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
//! Objects related to the "annotations" endpoint

use std::collections::HashMap;

use chrono::{DateTime, Utc};
#[cfg(feature = "cli")]
use clap::Parser;
#[cfg(feature = "cli")]
use clap::ValueEnum;
use serde::{Deserialize, Serialize};

use crate::{errors, is_default, UserAccountID};

#[cfg_attr(feature = "cli", derive(Parser))]
#[cfg_attr(
    feature = "cli",
    clap(
        about = "Create an annotation",
        long_about = "Create and upload an annotation to your Hypothesis"
    )
)]
/// Struct to create annotations
///
/// All fields except uri are optional, i.e. leave as default.
///
/// # Example
/// ```
/// use hypothesis::annotations::{InputAnnotation, Target, Selector};
/// # #[tokio::main]
/// # async fn main() -> Result<(), hypothesis::errors::HypothesisError> {
/// // A simple annotation
/// let annotation_simple = InputAnnotation::builder()
///     .uri("https://www.example.com")
///     .text("My new annotation").build()?;
///
/// // A complex annotation
/// let annotation_complex = InputAnnotation::builder()
///     .uri("https://www.example.com")
///     .text("this is a comment")
///     .target(Target::builder().source("https://www.example.com")
///         .selector(vec![Selector::new_quote("exact text in website to highlight",
///                                             "prefix of text",
///                                             "suffix of text")]).build()?)
///     .tags(vec!["tag1".into(), "tag2".into()])
///     .build()?;
/// # Ok(())
/// # }
/// ```
#[derive(Serialize, Debug, Default, Clone, Builder, PartialEq)]
#[builder(default, build_fn(name = "builder"))]
pub struct InputAnnotation {
    /// URI that this annotation is attached to.
    ///
    /// Can be a URL (a web page address) or a URN representing another kind of resource such as
    /// DOI (Digital Object Identifier) or a PDF fingerprint.
    #[serde(skip_serializing_if = "is_default")]
    #[cfg_attr(feature = "cli", clap(default_value = ""))]
    #[builder(setter(into))]
    pub uri: String,
    /// Annotation text / comment given by user
    ///
    /// This is NOT the selected text on the web-page
    #[serde(skip_serializing_if = "is_default")]
    #[cfg_attr(feature = "cli", clap(default_value = "", long))]
    #[builder(setter(into))]
    pub text: String,
    /// Tags attached to the annotation
    #[serde(skip_serializing_if = "is_default")]
    #[cfg_attr(feature = "cli", clap(long))]
    #[builder(setter(strip_option), default)]
    pub tags: Option<Vec<String>>,
    /// Further metadata about the target document
    #[serde(skip_serializing_if = "is_default")]
    #[cfg_attr(feature = "cli", clap(skip))]
    #[builder(setter(strip_option), default)]
    pub document: Option<Document>,
    #[serde(skip_serializing_if = "is_default")]
    /// The unique identifier for the annotation's group.
    ///
    /// If an annotation is a reply to another
    /// annotation (see `references`), this field will be ignored —
    /// replies belong to the same group as their parent annotations.
    #[cfg_attr(feature = "cli", clap(default_value = "", long))]
    #[builder(setter(into))]
    pub group: String,
    /// Which part of the document does the annotation target?
    ///
    /// If left as default then the annotation is linked to the whole page.
    #[serde(skip_serializing_if = "is_default")]
    #[cfg_attr(feature = "cli", clap(skip))]
    pub target: Target,
    /// Annotation IDs for any annotations this annotation references (e.g. is a reply to)
    #[serde(skip_serializing_if = "is_default")]
    #[cfg_attr(feature = "cli", clap(long))]
    pub references: Vec<String>,
}

impl InputAnnotation {
    pub fn builder() -> InputAnnotationBuilder {
        InputAnnotationBuilder::default()
    }
}

impl InputAnnotationBuilder {
    /// Builds a new `InputAnnotation`.
    pub fn build(&self) -> Result<InputAnnotation, errors::HypothesisError> {
        self.builder()
            .map_err(|e| errors::HypothesisError::BuilderError(e.to_string()))
    }
}

impl Annotation {
    pub fn update(&mut self, annotation: InputAnnotation) {
        if !annotation.uri.is_empty() {
            self.uri = annotation.uri;
        }
        if !annotation.text.is_empty() {
            self.text = annotation.text;
        }
        if let Some(tags) = annotation.tags {
            self.tags = tags;
        }
        if !annotation.group.is_empty() {
            self.group = annotation.group;
        }
        if annotation.references.is_empty() {
            self.references = annotation.references;
        }
    }
}

