JRay-public-server/tests/injection.rs

//! Injection resistance — SQL, JSON and header.
//!
//! These are regression tests for properties the design already provides, kept
//! separate from `api.rs` because their purpose is different: `api.rs` asserts the
//! spec's behaviour, this asserts that hostile input cannot escape its layer.
//!
//! Two distinct defences are at work, and it is worth being precise about which
//! applies where, because they fail differently:
//!
//! 1. **Parameterised queries** (§7, §8). Every value reaches SQLite through
//!    `params![]`; the only `format!`-built SQL interpolates compile-time
//!    constants (a column list and a status literal). So a value carrying SQL
//!    syntax is bound as *data* and simply matches nothing.
//! 2. **Closed-vocabulary validation** (§5a, §6 stage 2). Identifiers are
//!    regex-constrained and free text is restricted to a closed character class,
//!    so most injection strings are rejected before they reach the database.
//!
//! Defence 1 is what actually prevents injection; defence 2 means an attacker
//! usually cannot even reach it. Testing both matters: if validation were ever
//! loosened, these tests should still pass on the strength of parameterisation
//! alone.

use std::sync::Arc;

use axum::body::Body;
use axum::http::{Request, StatusCode};
use http_body_util::BodyExt;
use jray_server::app;
use jray_server::config::Config;
use jray_server::db::Db;
use jray_server::ratelimit::RateLimiter;
use jray_server::state::AppState;
use jray_server::tmdb::TmdbClient;
use serde_json::{json, Value};
use tower::ServiceExt;

/// Payloads spanning the usual SQL-injection shapes: boolean tautology, statement
/// termination, stacked statements, UNION exfiltration, comment truncation, and
/// string-concatenation exfiltration.
const SQL_PAYLOADS: &[&str] = &[
    "1' OR '1'='1",
    "1'; DROP TABLE manifests;--",
    "1 UNION SELECT token_hash FROM contributors",
    "' OR 1=1--",
    "1'||(SELECT token_hash FROM contributors)||'",
    "1)) OR 1=1 --",
    "'; UPDATE manifests SET status='listed' WHERE 1=1;--",
    "1/**/UNION/**/SELECT/**/1",
    "x' AND (SELECT COUNT(*) FROM sqlite_master)>0 --",
    "\"; DELETE FROM scenes; --",
];

struct TestServer {
    router: axum::Router,
    db: Db,
    _dir: TempDir,
}

struct TempDir(std::path::PathBuf);

impl TempDir {
    fn new(tag: &str) -> Self {
        let mut p = std::env::temp_dir();
        p.push(format!("jray-inj-{}-{}", tag, unique()));
        std::fs::create_dir_all(&p).expect("creating temp dir");
        Self(p)
    }
    fn db_path(&self) -> String {
        self.0.join("test.db").to_string_lossy().into_owned()
    }
}

impl Drop for TempDir {
    fn drop(&mut self) {
        let _ = std::fs::remove_dir_all(&self.0);
    }
}

fn unique() -> String {
    use std::sync::atomic::{AtomicU64, Ordering};
    static N: AtomicU64 = AtomicU64::new(0);
    let t = std::time::SystemTime::now()
        .duration_since(std::time::UNIX_EPOCH)
        .map(|d| d.as_nanos())
        .unwrap_or(0);
    format!("{t}-{}", N.fetch_add(1, Ordering::Relaxed))
}

impl TestServer {
    fn new(tag: &str) -> Self {
        let dir = TempDir::new(tag);
        let db = Db::open(&dir.db_path()).expect("opening database");
        let config = Arc::new(Config {
            bind: "127.0.0.1:0".into(),
            db_path: dir.db_path(),
            tmdb_api_key: None,
            tmdb_base_url: "http://127.0.0.1:1".into(),
            trusted_proxies: Vec::new(),
            server_id: "test.example".into(),
            publish_peer_directory: true,
            contact: Some("admin@test.example".into()),
            request_timeout: std::time::Duration::from_secs(30),
            job_batch: 8,
            job_poll_interval: std::time::Duration::from_secs(3600),
        });
        let state = AppState {
            db: db.clone(),
            config: config.clone(),
            limiter: Arc::new(RateLimiter::new()),
            tmdb: Arc::new(TmdbClient::new(config.tmdb_base_url.clone(), None)),
        };
        Self { router: app::router(state), db, _dir: dir }
    }

