aboutsummaryrefslogtreecommitdiffstats
path: root/rust/src/api_helpers.rs
blob: 5e68d8e2e345fdfa5fde5df877ced19cd10fb0b3 (plain)
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
use api_entity_crud::EntityCrud;
use data_encoding::BASE32_NOPAD;
use database_models::*;
use database_schema::*;
use diesel;
use diesel::prelude::*;
use errors::*;
use fatcat_api_spec::models::*;
use regex::Regex;
use serde_json;
use std::str::FromStr;
use uuid::Uuid;

pub type DbConn =
    diesel::r2d2::PooledConnection<diesel::r2d2::ConnectionManager<diesel::PgConnection>>;

pub struct EditContext {
    pub editor_id: FatCatId,
    pub editgroup_id: FatCatId,
    pub extra_json: Option<serde_json::Value>,
    pub autoaccept: bool,
}

impl EditContext {
    /// This function should always be run within a transaction
    pub fn check(&self, conn: &DbConn) -> Result<()> {
        let count: i64 = changelog::table
            .filter(changelog::editgroup_id.eq(&self.editgroup_id.to_uuid()))
            .count()
            .get_result(conn)?;
        if count > 0 {
            return Err(ErrorKind::EditgroupAlreadyAccepted(self.editgroup_id.to_string()).into());
        }
        return Ok(());
    }
}

#[derive(Clone, Copy, PartialEq)]
pub struct ExpandFlags {
    pub files: bool,
    pub filesets: bool,
    pub webcaptures: bool,
    pub container: bool,
    pub releases: bool,
    pub creators: bool,
}

impl FromStr for ExpandFlags {
    type Err = Error;
    fn from_str(param: &str) -> Result<ExpandFlags> {
        let list: Vec<&str> = param.split_terminator(",").collect();
        Ok(ExpandFlags::from_str_list(&list))
    }
}

impl ExpandFlags {
    pub fn from_str_list(list: &[&str]) -> ExpandFlags {
        ExpandFlags {
            files: list.contains(&"files"),
            filesets: list.contains(&"filesets"),
            webcaptures: list.contains(&"webcaptures"),
            container: list.contains(&"container"),
            releases: list.contains(&"releases"),
            creators: list.contains(&"creators"),
        }
    }
    pub fn none() -> ExpandFlags {
        ExpandFlags {
            files: false,
            filesets: false,
            webcaptures: false,
            container: false,
            releases: false,
            creators: false,
        }
    }
}

#[test]
fn test_expand_flags() {
    assert!(ExpandFlags::from_str_list(&vec![]).files == false);
    assert!(ExpandFlags::from_str_list(&vec!["files"]).files == true);
    assert!(ExpandFlags::from_str_list(&vec!["file"]).files == false);
    let all = ExpandFlags::from_str_list(&vec![
        "files",
        "filesets",
        "webcaptures",
        "container",
        "other_thing",
        "releases",
        "creators",
    ]);
    assert!(
        all == ExpandFlags {
            files: true,
            filesets: true,
            webcaptures: true,
            container: true,
            releases: true,
            creators: true
        }
    );
    assert!(ExpandFlags::from_str("").unwrap().files == false);
    assert!(ExpandFlags::from_str("files").unwrap().files == true);
    assert!(ExpandFlags::from_str("something,,files").unwrap().files == true);
    assert!(ExpandFlags::from_str("file").unwrap().files == false);
    let all =
        ExpandFlags::from_str("files,container,other_thing,releases,creators,filesets,webcaptures")
            .unwrap();
    assert!(
        all == ExpandFlags {
            files: true,
            filesets: true,
            webcaptures: true,
            container: true,
            releases: true,
            creators: true
        }
    );
}

#[derive(Clone, Copy, PartialEq)]
pub struct HideFlags {
    // release
    pub abstracts: bool,
    pub refs: bool,
    pub contribs: bool,
    // fileset
    pub manifest: bool,
    // webcapture
    pub cdx: bool,
}

impl FromStr for HideFlags {
    type Err = Error;
    fn from_str(param: &str) -> Result<HideFlags> {
        let list: Vec<&str> = param.split_terminator(",").collect();
        Ok(HideFlags::from_str_list(&list))
    }
}

impl HideFlags {
    pub fn from_str_list(list: &[&str]) -> HideFlags {
        HideFlags {
            abstracts: list.contains(&"abstracts"),
            refs: list.contains(&"refs"),
            contribs: list.contains(&"contribs"),
            manifest: list.contains(&"contribs"),
            cdx: list.contains(&"contribs"),
        }
    }
    pub fn none() -> HideFlags {
        HideFlags {
            abstracts: false,
            refs: false,
            contribs: false,
            manifest: false,
            cdx: false,
        }
    }
}

