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
//! Tokenizer is a type used for parsing a `&str` into slices in a way not easily
//! supported by the `Peekable<Chars>` iterator. The basic procedure is as follows:
//!
//! * Use `next` and `peek` to query the iterator in the usual way.
//! * Detect the beginning of a token and get its index from `mark`.
//! * Skip just past the end of the token using `next`, `skip`, etc.
//! * Use `token` to retrieve a slice from the mark to the index.
use core::iter::Peekable;
use core::str::Chars;
/// The Tokenizer type. See the module-level documentation.
#[derive(Clone, Debug)]
pub struct Tokenizer<'a> {
// The string being parsed.
input: &'a str,
// The starting index of the next character.
index: usize,
// The iterator used to extract characters from the input
chars: Peekable<Chars<'a>>,
}
impl<'a> Tokenizer<'a> {
/// Creates a new tokenizer for the given input.
pub fn new(input: &'a str) -> Self {
Self {
input,
index: 0,
chars: input.chars().peekable(),
}
}
/// Returns the entire input.
#[allow(dead_code)]
pub fn input(&self) -> &str {
self.input
}
// Returns the remainder of the input starting at the index.
pub fn as_str(&self) -> &str {
&self.input[self.index..]
}
// Returns the current index as a mark, for later use.
pub fn mark(&self) -> usize {
self.index
}
// Returns the remainder of the input starting at the given mark.
#[allow(dead_code)]
pub fn tail(&self, mark: usize) -> &str {
&self.input[mark..]
}
/// Returns the next character and updates the index.
#[allow(clippy::should_implement_trait)]
pub fn next(&mut self) -> Option<char> {
let ch = self.chars.next();
if let Some(c) = ch {
self.index += c.len_utf8();
}
ch
}
/// Returns the next character without updating the index.
pub fn peek(&mut self) -> Option<char> {
self.chars.peek().copied()
}
/// Get the token between the mark and the index. Returns "" if we're at the
/// end or mark == index.
pub fn token(&self, mark: usize) -> &str {
assert!(mark <= self.index, "mark follows index");
&self.input[mark..self.index]
}
/// Get the token between the mark and the index. Returns "" if
/// mark == index.
#[allow(dead_code)]
pub fn token2(&self, mark: usize, index: usize) -> &str {
assert!(mark <= index, "mark follows index");
&self.input[mark..index]
}
/// Resets the index to the given mark. For internal use only.
fn reset_to(&mut self, mark: usize) {
self.index = mark;
self.chars = self.input[self.index..].chars().peekable();
}
/// Is the next character the given character? Does not update the index.
pub fn is(&mut self, ch: char) -> bool {
if let Some(c) = self.chars.peek() {
*c == ch
} else {
false
}
}
/// Is the predicate true for the next character? Does not update the index.
pub fn has<P>(&mut self, predicate: P) -> bool
where
P: Fn(char) -> bool,
{
if let Some(ch) = self.chars.peek().copied() {
predicate(ch)
} else {
false
}
}
/// Is there anything left in the input?
pub fn at_end(&mut self) -> bool {
// &mut is needed because peek() can mutate the iterator
self.chars.peek().is_none()
}
/// Skip over the next character, updating the index. This is equivalent to
/// `next`, but communicates better.
pub fn skip(&mut self) {
self.next();
}
/// Skip over the given character, updating the index. This is equivalent to
/// `next`, but communicates better. Panics if the character is not matched.
pub fn skip_char(&mut self, ch: char) {
assert!(self.is(ch));
self.next();
}
/// Skips the given number of characters, updating the index.
/// It is not an error if the iterator doesn't contain that many.
pub fn skip_over(&mut self, num_chars: usize) {
for _ in 0..num_chars {
self.next();
}
}
/// Skips over characters while the predicate is true. Updates the index.
pub fn skip_while<P>(&mut self, predicate: P)
where
P: Fn(char) -> bool,
{
while let Some(ch) = self.chars.peek().copied() {
if predicate(ch) {
self.next();
} else {
break;
}
}
}
/// Parses a backslash-escape and returns its value. If the escape is valid,
/// the value will be the substituted character. If the escape is not valid,
/// it will be the single character following the backslash. Either way, the
/// the index will point at what's next. If there's nothing following the backslash,
/// return the backslash.
pub fn backslash_subst(&mut self) -> char {
// FIRST, skip the backslash.
self.skip_char('\\');
let start = self.mark(); // Mark the character following the backslash.