#[derive(Serialize, Deserialize, Debug, Default, Clone, PartialEq, Builder)]
#[builder(build_fn(name = "builder"))]
pub struct Document {
    #[serde(skip_serializing_if = "is_default", default)]
    pub title: Vec<String>,
    #[serde(skip_serializing_if = "is_default", default)]
    #[builder(setter(strip_option), default)]
    pub dc: Option<Dc>,
    #[serde(skip_serializing_if = "is_default", default)]
    #[builder(setter(strip_option), default)]
    pub highwire: Option<HighWire>,
    #[serde(skip_serializing_if = "is_default", default)]
    pub link: Vec<Link>,
}

impl Document {
    pub fn builder() -> DocumentBuilder {
        DocumentBuilder::default()
    }
}

impl DocumentBuilder {
    /// Builds a new `Document`.
    pub fn build(&self) -> Result<Document, errors::HypothesisError> {
        self.builder()
            .map_err(|e| errors::HypothesisError::BuilderError(e.to_string()))
    }
}

#[derive(Serialize, Deserialize, Default, Debug, Clone, PartialEq)]
pub struct HighWire {
    #[serde(skip_serializing_if = "is_default", default)]
    pub doi: Vec<String>,
    #[serde(skip_serializing_if = "is_default", default)]
    pub pdf_url: Vec<String>,
}

#[derive(Serialize, Deserialize, Debug, Default, Clone, PartialEq)]
pub struct Link {
    pub href: String,
    #[serde(skip_serializing_if = "is_default", rename = "type", default)]
    pub link_type: String,
}

#[derive(Serialize, Deserialize, Debug, Default, Clone, PartialEq)]
pub struct Dc {
    #[serde(skip_serializing_if = "is_default", default)]
    pub identifier: Vec<String>,
}

/// Full representation of an Annotation resource and applicable relationships.
#[derive(Serialize, Deserialize, Debug, Clone, PartialEq)]
pub struct Annotation {
    /// Annotation ID
    pub id: String,
    /// Date of creation
    pub created: DateTime<Utc>,
    /// Date of last update
    pub updated: DateTime<Utc>,
    /// User account ID in the format "acct:<username>@<authority>"
    pub user: UserAccountID,
    /// URL of document this annotation is attached to
    pub uri: String,
    /// The text content of the annotation body (NOT the selected text in the document)
    pub text: String,
    /// Tags attached to annotation
    pub tags: Vec<String>,
    /// The unique identifier for the annotation's group
    pub group: String,
    pub permissions: Permissions,
    /// Which part of the document does the annotation target.
    pub target: Vec<Target>,
    /// An object containing hypermedia links for this annotation
    pub links: HashMap<String, String>,
    /// Whether this annotation is hidden from public view
    pub hidden: bool,
    /// Whether this annotation has one or more flags for moderation
    pub flagged: bool,
    /// Document information
    #[serde(default)]
    pub document: Option<Document>,
    /// Annotation IDs for any annotations this annotation references (e.g. is a reply to)
    #[serde(default)]
    pub references: Vec<String>,
    #[serde(default)]
    pub user_info: Option<UserInfo>,
}

#[derive(Serialize, Deserialize, Debug, Clone, PartialEq)]
pub struct UserInfo {
    /// The annotation creator's display name
    pub display_name: Option<String>,
}

/// > While the API accepts arbitrary Annotation selectors in the target.selector property,
/// > the Hypothesis client currently supports TextQuoteSelector, RangeSelector and TextPositionSelector selector.
/// [Hypothesis API v1.0.0](https://h.readthedocs.io/en/latest/api-reference/v1/#tag/annotations/paths/~1annotations/post)
#[derive(Serialize, Deserialize, Debug, Clone, Default, PartialEq, Builder)]
#[builder(build_fn(name = "builder"))]
pub struct Target {
    /// The target URI for the annotation
    /// Leave empty when creating an annotation
    #[serde(skip_serializing_if = "is_default")]
    #[builder(setter(into))]
    pub source: String,
    /// An array of selectors that refine this annotation's target
    #[serde(default, skip_serializing_if = "is_default")]
    pub selector: Vec<Selector>,
}

impl Target {
    pub fn builder() -> TargetBuilder {
        TargetBuilder::default()
    }
}

impl TargetBuilder {
    /// Builds a new `Target`.
    pub fn build(&self) -> Result<Target, errors::HypothesisError> {
        self.builder()
            .map_err(|e| errors::HypothesisError::BuilderError(e.to_string()))
    }
}

