crawlrs 0.2.0

crawlrs - Enterprise-grade web scraping and crawling platform built with Rust
Documentation
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
587
588
589
590
591
592
593
594
595
596
597
598
599
600
601
602
603
604
605
606
607
608
609
610
611
612
613
614
615
616
617
618
619
620
621
622
623
624
625
626
627
628
629
630
631
632
633
634
635
636
637
638
639
640
641
642
643
644
645
646
647
648
649
650
651
652
653
654
655
656
657
658
659
660
661
662
663
664
665
666
667
668
669
670
671
672
673
674
675
676
677
678
679
680
681
682
683
684
685
686
687
688
689
690
691
692
693
694
695
696
697
698
699
700
701
702
703
704
705
706
707
708
709
710
711
712
713
714
715
716
717
718
719
720
721
722
723
724
725
726
727
728
729
730
731
732
733
734
735
736
737
738
739
740
741
742
743
744
745
746
747
748
749
750
751
752
753
754
755
756
757
758
759
760
761
762
763
764
765
766
767
768
769
770
771
772
773
774
775
776
777
778
779
780
781
782
783
784
785
786
787
788
789
790
791
792
793
794
795
796
797
798
799
800
801
802
803
804
805
806
807
808
809
810
811
812
813
814
815
816
817
818
819
820
821
822
823
824
825
826
827
828
829
830
831
832
833
834
835
836
837
838
839
840
841
842
843
844
845
846
847
848
849
850
851
852
853
854
855
856
857
858
859
860
861
862
863
864
865
866
867
868
869
870
871
872
873
874
875
876
877
878
879
880
881
882
883
884
885
886
887
888
889
890
891
892
893
894
895
896
897
898
899
900
901
902
903
904
905
906
907
908
909
910
911
912
913
914
915
916
917
918
919
920
921
922
923
924
925
926
927
928
929
930
931
932
933
934
935
936
937
938
939
940
941
942
943
944
945
946
947
948
// Copyright (c) 2025-2026 Kirky.X🌠
// SPDX-License-Identifier: Apache-2.0

//! ScrapeResult repository implementation using dbnexus

use crate::domain::models::ScrapeResult;
use crate::domain::repositories::scrape_result_repository::ScrapeResultRepository;
use crate::infrastructure::database::entities::scrape_result as db_entity;
use async_trait::async_trait;
use dbnexus::sea_orm::{
    ActiveModelTrait, ColumnTrait, ConnectionTrait, DatabaseBackend, EntityTrait, PaginatorTrait,
    QueryFilter, QueryOrder, QueryResult, QuerySelect, Set, Statement,
};
use dbnexus::DbPool;
use std::sync::Arc;

/// ScrapeResult repository implementation using dbnexus
pub struct ScrapeResultRepositoryImpl {
    /// Database pool
    pool: Arc<DbPool>,
}

impl ScrapeResultRepositoryImpl {
    /// Create new ScrapeResult repository instance
    pub fn new(pool: Arc<DbPool>) -> Self {
        Self { pool }
    }

    /// Get database pool reference
    pub fn pool(&self) -> &Arc<DbPool> {
        &self.pool
    }

    /// Convert domain model to database active model
    fn to_active_model(result: &ScrapeResult) -> db_entity::ActiveModel {
        use chrono::FixedOffset;
        db_entity::ActiveModel {
            id: Set(result.id.into()),
            task_id: Set(result.task_id.into()),
            url: Set(result.url.clone()),
            status_code: Set(result.status_code),
            content: Set(result.content.clone()),
            content_type: Set(result.content_type.clone()),
            headers: Set(Some(result.headers.clone())),
            meta_data: Set(Some(result.meta_data.clone())),
            screenshot: Set(result.screenshot.clone()),
            response_time_ms: Set(result.response_time_ms),
            created_at: Set(result
                .created_at
                .with_timezone(&FixedOffset::east_opt(0).unwrap())),
        }
    }

    /// Convert database model to domain model
    fn to_domain(model: db_entity::Model) -> ScrapeResult {
        ScrapeResult {
            id: model.id.into(),
            task_id: model.task_id.into(),
            url: model.url,
            status_code: model.status_code,
            content: model.content,
            content_type: model.content_type,
            headers: model.headers.unwrap_or(serde_json::json!({})),
            meta_data: model.meta_data.unwrap_or(serde_json::json!({})),
            screenshot: model.screenshot,
            response_time_ms: model.response_time_ms,
            created_at: model.created_at.with_timezone(&chrono::Utc),
        }
    }
}