    async fn send(&self, req: Request<Body>) -> (StatusCode, Value) {
        let resp = self.router.clone().oneshot(req).await.expect("router call");
        let status = resp.status();
        let bytes = resp.into_body().collect().await.expect("body").to_bytes();
        let body = if bytes.is_empty() {
            Value::Null
        } else {
            serde_json::from_slice(&bytes)
                .unwrap_or(Value::String(String::from_utf8_lossy(&bytes).into_owned()))
        };
        (status, body)
    }

    async fn get(&self, uri: &str) -> (StatusCode, Value) {
        self.send(Request::builder().uri(uri).body(Body::empty()).unwrap()).await
    }

    async fn post(&self, uri: &str, token: Option<&str>, body: &Value) -> (StatusCode, Value) {
        let mut b =
            Request::builder().method("POST").uri(uri).header("content-type", "application/json");
        if let Some(t) = token {
            b = b.header("authorization", format!("Bearer {t}"));
        }
        self.send(b.body(Body::from(body.to_string())).unwrap()).await
    }

    async fn token(&self) -> String {
        let (_, body) = self.post("/api/v1/tokens", None, &json!({})).await;
        body["token"].as_str().expect("token").to_string()
    }

    /// Confirms the schema is intact and the expected row counts hold.
    ///
    /// A successful injection would most likely drop a table or delete rows, so
    /// this is the assertion that actually matters after each payload.
    async fn assert_schema_intact(&self) {
        let tables: Vec<String> = self
            .db
            .read(|conn| {
                let mut stmt = conn
                    .prepare("SELECT name FROM sqlite_master WHERE type='table' ORDER BY name")?;
                let rows = stmt
                    .query_map([], |r| r.get::<_, String>(0))?
                    .collect::<rusqlite::Result<Vec<_>>>()?;
                Ok(rows)
            })
            .await
            .expect("listing tables");

        for expected in [
            "contributors",
            "jobs",
            "manifest_actors",
            "manifests",
            "people",
            "reports",
            "scenes",
            "titles",
            "tmdb_cache",
        ] {
            assert!(
                tables.iter().any(|t| t == expected),
                "table {expected} is missing — an injection may have dropped it. tables: {tables:?}"
            );
        }
    }
}

fn urlencode(s: &str) -> String {
    let mut out = String::new();
    for b in s.bytes() {
        match b {
            b'A'..=b'Z' | b'a'..=b'z' | b'0'..=b'9' | b'-' | b'_' | b'.' | b'~' => {
                out.push(b as char)
            }
            _ => out.push_str(&format!("%{b:02X}")),
        }
    }
    out
}

// ---------------------------------------------------------------------------
// SQL injection — query parameters
// ---------------------------------------------------------------------------

#[tokio::test]
async fn sql_payloads_in_query_parameters_are_inert() {
    let s = TestServer::new("query");

    for payload in SQL_PAYLOADS {
        let enc = urlencode(payload);
        for uri in [
            format!("/api/v1/manifests/exists?tmdb_id={enc}"),
            format!("/api/v1/manifests/exists?imdb_id={enc}"),
            format!("/api/v1/manifests/movie?tmdb_id={enc}"),
            format!("/api/v1/manifests/movie?imdb_id={enc}"),
            format!("/api/v1/manifests/episode?series_tmdb_id={enc}&season=1&episode=1"),
            format!("/api/v1/manifests/series/{enc}"),
            format!("/api/v1/manifests/exists?tmdb_id=1&runtime_sec={enc}"),
        ] {
            let (status, body) = s.get(&uri).await;
            // The payload is bound as data, so it matches nothing. What must never
            // happen is a 5xx, which would mean SQLite saw it as syntax.
            assert!(
                status.is_success()
                    || status == StatusCode::NOT_FOUND
                    || status == StatusCode::BAD_REQUEST,
                "payload {payload:?} on {uri} produced {status} — expected data-not-found, \
                 not a server error. body: {body}"
            );
        }
    }

