data_bucket 0.5.6

DataBucket is container for WorkTable's data
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
use eyre::eyre;
use rkyv::api::high::HighDeserializer;
use rkyv::Archive;
use std::io::SeekFrom;
use tokio::fs::File;
use tokio::io::{AsyncReadExt, AsyncSeekExt, AsyncWriteExt};

use super::SpaceInfoPage;
use crate::page::header::GeneralHeader;
use crate::page::ty::PageType;
use crate::page::PageId;
use crate::{
    DataPage, GeneralPage, Link, Persistable, GENERAL_HEADER_SIZE, INNER_PAGE_SIZE, PAGE_SIZE,
};

/// Returned when a write into a page would not fit the page slot: letting
/// it through would spill past a [`PAGE_SIZE`] boundary and corrupt a
/// neighboring page (or, for tail-first writes, this page's own header).
#[derive(Debug)]
pub struct PageOverflowError {
    /// The page whose write is over budget.
    pub page_id: PageId,
    /// Inner-page bytes the write needs (for slot writes, where the write
    /// would end within the slot).
    pub data_length: usize,
    /// The slot budget for inner data ([`INNER_PAGE_SIZE`]).
    pub capacity: usize,
}

impl std::fmt::Display for PageOverflowError {
    fn fmt(&self, f: &mut std::fmt::Formatter<'_>) -> std::fmt::Result {
        write!(
            f,
            "page {} write needs {} bytes, exceeding the {}-byte page slot",
            self.page_id, self.data_length, self.capacity
        )
    }
}

impl std::error::Error for PageOverflowError {}

pub fn map_data_pages_to_general<const DATA_LENGTH: usize>(
    pages: Vec<DataPage<DATA_LENGTH>>,
) -> Vec<GeneralPage<DataPage<DATA_LENGTH>>> {
    // We are starting ID's from `1` because `0`'s page in file is info page.
    let header = &mut GeneralHeader::new(1.into(), PageType::Data, 0.into());
    let mut general_pages = vec![];

    let mut pages = pages.into_iter();
    if let Some(p) = pages.next() {
        let general = GeneralPage {
            header: *header,
            inner: p,
        };
        general_pages.push(general);
    }
    let mut previous_header = header;

    for p in pages {
        let general = GeneralPage {
            header: previous_header.follow_with(PageType::Data),
            inner: p,
        };

        general_pages.push(general);
        previous_header = &mut general_pages.last_mut().unwrap().header;
    }

    general_pages
}

pub async fn persist_page<'a, T>(
    page: &'a mut GeneralPage<T>,
    file: &'a mut File,
) -> eyre::Result<()>
where
    T: Persistable + Send + Sync,
{
    seek_to_page_start(file, page.header.page_id.0).await?;

    let page_count = page.header.page_id.0 as i64 + 1;
    persist_page_in_place(page, file).await?;
    let curr_position = file.stream_position().await?;
    file.seek(SeekFrom::Current(
        (page_count * PAGE_SIZE as i64) - curr_position as i64,
    ))
    .await?;

    Ok(())
}

async fn persist_page_in_place<'a, T>(
    page: &'a mut GeneralPage<T>,
    file: &'a mut File,
) -> eyre::Result<()>
where
    T: Persistable + Send + Sync,
{
    let inner_bytes = page.inner.as_bytes();
    let inner_length = inner_bytes.as_ref().len();
    // An over-budget page must fail here, in its own persist, instead of
    // silently corrupting the neighboring page.
    if inner_length > INNER_PAGE_SIZE {
        return Err(eyre::Report::new(PageOverflowError {
            page_id: page.header.page_id,
            data_length: inner_length,
            capacity: INNER_PAGE_SIZE,
        }));
    }
    page.header.data_length = inner_length as u32;
    file.write_all(page.header.as_bytes().as_ref()).await?;
    file.write_all(inner_bytes.as_ref()).await?;
    Ok(())
}

pub async fn persist_pages_batch<T>(pages: Vec<GeneralPage<T>>, file: &mut File) -> eyre::Result<()>
where
    T: Persistable + Send + Sync,
{
    let mut iter = pages.into_iter();
    if let Some(mut page) = iter.next() {
        seek_to_page_start(file, page.header.page_id.0).await?;
        persist_page_in_place(&mut page, file).await?;

        for mut page in iter {
            seek_to_page_start_relatively(file, page.header.page_id.0).await?;
            persist_page_in_place(&mut page, file).await?;
        }

