//
// Copyright (c) 2025-2026 rustmailer.com (https://rustmailer.com)
//
// This file is part of the Bichon Email Archiving Project
//
// This program is free software: you can redistribute it and/or modify
// it under the terms of the GNU Affero General Public License as published by
// the Free Software Foundation, either version 3 of the License, or
// (at your option) any later version.
//
// This program is distributed in the hope that it will be useful,
// but WITHOUT ANY WARRANTY; without even the implied warranty of
// MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
// GNU Affero General Public License for more details.
//
// You should have received a copy of the GNU Affero General Public License
// along with this program. If not, see .
use regex::Regex;
use std::panic;
use std::sync::LazyLock;
use tracing::error;
/// Removes remote content references from HTML email body.
///
/// Strips attributes that load content from http:// or https:// URLs,
/// keeping data: URIs and cid: references intact. Does NOT affect
/// navigation links ().
pub fn block_remote_content(html: &str) -> String {
let mut result = html.to_string();
// 1. Strip src, poster, data attributes with remote URLs.
// These always load content regardless of the tag.
static SRC_ATTR_RE: LazyLock = LazyLock::new(|| {
Regex::new(r#"(?i)\s+(src|poster|data)\s*=\s*["'][^"']*(?:https?://|//)[^"']*["']"#).unwrap()
});
result = SRC_ATTR_RE.replace_all(&result, "").to_string();
// 2. Strip srcset attributes with remote URLs.
static SRCSET_ATTR_RE: LazyLock = LazyLock::new(|| {
Regex::new(r#"(?i)\s+srcset\s*=\s*["'][^"']*(?:https?://|//)[^"']*["']"#).unwrap()
});
result = SRCSET_ATTR_RE.replace_all(&result, "").to_string();
// 3. Strip href on tags (stylesheets), never links.
static LINK_HREF_RE: LazyLock = LazyLock::new(|| {
Regex::new(r#"(?i)(]*)\s+href\s*=\s*["'][^"']*(?:https?://|//)[^"']*["']"#).unwrap()
});
result = LINK_HREF_RE.replace_all(&result, "$1").to_string();
// 4. Strip CSS url() references with remote URLs in inline styles.
static CSS_URL_RE: LazyLock = LazyLock::new(|| {
Regex::new(r#"(?i)url\(\s*["']?\s*(?:https?://|//)[^)"'\s]*\s*["']?\s*\)"#).unwrap()
});
result = CSS_URL_RE.replace_all(&result, "").to_string();
// 5. Strip @import url(...) with remote URLs inside "#;
let result = block_remote_content(html);
assert!(!result.contains("https://fonts.example.com"));
}
#[test]
fn strips_video_poster() {
let html = r#""#;
let result = block_remote_content(html);
assert!(!result.contains("https://cdn.example.com"));
}
#[test]
fn strips_srcset() {
let html =
r#"![]()
"#;
let result = block_remote_content(html);
assert!(!result.contains("https://cdn.example.com"));
}
#[test]
fn strips_body_background() {
let html = r#""#;
let result = block_remote_content(html);
assert!(!result.contains("https://tracker.example.com"));
assert!(result.contains("
Read more
"#;
let result = block_remote_content(html);
// Remote content gone
assert!(!result.contains("spy.example.com"));
assert!(!result.contains("tracker.example.com"));
// Safe content preserved
assert!(result.contains("data:image/png;base64,OK123"));
assert!(result.contains(r#"href="https://example.com/read-more""#));
}
}
}
"#;
let result = block_remote_content(html);
assert!(!result.contains("https://cdn.example.com"));
}
#[test]
fn strips_body_background() {
let html = r#""#;
let result = block_remote_content(html);
assert!(!result.contains("https://tracker.example.com"));
assert!(result.contains("