    s.assert_schema_intact().await;
}

#[tokio::test]
async fn sql_payloads_in_path_parameters_are_inert() {
    let s = TestServer::new("path");

    for payload in SQL_PAYLOADS {
        let enc = urlencode(payload);
        for uri in [
            format!("/api/v1/manifests/{enc}"),
            format!("/api/v1/manifests/{enc}/status"),
            format!("/api/v1/manifests/series/{enc}"),
        ] {
            let (status, body) = s.get(&uri).await;
            assert!(
                !status.is_server_error(),
                "payload {payload:?} on {uri} produced {status}: {body}"
            );
        }
    }

    s.assert_schema_intact().await;
}

// ---------------------------------------------------------------------------
// SQL injection — JSON body fields
// ---------------------------------------------------------------------------

#[tokio::test]
async fn sql_payloads_in_identifier_fields_are_rejected() {
    // §6 stage 2 regex-constrains every identifier, so these never even reach the
    // query layer. The response must be a clean 400 naming the field.
    let s = TestServer::new("body-ids");
    let token = s.token().await;

    for payload in SQL_PAYLOADS {
        let manifest = json!({
            "jmanifest_version": 2,
            "identity": { "type": "movie", "tmdb_id": payload },
            "cut": { "runtime_sec": 100.0 },
            "actors": [ { "tmdb_id": "884", "scenes": [{"start":1.0,"end":2.0}] } ]
        });
        let (status, body) = s.post("/api/v1/manifests", Some(&token), &manifest).await;
        assert_eq!(
            status,
            StatusCode::BAD_REQUEST,
            "payload {payload:?} should be rejected by validation: {body}"
        );
    }

    s.assert_schema_intact().await;
}

#[tokio::test]
async fn sql_payloads_in_free_text_fields_are_rejected() {
    // The two free-text fields (§5a) are the only place arbitrary strings could
    // arrive. The closed character class excludes quotes, semicolons and digits,
    // which is what makes SQL syntax unrepresentable there.
    let s = TestServer::new("body-text");
    let token = s.token().await;

    for payload in SQL_PAYLOADS {
        for manifest in [
            json!({
                "jmanifest_version": 2,
                "identity": { "type": "movie", "tmdb_id": "504172", "title": payload },
                "cut": { "runtime_sec": 100.0 },
                "actors": [ { "tmdb_id": "884", "scenes": [{"start":1.0,"end":2.0}] } ]
            }),
            json!({
                "jmanifest_version": 2,
                "identity": { "type": "movie", "tmdb_id": "504172" },
                "cut": { "runtime_sec": 100.0 },
                "actors": [ { "name": payload, "tmdb_id": "884", "scenes": [{"start":1.0,"end":2.0}] } ]
            }),
        ] {
            let (status, body) = s.post("/api/v1/manifests", Some(&token), &manifest).await;
            assert_eq!(
                status,
                StatusCode::BAD_REQUEST,
                "free-text payload {payload:?} should be rejected: {body}"
            );
        }
    }

    s.assert_schema_intact().await;
}

#[tokio::test]
async fn sql_payloads_in_a_report_note_cannot_escape() {
    // `note` is the one field that accepts relatively free text (control
    // characters stripped, length capped) because only the operator reads it. It
    // reaches the database, so it is the strongest test of parameterisation:
    // validation is *not* filtering SQL syntax here.
    let s = TestServer::new("report-note");
    let token = s.token().await;

    let (_, body) = s
        .post(
            "/api/v1/manifests",
            Some(&token),
            &json!({
                "jmanifest_version": 2,
                "identity": { "type": "movie", "tmdb_id": "504172" },
                "cut": { "runtime_sec": 100.0 },
                "actors": [ { "tmdb_id": "884", "scenes": [{"start":1.0,"end":2.0}] } ]
            }),
        )
        .await;
    let id = body["manifest_id"].as_str().expect("manifest id").to_string();

