rays/ipodderx-rs
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

Collapse whitespace left by stripped filename separators

Browse Source 
A real feed titled with pipe separators produced a folder named
"Get in the Trunk  Anthology Series  Delta Green": removing a forbidden
character left the gap around it. Runs of whitespace now collapse, and
control characters map to a space rather than vanishing.

Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01RPyeapneuXrCdojsaiXGbe
This commit is contained in:
Ray Slakinski
2026-09-10 00:37:30 +00:00
parent 833c07240b
commit c12e8ca19c
2 changed files with 55 additions and 3 deletions
Download Patch File Download Diff File Expand all files Collapse all files

31
src/download.rs
View File

@@ -15,10 +15,24 @@ const MAX_NAME_BYTES: usize = 255;
/// Keeps UTF-8: the original transliterated to ASCII via latin1_to_ascii because 2004
/// filesystems demanded it. Ours do not.
pub fn sanitize(name: &str) -> String {
let mut out: String = name
let stripped: String = name
.chars()
.filter(|c| !c.is_control() && !FORBIDDEN.contains(c))
.map(|c| if c.is_control() { ' ' } else { c })
.filter(|c| !FORBIDDEN.contains(c))
.collect();
// Stripping a separator leaves a gap: "Show | Series | Delta" would otherwise become
// "Show Series Delta". Collapse runs of whitespace rather than leaving the seams.
let mut out = String::with_capacity(stripped.len());
for c in stripped.chars() {
if c.is_whitespace() {
if !out.ends_with(' ') {
out.push(' ');
}
} else {
out.push(c);
}
}
out = out.trim().trim_matches('.').trim().to_owned();
if out.len() > MAX_NAME_BYTES {
@@ -266,10 +280,21 @@ mod tests {
fn sanitize_strips_path_and_control_characters() {
assert_eq!(sanitize("../../etc/passwd"), "etcpasswd");
assert_eq!(sanitize("Ep 12: The \"Best\" One?"), "Ep 12 The Best One");
assert_eq!(sanitize("bad\u{0}name\u{7}.mp3"), "badname.mp3");
assert_eq!(sanitize("bad\u{0}name\u{7}.mp3"), "bad name .mp3");
assert_eq!(sanitize(" spaced.mp3 "), "spaced.mp3");
}
#[test]
fn sanitize_collapses_the_gaps_left_by_stripped_separators() {
// A real Patreon feed title; the pipes are forbidden characters.
assert_eq!(
sanitize("Get in the Trunk | Anthology Series | Delta Green"),
"Get in the Trunk Anthology Series Delta Green"
);
assert_eq!(sanitize("Ep 12: The One"), "Ep 12 The One");
assert_eq!(sanitize("a b"), "a b");
}
#[test]
fn sanitize_never_yields_an_empty_or_dot_name() {
assert_eq!(sanitize(""), "download");