        Ok(())
    } else {
        Ok(())
    }
}

/// Byte offset of the page with the given index, computed in `u64`.
///
/// The arithmetic must never be done in `u32`: with the default 16 KiB
/// [`PAGE_SIZE`], any index past 262 143 puts the page start beyond 4 GiB,
/// and a `u32` multiply silently wraps the offset back into the start of
/// the file.
pub(crate) fn page_start_offset(index: u32) -> u64 {
    index as u64 * PAGE_SIZE as u64
}

pub async fn seek_to_page_start(file: &mut File, index: u32) -> eyre::Result<()> {
    file.seek(SeekFrom::Start(page_start_offset(index))).await?;
    Ok(())
}

async fn seek_to_page_start_relatively(file: &mut File, index: u32) -> eyre::Result<()> {
    let curr_position = file.stream_position().await?;
    file.seek(SeekFrom::Current(
        page_start_offset(index) as i64 - curr_position as i64,
    ))
    .await?;
    Ok(())
}

pub async fn seek_by_link(file: &mut File, link: Link) -> eyre::Result<()> {
    file.seek(SeekFrom::Start(
        link.page_id.0 as u64 * PAGE_SIZE as u64 + GENERAL_HEADER_SIZE as u64 + link.offset as u64,
    ))
    .await?;

    Ok(())
}

pub async fn update_at<const DATA_LENGTH: u32>(
    file: &mut File,
    link: Link,
    new_data: &[u8],
) -> eyre::Result<()> {
    if new_data.len() as u32 != link.length {
        return Err(eyre!(
            "New data length {} does not match link length {}",
            new_data.len(),
            link.length
        ));
    }

    // Sum in u64: `offset + length` in u32 can wrap past 4 GiB and slip
    // under the bound, letting the write land outside the page.
    if link.offset as u64 + link.length as u64 > DATA_LENGTH as u64 {
        return Err(eyre!(
            "Link range (offset: {}, length: {}) exceeds data bounds ({})",
            link.offset,
            link.length,
            DATA_LENGTH
        ));
    }

    seek_by_link(file, link).await?;
    file.write_all(new_data).await?;
    Ok(())
}

pub async fn parse_general_header(file: &mut File) -> eyre::Result<GeneralHeader> {
    let mut buffer = [0; GENERAL_HEADER_SIZE];
    file.read_exact(&mut buffer).await?;
    // Validated: a header torn by a mid-write death must surface as an error
    // naming the page, not as undefined behavior in whatever reads it next.
    let archived = crate::access_archived::<<GeneralHeader as Archive>::Archived>(&buffer[..])
        .map_err(|error| eyre::eyre!("torn or corrupt page header: {error}"))?;
    let header = rkyv::deserialize::<_, rkyv::rancor::Error>(archived)
        .map_err(|error| eyre::eyre!("page header failed to deserialize: {error}"))?;

    Ok(header)
}

pub async fn parse_page<Page, const INNER_PAGE_SIZE: u32>(
    file: &mut File,
    index: u32,
) -> eyre::Result<GeneralPage<Page>>
where
    Page: rkyv::Archive + Persistable,
    <Page as rkyv::Archive>::Archived:
        rkyv::Deserialize<Page, HighDeserializer<rkyv::rancor::Error>>,
{
    seek_to_page_start(file, index).await?;
    parse_page_in_place::<Page, INNER_PAGE_SIZE>(file).await
}

async fn parse_page_in_place<Page, const INNER_PAGE_SIZE: u32>(
    file: &mut File,
) -> eyre::Result<GeneralPage<Page>>
where
    Page: rkyv::Archive + Persistable,
    <Page as rkyv::Archive>::Archived:
        rkyv::Deserialize<Page, HighDeserializer<rkyv::rancor::Error>>,
{
    let header = parse_general_header(file).await?;
    let length = if header.data_length == 0 {
        INNER_PAGE_SIZE
    } else {
        header.data_length
    };

    let mut buffer: Vec<u8> = vec![0u8; length as usize];
    file.read_exact(&mut buffer).await?;
    let info = Page::from_bytes(buffer.as_ref(), header.data_version);

