sx/examples/0714-modules-json-reader.sx

// JSON reader (parser) from `modules/std/json.sx` — the inverse of the
// F2.1 writer.
//
// Parses a representative document (nested object + array + a
// string-with-escapes + ints incl. negatives + bool + null) into the
// shared value model, then proves:
//
//   1. STRUCTURE — the parsed tree has the expected keys (in INSERTION
//      order), values, and nesting.
//   2. HEAP DISCIPLINE — an un-escaped string value is a zero-copy VIEW
//      into the input buffer (its bytes lie inside `src`), while an
//      escaped string is DECODED into a fresh `alloc`-ed buffer (its
//      bytes lie OUTSIDE `src`). Composite nodes + the decoded string are
//      the only allocations, all through the explicit Arena.
//   3. ROUND-TRIP — feeding the parsed tree back to the writer reproduces
//      the canonical input byte-for-byte.
//   4. UNICODE — `\uXXXX` (BMP + 2-byte) and a surrogate pair decode to
//      the right UTF-8 bytes.
//   5. FAILURE SURFACING — every malformed input raises the right
//      `JsonParseError` variant on the error channel, never a bogus value.

#import "modules/std.sx";
#import "modules/std/mem.sx"; // `Allocator` is non-transitive: name it, import it.
#import "modules/std/json.sx";

// Canonical document: no insignificant whitespace, escapes in the writer's
// own form — so re-serializing the parse must reproduce it exactly.
DOC :: "{\"name\":\"plain\",\"esc\":\"a\\nb\",\"xs\":[10,-20],\"yes\":true,\"nil\":null,\"sub\":{\"k\":\"v\"}}";

report :: (label: string, ok: bool) {
    if ok { print("{}: ok\n", label); } else { print("{}: FAIL\n", label); }
}

// Half-open containment [lo, hi).
in_range :: (x: i64, lo: i64, hi: i64) -> bool {
    return x >= lo and x < hi;
}

// True when `parse(src)` raised `want` — destructure captures the error
// tag without `try`, so a malformed input never aborts the example.
raises :: (src: string, want: JsonParseError, alloc: Allocator) -> bool {
    _, e := parse(src, alloc);
    e == want
}

// True when parsing `"a<b>b"` (a string holding the RAW control byte `b`)
// raises BadControlChar. Built from a byte buffer because a raw control
// byte can't appear in an sx string literal.
ctrl_raises :: (b: u8, alloc: Allocator) -> bool {
    raw : [5]u8 = ---;
    raw[0] = 34; raw[1] = 97; raw[2] = b; raw[3] = 98; raw[4] = 34;   // "a<b>b"
    return raises(string.{ ptr = @raw[0], len = 5 }, error.BadControlChar, alloc);
}

main :: () -> ! {
    gpa := GPA.init();
    arena := Arena.init(xx gpa, 8192);
    defer arena.deinit();

    // ── 1. Structure ─────────────────────────────────────────────────
    src := DOC;
    root := try parse(src, xx arena);

    is_object := if root == { case .object: true; else: false; };
    report("root-is-object", is_object);

    o := root.object;
    report("member-count",   o.len == 6);
    report("key-order-0",     o.items[0].key == "name");
    report("string-plain",    o.items[0].val.str == "plain");
    report("string-escaped",  o.items[1].val.str == "a\nb");   // \n decoded to 0x0A

    xs := o.items[2].val.array;
    report("array-len",  xs.len == 2);
    report("array-pos",  xs.items[0].int_ == 10);
    report("array-neg",  xs.items[1].int_ == 0 - 20);

    report("bool-value", o.items[3].val.bool_ == true);

    is_null := if o.items[4].val == { case .null_: true; else: false; };
    report("null-value", is_null);

    // The nested pair asserted as one expression — a string `==` on each
    // side of `and`.
    sub := o.items[5].val.object;
    report("nested-pair", sub.items[0].key == "k" and sub.items[0].val.str == "v");

