//! Deterministic robustness sweep: the stable-toolchain counterpart to
//! `cargo fuzz`.
//!
//! Phase 6 step 6.3 asks for zero panics on arbitrary input. `cargo-fuzz`
//! needs a nightly toolchain and libFuzzer, so it cannot gate a stable CI
//! run. This harness covers the same ground deterministically: it mutates
//! the real corpus with a fixed-seed PRNG, so a failure is reproducible from
//! the seed printed in the output rather than only from a saved artefact.
//!
//! The fuzz targets in `pdf-cos/fuzz/` remain the deeper, coverage-guided
//! search; this is the gate that runs on every push.

use std::path::PathBuf;

use nigig_pdf_cos::{decode_stream, Lexer, PdfDict, PdfObj, PdfStream, XRefTable};
use nigig_pdf_document::PdfDocument;
use nigig_pdf_graphics::content::parse_content_stream;
use nigig_pdf_graphics::recording::RecordingDevice;

/// xorshift64*: tiny, deterministic, and good enough to shuffle bytes.
struct Rng(u64);

impl Rng {
    fn new(seed: u64) -> Self {
        // A zero state would stay zero forever.
        Self(seed | 1)
    }

    fn next(&mut self) -> u64 {
        let mut x = self.0;
        x ^= x >> 12;
        x ^= x << 25;
        x ^= x >> 27;
        self.0 = x;
        x.wrapping_mul(0x2545_F491_4F6C_DD1D)
    }

    fn below(&mut self, n: usize) -> usize {
        if n == 0 {
            return 0;
        }
        (self.next() % n as u64) as usize
    }
}

fn corpus_files() -> Vec<PathBuf> {
    let root = PathBuf::from(env!("CARGO_MANIFEST_DIR")).join("../tests/corpus");
    let mut found = Vec::new();
    let mut stack = vec![root];
    while let Some(dir) = stack.pop() {
        let Ok(entries) = std::fs::read_dir(&dir) else {
            continue;
        };
        for entry in entries.flatten() {
            let path = entry.path();
            if path.is_dir() {
                stack.push(path);
            } else if path.extension().is_some_and(|e| e == "pdf") {
                found.push(path);
            }
        }
    }
    found.sort();
    found
}

/// Apply one of several mutation strategies, chosen by the PRNG.
fn mutate(seed: &[u8], rng: &mut Rng) -> Vec<u8> {
    let mut out = seed.to_vec();
    if out.is_empty() {
        return out;
    }
    match rng.below(6) {
        // Flip a byte.
        0 => {
            let at = rng.below(out.len());
            out[at] ^= (rng.next() & 0xFF) as u8;
        }
        // Truncate: the single most productive PDF mutation.
        1 => {
            let keep = rng.below(out.len());
            out.truncate(keep);
        }
        // Splice out a run.
        2 => {
            let start = rng.below(out.len());
            let end = (start + 1 + rng.below(64)).min(out.len());
            out.drain(start..end);
        }
        // Insert junk.
        3 => {
            let at = rng.below(out.len());
            let byte = (rng.next() & 0xFF) as u8;
            let count = 1 + rng.below(32);
            for _ in 0..count {
                out.insert(at, byte);
            }
        }
        // Corrupt a number, which is what drives offsets and lengths.
        4 => {
            let at = rng.below(out.len());
            for i in at..(at + 8).min(out.len()) {
                if out[i].is_ascii_digit() {
                    out[i] = b'0' + (rng.next() % 10) as u8;
                }
            }
        }
        // Overwrite a structural keyword.
        _ => {
            for needle in [&b"obj"[..], b"endstream", b"xref", b"trailer"] {
                if let Some(pos) = out.windows(needle.len()).position(|w| w == needle) {
                    let replacement = b"ZZZZZZZZZ";
                    for (i, b) in needle.iter().enumerate() {
                        let _ = b;
                        out[pos + i] = replacement[i % replacement.len()];
                    }
                    break;
                }
            }
        }
    }
    out
}

