//! TRACES: NFR-SEC-2
//! Taking the credentials back out of a line that already contains them.
//!
//! NFR-SEC-2 says credentials are never written to logs. NFR-OPS-1 restates it
//! as an obligation on the diagnostics path specifically — "automatic
//! redaction of credentials and tokens" — and the word doing the work is
//! *automatic*. A rule that every call site must remember is not a rule; it is
//! a hope, and it fails the first time somebody debugging a 401 writes
//! `log::debug!("{response:?}")` at two in the morning and forgets to take it
//! out. So the redaction happens once, at the sink, on the formatted line,
//! after every call site has had its say.
//!
//! On Android this is not a defence-in-depth nicety. The log lives in the
//! app's *external* directory so that `adb pull` can reach it
//! ([`crate::state`]), which means anyone holding the device can read it, and
//! a Nextcloud app password in there is a working credential for the user's
//! whole server.
//!
//! # What it looks for, and why not a regex
//!
//! A credential in a log line is nearly always adjacent to a word that names
//! it — `appPassword`, `Authorization`, `token=` — because it got there
//! through a `Debug` impl, a serialised request, or a URL. That adjacency is
//! the only reliable signal there is: the app password Nextcloud issues is an
//! opaque 72-character string with no structure to match on, so a scanner that
//! hunted for *secret-shaped* text would find every base64 blob and every
//! content hash in the file and redact those instead.
//!
//! Hence a keyword scanner, hand-rolled rather than `regex`. The workspace has
//! no regex dependency and this is not worth acquiring one for — the grammar
//! is "a known word, an `=` or a `:`, a value" plus the two forms that carry a
//! credential with no keyword at all: an `Authorization` scheme and a URL's
//! userinfo. Three rules, each of which fits in a function and has a test.
//!
//! # What it deliberately leaves alone
//!
//! **Filesystem paths, and the names of the user's own photographs.** They are
//! not in NFR-SEC-2's list, they are not in NFR-SEC-5's, and they are the
//! single most useful thing in a log about a file that would not open. A
//! diagnostics file that says "failed to decode <redacted>" is not a
//! diagnostic. The rule NFR-OPS-1 states — an explicit preview-and-consent
//! step before anything leaves the device — is the one that governs paths, and
//! it governs them better than scrubbing would, because it lets the user look.
//!
//! **Face data (NFR-SEC-5).** Not because it is permitted here, but because
//! this is the wrong instrument for it. An embedding is 512 floats; by the
//! time one has reached a formatted log line, redacting it would be a guess at
//! what a `[f32]` looks like in prose. NFR-SEC-5 makes confinement
//! *structural* — "the code path does not exist" — and the sink's contribution
//! to that is to not be one: it opens no bundle, uploads nothing, and adds no
//! new route off the device. The one thing it does do about the shape of the
//! problem is cap the line length (see [`super::MAX_LINE_BYTES`]), so a
//! `{embedding:?}` that should never have been written costs kilobytes rather
//! than megabytes and is obvious in the file rather than buried.

/// What a redacted value is replaced by. Chosen to be greppable and obviously
/// not a value: a reader finding this in a log knows something was removed,
/// which an empty string or a row of asterisks would not tell them.
pub const PLACEHOLDER: &str = "<redacted>";

/// The words that introduce a credential.
///
/// Matched case-insensitively and only on a whole-word boundary, so `password`
/// does not fire inside `passwordless` and `token` does not fire inside
/// `tokenizer`. Longer entries are not redundant with shorter ones for the
/// same reason — `apppassword` has no boundary before its `password`, so
/// without its own entry `"appPassword": "…"` would sail through, and that is
/// the exact key Nextcloud's Login Flow v2 returns the credential under
/// (`dr_sync_nextcloud::auth::AppCredentials`).
const SENSITIVE_KEYS: &[&str] = &[
    "apppassword",
    "app_password",
    "password",
    "passwd",
    "pwd",
    "access_token",
    "refresh_token",
    "id_token",
    "apikey",
    "api_key",
    "authorization",
    "credentials",
    "credential",
    "secret",
    "token",
];

/// The `Authorization` schemes that carry the credential in the value rather
/// than after a keyword. `Basic dXNlcjpwdw==` is `login:password` in base64 —
/// reversible with one shell command — and every WebDAV request this app makes
/// is signed with one (`dr_sync_nextcloud`, `basic_auth`).
const AUTH_SCHEMES: &[&str] = &["basic ", "bearer "];