#[test]
fn test_hide_flags() {
    assert!(HideFlags::from_str_list(&vec![]).abstracts == false);
    assert!(HideFlags::from_str_list(&vec!["abstracts"]).abstracts == true);
    assert!(HideFlags::from_str_list(&vec!["abstract"]).abstracts == false);
    let all = HideFlags::from_str_list(&vec![
        "abstracts",
        "refs",
        "other_thing",
        "contribs",
        "manifest",
        "cdx",
    ]);
    assert!(
        all == HideFlags {
            abstracts: true,
            refs: true,
            contribs: true,
            manifest: true,
            cdx: true,
        }
    );
    assert!(HideFlags::from_str("").unwrap().abstracts == false);
    assert!(HideFlags::from_str("abstracts").unwrap().abstracts == true);
    assert!(
        HideFlags::from_str("something,,abstracts")
            .unwrap()
            .abstracts
            == true
    );
    assert!(HideFlags::from_str("file").unwrap().abstracts == false);
    let all = HideFlags::from_str("abstracts,cdx,refs,manifest,other_thing,contribs").unwrap();
    assert!(
        all == HideFlags {
            abstracts: true,
            refs: true,
            contribs: true,
            manifest: true,
            cdx: true,
        }
    );
}

pub fn make_edit_context(
    conn: &DbConn,
    editor_id: FatCatId,
    editgroup_id: Option<FatCatId>,
    autoaccept: bool,
) -> Result<EditContext> {
    let editgroup_id: FatCatId = match (editgroup_id, autoaccept) {
        (Some(eg), _) => eg,
        // If autoaccept and no editgroup_id passed, always create a new one for this transaction
        (None, true) => {
            let eg_row: EditgroupRow = diesel::insert_into(editgroup::table)
                .values((editgroup::editor_id.eq(editor_id.to_uuid()),))
                .get_result(conn)?;
            FatCatId::from_uuid(&eg_row.id)
        }
        (None, false) => FatCatId::from_uuid(&get_or_create_editgroup(editor_id.to_uuid(), conn)?),
    };
    Ok(EditContext {
        editor_id: editor_id,
        editgroup_id: editgroup_id,
        extra_json: None,
        autoaccept: autoaccept,
    })
}

pub fn create_editor(
    conn: &DbConn,
    username: String,
    is_admin: bool,
    is_bot: bool,
) -> Result<EditorRow> {
    check_username(&username)?;
    let ed: EditorRow = diesel::insert_into(editor::table)
        .values((
            editor::username.eq(username),
            editor::is_admin.eq(is_admin),
            editor::is_bot.eq(is_bot),
        ))
        .get_result(conn)?;
    Ok(ed)
}

pub fn update_editor_username(
    conn: &DbConn,
    editor_id: FatCatId,
    username: String,
) -> Result<EditorRow> {
    check_username(&username)?;
    diesel::update(editor::table.find(editor_id.to_uuid()))
        .set(editor::username.eq(username))
        .execute(conn)?;
    let editor: EditorRow = editor::table.find(editor_id.to_uuid()).get_result(conn)?;
    Ok(editor)
}

/// This function should always be run within a transaction
pub fn get_or_create_editgroup(editor_id: Uuid, conn: &DbConn) -> Result<Uuid> {
    // check for current active
    let ed_row: EditorRow = editor::table.find(editor_id).first(conn)?;
    if let Some(current) = ed_row.active_editgroup_id {
        return Ok(current);
    }

    // need to insert and update
    let eg_row: EditgroupRow = diesel::insert_into(editgroup::table)
        .values((editgroup::editor_id.eq(ed_row.id),))
        .get_result(conn)?;
    diesel::update(editor::table.find(ed_row.id))
        .set(editor::active_editgroup_id.eq(eg_row.id))
        .execute(conn)?;
    Ok(eg_row.id)
}

/// This function should always be run within a transaction
pub fn accept_editgroup(editgroup_id: FatCatId, conn: &DbConn) -> Result<ChangelogRow> {
    // check that we haven't accepted already (in changelog)
    // NB: could leave this to a UNIQUE constraint
    // TODO: redundant with check_edit_context
    let count: i64 = changelog::table
        .filter(changelog::editgroup_id.eq(editgroup_id.to_uuid()))
        .count()
        .get_result(conn)?;
    if count > 0 {
        return Err(ErrorKind::EditgroupAlreadyAccepted(editgroup_id.to_string()).into());
    }

