Refactor dashboard repository to integrate ProcedureDocumentsLister
- Introduced the ProcedureDocumentsLister interface to list contract folders with scraped documents, enhancing the accuracy of document-scrape statistics. - Updated the dashboard repository to accept ProcedureDocumentsLister as a dependency, allowing for improved data retrieval. - Implemented tests for the new functionality, ensuring proper handling of scraped document folder IDs and error propagation. This update enhances the dashboard's capability to manage and report on scraped documents, improving overall system efficiency and data integrity.
This commit is contained in:
Mazyar
@@ -6,6 +6,7 @@ import (
|
||||
"strings"
|
||||
"time"
|
||||
"tm/internal/tender"
|
||||
"tm/pkg/ai_summarizer"
|
||||
"tm/pkg/logger"
|
||||
orm "tm/pkg/mongo"
|
||||
|
||||
@@ -13,6 +14,12 @@ import (
|
||||
"go.mongodb.org/mongo-driver/v2/mongo"
|
||||
)
|
||||
|
||||
// ProcedureDocumentsLister lists contract folders that have scraped documents in MinIO.
|
||||
// This is the source of truth for document-scrape statistics, matching tender panel search.
|
||||
type ProcedureDocumentsLister interface {
|
||||
ListProceduresWithDocuments(ctx context.Context) ([]ai_summarizer.ProcedureDocumentsSummary, error)
|
||||
}
|
||||
|
||||
const defaultValueCurrency = "EUR"
|
||||
|
||||
// Repository defines dashboard data access.
|
||||
@@ -27,19 +34,21 @@ type Repository interface {
|
||||
}
|
||||
|
||||
type repository struct {
|
||||
ormRepo orm.Repository[tender.Tender]
|
||||
mongoManager *orm.ConnectionManager
|
||||
metricsCounter *orm.Counter
|
||||
logger logger.Logger
|
||||
ormRepo orm.Repository[tender.Tender]
|
||||
mongoManager *orm.ConnectionManager
|
||||
metricsCounter *orm.Counter
|
||||
procedureLister ProcedureDocumentsLister
|
||||
logger logger.Logger
|
||||
}
|
||||
|
||||
// NewRepository creates a dashboard repository backed by the tenders collection.
|
||||
func NewRepository(mongoManager *orm.ConnectionManager, log logger.Logger) Repository {
|
||||
func NewRepository(mongoManager *orm.ConnectionManager, log logger.Logger, procedureLister ProcedureDocumentsLister) Repository {
|
||||
return &repository{
|
||||
ormRepo: orm.NewRepository[tender.Tender](mongoManager.GetCollection(tenderCollectionName()), log),
|
||||
mongoManager: mongoManager,
|
||||
metricsCounter: orm.NewCounter(mongoManager),
|
||||
logger: log,
|
||||
ormRepo: orm.NewRepository[tender.Tender](mongoManager.GetCollection(tenderCollectionName()), log),
|
||||
mongoManager: mongoManager,
|
||||
metricsCounter: orm.NewCounter(mongoManager),
|
||||
procedureLister: procedureLister,
|
||||
logger: log,
|
||||
}
|
||||
}
|
||||
|
||||
@@ -313,16 +322,16 @@ func (r *repository) ClosingSoon(ctx context.Context, limit int, windowSec int64
|
||||
{{Key: "$sort", Value: bson.M{"effective_deadline": 1}}},
|
||||
{{Key: "$limit", Value: limit}},
|
||||
{{Key: "$project", Value: bson.M{
|
||||
"_id": 1,
|
||||
"title": 1,
|
||||
"country_code": 1,
|
||||
"buyer_organization": 1,
|
||||
"submission_deadline": 1,
|
||||
"tender_deadline": 1,
|
||||
"status": 1,
|
||||
"estimated_value": 1,
|
||||
"currency": 1,
|
||||
"effective_deadline": 1,
|
||||
"_id": 1,
|
||||
"title": 1,
|
||||
"country_code": 1,
|
||||
"buyer_organization": 1,
|
||||
"submission_deadline": 1,
|
||||
"tender_deadline": 1,
|
||||
"status": 1,
|
||||
"estimated_value": 1,
|
||||
"currency": 1,
|
||||
"effective_deadline": 1,
|
||||
}}},
|
||||
}
|
||||
|
||||
@@ -351,12 +360,12 @@ func (r *repository) Recent(ctx context.Context, limit int, cursor string) ([]Re
|
||||
filter,
|
||||
orm.ListPaginationOptions{
|
||||
Projection: bson.M{
|
||||
"title": 1,
