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
//! An implementation of the "stringprep" algorithm defined in [RFC 3454][].
//!
//! [RFC 3454]: https://tools.ietf.org/html/rfc3454
#![warn(missing_docs)]
extern crate unicode_bidi;
extern crate unicode_normalization;
extern crate unicode_properties;

use std::borrow::Cow;
use std::fmt;
use unicode_normalization::UnicodeNormalization;
use unicode_properties::{GeneralCategoryGroup, UnicodeGeneralCategory};

mod rfc3454;
pub mod tables;

/// Describes why a string failed stringprep normalization.
#[derive(Debug)]
enum ErrorCause {
    /// Contains stringprep prohibited characters.
    ProhibitedCharacter(char),
    /// Violates stringprep rules for bidirectional text.
    ProhibitedBidirectionalText,
    /// Starts with a combining character
    StartsWithCombiningCharacter,
    /// Empty String
    EmptyString,
}

/// An error performing the stringprep algorithm.
#[derive(Debug)]
pub struct Error(ErrorCause);

impl fmt::Display for Error {
    fn fmt(&self, fmt: &mut fmt::Formatter) -> fmt::Result {
        match self.0 {
            ErrorCause::ProhibitedCharacter(c) => write!(fmt, "prohibited character `{}`", c),
            ErrorCause::ProhibitedBidirectionalText => write!(fmt, "prohibited bidirectional text"),
            ErrorCause::StartsWithCombiningCharacter => {
                write!(fmt, "starts with combining character")
            }
            ErrorCause::EmptyString => write!(fmt, "empty string"),
        }
    }
}

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

/// Prepares a string with the SASLprep profile of the stringprep algorithm.
///
/// SASLprep is defined in [RFC 4013][].
///
/// [RFC 4013]: https://tools.ietf.org/html/rfc4013
pub fn saslprep(s: &str) -> Result<Cow<'_, str>, Error> {
    // fast path for ascii text
    if s.chars()
        .all(|c| c.is_ascii() && !tables::ascii_control_character(c))
    {
        return Ok(Cow::Borrowed(s));
    }

    // 2.1 Mapping
    let mapped = s
        .chars()
        .map(|c| {
            if tables::non_ascii_space_character(c) {
                ' '
            } else {
                c
            }
        })
        .filter(|&c| !tables::commonly_mapped_to_nothing(c));

    // 2.2 Normalization
    let normalized = mapped.nfkc().collect::<String>();

    // 2.3 Prohibited Output
    let prohibited = normalized.chars().find(|&c| {
        tables::non_ascii_space_character(c) /* C.1.2 */ ||
            tables::ascii_control_character(c) /* C.2.1 */ ||
            tables::non_ascii_control_character(c) /* C.2.2 */ ||
            tables::private_use(c) /* C.3 */ ||
            tables::non_character_code_point(c) /* C.4 */ ||
            tables::surrogate_code(c) /* C.5 */ ||
            tables::inappropriate_for_plain_text(c) /* C.6 */ ||
            tables::inappropriate_for_canonical_representation(c) /* C.7 */ ||
            tables::change_display_properties_or_deprecated(c) /* C.8 */ ||
            tables::tagging_character(c) /* C.9 */
    });
    if let Some(c) = prohibited {
        return Err(Error(ErrorCause::ProhibitedCharacter(c)));
    }

    // 2.4. Bidirectional Characters
    if is_prohibited_bidirectional_text(&normalized) {
        return Err(Error(ErrorCause::ProhibitedBidirectionalText));
    }

    // 2.5 Unassigned Code Points
    let unassigned = normalized
        .chars()
        .find(|&c| tables::unassigned_code_point(c));
    if let Some(c) = unassigned {
        return Err(Error(ErrorCause::ProhibitedCharacter(c)));
    }

    Ok(Cow::Owned(normalized))
}

// RFC3454, 6. Bidirectional Characters
fn is_prohibited_bidirectional_text(s: &str) -> bool {
    if s.contains(tables::bidi_r_or_al) {
        // 2) If a string contains any RandALCat character, the string
        // MUST NOT contain any LCat character.
        if s.contains(tables::bidi_l) {
            return true;
        }

