Skip to content

Commit b5b9850

Browse files
sfacklersfackler
committed
cleanup
1 parent f793c34 commit b5b9850

File tree

2 files changed

+237
-194
lines changed

2 files changed

+237
-194
lines changed

‎src/lib.rs

Lines changed: 89 additions & 96 deletions
Original file line numberDiff line numberDiff line change
@@ -1,15 +1,15 @@
11
//! An implementation of the "stringprep" algorithm defined in [RFC 3454][].
22
//!
33
//! [RFC 3454]: https://tools.ietf.org/html/rfc3454
4-
#![doc(html_root_url="https://docs.rs/stringprep/0.1.2")]
4+
#![doc(html_root_url = "https://docs.rs/stringprep/0.1.2")]
55
#![warn(missing_docs)]
6+
extern crate finl_unicode;
67
extern crate unicode_bidi;
78
extern crate unicode_normalization;
8-
extern crate finl_unicode;
99

10+
use finl_unicode::categories::CharacterCategories;
1011
use std::borrow::Cow;
1112
use std::fmt;
12-
use finl_unicode::categories::CharacterCategories;
1313
use unicode_normalization::UnicodeNormalization;
1414

1515
mod rfc3454;
@@ -37,7 +37,9 @@ impl fmt::Display for Error {
3737
match self.0 {
3838
ErrorCause::ProhibitedCharacter(c) => write!(fmt, "prohibited character `{}`", c),
3939
ErrorCause::ProhibitedBidirectionalText => write!(fmt, "prohibited bidirectional text"),
40-
ErrorCause::StartsWithCombiningCharacter => write!(fmt, "starts with combining character"),
40+
ErrorCause::StartsWithCombiningCharacter => {
41+
write!(fmt, "starts with combining character")
42+
}
4143
ErrorCause::EmptyString => write!(fmt, "empty string"),
4244
}
4345
}
@@ -59,22 +61,23 @@ pub fn saslprep(s: &str) -> Result<Cow<'_, str>, Error> {
5961
}
6062

6163
// 2.1 Mapping
62-
let mapped = s.chars()
63-
.map(|c| if tables::non_ascii_space_character(c) {
64-
' '
65-
} else {
66-
c
67-
})
64+
let mapped = s
65+
.chars()
66+
.map(|c| {
67+
if tables::non_ascii_space_character(c) {
68+
' '
69+
} else {
70+
c
71+
}
72+
})
6873
.filter(|&c| !tables::commonly_mapped_to_nothing(c));
6974

7075
// 2.2 Normalization
7176
let normalized = mapped.nfkc().collect::<String>();
7277

7378
// 2.3 Prohibited Output
74-
let prohibited = normalized
75-
.chars()
76-
.find(|&c| {
77-
tables::non_ascii_space_character(c) /* C.1.2 */ ||
79+
let prohibited = normalized.chars().find(|&c| {
80+
tables::non_ascii_space_character(c) /* C.1.2 */ ||
7881
tables::ascii_control_character(c) /* C.2.1 */ ||
7982
tables::non_ascii_control_character(c) /* C.2.2 */ ||
8083
tables::private_use(c) /* C.3 */ ||
@@ -84,7 +87,7 @@ pub fn saslprep(s: &str) -> Result<Cow<'_, str>, Error> {
8487
tables::inappropriate_for_canonical_representation(c) /* C.7 */ ||
8588
tables::change_display_properties_or_deprecated(c) /* C.8 */ ||
8689
tables::tagging_character(c) /* C.9 */
87-
});
90+
});
8891
if let Some(c) = prohibited {
8992
return Err(Error(ErrorCause::ProhibitedCharacter(c)));
9093
}
@@ -117,8 +120,9 @@ fn is_prohibited_bidirectional_text(s: &str) -> bool {
117120
// 3) If a string contains any RandALCat character, a RandALCat
118121
// character MUST be the first character of the string, and a
119122
// RandALCat character MUST be the last character of the string.
120-
if !tables::bidi_r_or_al(s.chars().next().unwrap()) ||
121-
!tables::bidi_r_or_al(s.chars().next_back().unwrap()) {
123+
if !tables::bidi_r_or_al(s.chars().next().unwrap())
124+
|| !tables::bidi_r_or_al(s.chars().next_back().unwrap())
125+
{
122126
return true;
123127
}
124128
}
@@ -140,18 +144,17 @@ pub fn nameprep(s: &str) -> Result<Cow<'_, str>, Error> {
140144
}
141145

