tm_back/cmd/worker/workers/translation.go

package workers

import (
	"context"
	"strings"
	"tm/internal/tender"
	"tm/pkg/ai_summarizer"
	"tm/pkg/logger"
	"tm/pkg/mongo"
)

// TranslationWorker syncs translation completion from the AI pipeline MinIO storage.
// Batch translation is triggered via POST /pipeline/translate; this worker only
// verifies which tenders now have translations available in storage.
type TranslationWorker struct {
	Mongo                     *mongo.ConnectionManager
	Logger                    logger.Logger
	TenderRepo                tender.TenderRepository
	AIClient                  *ai_summarizer.Client
	AIStorage                 *ai_summarizer.StorageClient
	TranslationSuccessCounter *mongo.Counter
	TargetLanguages           []string
	BatchSize                 int
}

// NewTranslationWorker creates a translation worker for the given target languages.
func NewTranslationWorker(
	mongo *mongo.ConnectionManager,
	logger logger.Logger,
	tenderRepo tender.TenderRepository,
	aiClient *ai_summarizer.Client,
	aiStorage *ai_summarizer.StorageClient,
	translationSuccessCounter *mongo.Counter,
	targetLanguages []string,
	batchSize int,
) *TranslationWorker {
	langs := make([]string, 0, len(targetLanguages))
	seen := make(map[string]struct{}, len(targetLanguages))
	for _, lang := range targetLanguages {
		clean := strings.ToLower(strings.TrimSpace(lang))
		if clean == "" {
			continue
		}
		if _, dup := seen[clean]; dup {
			continue
		}
		seen[clean] = struct{}{}
		langs = append(langs, clean)
	}
	if len(langs) == 0 {
		langs = []string{"en"}
	}
	if batchSize <= 0 {
		batchSize = 20
	}

	return &TranslationWorker{
		Mongo:                     mongo,
		Logger:                    logger,
		TenderRepo:                tenderRepo,
		AIClient:                  aiClient,
		AIStorage:                 aiStorage,
		TranslationSuccessCounter: translationSuccessCounter,
		TargetLanguages:           langs,
		BatchSize:                 batchSize,
	}
}

// Run triggers the AI translation pipeline and logs tenders with ready translations in MinIO.
func (w *TranslationWorker) Run() {
	if w.AIClient == nil {
		w.Logger.Warn("Translation worker skipped: AI client is not configured", map[string]interface{}{
			"target_languages": w.TargetLanguages,
		})
		return
	}

	w.Logger.Info("Translation worker started", map[string]interface{}{
		"target_languages": w.TargetLanguages,
		"batch_size":       w.BatchSize,
	})

	startCount := w.getSuccessfulTranslationCount(mongo.AITranslationSuccessCounterKeyDailyJob)

	if _, err := w.AIClient.TriggerPipelineTranslate(context.Background(), w.TargetLanguages); err != nil {
		w.Logger.Warn("Failed to trigger AI pipeline translate", map[string]interface{}{
			"target_languages": w.TargetLanguages,
			"error":            err.Error(),
		})
	}

	readyCount := 0
	for _, language := range w.TargetLanguages {
		readyCount += w.syncLanguageFromStorage(language)
	}

	endCount := w.getSuccessfulTranslationCount(mongo.AITranslationSuccessCounterKeyDailyJob)
	totalCount := w.getSuccessfulTranslationCount(mongo.AITranslationSuccessCounterKey)
	runCount := endCount - startCount
	if runCount < 0 {
		runCount = 0
	}

	w.Logger.Info("Translation worker completed", map[string]interface{}{
		"target_languages":                             w.TargetLanguages,
		"translations_ready_in_storage":                readyCount,
		"successful_ai_translation_requests_run":       runCount,
		"successful_ai_translation_requests_daily_job": endCount,
		"successful_ai_translation_requests_total":     totalCount,
	})
}

func (w *TranslationWorker) getSuccessfulTranslationCount(key string) int64 {
	if w.TranslationSuccessCounter == nil {
		return 0
	}
	count, err := w.TranslationSuccessCounter.Get(context.Background(), key)
	if err != nil {
		w.Logger.Warn("Failed to read AI translation success counter", map[string]interface{}{
			"counter_key": key,
			"error":       err.Error(),
		})
		return 0
	}
	return count
}

func (w *TranslationWorker) syncLanguageFromStorage(language string) int {
	if w.AIStorage == nil {
		w.Logger.Warn("Translation storage client not configured; skipping MinIO sync", map[string]interface{}{
			"target_language": language,
		})
		return 0
	}

	readyCount := 0
	skip := 0
	for {
		tenders, totalCount, err := w.TenderRepo.GetUnTranslatedTenders(context.Background(), language, w.BatchSize, skip)
		if err != nil {
			w.Logger.Error("Failed to fetch tenders for translation sync", map[string]interface{}{
				"target_language": language,
				"error":           err.Error(),
			})
			return readyCount
		}

		w.Logger.Info("Fetched tenders for translation sync", map[string]interface{}{
			"target_language": language,
			"batch_count":     len(tenders),
			"total_count":     totalCount,
			"skip":            skip,
		})

		if len(tenders) == 0 {
			return readyCount
		}

		for _, t := range tenders {
			if w.hasTranslationInStorage(&t, language) {
				readyCount++
				w.Logger.Debug("Translation available in MinIO", map[string]interface{}{
					"tender_id":       t.ID.Hex(),
					"notice_id":       t.NoticePublicationID,
					"target_language": language,
				})
			}
		}

		skip += len(tenders)
		if int64(skip) >= totalCount {
			return readyCount
		}
	}
}

func (w *TranslationWorker) hasTranslationInStorage(t *tender.Tender, language string) bool {
	if strings.TrimSpace(t.ContractFolderID) == "" || t.NoticePublicationID == "" {
		return false
	}
	stored, err := w.AIStorage.GetTranslationFromStorage(
		context.Background(),
		t.ContractFolderID,
		t.NoticePublicationID,
		language,
	)
	return err == nil && strings.TrimSpace(stored.Title) != ""
}