introducing Int32HashTable

Author: realead

pandas/_libs/hashtable.pxd

@@ -3,12 +3,14 @@ from numpy cimport intp_t, ndarray
 from pandas._libs.khash cimport (
     float64_t,
     int64_t,
+    int32_t,
+    uint64_t,
     kh_float64_t,
     kh_int64_t,
+    kh_int32_t,
     kh_pymap_t,
     kh_str_t,
     kh_uint64_t,
-    uint64_t,
 )
 
 # prototypes for sharing
@@ -28,6 +30,12 @@ cdef class Int64HashTable(HashTable):
     cpdef get_item(self, int64_t val)
     cpdef set_item(self, int64_t key, Py_ssize_t val)
 
+cdef class Int32HashTable(HashTable):
+    cdef kh_int32_t *table
+
+    cpdef get_item(self, int32_t val)
+    cpdef set_item(self, int32_t key, Py_ssize_t val)
+
 cdef class Float64HashTable(HashTable):
     cdef kh_float64_t *table
 

pandas/_libs/hashtable.pyx

@@ -16,36 +16,42 @@ from pandas._libs cimport util
 from pandas._libs.khash cimport (
     kh_destroy_float64,
     kh_destroy_int64,
+    kh_destroy_int32,
     kh_destroy_pymap,
     kh_destroy_str,
     kh_destroy_uint64,
     kh_exist_float64,
     kh_exist_int64,
+    kh_exist_int32,
     kh_exist_pymap,
     kh_exist_str,
     kh_exist_uint64,
     kh_float64_t,
     kh_get_float64,
     kh_get_int64,
+    kh_get_int32,
     kh_get_pymap,
     kh_get_str,
     kh_get_strbox,
     kh_get_uint64,
     kh_init_float64,
     kh_init_int64,
+    kh_init_int32,
     kh_init_pymap,
     kh_init_str,
     kh_init_strbox,
     kh_init_uint64,
     kh_int64_t,
     kh_put_float64,
     kh_put_int64,
+    kh_put_int32,
     kh_put_pymap,
     kh_put_str,
     kh_put_strbox,
     kh_put_uint64,
     kh_resize_float64,
     kh_resize_int64,
+    kh_resize_int32,
     kh_resize_pymap,
     kh_resize_str,
     kh_resize_uint64,

pandas/_libs/hashtable_class_helper.pxi.in

@@ -21,6 +21,7 @@ from pandas._libs.missing cimport C_NA
 
 dtypes = [('Float64', 'float64', 'float64_t'),
           ('Int64', 'int64', 'int64_t'),
+          ('Int32', 'int32', 'int32_t'),
           ('String', 'string', 'char *'),
           ('UInt64', 'uint64', 'uint64_t')]
 }}
@@ -49,6 +50,7 @@ cdef inline void append_data_{{dtype}}({{name}}VectorData *data,
 
 ctypedef fused vector_data:
     Int64VectorData
+    Int32VectorData
     UInt64VectorData
     Float64VectorData
     StringVectorData
@@ -65,7 +67,8 @@ cdef inline bint needs_resize(vector_data *data) nogil:
 # name, dtype, c_type
 dtypes = [('Float64', 'float64', 'float64_t'),
           ('UInt64', 'uint64', 'uint64_t'),
-          ('Int64', 'int64', 'int64_t')]
+          ('Int64', 'int64', 'int64_t'),
+          ('Int32', 'int32', 'int32_t')]
 
 }}
 
@@ -256,7 +259,8 @@ cdef class HashTable:
 # name, dtype, float_group, default_na_value
 dtypes = [('Float64', 'float64', True, 'np.nan'),
           ('UInt64', 'uint64', False, 0),
-          ('Int64', 'int64', False, 'NPY_NAT')]
+          ('Int64', 'int64', False, 'NPY_NAT'),
+          ('Int32', 'int32', False, 0)]
 
 }}
 

pandas/_libs/hashtable_func_helper.pxi.in

@@ -10,7 +10,8 @@ WARNING: DO NOT edit .pxi FILE directly, .pxi is generated from .pxi.in
 dtypes = [('float64', 'float64', 'float64_t'),
           ('uint64', 'uint64', 'uint64_t'),
           ('object', 'pymap', 'object'),
-          ('int64', 'int64', 'int64_t')]
+          ('int64', 'int64', 'int64_t'),
+          ('int32', 'int32', 'int32_t')]
 
 }}
 
@@ -276,6 +277,7 @@ def ismember_{{dtype}}(const {{c_type}}[:] arr, const {{c_type}}[:] values):
 # dtype, ctype, table_type, npy_dtype
 dtypes = [('float64', 'float64_t', 'float64', 'float64'),
           ('int64', 'int64_t', 'int64', 'int64'),
+          ('int32', 'int32_t', 'int32', 'int32'),
           ('uint64', 'uint64_t', 'uint64', 'uint64'),
           ('object', 'object', 'pymap', 'object_')]
 }}