142146
// 3. Mapping
143-
let mapped = s.chars()
147+
let mapped = s
148+
.chars()
144149
.filter(|&c| !tables::commonly_mapped_to_nothing(c))
145150
.flat_map(tables::case_fold_for_nfkc);
146151

147152
// 4. Normalization
148153
let normalized = mapped.nfkc().collect::<String>();
149154

150155
// 5. Prohibited Output
151-
let prohibited = normalized
152-
.chars()
153-
.find(|&c| {
154-
tables::non_ascii_space_character(c) /* C.1.2 */ ||
156+
let prohibited = normalized.chars().find(|&c| {
157+
tables::non_ascii_space_character(c) /* C.1.2 */ ||
155158
tables::non_ascii_control_character(c) /* C.2.2 */ ||
156159
tables::private_use(c) /* C.3 */ ||
157160
tables::non_character_code_point(c) /* C.4 */ ||
@@ -160,7 +163,7 @@ pub fn nameprep(s: &str) -> Result<Cow<'_, str>, Error> {
160163
tables::inappropriate_for_canonical_representation(c) /* C.7 */ ||
161164
tables::change_display_properties_or_deprecated(c) /* C.9 */ ||
162165
tables::tagging_character(c) /* C.9 */
163-
});
166+
});
164167
if let Some(c) = prohibited {
165168
return Err(Error(ErrorCause::ProhibitedCharacter(c)));
166169
}
@@ -195,18 +198,17 @@ pub fn nodeprep(s: &str) -> Result<Cow<'_, str>, Error> {
195198
}
196199

197200
// A.3. Mapping
198-
let mapped = s.chars()
201+
let mapped = s
202+
.chars()
199203
.filter(|&c| !tables::commonly_mapped_to_nothing(c))
200204
.flat_map(tables::case_fold_for_nfkc);
201205

202206
// A.4. Normalization
203207
let normalized = mapped.nfkc().collect::<String>();
204208

205209
// A.5. Prohibited Output
206-
let prohibited = normalized
207-
.chars()
208-
.find(|&c| {
209-
tables::ascii_space_character(c) /* C.1.1 */ ||
210+
let prohibited = normalized.chars().find(|&c| {
211+
tables::ascii_space_character(c) /* C.1.1 */ ||
210212
tables::non_ascii_space_character(c) /* C.1.2 */ ||
211213
tables::ascii_control_character(c) /* C.2.1 */ ||
212214
tables::non_ascii_control_character(c) /* C.2.2 */ ||
@@ -218,7 +220,7 @@ pub fn nodeprep(s: &str) -> Result<Cow<'_, str>, Error> {
218220
tables::change_display_properties_or_deprecated(c) /* C.9 */ ||
219221
tables::tagging_character(c) /* C.9 */ ||
220222
prohibited_node_character(c)
221-
});
223+
});
222224
if let Some(c) = prohibited {
223225
return Err(Error(ErrorCause::ProhibitedCharacter(c)));
224226
}
@@ -240,10 +242,7 @@ pub fn nodeprep(s: &str) -> Result<Cow<'_, str>, Error> {
240242

241243
// Additional characters not allowed in JID nodes, by RFC3920.
242244
fn prohibited_node_character(c: char) -> bool {
243-
match c {
244-
'"' | '&' | '\'' | '/' | ':' | '<' | '>' | '@' => true,
245-
_ => false
246-
}
245+
matches!(c, '"' | '&' | '\'' | '/' | ':' | '<' | '>' | '@')
247246
}
248247

249248
/// Prepares a string with the Resourceprep profile of the stringprep algorithm.
@@ -253,25 +252,22 @@ fn prohibited_node_character(c: char) -> bool {
253252
/// [RFC 3920, Appendix B]: https://tools.ietf.org/html/rfc3920#appendix-B
254253
pub fn resourceprep(s: &str) -> Result<Cow<'_, str>, Error> {
255254
// fast path for ascii text
256-
if s.chars()
257-
.all(|c| matches!(c, ' '..='~'))
258-
{
255+
if s.chars().all(|c| matches!(c, ' '..='~')) {
259256
return Ok(Cow::Borrowed(s));
260257
}
261258

262259
// B.3. Mapping
263-
let mapped = s.chars()
260+
let mapped = s
261+
.chars()
264262
.filter(|&c| !tables::commonly_mapped_to_nothing(c))
265263
.collect::<String>();
266264

