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
|
/* This Source Code Form is subject to the terms of the Mozilla Public
* License, v. 2.0. If a copy of the MPL was not distributed with this
* file, You can obtain one at http://mozilla.org/MPL/2.0/. */
use text::glyph::CharIndex;
#[derive(PartialEq, Eq, Copy)]
pub enum CompressionMode {
CompressNone,
CompressWhitespace,
CompressWhitespaceNewline,
DiscardNewline
}
// ported from Gecko's nsTextFrameUtils::TransformText.
//
// High level TODOs:
//
// * Issue #113: consider incoming text state (arabic, etc)
// and propagate outgoing text state (dual of above)
//
// * Issue #114: record skipped and kept chars for mapping original to new text
//
// * Untracked: various edge cases for bidi, CJK, etc.
pub fn transform_text(text: &str,
mode: CompressionMode,
incoming_whitespace: bool,
output_text: &mut String,
new_line_pos: &mut Vec<CharIndex>)
-> bool {
let out_whitespace = match mode {
CompressionMode::CompressNone | CompressionMode::DiscardNewline => {
let mut new_line_index = CharIndex(0);
for ch in text.chars() {
if is_discardable_char(ch, mode) {
// TODO: record skipped char
} else {
// TODO: record kept char
if ch == '\t' {
// TODO: set "has tab" flag
} else if ch == '\n' {
// Save new-line's position for line-break
// This value is relative(not absolute)
new_line_pos.push(new_line_index);
new_line_index = CharIndex(0);
}
if ch != '\n' {
new_line_index = new_line_index + CharIndex(1);
}
output_text.push(ch);
}
}
text.len() > 0 && is_in_whitespace(text.char_at_reverse(0), mode)
},
CompressionMode::CompressWhitespace | CompressionMode::CompressWhitespaceNewline => {
let mut in_whitespace: bool = incoming_whitespace;
for ch in text.chars() {
// TODO: discard newlines between CJK chars
let mut next_in_whitespace: bool = is_in_whitespace(ch, mode);
if !next_in_whitespace {
if is_always_discardable_char(ch) {
// revert whitespace setting, since this char was discarded
next_in_whitespace = in_whitespace;
// TODO: record skipped char
} else {
// TODO: record kept char
output_text.push(ch);
}
} else { /* next_in_whitespace; possibly add a space char */
if in_whitespace {
// TODO: record skipped char
} else {
// TODO: record kept char
output_text.push(' ');
}
}
// save whitespace context for next char
in_whitespace = next_in_whitespace;
} /* /for str::each_char */
in_whitespace
}
};
return out_whitespace;
fn is_in_whitespace(ch: char, mode: CompressionMode) -> bool {
match (ch, mode) {
(' ', _) => true,
('\t', _) => true,
('\n', CompressionMode::CompressWhitespaceNewline) => true,
(_, _) => false
}
}
fn is_discardable_char(ch: char, mode: CompressionMode) -> bool {
if is_always_discardable_char(ch) {
return true;
}
match mode {
CompressionMode::DiscardNewline | CompressionMode::CompressWhitespaceNewline => ch == '\n',
_ => false
}
}
fn is_always_discardable_char(_ch: char) -> bool {
// TODO: check for bidi control chars, soft hyphens.
false
}
}
pub fn float_to_fixed(before: int, f: f64) -> i32 {
((1i32 << before as uint) as f64 * f) as i32
}
pub fn fixed_to_float(before: int, f: i32) -> f64 {
f as f64 * 1.0f64 / ((1i32 << before as uint) as f64)
}
pub fn fixed_to_rounded_int(before: int, f: i32) -> int {
let half = 1i32 << (before-1) as uint;
if f > 0i32 {
((half + f) >> before as uint) as int
} else {
-((half - f) >> before as uint) as int
}
}
#[test]
fn test_transform_compress_none() {
let test_strs = [
" foo bar",
"foo bar ",
"foo\n bar",
"foo \nbar",
" foo bar \nbaz",
"foo bar baz",
"foobarbaz\n\n",
];
let mode = CompressionMode::CompressNone;
for &test in test_strs.iter() {
let mut new_line_pos = vec![];
let mut trimmed_str = String::new();
transform_text(test, mode, true, &mut trimmed_str, &mut new_line_pos);
assert_eq!(trimmed_str.as_slice(), test)
}
}
#[test]
fn test_transform_discard_newline() {
let test_strs = [
(" foo bar",
" foo bar"),
("foo bar ",
"foo bar "),
("foo\n bar",
"foo bar"),
("foo \nbar",
"foo bar"),
(" foo bar \nbaz",
" foo bar baz"),
("foo bar baz",
"foo bar baz"),
("foobarbaz\n\n",
"foobarbaz"),
];
let mode = CompressionMode::DiscardNewline;
for &(test, oracle) in test_strs.iter() {
let mut new_line_pos = vec![];
let mut trimmed_str = String::new();
transform_text(test, mode, true, &mut trimmed_str, &mut new_line_pos);
assert_eq!(trimmed_str.as_slice(), oracle)
}
}
#[test]
fn test_transform_compress_whitespace() {
let test_strs = [
(" foo bar",
"foo bar"),
("foo bar ",
"foo bar "),
("foo\n bar",
"foo\n bar"),
("foo \nbar",
"foo \nbar"),
(" foo bar \nbaz",
"foo bar \nbaz"),
("foo bar baz",
"foo bar baz"),
("foobarbaz\n\n",
"foobarbaz\n\n"),
];
let mode = CompressionMode::CompressWhitespace;
for &(test, oracle) in test_strs.iter() {
let mut new_line_pos = vec![];
let mut trimmed_str = String::new();
transform_text(test, mode, true, &mut trimmed_str, &mut new_line_pos);
assert_eq!(&*trimmed_str, oracle)
}
}
#[test]
fn test_transform_compress_whitespace_newline() {
let test_strs = vec![
(" foo bar",
"foo bar"),
("foo bar ",
"foo bar "),
("foo\n bar",
"foo bar"),
("foo \nbar",
"foo bar"),
(" foo bar \nbaz",
"foo bar baz"),
("foo bar baz",
"foo bar baz"),
("foobarbaz\n\n",
"foobarbaz "),
];
let mode = CompressionMode::CompressWhitespaceNewline;
for &(test, oracle) in test_strs.iter() {
let mut new_line_pos = vec![];
let mut trimmed_str = String::new();
transform_text(test, mode, true, &mut trimmed_str, &mut new_line_pos);
assert_eq!(&*trimmed_str, oracle)
}
}
#[test]
fn test_transform_compress_whitespace_newline_no_incoming() {
let test_strs = [
(" foo bar",
" foo bar"),
("\nfoo bar",
" foo bar"),
("foo bar ",
"foo bar "),
("foo\n bar",
"foo bar"),
("foo \nbar",
"foo bar"),
(" foo bar \nbaz",
" foo bar baz"),
("foo bar baz",
"foo bar baz"),
("foobarbaz\n\n",
"foobarbaz "),
];
let mode = CompressionMode::CompressWhitespaceNewline;
for &(test, oracle) in test_strs.iter() {
let mut new_line_pos = vec![];
let mut trimmed_str = String::new();
transform_text(test, mode, false, &mut trimmed_str, &mut new_line_pos);
assert_eq!(trimmed_str.as_slice(), oracle)
}
}
|