#[async_trait]
impl ScrapeResultRepository for ScrapeResultRepositoryImpl {
    /// 存在性投影(COUNT):供结果行不变量检查使用,避免整行(content/
    /// screenshot 大字段)回读
    async fn has_result_for_task(&self, task_id: crate::domain::id::Id) -> anyhow::Result<bool> {
        let session = self
            .pool
            .get_session("admin")
            .await
            .map_err(|e| anyhow::anyhow!("Failed to get session: {}", e))?;
        let conn = session
            .connection()
            .map_err(|e| anyhow::anyhow!("Failed to get connection: {}", e))?;

        let count = db_entity::Entity::find()
            .filter(db_entity::Column::TaskId.eq(task_id))
            .count(conn)
            .await
            .map_err(|e| anyhow::anyhow!("Failed to count results: {}", e))?;
        Ok(count > 0)
    }

    async fn save(&self, result: ScrapeResult) -> anyhow::Result<()> {
        let session = self
            .pool
            .get_session("admin")
            .await
            .map_err(|e| anyhow::anyhow!("Failed to get session: {}", e))?;

        let conn = session
            .connection()
            .map_err(|e| anyhow::anyhow!("Failed to get connection: {}", e))?;

        let active_model = Self::to_active_model(&result);

        active_model
            .insert(conn)
            .await
            .map_err(|e| anyhow::anyhow!("Failed to insert: {}", e))?;

        Ok(())
    }

    async fn find_by_task_id(
        &self,
        task_id: crate::domain::id::Id,
    ) -> anyhow::Result<Option<ScrapeResult>> {
        let session = self
            .pool
            .get_session("admin")
            .await
            .map_err(|e| anyhow::anyhow!("Failed to get session: {}", e))?;

        let conn = session
            .connection()
            .map_err(|e| anyhow::anyhow!("Failed to get connection: {}", e))?;

        let result = db_entity::Entity::find()
            .filter(db_entity::Column::TaskId.eq(task_id))
            .one(conn)
            .await
            .map_err(|e| anyhow::anyhow!("Failed to find: {}", e))?;

        Ok(result.map(Self::to_domain))
    }

    async fn find_by_task_ids(
        &self,
        task_ids: &[crate::domain::id::Id],
    ) -> anyhow::Result<Vec<ScrapeResult>> {
        if task_ids.is_empty() {
            return Ok(Vec::new());
        }

        let session = self
            .pool
            .get_session("admin")
            .await
            .map_err(|e| anyhow::anyhow!("Failed to get session: {}", e))?;

        let conn = session
            .connection()
            .map_err(|e| anyhow::anyhow!("Failed to get connection: {}", e))?;

        let results = db_entity::Entity::find()
            .filter(db_entity::Column::TaskId.is_in(task_ids.to_vec()))
            .all(conn)
            .await
            .map_err(|e| anyhow::anyhow!("Failed to find: {}", e))?;

        Ok(results.into_iter().map(Self::to_domain).collect())
    }

    async fn get_team_avg_response_time(
        &self,
        team_id: crate::domain::id::Id,
    ) -> anyhow::Result<f64> {
        let session = self
            .pool
            .get_session("admin")
            .await
            .map_err(|e| anyhow::anyhow!("Failed to get session: {}", e))?;

        let conn = session
            .connection()
            .map_err(|e| anyhow::anyhow!("Failed to get connection: {}", e))?;

        // JOIN scrape_results with tasks on task_id, filter by team_id and
        // last 30 days. AVG(bigint) returns numeric; cast to DOUBLE PRECISION
        // so it maps cleanly to f64. COALESCE returns 0.0 when no rows match.
        let stmt = Statement::from_sql_and_values(
            DatabaseBackend::Postgres,
            r#"SELECT COALESCE(AVG(sr.response_time_ms), 0)::DOUBLE PRECISION AS avg_ms
               FROM scrape_results sr
               JOIN tasks t ON sr.task_id = t.id
               WHERE t.team_id = $1
                 AND sr.created_at >= NOW() - INTERVAL '30 days'"#,
            [team_id.into()],
        );

        let row: Option<QueryResult> = conn
            .query_one_raw(stmt)
            .await
            .map_err(|e| anyhow::anyhow!("Failed to query avg response time: {}", e))?;

        let avg = row
            .and_then(|r| r.try_get::<f64>("", "avg_ms").ok())
            .unwrap_or(0.0);