// NEXT, get the next character.
if let Some(c) = self.next() {
// FIRST, match the character.
match c {
// Single character escapes
'a' => '\x07', // Audible Alarm
'b' => '\x08', // Backspace
'f' => '\x0c', // Form Feed
'n' => '\n', // New Line
'r' => '\r', // Carriage Return
't' => '\t', // Tab
'v' => '\x0b', // Vertical Tab
// 1 to 3 octal digits
'0'..='7' => {
// Note: only works because these digits are single bytes.
// TODO: count instead.
while self.has(|ch| ch.is_digit(8)) && self.index - start < 3 {
self.next();
}
let octal = &self.input[start..self.index];
let val = u8::from_str_radix(octal, 8).map_err(|_| ()).unwrap();
val as char
}
// \xhh, \uhhhh, \Uhhhhhhhh
'x' | 'u' | 'U' => {
let mark = self.mark();
let max = match c {
'x' => 2,
'u' => 4,
'U' => 8,
_ => unreachable!(),
};
// Note: only works because these digits are single bytes.
// TODO: count instead.
while self.has(|ch| ch.is_ascii_hexdigit()) && self.index - mark < max {
self.next();
}
if self.index == mark {
return c;
}
let hex = &self.input[mark..self.index];
let val = u32::from_str_radix(hex, 16).map_err(|_| ()).unwrap();
if let Some(ch) = char::from_u32(val) {
ch
} else {
self.reset_to(mark);
c
}
}
// Arbitrary single characters
_ => c,
}
} else {
// Return the backslash; no escape, since no following character.
'\\'
}
}
}
#[cfg(test)]
mod tests {
use crate::util;
use super::*;
#[test]
fn test_basics() {
// Create the iterator
let mut ptr = Tokenizer::new("abc");
// Initial state
assert_eq!(ptr.input(), "abc");
assert_eq!(ptr.as_str(), "abc");
assert_eq!(ptr.peek(), Some('a'));
}
#[test]
fn test_next() {
// Create the iterator
let mut ptr = Tokenizer::new("abc");
assert_eq!(ptr.next(), Some('a'));
assert_eq!(ptr.as_str(), "bc");
assert_eq!(ptr.next(), Some('b'));
assert_eq!(ptr.as_str(), "c");
assert_eq!(ptr.next(), Some('c'));
assert_eq!(ptr.as_str(), "");
assert_eq!(ptr.next(), None);
}
#[test]
fn test_token() {
// Create the iterator
let mut ptr = Tokenizer::new("abcdef");
ptr.next();
ptr.next();
assert_eq!(ptr.as_str(), "cdef");
let start = ptr.mark();
ptr.next();
ptr.next();
assert_eq!(ptr.token(start), "cd");
assert_eq!(ptr.as_str(), "ef");
let ptr = Tokenizer::new("abc");
let start = ptr.mark();
assert_eq!(ptr.token(start), "");
}
#[test]
fn test_peek() {
let mut ptr = Tokenizer::new("abcdef");
assert_eq!(ptr.peek(), Some('a'));
assert_eq!(ptr.as_str(), "abcdef");
ptr.next();
ptr.next();
assert_eq!(ptr.peek(), Some('c'));
assert_eq!(ptr.as_str(), "cdef");
}
#[test]
fn test_reset_to() {
let mut ptr = Tokenizer::new("abcdef");
ptr.next();
ptr.next();
ptr.reset_to(0);
assert_eq!(ptr.as_str(), "abcdef");
assert_eq!(ptr.peek(), Some('a'));
ptr.next();
ptr.next();
let start = ptr.mark();
ptr.next();
ptr.next();
ptr.reset_to(start);
assert_eq!(ptr.as_str(), "cdef");
assert_eq!(ptr.peek(), Some('c'));
}
#[test]
fn test_is() {
let mut ptr = Tokenizer::new("a");
assert!(ptr.is('a'));
assert!(!ptr.is('b'));
ptr.next();
assert!(!ptr.is('a'));
}
#[test]
fn test_has() {
let mut ptr = Tokenizer::new("a1");
assert!(ptr.has(util::is_alphabetic));
ptr.skip();
assert!(!ptr.has(util::is_alphabetic));
ptr.skip();
assert!(!ptr.has(util::is_alphabetic));
}
#[test]
fn test_skip() {
let mut ptr = Tokenizer::new("abc");
