Phase 1 — Foundation

Mirror NPE's dependency-free spine in Rust:

* exceptions   — NetworkError + ParsingError + ContentUnavailable
                 + ExtractionError tree, with reqwest/serde_json conversions
* localization — Localization + ContentCountry, default (en, GB)
* downloader/  — Downloader trait, Request builder, Response,
                 reqwest blocking default impl
* page         — continuation-token carrier
* image        — Image + ImageSet + ResolutionLevel
                 (HEIGHT_UNKNOWN/WIDTH_UNKNOWN = -1)
* metainfo     — title/content/url/url_text grab-bag
* service      — StreamingService trait + LinkType + ServiceInfo
* newpipe      — process-global Downloader / Localization /
                 ContentCountry singleton

Foundational invariants nailed down (per SPEC §3):
* HTTP non-2xx returns Ok(Response); only 429 throws NetworkError::Recaptcha
* Response header keys lowercase-normalized
* Request.add_header PARITY with NPE bug (silent overwrite);
  append_header is our clean addition
* default Localization is en-GB
* No cookie jar in the default downloader

Tests: 7 unit + 7 live smoke against httpbin.org (gated on
'online-tests' feature). All green.
This commit is contained in:
Sulkta 2026-05-24 16:32:36 -07:00
parent 6340b54ad3
commit 2a2367a3d0
16 changed files with 2689 additions and 1 deletions

109
src/localization.rs Normal file
View file

@ -0,0 +1,109 @@
// Localization + ContentCountry. Per SPEC §3 invariant #9, the DEFAULT
// Localization is ("en", "GB") — not en-US, not the system locale.
// NPE's Localization.java exposes ~100 country codes; we ship a small
// in-source set today and grow as needed.
use std::fmt;
#[derive(Clone, Debug, Eq, PartialEq, Hash)]
pub struct Localization {
language_code: String,
country_code: Option<String>,
}
impl Localization {
pub fn new(language_code: impl Into<String>, country_code: Option<String>) -> Self {
Self { language_code: language_code.into(), country_code }
}
pub fn from_localization_code(code: &str) -> Option<Self> {
let (lang, country) = code.split_once('-').unwrap_or((code, ""));
if lang.is_empty() {
return None;
}
Some(Self {
language_code: lang.to_string(),
country_code: if country.is_empty() { None } else { Some(country.to_string()) },
})
}
pub fn language_code(&self) -> &str {
&self.language_code
}
pub fn country_code(&self) -> Option<&str> {
self.country_code.as_deref()
}
pub fn localization_code(&self) -> String {
match &self.country_code {
Some(c) => format!("{}-{}", self.language_code, c),
None => self.language_code.clone(),
}
}
}
impl Default for Localization {
fn default() -> Self {
Self::new("en", Some("GB".into()))
}
}
impl fmt::Display for Localization {
fn fmt(&self, f: &mut fmt::Formatter<'_>) -> fmt::Result {
f.write_str(&self.localization_code())
}
}
#[derive(Clone, Debug, Eq, PartialEq, Hash)]
pub struct ContentCountry {
country_code: String,
}
impl ContentCountry {
pub fn new(country_code: impl Into<String>) -> Self {
Self { country_code: country_code.into() }
}
pub fn country_code(&self) -> &str {
&self.country_code
}
}
impl Default for ContentCountry {
fn default() -> Self {
Self::new("GB")
}
}
impl fmt::Display for ContentCountry {
fn fmt(&self, f: &mut fmt::Formatter<'_>) -> fmt::Result {
f.write_str(&self.country_code)
}
}
#[cfg(test)]
mod tests {
use super::*;
#[test]
fn default_is_en_gb() {
let l = Localization::default();
assert_eq!(l.language_code(), "en");
assert_eq!(l.country_code(), Some("GB"));
assert_eq!(l.localization_code(), "en-GB");
}
#[test]
fn parse_localization_code() {
let l = Localization::from_localization_code("en-US").unwrap();
assert_eq!(l.language_code(), "en");
assert_eq!(l.country_code(), Some("US"));
let l = Localization::from_localization_code("de").unwrap();
assert_eq!(l.language_code(), "de");
assert_eq!(l.country_code(), None);
assert!(Localization::from_localization_code("").is_none());
}
}