        // 3) If a string contains any RandALCat character, a RandALCat
        // character MUST be the first character of the string, and a
        // RandALCat character MUST be the last character of the string.
        if !tables::bidi_r_or_al(s.chars().next().unwrap())
            || !tables::bidi_r_or_al(s.chars().next_back().unwrap())
        {
            return true;
        }
    }

    false
}

/// Prepares a string with the Nameprep profile of the stringprep algorithm.
///
/// Nameprep is defined in [RFC 3491][].
///
/// [RFC 3491]: https://tools.ietf.org/html/rfc3491
pub fn nameprep(s: &str) -> Result<Cow<'_, str>, Error> {
    // fast path for ascii text
    if s.chars()
        .all(|c| c.is_ascii_lowercase() || c.is_ascii_digit() || c == '.' || c == '-')
    {
        return Ok(Cow::Borrowed(s));
    }

    // 3. Mapping
    let mapped = s
        .chars()
        .filter(|&c| !tables::commonly_mapped_to_nothing(c))
        .flat_map(tables::case_fold_for_nfkc);

    // 4. Normalization
    let normalized = mapped.nfkc().collect::<String>();

    // 5. Prohibited Output
    let prohibited = normalized.chars().find(|&c| {
        tables::non_ascii_space_character(c) /* C.1.2 */ ||
            tables::non_ascii_control_character(c) /* C.2.2 */ ||
            tables::private_use(c) /* C.3 */ ||
            tables::non_character_code_point(c) /* C.4 */ ||
            tables::surrogate_code(c) /* C.5 */ ||
            tables::inappropriate_for_plain_text(c) /* C.6 */ ||
            tables::inappropriate_for_canonical_representation(c) /* C.7 */ ||
            tables::change_display_properties_or_deprecated(c) /* C.9 */ ||
            tables::tagging_character(c) /* C.9 */
    });
    if let Some(c) = prohibited {
        return Err(Error(ErrorCause::ProhibitedCharacter(c)));
    }

    // 6. Bidirectional Characters
    if is_prohibited_bidirectional_text(&normalized) {
        return Err(Error(ErrorCause::ProhibitedBidirectionalText));
    }

    // 7 Unassigned Code Points
    let unassigned = normalized
        .chars()
        .find(|&c| tables::unassigned_code_point(c));
    if let Some(c) = unassigned {
        return Err(Error(ErrorCause::ProhibitedCharacter(c)));
    }

    Ok(Cow::Owned(normalized))
}

/// Prepares a string with the Nodeprep profile of the stringprep algorithm.
///
/// Nameprep is defined in [RFC 3920, Appendix A][].
///
/// [RFC 3920, Appendix A]: https://tools.ietf.org/html/rfc3920#appendix-A
pub fn nodeprep(s: &str) -> Result<Cow<'_, str>, Error> {
    // fast path for common ascii text
    if s.chars()
        .all(|c| matches!(c, '['..='~' | '0'..='9' | '('..='.' | '#'..='%'))
    {
        return Ok(Cow::Borrowed(s));
    }

    // A.3. Mapping
    let mapped = s
        .chars()
        .filter(|&c| !tables::commonly_mapped_to_nothing(c))
        .flat_map(tables::case_fold_for_nfkc);

    // A.4. Normalization
    let normalized = mapped.nfkc().collect::<String>();

