementEntries.flatMap(([from, to]) => [from, to]);
+    // Two bound lists keep the SQL and parameter count fixed as the mapping
+    // grows. Side-by-side UNNEST zips the equally sized lists into mapping rows,
+    // which DuckDB can hash-join to the original table.
+    const values = [
+        new node_api_1.DuckDBListValue([...replacement.keys()]),
+        new node_api_1.DuckDBListValue([...replacement.values()]),
+    ];
+    const mapping = `WITH mapping(original, canonical) AS (
+    SELECT UNNEST(?::VARCHAR[]), UNNEST(?::VARCHAR[])
+  )`;
     const query = newColumn !== column
         ? `ALTER TABLE ${(0, quoteIdentifier_js_1.default)(table.name)} ADD ${(0, quoteIdentifier_js_1.default)(newColumn)} VARCHAR;
        UPDATE ${(0, quoteIdentifier_js_1.default)(table.name)}
          SET ${(0, quoteIdentifier_js_1.default)(newColumn)} = ${(0, quoteIdentifier_js_1.default)(column)};
-       WITH mapping(original, canonical) AS (VALUES ${valuesList})
+       ${mapping}
        UPDATE ${(0, quoteIdentifier_js_1.default)(table.name)}
          SET ${(0, quoteIdentifier_js_1.default)(newColumn)} = m.canonical
          FROM mapping m
          WHERE ${(0, quoteIdentifier_js_1.default)(table.name)}.${(0, quoteIdentifier_js_1.default)(newColumn)} = m.original`
-        : `WITH mapping(original, canonical) AS (VALUES ${valuesList})
+        : `${mapping}
        UPDATE ${(0, quoteIdentifier_js_1.default)(table.name)}
          SET ${(0, quoteIdentifier_js_1.default)(column)} = m.canonical
          FROM mapping m