assert_eq!(ptr.peek(), Some('a'));
assert_eq!(ptr.as_str(), "abc");
ptr.skip();
assert_eq!(ptr.peek(), Some('b'));
assert_eq!(ptr.as_str(), "bc");
ptr.skip();
assert_eq!(ptr.peek(), Some('c'));
assert_eq!(ptr.as_str(), "c");
ptr.skip();
assert_eq!(ptr.peek(), None);
assert_eq!(ptr.as_str(), "");
}
#[test]
fn test_skip_over() {
let mut ptr = Tokenizer::new("abc");
ptr.skip_over(2);
assert_eq!(ptr.peek(), Some('c'));
assert_eq!(ptr.as_str(), "c");
let mut ptr = Tokenizer::new("abc");
ptr.skip_over(3);
assert_eq!(ptr.peek(), None);
assert_eq!(ptr.as_str(), "");
let mut ptr = Tokenizer::new("abc");
ptr.skip_over(6);
assert_eq!(ptr.peek(), None);
assert_eq!(ptr.as_str(), "");
}
#[test]
fn test_skip_while() {
let mut ptr = Tokenizer::new("aaabc");
ptr.skip_while(|ch| ch == 'a');
assert_eq!(ptr.peek(), Some('b'));
assert_eq!(ptr.as_str(), "bc");
let mut ptr = Tokenizer::new("aaa");
ptr.skip_while(|ch| ch == 'a');
assert_eq!(ptr.peek(), None);
assert_eq!(ptr.as_str(), "");
}
#[test]
fn test_backslash_subst_single() {
// Single Character Escapes
assert_eq!(bsubst("\\a-"), ('\x07', Some('-')));
assert_eq!(bsubst("\\b-"), ('\x08', Some('-')));
assert_eq!(bsubst("\\f-"), ('\x0c', Some('-')));
assert_eq!(bsubst("\\n-"), ('\n', Some('-')));
assert_eq!(bsubst("\\r-"), ('\r', Some('-')));
assert_eq!(bsubst("\\t-"), ('\t', Some('-')));
assert_eq!(bsubst("\\v-"), ('\x0b', Some('-')));
}
#[test]
fn test_backslash_subst_octal() {
// Octals
assert_eq!(bsubst("\\1-"), ('\x01', Some('-')));
assert_eq!(bsubst("\\17-"), ('\x0f', Some('-')));
assert_eq!(bsubst("\\177-"), ('\x7f', Some('-')));
assert_eq!(bsubst("\\1772-"), ('\x7f', Some('2')));
assert_eq!(bsubst("\\18-"), ('\x01', Some('8')));
assert_eq!(bsubst("\\8-"), ('8', Some('-')));
}
#[test]
fn test_backslash_subst_hex2() {
// \xhh: One or two hex digits.
assert_eq!(bsubst("\\x-"), ('x', Some('-')));
assert_eq!(bsubst("\\x1-"), ('\x01', Some('-')));
assert_eq!(bsubst("\\x7f-"), ('\x7f', Some('-')));
}
#[test]
fn test_backslash_subst_hex4() {
// \uhhhh: 1-4 hex digits.
assert_eq!(bsubst("\\u-"), ('u', Some('-')));
assert_eq!(bsubst("\\u7-"), ('\x07', Some('-')));
assert_eq!(bsubst("\\u77-"), ('w', Some('-')));
assert_eq!(bsubst("\\u077-"), ('w', Some('-')));
assert_eq!(bsubst("\\u0077-"), ('w', Some('-')));
assert_eq!(bsubst("\\u00077-"), ('\x07', Some('7')));
}
#[test]
fn test_backslash_subst_hex8() {
// \Uhhhhhhhh: 1-8 hex digits.
assert_eq!(bsubst("\\U-"), ('U', Some('-')));
assert_eq!(bsubst("\\U7-"), ('\x07', Some('-')));
assert_eq!(bsubst("\\U77-"), ('w', Some('-')));
assert_eq!(bsubst("\\U077-"), ('w', Some('-')));
assert_eq!(bsubst("\\U0077-"), ('w', Some('-')));
assert_eq!(bsubst("\\U00077-"), ('w', Some('-')));
assert_eq!(bsubst("\\U000077-"), ('w', Some('-')));
assert_eq!(bsubst("\\U0000077-"), ('w', Some('-')));
assert_eq!(bsubst("\\U00000077-"), ('w', Some('-')));
assert_eq!(bsubst("\\U000000077-"), ('\x07', Some('7')));
}
#[test]
fn test_backslash_subst_other() {
// Arbitrary Character
assert_eq!(bsubst("\\*-"), ('*', Some('-')));
// backslash only
assert_eq!(bsubst("\\"), ('\\', None));
}
fn bsubst(input: &str) -> (char, Option<char>) {
let mut ctx = Tokenizer::new(input);
(ctx.backslash_subst(), ctx.as_str().chars().next())
}
}