add Int8HashTable

Author: tp

pandas/_libs/hashtable.pyx

@@ -11,7 +11,7 @@ from libc.stdlib cimport malloc, free
 
 import numpy as np
 cimport numpy as cnp
-from numpy cimport ndarray, uint8_t, uint32_t
+from numpy cimport ndarray, int8_t, uint8_t, uint32_t
 cnp.import_array()
 
 cdef extern from "numpy/npy_math.h":

pandas/_libs/hashtable_class_helper.pxi.in

@@ -18,6 +18,7 @@ WARNING: DO NOT edit .pxi FILE directly, .pxi is generated from .pxi.in
 
 dtypes = [('Float64', 'float64', 'float64_t'),
           ('Int64', 'int64', 'int64_t'),
+          ('Int8', 'int8', 'int8_t'),
           ('String', 'string', 'char *'),
           ('UInt64', 'uint64', 'uint64_t')]
 }}
@@ -62,7 +63,9 @@ cdef inline bint needs_resize(vector_data *data) nogil:
 # name, dtype, arg, idtype
 dtypes = [('Float64', 'float64', 'float64_t', 'np.float64'),
           ('UInt64', 'uint64', 'uint64_t', 'np.uint64'),
-          ('Int64', 'int64', 'int64_t', 'np.int64')]
+          ('Int64', 'int64', 'int64_t', 'np.int64'),
+          ('Int8', 'int8', 'int8_t', 'np.int8'),
+          ]
 
 }}
 
@@ -251,7 +254,9 @@ cdef class HashTable:
 # name, dtype, float_group, default_na_value
 dtypes = [('Float64', 'float64', True, 'nan'),
           ('UInt64', 'uint64', False, 0),
-          ('Int64', 'int64', False, 'iNaT')]
+          ('Int64', 'int64', False, 'iNaT'),
+          ('Int8', 'int8', False, 'iNaT'),
+          ]
 
 def get_dispatch(dtypes):
   for (name, dtype, float_group, default_na_value) in dtypes:

pandas/_libs/khash.pxd

@@ -1,7 +1,7 @@
 # -*- coding: utf-8 -*-
 # cython: profile=False
 from cpython cimport PyObject
-from numpy cimport int64_t, uint64_t, int32_t, uint32_t, float64_t
+from numpy cimport int64_t, uint64_t, int32_t, uint32_t, int8_t, float64_t
 
 cdef extern from "khash_python.h":
     ctypedef uint32_t khint_t