A quoted word that isn't a file name; split parts with two digits
From the re-index's single-file releases:
- A quoted text without an extension ("My \"Official\" remaining set's
of Inna … 025.jpg [25/74]", "… lr140x16.jpg ( file 046 of 922)
\"yEnc\"", "\"Dr. Lust\" - … - [12/21] - Ed_DRL_VDR_LM.part09.rar") was
the file name, the real one stayed in the subject: every file a release.
It gives way to a file name with an extension beside it
(nameBesideQuotes); random quoted names with none beside keep theirs.
- Split parts numbered with two digits ("Admiral.EP05.2008.720p.Rus.
HDCLUB.mkv.21", a.b.movies.divx.russian) share their stem, as .001.
Both implementations; tests; fixtures identical.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
This commit is contained in:
1 parent
625ea23171
commit
2814c77225
8 files changed
+77
-9
No files matched your search
+36
-1
@@ -227,7 +227,7 @@ fn describe(subject: &str, name_end: Option<usize>, counter: &Counter, from: &st
|
||||
_ => None,
|
||||
};
|
||||
let name = match quoted {
|
||||
Some(name) => name,
|
||||
Some(name) => name_beside_quotes(&name, &subject[..counter.index]).unwrap_or(name),
|
||||
None => unquoted_name(&subject[..counter.index])?,
|
||||
};
|
||||
let name = name.as_str();
|
||||
@@ -273,6 +273,28 @@ fn first_track(text: &str) -> Option<usize> {
|
||||
None
|
||||
}
|
||||
|
||||
/// nameBesideQuotes (lib/headers/subject.ts): a file name elsewhere when the quoted text has no extension.
|
||||
pub fn name_beside_quotes(quoted: &str, before_counter: &str) -> Option<String> {
|
||||
if has_extension(quoted) {
|
||||
return None;
|
||||
}
|
||||
// .replace(/"[^"]*"/g, ' ')
|
||||
let mut text = String::with_capacity(before_counter.len());
|
||||
let mut rest = before_counter;
|
||||
while let Some(open) = rest.find('"') {
|
||||
match rest[open + 1..].find('"') {
|
||||
Some(close) => {
|
||||
text.push_str(&rest[..open]);
|
||||
text.push(' ');
|
||||
rest = &rest[open + 1 + close + 1..];
|
||||
}
|
||||
None => break,
|
||||
}
|
||||
}
|
||||
text.push_str(rest);
|
||||
unquoted_name(&text).filter(|n| has_extension(n))
|
||||
}
|
||||
|
||||
/// unquotedName (lib/headers/subject.ts): the file name of a subject without a quoted one, from the text before its counter.
|
||||
pub fn unquoted_name(before_counter: &str) -> Option<String> {
|
||||
let mut text = before_counter.trim_end_matches(js::is_space);
|
||||
@@ -896,4 +918,17 @@ mod unquoted_tests {
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
#[cfg(test)]
|
||||
mod beside_quotes_tests {
|
||||
use super::name_beside_quotes;
|
||||
|
||||
#[test]
|
||||
fn a_name_beside_a_quoted_word() {
|
||||
assert_eq!(name_beside_quotes("Official", "My \"Official\" remaining set's of Inna, Please help up to #69 if you can 025.jpg [25/74] - yEnc ").as_deref(), Some("025.jpg"));
|
||||
assert_eq!(name_beside_quotes("Dr. Lust", "\"Dr. Lust\" - Lily Marlene, Vanessa Del Rio, Scorpio? - yEnc - [12/21] - Ed_DRL_VDR_LM.part09.rar ").as_deref(), Some("Ed_DRL_VDR_LM.part09.rar"));
|
||||
assert_eq!(name_beside_quotes("1f0554e5fec14b8b05ca", "77cd6d03d19281a775f5bdc5 [2/8] - \"1f0554e5fec14b8b05ca\" yEnc ").as_deref(), None);
|
||||
assert_eq!(name_beside_quotes("x.rar", "\"x.rar\" other.zip ").as_deref(), None);
|
||||
}
|
||||
}
|
||||
}
|
||||
+10
-3
@@ -36,7 +36,7 @@ static SUFFIXES: LazyLock<Vec<(Regex, &'static str)>> = LazyLock::new(|| {
|
||||
(re(r"(?i)\.7z(\.[0-9]{3})?$"), ""),
|
||||
(re(r"(?i)\.zip(\.[0-9]{3})?$"), ""),
|
||||
// JS: (?<=\.(7z|…))\.\d{3}$ — no lookbehind here, so the extension is matched and put back.
|
||||
(re(r"(?i)(\.(?:7z|zip|rar|tar|mkv|mp4|avi|m4v|ts|m2ts|iso|img|bin|vob))\.[0-9]{3}$"), "$1"),
|
||||
(re(r"(?i)(\.(?:7z|zip|rar|tar|mkv|mp4|avi|m4v|ts|m2ts|iso|img|bin|vob))\.[0-9]{2,3}$"), "$1"),
|
||||
(re(r"(?i)\.(nfo|sfv|nzb|srr|srs|txt|jpg|png|md5|sha1|srt|sub|idx|ass|ssa|m3u|m3u8|cue|log)$"), ""),
|
||||
(re(r"(?i)\.tar$"), ""),
|
||||
(re(r"(?i)\.(zst|gz|xz|bz2)$"), ""),
|
||||
@@ -114,6 +114,13 @@ fn strip_three_digits(s: &[u8]) -> Option<usize> {
|
||||
(n >= 4 && s[n - 4] == b'.' && s[n - 3..].iter().all(u8::is_ascii_digit)).then(|| n - 4)
|
||||
}
|
||||
|
||||
/// \.\d{2,3}$: where a split volume's number starts (its dot).
|
||||
fn strip_volume_digits(s: &[u8]) -> Option<usize> {
|
||||
let n = s.len();
|
||||
let d = s.iter().rev().take_while(|c| c.is_ascii_digit()).count();
|
||||
((2..=3).contains(&d) && n > d && s[n - d - 1] == b'.').then(|| n - d - 1)
|
||||
}
|
||||
|
||||
const SPLIT_EXTS: [&[u8]; 14] = [b"7z", b"zip", b"rar", b"tar", b"mkv", b"mp4", b"avi", b"m4v", b"ts", b"m2ts", b"iso", b"img", b"bin", b"vob"];
|
||||
const SIDE_EXTS: [&[u8]; 19] = [b"nfo", b"sfv", b"nzb", b"srr", b"srs", b"txt", b"jpg", b"png", b"md5", b"sha1", b"srt", b"sub", b"idx", b"ass", b"ssa", b"m3u", b"m3u8", b"cue", b"log"];
|
||||
const PACK_EXTS: [&[u8]; 4] = [b"zst", b"gz", b"xz", b"bz2"];
|
||||
@@ -164,9 +171,9 @@ fn strip_suffix_rule(s: &[u8], rule: usize) -> Option<usize> {
|
||||
}
|
||||
ends_ci(s, ext).then(|| n - ext.len())
|
||||
}
|
||||
// (?<=\.(7z|…))\.\d{3}$: only the volume number goes.
|
||||
// (?<=\.(7z|…))\.\d{2,3}$: only the volume number goes.
|
||||
7 => {
|
||||
let m = strip_three_digits(s)?;
|
||||
let m = strip_volume_digits(s)?;
|
||||
strip_ext(&s[..m], &SPLIT_EXTS).map(|_| m)
|
||||
}
|
||||
8 => strip_ext(s, &SIDE_EXTS),
|
||||
|
||||
Reference in new issue
Block a user