        Ok(avg)
    }

    async fn cleanup_expired(&self, retention_days: i64) -> anyhow::Result<u64> {
        // 保留期 <= 0 表示禁用清理(旧行为:永不删除)
        if retention_days <= 0 {
            return Ok(0);
        }

        // try_days 在 i64 极端值下返回 None,避免 Duration::days 的 panic 路径
        let delta = chrono::TimeDelta::try_days(retention_days)
            .ok_or_else(|| anyhow::anyhow!("retention_days out of range: {}", retention_days))?;
        let cutoff = chrono::Utc::now() - delta;
        let cutoff = cutoff.with_timezone(&chrono::FixedOffset::east_opt(0).unwrap());

        let session = self
            .pool
            .get_session("admin")
            .await
            .map_err(|e| anyhow::anyhow!("Failed to get session: {}", e))?;

        let conn = session
            .connection()
            .map_err(|e| anyhow::anyhow!("Failed to get connection: {}", e))?;

        let result = db_entity::Entity::delete_many()
            .filter(db_entity::Column::CreatedAt.lt(cutoff))
            .exec(conn)
            .await
            .map_err(|e| anyhow::anyhow!("Failed to cleanup expired results: {}", e))?;

        Ok(result.rows_affected)
    }

    async fn list_distinct_urls(
        &self,
        limit: u32,
        after_url: Option<String>,
    ) -> anyhow::Result<Vec<String>> {
        let session = self
            .pool
            .get_session("admin")
            .await
            .map_err(|e| anyhow::anyhow!("Failed to get session: {}", e))?;

        let conn = session
            .connection()
            .map_err(|e| anyhow::anyhow!("Failed to get connection: {}", e))?;

        // keyset 分页(url > after_url):每页 O(limit),配合 url 升序稳定
        // 翻页。语义对齐 TaskRepository::list_distinct_urls(seen 预热路径)。
        let mut query = db_entity::Entity::find()
            .select_only()
            .column(db_entity::Column::Url)
            .distinct()
            .order_by_asc(db_entity::Column::Url)
            .limit(u64::from(limit));
        if let Some(after) = after_url {
            query = query.filter(db_entity::Column::Url.gt(after));
        }
        let urls = query
            .into_tuple::<String>()
            .all(conn)
            .await
            .map_err(|e| anyhow::anyhow!("Failed to list distinct urls: {}", e))?;

        Ok(urls)
    }
}

#[cfg(test)]
mod tests {
    use super::*;
    use crate::common::test_helpers::create_test_db_pool;
    use chrono::{FixedOffset, TimeZone};

    fn sample_scrape_result() -> ScrapeResult {
        ScrapeResult {
            id: crate::domain::id::Id::generate(),
            task_id: crate::domain::id::Id::generate(),
            url: "https://example.com/page".to_string(),
            status_code: 200,
            content: "<html>hello</html>".to_string(),
            content_type: "text/html".to_string(),
            headers: serde_json::json!({"content-type": "text/html"}),
            meta_data: serde_json::json!({"lang": "en"}),
            screenshot: Some("base64screenshot".to_string()),
            response_time_ms: 150,
            created_at: chrono::DateTime::from_timestamp(1_700_000_000, 0)
                .expect("valid timestamp"),
        }
    }

    fn sample_db_model() -> db_entity::Model {
        db_entity::Model {
            id: crate::domain::id::Id::generate().into(),
            task_id: crate::domain::id::Id::generate().into(),
            url: "https://example.com/page".to_string(),
            status_code: 404,
            content: "not found".to_string(),
            content_type: "text/plain".to_string(),
            response_time_ms: 42,
            created_at: FixedOffset::east_opt(0).unwrap().from_utc_datetime(
                &chrono::DateTime::from_timestamp(1_700_000_000, 0)
                    .expect("valid timestamp")
                    .naive_utc(),
            ),
            headers: Some(serde_json::json!({"x-custom": "value"})),
            meta_data: Some(serde_json::json!({"source": "test"})),
            screenshot: None,
        }
    }

    // construction & accessor

    #[test]
    fn test_new_creates_repository_instance() {
        if crate::common::test_helpers::skip_if_no_test_db() {
            return;
        }
        let pool = create_test_db_pool();
        let repo = ScrapeResultRepositoryImpl::new(pool);
        // pool accessor should return the same Arc
        let pool_ref = repo.pool();
        assert!(Arc::strong_count(pool_ref) >= 1);
    }