/// > Many Annotations refer to part of a resource, rather than all of it, as the Target.
/// > We call that part of the resource a Segment (of Interest). A Selector is used to describe how
/// > to determine the Segment from within the Source resource.
/// [Web Annotation Data Model - Selectors](https://www.w3.org/TR/annotation-model/#selectors)
#[derive(Serialize, Deserialize, Debug, Clone, PartialEq)]
#[serde(tag = "type")]
pub enum Selector {
    TextQuoteSelector(TextQuoteSelector),
    /// > Selections made by users may be extensive and/or cross over internal boundaries in the
    /// > representation, making it difficult to construct a single selector that robustly describes
    /// > the correct content. A Range Selector can be used to identify the beginning and the end of
    /// > the selection by using other Selectors. In this way, two points can be accurately identified
    /// > using the most appropriate selection mechanisms, and then linked together to form the selection.
    /// > The selection consists of everything from the beginning of the starting selector through to the
    /// > beginning of the ending selector, but not including it.
    /// [Web Annotation Data Model - Range Selector](https://www.w3.org/TR/annotation-model/#range-selector)
    /// NOTE - the Hypothesis API doesn't seem to follow this standard for RangeSelector so this just returns a HashMap for now
    /// TODO: make Selectors into structs
    TextPositionSelector(HashMap<String, serde_json::Value>),
    RangeSelector(HashMap<String, serde_json::Value>),
    FragmentSelector(HashMap<String, serde_json::Value>),
    CssSelector(HashMap<String, serde_json::Value>),
    XPathSelector(HashMap<String, serde_json::Value>),
    DataPositionSelector(HashMap<String, serde_json::Value>),
    SvgSelector(HashMap<String, serde_json::Value>),
    // See https://github.com/hypothesis/h/issues/7803:
    PageSelector(HashMap<String, serde_json::Value>),
    EPUBContentSelector(HashMap<String, serde_json::Value>),
}

impl Selector {
    pub fn new_quote(exact: &str, prefix: &str, suffix: &str) -> Self {
        Self::TextQuoteSelector(TextQuoteSelector {
            exact: exact.to_string(),
            prefix: prefix.to_string(),
            suffix: suffix.to_string(),
        })
    }
}

/// > This Selector describes a range of text by copying it, and including some of the text
/// > immediately before (a prefix) and after (a suffix) it to distinguish between multiple
/// > copies of the same sequence of characters.
///
/// > For example, if the document were again "abcdefghijklmnopqrstuvwxyz", one could select
/// > "efg" by a prefix of "abcd", the match of "efg" and a suffix of "hijk".
/// [Web Annotation Data Model - Text Quote Selector](https://www.w3.org/TR/annotation-model/#text-quote-selector)
#[derive(Serialize, Deserialize, Debug, Clone, PartialEq)]
pub struct TextQuoteSelector {
    /// A copy of the text which is being selected, after normalization.
    pub exact: String,
    /// A snippet of text that occurs immediately before the text which is being selected.
    pub prefix: String,
    /// The snippet of text that occurs immediately after the text which is being selected.
    pub suffix: String,
}

#[cfg_attr(feature = "cli", derive(ValueEnum))]
#[derive(Serialize, Deserialize, Debug, Clone, PartialEq)]
#[serde(rename_all = "lowercase")]
pub enum Sort {
    Created,
    Updated,
    Id,
    Group,
    User,
}

impl Default for Sort {
    fn default() -> Self {
        Self::Updated
    }
}

#[cfg_attr(feature = "cli", derive(ValueEnum))]
#[derive(Serialize, Deserialize, Debug, Clone, PartialEq)]
#[serde(rename_all = "lowercase")]
pub enum Order {
    Asc,
    Desc,
}