    for payload in SQL_PAYLOADS {
        let (status, body) = s
            .post(
                &format!("/api/v1/manifests/{id}/report"),
                None,
                &json!({ "reason": "spam", "note": payload }),
            )
            .await;
        assert!(
            status.is_success() || status == StatusCode::TOO_MANY_REQUESTS,
            "note payload {payload:?} produced {status}: {body}"
        );
        if status.is_success() {
            s.assert_schema_intact().await;
        }
    }

    // The notes were stored verbatim as *data* — proving they were bound, not
    // executed. Verified by reading them back out.
    let stored: i64 =
        s.db.read(|conn| Ok(conn.query_row("SELECT COUNT(*) FROM reports", [], |r| r.get(0))?))
            .await
            .expect("counting reports");
    assert!(stored > 0, "reports should have been stored as inert data");
}

#[tokio::test]
async fn sql_payloads_in_a_bearer_token_are_inert() {
    // The token is hashed before it reaches any query, but a payload arriving via
    // a header must still not produce a 5xx.
    let s = TestServer::new("token-inj");

    for payload in SQL_PAYLOADS {
        let req = Request::builder()
            .method("POST")
            .uri("/api/v1/manifests")
            .header("content-type", "application/json")
            .header("authorization", format!("Bearer {payload}"))
            .body(Body::from(
                json!({
                    "jmanifest_version": 2,
                    "identity": { "type": "movie", "tmdb_id": "504172" },
                    "cut": { "runtime_sec": 100.0 },
                    "actors": [ { "tmdb_id": "884", "scenes": [{"start":1.0,"end":2.0}] } ]
                })
                .to_string(),
            ))
            .unwrap();
        let (status, body) = s.send(req).await;
        assert_eq!(
            status,
            StatusCode::UNAUTHORIZED,
            "token payload {payload:?} produced {status}: {body}"
        );
    }

    s.assert_schema_intact().await;
}

#[tokio::test]
async fn sql_payloads_in_the_batch_exists_body_are_inert() {
    let s = TestServer::new("batch-inj");
    let items: Vec<Value> = SQL_PAYLOADS.iter().map(|p| json!({ "tmdb_id": p })).collect();
    let (status, body) = s.post("/api/v1/manifests/exists", None, &json!({ "items": items })).await;
    assert_eq!(status, StatusCode::OK, "{body}");
    // Each malformed item degrades to "absent" rather than erroring the batch.
    for result in body["results"].as_array().expect("results") {
        assert_eq!(result["exists"], false);
    }
    s.assert_schema_intact().await;
}

// ---------------------------------------------------------------------------
// JSON injection / parser abuse
// ---------------------------------------------------------------------------

#[tokio::test]
async fn json_structure_abuse_is_rejected_cleanly() {
    // A parser handed hostile structure must fail with 400/413, never 5xx and
    // never a hang (§6 stage 1: "a parser handed an unbounded body is a
    // denial-of-service primitive").
    let s = TestServer::new("json-abuse");
    let token = s.token().await;

    let cases: Vec<(&str, String)> = vec![
        ("deep nesting", format!("{}{}", "[".repeat(20_000), "]".repeat(20_000))),
        ("unterminated", "{\"identity\": {\"type\": \"movie\"".to_string()),
        ("duplicate keys", r#"{"jmanifest_version":2,"jmanifest_version":2}"#.to_string()),
        ("null bytes", "{\"jmanifest_version\":\u{0}1}".to_string()),
        ("huge number", format!("{{\"jmanifest_version\":{}}}", "9".repeat(5000))),
        ("nan literal", r#"{"jmanifest_version":2,"cut":{"runtime_sec":NaN}}"#.to_string()),
        ("bare array", "[1,2,3]".to_string()),
        ("bare string", "\"just a string\"".to_string()),
        ("empty body", String::new()),
        (
            "prototype-style key",
            r#"{"__proto__":{"admin":true},"jmanifest_version":2}"#.to_string(),
        ),
    ];