/// Remove anything that looks like a credential from one formatted line.
///
/// Cheap enough for the write path: one ASCII-lowercased copy and a single
/// left-to-right pass, with no allocation per match beyond the output string.
/// Non-ASCII is untouched by the lowercasing, which is what keeps the byte
/// offsets of the copy and the original identical — `to_lowercase` would not,
/// and a one-byte drift would slice a message mid-character.
pub fn redact(line: &str) -> String {
    let lower = line.to_ascii_lowercase();
    let low = lower.as_bytes();

    let mut out = String::with_capacity(line.len());
    // Everything from here to the current position is verbatim text not yet
    // copied, so an unmatched line copies itself in one `push_str`.
    let mut copied = 0usize;
    let mut i = 0usize;

    while i < low.len() {
        match secret_at(low, i) {
            Some((start, end)) => {
                out.push_str(&line[copied..start]);
                out.push_str(PLACEHOLDER);
                copied = end;
                i = end;
            }
            None => i += 1,
        }
    }

    out.push_str(&line[copied..]);
    out
}

/// The byte range of a secret beginning at or just after `i`, if there is one.
///
/// Every rule is anchored on an ASCII byte, and every boundary it returns is
/// found by scanning for ASCII delimiters — which cannot occur inside a
/// multi-byte UTF-8 sequence — so the ranges are always char boundaries even
/// though the scan is over bytes.
fn secret_at(low: &[u8], i: usize) -> Option<(usize, usize)> {
    if let Some(range) = keyed_value_at(low, i) {
        return Some(range);
    }
    if let Some(range) = bare_scheme_at(low, i) {
        return Some(range);
    }
    url_userinfo_at(low, i)
}

/// `password=hunter2`, `"appPassword": "…"`, `Authorization: Basic …`.
fn keyed_value_at(low: &[u8], i: usize) -> Option<(usize, usize)> {
    if i > 0 && is_word_byte(low[i - 1]) {
        return None;
    }
    for key in SENSITIVE_KEYS {
        if !low[i..].starts_with(key.as_bytes()) {
            continue;
        }
        let after = i + key.len();
        // A whole word, so `tokenizer` is not a token and `secretary` is not
        // a secret. `continue` rather than `return`: a short key failing its
        // boundary test must not mask a longer one that would have passed,
        // which is how `credential` would otherwise swallow `credentials`.
        if low.get(after).is_some_and(|b| is_word_byte(*b)) {
            continue;
        }
        return value_after_assignment(low, after);
    }
    None
}

/// The value introduced by an `=` or a `:` following a key.
///
/// Requiring one of those two is what keeps prose out of it. Plenty of log
/// lines say the word — "password rejected", "no token yet" — and a rule that
/// redacted the next word after any mention of a credential would make those
/// lines unreadable while protecting nothing.
fn value_after_assignment(low: &[u8], mut j: usize) -> Option<(usize, usize)> {
    j = skip_spaces(low, j);
    // The closing quote of a quoted key: `"password": "…"`.
    if matches!(low.get(j), Some(b'"' | b'\'')) {
        j = skip_spaces(low, j + 1);
    }
    if !matches!(low.get(j), Some(b'=' | b':')) {
        return None;
    }
    j = skip_spaces(low, j + 1);

    // An opening quote is stepped over rather than redacted, so the result is
    // still shaped like what it replaced: `"password": "<redacted>"` reads as
    // a redacted field, `"password": <redacted>` reads as damage.
    let quote = match low.get(j) {
        Some(&q) if q == b'"' || q == b'\'' => {
            j += 1;
            Some(q)
        }
        _ => None,
    };

    // `Authorization: Basic dXNlcjpwdw==` — keep the scheme, take the rest.
    // Which scheme was in use is diagnostic (a request signed as `Bearer`
    // where the app only ever issues `Basic` is a bug worth seeing) and it is
    // not itself a secret.
    for scheme in AUTH_SCHEMES {
        if low[j..].starts_with(scheme.as_bytes()) {
            j = skip_spaces(low, j + scheme.len());
            break;
        }
    }

    let start = j;
    let end = match quote {
        Some(q) => low[start..]
            .iter()
            .position(|b| *b == q)
            .map_or(low.len(), |n| start + n),
        None => value_end(low, start),
    };

    // `password=` with nothing after it has nothing to hide, and replacing an
    // empty value would only make the line say less.
    (end > start).then_some((start, end))
}