    // pure conversion functions

    #[test]
    fn test_to_active_model_converts_all_fields() {
        if crate::common::test_helpers::skip_if_no_test_db() {
            return;
        }
        let result = sample_scrape_result();
        let active = ScrapeResultRepositoryImpl::to_active_model(&result);

        // ActiveModel fields are Set; extract via unwrap to verify
        assert_eq!(result.id, active.id.unwrap());
        assert_eq!(result.task_id, active.task_id.unwrap());
        assert_eq!(active.url.unwrap(), result.url);
        assert_eq!(active.status_code.unwrap(), result.status_code);
        assert_eq!(active.content.unwrap(), result.content);
        assert_eq!(active.content_type.unwrap(), result.content_type);
        assert_eq!(active.response_time_ms.unwrap(), result.response_time_ms);
        assert_eq!(active.screenshot.unwrap(), result.screenshot);
        // headers/meta_data wrapped in Some
        assert_eq!(active.headers.unwrap(), Some(result.headers.clone()));
        assert_eq!(active.meta_data.unwrap(), Some(result.meta_data.clone()));
    }

    #[test]
    fn test_to_active_model_with_none_screenshot() {
        if crate::common::test_helpers::skip_if_no_test_db() {
            return;
        }
        let mut result = sample_scrape_result();
        result.screenshot = None;
        let active = ScrapeResultRepositoryImpl::to_active_model(&result);
        assert_eq!(active.screenshot.unwrap(), None);
    }

    #[test]
    fn test_to_domain_converts_all_fields() {
        if crate::common::test_helpers::skip_if_no_test_db() {
            return;
        }
        let model = sample_db_model();
        let domain = ScrapeResultRepositoryImpl::to_domain(model.clone());

        assert_eq!(domain.id, model.id);
        assert_eq!(domain.task_id, model.task_id);
        assert_eq!(domain.url, model.url);
        assert_eq!(domain.status_code, model.status_code);
        assert_eq!(domain.content, model.content);
        assert_eq!(domain.content_type, model.content_type);
        assert_eq!(domain.response_time_ms, model.response_time_ms);
        assert_eq!(domain.screenshot, model.screenshot);
        // headers/meta_data unwrapped from Option
        assert_eq!(domain.headers, model.headers.unwrap());
        assert_eq!(domain.meta_data, model.meta_data.unwrap());
    }

    #[test]
    fn test_to_domain_with_null_headers_uses_default_object() {
        if crate::common::test_helpers::skip_if_no_test_db() {
            return;
        }
        let mut model = sample_db_model();
        model.headers = None;
        let domain = ScrapeResultRepositoryImpl::to_domain(model);
        assert_eq!(domain.headers, serde_json::json!({}));
    }

    #[test]
    fn test_to_domain_with_null_meta_data_uses_default_object() {
        if crate::common::test_helpers::skip_if_no_test_db() {
            return;
        }
        let mut model = sample_db_model();
        model.meta_data = None;
        let domain = ScrapeResultRepositoryImpl::to_domain(model);
        assert_eq!(domain.meta_data, serde_json::json!({}));
    }

    #[test]
    fn test_to_domain_roundtrip_preserves_core_fields() {
        if crate::common::test_helpers::skip_if_no_test_db() {
            return;
        }
        let original = sample_scrape_result();
        let active = ScrapeResultRepositoryImpl::to_active_model(&original);
        // Reconstruct a Model from the ActiveModel (all fields are Set)
        let model = db_entity::Model {
            id: active.id.unwrap(),
            task_id: active.task_id.unwrap(),
            url: active.url.unwrap(),
            status_code: active.status_code.unwrap(),
            content: active.content.unwrap(),
            content_type: active.content_type.unwrap(),
            response_time_ms: active.response_time_ms.unwrap(),
            created_at: active.created_at.unwrap(),
            headers: active.headers.unwrap(),
            meta_data: active.meta_data.unwrap(),
            screenshot: active.screenshot.unwrap(),
        };
        let roundtrip = ScrapeResultRepositoryImpl::to_domain(model);
        assert_eq!(roundtrip.id, original.id);
        assert_eq!(roundtrip.url, original.url);
        assert_eq!(roundtrip.content, original.content);
        assert_eq!(roundtrip.headers, original.headers);
        assert_eq!(roundtrip.meta_data, original.meta_data);
    }

