gitnexus 1.6.8-rc.8 → 1.6.8

package/dist/core/lbug/csv-generator.d.ts

@@ -11,23 +11,71 @@
  * - Double quotes within fields are escaped by doubling them ("")
  * - All fields are consistently quoted for safety with code content
  */
+import type { GraphNode, GraphRelationship } from '../../_shared/index.js';
 import { KnowledgeGraph } from '../graph/types.js';
 import { NodeTableName } from './schema.js';
 export declare const sanitizeUTF8: (str: string) => string;
 export declare const escapeCSVField: (value: string | number | undefined | null) => string;
 export declare const escapeCSVNumber: (value: number | undefined | null, defaultValue?: number) => string;
 export declare const isBinaryContent: (content: string) => boolean;
+/** Canonical relationship CSV header — shared by the emit pass and the
+ * `splitRelCsvByLabelPair` differential oracle. */
+export declare const REL_CSV_HEADER = "from,to,type,confidence,reason,step";
+/** Build the escaped CSV row (no trailing newline) for one relationship.
+ * Single source of the relationship row bytes — used by the emit pass and by
+ * the byte-identity differential test that feeds the legacy split oracle. */
+export declare const buildRelRow: (rel: GraphRelationship) => string;
+/** Canonical BasicBlock node CSV header — taint/PDG substrate (issue #2080).
+ * No `name` column; blocks are identified by id + source span. Shared by the
+ * whole-graph emit pass and the streaming PDG emit sink (issue #2202) so the
+ * two paths produce byte-identical BasicBlock rows by construction. */
+export declare const BASICBLOCK_CSV_HEADER = "id,filePath,startLine,endLine,text,callees,calleeIds";
+/** Build the escaped CSV row (no trailing newline) for one BasicBlock node.
+ * Single source of the BasicBlock row bytes — used by `streamAllCSVsToDisk`
+ * and by the streaming `PdgEmitSink` (issue #2202). `callees` is a comma-free
+ * (space-joined) list of the leaf callee names invoked in the block — the
+ * statement-precise inter-procedural reach substrate (the field is itself a CSV
+ * cell, so the inner separator must NOT be a comma). `calleeIds` is the SOUND
+ * parallel to `callees`: the space-joined RESOLVED callee symbol ids for the
+ * block (#2227 follow-up), likewise a comma-free cell. */
+export declare const buildBasicBlockRow: (node: GraphNode) => string;
 export interface StreamedCSVResult {
     nodeFiles: Map<NodeTableName, {
         csvPath: string;
         rows: number;
     }>;
-    relCsvPath: string;
-    relRows: number;
+    /** pairKey (`From|To`) → per-FROM→TO-label-pair CSV file. */
+    relsByPair: Map<string, {
+        csvPath: string;
+        rows: number;
+    }>;
+    /** Header line shared by every per-pair file. */
+    relHeader: string;
+    /** Edges skipped because an endpoint label is not a valid node table. */
+    skippedRels: number;
+    /** Edges routed to a per-pair file. */
+    totalValidRels: number;
 }
 /**
  * Stream all CSV data directly to disk files.
  * Iterates graph nodes exactly ONCE — routes each node to the right writer.
  * File contents are lazy-read from disk with a generous LRU cache.
+ *
+ * `onNodePhaseComplete` (optional, #2203 parallelism leg): fired exactly once,
+ * right after every node CSV is fully flushed to disk and BEFORE the
+ * relationship pass starts writing any `rel_*.csv`. It receives the finished
+ * node-file manifest so the caller can begin `COPY`-ing nodes while this
+ * function keeps generating relationship CSVs (the only single-writer-safe
+ * overlap — node `COPY` ‖ relationship emit). It is intentionally NOT awaited:
+ * the relationship pass proceeds concurrently with whatever the caller
+ * schedules. A synchronous throw from the callback is allowed and propagates out
+ * of this function (rejecting the returned promise) — it is raised before the
+ * relationship pass begins, so no `rel_*.csv` is written; `loadGraphToLbug` uses
+ * this to surface its PDG-manifest collision guard. The callback must NOT, however,
+ * schedule un-awaited async work that can reject unobserved. Absent ⇒ today's
+ * behavior, byte-for-byte.
  */
-export declare const streamAllCSVsToDisk: (graph: KnowledgeGraph, repoPath: string, csvDir: string) => Promise<StreamedCSVResult>;
+export declare const streamAllCSVsToDisk: (graph: KnowledgeGraph, repoPath: string, csvDir: string, onNodePhaseComplete?: (nodeFiles: Map<NodeTableName, {
+    csvPath: string;
+    rows: number;
+}>) => void) => Promise<StreamedCSVResult>;