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
|
use crate::Cursor;
use lazy_static::lazy_static;
use regex::Regex;
use scraper::Html;
/// Pass any text here to be validated as HTML, breaks on validation errors
pub fn validate (text: &str) -> Result<&str> {
// Technically full validation is not needed nor required here, all text after validation
// is used in Telegram messages as RAW text enclosed in `pre`/`code` tags, so the only reason
// for this check is to make sure there's no dangling closing tags in the text that might
// break Telegram message formatting
let fragment = Html::parse_fragment(text);
if !fragment.errors.is_empty() {
bail!(fragment.errors.join("\n"));
}
Ok(text)
|
>
>
>
<
>
|
>
|
<
|
|
|
|
<
<
<
|
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
|
use crate::Cursor;
use std::borrow::Cow;
use html_escape::encode_text;
use lazy_static::lazy_static;
use regex::Regex;
use stacked_errors::{
bail,
Result,
};
lazy_static! {
pub static ref RE_DOMAIN: Regex = Regex::new(r"^[a-z0-9]([-a-z0-9]*[a-z0-9])?(\.[a-z0-9]([-a-z0-9]*[a-z0-9])?)*$").unwrap();
pub static ref RE_CLOSING: Regex = Regex::new(r"</[ \t]*(pre|code)[ \t]*>").unwrap();
}
/// `Attachment` object to store number attachment data and corresponding file name
#[derive(Debug)]
pub struct Attachment {
pub data: Cursor<Vec<u8>>,
pub name: String,
}
/// Pass any text here to be validated as not breaking from Telegram preformatted blocks
/// escape all HTML chars afterwards
pub fn validate (text: &str) -> Result<Cow<'_, str>> {
if RE_CLOSING.is_match(text) {
bail!("Telegram closing tag found.");
} else {
Ok(encode_text(text))
}
}
|