    // CRUD against real DB

    #[tokio::test]
    async fn test_save_creates_record() {
        if crate::common::test_helpers::skip_if_no_test_db() {
            return;
        }
        let repo = ScrapeResultRepositoryImpl::new(create_test_db_pool());
        let mut result = sample_scrape_result();
        result.id = crate::domain::id::Id::generate();
        result.task_id = crate::domain::id::Id::generate();
        let saved = repo.save(result.clone()).await;
        assert!(saved.is_ok(), "save failed: {:?}", saved.err());

        // Verify DB state: find_by_task_id should return the created record
        let found = repo
            .find_by_task_id(result.task_id)
            .await
            .expect("find_by_task_id failed")
            .expect("record should exist after save");
        assert_eq!(found.id, result.id);
        assert_eq!(found.task_id, result.task_id);
        assert_eq!(found.url, result.url);
        assert_eq!(found.status_code, result.status_code);
        assert_eq!(found.content, result.content);
        assert_eq!(found.content_type, result.content_type);
        assert_eq!(found.response_time_ms, result.response_time_ms);
    }

    #[tokio::test]
    async fn test_find_by_task_id_returns_none_for_unknown() {
        if crate::common::test_helpers::skip_if_no_test_db() {
            return;
        }
        let repo = ScrapeResultRepositoryImpl::new(create_test_db_pool());
        let result = repo
            .find_by_task_id(crate::domain::id::Id::generate())
            .await;
        assert!(result.is_ok(), "find_by_task_id failed: {:?}", result.err());
        assert!(
            result.unwrap().is_none(),
            "unknown task_id should return None"
        );
    }

    #[tokio::test]
    async fn test_find_by_task_ids_returns_empty_for_unknown() {
        if crate::common::test_helpers::skip_if_no_test_db() {
            return;
        }
        let repo = ScrapeResultRepositoryImpl::new(create_test_db_pool());
        let result = repo
            .find_by_task_ids(&[
                crate::domain::id::Id::generate(),
                crate::domain::id::Id::generate(),
            ])
            .await;
        assert!(
            result.is_ok(),
            "find_by_task_ids failed: {:?}",
            result.err()
        );
        assert!(
            result.unwrap().is_empty(),
            "unknown task_ids should return empty vec"
        );
    }

    // fast-path (no DB access)

    #[tokio::test]
    async fn test_find_by_task_ids_with_empty_slice_returns_empty_vec() {
        if crate::common::test_helpers::skip_if_no_test_db() {
            return;
        }
        let repo = ScrapeResultRepositoryImpl::new(create_test_db_pool());
        let result = repo.find_by_task_ids(&[]).await;
        assert!(
            result.is_ok(),
            "empty slice should short-circuit without DB"
        );
        assert!(result.unwrap().is_empty());
    }

    #[tokio::test]
    async fn test_get_team_avg_response_time_returns_zero_for_unknown_team() {
        if crate::common::test_helpers::skip_if_no_test_db() {
            return;
        }
        // Unknown team_id → JOIN yields no rows → COALESCE returns 0.0.
        let repo = ScrapeResultRepositoryImpl::new(create_test_db_pool());
        let result = repo
            .get_team_avg_response_time(crate::domain::id::Id::generate())
            .await;
        assert!(
            result.is_ok(),
            "get_team_avg_response_time failed: {:?}",
            result.err()
        );
        assert_eq!(result.unwrap(), 0.0);
    }

    // additional boundary variants

    #[tokio::test]
    async fn test_find_by_task_ids_with_single_id_returns_empty_for_unknown() {
        if crate::common::test_helpers::skip_if_no_test_db() {
            return;
        }
        let repo = ScrapeResultRepositoryImpl::new(create_test_db_pool());
        let result = repo
            .find_by_task_ids(&[crate::domain::id::Id::generate()])
            .await;
        assert!(
            result.is_ok(),
            "find_by_task_ids failed: {:?}",
            result.err()
        );
        assert!(
            result.unwrap().is_empty(),
            "unknown single id should return empty vec"
        );
    }

    #[tokio::test]
    async fn test_find_by_task_ids_with_many_ids_returns_empty_for_unknown() {
        if crate::common::test_helpers::skip_if_no_test_db() {
            return;
        }
        let repo = ScrapeResultRepositoryImpl::new(create_test_db_pool());
        let ids: Vec<crate::domain::id::Id> = (0..100)
            .map(|_| crate::domain::id::Id::generate())
            .collect();
        let result = repo.find_by_task_ids(&ids).await;
        assert!(
            result.is_ok(),
            "find_by_task_ids failed: {:?}",
            result.err()
        );
        assert!(
            result.unwrap().is_empty(),
            "unknown ids should return empty vec"
        );
    }

