"""Regression check: our output must be byte-identical to sedonac.exe's, both ways.

    sax -> sab   check_encode()
    sab -> sax   check_decode()
    sab -> sax -> sab  round trip

Usage:  python verify.py [sedona_home]

Without an argument the home comes from system.properties (see config.py), which
pops a folder chooser the first time.
"""
import os, sys, subprocess, tempfile, shutil
import sab, sax, config

HERE = os.path.dirname(os.path.abspath(__file__))
HOME = sys.argv[1] if len(sys.argv) > 1 else config.get_sedona_home()
TESTS = os.path.join(HERE, "testprogram")


def sedonac(src, tmp):
    """Run sedonac on a copy of `src`; return the file it produced (needs a JRE)."""
    work = os.path.join(tmp, os.path.basename(src))
    shutil.copy(src, work)
    exe = os.path.join(HOME, "bin", "sedonac.exe")
    r = subprocess.run([exe, work], capture_output=True, text=True)
    if r.returncode != 0:
        print("  sedonac failed:\n" + r.stdout + r.stderr)
        return None
    other = ".sax" if work.endswith(".sab") else ".sab"
    return os.path.splitext(work)[0] + other


def compare(label, reference, mine, binary):
    a = open(reference, "rb").read()
    b = open(mine, "rb").read()
    if a == b:
        print("  PASS  %-28s %d bytes identical" % (label, len(a)))
        return True

    diffs = [i for i in range(min(len(a), len(b))) if a[i] != b[i]]
    print("  FAIL  %-28s sedonac=%d ours=%d, %d byte diffs" % (label, len(a), len(b), len(diffs)))
    if diffs:
        i = diffs[0]
        if binary:
            lo, hi = max(0, i - 12), i + 12
            print("        first diff at offset %d" % i)
            print("        sedonac  %s" % a[lo:hi].hex())
            print("        ours     %s" % b[lo:hi].hex())
        else:
            line = a[:i].count(b"\n") + 1
            print("        first diff at line %d" % line)
            print("        sedonac  %s" % a.splitlines()[line - 1])
            print("        ours     %s" % b.splitlines()[line - 1])
    return False


def check_encode(sax_file, reference=None):
    """sax -> sab, against `reference` or a fresh sedonac run."""
    tmp = tempfile.mkdtemp()
    try:
        reference = reference or sedonac(sax_file, tmp)
        if reference is None:
            return False
        mine = os.path.join(tmp, "mine.sab")
        sab.encode(sax_file, HOME, mine)
        return compare(os.path.basename(sax_file) + " -> sab", reference, mine, True)
    finally:
        shutil.rmtree(tmp, ignore_errors=True)


def check_decode(sab_file, reference=None):
    """sab -> sax, against `reference` or a fresh sedonac run."""
    tmp = tempfile.mkdtemp()
    try:
        reference = reference or sedonac(sab_file, tmp)
        if reference is None:
            return False
        mine = os.path.join(tmp, "mine.sax")
        sax.decode(sab_file, HOME, mine)
        return compare(os.path.basename(sab_file) + " -> sax", reference, mine, False)
    finally:
        shutil.rmtree(tmp, ignore_errors=True)


def check_round_trip(sab_file):
    """sab -> sax -> sab must come back to the same bytes."""
    tmp = tempfile.mkdtemp()
    try:
        mid = os.path.join(tmp, "mid.sax")
        back = os.path.join(tmp, "back.sab")
        sax.decode(sab_file, HOME, mid)
        sab.encode(mid, HOME, back)
        return compare(os.path.basename(sab_file) + " round trip", sab_file, back, True)
    finally:
        shutil.rmtree(tmp, ignore_errors=True)


if __name__ == "__main__":
    print("sedona home: %s" % HOME)
    saxf = os.path.join(TESTS, "test_normal.sax")
    sabf = os.path.join(TESTS, "test_normal_sedonac.sab")
    ok = check_encode(saxf, sabf)
    ok &= check_decode(sabf, saxf)
    ok &= check_round_trip(sabf)
    sys.exit(0 if ok else 1)