proofdb/app/service/Search/ChunkSearchIndexRepository.php

<?php

namespace app\service\Search;

use app\service\Embedding\EmbeddingStatus;
use support\Db;

class ChunkSearchIndexRepository
{
    public function resetEmbeddedChunksToPending(?string $archiveUid = null): int
    {
        $query = Db::table('chunks')
            ->where('embedding_status', EmbeddingStatus::EMBEDDED);

        if ($archiveUid !== null && trim($archiveUid) !== '') {
            $query->where('archive_uid', trim($archiveUid));
        }

        return $query->update([
            'search_index_status' => SearchIndexStatus::PENDING,
            'search_index_error' => null,
            'search_index_updated_at' => null,
        ]);
    }

    public function queuePendingArchiveTasks(int $limit): array
    {
        $statuses = [
            SearchIndexStatus::PENDING,
            SearchIndexStatus::QUEUED,
            SearchIndexStatus::INDEXING,
            SearchIndexStatus::FAILED_RETRYABLE,
        ];

        $archiveUids = Db::table('chunks')
            ->where('embedding_status', EmbeddingStatus::EMBEDDED)
            ->whereIn('search_index_status', $statuses)
            ->select('archive_uid')
            ->groupBy('archive_uid')
            ->orderByRaw('MIN(id)')
            ->limit($limit)
            ->pluck('archive_uid')
            ->all();

        $archiveUids = array_values(array_filter(array_map('strval', $archiveUids)));
        foreach ($archiveUids as $archiveUid) {
            Db::table('chunks')
                ->where('archive_uid', $archiveUid)
                ->where('embedding_status', EmbeddingStatus::EMBEDDED)
                ->whereIn('search_index_status', $statuses)
                ->update([
                    'search_index_status' => SearchIndexStatus::QUEUED,
                    'search_index_error' => null,
                    'search_index_updated_at' => Db::raw('CURRENT_TIMESTAMP'),
                ]);
        }

        return $archiveUids;
    }

    public function findQueuedDocuments(string $archiveUid, int $limit): array
    {
        $rows = Db::table('chunks')
            ->join('archives', 'chunks.archive_uid', '=', 'archives.archive_uid')
            ->where('chunks.archive_uid', $archiveUid)
            ->where('chunks.embedding_status', EmbeddingStatus::EMBEDDED)
            ->whereIn('chunks.search_index_status', [SearchIndexStatus::QUEUED, SearchIndexStatus::INDEXING])
            ->orderBy('chunks.chunk_index')
            ->limit($limit)
            ->get([
                'chunks.chunk_uid',
                'chunks.archive_uid',
                'chunks.chunk_index',
                'chunks.page_start',
                'chunks.page_end',
                'chunks.text',
                'chunks.embedding_ref',
                'chunks.embedding_model',
                'chunks.created_time',
                'chunks.updated_time',
                'archives.title',
                'archives.summary',
                'archives.source',
                'archives.author',
                'archives.year',
                'archives.series',
                'archives.tags',
            ])
            ->all();

        return array_map(fn (object $row): array => $this->documentFromRow($row), $rows);
    }

    public function markIndexing(array $chunkUids): void
    {
        $this->updateStatus($chunkUids, SearchIndexStatus::INDEXING, null);
    }

    public function markIndexed(array $chunkUids): void
    {
        $this->updateStatus($chunkUids, SearchIndexStatus::INDEXED, null);
    }

    public function markFailed(array $chunkUids, string $error, bool $retryable): void
    {
        $this->updateStatus(
            $chunkUids,
            $retryable ? SearchIndexStatus::FAILED_RETRYABLE : SearchIndexStatus::FAILED_TERMINAL,
            $error
        );
    }

    private function documentFromRow(object $row): array
    {
        $embeddingRef = $this->decodeJson($row->embedding_ref ?? null, []);
        $embedding = is_array($embeddingRef['embedding'] ?? null) ? $embeddingRef['embedding'] : [];

        return [
            'chunk_uid' => (string) $row->chunk_uid,
            'archive_uid' => (string) $row->archive_uid,
            'chunk_index' => (int) $row->chunk_index,
            'page_start' => $row->page_start === null ? null : (int) $row->page_start,
            'page_end' => $row->page_end === null ? null : (int) $row->page_end,
            'title' => $row->title,
            'summary' => $row->summary,
            'source' => $row->source,
            'author' => $row->author,
            'year' => $row->year === null ? null : (int) $row->year,
            'series' => $row->series,
            'tags' => $this->decodeJson($row->tags ?? null, []),
            'text' => (string) $row->text,
            'embedding' => array_map('floatval', $embedding),
            'embedding_model' => (string) $row->embedding_model,
            'embedding_dimensions' => count($embedding),
            'created_time' => $this->dateString($row->created_time ?? null),
            'updated_time' => $this->dateString($row->updated_time ?? null),
        ];
    }

    private function updateStatus(array $chunkUids, int $status, ?string $error): void
    {
        if ($chunkUids === []) {
            return;
        }

        Db::table('chunks')->whereIn('chunk_uid', $chunkUids)->update([
            'search_index_status' => $status,
            'search_index_error' => $error === null ? null : mb_substr($error, 0, 4000),
            'search_index_updated_at' => Db::raw('CURRENT_TIMESTAMP'),
        ]);
    }

    private function decodeJson(mixed $value, array $fallback): array
    {
        if (is_array($value)) {
            return $value;
        }

        if (!is_string($value) || trim($value) === '') {
            return $fallback;
        }

        $decoded = json_decode($value, true);
        return is_array($decoded) ? $decoded : $fallback;
    }

    private function dateString(mixed $value): ?string
    {
        if ($value === null) {
            return null;
        }

        return date(DATE_ATOM, strtotime((string) $value) ?: time());
    }
}