    Ok(GeneralPage {
        header,
        inner: info,
    })
}

pub async fn parse_pages_batch<Page, const PAGE_SIZE: u32>(
    file: &mut File,
    indexes: Vec<u32>,
) -> eyre::Result<Vec<GeneralPage<Page>>>
where
    Page: rkyv::Archive + Persistable,
    <Page as rkyv::Archive>::Archived:
        rkyv::Deserialize<Page, HighDeserializer<rkyv::rancor::Error>>,
{
    let mut iter = indexes.into_iter();
    if let Some(index) = iter.next() {
        let mut pages = vec![];
        seek_to_page_start(file, index).await?;
        let page = parse_page_in_place::<Page, PAGE_SIZE>(file).await?;
        pages.push(page);

        for index in iter {
            seek_to_page_start_relatively(file, index).await?;
            let page = parse_page_in_place::<Page, PAGE_SIZE>(file).await?;
            pages.push(page);
        }

        Ok(pages)
    } else {
        Ok(vec![])
    }
}

pub async fn parse_general_header_by_index(
    file: &mut File,
    index: u32,
) -> eyre::Result<GeneralHeader> {
    seek_to_page_start(file, index).await?;
    let header = parse_general_header(file).await?;

    Ok(header)
}

pub async fn parse_data_page<const PAGE_SIZE: u32, const INNER_PAGE_SIZE: usize>(
    file: &mut File,
    index: u32,
) -> eyre::Result<GeneralPage<DataPage<INNER_PAGE_SIZE>>> {
    seek_to_page_start(file, index).await?;
    parse_data_page_in_place::<PAGE_SIZE, INNER_PAGE_SIZE>(file).await
}

async fn parse_data_page_in_place<const PAGE_SIZE: u32, const INNER_PAGE_SIZE: usize>(
    file: &mut File,
) -> eyre::Result<GeneralPage<DataPage<INNER_PAGE_SIZE>>> {
    let header = parse_general_header(file).await?;

    let mut buffer = [0u8; INNER_PAGE_SIZE];
    if header.next_id == 0.into() {
        #[allow(clippy::unused_io_amount)]
        file.read(&mut buffer).await?;
    } else {
        file.read_exact(&mut buffer).await?;
    }

    let data = DataPage {
        data: buffer,
        length: header.data_length,
    };

    Ok(GeneralPage {
        header,
        inner: data,
    })
}

pub async fn parse_data_pages_batch<const PAGE_SIZE: u32, const INNER_PAGE_SIZE: usize>(
    file: &mut File,
    indexes: Vec<u32>,
) -> eyre::Result<Vec<GeneralPage<DataPage<INNER_PAGE_SIZE>>>> {
    let mut iter = indexes.into_iter();
    if let Some(index) = iter.next() {
        let mut pages = vec![];
        seek_to_page_start(file, index).await?;
        let page = parse_data_page_in_place::<PAGE_SIZE, INNER_PAGE_SIZE>(file).await?;
        pages.push(page);

        for index in iter {
            seek_to_page_start_relatively(file, index).await?;
            let page = parse_data_page_in_place::<PAGE_SIZE, INNER_PAGE_SIZE>(file).await?;
            pages.push(page);
        }

