Sylpheed/crates/sylpheed-export/src/video.rs

//! Movies: disc WMV → Ogg Theora, because Godot 4 plays Theora natively and
//! will never be taught to read WMV.
//!
//! The transcode command is **recorded in the manifest verbatim**. A modder who
//! dislikes the quality re-runs one line rather than reverse-engineering what
//! was done to their video, which is the whole reason this project converts the
//! disc instead of reading it at runtime.

use anyhow::{bail, Context, Result};
use std::path::Path;
use std::process::Command;

/// A movie in scope for this port.
pub struct Movie {
    /// Path under the disc root.
    pub src: &'static str,
    /// Output stem under `export/video/`.
    pub stem: &'static str,
    pub why: &'static str,
}

/// MISSION §6: the boot intro and the one new-game intro. The disc holds 3.3 GB
/// of video and transcoding all of it is not this milestone.
pub const MOVIES: &[Movie] = &[
    Movie {
        src: "dat/movie/ADV.wmv",
        stem: "ADV",
        why: "HANDOFF Q9: ADVERTISE_MOVIE -> ADV.wmv, and the boot intro and the \
              attract movie are the SAME asset -- there is no separate boot slot.",
    },
    Movie {
        src: "dat/movie/S00A.wmv",
        stem: "S00A",
        why: "HANDOFF Q9: MS00A -> S00A.wmv is the new-game intro. P7.",
    },
];

/// The encode.
///
/// `-q:v 8` was chosen by measurement, not taste: against the decoded source,
/// SSIM over a 10 s sample is 0.9863 at q6, **0.9896 at q8** and 0.9924 at q10,
/// and q8 is visually indistinguishable at 200 % zoom on the reel's hardest
/// case — fine serif text and soft gradients over near-black, which is where
/// Theora usually breaks first. MISSION §6 anticipated that 720p Theora might
/// be too poor and asked for the FFmpeg-GDExtension fallback to be *proposed*
/// if so. It is not: **no runtime dependency is needed, and none is requested.**
///
/// The stereo downmix, **stated explicitly rather than inherited**.
///
/// The disc ships movies in two audio profiles: 28 files are 5.1 WMA Pro (every
/// cutscene, including both movies this port needs) and 69 are already stereo.
/// A bare `-ac 2` therefore does two different things and records neither — the
/// stereo files pass through, and the 5.1 files are folded by **ffmpeg's default
/// matrix**. How loudly centre-channel dialogue sits against the music is a
/// CONTENT decision, and leaving it to a default means it is made by accident
/// and can move under an ffmpeg upgrade.
///
/// So the matrix is written out: **ITU-R BS.775, LFE dropped**, normalised by
/// `1/(1 + √½ + √½) = 0.4142` so the sum of coefficients cannot clip.
///
/// This does not change the audio. Measured against the inherited default over a
/// 25 s stretch, the residual is **−91 dB** — roughly one LSB at 16-bit, i.e.
/// coefficient rounding — and peak and mean levels agree to 0.1 dB. ffmpeg's
/// default *is* this matrix; the point is that the manifest now says so.
///
/// # 🔴 This is NOT the matrix MISSION §6 pins, and that was never said out loud
///
/// MISSION §6 records a **human decision of 2026-08-29** fixing the fold at
/// `FL = 1.0·FL + 0.707·FC + 0.707·BL` (plus 7.1 terms a 5.1 source does not
/// have). This constant is that matrix scaled by 0.4142 — the same relative
/// weighting, **7.65 dB quieter** — and until now nothing in the code, the
/// manifest or the docs said so. Recording the command you ran does not disclose
/// that it is not the command you were given.
///
/// The original justification for the deviation was *"the unnormalised form
/// clips: peak 0.0 dBFS"*, and that is a peak reading — the instrument
/// `docs/port/BLOCKED.md` records this port declaring unfit for the clipping
/// question, because one sample at full scale and two seconds of square wave
/// give the same number. Re-measured properly (float decode, whole file, count
/// the samples that would clamp):
///
/// | | peak | ≥ full scale | > +1 dB over | longest run |
/// |---|---|---|---|---|
/// | `ADV`, MISSION §6 | **+4.26 dBFS** | 4 406 / 13 187 900 | 1 874 | 0.333 ms |
/// | `S00A`, MISSION §6 | −1.34 dBFS | **0** | 0 | — |
///
/// So the pin really does overload `ADV` — and this constant is over-broad,
/// because `S00A` never needed it. The smallest single scalar under which
/// neither clamps is `1/1.6339 = 0.612`, +3.39 dB on today.
///
/// **Not changed here.** The level of a mix is what §6 reserves to a human
/// (*"adjust it deliberately, as a commit"*), so the export carries a warning
/// with these numbers instead. See `docs/port/DECISIONS.md`.
const DOWNMIX_51: &str = "pan=stereo|FL=0.4142*FL+0.2929*FC+0.2929*BL                          |FR=0.4142*FR+0.2929*FC+0.2929*BR";