    // A.5. Prohibited Output
    let prohibited = normalized.chars().find(|&c| {
        tables::ascii_space_character(c) /* C.1.1 */ ||
            tables::non_ascii_space_character(c) /* C.1.2 */ ||
            tables::ascii_control_character(c) /* C.2.1 */ ||
            tables::non_ascii_control_character(c) /* C.2.2 */ ||
            tables::private_use(c) /* C.3 */ ||
            tables::non_character_code_point(c) /* C.4 */ ||
            tables::surrogate_code(c) /* C.5 */ ||
            tables::inappropriate_for_plain_text(c) /* C.6 */ ||
            tables::inappropriate_for_canonical_representation(c) /* C.7 */ ||
            tables::change_display_properties_or_deprecated(c) /* C.9 */ ||
            tables::tagging_character(c) /* C.9 */ ||
            prohibited_node_character(c)
    });
    if let Some(c) = prohibited {
        return Err(Error(ErrorCause::ProhibitedCharacter(c)));
    }

    // A.6. Bidirectional Characters
    if is_prohibited_bidirectional_text(&normalized) {
        return Err(Error(ErrorCause::ProhibitedBidirectionalText));
    }

    let unassigned = normalized
        .chars()
        .find(|&c| tables::unassigned_code_point(c));
    if let Some(c) = unassigned {
        return Err(Error(ErrorCause::ProhibitedCharacter(c)));
    }

    Ok(Cow::Owned(normalized))
}

// Additional characters not allowed in JID nodes, by RFC3920.
fn prohibited_node_character(c: char) -> bool {
    matches!(c, '"' | '&' | '\'' | '/' | ':' | '<' | '>' | '@')
}

/// Prepares a string with the Resourceprep profile of the stringprep algorithm.
///
/// Nameprep is defined in [RFC 3920, Appendix B][].
///
/// [RFC 3920, Appendix B]: https://tools.ietf.org/html/rfc3920#appendix-B
pub fn resourceprep(s: &str) -> Result<Cow<'_, str>, Error> {
    // fast path for ascii text
    if s.chars().all(|c| matches!(c, ' '..='~')) {
        return Ok(Cow::Borrowed(s));
    }

    // B.3. Mapping
    let mapped = s
        .chars()
        .filter(|&c| !tables::commonly_mapped_to_nothing(c))
        .collect::<String>();

    // B.4. Normalization
    let normalized = mapped.nfkc().collect::<String>();

    // B.5. Prohibited Output
    let prohibited = normalized.chars().find(|&c| {
        tables::non_ascii_space_character(c) /* C.1.2 */ ||
            tables::ascii_control_character(c) /* C.2.1 */ ||
            tables::non_ascii_control_character(c) /* C.2.2 */ ||
            tables::private_use(c) /* C.3 */ ||
            tables::non_character_code_point(c) /* C.4 */ ||
            tables::surrogate_code(c) /* C.5 */ ||
            tables::inappropriate_for_plain_text(c) /* C.6 */ ||
            tables::inappropriate_for_canonical_representation(c) /* C.7 */ ||
            tables::change_display_properties_or_deprecated(c) /* C.9 */ ||
            tables::tagging_character(c) /* C.9 */
    });
    if let Some(c) = prohibited {
        return Err(Error(ErrorCause::ProhibitedCharacter(c)));
    }

    // B.6. Bidirectional Characters
    if is_prohibited_bidirectional_text(&normalized) {
        return Err(Error(ErrorCause::ProhibitedBidirectionalText));
    }

    let unassigned = normalized
        .chars()
        .find(|&c| tables::unassigned_code_point(c));
    if let Some(c) = unassigned {
        return Err(Error(ErrorCause::ProhibitedCharacter(c)));
    }

    Ok(Cow::Owned(normalized))
}

/// Prepares a string according to the procedures described in Section 7 of
/// [ITU-T Recommendation X.520 (2019)](https://www.itu.int/rec/T-REC-X.520-201910-I/en).
///
/// Note that this function does _not_ remove leading, trailing, or inner
/// spaces as described in Section 7.6, because the characters needing removal
/// will vary across the matching rules and ASN.1 syntaxes used.
pub fn x520prep(s: &str, case_fold: bool) -> Result<Cow<'_, str>, Error> {
    if s.is_empty() {
        return Err(Error(ErrorCause::EmptyString));
    }
    if s.chars()
        .all(|c| matches!(c, ' '..='~') && (!case_fold || c.is_ascii_lowercase()))
    {
        return Ok(Cow::Borrowed(s));
    }

    // 1. Transcode
    // Already done because &str is enforced to be Unicode.