        Ok(pages)
    } else {
        Ok(vec![])
    }
}

// pub fn parse_data_record<const PAGE_SIZE: usize>(
//     file: &mut std::fs::File,
//     index: u32,
//     offset: u32,
//     length: u32,
//     schema: &Vec<(String, String)>,
// ) -> eyre::Result<Vec<DataTypeValue>> {
//     seek_to_page_start(file, index)?;
//     let header = parse_general_header(file)?;
//     if header.page_type != PageType::Data {
//         return Err(eyre::Report::msg(format!(
//             "The type of the page with index {} is not `Data`",
//             index
//         )));
//     }
//     file.seek(io::SeekFrom::Current(offset as i64))?;
//     let mut buffer = vec![0u8; length as usize];
//     file.read_exact(&mut buffer)?;
//
//     let parsed_record = parse_archived_row(&buffer, &schema);
//
//     Ok(parsed_record)
// }

pub async fn parse_space_info<const PAGE_SIZE: usize>(
    file: &mut File,
) -> eyre::Result<SpaceInfoPage> {
    file.seek(SeekFrom::Start(0)).await?;
    let header = parse_general_header(file).await?;

    let mut buffer = vec![0u8; header.data_length as usize];
    file.read_exact(&mut buffer).await?;

    Ok(SpaceInfoPage::from_bytes(&buffer, header.data_version))
}

// pub fn read_index_pages<T, const PAGE_SIZE: usize>(
//     file: &mut std::fs::File,
//     length: u32,
// ) -> eyre::Result<Vec<IndexValue<T>>>
// where
//     T: Archive,
//     <T as rkyv::Archive>::Archived: rkyv::Deserialize<T, HighDeserializer<rkyv::rancor::Error>>,
// {
//     let mut result: Vec<IndexValue<T>> = vec![];
//     for index in 0..length {
//         let mut index_records = parse_index_page::<T, PAGE_SIZE>(file, index)?;
//         result.append(&mut index_records);
//     }
//     Ok(result)
// }
//
// fn read_links<DataType, const PAGE_SIZE: usize>(
//     mut file: &mut std::fs::File,
//     space_info: &SpaceInfo,
// ) -> eyre::Result<Vec<Link>> {
//     Ok(
//         read_index_pages::<i32, PAGE_SIZE>(&mut file, space_info.primary_key_length)?
//             .iter()
//             .map(|index_value| index_value.link)
//             .collect::<Vec<Link>>(),
//     )
// }
//
// pub fn read_rows_schema<const PAGE_SIZE: usize>(
//     file: &mut std::fs::File,
// ) -> eyre::Result<Vec<(String, String)>> {
//     let space_info = parse_space_info::<PAGE_SIZE>(file)?;
//     Ok(space_info.row_schema)
// }
//
// pub fn read_data_pages<const PAGE_SIZE: usize>(
//     mut file: &mut std::fs::File,
// ) -> eyre::Result<Vec<Vec<DataTypeValue>>> {
//     let space_info = parse_space_info::<PAGE_SIZE>(file)?;
//     let primary_key_fields = &space_info.primary_key_fields;
//     if primary_key_fields.len() != 1 {
//         panic!("Currently only single primary key is supported");
//     }
//
//     let primary_key_type = space_info
//         .row_schema
//         .iter()
//         .filter(|(field_name, _)| field_name == &primary_key_fields[0])
//         .map(|(_, field_type)| field_type)
//         .take(1)
//         .collect::<Vec<&String>>()[0]
//         .as_str();
//     let links = match primary_key_type {
//         "String" => read_links::<String, PAGE_SIZE>(&mut file, &space_info)?,
//         "i128" => read_links::<i128, PAGE_SIZE>(&mut file, &space_info)?,
//         "i64" => read_links::<i64, PAGE_SIZE>(&mut file, &space_info)?,
//         "i32" => read_links::<i32, PAGE_SIZE>(&mut file, &space_info)?,
//         "i16" => read_links::<i16, PAGE_SIZE>(&mut file, &space_info)?,
//         "i8" => read_links::<i8, PAGE_SIZE>(&mut file, &space_info)?,
//         "u128" => read_links::<u128, PAGE_SIZE>(&mut file, &space_info)?,
//         "u64" => read_links::<u64, PAGE_SIZE>(&mut file, &space_info)?,
//         "u32" => read_links::<u32, PAGE_SIZE>(&mut file, &space_info)?,
//         "u16" => read_links::<u16, PAGE_SIZE>(&mut file, &space_info)?,
//         "u8" => read_links::<u8, PAGE_SIZE>(&mut file, &space_info)?,
//         "f64" => read_links::<f64, PAGE_SIZE>(&mut file, &space_info)?,
//         "f32" => read_links::<f32, PAGE_SIZE>(&mut file, &space_info)?,
//         _ => panic!("Unsupported primary key data type `{}`", primary_key_type),
//     };
//
//     let mut result: Vec<Vec<_>> = vec![];
//     for link in links {
//         let row = parse_data_record::<PAGE_SIZE>(
//             &mut file,
//             link.page_id.0,
//             link.offset,
//             link.length,
//             &space_info.row_schema,
//         )?;
//         result.push(row);
//     }
//
//     Ok(result)
// }