267265
// B.4. Normalization
268266
let normalized = mapped.nfkc().collect::<String>();
269267

270268
// B.5. Prohibited Output
271-
let prohibited = normalized
272-
.chars()
273-
.find(|&c| {
274-
tables::non_ascii_space_character(c) /* C.1.2 */ ||
269+
let prohibited = normalized.chars().find(|&c| {
270+
tables::non_ascii_space_character(c) /* C.1.2 */ ||
275271
tables::ascii_control_character(c) /* C.2.1 */ ||
276272
tables::non_ascii_control_character(c) /* C.2.2 */ ||
277273
tables::private_use(c) /* C.3 */ ||
@@ -281,7 +277,7 @@ pub fn resourceprep(s: &str) -> Result<Cow<'_, str>, Error> {
281277
tables::inappropriate_for_canonical_representation(c) /* C.7 */ ||
282278
tables::change_display_properties_or_deprecated(c) /* C.9 */ ||
283279
tables::tagging_character(c) /* C.9 */
284-
});
280+
});
285281
if let Some(c) = prohibited {
286282
return Err(Error(ErrorCause::ProhibitedCharacter(c)));
287283
}
@@ -301,48 +297,36 @@ pub fn resourceprep(s: &str) -> Result<Cow<'_, str>, Error> {
301297
Ok(Cow::Owned(normalized))
302298
}
303299

304-
/// Determines if `c` is to be removed according to section 7.2 of
305-
/// [ITU-T Recommendation X.520 (2019)](https://www.itu.int/rec/T-REC-X.520-201910-I/en).
306-
fn x520_mapped_to_nothing(c: char) -> bool {
307-
match c {
308-
'\u{00AD}' | '\u{1806}' | '\u{034F}' | '\u{180B}'..='\u{180D}' |
309-
'\u{FE00}'..='\u{FE0F}' | '\u{FFFC}' | '\u{200B}' => true,
310-
// Technically control characters, but mapped to whitespace in X.520.
311-
'\u{09}' | '\u{0A}'..='\u{0D}' | '\u{85}' => false,
312-
_ => c.is_control(),
313-
}
314-
}
315-
316-
/// Determines if `c` is to be replaced by SPACE (0x20) according to section 7.2 of
317-
/// [ITU-T Recommendation X.520 (2019)](https://www.itu.int/rec/T-REC-X.520-201910-I/en).
318-
fn x520_mapped_to_space(c: char) -> bool {
319-
match c {
320-
'\u{09}' | '\u{0A}'..='\u{0D}' | '\u{85}' => true,
321-
_ => c.is_separator(),
322-
}
323-
}
324-
325300
/// Prepares a string according to the procedures described in Section 7 of
326301
/// [ITU-T Recommendation X.520 (2019)](https://www.itu.int/rec/T-REC-X.520-201910-I/en).
327302
///
328303
/// Note that this function does _not_ remove leading, trailing, or inner
329304
/// spaces as described in Section 7.6, because the characters needing removal
330305
/// will vary across the matching rules and ASN.1 syntaxes used.
331306
pub fn x520prep(s: &str, case_fold: bool) -> Result<Cow<'_, str>, Error> {
332-
if s.len() == 0 {
307+
if s.is_empty() {
333308
return Err(Error(ErrorCause::EmptyString));
334309
}
335-
if s.chars().all(|c| matches!(c, ' '..='~') && (!case_fold || c.is_ascii_lowercase())) {
310+
if s.chars()
311+
.all(|c| matches!(c, ' '..='~') && (!case_fold || c.is_ascii_lowercase()))
312+
{
336313
return Ok(Cow::Borrowed(s));
337314
}
338315

339316
// 1. Transcode
340317
// Already done because &str is enforced to be Unicode.
341318

342319
// 2. Map
343-
let mapped = s.chars()
344-
.filter(|&c| !x520_mapped_to_nothing(c))
345-
.map(|c| if x520_mapped_to_space(c) { ' ' } else { c });
320+
let mapped = s
321+
.chars()
322+
.filter(|&c| !tables::x520_mapped_to_nothing(c))
323+
.map(|c| {
324+
if tables::x520_mapped_to_space(c) {
325+
' '
326+
} else {
327+
c
328+
}
329+
});
346330

