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
#[derive(Parser)]
#[grammar = "tokens/parse.pest"]
pub struct ExprParser;
use std::borrow::Cow;
use pest::Parser;
#[derive(Debug, Clone, Eq, PartialEq)]
pub enum TokenKind {
Ident,
NonNegativeDecimal(u64),
Decimal(i64),
SubscriptOpen,
SubscriptClose,
TupleOpen,
TupleClose,
CurlyOpen,
CurlyClose,
FieldAccess,
Assign,
Colon,
Asterix,
Char(char),
String(String),
Range(bool),
Comma,
InvalidToken,
}
#[derive(Debug, Clone, Eq, PartialEq)]
pub struct Token<'a> {
pub kind: TokenKind,
pub text: Cow<'a, str>,
pub space_diff: usize,
}
impl<'a> Token<'a> {
pub fn new_owned(s: String) -> Self {
Token {
kind: TokenKind::Ident,
text: Cow::Owned(s),
space_diff: 0,
}
}
pub fn new_borrowed(kind: TokenKind, s: &'static str) -> Self {
Token {
kind,
text: Cow::from(s),
space_diff: 0,
}
}
pub fn clone_owned(&self) -> Token<'static> {
Token {
kind: self.kind.clone(),
text: Cow::Owned(String::from(self.text.as_ref())),
space_diff: self.space_diff,
}
}
pub fn similar(&self, token: &Token) -> bool {
if self.kind != token.kind {
return false;
}
let mut a = self.text.split_whitespace();
let mut b = token.text.split_whitespace();
a.next() == b.next()
}
pub fn is_prefix_of(&self, token: &Token) -> bool {
if self.kind != token.kind {
return false;
}
token.text.starts_with(self.text.as_ref())
}
pub fn space_suffix(&self) -> usize {
let mut a = self.text.split_whitespace();
self.text.len() - a.next().unwrap().len()
}
}
#[derive(Debug, Clone)]
pub struct TokenVec<'a> {
tokens: Cow<'a, [Token<'a>]>,
pos: usize,
}
impl<'a> TokenVec<'a> {
pub fn new(tokens: &'a [Token<'a>]) -> Self {
Self {
tokens: Cow::Borrowed(tokens),
pos: 0,
}
}
pub fn clone_owned(&self) -> TokenVec<'static> {
let mut v = vec![];
for token in self.tokens.iter() {
v.push(token.clone_owned());
}
TokenVec {
tokens: Cow::Owned(v),
pos: self.pos,
}
}
pub fn take_pos(&mut self, other: usize) {
self.pos = other;
}
pub fn pos(&self) -> usize {
self.pos
}
pub fn new_empty() -> Self {
Self {
tokens: Cow::Borrowed(&[]),
pos: 0,
}
}
pub fn remaining(&self) -> usize {
self.tokens.len() - self.pos
}
pub fn has_remaining(&self) -> bool {
self.remaining() > 0
}
pub fn is_empty(&self) -> bool {
self.remaining() == 0
}
pub fn top(&self) -> &Token<'a> {
&self.tokens[self.pos]
}
pub fn top_kind(&self) -> &TokenKind {
&self.tokens[self.pos].kind
}
pub fn len(&self) -> usize {
self.tokens.len()
}
pub fn advance(&mut self, count: usize) {
self.pos += count;
if self.pos > self.tokens.len() {
panic!("invalid token advance {} > {}", self.pos, self.tokens.len());
}
}
pub fn step(&mut self) {
self.advance(1)
}
}
#[derive(Debug)]
pub enum Error {
Pest(pest::error::Error<Rule>),
IntError(std::num::ParseIntError),
RonError(ron::de::Error),
}
pub fn parse_to_tokens<'a>(s: &'a str) -> Result<Vec<Token<'a>>, Error> {
let mut vec = vec![];
let pairs = ExprParser::parse(Rule::token_list, s).map_err(Error::Pest)?;
let mut last_end = 0;
for pair in pairs {
let span = pair.clone().as_span();
let mut stop = false;
let token_inner = match pair.as_rule() {
Rule::identifier => TokenKind::Ident,
Rule::nonnegative_decimal => {
TokenKind::NonNegativeDecimal({ span.as_str().parse().map_err(Error::IntError)? })
}
Rule::decimal => {
TokenKind::Decimal({ ron::de::from_str(span.as_str()).map_err(Error::RonError)? })
}
Rule::invalid => {
stop = true;
TokenKind::InvalidToken
}
Rule::field_access => TokenKind::FieldAccess,
Rule::subscript_open => TokenKind::SubscriptOpen,
Rule::subscript_close => TokenKind::SubscriptClose,
Rule::tuple_open => TokenKind::TupleOpen,
Rule::tuple_close => TokenKind::TupleClose,
Rule::curly_open => TokenKind::CurlyOpen,
Rule::curly_close => TokenKind::CurlyClose,
Rule::comma => TokenKind::Comma,
Rule::colon => TokenKind::Colon,
Rule::asterix => TokenKind::Asterix,
Rule::char_literal => {
TokenKind::Char({ ron::de::from_str(span.as_str()).map_err(Error::RonError)? })
}
Rule::assign => TokenKind::Assign,
Rule::range_access => TokenKind::Range(false),
Rule::range_access_inclusive => TokenKind::Range(true),
Rule::string_literal => {
TokenKind::String({ ron::de::from_str(span.as_str()).map_err(Error::RonError)? })
}
Rule::underscore
| Rule::alpha
| Rule::alphanumeric
| Rule::digit
| Rule::nonzero
| Rule::token
| Rule::negative_decimal
| Rule::escape_sequence
| Rule::whitespace_char
| Rule::literal_char
| Rule::single_literal_char
| Rule::token_list
| Rule::WHITESPACE => {
continue;
}
};
vec.push(Token {
kind: token_inner,
text: Cow::Borrowed(span.as_str()),
space_diff: span.start() - last_end,
});
if stop {
break;
}
last_end = span.end();
}
Ok(vec)
}