#[cfg(test)]
mod tests {
    use super::{page_start_offset, parse_data_pages_batch, persist_pages_batch};
    use crate::page::header::GeneralHeader;
    use crate::page::ty::PageType;
    use crate::{DataPage, GeneralPage, DATA_VERSION, INNER_PAGE_SIZE, PAGE_SIZE};

    /// First page index whose start offset no longer fits in `u32`.
    const FIRST_PAGE_PAST_4_GIB: u32 = (u32::MAX / PAGE_SIZE as u32) + 1;

    #[test]
    fn page_start_offset_is_computed_in_u64() {
        assert_eq!(
            page_start_offset(FIRST_PAGE_PAST_4_GIB),
            FIRST_PAGE_PAST_4_GIB as u64 * PAGE_SIZE as u64
        );
        assert!(page_start_offset(FIRST_PAGE_PAST_4_GIB) > u32::MAX as u64);
        // The largest possible page id must be addressable too.
        assert_eq!(
            page_start_offset(u32::MAX),
            u32::MAX as u64 * PAGE_SIZE as u64
        );
        // The old `u32` arithmetic wrapped this offset back into the first
        // pages of the file.
        assert_ne!(
            page_start_offset(FIRST_PAGE_PAST_4_GIB),
            FIRST_PAGE_PAST_4_GIB.wrapping_mul(PAGE_SIZE as u32) as u64
        );
    }

    fn data_page_with_marker(marker: &[u8]) -> DataPage<INNER_PAGE_SIZE> {
        let mut data = [0u8; INNER_PAGE_SIZE];
        data[..marker.len()].copy_from_slice(marker);
        DataPage {
            length: marker.len() as u32,
            data,
        }
    }

    #[tokio::test]
    async fn persist_page_rejects_inner_data_past_the_page_slot() {
        // A data page whose buffer is larger than the slot budget can hand
        // persist more bytes than fit between two page starts.
        const OVERSIZED: usize = crate::PAGE_SIZE + 128;

        let path = std::env::temp_dir().join(format!(
            "data_bucket_persist_overflow_{}.wt",
            std::process::id()
        ));
        let mut file = tokio::fs::OpenOptions::new()
            .read(true)
            .write(true)
            .create(true)
            .truncate(true)
            .open(&path)
            .await
            .unwrap();

        let mut page = GeneralPage {
            header: GeneralHeader {
                data_version: DATA_VERSION,
                space_id: 1.into(),
                page_id: 1.into(),
                previous_id: 0.into(),
                next_id: 0.into(),
                page_type: PageType::Data,
                data_length: 0,
            },
            inner: DataPage {
                length: OVERSIZED as u32,
                data: [7u8; OVERSIZED],
            },
        };

        let err = super::persist_page(&mut page, &mut file).await.unwrap_err();
        assert!(
            err.downcast_ref::<super::PageOverflowError>().is_some(),
            "expected PageOverflowError, got: {err}"
        );

        // Nothing may have been written: the neighboring page is the one an
        // unchecked write would have corrupted.
        assert_eq!(file.metadata().await.unwrap().len(), 0);