    for (label, body) in cases {
        let req = Request::builder()
            .method("POST")
            .uri("/api/v1/manifests")
            .header("content-type", "application/json")
            .header("authorization", format!("Bearer {token}"))
            .body(Body::from(body))
            .unwrap();
        let (status, resp) = s.send(req).await;
        assert!(
            status == StatusCode::BAD_REQUEST || status == StatusCode::PAYLOAD_TOO_LARGE,
            "{label} produced {status}, expected a clean rejection: {resp}"
        );
    }

    s.assert_schema_intact().await;
}

#[tokio::test]
async fn non_finite_scene_times_are_rejected() {
    // §6 explicitly rejects NaN/Infinity. They cannot arrive as JSON literals, but
    // they can arrive as overflowing decimals, which parse to f64 infinity.
    let s = TestServer::new("nonfinite");
    let token = s.token().await;

    // Sent as raw JSON text rather than via `json!`, because rustc refuses an
    // out-of-range float literal — and the point is to make the *server's* parser
    // handle it, which is the real attack path.
    let raw = r#"{"jmanifest_version":2,
        "identity":{"type":"movie","tmdb_id":"504172"},
        "cut":{"runtime_sec":100.0},
        "actors":[{"tmdb_id":"884","scenes":[[1.0,1e400]]}]}"#;

    let req = Request::builder()
        .method("POST")
        .uri("/api/v1/manifests")
        .header("content-type", "application/json")
        .header("authorization", format!("Bearer {token}"))
        .body(Body::from(raw))
        .unwrap();
    let (status, body) = s.send(req).await;
    assert_eq!(status, StatusCode::BAD_REQUEST, "{body}");

    // Likewise an overflowing runtime.
    let raw = r#"{"jmanifest_version":2,
        "identity":{"type":"movie","tmdb_id":"504172"},
        "cut":{"runtime_sec":1e400},
        "actors":[{"tmdb_id":"884","scenes":[{"start":1.0,"end":2.0}]}]}"#;
    let req = Request::builder()
        .method("POST")
        .uri("/api/v1/manifests")
        .header("content-type", "application/json")
        .header("authorization", format!("Bearer {token}"))
        .body(Body::from(raw))
        .unwrap();
    let (status, body) = s.send(req).await;
    assert_eq!(status, StatusCode::BAD_REQUEST, "{body}");
}

// ---------------------------------------------------------------------------
// Header injection
// ---------------------------------------------------------------------------

#[tokio::test]
async fn crlf_in_a_header_value_cannot_split_the_response() {
    // A CRLF-carrying header value must not appear in the response as new headers.
    // `http` rejects such values at construction, so this asserts the invariant
    // holds at the boundary rather than relying on our own escaping.
    let bad = "1.2.3.4\r\nX-Injected: yes";
    assert!(
        axum::http::HeaderValue::from_str(bad).is_err(),
        "the http crate must refuse CRLF in header values"
    );

    // And a percent-encoded variant reaching a handler stays inert data.
    let s = TestServer::new("crlf");
    let (status, _) = s.get("/api/v1/manifests/exists?tmdb_id=1%0D%0AX-Injected:%20yes").await;
    assert!(!status.is_server_error());
    s.assert_schema_intact().await;
}

#[tokio::test]
async fn oversized_headers_do_not_take_the_server_down() {
    let s = TestServer::new("big-header");
    let big = "a".repeat(100_000);
    let req = Request::builder()
        .uri("/api/v1/manifests/exists?tmdb_id=1")
        .header("x-filler", big)
        .body(Body::empty())
        .unwrap();
    let (status, _) = s.send(req).await;
    assert!(!status.is_server_error(), "got {status}");
}

// ---------------------------------------------------------------------------
// Path traversal
// ---------------------------------------------------------------------------

