Arbitrary length Dice coefficients

README.rst

@@ -135,8 +135,6 @@ Limitations
 -  The linkage process has order n^2 time complexity - although algorithms exist to
    significantly speed this up. Several possible speedups are described
    in http://dbs.uni-leipzig.de/file/P4Join-BTW2015.pdf
--  The C++ code makes an assumption of 1024 bit keys (although this would be easy
-   to change).
 
 
 License

_cffi_build/build_matcher.py

@@ -15,14 +15,14 @@
     "_entitymatcher",
     source,
     source_extension='.cpp',
-    extra_compile_args=['-Wall', '-Wextra', '-Werror', '-O3', '-std=c++11', '-mssse3', '-mpopcnt'],
+    extra_compile_args=['-Wall', '-Wextra', '-Werror', '-O3', '-std=c++11', '-march=native', '-mssse3', '-mpopcnt', '-fvisibility=hidden'
+    ],
 )
 
 ffibuilder.cdef("""
-    int match_one_against_many_dice(const char * one, const char * many, int n, double * score);
-    int match_one_against_many_dice_1024_k_top(const char *one, const char *many, const uint32_t *counts_many, int n, uint32_t k, double threshold, int *indices, double *scores);
-    double dice_coeff_1024(const char *e1, const char *e2);
-    double popcount_1024_array(const char *many, int n, uint32_t *counts_many);
+    int match_one_against_many_dice_k_top(const char *one, const char *many, const uint32_t *counts_many, int n, int keybytes, uint32_t k, double threshold, int *indices, double *scores);
+    double dice_coeff(const char *array1, const char *array2, int array_bytes);
+    double popcount_arrays(uint32_t *counts, const char *arrays, int narrays, int array_bytes);
 """)