    #[tokio::test]
    async fn test_find_by_task_id_with_nil_uuid_returns_none() {
        if crate::common::test_helpers::skip_if_no_test_db() {
            return;
        }
        let repo = ScrapeResultRepositoryImpl::new(create_test_db_pool());
        // Use a fresh random UUID instead of crate::domain::id::Id::nil to avoid cross-test
        // data pollution (other tests may insert records with nil task_id).
        let result = repo
            .find_by_task_id(crate::domain::id::Id::generate())
            .await;
        assert!(result.is_ok(), "find_by_task_id failed: {:?}", result.err());
        assert!(
            result.unwrap().is_none(),
            "unknown task_id should return None"
        );
    }

    #[tokio::test]
    async fn test_save_with_nil_task_id_succeeds() {
        if crate::common::test_helpers::skip_if_no_test_db() {
            return;
        }
        let repo = ScrapeResultRepositoryImpl::new(create_test_db_pool());
        let mut result = sample_scrape_result();
        result.id = crate::domain::id::Id::generate();
        result.task_id = crate::domain::id::Id::nil();
        let res = repo.save(result).await;
        assert!(res.is_ok(), "save with nil task_id failed: {:?}", res.err());
    }

    #[tokio::test]
    async fn test_get_team_avg_response_time_with_nil_uuid_returns_zero() {
        if crate::common::test_helpers::skip_if_no_test_db() {
            return;
        }
        // nil UUID as team_id: no tasks carry team_id=Nil, so JOIN yields 0 rows.
        let repo = ScrapeResultRepositoryImpl::new(create_test_db_pool());
        let result = repo
            .get_team_avg_response_time(crate::domain::id::Id::nil())
            .await;
        assert!(result.is_ok());
        assert_eq!(result.unwrap(), 0.0);
    }

    // list_distinct_urls(F3 seen 预热 keyset 分页)

    /// 保存一批结果并返回其 URL 列表
    async fn save_results_with_urls(repo: &ScrapeResultRepositoryImpl, urls: &[&str]) {
        for url in urls {
            let mut result = sample_scrape_result();
            result.id = crate::domain::id::Id::generate();
            result.task_id = crate::domain::id::Id::generate();
            result.url = url.to_string();
            repo.save(result).await.expect("save failed");
        }
    }

    #[tokio::test]
    async fn test_list_distinct_urls_returns_distinct_sorted() {
        if crate::common::test_helpers::skip_if_no_test_db() {
            return;
        }
        let repo = ScrapeResultRepositoryImpl::new(create_test_db_pool());
        let prefix = format!(
            "https://listdistinct-{}.example.com",
            crate::domain::id::Id::generate()
        );
        let a = format!("{prefix}/a");
        let b = format!("{prefix}/b");
        // 同 URL 两行 → distinct 只出一个
        save_results_with_urls(&repo, &[&b, &a, &b]).await;

        // keyset 起点设在本次前缀之后:共享测试库累积的 URL 不会挤占前 100 条。
        let urls = repo
            .list_distinct_urls(100, Some(prefix.clone()))
            .await
            .expect("list_distinct_urls failed");
        let own: Vec<String> = urls
            .into_iter()
            .filter(|u| u.starts_with(&prefix))
            .collect();
        assert_eq!(own, vec![a, b], "distinct + url 升序");
    }

    #[tokio::test]
    async fn test_list_distinct_urls_keyset_strictly_greater_than_after() {
        if crate::common::test_helpers::skip_if_no_test_db() {
            return;
        }
        let repo = ScrapeResultRepositoryImpl::new(create_test_db_pool());
        let prefix = format!(
            "https://keyset-{}.example.com",
            crate::domain::id::Id::generate()
        );
        let a = format!("{prefix}/a");
        let b = format!("{prefix}/b");
        let c = format!("{prefix}/c");
        save_results_with_urls(&repo, &[&a, &b, &c]).await;

        // after_url = b → 只返回严格大于 b 的记录(c),不含 b 本身
        let urls = repo
            .list_distinct_urls(100, Some(b.clone()))
            .await
            .expect("keyset page failed");
        let own: Vec<String> = urls
            .into_iter()
            .filter(|u| u.starts_with(&prefix))
            .collect();
        assert_eq!(own, vec![c], "after_url 语义必须为严格大于");

        // limit 截断生效
        let urls = repo
            .list_distinct_urls(1, None)
            .await
            .expect("limit page failed");
        assert_eq!(urls.len(), 1, "limit=1 必须只返回一页一条");
    }

