def _sdc_take_list_str_impl(data, indexes):
res_size = 0
for i in numba.prange(len(indexes)):
res_size += len(indexes[i])
nan_mask = numpy.zeros(res_size, dtype=numpy.bool_)
num_total_bytes = 0
for i in numba.prange(len(indexes)):
start = 0
for l in range(len(indexes[0:i])):
start += len(indexes[l])
current_pos = start
for j in range(len(indexes[i])):
num_total_bytes += get_utf8_size(data[indexes[i][j]])
if isna(data, indexes[i][j]):
nan_mask[current_pos] = True
current_pos += 1
res_arr = pre_alloc_string_array(res_size, num_total_bytes)
for i in numba.prange(len(indexes)):
start = 0
for l in range(len(indexes[0:i])):
start += len(indexes[l])
current_pos = start
for j in range(len(indexes[i])):
res_arr[current_pos] = data[indexes[i][j]]
if nan_mask[current_pos]:
str_arr_set_na(res_arr, current_pos)
current_pos += 1
return res_arr
def sdc_fillna_str_impl(self, inplace=False, value=None):
n = len(self)
num_chars = 0
# get total chars in new array
for i in prange(n):
s = self[i]
if sdc.hiframes.api.isna(self, i):
num_chars += get_utf8_size(value)
else:
num_chars += get_utf8_size(s)
filled_data = pre_alloc_string_array(n, num_chars)
for i in prange(n):
if sdc.hiframes.api.isna(self, i):
filled_data[i] = value
else:
filled_data[i] = self[i]
return filled_data
def _str_replace_noregex_impl(str_arr, pat, val):
numba.parfor.init_prange()
n = len(str_arr)
n_total_chars = 0
str_list = sdc.str_ext.alloc_str_list(n)
for i in numba.parfor.internal_prange(n):
out_str = str_arr[i].replace(pat, val)
str_list[i] = out_str
n_total_chars += get_utf8_size(out_str)
numba.parfor.init_prange()
out_arr = pre_alloc_string_array(n, n_total_chars)
for i in numba.parfor.internal_prange(n):
_str = str_list[i]
out_arr[i] = _str
return sdc.hiframes.api.init_series(out_arr)
def sdc_astype_number_to_string_impl(self, dtype):
num_bytes = 0
arr_len = len(self)
# Get total bytes for new array
for i in prange(arr_len):
item = self[i]
num_bytes += get_utf8_size(str(item))
data = pre_alloc_string_array(arr_len, num_bytes)
for i in range(arr_len):
item = self[i]
data[i] = str(item) # TODO: check NA
return data
def _sdc_take_str_arr_impl(data, indexes):
res_size = len(indexes)
nan_mask = numpy.zeros(res_size, dtype=numpy.bool_)
num_total_bytes = 0
for i in numba.prange(res_size):
num_total_bytes += get_utf8_size(data[indexes[i]])
if isna(data, indexes[i]):
nan_mask[i] = True
res_arr = pre_alloc_string_array(res_size, num_total_bytes)
for i in numpy.arange(res_size):
res_arr[i] = data[indexes[i]]
if nan_mask[i]:
str_arr_set_na(res_arr, i)
return res_arr
def sdc_astype_number_to_string_impl(self, dtype):
num_bytes = 0
arr_len = len(self)
# Get total bytes for new array
for i in np.arange(arr_len): # FIXME_Numba#6969: prange segfaults, use it when resolved
item = self[i]
num_bytes += get_utf8_size(str(item))
data = pre_alloc_string_array(arr_len, num_bytes)
for i in range(arr_len):
item = self[i]
data[i] = str(item) # TODO: check NA
return data