impl Default for Order {
    fn default() -> Self {
        Self::Desc
    }
}

/// Options to filter and sort search results. See [the Hypothesis API docs](https://h.readthedocs.io/en/latest/api-reference/v1/#tag/annotations/paths/~1search/get) for more details on using these fields
#[cfg_attr(feature = "cli", derive(Parser))]
#[derive(Serialize, Debug, Clone, PartialEq, Builder, Default)]
#[builder(build_fn(name = "builder"), default)]
pub struct SearchQuery {
    /// The maximum number of annotations to return.
    ///
    /// Default: 20. Range: [ 0 .. 200 ]
    #[builder(default = "20")]
    #[cfg_attr(feature = "cli", clap(default_value = "20", long))]
    pub limit: u8,
    /// The field by which annotations should be sorted
    /// One of created, updated, id, group, user
    ///
    /// Default: updated
    #[cfg_attr(feature = "cli", clap(default_value = "updated", long, value_parser = clap::builder::EnumValueParser::<Sort>::new()))]
    pub sort: Sort,
    /// Example: "2019-01-03T19:46:09.334Z"
    ///
    /// Define a start point for a subset (page) of annotation search results.
    /// NOTE: make sure to set sort to `Sort::Asc` if using `search_after`
    #[serde(skip_serializing_if = "is_default")]
    #[cfg_attr(feature = "cli", clap(default_value = "", long))]
    #[builder(setter(into))]
    pub search_after: String,
    /// The number of initial annotations to skip in the result set.
    ///
    /// Default: 0. Range: <= 9800.
    /// search_after is more efficient.
    #[cfg_attr(feature = "cli", clap(default_value = "0", long))]
    pub offset: usize,
    /// The order in which the results should be sorted.
    /// One of asc, desc
    ///
    /// Default: desc
    #[cfg_attr(feature = "cli", clap(default_value = "desc", long, value_parser = clap::builder::EnumValueParser::<Order>::new()))]
    pub order: Order,
    /// Limit the results to annotations matching the specific URI or equivalent URIs.
    ///
    /// URI can be a URL (a web page address) or a URN representing another kind of resource such
    /// as DOI (Digital Object Identifier) or a PDF fingerprint.
    #[serde(skip_serializing_if = "is_default")]
    #[cfg_attr(feature = "cli", clap(default_value = "", long))]
    #[builder(setter(into))]
    pub uri: String,
    /// Limit the results to annotations containing the given keyword (tokenized chunk) in the URI.
    /// The value must exactly match an individual URI keyword.
    ///
    #[serde(rename = "uri.parts", skip_serializing_if = "is_default")]
    #[cfg_attr(feature = "cli", clap(default_value = "", long))]
    #[builder(setter(into))]
    pub uri_parts: String,
    /// Limit the results to annotations whose URIs match the wildcard pattern.
    #[serde(rename = "wildcard_uri", skip_serializing_if = "is_default")]
    #[cfg_attr(feature = "cli", clap(default_value = "", long))]
    #[builder(setter(into))]
    pub wildcard_uri: String,
    /// Limit the results to annotations made by the specified user. (in the format `acct:<username>@<authority>`)
    #[serde(skip_serializing_if = "is_default")]
    #[cfg_attr(feature = "cli", clap(default_value = "", long))]
    #[builder(setter(into))]
    pub user: String,
    /// Limit the results to annotations made in the specified group (by group ID).
    /// This can be specified multiple times to retrieve multiple groups.
    #[serde(skip_serializing_if = "is_default")]
    #[cfg_attr(feature = "cli", clap(long))]
    #[builder(setter(into))]
    pub group: Vec<String>,
    /// Limit the results to annotations tagged with the specified value.
    #[serde(skip_serializing_if = "is_default")]
    #[cfg_attr(feature = "cli", clap(default_value = "", long))]
    #[builder(setter(into))]
    pub tag: String,
    /// Similar to tag but allows a list of multiple tags.
    #[serde(skip_serializing_if = "is_default")]
    #[cfg_attr(feature = "cli", clap(long))]
    pub tags: Vec<String>,
    /// Limit the results to annotations who contain the indicated keyword in any of the following fields:
    /// `quote`, `tags`, `text`, `url`
    #[serde(skip_serializing_if = "is_default")]
    #[cfg_attr(feature = "cli", clap(default_value = "", long))]
    #[builder(setter(into))]
    pub any: String,
    /// Limit the results to annotations that contain this text inside the text that was annotated.
    #[serde(skip_serializing_if = "is_default")]
    #[cfg_attr(feature = "cli", clap(default_value = "", long))]
    #[builder(setter(into))]
    pub quote: String,
    /// Returns annotations that are replies to this parent annotation ID.
    #[serde(skip_serializing_if = "is_default")]
    #[cfg_attr(feature = "cli", clap(default_value = "", long))]
    #[builder(setter(into))]
    pub references: String,
    /// Limit the results to annotations that contain this text in their textual body.
    #[serde(skip_serializing_if = "is_default")]
    #[cfg_attr(feature = "cli", clap(default_value = "", long))]
    #[builder(setter(into))]
    pub text: String,
}

impl SearchQuery {
    pub fn builder() -> SearchQueryBuilder {
        SearchQueryBuilder::default()
    }
}

impl SearchQueryBuilder {
    /// Builds a new `SearchQuery`.
    pub fn build(&self) -> Result<SearchQuery, errors::HypothesisError> {
        self.builder()
            .map_err(|e| errors::HypothesisError::BuilderError(e.to_string()))
    }
}

#[derive(Serialize, Deserialize, Debug, Clone, PartialEq)]
pub struct Permissions {
    pub read: Vec<String>,
    pub delete: Vec<String>,
    pub admin: Vec<String>,
    pub update: Vec<String>,
}