    // cleanup_expired

    #[tokio::test]
    async fn test_cleanup_expired_disabled_returns_zero() {
        if crate::common::test_helpers::skip_if_no_test_db() {
            return;
        }
        let repo = ScrapeResultRepositoryImpl::new(create_test_db_pool());
        // retention_days = 0 表示禁用清理:直接返回 0,不产生任何删除
        let result = repo.cleanup_expired(0).await;
        assert!(
            result.is_ok(),
            "cleanup_expired(0) failed: {:?}",
            result.err()
        );
        assert_eq!(result.unwrap(), 0);

        let result = repo.cleanup_expired(-5).await;
        assert!(
            result.is_ok(),
            "cleanup_expired(-5) failed: {:?}",
            result.err()
        );
        assert_eq!(result.unwrap(), 0);
    }

    #[tokio::test]
    async fn test_cleanup_expired_with_overflow_days_returns_error() {
        if crate::common::test_helpers::skip_if_no_test_db() {
            return;
        }
        let repo = ScrapeResultRepositoryImpl::new(create_test_db_pool());
        // i64::MAX 天超出 chrono TimeDelta 范围,应返回错误而非 panic
        let result = repo.cleanup_expired(i64::MAX).await;
        assert!(
            result.is_err(),
            "overflow retention_days should be an error"
        );
    }

    #[tokio::test]
    async fn test_cleanup_expired_deletes_only_ancient_rows() {
        if crate::common::test_helpers::skip_if_no_test_db() {
            return;
        }
        let repo = ScrapeResultRepositoryImpl::new(create_test_db_pool());

        // 远古行(1970 年):比 cutoff(now - 20_000 天 ≈ 1971 年)更旧,必被删除
        let mut ancient = sample_scrape_result();
        ancient.id = crate::domain::id::Id::generate();
        ancient.task_id = crate::domain::id::Id::generate();
        ancient.created_at = chrono::DateTime::from_timestamp(1_000, 0).expect("valid timestamp");
        repo.save(ancient.clone())
            .await
            .expect("save ancient failed");

        // 保留期内的行(2023 年):比 cutoff 新,必须存活
        let mut recent = sample_scrape_result();
        recent.id = crate::domain::id::Id::generate();
        recent.task_id = crate::domain::id::Id::generate();
        repo.save(recent.clone()).await.expect("save recent failed");

        let deleted = repo.cleanup_expired(20_000).await.expect("cleanup failed");
        assert!(deleted >= 1, "at least the ancient row should be deleted");

        let ancient_gone = repo
            .find_by_task_id(ancient.task_id)
            .await
            .expect("find ancient failed");
        assert!(ancient_gone.is_none(), "ancient row must be deleted");

        let recent_alive = repo
            .find_by_task_id(recent.task_id)
            .await
            .expect("find recent failed");
        assert!(recent_alive.is_some(), "recent row must survive cleanup");
    }

    // to_active_model / to_domain additional boundaries

    #[test]
    fn test_to_active_model_with_empty_content() {
        if crate::common::test_helpers::skip_if_no_test_db() {
            return;
        }
        let mut result = sample_scrape_result();
        result.content = "".to_string();
        let active = ScrapeResultRepositoryImpl::to_active_model(&result);
        assert_eq!(active.content.unwrap(), "");
    }

    #[test]
    fn test_to_active_model_with_empty_url() {
        if crate::common::test_helpers::skip_if_no_test_db() {
            return;
        }
        let mut result = sample_scrape_result();
        result.url = "".to_string();
        let active = ScrapeResultRepositoryImpl::to_active_model(&result);
        assert_eq!(active.url.unwrap(), "");
    }

    #[test]
    fn test_to_active_model_with_zero_status_code() {
        if crate::common::test_helpers::skip_if_no_test_db() {
            return;
        }
        let mut result = sample_scrape_result();
        result.status_code = 0;
        let active = ScrapeResultRepositoryImpl::to_active_model(&result);
        assert_eq!(active.status_code.unwrap(), 0);
    }

    #[test]
    fn test_to_active_model_with_large_status_code() {
        if crate::common::test_helpers::skip_if_no_test_db() {
            return;
        }
        let mut result = sample_scrape_result();
        result.status_code = 599;
        let active = ScrapeResultRepositoryImpl::to_active_model(&result);
        assert_eq!(active.status_code.unwrap(), 599);
    }