        // A page that fits its slot still persists.
        page.inner.length = 64;
        super::persist_page(&mut page, &mut file).await.unwrap();

        drop(file);
        std::fs::remove_file(&path).unwrap();
    }

    #[tokio::test]
    async fn update_at_rejects_offset_plus_length_wrapping_u32() {
        let path = std::env::temp_dir().join(format!(
            "data_bucket_update_at_wrap_{}.wt",
            std::process::id()
        ));
        let mut file = tokio::fs::OpenOptions::new()
            .read(true)
            .write(true)
            .create(true)
            .truncate(true)
            .open(&path)
            .await
            .unwrap();

        // In u32, offset + length wraps to 5 and used to pass the bounds
        // check, sending the write far outside the page.
        let link = crate::Link {
            page_id: 1.into(),
            offset: u32::MAX - 2,
            length: 8,
        };
        let err = super::update_at::<100>(&mut file, link, &[1, 2, 3, 4, 5, 6, 7, 8])
            .await
            .unwrap_err();
        assert!(err.to_string().contains("exceeds data bounds"));

        drop(file);
        std::fs::remove_file(&path).unwrap();
    }

    #[tokio::test]
    async fn batch_persist_and_parse_address_pages_past_4_gib() {
        const FIRST_MARKER: &[u8] = b"FIRSTPG!";
        const BOUNDARY_MARKER: &[u8] = b"BOUNDARY";

        let path = std::env::temp_dir().join(format!(
            "data_bucket_seek_past_4gib_{}.wt",
            std::process::id()
        ));
        let mut file = tokio::fs::OpenOptions::new()
            .read(true)
            .write(true)
            .create(true)
            .truncate(true)
            .open(&path)
            .await
            .unwrap();

        let first_page = GeneralPage {
            header: GeneralHeader {
                data_version: DATA_VERSION,
                space_id: 1.into(),
                page_id: 1.into(),
                previous_id: 0.into(),
                next_id: 2.into(),
                page_type: PageType::Data,
                data_length: 0,
            },
            inner: data_page_with_marker(FIRST_MARKER),
        };
        let boundary_page = GeneralPage {
            header: GeneralHeader {
                data_version: DATA_VERSION,
                space_id: 1.into(),
                page_id: FIRST_PAGE_PAST_4_GIB.into(),
                previous_id: 1.into(),
                next_id: 0.into(),
                page_type: PageType::Data,
                data_length: 0,
            },
            inner: data_page_with_marker(BOUNDARY_MARKER),
        };

        persist_pages_batch(vec![first_page, boundary_page], &mut file)
            .await
            .unwrap();

        // The boundary page must have been written past 4 GiB (the file is
        // sparse, so this stays cheap), not wrapped back onto the first pages.
        // tokio's File buffers writes; flush so metadata() sees them.
        tokio::io::AsyncWriteExt::flush(&mut file).await.unwrap();
        let file_length = file.metadata().await.unwrap().len();
        assert!(file_length > page_start_offset(FIRST_PAGE_PAST_4_GIB));

        let pages = parse_data_pages_batch::<{ PAGE_SIZE as u32 }, INNER_PAGE_SIZE>(
            &mut file,
            vec![1, FIRST_PAGE_PAST_4_GIB],
        )
        .await
        .unwrap();

        assert_eq!(pages.len(), 2);
        assert_eq!(pages[0].header.page_id, 1.into());
        assert_eq!(&pages[0].inner.data[..FIRST_MARKER.len()], FIRST_MARKER);
        assert_eq!(pages[1].header.page_id, FIRST_PAGE_PAST_4_GIB.into());
        assert_eq!(
            &pages[1].inner.data[..BOUNDARY_MARKER.len()],
            BOUNDARY_MARKER
        );

