File size: 10,690 Bytes
c8e724e | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 | import argparse
# ==============================================================================
# COPY OF THE ACTUAL RANGE CODER CODEBASE (test_semantic_vocab_range_coder.py)
# ==============================================================================
class PythonRadicalPredictor:
def __init__(self, alpha=1, weight=128):
self.alpha = alpha
self.weight = weight
self.trans_rc = {}
self.trans_rf = {}
self.trans_ra = {}
self.prev_rc = 0
self.prev_rf = 0
self.prev_ra = 0
def observe(self, rc, rf, ra):
key_rc = self.prev_rc
if key_rc not in self.trans_rc:
self.trans_rc[key_rc] = {}
self.trans_rc[key_rc][rc] = self.trans_rc[key_rc].get(rc, 0) + self.weight
key_rf = (rc << 8) | self.prev_rf
if key_rf not in self.trans_rf:
self.trans_rf[key_rf] = {}
self.trans_rf[key_rf][rf] = self.trans_rf[key_rf].get(rf, 0) + self.weight
key_ra = (rc << 16) | (rf << 8) | self.prev_ra
if key_ra not in self.trans_ra:
self.trans_ra[key_ra] = {}
self.trans_ra[key_ra][ra] = self.trans_ra[key_ra].get(ra, 0) + self.weight
self.prev_rc = rc
self.prev_rf = rf
self.prev_ra = ra
def get_cum_freqs_rc(self, prev_rc):
freqs = [self.alpha] * 256
if prev_rc in self.trans_rc:
for sym, count in self.trans_rc[prev_rc].items():
freqs[sym] += count
cum_freqs = [0] * 257
for i in range(256):
cum_freqs[i+1] = cum_freqs[i] + freqs[i]
return cum_freqs
def get_cum_freqs_rf(self, curr_rc, prev_rf):
freqs = [self.alpha] * 256
key = (curr_rc << 8) | prev_rf
if key in self.trans_rf:
for sym, count in self.trans_rf[key].items():
freqs[sym] += count
cum_freqs = [0] * 257
for i in range(256):
cum_freqs[i+1] = cum_freqs[i] + freqs[i]
return cum_freqs
def get_cum_freqs_ra(self, curr_rc, curr_rf, prev_ra):
freqs = [self.alpha] * 256
key = (curr_rc << 16) | (curr_rf << 8) | prev_ra
if key in self.trans_ra:
for sym, count in self.trans_ra[key].items():
freqs[sym] += count
cum_freqs = [0] * 257
for i in range(256):
cum_freqs[i+1] = cum_freqs[i] + freqs[i]
return cum_freqs
class BitWriter:
def __init__(self):
self.buffer = []
self.current_byte = 0
self.bit_count = 0
def write_bit(self, bit):
self.current_byte = (self.current_byte << 1) | (bit & 1)
self.bit_count += 1
if self.bit_count % 8 == 0:
self.buffer.append(self.current_byte)
self.current_byte = 0
def write_bit_helper(self, underflow_bits, bit):
self.write_bit(bit)
for _ in range(underflow_bits[0]):
self.write_bit(1 - bit)
underflow_bits[0] = 0
def flush(self):
if self.bit_count % 8 != 0:
padding_bits = 8 - (self.bit_count % 8)
self.current_byte <<= padding_bits
self.buffer.append(self.current_byte)
self.current_byte = 0
self.bit_count += padding_bits
return bytes(self.buffer)
class BitReader:
def __init__(self, data):
self.data = data
self.byte_index = 0
self.bit_index = 0
def read_bit(self):
if self.byte_index >= len(self.data):
return 0
bit = (self.data[self.byte_index] >> (7 - self.bit_index)) & 1
self.bit_index += 1
if self.bit_index == 8:
self.bit_index = 0
self.byte_index += 1
return bit
def range_encode_radicals(radicals, alpha=1, weight=128):
pred = PythonRadicalPredictor(alpha, weight)
w = BitWriter()
low = 0
high = 0xFFFFFFFF
underflow_bits = [0]
for rc, rf, ra in radicals:
symbols = [rc, rf, ra]
prev_rc = pred.prev_rc
prev_rf = pred.prev_rf
prev_ra = pred.prev_ra
for step in range(3):
if step == 0:
cum_freqs = pred.get_cum_freqs_rc(prev_rc)
elif step == 1:
cum_freqs = pred.get_cum_freqs_rf(symbols[0], prev_rf)
else:
cum_freqs = pred.get_cum_freqs_ra(symbols[0], symbols[1], prev_ra)
sym = symbols[step]
total = cum_freqs[256]
cum_low = cum_freqs[sym]
cum_high = cum_freqs[sym + 1]
range_width = high - low + 1
high = low + (range_width * cum_high) // total - 1
low = low + (range_width * cum_low) // total
while True:
if high < 0x80000000:
w.write_bit_helper(underflow_bits, 0)
low = (low << 1) & 0xFFFFFFFF
high = ((high << 1) | 1) & 0xFFFFFFFF
elif low >= 0x80000000:
w.write_bit_helper(underflow_bits, 1)
low = ((low - 0x80000000) << 1) & 0xFFFFFFFF
high = (((high - 0x80000000) << 1) | 1) & 0xFFFFFFFF
elif low >= 0x40000000 and high < 0xC0000000:
underflow_bits[0] += 1
low = ((low - 0x40000000) << 1) & 0xFFFFFFFF
