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
use crate::{MarkdownIt, Node};
use crate::common::sourcemap::SourcePos;
use crate::parser::extset::{InlineRootExtSet, RootExtSet};
use crate::parser::inline::Text;
#[derive(Debug, Clone, Copy)]
pub struct DelimiterRun {
pub marker: char,
pub can_open: bool,
pub can_close: bool,
pub length: usize,
}
fn is_punct_char(ch: char) -> bool {
use unicode_general_category::get_general_category;
use unicode_general_category::GeneralCategory::*;
match get_general_category(ch) {
ConnectorPunctuation | DashPunctuation | OpenPunctuation | ClosePunctuation |
InitialPunctuation | FinalPunctuation | OtherPunctuation => true,
UppercaseLetter | LowercaseLetter | TitlecaseLetter | ModifierLetter | OtherLetter |
NonspacingMark | SpacingMark | EnclosingMark |
DecimalNumber | LetterNumber | OtherNumber |
MathSymbol | CurrencySymbol | ModifierSymbol | OtherSymbol |
SpaceSeparator | LineSeparator | ParagraphSeparator |
Control | Format | Surrogate | PrivateUse | Unassigned => false
}
}
#[derive(Debug)]
#[readonly::make]
pub struct InlineState<'a, 'b> where 'b: 'a {
#[readonly]
pub src: String,
#[readonly]
pub md: &'a MarkdownIt,
pub node: Node,
pub srcmap: Vec<(usize, usize)>,
pub root_ext: &'b mut RootExtSet,
pub inline_ext: &'b mut InlineRootExtSet,
pub pos: usize,
pub pos_max: usize,
pub link_level: i32,
pub level: u32,
}
impl<'a, 'b> InlineState<'a, 'b> {
pub fn new(
src: String,
srcmap: Vec<(usize, usize)>,
md: &'a MarkdownIt,
root_ext: &'b mut RootExtSet,
inline_ext: &'b mut InlineRootExtSet,
node: Node,
) -> Self {
let mut result = Self {
pos: 0,
pos_max: src.len(),
src,
srcmap,
root_ext,
inline_ext,
md,
node,
link_level: 0,
level: 0,
};
result.trim_src();
result
}
fn trim_src(&mut self) {
let mut chars = self.src.as_bytes().iter();
while let Some(b' ' | b'\t') = chars.next_back() {
self.pos_max -= 1;
}
while let Some(b' ' | b'\t') = chars.next() {
self.pos += 1;
}
}
pub fn trailing_text_push(&mut self, start: usize, end: usize) {
if let Some(text) = self.node.children.last_mut()
.and_then(|t| t.cast_mut::<Text>()) {
text.content.push_str(&self.src[start..end]);
if let Some(map) = self.node.children.last_mut().unwrap().srcmap {
let (map_start, _) = map.get_byte_offsets();
let map_end = self.get_source_pos_for(end);
self.node.children.last_mut().unwrap().srcmap = Some(SourcePos::new(map_start, map_end));
}
} else {
let mut node = Node::new(Text { content: self.src[start..end].to_owned() });
node.srcmap = self.get_map(start, end);
self.node.children.push(node);
}
}
pub fn trailing_text_pop(&mut self, count: usize) {
if count == 0 { return; }
let mut node = self.node.children.pop().unwrap();
let text = node.cast_mut::<Text>().unwrap();
if text.content.len() == count {
drop(node);
} else {
text.content.truncate(text.content.len() - count);
if let Some(map) = node.srcmap {
let (map_start, map_end) = map.get_byte_offsets();
let map_end = self.get_source_pos_for(map_end - count);
node.srcmap = Some(SourcePos::new(map_start, map_end));
}
self.node.children.push(node);
}
}
#[must_use]
pub fn trailing_text_get(&self) -> &str {
if let Some(text) = self.node.children.last()
.and_then(|t| t.cast::<Text>()) {
text.content.as_str()
} else {
""
}
}
#[must_use]
pub fn scan_delims(&self, start: usize, can_split_word: bool) -> DelimiterRun {
let mut left_flanking = true;
let mut right_flanking = true;
let last_char = if start > 0 {
self.src[..start].chars().next_back().unwrap()
} else {
' '
};
let mut chars = self.src[start..self.pos_max].chars();
let marker = chars.next().unwrap();
let next_char;
let mut count = 1;
loop {
match chars.next() {
None => {
next_char = ' ';
break;
}
Some(x) => {
if x != marker {
next_char = x;
break;
}
}
}
count += 1;
}
let is_last_punct_char = last_char.is_ascii_punctuation() || is_punct_char(last_char);
let is_next_punct_char = next_char.is_ascii_punctuation() || is_punct_char(next_char);
let is_last_whitespace = last_char.is_whitespace();
let is_next_whitespace = next_char.is_whitespace();
#[allow(clippy::collapsible_if)]
if is_next_whitespace {
left_flanking = false;
} else if is_next_punct_char {
if !(is_last_whitespace || is_last_punct_char) {
left_flanking = false;
}
}
#[allow(clippy::collapsible_if)]
if is_last_whitespace {
right_flanking = false;
} else if is_last_punct_char {
if !(is_next_whitespace || is_next_punct_char) {
right_flanking = false;
}
}
let can_open;
let can_close;
if !can_split_word {
can_open = left_flanking && (!right_flanking || is_last_punct_char);
can_close = right_flanking && (!left_flanking || is_next_punct_char);
} else {
can_open = left_flanking;
can_close = right_flanking;
}
DelimiterRun {
marker,
can_open,
can_close,
length: count
}
}
#[must_use]
fn get_source_pos_for(&self, pos: usize) -> usize {
let line = match self.srcmap.binary_search_by(|x| x.0.cmp(&pos)) {
Ok(x) => x,
Err(x) => x - 1,
};
self.srcmap[line].1 + (pos - self.srcmap[line].0)
}
#[must_use]
pub fn get_map(&self, start_pos: usize, end_pos: usize) -> Option<SourcePos> {
debug_assert!(start_pos <= end_pos);
Some(SourcePos::new(
self.get_source_pos_for(start_pos),
self.get_source_pos_for(end_pos)
))
}
}