        drop(file);
        std::fs::remove_file(&path).unwrap();
    }
}

// #[cfg(test)]
// pub mod test {
//     use std::collections::HashMap;
//     use std::fs::remove_file;
//     use std::path::Path;
//
//     use rkyv::{Archive, Deserialize, Serialize};
//
//     use crate::page::index::IndexValue;
//     use crate::persistence::data::DataTypeValue;
//     use crate::{read_data_pages, GeneralHeader, GeneralPage, IndexData, Interval, Link, PageType, SpaceInfoData, DATA_VERSION, PAGE_SIZE};
//
//     use super::persist_page;
//
//     fn create_space_with_intervals(intervals: &Vec<Interval>) -> GeneralPage<SpaceInfoData> {
//         let space_info_header = GeneralHeader {
//             data_version: DATA_VERSION,
//             space_id: 1.into(),
//             page_id: 0.into(),
//             previous_id: 0.into(),
//             next_id: 1.into(),
//             page_type: PageType::SpaceInfo,
//             data_length: 0u32,
//         };
//         let space_info = SpaceInfoData {
//             id: 0.into(),
//             page_count: 0,
//             name: "Test".to_string(),
//             row_schema: vec![],
//             primary_key_fields: vec![],
//             primary_key_length: 1,
//             secondary_index_lengths: HashMap::from([(
//                 "string_index".to_owned(),
//                 1,
//             )]),
//             data_length: 1,
//             pk_gen_state: (),
//             empty_links_list: vec![],
//             secondary_index_types: vec![("string_index".to_string(), "String".to_string())],
//         };
//         let space_info_page = GeneralPage {
//             header: space_info_header,
//             inner: space_info,
//         };
//
//         space_info_page
//     }
//
//     fn create_index_pages(intervals: &Vec<Interval>) -> Vec<GeneralPage<IndexData<String>>> {
//         let mut index_pages = Vec::<GeneralPage<IndexData<String>>>::new();
//
//         for interval in intervals {
//             for index in interval.0..=interval.1 {
//                 let index_header = GeneralHeader {
//                     data_version: DATA_VERSION,
//                     space_id: 1.into(),
//                     page_id: (index as u32).into(),
//                     previous_id: (if index > 0 { index as u32 - 1 } else { 0 }).into(),
//                     next_id: (index as u32 + 1).into(),
//                     page_type: PageType::SpaceInfo,
//                     data_length: 0u32,
//                 };
//                 let index_data = IndexData {
//                     index_values: vec![IndexValue {
//                         key: "first_value".to_string(),
//                         link: Link {
//                             page_id: 2.into(),
//                             length: 0,
//                             offset: 0,
//                         },
//                     }],
//                 };
//                 let index_page = GeneralPage {
//                     header: index_header,
//                     inner: index_data,
//                 };
//                 index_pages.push(index_page);
//             }
//         }
//
//         index_pages
//     }
//
//     #[test]
//     fn test_read_index_pages() {
//         let filename = "tests/data/table.wt";
//         if Path::new(filename).exists() {
//             remove_file(filename).unwrap();
//         }
//         let mut file: std::fs::File = std::fs::File::create(filename).unwrap();
//
//         let intervals = vec![Interval(1, 2), Interval(5, 7)];
//
//         // create the space page
//         let mut space_info_page = create_space_with_intervals(&intervals);
//         persist_page(&mut space_info_page, &mut file).unwrap();
//
//         // create the index pages
//         for mut index_page in create_index_pages(&intervals) {
//             persist_page(&mut index_page, &mut file).unwrap();
//         }
//
//         // read the data
//         let mut file = std::fs::File::open(filename).unwrap();
//         let index_pages = read_secondary_index_pages::<String, PAGE_SIZE>(
//             &mut file,
//             "string_index",
//             vec![Interval(1, 2), Interval(5, 6)],
//         )
//         .unwrap();
//         assert_eq!(index_pages.len(), 4);
//         assert_eq!(index_pages[0].key, "first_value");
//         assert_eq!(index_pages[0].link.page_id, 2.into());
//         assert_eq!(index_pages[0].link.offset, 0);
//         assert_eq!(index_pages[0].link.length, 0);
//     }
//
//     #[derive(Archive, Debug, Deserialize, Serialize)]
//     struct TableStruct {
//         int1: i32,
//         string1: String,
//     }
//
//     pub fn create_test_database_file(filename: &str) {
//         if Path::new(filename).exists() {