    // ── 2. Heap discipline: view vs decoded ──────────────────────────
    base : i64 = xx src.ptr;
    stop := base + src.len;
    p_plain : i64 = xx o.items[0].val.str.ptr;   // "plain": no escape -> VIEW into src
    p_esc   : i64 = xx o.items[1].val.str.ptr;   // "a\nb": escaped -> DECODED into arena
    report("plain-is-view",     in_range(p_plain, base, stop));
    report("escaped-allocated", !in_range(p_esc, base, stop));

    // ── 3. Round-trip back through the writer ────────────────────────
    buf : [256]u8 = ---;
    n := try write_to_buffer(root, string.{ ptr = @buf[0], len = 256 });
    rt := string.{ ptr = @buf[0], len = n };
    report("round-trip", rt == src);

    // ── 4. Leading/trailing/inner whitespace is insignificant ────────
    wsv := try parse("  [ 1 , 2 , 3 ]  ", xx arena);
    wa := wsv.array;
    report("ws-count", wa.len == 3);
    report("ws-first", wa.items[0].int_ == 1);
    report("ws-last",  wa.items[2].int_ == 3);

    // Empty container literals (the manifest/db.json use these).
    ea := try parse("[]", xx arena);
    report("empty-array", ea.array.len == 0);
    eo := try parse("{}", xx arena);
    report("empty-object", eo.object.len == 0);

    // ── 5. Unicode: \uXXXX (1- and 2-byte) + surrogate pair (4-byte) ──
    // JSON "Aé😀" -> 'A', 'é' (C3 A9), '😀' (F0 9F 98 80). One byte per report.
    univ := try parse("\"\\u0041\\u00e9\\uD83D\\uDE00\"", xx arena);
    u := univ.str;
    report("uni-len", u.len == 7);
    report("uni-A",   u[0] == 0x41);                    // U+0041 -> 1 byte
    report("uni-e1",  u[1] == 0xC3);                    // U+00E9 -> 2 bytes
    report("uni-e2",  u[2] == 0xA9);
    report("uni-i0",  u[3] == 0xF0);                    // U+1F600 (surrogate pair) -> 4 bytes
    report("uni-i1",  u[4] == 0x9F);
    report("uni-i2",  u[5] == 0x98);
    report("uni-i3",  u[6] == 0x80);

    // ── 6. Malformed inputs each surface the right error variant ─────
    report("err-truncated",     raises("{\"a\":",       error.UnexpectedEnd,   xx arena));
    report("err-bad-escape",    raises("\"a\\xb\"",     error.BadEscape,       xx arena));
    report("err-trailing-junk", raises("[1,2] x",       error.TrailingGarbage, xx arena));
    report("err-bad-token",     raises("xyz",           error.UnexpectedToken, xx arena));
    report("err-fraction",      raises("1.5",           error.BadNumber,       xx arena));
    report("err-leading-zero",  raises("01",            error.BadNumber,       xx arena));
    report("err-overflow",      raises("9223372036854775808", error.BadNumber, xx arena));
    report("err-unterminated",  raises("\"abc",         error.UnexpectedEnd,   xx arena));

    // ── 7. RFC 8259 §7: unescaped control bytes (U+0000..U+001F) ──────
    // A RAW control byte inside a string is invalid JSON -> BadControlChar.
    report("err-raw-tab", ctrl_raises(9,  xx arena));   // raw 0x09
    report("err-raw-lf",  ctrl_raises(10, xx arena));   // raw 0x0A
    report("err-raw-nul", ctrl_raises(0,  xx arena));   // raw 0x00

    // POSITIVE: the ESCAPED control forms stay valid and decode to the
    // exact bytes. JSON "\t\n\u0009" -> 0x09 0x0A 0x09 (3 bytes).
    esc := try parse("\"\\t\\n\\u0009\"", xx arena);
    es := esc.str;
    report("esc-ctrl-len", es.len == 3);
    report("esc-tab", es[0] == 0x09);   // \t
    report("esc-lf",  es[1] == 0x0A);   // \n
    report("esc-u",   es[2] == 0x09);   // \u0009

    print("=== DONE ===\n");
    return;
}