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
|
/* 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/. */
#[derive(PartialEq, Eq, Copy, Clone)]
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)
-> bool {
let out_whitespace = match mode {
CompressionMode::CompressNone | CompressionMode::DiscardNewline => {
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
}
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 soft hyphens.
is_bidi_control(ch)
}
}
pub fn float_to_fixed(before: usize, f: f64) -> i32 {
((1i32 << before) as f64 * f) as i32
}
pub fn fixed_to_float(before: usize, f: i32) -> f64 {
f as f64 * 1.0f64 / ((1i32 << before) as f64)
}
pub fn is_bidi_control(c: char) -> bool {
match c {
'\u{202A}'...'\u{202E}' => true,
'\u{2066}'...'\u{2069}' => true,
'\u{200E}' | '\u{200F}' | '\u{061C}' => true,
_ => false
}
}
|
