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
|
// Copyright 2017 The xi-editor Authors.
//
// Licensed under the Apache License, Version 2.0 (the "License");
// you may not use this file except in compliance with the License.
// You may obtain a copy of the License at
//
// http://www.apache.org/licenses/LICENSE-2.0
//
// Unless required by applicable law or agreed to in writing, software
// distributed under the License is distributed on an "AS IS" BASIS,
// WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
// See the License for the specific language governing permissions and
// limitations under the License.
//! Segmentation of word boundaries. Note: this current implementation
//! is intended to work for code. Future work is to make it Unicode aware.
use xi_rope::{Cursor, Rope, RopeInfo};
pub struct WordCursor<'a> {
inner: Cursor<'a, RopeInfo>,
}
impl<'a> WordCursor<'a> {
pub fn new(text: &'a Rope, pos: usize) -> WordCursor<'a> {
let inner = Cursor::new(text, pos);
WordCursor { inner }
}
/// Get previous boundary, and set the cursor at the boundary found.
pub fn prev_boundary(&mut self) -> Option<usize> {
if let Some(ch) = self.inner.prev_codepoint() {
let mut prop = get_word_property(ch);
let mut candidate = self.inner.pos();
while let Some(prev) = self.inner.prev_codepoint() {
let prop_prev = get_word_property(prev);
if classify_boundary(prop_prev, prop).is_start() {
break;
}
prop = prop_prev;
candidate = self.inner.pos();
}
self.inner.set(candidate);
return Some(candidate);
}
None
}
/// Get next boundary, and set the cursor at the boundary found.
pub fn next_boundary(&mut self) -> Option<usize> {
if let Some(ch) = self.inner.next_codepoint() {
let mut prop = get_word_property(ch);
let mut candidate = self.inner.pos();
while let Some(next) = self.inner.next_codepoint() {
let prop_next = get_word_property(next);
if classify_boundary(prop, prop_next).is_end() {
break;
}
prop = prop_next;
candidate = self.inner.pos();
}
self.inner.set(candidate);
return Some(candidate);
}
None
}
/// Return the selection for the word containing the current cursor. The
/// cursor is moved to the end of that selection.
pub fn select_word(&mut self) -> (usize, usize) {
let initial = self.inner.pos();
let init_prop_after = self.inner.next_codepoint().map(get_word_property);
self.inner.set(initial);
let init_prop_before = self.inner.prev_codepoint().map(get_word_property);
let mut start = initial;
let init_boundary = if let (Some(pb), Some(pa)) = (init_prop_before, init_prop_after) {
classify_boundary_initial(pb, pa)
} else {
WordBoundary::Both
};
let mut prop_after = init_prop_after;
let mut prop_before = init_prop_before;
if prop_after.is_none() {
start = self.inner.pos();
prop_after = prop_before;
prop_before = self.inner.prev_codepoint().map(get_word_property);
}
while let (Some(pb), Some(pa)) = (prop_before, prop_after) {
if start == initial {
if init_boundary.is_start() {
break;
}
} else if !init_boundary.is_boundary() {
if classify_boundary(pb, pa).is_boundary() {
break;
}
} else if classify_boundary(pb, pa).is_start() {
break;
}
start = self.inner.pos();
prop_after = prop_before;
prop_before = self.inner.prev_codepoint().map(get_word_property);
}
self.inner.set(initial);
let mut end = initial;
prop_after = init_prop_after;
prop_before = init_prop_before;
if prop_before.is_none() {
prop_before = self.inner.next_codepoint().map(get_word_property);
end = self.inner.pos();
prop_after = self.inner.next_codepoint().map(get_word_property);
}
while let (Some(pb), Some(pa)) = (prop_before, prop_after) {
if end == initial {
if init_boundary.is_end() {
break;
}
} else if !init_boundary.is_boundary() {
if classify_boundary(pb, pa).is_boundary() {
break;
}
} else if classify_boundary(pb, pa).is_end() {
break;
}
end = self.inner.pos();
prop_before = prop_after;
prop_after = self.inner.next_codepoint().map(get_word_property);
}
self.inner.set(end);
(start, end)
}
}
#[derive(PartialEq, Eq)]
enum WordBoundary {
Interior,
Start, // a boundary indicating the end of a word
End, // a boundary indicating the start of a word
Both,
}
impl WordBoundary {
fn is_start(&self) -> bool {
*self == WordBoundary::Start || *self == WordBoundary::Both
}
fn is_end(&self) -> bool {
*self == WordBoundary::End || *self == WordBoundary::Both
}
fn is_boundary(&self) -> bool {
*self != WordBoundary::Interior
}
}
fn classify_boundary(prev: WordProperty, next: WordProperty) -> WordBoundary {
use self::WordBoundary::*;
use self::WordProperty::*;
match (prev, next) {
(Lf, _) => Both,
(_, Lf) => Both,
(Space, Other) => Start,
(Space, Punctuation) => Start,
(Punctuation, Other) => Start,
(Other, Space) => End,
(Punctuation, Space) => End,
(Other, Punctuation) => End,
_ => Interior,
}
}
fn classify_boundary_initial(prev: WordProperty, next: WordProperty) -> WordBoundary {
use self::WordBoundary::*;
use self::WordProperty::*;
match (prev, next) {
(Lf, Other) => Start,
(Other, Lf) => End,
(Lf, Space) => Interior,
(Lf, Punctuation) => Interior,
(Space, Lf) => Interior,
(Punctuation, Lf) => Interior,
(Space, Punctuation) => Interior,
(Punctuation, Space) => Interior,
_ => classify_boundary(prev, next),
}
}
#[derive(Copy, Clone)]
enum WordProperty {
Lf,
Space,
Punctuation,
Other, // includes letters and all of non-ascii unicode
}
fn get_word_property(codepoint: char) -> WordProperty {
if codepoint <= ' ' {
// TODO: deal with \r
if codepoint == '\n' {
return WordProperty::Lf;
}
return WordProperty::Space;
} else if codepoint <= '\u{3f}' {
// Hardcoded: !"#$%&'()*+,-./:;<=>?
if (0xfc00fffe00000000u64 >> (codepoint as u32)) & 1 != 0 {
return WordProperty::Punctuation;
}
} else if codepoint <= '\u{7f}' {
// Hardcoded: @[\]^`{|}~
if (0x7800000178000001u64 >> ((codepoint as u32) & 0x3f)) & 1 != 0 {
return WordProperty::Punctuation;
}
}
WordProperty::Other
}
|