/// `Basic dXNlcjpwdw==` on its own, with no keyword in front of it — a header
/// dumped by its value, or a `curl` line pasted into a message.
fn bare_scheme_at(low: &[u8], i: usize) -> Option<(usize, usize)> {
    if i > 0 && is_word_byte(low[i - 1]) {
        return None;
    }
    let scheme = AUTH_SCHEMES
        .iter()
        .find(|scheme| low[i..].starts_with(scheme.as_bytes()))?;
    let start = skip_spaces(low, i + scheme.len());
    let end = value_end(low, start);
    // Unlike the keyed rule, nothing here has established that a credential
    // was intended — and `basic` is an ordinary English word. "using basic
    // sRGB as the fallback" must survive, so the token itself has to look the
    // part.
    looks_like_a_credential(&low[start..end]).then_some((start, end))
}

/// Whether an unkeyed token is credential-shaped.
///
/// Base64 is long and drawn from a fixed alphabet; a word of prose is neither.
/// Sixteen bytes is comfortably below the shortest thing that could be a real
/// `Basic` credential — base64 of `a:b` is already 8, and a Nextcloud app
/// password is 72 — and comfortably above the words that follow "basic" in a
/// sentence.
fn looks_like_a_credential(token: &[u8]) -> bool {
    token.len() >= 16
        && token.iter().all(|b| {
            b.is_ascii_alphanumeric() || matches!(*b, b'+' | b'/' | b'=' | b'-' | b'_' | b'.')
        })
}

/// The password in `https://duncan:hunter2@cloud.example/remote.php/dav`.
///
/// URLs are logged constantly and this form survives every keyword rule, since
/// the credential is punctuation-delimited rather than named. The host and the
/// login are left in place: which server failed, and as whom, is the substance
/// of a sync bug report.
fn url_userinfo_at(low: &[u8], i: usize) -> Option<(usize, usize)> {
    if !low[i..].starts_with(b"://") {
        return None;
    }
    let authority = i + 3;
    // The authority ends at the path, the query, the fragment, or whatever
    // punctuation the surrounding prose used to end the URL.
    let end = low[authority..]
        .iter()
        .position(|b| matches!(*b, b'/' | b'?' | b'#') || is_value_delimiter(*b))
        .map_or(low.len(), |n| authority + n);

    // The *last* `@`, because a userinfo may legally contain a percent-encoded
    // one and the host may not.
    let at = authority + low[authority..end].iter().rposition(|b| *b == b'@')?;
    let colon = authority + low[authority..at].iter().position(|b| *b == b':')?;

    (at > colon + 1).then_some((colon + 1, at))
}

fn skip_spaces(low: &[u8], mut j: usize) -> usize {
    while matches!(low.get(j), Some(b' ' | b'\t')) {
        j += 1;
    }
    j
}

/// Where an unquoted value stops.
fn value_end(low: &[u8], start: usize) -> usize {
    low[start..]
        .iter()
        .position(|b| is_value_delimiter(*b))
        .map_or(low.len(), |n| start + n)
}

/// The punctuation that ends an unquoted value in every form this sees: JSON
/// (`,` `}` `]` `"`), a query string (`&` `;`), a `Debug` impl (`,` `)` `}`),
/// and prose (whitespace).
fn is_value_delimiter(b: u8) -> bool {
    matches!(
        b,
        b' ' | b'\t'
            | b'\r'
            | b'\n'
            | b'"'
            | b'\''
            | b','
            | b';'
            | b'&'
            | b')'
            | b']'
            | b'}'
            | b'>'
    )
}

/// What counts as "inside a word" for the boundary test. `_` is included so
/// that `access_token` is one word rather than two, which is what stops the
/// `token` rule from firing in the middle of it and redacting from there.
fn is_word_byte(b: u8) -> bool {
    b.is_ascii_alphanumeric() || b == b'_'
}

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

    /// The strongest form of the assertion: not "the line changed" but "the
    /// secret is gone". A rule that redacted the wrong span would pass a
    /// weaker test.
    fn assert_gone(secret: &str, line: &str) -> String {
        let out = redact(line);
        assert!(
            !out.contains(secret),
            "redaction left the credential behind\n  in:  {line}\n  out: {out}"
        );
        assert!(
            out.contains(PLACEHOLDER),
            "nothing was marked as removed: {out}"
        );
        out
    }

    #[test]
    fn the_credential_login_flow_returns_never_reaches_the_file() {
        // Verbatim the shape of `AppCredentials` as serde writes it — the one
        // credential this application actually holds (FR-NC-1).
        let out = assert_gone(
            "wYh3K8mLpQr2",
            r#"got {"server":"https://cloud.example","loginName":"duncan","appPassword":"wYh3K8mLpQr2"}"#,
        );
        // The rest of the response is the diagnostic, and it survives.
        assert!(out.contains("cloud.example"));
        assert!(out.contains("duncan"));
    }

