Files
epub-read/src/book.rs

91 lines
2.1 KiB
Rust
Raw Normal View History

pub fn strip_html(input: &str) -> String {
let mut result = String::with_capacity(input.len());
let mut in_tag = false;
let mut in_entity = false;
let mut entity = String::new();
for c in input.chars() {
match c {
'<' => in_tag = true,
'>' if in_tag => in_tag = false,
'&' if !in_tag => {
in_entity = true;
entity.clear();
}
';' if in_entity => {
in_entity = false;
let decoded = match entity.as_str() {
"amp" => "&",
"lt" => "<",
"gt" => ">",
"quot" => "\"",
"nbsp" => " ",
_ => "",
};
result.push_str(decoded);
}
c if !in_tag && !in_entity => result.push(c),
c if in_entity => entity.push(c),
_ => {}
}
}
result
}
#[derive(Debug, Clone)]
pub struct TocEntry {
pub label: String,
pub section: usize,
pub children: Vec<TocEntry>,
}
#[derive(Debug, Clone)]
pub struct Section {
pub title: String,
pub content: String,
pub pages: Vec<usize>,
}
#[derive(Debug, Clone)]
pub struct Book {
pub title: String,
pub author: String,
pub cover: Option<Vec<u8>>,
pub sections: Vec<Section>,
pub toc: Vec<TocEntry>,
}
#[cfg(test)]
mod tests {
use super::*;
#[test]
fn test_strip_html_plain_text() {
assert_eq!(strip_html("Hello World"), "Hello World");
}
#[test]
fn test_strip_html_simple_tags() {
assert_eq!(strip_html("<p>Hello</p>"), "Hello");
}
#[test]
fn test_strip_html_nested_tags() {
assert_eq!(
strip_html("<div><p>Hello <b>World</b></p></div>"),
"Hello World"
);
}
#[test]
fn test_strip_html_html_entities() {
assert_eq!(strip_html("Hello &amp; World"), "Hello & World");
assert_eq!(strip_html("Hello&nbsp;World"), "Hello World");
}
#[test]
fn test_strip_html_empty() {
assert_eq!(strip_html(""), "");
}
}