Rebuild: the fragment merger

Files cut by a range's edge are put together once the ranges around them
are done (coordinator:run, every minute): a complete file is judged by the
rules and written as a release chunk with probe candidates; one still
missing parts while both neighbouring ranges are done is dropped and
counted (incomplete/edge). A neighbour not planned yet counts as not done,
except before the group's oldest article. BatchStore.writeReleases is the
shared write path.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>

lib/edge/index.ts

@@ -1,4 +1,6 @@
-export { RangeIndexer, type EdgeBatch, type ReleaseChunk, type DroppedChunk, type ProbeCandidate, type CandidateKind, type RuleCount, type Fragment, type RangeIndexerOptions } from './range_indexer.js'
+export { RangeIndexer, chunkOf, candidatesOf, releaseKeyOf, type EdgeBatch, type ReleaseChunk, type DroppedChunk, type ProbeCandidate, type CandidateKind, type RuleCount, type Fragment, type RangeIndexerOptions } from './range_indexer.js'
 export { encodeFrame, decodeFrames, isKeepalive, KEEPALIVE, type Frame } from './stream.js'
 export { toWire, fromWire, type WireBatch } from './wire.js'
 export type { Lease } from './lease.js'
+export { mergeFragments } from './merge.js'
+export type { EdgeSegment, FileMeta } from './scan.js'

lib/edge/merge.ts

@@ -0,0 +1,35 @@
+import type { AggregatedFile } from '../files/index.js'
+import type { Fragment } from './range_indexer.js'
+import type { EdgeSegment, FileMeta } from './scan.js'
+
+/**
+ * The fragments of one file from neighbouring ranges, put together
+ * (REBUILD.md, fragments): the complete file when every part from 1 to its
+ * total is there (the first article seen of a part wins), else null.
+ */
+export function mergeFragments(fragments: Fragment[]): AggregatedFile<EdgeSegment> | null {
+  if (fragments.length === 0) return null
+  const first = fragments[0]
+  const meta: FileMeta = {
+    fileKey: first.fileKey,
+    name: first.name,
+    poster: first.poster,
+    subject: first.subject,
+    totalParts: first.totalParts,
+    groups: first.groups,
+    release: first.release ? { ...first.release, source: first.release.source as any } : null,
+  }
+  const parts = new Map<number, EdgeSegment>()
+  for (const fragment of fragments) {
+    const postedAt = fragment.postedAt ?? Number.NaN
+    for (const [number, messageId, bytes, articleNumber] of fragment.segments) {
+      const known = parts.get(number)
+      if (!known || articleNumber < known.articleNumber) {
+        parts.set(number, { fileKey: meta.fileKey, number, totalParts: meta.totalParts, messageId, bytes, articleNumber, postedAt, file: meta })
+      }
+    }
+  }
+  if (parts.size < meta.totalParts) return null
+  for (let n = 1; n <= meta.totalParts; n++) if (!parts.has(n)) return null
+  return { fileKey: meta.fileKey, segments: [...parts.values()].sort((a, b) => a.number - b.number) }
+}

lib/edge/range_indexer.ts

@@ -280,7 +280,7 @@ export class RangeIndexer {
 }
 
 /** The release key; a file without a recognisable release becomes a release of its own. */
-function releaseKeyOf(s: EdgeSegment): string {
+export function releaseKeyOf(s: EdgeSegment): string {
   return s.file.release?.key ?? createHash('sha1').update(`file\n${s.fileKey}`).digest('hex')
 }
 
@@ -293,7 +293,7 @@ function postedOf(segments: EdgeSegment[]): number | null {
   return min
 }
 
-function chunkOf(key: string, files: AggregatedFile<EdgeSegment>[]): ReleaseChunk {
+export function chunkOf(key: string, files: AggregatedFile<EdgeSegment>[]): ReleaseChunk {
   const first = files[0].segments[0].file
   const chunkFiles: ChunkFile[] = files.map((f) => {
     const m = f.segments[0].file
@@ -339,7 +339,7 @@ function chunkOf(key: string, files: AggregatedFile<EdgeSegment>[]): ReleaseChun
  * volume, of its par2 index, of a lone random-named file, and a 7z set's
  * last volume (its listing is in the tail). At most a few per release.
  */
-function candidatesOf(key: string, files: AggregatedFile<EdgeSegment>[]): ProbeCandidate[] {
+export function candidatesOf(key: string, files: AggregatedFile<EdgeSegment>[]): ProbeCandidate[] {
   const out: ProbeCandidate[] = []
   let tail: { volume: number; file: AggregatedFile<EdgeSegment> } | null = null
   for (const f of files) {