    #[test]
    fn test_to_active_model_with_zero_response_time() {
        if crate::common::test_helpers::skip_if_no_test_db() {
            return;
        }
        let mut result = sample_scrape_result();
        result.response_time_ms = 0;
        let active = ScrapeResultRepositoryImpl::to_active_model(&result);
        assert_eq!(active.response_time_ms.unwrap(), 0);
    }

    #[test]
    fn test_to_active_model_with_empty_headers_and_metadata() {
        if crate::common::test_helpers::skip_if_no_test_db() {
            return;
        }
        let mut result = sample_scrape_result();
        result.headers = serde_json::json!({});
        result.meta_data = serde_json::json!({});
        let active = ScrapeResultRepositoryImpl::to_active_model(&result);
        // headers/meta_data are wrapped in Some
        assert_eq!(active.headers.unwrap(), Some(serde_json::json!({})));
        assert_eq!(active.meta_data.unwrap(), Some(serde_json::json!({})));
    }

    #[test]
    fn test_to_active_model_with_complex_headers() {
        if crate::common::test_helpers::skip_if_no_test_db() {
            return;
        }
        let mut result = sample_scrape_result();
        result.headers = serde_json::json!({
            "content-type": "application/json",
            "x-custom-header": "value-with-unicode-🔑",
            "x-numbers": [1, 2, 3],
            "x-nested": {"key": "value"}
        });
        let active = ScrapeResultRepositoryImpl::to_active_model(&result);
        let headers = active.headers.unwrap().unwrap();
        assert_eq!(headers["content-type"], "application/json");
        assert_eq!(headers["x-custom-header"], "value-with-unicode-🔑");
        assert_eq!(headers["x-numbers"][2], 3);
        assert_eq!(headers["x-nested"]["key"], "value");
    }

    #[test]
    fn test_to_domain_with_zero_response_time() {
        if crate::common::test_helpers::skip_if_no_test_db() {
            return;
        }
        let mut model = sample_db_model();
        model.response_time_ms = 0;
        let domain = ScrapeResultRepositoryImpl::to_domain(model);
        assert_eq!(domain.response_time_ms, 0);
    }

    #[test]
    fn test_to_domain_with_empty_strings() {
        if crate::common::test_helpers::skip_if_no_test_db() {
            return;
        }
        let mut model = sample_db_model();
        model.url = "".to_string();
        model.content = "".to_string();
        model.content_type = "".to_string();
        let domain = ScrapeResultRepositoryImpl::to_domain(model);
        assert_eq!(domain.url, "");
        assert_eq!(domain.content, "");
        assert_eq!(domain.content_type, "");
    }

    #[test]
    fn test_to_domain_with_both_headers_and_metadata_null() {
        if crate::common::test_helpers::skip_if_no_test_db() {
            return;
        }
        let mut model = sample_db_model();
        model.headers = None;
        model.meta_data = None;
        let domain = ScrapeResultRepositoryImpl::to_domain(model);
        // Both should default to empty JSON objects
        assert_eq!(domain.headers, serde_json::json!({}));
        assert_eq!(domain.meta_data, serde_json::json!({}));
    }

    #[test]
    fn test_to_domain_with_screenshot_present() {
        if crate::common::test_helpers::skip_if_no_test_db() {
            return;
        }
        let mut model = sample_db_model();
        model.screenshot = Some("base64data".to_string());
        let domain = ScrapeResultRepositoryImpl::to_domain(model);
        assert_eq!(domain.screenshot, Some("base64data".to_string()));
    }

    // sample_scrape_result boundary verification

    #[test]
    fn test_sample_scrape_result_construction_values() {
        if crate::common::test_helpers::skip_if_no_test_db() {
            return;
        }
        let result = sample_scrape_result();
        assert_eq!(result.status_code, 200);
        assert_eq!(result.content_type, "text/html");
        assert_eq!(result.response_time_ms, 150);
        assert!(result.screenshot.is_some());
        assert_eq!(result.screenshot.as_ref().unwrap(), "base64screenshot");
        assert_eq!(result.url, "https://example.com/page");
    }

    #[test]
    fn test_sample_db_model_construction_values() {
        if crate::common::test_helpers::skip_if_no_test_db() {
            return;
        }
        let model = sample_db_model();
        assert_eq!(model.status_code, 404);
        assert_eq!(model.content_type, "text/plain");
        assert_eq!(model.response_time_ms, 42);
        assert!(model.screenshot.is_none());
        assert!(model.headers.is_some());
        assert!(model.meta_data.is_some());
    }
}