    // copy edit columns to ident table
    ContainerEntity::db_accept_edits(conn, editgroup_id)?;
    CreatorEntity::db_accept_edits(conn, editgroup_id)?;
    FileEntity::db_accept_edits(conn, editgroup_id)?;
    FilesetEntity::db_accept_edits(conn, editgroup_id)?;
    WebcaptureEntity::db_accept_edits(conn, editgroup_id)?;
    ReleaseEntity::db_accept_edits(conn, editgroup_id)?;
    WorkEntity::db_accept_edits(conn, editgroup_id)?;

    // append log/changelog row
    let entry: ChangelogRow = diesel::insert_into(changelog::table)
        .values((changelog::editgroup_id.eq(editgroup_id.to_uuid()),))
        .get_result(conn)?;

    // update any editor's active editgroup
    let no_active: Option<Uuid> = None;
    diesel::update(editor::table)
        .filter(editor::active_editgroup_id.eq(editgroup_id.to_uuid()))
        .set(editor::active_editgroup_id.eq(no_active))
        .execute(conn)?;
    Ok(entry)
}

#[derive(Clone, Copy, PartialEq, Debug)]
pub struct FatCatId(Uuid);

impl ToString for FatCatId {
    fn to_string(&self) -> String {
        uuid2fcid(&self.to_uuid())
    }
}

impl FromStr for FatCatId {
    type Err = Error;
    fn from_str(s: &str) -> Result<FatCatId> {
        fcid2uuid(s).map(|u| FatCatId(u))
    }
}

impl FatCatId {
    pub fn to_uuid(&self) -> Uuid {
        self.0
    }
    // TODO: just make it u: Uuid and clone (not by ref)
    pub fn from_uuid(u: &Uuid) -> FatCatId {
        FatCatId(*u)
    }
}

/// Convert fatcat IDs (base32 strings) to UUID
pub fn fcid2uuid(fcid: &str) -> Result<Uuid> {
    if fcid.len() != 26 {
        return Err(ErrorKind::InvalidFatcatId(fcid.to_string()).into());
    }
    let mut raw = vec![0; 16];
    BASE32_NOPAD
        .decode_mut(fcid.to_uppercase().as_bytes(), &mut raw)
        .map_err(|_dp| ErrorKind::InvalidFatcatId(fcid.to_string()))?;
    // unwrap() is safe here, because we know raw is always 16 bytes
    Ok(Uuid::from_bytes(&raw).unwrap())
}

/// Convert UUID to fatcat ID string (base32 encoded)
pub fn uuid2fcid(id: &Uuid) -> String {
    let raw = id.as_bytes();
    BASE32_NOPAD.encode(raw).to_lowercase()
}

pub fn check_username(raw: &str) -> Result<()> {
    lazy_static! {
        static ref RE: Regex = Regex::new(r"^[A-Za-z0-9][A-Za-z0-9._-]{2,19}$").unwrap();
    }
    if RE.is_match(raw) {
        Ok(())
    } else {
        Err(ErrorKind::MalformedExternalId(format!(
            "not a valid username: '{}' (expected, eg, 'AcidBurn')",
            raw
        ))
        .into())
    }
}

#[test]
fn test_check_username() {
    assert!(check_username("bnewbold").is_ok());
    assert!(check_username("BNEWBOLD").is_ok());
    assert!(check_username("admin").is_ok());
    assert!(check_username("friend-bot").is_ok());
    assert!(check_username("dog").is_ok());
    assert!(check_username("g_____").is_ok());

    assert!(check_username("").is_err());
    assert!(check_username("_").is_err());
    assert!(check_username("gg").is_err());
    assert!(check_username("adminadminadminadminadminadminadmin").is_err());
    assert!(check_username("bryan newbold").is_err());
    assert!(check_username("01234567-3456-6780").is_err());
    assert!(check_username(".admin").is_err());
    assert!(check_username("-bot").is_err());
}

pub fn check_pmcid(raw: &str) -> Result<()> {
    lazy_static! {
        static ref RE: Regex = Regex::new(r"^PMC\d+$").unwrap();
    }
    if RE.is_match(raw) {
        Ok(())
    } else {
        Err(ErrorKind::MalformedExternalId(format!(
            "not a valid PubMed Central ID (PMCID): '{}' (expected, eg, 'PMC12345')",
            raw
        ))
        .into())
    }
}