    #[test]
    fn a_debug_printed_credential_struct_is_scrubbed() {
        // The two-in-the-morning case: `log::debug!("{creds:?}")`.
        assert_gone(
            "wYh3K8mLpQr2",
            r#"AppCredentials { server: "https://cloud.example", login_name: "duncan", app_password: "wYh3K8mLpQr2" }"#,
        );
    }

    #[test]
    fn a_basic_auth_header_keeps_its_scheme_and_loses_its_secret() {
        let out = assert_gone(
            "ZHVuY2FuOmh1bnRlcjI=",
            "PROPFIND /remote.php/dav authorization: Basic ZHVuY2FuOmh1bnRlcjI=",
        );
        assert!(
            out.contains("Basic"),
            "which scheme was used is diagnostic, and is not the secret: {out}"
        );
    }

    #[test]
    fn a_bearer_token_with_no_keyword_in_front_of_it_still_goes() {
        assert_gone(
            "eyJhbGciOiJIUzI1NiJ9",
            "sending Bearer eyJhbGciOiJIUzI1NiJ9",
        );
    }

    #[test]
    fn a_password_in_a_url_goes_and_the_server_stays() {
        let out = assert_gone(
            "hunter2",
            "PUT https://duncan:hunter2@cloud.example/remote.php/dav/files/x.cr2 failed",
        );
        assert!(
            out.contains("duncan") && out.contains("cloud.example"),
            "which server, and as whom, is the whole of a sync bug report: {out}"
        );
    }

    #[test]
    fn a_query_string_token_goes() {
        assert_gone(
            "abc123def",
            "polling https://cloud.example/login/v2/poll?token=abc123def&x=1",
        );
    }

    #[test]
    fn the_word_alone_is_not_a_secret() {
        // The over-redaction failure, which is how a scrubber makes a log
        // useless without ever being caught: these lines say nothing secret
        // and must come through untouched.
        for line in [
            "password rejected by the server",
            "no token yet; still polling",
            "the tokenizer produced 41 tokens",
            "authorization failed with 401",
            "secretary@cloud.example added",
            // The unkeyed `Basic ` rule has no keyword to justify itself, and
            // `basic` is an ordinary word. This is the line it must not eat.
            "using basic sRGB as the fallback",
            "bearer of the news: 12 images",
        ] {
            assert_eq!(redact(line), line, "over-redacted: {line}");
        }
    }

    #[test]
    fn a_photographs_path_is_not_a_secret() {
        // Stated as a test because it is a design decision and not an
        // oversight: NFR-SEC-2 lists credentials, and a log that cannot name
        // the file that failed to decode is not a diagnostic. See the module
        // documentation.
        let line = "decode failed: /home/duncan/Pictures/2026/Iceland/DSC_0431.NEF";
        assert_eq!(redact(line), line);
    }

    #[test]
    fn several_secrets_in_one_line_all_go() {
        let out = redact(r#"{"password":"a1b2c3","token":"d4e5f6","user":"duncan"}"#);
        assert!(!out.contains("a1b2c3"), "{out}");
        assert!(!out.contains("d4e5f6"), "{out}");
        assert!(out.contains("duncan"), "{out}");
    }

    #[test]
    fn redaction_keeps_the_line_shaped_like_what_it_replaced() {
        assert_eq!(
            redact(r#"{"password": "hunter2"}"#),
            r#"{"password": "<redacted>"}"#
        );
        assert_eq!(redact("password=hunter2"), "password=<redacted>");
    }

    #[test]
    fn a_line_with_no_secret_survives_byte_for_byte() {
        // Including non-ASCII, which is the case the ASCII lowercasing exists
        // to protect: a `to_lowercase` here would shift byte offsets under a
        // Turkish dotted capital and slice the next character in half.
        for line in [
            "opened /home/duncan/Bilder/Ölandsbron/DSC_0431.NEF",
            "İSTANBUL library scanned: 12 034 images",
            "",
        ] {
            assert_eq!(redact(line), line);
        }
    }

    #[test]
    fn a_url_without_a_credential_is_left_whole() {
        let line = "GET https://cloud.example/remote.php/dav/files/duncan/";
        assert_eq!(redact(line), line);
    }

    #[test]
    fn an_email_address_is_not_a_url_userinfo() {
        let line = "sharing with duncan@tourolle.paris";
        assert_eq!(redact(line), line);
    }
}