sdocx 1.0.0

Reverse-engineered tooling and SDK for converting Samsung Notes (.sdocx) files
Documentation 
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

use unicode_linebreak::{BreakOpportunity, linebreaks};
use unicode_segmentation::UnicodeSegmentation;

#[derive(Debug, Clone, Copy, PartialEq, Eq)]
pub(in crate::render) enum BreakKind {
    Allowed,
    Mandatory,
}

#[derive(Debug, Clone, Copy, PartialEq, Eq)]
pub(in crate::render) struct BreakCandidate {
    /// Scalar offset immediately after the source text retained on the line.
    pub end: usize,
    pub kind: BreakKind,
}

#[derive(Debug, Clone, PartialEq, Eq)]
pub(in crate::render) struct ParagraphBreaks {
    pub candidates: Vec<BreakCandidate>,
    /// Grapheme ends for overflow fallback, independent of normal line-breaking rules.
    pub emergency: Vec<usize>,
}

pub(in crate::render) fn break_candidates(text: &str) -> ParagraphBreaks {
    let scalar_boundaries = text
        .char_indices()
        .map(|(byte, _)| byte)
        .chain(std::iter::once(text.len()))
        .collect::<Vec<_>>();
    let emergency = text
        .grapheme_indices(true)
        .filter_map(|(byte, grapheme)| {
            let end = byte.checked_add(grapheme.len())?;
            scalar_boundaries.binary_search(&end).ok()
        })
        .collect::<Vec<_>>();
    let candidates = linebreaks(text)
        .filter_map(|(byte, opportunity)| {
            let end = scalar_boundaries.binary_search(&byte).ok()?;
            emergency.binary_search(&end).ok()?;
            Some(BreakCandidate {
                end,
                kind: match opportunity {
                    BreakOpportunity::Allowed => BreakKind::Allowed,
                    BreakOpportunity::Mandatory => BreakKind::Mandatory,
                },
            })
        })
        .collect();
    ParagraphBreaks {
        candidates,
        emergency,
    }
}

#[cfg(test)]
mod tests {
    use super::*;
    use BreakKind::{Allowed, Mandatory};

    fn candidates(text: &str) -> Vec<(usize, BreakKind)> {
        break_candidates(text)
            .candidates
            .into_iter()
            .map(|candidate| (candidate.end, candidate.kind))
            .collect()
    }

    #[test]
    fn cjk_breaks_use_scalar_offsets_instead_of_utf8_bytes() {
        assert_eq!(
            candidates("中文测试"),
            [(1, Allowed), (2, Allowed), (3, Allowed), (4, Mandatory)]
        );
        assert_eq!(break_candidates("中文测试").emergency, [1, 2, 3, 4]);
    }

    #[test]
    fn nonbreaking_space_and_word_joiner_suppress_normal_breaks() {
        for text in ["ab\u{a0}cd ef", "ab\u{2060}cd ef"] {
            assert_eq!(candidates(text), [(6, Allowed), (8, Mandatory)]);
            assert!(break_candidates(text).emergency.contains(&3));
        }
    }

    #[test]
    fn combining_marks_and_emoji_zwj_sequences_are_indivisible() {
        assert_eq!(break_candidates("e\u{301}x").emergency, [2, 3]);
        assert_eq!(candidates("e\u{301}x"), [(3, Mandatory)]);
        assert_eq!(break_candidates("A👩‍👩‍👧‍👦B").emergency, [1, 8, 9]);
        assert_eq!(
            candidates("A👩‍👩‍👧‍👦B"),
            [(1, Allowed), (8, Allowed), (9, Mandatory)]
        );
    }

    #[test]
    fn crlf_is_one_mandatory_break_and_one_grapheme() {
        assert_eq!(candidates("a\r\nb"), [(3, Mandatory), (4, Mandatory)]);
        assert_eq!(break_candidates("a\r\nb").emergency, [1, 3, 4]);
    }

    #[test]
    fn leading_repeated_and_trailing_spaces_remain_in_source_ranges() {
        let source = " a  b   ";
        let breaks = break_candidates(source);
        assert_eq!(
            candidates(source),
            [(1, Allowed), (4, Allowed), (8, Mandatory)]
        );
        let mut start = 0;
        let chunks = breaks
            .candidates
            .iter()
            .map(|candidate| {
                let chunk = source
                    .chars()
                    .skip(start)
                    .take(candidate.end - start)
                    .collect::<String>();
                start = candidate.end;
                chunk
            })
            .collect::<Vec<_>>();
        assert_eq!(chunks, [" ", "a  ", "b   "]);
        assert_eq!(chunks.concat(), source);
    }

    #[test]
    fn empty_text_has_no_breaks_but_spaces_have_a_terminal_break() {
        let empty = break_candidates("");
        assert!(empty.candidates.is_empty());
        assert!(empty.emergency.is_empty());
        assert_eq!(candidates("   "), [(3, Mandatory)]);
        assert_eq!(break_candidates("   ").emergency, [1, 2, 3]);
    }
}