    // 2. Map
    let mapped = s
        .chars()
        .filter(|&c| !tables::x520_mapped_to_nothing(c))
        .map(|c| {
            if tables::x520_mapped_to_space(c) {
                ' '
            } else {
                c
            }
        });

    // 3. Normalize
    let normalized = if case_fold {
        mapped
            .flat_map(tables::case_fold_for_nfkc)
            .collect::<String>()
    } else {
        mapped.nfkc().collect::<String>()
    };

    // 4. Prohibit
    let prohibited = normalized.chars().find(
        |&c| {
            tables::unassigned_code_point(c)
                || tables::private_use(c)
                || tables::non_character_code_point(c)
                || tables::surrogate_code(c)
                || c == '\u{FFFD}'
        }, // REPLACEMENT CHARACTER
    );
    if let Some(c) = prohibited {
        return Err(Error(ErrorCause::ProhibitedCharacter(c)));
    }
    // From ITU-T Recommendation X.520, Section 7.4:
    // "The first code point of a string is prohibited from being a combining character."
    match s.chars().next() {
        Some(c) => {
            if c.general_category_group() == GeneralCategoryGroup::Mark {
                return Err(Error(ErrorCause::StartsWithCombiningCharacter));
            }
        }
        None => return Err(Error(ErrorCause::EmptyString)),
    }

    // 5. Check bidi
    // From ITU-T Recommendation X.520, Section 7.4:
    // "There are no bidirectional restrictions. The output string is the input string."
    // So there is nothing to do for this step.

    // 6. Insignificant Character Removal
    // Done in calling functions.

    Ok(normalized.into())
}

#[cfg(test)]
mod test {
    use super::*;

    fn assert_prohibited_character<T>(result: Result<T, Error>) {
        match result {
            Err(Error(ErrorCause::ProhibitedCharacter(_))) => (),
            _ => panic!(),
        }
    }

    fn assert_starts_with_combining_char<T>(result: Result<T, Error>) {
        match result {
            Err(Error(ErrorCause::StartsWithCombiningCharacter)) => (),
            _ => panic!(),
        }
    }

    // RFC4013, 3. Examples
    #[test]
    fn saslprep_examples() {
        assert_prohibited_character(saslprep("\u{0007}"));
    }

    #[test]
    fn nodeprep_examples() {
        assert_prohibited_character(nodeprep(" "));
        assert_prohibited_character(nodeprep("\u{00a0}"));
        assert_prohibited_character(nodeprep("foo@bar"));
    }

    #[test]
    fn resourceprep_examples() {
        assert_eq!("foo@bar", resourceprep("foo@bar").unwrap());
    }

    #[test]
    fn x520prep_examples() {
        assert_eq!(x520prep("foo@bar", true).unwrap(), "foo@bar");
        assert_eq!(
            x520prep("J.\u{FE00} \u{9}W. \u{B}wuz h\u{0115}re", false).unwrap(),
            "J.  W.  wuz h\u{0115}re"
        );
        assert_eq!(
            x520prep("J.\u{FE00} \u{9}W. \u{B}wuz h\u{0115}re", true).unwrap(),
            "j.  w.  wuz h\u{0115}re"
        );
        assert_eq!(x520prep("UPPERCASED", true).unwrap(), "uppercased");
        assert_starts_with_combining_char(x520prep("\u{0306}hello", true));
    }

    #[test]
    fn ascii_optimisations() {
        if let Cow::Owned(_) = nodeprep("nodepart").unwrap() {
            panic!("“nodepart” should get optimised as ASCII");
        }
        if let Cow::Owned(_) = nameprep("domainpart.example").unwrap() {
            panic!("“domainpart.example” should get optimised as ASCII");
        }
        if let Cow::Owned(_) = resourceprep("resourcepart").unwrap() {
            panic!("“resourcepart” should get optimised as ASCII");
        }
    }
}