Fix bug with RANS_ORDER_STRIPE on large blocks.

The meta-data is 2 bytes for order + N, ? bytes for original size, and
?*N bytes for the N compressed sizes.  We forgot about the original
size so only left room for 2+5*N (with 5 being the maximum size of a
32-bit var int).  So blocks larger than 2^28 risked not fitting in the
allocated meta-data size.

Reported by Divon Lan.

Author: jkbonfield

NEWS.md

@@ -1,5 +1,5 @@
-Release 1.3.0: 19th July 2022
------------------------------
+Release 1.3.0: 9th August 2022
+------------------------------
 
 The primary change in this release is a new SIMD enabled rANS codec.
 
@@ -49,6 +49,8 @@ Bug fixes
   (Additionally blocks above 2GB now error, rather than crashing or
   returning incorrect results.)
 
+- Fix encode error with large blocks using RANS_ORDER_STRIPE.
+
 
 Release 1.2.2: 1st April 2022
 -----------------------------

htscodecs/arith_dynamic.c

@@ -75,11 +75,14 @@
 #define MAGIC 8
 
 unsigned int arith_compress_bound(unsigned int size, int order) {
+    int N = (order>>8) & 0xff;
+    if (!N) N=4;
     return (order == 0
         ? 1.05*size + 257*3 + 4
-        : 1.05*size + 257*257*3 + 4 + 257*3+4) +
+        : 1.05*size + 257*257*3 + 4 + 257*3+4) + 5 +
         ((order & X_PACK) ? 1 : 0) +
-        ((order & X_RLE) ? 1 + 257*3+4: 0) + 5;
+        ((order & X_RLE) ? 1 + 257*3+4: 0) +
+        ((order & X_STRIPE) ? 7 + 5*N: 0);
 }
 
 #ifndef MODEL_256 // see fqzcomp_qual_fuzz.c
@@ -735,7 +738,7 @@ unsigned char *arith_compress_to(unsigned char *in,  unsigned int in_size,
         c_meta_len += var_put_u32(out+c_meta_len, out_end, in_size);
         out[c_meta_len++] = N;
 
-        out2_start = out2 = out+2+5*N; // shares a buffer with c_meta
+        out2_start = out2 = out+7+5*N; // shares a buffer with c_meta
         for (i = 0; i < N; i++) {
             // Brute force try all methods.
             // FIXME: optimise this bit.  Maybe learn over time?

htscodecs/rANS_static4x16pr.c

@@ -97,7 +97,7 @@ unsigned int rans_compress_bound_4x16(unsigned int size, int order) {
         ((order & RANS_ORDER_PACK) ? 1 : 0) +
         ((order & RANS_ORDER_RLE) ? 1 + 257*3+4: 0) + 20 +
         ((order & RANS_ORDER_X32) ? (32-4)*4 : 0) +
-        ((order & RANS_ORDER_STRIPE) ? 1 + 5*N: 0);
+        ((order & RANS_ORDER_STRIPE) ? 7 + 5*N: 0);
     return sz + (sz&1) + 2; // make this even so buffers are word aligned
 }
 
@@ -1181,7 +1181,7 @@ unsigned char *rans_compress_to_4x16(unsigned char *in, unsigned int in_size,
         unsigned char *out_best = NULL;
         unsigned int out_best_len = 0;
 
-        out2_start = out2 = out+2+5*N; // shares a buffer with c_meta
+        out2_start = out2 = out+7+5*N; // shares a buffer with c_meta
         for (i = 0; i < N; i++) {
             // Brute force try all methods.
             int j, m[] = {1,64,128,0}, best_j = 0, best_sz = in_size+10;