quick_search/crates/quicksearch-core/src/extract/audio.rs

//! Audio tag extraction via [`lofty`]: title, artist, album, genre, and
//! comment concatenate into the searchable `text`.

use std::path::Path;

use lofty::{
    file::TaggedFileExt,
    probe::Probe,
    tag::{Accessor, ItemKey},
};

use super::{ExtractError, Extractor, Scratch};

pub struct AudioExtractor;

impl Extractor for AudioExtractor {
    fn supports(&self, mime: &str) -> bool {
        mime.starts_with("audio/")
    }

    fn extract(
        &self,
        path: &Path,
        out: &mut String,
        _scratch: &mut Scratch,
    ) -> Result<(), ExtractError> {
        let tagged = Probe::open(path)
            .map_err(|e| format!("lofty probe {}: {}", path.display(), e))?
            .read()
            .map_err(|e| format!("lofty read {}: {}", path.display(), e))?;

        // Straight into the caller's buffer: the fields are short and few,
        // and a `Vec<String>` then `join` allocated every piece twice over.
        if let Some(tag) = tagged.primary_tag().or_else(|| tagged.first_tag()) {
            // The `Accessor` shortcuts hand back a `Cow`, so their fallbacks
            // are bound here rather than inside an `or_else` that would let
            // the temporary die before it is read.
            let (title, artist, album) = (tag.title(), tag.artist(), tag.album());
            let mut push = |value: Option<&str>| {
                if let Some(v) = value.filter(|v: &&str| !v.is_empty()) {
                    if !out.is_empty() {
                        out.push(' ');
                    }
                    out.push_str(v);
                }
            };
            // A tag can carry a value under `ItemKey` or the `Accessor` shortcut.
            push(
                tag.get_string(&ItemKey::TrackTitle)
                    .filter(|v| !v.is_empty())
                    .or(title.as_deref()),
            );
            push(
                tag.get_string(&ItemKey::TrackArtist)
                    .filter(|v| !v.is_empty())
                    .or(artist.as_deref()),
            );
            push(
                tag.get_string(&ItemKey::AlbumTitle)
                    .filter(|v| !v.is_empty())
                    .or(album.as_deref()),
            );
            push(tag.get_string(&ItemKey::Genre));
            push(tag.get_string(&ItemKey::Comment));
        }

        Ok(())
    }
}

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

    /// The one-file form: these assert on text, not on buffer reuse.
    fn extract(path: &std::path::Path) -> Result<String, ExtractError> {
        let mut out = String::new();
        let mut scratch = Scratch::new(&crate::config::Config::default());
        AudioExtractor.extract(path, &mut out, &mut scratch).map(|()| out)
    }

    /// An ID3v2.3 tag carrying `frames`, then silent MPEG frames so the probe
    /// recognizes the format from content.
    fn write_mp3(tag: &str, frames: &[(&str, &str)]) -> std::path::PathBuf {
        let mut body = Vec::new();
        for (id, value) in frames {
            let mut payload = vec![0x00]; // ISO-8859-1
            payload.extend_from_slice(value.as_bytes());
            body.extend_from_slice(id.as_bytes());
            // ID3v2.3 frame sizes are plain big-endian, unlike the tag size.
            body.extend_from_slice(&(payload.len() as u32).to_be_bytes());
            body.extend_from_slice(&[0, 0]); // flags
            body.extend_from_slice(&payload);
        }

        let mut out = Vec::new();
        out.extend_from_slice(b"ID3");
        out.extend_from_slice(&[0x03, 0x00, 0x00]); // v2.3, no flags
                                                    // Tag size is syncsafe: seven bits per byte.
        let n = body.len() as u32;
        out.extend_from_slice(&[
            ((n >> 21) & 0x7F) as u8,
            ((n >> 14) & 0x7F) as u8,
            ((n >> 7) & 0x7F) as u8,
            (n & 0x7F) as u8,
        ]);
        out.extend_from_slice(&body);

        // MPEG-1 Layer III, 128 kbps, 44.1 kHz, no padding: 417-byte frames;
        // the probe confirms sync by finding the next frame where the first says.
        for _ in 0..4 {
            out.extend_from_slice(&[0xFF, 0xFB, 0x90, 0x00]);
            out.resize(out.len() + 413, 0);
        }

        let path = crate::testutil::scratch_dir(tag).join("track.mp3");
        std::fs::write(&path, &out).expect("write fixture mp3");
        path
    }

    #[test]
    fn tag_values_become_searchable_text() {
        let path = write_mp3(
            "audio-tags",
            &[
                ("TIT2", "Blue Monday"),
                ("TPE1", "New Order"),
                ("TALB", "Power Corruption"),
                ("TCON", "Synthpop"),
            ],
        );
        let out = extract(&path).expect("extract");
        for expected in ["Blue Monday", "New Order", "Power Corruption", "Synthpop"] {
            assert!(
                out.contains(expected),
                "{:?} missing from {:?}",
                expected,
                out
            );
        }
        assert_eq!(out, "Blue Monday New Order Power Corruption Synthpop");
    }

    #[test]
    fn an_untagged_file_yields_empty_text() {
        let path = write_mp3("audio-untagged", &[]);
        let out = extract(&path).expect("extract");
        assert!(out.is_empty(), "unexpected text {:?}", out);
    }

    #[test]
    fn supports_audio_mimes() {
        let e = AudioExtractor;
        assert!(e.supports("audio/mpeg"));
        assert!(e.supports("audio/flac"));
        assert!(!e.supports("video/mp4"));
        assert!(!e.supports("image/png"));
    }
}