/// How many audio channels the source declares.
fn channels(src: &Path) -> Result<u32> {
    let out = Command::new("ffprobe")
        .args([
            "-v", "error", "-select_streams", "a:0",
            "-show_entries", "stream=channels", "-of", "csv=p=0",
        ])
        .arg(src)
        .output()
        .context("run ffprobe -- is it on PATH?")?;
    Ok(String::from_utf8_lossy(&out.stdout).trim().parse().unwrap_or(2))
}

fn args(src: &Path, out: &Path, channels: u32) -> Vec<String> {
    let mut v: Vec<String> = [
        "-hide_banner", "-loglevel", "error", "-y",
        "-i", &src.display().to_string(),
        "-c:v", "libtheora", "-q:v", "8",
        "-c:a", "libvorbis", "-q:a", "5",
    ]
    .iter()
    .map(|s| s.to_string())
    .collect();
    // Only 5.1 sources are folded. A source that is already stereo is passed
    // through untouched rather than run through a matrix that would silently
    // reference channels it does not have.
    if channels == 6 {
        v.push("-af".into());
        v.push(DOWNMIX_51.into());
    }
    v.push("-ac".into());
    v.push("2".into());
    v.push(out.display().to_string());
    v
}

pub struct Transcoded {
    pub name: String,
    pub file: String,
    pub command: String,
    pub why: &'static str,
}

/// Transcode one movie, skipping the encode when the output already exists and
/// was produced by exactly this command against exactly this source.
///
/// `export/` is still regenerated wholesale — this is a cache, not a hand-edit.
/// The sidecar records the command and the source size, so any change to either
/// re-encodes. Without it every re-export pays ~4 minutes to produce a
/// byte-identical file, and an exporter nobody re-runs is worse than a cache.
pub fn transcode(disc: &Path, out: &Path, m: &Movie) -> Result<Option<Transcoded>> {
    let src = disc.join(m.src);
    if !src.exists() {
        return Ok(None);
    }
    let dir = out.join("video");
    std::fs::create_dir_all(&dir)?;
    let ogv = dir.join(format!("{}.ogv", m.stem));
    let stamp = dir.join(format!("{}.cmd", m.stem));

    let ch = channels(&src)?;
    let argv = args(&src, &ogv, ch);
    let command = format!("ffmpeg {}", argv.join(" "));
    let size = std::fs::metadata(&src)?.len();
    // The sidecar SAYS WHAT IT IS. It sits in the modder-facing asset tree next
    // to the `.ogv`, and MODDING rule 2's principle is that a generated file
    // should be tellable from a hand-made one by reading it -- a bare ffmpeg
    // line beside a video looks like something a modder should edit or delete.
    //
    // The header is NOT part of the cache key: `fresh` compares only the lines
    // that describe the encode. Otherwise rewording this comment would re-encode
    // four minutes of video to no purpose, which is a cache that punishes
    // documentation.
    let key = format!("{command}\nsource-bytes: {size}\nsource-channels: {ch}\n");
    let want = format!(
        "# Generated by sylpheed-export. NOT an asset and not hand-editable: this\n\
         # records how {}.ogv beside it was encoded, so a re-export can skip the\n\
         # encode when the source and the command are both unchanged. Deleting it\n\
         # only forces one re-encode. To change the video, override the .ogv under\n\
         # data/mods/ (MODDING rule 4) -- editing this file changes nothing.\n{key}",
        m.stem
    );

    let cache_key = |s: &str| -> String {
        s.lines()
            .filter(|l| !l.starts_with('#'))
            .collect::<Vec<_>>()
            .join("\n")
    };
    let fresh = ogv.exists()
        && std::fs::read_to_string(&stamp)
            .map(|s| cache_key(&s) == cache_key(&want))
            .unwrap_or(false);
    if !fresh {
        // Encode to a temp name and rename on success. A reader that catches
        // this mid-write sees no file at all rather than a valid-looking one
        // with a wrong duration -- ffprobe reported 33 s against a 137 s source
        // during one such race, with no error, and it looked exactly like
        // catastrophic truncation. The filesystem is shared with another agent,
        // so this is a race and not an edge case.
        let partial = dir.join(format!(".{}.partial.ogv", m.stem));
        let mut argv = argv.clone();
        let last = argv.len() - 1;
        argv[last] = partial.display().to_string();
        let status = Command::new("ffmpeg")
            .args(&argv)
            .status()
            .context("run ffmpeg -- is it on PATH?")?;
        if !status.success() {
            let _ = std::fs::remove_file(&partial);
            bail!("ffmpeg failed on {}", m.src);
        }
        std::fs::rename(&partial, &ogv)?;
    }
    // Refresh the sidecar whenever its TEXT differs, encode or no encode.
    //
    // It used to be written only inside the `!fresh` branch, which is right for
    // the cache and wrong for the file: a change to the header alone -- the part
    // deliberately excluded from the key -- would then never reach an existing
    // export, because nothing that reads the header can trigger the write that
    // updates it. The explanation would be correct in the source and absent on
    // disc, which is the same shape as every other documented-but-unexercised
    // thing this port has had to find the hard way.
    if std::fs::read_to_string(&stamp).map(|s| s != want).unwrap_or(true) {
        std::fs::write(&stamp, &want)?;
    }
    Ok(Some(Transcoded {
        name: m.stem.to_string(),
        file: format!("video/{}.ogv", m.stem),
        command,
        why: m.why,
    }))
}