/// Exercise every entry point that consumes untrusted bytes.
///
/// Nothing here asserts an outcome: the assertion is that the process
/// survives. A panic fails the test by aborting it.
fn exercise(data: &[u8]) {
    let mut lexer = Lexer::new(data, 0);
    for _ in 0..8 {
        if lexer.read_object().is_err() {
            break;
        }
    }

    let _ = XRefTable::parse(data);

    if let Ok(ops) = parse_content_stream(data) {
        let _ = RecordingDevice::from_ops(&ops);
    }

    for filter in [
        "FlateDecode",
        "LZWDecode",
        "ASCII85Decode",
        "ASCIIHexDecode",
        "RunLengthDecode",
    ] {
        let mut dict = PdfDict::new();
        dict.set("Filter", PdfObj::Name(filter.to_string()));
        let _ = decode_stream(&PdfStream {
            dict,
            data: data.to_vec(),
        });
    }

    if let Ok(mut doc) = PdfDocument::parse(data) {
        let pages = doc.page_count().min(4);
        for index in 0..pages {
            if let Ok(page) = doc.page(index) {
                let _ = parse_content_stream(&page.content_data);
            }
            let _ = doc.page_annotations(index);
        }
        let _ = doc.acroform();
    }
}

#[test]
fn mutated_corpus_never_panics() {
    let files = corpus_files();
    assert!(!files.is_empty(), "corpus must be present");

    // Fixed seed: a failure here is reproducible, unlike a random fuzz run.
    let mut rng = Rng::new(0x5EED_1234_ABCD_0001);
    let iterations_per_file = 200;

    for path in &files {
        let Ok(seed) = std::fs::read(path) else {
            continue;
        };
        for round in 0..iterations_per_file {
            let mutated = mutate(&seed, &mut rng);
            // Printed so a crash names the exact input that produced it.
            if std::env::var("VERBOSE_ROBUSTNESS").is_ok() {
                println!("{} round {round}", path.display());
            }
            exercise(&mutated);
        }
    }
    println!(
        "exercised {} mutations across {} corpus files",
        files.len() * iterations_per_file,
        files.len()
    );
}

#[test]
fn structured_edge_cases_never_panic() {
    // Inputs that specifically target the recursion and arithmetic the
    // corpus found bugs in.
    let cases: Vec<Vec<u8>> = vec![
        Vec::new(),
        b"%PDF-1.7".to_vec(),
        b"\x00".repeat(1024),
        b"[".repeat(5000),
        b"<<".repeat(5000),
        b"((((((((((".repeat(500),
        b"1 0 obj".to_vec(),
        b"trailer << /Root 1 0 R >>".to_vec(),
        b"xref\n0 99999999\n".to_vec(),
        b"stream\n".to_vec(),
        // A length claiming far more than exists.
        b"<< /Length 4294967295 >>\nstream\nshort\nendstream".to_vec(),
        // Self-referential object number.
        b"1 0 obj\n1 0 R\nendobj".to_vec(),
        // Enormous numbers, to catch overflow in offset arithmetic.
        b"99999999999999999999 0 obj\n<< >>\nendobj".to_vec(),
        b"-99999999999999999999".to_vec(),
        // Content stream operators with missing operands.
        b"m l c re f S W n Tj TJ Do BI ID EI".to_vec(),
        b"BT ET Q Q Q Q q q q q".to_vec(),
        b"1e400 1e400 m".to_vec(),
        // Inline image that never terminates.
        b"BI /W 99999 /H 99999 /BPC 8 ID ".to_vec(),
    ];

    for case in &cases {
        exercise(case);
    }
    println!("{} structured edge cases survived", cases.len());
}

#[test]
fn concatenated_corpus_pairs_never_panic() {
    // Splicing two files together produces structurally confusing input:
    // two headers, two trailers, offsets pointing into the wrong half.
    let files = corpus_files();
    let mut rng = Rng::new(0xC0FFEE);
    for _ in 0..100 {
        let a = &files[rng.below(files.len())];
        let b = &files[rng.below(files.len())];
        let (Ok(mut first), Ok(second)) = (std::fs::read(a), std::fs::read(b)) else {
            continue;
        };
        first.extend_from_slice(&second);
        exercise(&first);
    }
}