pub fn check_pmid(raw: &str) -> Result<()> {
    lazy_static! {
        static ref RE: Regex = Regex::new(r"^\d+$").unwrap();
    }
    if RE.is_match(raw) {
        Ok(())
    } else {
        Err(ErrorKind::MalformedExternalId(format!(
            "not a valid PubMed ID (PMID): '{}' (expected, eg, '1234')",
            raw
        ))
        .into())
    }
}

pub fn check_wikidata_qid(raw: &str) -> Result<()> {
    lazy_static! {
        static ref RE: Regex = Regex::new(r"^Q\d+$").unwrap();
    }
    if RE.is_match(raw) {
        Ok(())
    } else {
        Err(ErrorKind::MalformedExternalId(format!(
            "not a valid Wikidata QID: '{}' (expected, eg, 'Q1234')",
            raw
        ))
        .into())
    }
}

pub fn check_doi(raw: &str) -> Result<()> {
    lazy_static! {
        static ref RE: Regex = Regex::new(r"^10.\d{3,6}/.+$").unwrap();
    }
    if RE.is_match(raw) {
        Ok(())
    } else {
        Err(ErrorKind::MalformedExternalId(format!(
            "not a valid DOI: '{}' (expected, eg, '10.1234/aksjdfh')",
            raw
        ))
        .into())
    }
}

pub fn check_issn(raw: &str) -> Result<()> {
    lazy_static! {
        static ref RE: Regex = Regex::new(r"^\d{4}-\d{3}[0-9X]$").unwrap();
    }
    if RE.is_match(raw) {
        Ok(())
    } else {
        Err(ErrorKind::MalformedExternalId(format!(
            "not a valid ISSN: '{}' (expected, eg, '1234-5678')",
            raw
        ))
        .into())
    }
}

pub fn check_orcid(raw: &str) -> Result<()> {
    lazy_static! {
        static ref RE: Regex = Regex::new(r"^\d{4}-\d{4}-\d{4}-\d{3}[\dX]$").unwrap();
    }
    if RE.is_match(raw) {
        Ok(())
    } else {
        Err(ErrorKind::MalformedExternalId(format!(
            "not a valid ORCID: '{}' (expected, eg, '0123-4567-3456-6789')",
            raw
        ))
        .into())
    }
}

#[test]
fn test_check_orcid() {
    assert!(check_orcid("0123-4567-3456-6789").is_ok());
    assert!(check_orcid("0123-4567-3456-678X").is_ok());
    assert!(check_orcid("01234567-3456-6780").is_err());
    assert!(check_orcid("0x23-4567-3456-6780").is_err());
}

pub fn check_md5(raw: &str) -> Result<()> {
    lazy_static! {
        static ref RE: Regex = Regex::new(r"^[a-f0-9]{32}$").unwrap();
    }
    if RE.is_match(raw) {
        Ok(())
    } else {
        Err(ErrorKind::MalformedChecksum(format!(
            "not a valid MD5: '{}' (expected lower-case hex, eg, '1b39813549077b2347c0f370c3864b40')",
            raw
        ))
        .into())
    }
}

#[test]
fn test_check_md5() {
    assert!(check_md5("1b39813549077b2347c0f370c3864b40").is_ok());
    assert!(check_md5("1g39813549077b2347c0f370c3864b40").is_err());
    assert!(check_md5("1B39813549077B2347C0F370c3864b40").is_err());
    assert!(check_md5("1b39813549077b2347c0f370c3864b4").is_err());
    assert!(check_md5("1b39813549077b2347c0f370c3864b411").is_err());
}

pub fn check_sha1(raw: &str) -> Result<()> {
    lazy_static! {
        static ref RE: Regex = Regex::new(r"^[a-f0-9]{40}$").unwrap();
    }
    if RE.is_match(raw) {
        Ok(())
    } else {
        Err(ErrorKind::MalformedChecksum(format!(
            "not a valid SHA-1: '{}' (expected lower-case hex, eg, 'e9dd75237c94b209dc3ccd52722de6931a310ba3')",
            raw
        ))
        .into())
    }
}