//             remove_file(filename).unwrap();
//         }
//         let mut file: std::fs::File = std::fs::File::create(filename).unwrap();
//
//         let space_info_header = GeneralHeader {
//             data_version: DATA_VERSION,
//             space_id: 1.into(),
//             page_id: 0.into(),
//             previous_id: 0.into(),
//             next_id: 1.into(),
//             page_type: PageType::SpaceInfo,
//             data_length: 0u32,
//         };
//         let space_info = SpaceInfoData {
//             id: 1.into(),
//             page_count: 4,
//             name: "test space".to_owned(),
//             row_schema: vec![
//                 ("int1".to_string(), "i32".to_string()),
//                 ("string1".to_string(), "String".to_string()),
//             ],
//             primary_key_fields: vec!["int1".to_string()],
//             primary_key_intervals: vec![Interval(1, 1)],
//             secondary_index_types: vec![],
//             secondary_index_intervals: Default::default(),
//             data_intervals: vec![],
//             pk_gen_state: (),
//             empty_links_list: vec![],
//         };
//         let mut space_info_page = GeneralPage {
//             header: space_info_header,
//             inner: space_info,
//         };
//         persist_page(&mut space_info_page, &mut file).unwrap();
//
//         let index_header = GeneralHeader {
//             data_version: DATA_VERSION,
//             space_id: 1.into(),
//             page_id: 1.into(),
//             previous_id: 0.into(),
//             next_id: 2.into(),
//             page_type: PageType::Index,
//             data_length: 0,
//         };
//
//         let data_header = GeneralHeader {
//             data_version: DATA_VERSION,
//             space_id: 1.into(),
//             page_id: 2.into(),
//             previous_id: 2.into(),
//             next_id: 4.into(),
//             page_type: PageType::Data,
//             data_length: 0,
//         };
//
//         let data_row1 = TableStruct {
//             int1: 1,
//             string1: "first string".to_string(),
//         };
//
//         let data_row2 = TableStruct {
//             int1: 2,
//             string1: "second string".to_string(),
//         };
//
//         let data_row1_inner = rkyv::to_bytes::<rkyv::rancor::Error>(&data_row1).unwrap();
//         let data_row1_offset = 0;
//         let data_row1_length = data_row1_inner.len();
//
//         let data_row2_inner = rkyv::to_bytes::<rkyv::rancor::Error>(&data_row2).unwrap();
//         let data_row2_offset = data_row1_offset + data_row1_length;
//         let data_row2_length = data_row2_inner.len();
//
//         let data_rows12_buffer = [data_row1_inner, data_row2_inner].concat();
//
//         let mut data_page = GeneralPage::<Vec<u8>> {
//             header: data_header,
//             inner: data_rows12_buffer,
//         };
//
//         let index_data: IndexData<i32> = IndexData::<i32> {
//             index_values: vec![
//                 IndexValue::<i32> {
//                     key: 1,
//                     link: Link {
//                         page_id: data_header.page_id,
//                         offset: data_row1_offset as u32,
//                         length: data_row1_length as u32,
//                     },
//                 },
//                 IndexValue::<i32> {
//                     key: 2,
//                     link: Link {
//                         page_id: data_header.page_id,
//                         offset: data_row2_offset as u32,
//                         length: data_row2_length as u32,
//                     },
//                 },
//             ],
//         };
//         let mut index_page = GeneralPage {
//             header: index_header,
//             inner: index_data,
//         };
//
//         persist_page(&mut index_page, &mut file).unwrap();
//         persist_page(&mut data_page, &mut file).unwrap();
//     }
//
//     #[test]
//     fn test_read_table_data() {
//         let filename = "tests/data/table_with_rows.wt";
//         create_test_database_file(filename);
//
//         let mut file: std::fs::File = std::fs::File::open(filename).unwrap();
//         let data_pages: Vec<Vec<DataTypeValue>> = read_data_pages::<PAGE_SIZE>(&mut file).unwrap();
//         assert_eq!(data_pages[0][0], DataTypeValue::I32(1));
//         assert_eq!(
//             data_pages[0][1],
//             DataTypeValue::String("first string".to_string())
//         );
//         assert_eq!(data_pages[1][0], DataTypeValue::I32(2));
//         assert_eq!(
//             data_pages[1][1],
//             DataTypeValue::String("second string".to_string())
//         );
//     }
// }