#[tokio::test]
async fn path_traversal_attempts_reach_no_filesystem() {
    // The server serves no files at all, so traversal has nowhere to go. Asserted
    // anyway, because the manifest id is a path segment.
    let s = TestServer::new("traversal");
    for probe in [
        "..%2F..%2F..%2Fetc%2Fpasswd",
        "....%2F%2F....%2F%2Fetc%2Fpasswd",
        "%2e%2e%2f%2e%2e%2fetc%2fshadow",
        "..%5C..%5Cwindows%5Csystem32",
        "%00/etc/passwd",
    ] {
        let (status, body) = s.get(&format!("/api/v1/manifests/{probe}")).await;
        assert!(
            status == StatusCode::NOT_FOUND || status == StatusCode::BAD_REQUEST,
            "probe {probe} produced {status}: {body}"
        );
        // Nothing that looks like file content should ever come back.
        let text = body.to_string();
        assert!(!text.contains("root:"), "probe {probe} returned passwd-like content");
    }
}

// ---------------------------------------------------------------------------
// Unicode and encoding tricks against the §5a character class
// ---------------------------------------------------------------------------

#[tokio::test]
async fn unicode_tricks_cannot_smuggle_text_past_the_character_class() {
    // §5a's class is checked *after* NFC normalisation, so decomposed and
    // compatibility forms must not provide a way in. Fullwidth digits are the
    // sharpest case: NFKC would fold them to ASCII digits, but NFC does not, and
    // they are `Nd` (not a letter), so the class rejects them either way.
    let s = TestServer::new("unicode");
    let token = s.token().await;

    for payload in [
        "Ａｃｔｏｒ　１２３",        // fullwidth letters and digits
        "Steve\u{FEFF}Buscemi",      // zero-width no-break space
        "Ste\u{0301}ve\u{202E}",     // combining acute plus bidi override
        "𝐒𝐭𝐞𝐯𝐞",                     // mathematical bold (compatibility form)
        "Steve\u{2028}Buscemi",      // line separator
        "\u{1F600} Actor",           // emoji
        "Actor\u{00A0}Name\u{0000}", // nbsp plus NUL
    ] {
        let (status, body) = s
            .post(
                "/api/v1/manifests",
                Some(&token),
                &json!({
                    "jmanifest_version": 2,
                    "identity": { "type": "movie", "tmdb_id": "504172" },
                    "cut": { "runtime_sec": 100.0 },
                    "actors": [ { "name": payload, "tmdb_id": "884", "scenes": [{"start":1.0,"end":2.0}] } ]
                }),
            )
            .await;
        assert_eq!(
            status,
            StatusCode::BAD_REQUEST,
            "unicode payload {payload:?} should be rejected: {body}"
        );
    }
}

#[tokio::test]
async fn the_audio_signature_field_cannot_carry_arbitrary_bytes() {
    // §3: a variable-length blob would be a payload channel — "precisely what §5a
    // closes". Length is fixed and every byte is structurally constrained.
    let s = TestServer::new("audio-sig");
    let token = s.token().await;

    for sig in [
        "v1:aGVsbG8gd29ybGQ=",                  // too short to be a signature
        &format!("v1:{}", "/".repeat(4000)),    // high bit set throughout
        &format!("v1:{}", "A".repeat(100_000)), // oversized
        "not-base64-at-all",                    // missing version prefix
        &"A".repeat(1720),                      // unprefixed
    ] {
        let (status, body) = s
            .post(
                "/api/v1/manifests",
                Some(&token),
                &json!({
                    "jmanifest_version": 2,
                    "identity": { "type": "movie", "tmdb_id": "504172" },
                    "cut": { "runtime_sec": 6420.5, "audio_signature": sig },
                    "actors": [ { "tmdb_id": "884", "scenes": [{"start":1.0,"end":2.0}] } ]
                }),
            )
            .await;
        assert_eq!(
            status,
            StatusCode::BAD_REQUEST,
            "signature {:?} should be rejected: {body}",
            sig.chars().take(40).collect::<String>()
        );
    }
}