347331
// 3. Normalize
348332
let normalized = if case_fold {
@@ -354,24 +338,27 @@ pub fn x520prep(s: &str, case_fold: bool) -> Result<Cow<'_, str>, Error> {
354338
};
355339

356340
// 4. Prohibit
357-
let prohibited = normalized.chars().find(|&c| tables::unassigned_code_point(c)
358-
|| tables::private_use(c)
359-
|| tables::non_character_code_point(c)
360-
|| tables::surrogate_code(c)
361-
|| c == '\u{FFFD}' // REPLACEMENT CHARACTER
341+
let prohibited = normalized.chars().find(
342+
|&c| {
343+
tables::unassigned_code_point(c)
344+
|| tables::private_use(c)
345+
|| tables::non_character_code_point(c)
346+
|| tables::surrogate_code(c)
347+
|| c == '\u{FFFD}'
348+
}, // REPLACEMENT CHARACTER
362349
);
363350
if let Some(c) = prohibited {
364351
return Err(Error(ErrorCause::ProhibitedCharacter(c)));
365352
}
366353
// From ITU-T Recommendation X.520, Section 7.4:
367354
// "The first code point of a string is prohibited from being a combining character."
368-
let first_char = s.chars().next();
369-
if let Some(c) = first_char {
370-
if c.is_mark() {
371-
return Err(Error(ErrorCause::StartsWithCombiningCharacter));
355+
match s.chars().next() {
356+
Some(c) => {
357+
if c.is_mark() {
358+
return Err(Error(ErrorCause::StartsWithCombiningCharacter));
359+
}
372360
}
373-
} else {
374-
return Err(Error(ErrorCause::EmptyString));
361+
None => return Err(Error(ErrorCause::EmptyString)),
375362
}
376363

377364
// 5. Check bidi
@@ -389,32 +376,32 @@ pub fn x520prep(s: &str, case_fold: bool) -> Result<Cow<'_, str>, Error> {
389376
mod test {
390377
use super::*;
391378

392-
fn assert_prohibited_character<T>(result: Result<T, Error>) {
393-
match result {
394-
Err(Error(ErrorCause::ProhibitedCharacter(_))) => (),
395-
_ => assert!(false)
396-
}
397-
}
379+
fn assert_prohibited_character<T>(result: Result<T, Error>) {
380+
match result {
381+
Err(Error(ErrorCause::ProhibitedCharacter(_))) => (),
382+
_ => panic!(),
383+
}
384+
}
398385

399386
fn assert_starts_with_combining_char<T>(result: Result<T, Error>) {
400-
match result {
401-
Err(Error(ErrorCause::StartsWithCombiningCharacter)) => (),
402-
_ => assert!(false)
403-
}
404-
}
387+
match result {
388+
Err(Error(ErrorCause::StartsWithCombiningCharacter)) => (),
389+
_ => panic!(),
390+
}
391+
}
405392

406393
// RFC4013, 3. Examples
407394
#[test]
408395
fn saslprep_examples() {
409-
assert_prohibited_character(saslprep("\u{0007}"));
396+
assert_prohibited_character(saslprep("\u{0007}"));
410397
}
411398

412-
#[test]
413-
fn nodeprep_examples() {
399+
#[test]
400+
fn nodeprep_examples() {
414401
assert_prohibited_character(nodeprep(" "));
415402
assert_prohibited_character(nodeprep("\u{00a0}"));
416403
assert_prohibited_character(nodeprep("foo@bar"));
417-
}
404+
}
418405

419406
#[test]
420407
fn resourceprep_examples() {
@@ -424,8 +411,14 @@ mod test {
424411
#[test]
425412
fn x520prep_examples() {
426413
assert_eq!(x520prep("foo@bar", true).unwrap(), "foo@bar");
427-
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");
428-
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");
414+
assert_eq!(
415+
x520prep("J.\u{FE00} \u{9}W. \u{B}wuz h\u{0115}re", false).unwrap(),
416+
"J. W. wuz h\u{0115}re"
417+
);
418+
assert_eq!(
419+
x520prep("J.\u{FE00} \u{9}W. \u{B}wuz h\u{0115}re", true).unwrap(),
420+
"j. w. wuz h\u{0115}re"
421+
);
429422
assert_eq!(x520prep("UPPERCASED", true).unwrap(), "uppercased");
430423
assert_starts_with_combining_char(x520prep("\u{0306}hello", true));
431424
}

0 commit comments

Comments
 (0)