|
||||
"country_code": 1,
|
||||
"status": 1,
|
||||
"title": 1,
|
||||
"country_code": 1,
|
||||
"status": 1,
|
||||
"buyer_organization": 1,
|
||||
"created_at": 1,
|
||||
"publication_date": 1,
|
||||
"created_at": 1,
|
||||
"publication_date": 1,
|
||||
},
|
||||
},
|
||||
)
|
||||
|
||||
@@ -3,6 +3,7 @@ package dashboard
|
||||
import (
|
||||
"context"
|
||||
"fmt"
|
||||
"strings"
|
||||
"time"
|
||||
|
||||
"tm/internal/notice"
|
||||
@@ -63,9 +64,9 @@ func (r *repository) Statistics(ctx context.Context, days int, startUnix int64)
|
||||
})
|
||||
|
||||
g.Go(func() error {
|
||||
total, err := r.totalScrapedDocuments(gctx)
|
||||
total, err := r.totalScrapedTenders(gctx)
|
||||
if err != nil {
|
||||
return fmt.Errorf("total scraped documents: %w", err)
|
||||
return fmt.Errorf("total scraped tenders: %w", err)
|
||||
}
|
||||
totalDocuments = total
|
||||
return nil
|
||||
@@ -127,23 +128,18 @@ func (r *repository) dailyCountByTimestamp(ctx context.Context, collection strin
|
||||
}
|
||||
|
||||
func (r *repository) scrapedDocumentsPerDay(ctx context.Context, startUnix int64) (map[string]int64, error) {
|
||||
match, err := r.scrapedTendersMatchFilter(ctx)
|
||||
if err != nil {
|
||||
return nil, err
|
||||
}
|
||||
if len(match) == 0 {
|
||||
return map[string]int64{}, nil
|
||||
}
|
||||
|
||||
pipeline := mongodriver.Pipeline{
|
||||
{{Key: "$match", Value: bson.M{
|
||||
"processing_metadata.documents_scraped": true,
|
||||
"scraped_documents": bson.M{"$exists": true, "$ne": bson.A{}},
|
||||
}}},
|
||||
{{Key: "$unwind", Value: "$scraped_documents"}},
|
||||
{{Key: "$match", Value: match}},
|
||||
{{Key: "$addFields", Value: bson.M{
|
||||
"metric_ts": bson.M{
|
||||
"$cond": bson.A{
|
||||
bson.M{"$gt": bson.A{"$scraped_documents.scraped_at", 0}},
|
||||
"$scraped_documents.scraped_at",
|
||||
"$processing_metadata.documents_scraped_at",
|
||||
},
|
||||
},
|
||||
}}},
|
||||
{{Key: "$addFields", Value: bson.M{
|
||||
"metric_ts": normalizeTimestampExpr("metric_ts"),
|
||||
"metric_ts": normalizeTimestampExpr("processing_metadata.documents_scraped_at"),
|
||||
}}},
|
||||
{{Key: "$match", Value: bson.M{
|
||||
"metric_ts": bson.M{"$gte": startUnix, "$gt": 0},
|
||||
@@ -173,37 +169,63 @@ func (r *repository) translatedNoticesPerDay(ctx context.Context, startDay, endD
|
||||
return r.metricsCounter.GetDailyCounts(ctx, startDay, endDay)
|
||||
}
|
||||
|
||||
func (r *repository) totalScrapedDocuments(ctx context.Context) (int64, error) {
|
||||
pipeline := mongodriver.Pipeline{
|
||||
{{Key: "$match", Value: bson.M{
|
||||
"processing_metadata.documents_scraped": true,
|
||||
"scraped_documents": bson.M{"$exists": true, "$ne": bson.A{}},
|
||||
}}},
|
||||
{{Key: "$project", Value: bson.M{
|
||||
"doc_count": bson.M{"$size": "$scraped_documents"},
|
||||
}}},
|
||||
{{Key: "$group", Value: bson.M{
|
||||
"_id": nil,
|
||||
"total": bson.M{"$sum": "$doc_count"},
|
||||
}}},
|
||||
}
|
||||
|
||||
cursor, err := r.mongoManager.GetCollection(tenderCollectionName()).Aggregate(ctx, pipeline)
|
||||
func (r *repository) totalScrapedTenders(ctx context.Context) (int64, error) {
|
||||
match, err := r.scrapedTendersMatchFilter(ctx)
|
||||
if err != nil {
|
||||
return 0, err
|
||||
}
|
||||
defer cursor.Close(ctx)
|
||||
|
||||
if !cursor.Next(ctx) {
|
||||
if len(match) == 0 {
|
||||
return 0, nil
|
||||
}
|
||||
|
||||
var row bson.M
|
||||
if err := cursor.Decode(&row); err != nil {
|
||||
return 0, err
|
||||
return r.ormRepo.Count(ctx, match)
|
||||
}
|
||||
|
||||
func (r *repository) scrapedTendersMatchFilter(ctx context.Context) (bson.M, error) {
|
||||
folderIDs, err := r.scrapedDocumentsFolderIDs(ctx)
|
||||
if err != nil {
|
