verso-reader 0.1.0

A terminal EPUB reader with vim navigation, a Kindle-style library, and Markdown highlight export
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

use scraper::{Html, Selector};

/// Produce the canonical plain-text extraction used for the location model.
/// Must be deterministic and stable — `char_offset` semantics depend on it.
pub fn from_html(html: &str) -> String {
    // Parse once; traverse in document order.
    let doc = Html::parse_document(html);
    let body_sel = Selector::parse("body, html").unwrap();

    let mut out = String::new();
    // First body element only.
    if let Some(root) = doc.select(&body_sel).next() {
        walk(root, &mut out);
    }
    if out.is_empty() {
        // Fallback: some EPUB chapters are fragments without a body.
        walk(doc.root_element(), &mut out);
    }
    normalise_whitespace(&out)
}

fn walk(node: scraper::ElementRef, out: &mut String) {
    use scraper::Node;
    for child in node.children() {
        match child.value() {
            Node::Text(t) => out.push_str(&collapse_spaces(t)),
            Node::Element(el) => {
                let name = el.name();
                if matches!(name, "script" | "style" | "iframe" | "object" | "embed") {
                    continue;
                }
                let is_block = matches!(
                    name,
                    "p" | "div"
                        | "br"
                        | "h1"
                        | "h2"
                        | "h3"
                        | "h4"
                        | "h5"
                        | "h6"
                        | "li"
                        | "blockquote"
                        | "pre"
                        | "tr"
                        | "hr"
                        | "figure"
                        | "figcaption"
                );
                if is_block && !out.ends_with('\n') {
                    out.push('\n');
                }
                if let Some(er) = scraper::ElementRef::wrap(child) {
                    walk(er, out);
                }
                if matches!(
                    name,
                    "p" | "h1" | "h2" | "h3" | "h4" | "h5" | "h6" | "blockquote" | "pre" | "figure"
                ) && !out.ends_with("\n\n")
                {
                    out.push('\n');
                }
            }
            _ => {}
        }
    }
}

fn normalise_whitespace(s: &str) -> String {
    let mut out = String::with_capacity(s.len());
    let mut last_blank = false;
    for line in s.split('\n') {
        let trimmed = collapse_spaces(line.trim_end());
        if trimmed.is_empty() {
            if !last_blank && !out.is_empty() {
                out.push_str("\n\n");
                last_blank = true;
            }
        } else {
            if !out.is_empty() && !out.ends_with("\n\n") && !out.ends_with('\n') {
                out.push('\n');
            }
            out.push_str(&trimmed);
            last_blank = false;
        }
    }
    out.trim().to_string()
}

fn collapse_spaces(s: &str) -> String {
    let mut out = String::with_capacity(s.len());
    let mut prev_space = false;
    for ch in s.chars() {
        if ch.is_whitespace() {
            if !prev_space {
                out.push(' ');
            }
            prev_space = true;
        } else {
            out.push(ch);
            prev_space = false;
        }
    }
    out
}