hash function for tuples

Author: realead

pandas/_libs/src/klib/khash_python.h

@@ -242,7 +242,7 @@ int PANDAS_INLINE pyobject_cmp(PyObject* a, PyObject* b) {
 }
 
 
-Py_hash_t PANDAS_INLINE _Pandas_HashDouble(double val){
+Py_hash_t PANDAS_INLINE _Pandas_HashDouble(double val) {
     //Since Python3.10, nan is no longer has hash 0
     if (Py_IS_NAN(val)) {
         return 0;
@@ -255,13 +255,13 @@ Py_hash_t PANDAS_INLINE _Pandas_HashDouble(double val){
 }
 
 
-Py_hash_t PANDAS_INLINE floatobject_hash(PyFloatObject* key){
+Py_hash_t PANDAS_INLINE floatobject_hash(PyFloatObject* key) {
     return _Pandas_HashDouble(PyFloat_AS_DOUBLE(key));
 }
 
 
 // replaces _Py_HashDouble with _Pandas_HashDouble
-Py_hash_t PANDAS_INLINE complexobject_hash(PyComplexObject* key){
+Py_hash_t PANDAS_INLINE complexobject_hash(PyComplexObject* key) {
     Py_uhash_t realhash = (Py_uhash_t)_Pandas_HashDouble(key->cval.real);
     Py_uhash_t imaghash = (Py_uhash_t)_Pandas_HashDouble(key->cval.imag);
     if (realhash == (Py_uhash_t)-1 || imaghash == (Py_uhash_t)-1) {
@@ -275,11 +275,52 @@ Py_hash_t PANDAS_INLINE complexobject_hash(PyComplexObject* key){
 }
 
 
-khint32_t PANDAS_INLINE kh_python_hash_func(PyObject* key){
+khint32_t PANDAS_INLINE kh_python_hash_func(PyObject* key);
+
+//we could use any hashing algorithm, this is the original CPython's for tuples
+
+#if SIZEOF_PY_UHASH_T > 4
+#define _PandasHASH_XXPRIME_1 ((Py_uhash_t)11400714785074694791ULL)
+#define _PandasHASH_XXPRIME_2 ((Py_uhash_t)14029467366897019727ULL)
+#define _PandasHASH_XXPRIME_5 ((Py_uhash_t)2870177450012600261ULL)
+#define _PandasHASH_XXROTATE(x) ((x << 31) | (x >> 33))  /* Rotate left 31 bits */
+#else
+#define _PandasHASH_XXPRIME_1 ((Py_uhash_t)2654435761UL)
+#define _PandasHASH_XXPRIME_2 ((Py_uhash_t)2246822519UL)
+#define _PandasHASH_XXPRIME_5 ((Py_uhash_t)374761393UL)
+#define _PandasHASH_XXROTATE(x) ((x << 13) | (x >> 19))  /* Rotate left 13 bits */
+#endif
+
+Py_hash_t PANDAS_INLINE tupleobject_hash(PyTupleObject* key) {
+    Py_ssize_t i, len = Py_SIZE(key);
+    PyObject **item = key->ob_item;
+
+    Py_uhash_t acc = _PandasHASH_XXPRIME_5;
+    for (i = 0; i < len; i++) {
+        Py_uhash_t lane = kh_python_hash_func(item[i]);
+        if (lane == (Py_uhash_t)-1) {
+            return -1;
+        }
+        acc += lane * _PandasHASH_XXPRIME_2;
+        acc = _PandasHASH_XXROTATE(acc);
+        acc *= _PandasHASH_XXPRIME_1;
+    }
+
+    /* Add input length, mangled to keep the historical value of hash(()). */
+    acc += len ^ (_PandasHASH_XXPRIME_5 ^ 3527539UL);
+
+    if (acc == (Py_uhash_t)-1) {
+        return 1546275796;
+    }
+    return acc;
+}
+
+
+khint32_t PANDAS_INLINE kh_python_hash_func(PyObject* key) {
     Py_hash_t hash;
     // For PyObject_Hash holds:
     //    hash(0.0) == 0 == hash(-0.0)
-    //    yet for different nan-object different hash-values
+    //    yet for different nan-objects different hash-values
     //    are possible
     if (PyFloat_CheckExact(key)) {
         // we cannot use kh_float64_hash_func
@@ -293,6 +334,9 @@ khint32_t PANDAS_INLINE kh_python_hash_func(PyObject* key){
         // and kh_complex128_hash_func doesn't respect it
         hash = complexobject_hash((PyComplexObject*)key);
     }
+    else if (PyTuple_CheckExact(key)) {
+        hash = tupleobject_hash((PyTupleObject*)key);
+    }
     else {
         hash = PyObject_Hash(key);
     }