||||
return nil, err
|
||||
}
|
||||
if len(folderIDs) > 0 {
|
||||
return bson.M{"contract_folder_id": bson.M{"$in": folderIDs}}, nil
|
||||
}
|
||||
if r.procedureLister != nil {
|
||||
return bson.M{}, nil
|
||||
}
|
||||
return bson.M{
|
||||
"processing_metadata.documents_scraped": true,
|
||||
"scraped_documents": bson.M{"$exists": true, "$ne": bson.A{}},
|
||||
}, nil
|
||||
}
|
||||
|
||||
func (r *repository) scrapedDocumentsFolderIDs(ctx context.Context) ([]string, error) {
|
||||
if r.procedureLister == nil {
|
||||
return nil, nil
|
||||
}
|
||||
|
||||
return aggregateCount(row, "total"), nil
|
||||
procedures, err := r.procedureLister.ListProceduresWithDocuments(ctx)
|
||||
if err != nil {
|
||||
return nil, err
|
||||
}
|
||||
|
||||
folderIDs := make([]string, 0, len(procedures))
|
||||
seen := make(map[string]struct{}, len(procedures))
|
||||
for _, proc := range procedures {
|
||||
if proc.DocumentCount <= 0 {
|
||||
continue
|
||||
}
|
||||
id := strings.TrimSpace(proc.ContractFolderID)
|
||||
if id == "" {
|
||||
continue
|
||||
}
|
||||
if _, ok := seen[id]; ok {
|
||||
continue
|
||||
}
|
||||
seen[id] = struct{}{}
|
||||
folderIDs = append(folderIDs, id)
|
||||
}
|
||||
|
||||
return folderIDs, nil
|
||||
}
|
||||
|
||||
func decodeDailyCounts(ctx context.Context, cursor *mongodriver.Cursor) (map[string]int64, error) {
|
||||
|
||||
@@ -0,0 +1,74 @@
|
||||
package dashboard
|
||||
|
||||
import (
|
||||
"context"
|
||||
"errors"
|
||||
"testing"
|
||||
|
||||
"tm/pkg/ai_summarizer"
|
||||
)
|
||||
|
||||
type mockProcedureDocumentsLister struct {
|
||||
procedures []ai_summarizer.ProcedureDocumentsSummary
|
||||
err error
|
||||
}
|
||||
|
||||
func (m *mockProcedureDocumentsLister) ListProceduresWithDocuments(context.Context) ([]ai_summarizer.ProcedureDocumentsSummary, error) {
|
||||
if m.err != nil {
|
||||
return nil, m.err
|
||||
}
|
||||
return m.procedures, nil
|
||||
}
|
||||
|
||||
func TestScrapedDocumentsFolderIDsUsesMinIOProcedures(t *testing.T) {
|
||||
repo := &repository{
|
||||
procedureLister: &mockProcedureDocumentsLister{
|
||||
procedures: []ai_summarizer.ProcedureDocumentsSummary{
|
||||
{ContractFolderID: "PROC-1", DocumentCount: 3},
|
||||
{ContractFolderID: "PROC-2", DocumentCount: 0},
|
||||
{ContractFolderID: " PROC-3 ", DocumentCount: 1},
|
||||
{ContractFolderID: "PROC-1", DocumentCount: 2},
|
||||
},
|
||||
},
|
||||
}
|
||||
|
||||
got, err := repo.scrapedDocumentsFolderIDs(context.Background())
|
||||
if err != nil {
|
||||
t.Fatalf("unexpected error: %v", err)
|
||||
}
|
||||
|
||||
want := []string{"PROC-1", "PROC-3"}
|
||||
if len(got) != len(want) {
|
||||
t.Fatalf("expected %d folder IDs, got %d: %v", len(want), len(got), got)
|
||||
}
|
||||
for i, id := range want {
|
||||
if got[i] != id {
|
||||
t.Fatalf("expected folder ID %q at index %d, got %q", id, i, got[i])
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
func TestScrapedDocumentsFolderIDsWithoutLister(t *testing.T) {
|
||||
repo := &repository{}
|
||||
|
||||
got, err := repo.scrapedDocumentsFolderIDs(context.Background())
|
||||
if err != nil {
|
||||
t.Fatalf("unexpected error: %v", err)
|
||||
}
|
||||
if got != nil {
|
||||
t.Fatalf("expected nil folder IDs without lister, got %v", got)
|
||||
}
|
||||
}
|
||||
|
||||
func TestScrapedDocumentsFolderIDsPropagatesError(t *testing.T) {
|
||||
repo := &repository{
|
||||
procedureLister: &mockProcedureDocumentsLister{
|
||||
err: errors.New("minio unavailable"),
|
||||
},
|
||||
}
|
||||
|
||||
_, err := repo.scrapedDocumentsFolderIDs(context.Background())
|
||||
if err == nil {
|
||||
t.Fatal("expected error")
|
||||
}
|
||||
}
|
||||
Reference in New Issue
Block a user