high = (((high - 0x40000000) << 1) | 1) & 0xFFFFFFFF
else:
break
pred.observe(rc, rf, ra)
underflow_bits[0] += 1
if low < 0x40000000:
w.write_bit_helper(underflow_bits, 0)
else:
w.write_bit_helper(underflow_bits, 1)
return w.flush()
def range_decode_radicals(encoded_bytes, num_concepts, alpha=1, weight=128):
pred = PythonRadicalPredictor(alpha, weight)
r = BitReader(encoded_bytes)
value = 0
for _ in range(32):
value = (value << 1) | r.read_bit()
low = 0
high = 0xFFFFFFFF
decoded_radicals = []
for c in range(num_concepts):
prev_rc = pred.prev_rc
prev_rf = pred.prev_rf
prev_ra = pred.prev_ra
symbols = [0, 0, 0]
for step in range(3):
if step == 0:
cum_freqs = pred.get_cum_freqs_rc(prev_rc)
elif step == 1:
cum_freqs = pred.get_cum_freqs_rf(symbols[0], prev_rf)
else:
cum_freqs = pred.get_cum_freqs_ra(symbols[0], symbols[1], prev_ra)
total = cum_freqs[256]
range_width = high - low + 1
scaled_val = (((value - low) + 1) * total - 1) // range_width
# Binary search
sym = 0
l = 0
rr = 255
while l <= rr:
mid = (l + rr) // 2
if cum_freqs[mid] <= scaled_val < cum_freqs[mid + 1]:
sym = mid
break
elif scaled_val >= cum_freqs[mid + 1]:
l = mid + 1
else:
rr = mid - 1
symbols[step] = sym
cum_low = cum_freqs[sym]
cum_high = cum_freqs[sym + 1]
high = low + (range_width * cum_high) // total - 1
low = low + (range_width * cum_low) // total
while True:
if high < 0x80000000:
low = (low << 1) & 0xFFFFFFFF
high = ((high << 1) | 1) & 0xFFFFFFFF
value = ((value << 1) | r.read_bit()) & 0xFFFFFFFF
elif low >= 0x80000000:
low = ((low - 0x80000000) << 1) & 0xFFFFFFFF
high = (((high - 0x80000000) << 1) | 1) & 0xFFFFFFFF
value = (((value - 0x80000000) << 1) | r.read_bit()) & 0xFFFFFFFF
elif low >= 0x40000000 and high < 0xC0000000:
low = ((low - 0x40000000) << 1) & 0xFFFFFFFF
high = (((high - 0x40000000) << 1) | 1) & 0xFFFFFFFF
value = (((value - 0x40000000) << 1) | r.read_bit()) & 0xFFFFFFFF
else:
break
decoded_radicals.append((symbols[0], symbols[1], symbols[2]))
pred.observe(symbols[0], symbols[1], symbols[2])
return decoded_radicals
# ==============================================================================
def run_proof():
print("======================================================================")
print("ZYMATICA | LLD-AC Range Coder: Actual Codebase Implementation Proof")
print("======================================================================\n")
# Sample sequence of radicals: (R_C, R_F, R_A)
# Replicates typical repetitive/structured state packets
input_radicals = [
(0x12, 0x01, 0x80),
(0x12, 0x01, 0x80),
(0x11, 0x00, 0xA0),
(0x11, 0x00, 0xA0),
(0x11, 0x00, 0xA0),
(0x21, 0x01, 0xA0),
(0x22, 0x02, 0xF0),
(0x22, 0x02, 0xF0)
]
print("[1] Original Radical Sequence (3 Bytes per concept):")
for idx, rad in enumerate(input_radicals):
print(f" Concept {idx+1}: RC=0x{rad[0]:02X}, RF=0x{rad[1]:02X}, RA=0x{rad[2]:02X}")
uncompressed_bytes = len(input_radicals) * 3
print(f" -> Total Uncompressed Size: {uncompressed_bytes} bytes")
print("\n[2] Executing Range Encoder...")
compressed_bytes = range_encode_radicals(input_radicals, alpha=1, weight=128)
compressed_len = len(compressed_bytes)
print(f" -> Compressed Size: {compressed_len} bytes")
print(f" -> Binary Stream (Hex): {compressed_bytes.hex().upper()}")
print("\n[3] Executing Lossless Decoder...")
decoded_radicals = range_decode_radicals(compressed_bytes, len(input_radicals), alpha=1, weight=128)
# Validation check
assert input_radicals == decoded_radicals, "Validation failed! Decoded sequence does not match original."
print(" -> Lossless verification passed. Decoded sequence is identical.")
compression_ratio = uncompressed_bytes / compressed_len
savings = (1 - (compressed_len / uncompressed_bytes)) * 100
print("\n[4] Summary Metrics:")
print(f" - Uncompressed: {uncompressed_bytes} bytes")
print(f" - Compressed: {compressed_len} bytes")
print(f" - Space Savings: {savings:.2f}%")
print(f" - Compression Ratio: {compression_ratio:.2f}x")
print("\n[VERIFICATION] LLD-AC range coder verified from actual codebase.")
if __name__ == "__main__":
parser = argparse.ArgumentParser(description="Zymatica LLD-AC Range Coder Proof")
parser.add_argument("--test", action="store_true", help="Run test mode")
args = parser.parse_args()
run_proof()
|