#[test]
fn test_check_sha1() {
    assert!(check_sha1("e9dd75237c94b209dc3ccd52722de6931a310ba3").is_ok());
    assert!(check_sha1("g9dd75237c94b209dc3ccd52722de6931a310ba3").is_err());
    assert!(check_sha1("e9DD75237C94B209DC3CCD52722de6931a310ba3").is_err());
    assert!(check_sha1("e9dd75237c94b209dc3ccd52722de6931a310ba").is_err());
    assert!(check_sha1("e9dd75237c94b209dc3ccd52722de6931a310ba33").is_err());
}

pub fn check_sha256(raw: &str) -> Result<()> {
    lazy_static! {
        static ref RE: Regex = Regex::new(r"^[a-f0-9]{64}$").unwrap();
    }
    if RE.is_match(raw) {
        Ok(())
    } else {
        Err(ErrorKind::MalformedChecksum(format!(
            "not a valid SHA-256: '{}' (expected lower-case hex, eg, 'cb1c378f464d5935ddaa8de28446d82638396c61f042295d7fb85e3cccc9e452')",
            raw
        ))
        .into())
    }
}

#[test]
fn test_check_sha256() {
    assert!(
        check_sha256("cb1c378f464d5935ddaa8de28446d82638396c61f042295d7fb85e3cccc9e452").is_ok()
    );
    assert!(
        check_sha256("gb1c378f464d5935ddaa8de28446d82638396c61f042295d7fb85e3cccc9e452").is_err()
    );
    assert!(
        check_sha256("UB1C378F464d5935ddaa8de28446d82638396c61f042295d7fb85e3cccc9e452").is_err()
    );
    assert!(
        check_sha256("cb1c378f464d5935ddaa8de28446d82638396c61f042295d7fb85e3cccc9e45").is_err()
    );
    assert!(
        check_sha256("cb1c378f464d5935ddaa8de28446d82638396c61f042295d7fb85e3cccc9e4522").is_err()
    );
}

pub fn check_release_type(raw: &str) -> Result<()> {
    let valid_types = vec![
        // Citation Style Language official types
        "article",
        "article-magazine",
        "article-newspaper",
        "article-journal",
        "bill",
        "book",
        "broadcast",
        "chapter",
        "dataset",
        "entry",
        "entry-dictionary",
        "entry-encyclopedia",
        "figure",
        "graphic",
        "interview",
        "legislation",
        "legal_case",
        "manuscript",
        "map",
        "motion_picture",
        "musical_score",
        "pamphlet",
        "paper-conference",
        "patent",
        "post",
        "post-weblog",
        "personal_communication",
        "report",
        "review",
        "review-book",
        "song",
        "speech",
        "thesis",
        "treaty",
        "webpage",
        // fatcat-specific extensions
        "peer_review",
        "software",
        "standard",
    ];
    for good in valid_types {
        if raw == good {
            return Ok(());
        }
    }
    Err(ErrorKind::NotInControlledVocabulary(format!(
        "not a valid release_type: '{}' (expected a CSL type, eg, 'article-journal', 'book')",
        raw
    ))
    .into())
}

#[test]
fn test_check_release_type() {
    assert!(check_release_type("book").is_ok());
    assert!(check_release_type("article-journal").is_ok());
    assert!(check_release_type("standard").is_ok());
    assert!(check_release_type("journal-article").is_err());
    assert!(check_release_type("BOOK").is_err());
    assert!(check_release_type("book ").is_err());
}

pub fn check_contrib_role(raw: &str) -> Result<()> {
    let valid_types = vec![
        // Citation Style Language official role types
        "author",
        "collection-editor",
        "composer",
        "container-author",
        "director",
        "editor",
        "editorial-director",
        "editortranslator",
        "illustrator",
        "interviewer",
        "original-author",
        "recipient",
        "reviewed-author",
        "translator",
        // common extension (for conference proceeding chair)
        //"chair",
    ];
    for good in valid_types {
        if raw == good {
            return Ok(());
        }
    }
    Err(ErrorKind::NotInControlledVocabulary(format!(
        "not a valid contrib.role: '{}' (expected a CSL type, eg, 'author', 'editor')",
        raw
    ))
    .into())
}

#[test]
fn test_check_contrib_role() {
    assert!(check_contrib_role("author").is_ok());
    assert!(check_contrib_role("editor").is_ok());
    assert!(check_contrib_role("chair").is_err());
    assert!(check_contrib_role("EDITOR").is_err());
    assert!(check_contrib_role("editor ").is_err());
}

// TODO: make the above checks "more correct"
// TODO: check ISBN-13