gui-video-clipper/src-tauri/src/services/video_resolver.rs

use crate::models::{CookieSource, VideoMetadata};
use serde::Deserialize;
use std::collections::HashMap;
use std::process::Command;

#[derive(Debug, Deserialize)]
pub struct SubtitleFormat {
    pub ext: Option<String>,
    pub url: Option<String>,
}

#[derive(Debug, Deserialize)]
pub struct YtDlpJson {
    pub title: String,
    pub duration: Option<f64>,
    pub fps: Option<f64>,
    pub thumbnail: Option<String>,
    /// Manually authored subtitles: language_code -> [formats]
    #[serde(default)]
    pub subtitles: HashMap<String, Vec<SubtitleFormat>>,
    /// Auto-generated subtitles: language_code -> [formats]
    #[serde(default)]
    pub automatic_captions: HashMap<String, Vec<SubtitleFormat>>,
}

/// Check if subtitles have a VTT format for English (en, en-US, en-GB, en-orig).
fn find_english_key(map: &HashMap<String, Vec<SubtitleFormat>>) -> Option<&str> {
    // Prefer exact "en", then any en-* variant
    for key in ["en", "en-US", "en-GB", "en-orig"] {
        if map.contains_key(key) {
            return Some(key);
        }
    }
    // Try any key starting with "en"
    for key in map.keys() {
        if key.starts_with("en") {
            return Some(key.as_str());
        }
    }
    None
}

/// Determine caption availability: (has_captions, is_auto)
pub fn detect_captions(meta: &YtDlpJson) -> (bool, bool) {
    // Priority 1: manual English subtitles
    if find_english_key(&meta.subtitles).is_some() {
        return (true, false);
    }
    // Priority 2: auto-generated English captions
    if find_english_key(&meta.automatic_captions).is_some() {
        return (true, true);
    }
    (false, false)
}

pub fn parse_ytdlp_json(json_str: &str) -> Result<YtDlpJson, String> {
    serde_json::from_str::<YtDlpJson>(json_str)
        .map_err(|e| format!("Failed to parse yt-dlp JSON: {e}"))
}

pub fn resolve(url: &str, cookie_source: &CookieSource) -> Result<VideoMetadata, String> {
    let cookie_args = cookie_source.to_ytdlp_args();

    let mut meta_cmd = Command::new("yt-dlp");
    meta_cmd
        .arg("--dump-json")
        .arg("--no-download")
        .arg("--remote-components")
        .arg("ejs:github");
    for arg in &cookie_args {
        meta_cmd.arg(arg);
    }
    meta_cmd.arg(url);

    let meta_output = meta_cmd
        .output()
        .map_err(|e| format!("Failed to run yt-dlp: {e}"))?;

    if !meta_output.status.success() {
        let stderr = String::from_utf8_lossy(&meta_output.stderr);
        return Err(format!("yt-dlp metadata failed: {stderr}"));
    }

    let json_str = String::from_utf8_lossy(&meta_output.stdout);
    let meta = parse_ytdlp_json(&json_str)?;

    let (has_captions, captions_are_auto) = detect_captions(&meta);

    let mut stream_cmd = Command::new("yt-dlp");
    stream_cmd
        .arg("-g")
        .arg("--no-download")
        .arg("--remote-components")
        .arg("ejs:github");
    for arg in &cookie_args {
        stream_cmd.arg(arg);
    }
    stream_cmd.arg(url);

    let stream_output = stream_cmd
        .output()
        .map_err(|e| format!("Failed to get stream URL: {e}"))?;

    if !stream_output.status.success() {
        let stderr = String::from_utf8_lossy(&stream_output.stderr);
        return Err(format!("yt-dlp stream URL failed: {stderr}"));
    }

    let stream_url = String::from_utf8_lossy(&stream_output.stdout)
        .lines()
        .next()
        .unwrap_or("")
        .trim()
        .to_string();

    if stream_url.is_empty() {
        return Err("yt-dlp returned an empty stream URL".to_string());
    }

    Ok(VideoMetadata {
        url: url.to_string(),
        title: meta.title,
        duration: meta.duration.unwrap_or(0.0),
        fps: meta.fps.unwrap_or(30.0),
        thumbnail_url: meta.thumbnail,
        stream_url,
        has_captions,
        captions_are_auto,
    })
}

#[cfg(test)]
mod tests {
    use super::*;

    #[test]
    fn test_parse_ytdlp_json_valid() {
        let json = r#"{"title": "Test Video", "duration": 125.5, "fps": 29.97, "thumbnail": "https://i.ytimg.com/vi/abc/hqdefault.jpg"}"#;
        let result = parse_ytdlp_json(json).unwrap();
        assert_eq!(result.title, "Test Video");
        assert!((result.duration.unwrap() - 125.5).abs() < 0.001);
        assert!((result.fps.unwrap() - 29.97).abs() < 0.001);
        assert_eq!(
            result.thumbnail.unwrap(),
            "https://i.ytimg.com/vi/abc/hqdefault.jpg"
        );
    }

    #[test]
    fn test_parse_ytdlp_json_missing_optional_fields() {
        let json = r#"{"title": "Minimal Video"}"#;
        let result = parse_ytdlp_json(json).unwrap();
        assert_eq!(result.title, "Minimal Video");
        assert!(result.duration.is_none());
        assert!(result.fps.is_none());
        assert!(result.thumbnail.is_none());
        assert!(result.subtitles.is_empty());
        assert!(result.automatic_captions.is_empty());
    }

    #[test]
    fn test_parse_ytdlp_json_invalid() {
        let result = parse_ytdlp_json("not json");
        assert!(result.is_err());
    }

    #[test]
    fn test_detect_captions_manual() {
        let json = r#"{"title": "T", "subtitles": {"en": [{"ext": "vtt", "url": "http://x"}]}, "automatic_captions": {}}"#;
        let meta = parse_ytdlp_json(json).unwrap();
        let (has, is_auto) = detect_captions(&meta);
        assert!(has);
        assert!(!is_auto);
    }

    #[test]
    fn test_detect_captions_auto_only() {
        let json = r#"{"title": "T", "subtitles": {}, "automatic_captions": {"en": [{"ext": "vtt", "url": "http://x"}]}}"#;
        let meta = parse_ytdlp_json(json).unwrap();
        let (has, is_auto) = detect_captions(&meta);
        assert!(has);
        assert!(is_auto);
    }

    #[test]
    fn test_detect_captions_none() {
        let json = r#"{"title": "T"}"#;
        let meta = parse_ytdlp_json(json).unwrap();
        let (has, _) = detect_captions(&meta);
        assert!(!has);
    }

    #[test]
    fn test_detect_captions_en_variant() {
        let json = r#"{"title": "T", "subtitles": {"en-US": [{"ext": "vtt"}]}}"#;
        let meta = parse_ytdlp_json(json).unwrap();
        let (has, is_auto) = detect_captions(&meta);
        assert!(has);
        assert!(!is_auto);
    }
}