replaced get_c_string to get_string_data, added 'note' paragraph in get_string_data docstring

Author: anmyachev

pandas/_libs/hashtable_class_helper.pxi.in

@@ -9,6 +9,8 @@ WARNING: DO NOT edit .pxi FILE directly, .pxi is generated from .pxi.in
 # VectorData
 # ----------------------------------------------------------------------
 
+from pandas._libs.tslibs.util cimport get_string_data
+
 {{py:
 
 # name, dtype, arg
@@ -595,7 +597,7 @@ cdef class StringHashTable(HashTable):
         cdef:
             khiter_t k
             const char *v
-        v = util.get_c_string(val)
+        get_string_data(val, &v, NULL)
 
         k = kh_get_str(self.table, v)
         if k != self.table.n_buckets:
@@ -609,7 +611,7 @@ cdef class StringHashTable(HashTable):
             int ret = 0
             const char *v
 
-        v = util.get_c_string(val)
+        get_string_data(val, &v, NULL)
 
         k = kh_put_str(self.table, v, &ret)
         self.table.keys[k] = key
@@ -632,7 +634,7 @@ cdef class StringHashTable(HashTable):
         vecs = <const char **>malloc(n * sizeof(char *))
         for i in range(n):
             val = values[i]
-            v = util.get_c_string(val)
+            get_string_data(val, &v, NULL)
             vecs[i] = v
 
         with nogil:
@@ -662,9 +664,9 @@ cdef class StringHashTable(HashTable):
             val = values[i]
 
             if isinstance(val, (str, unicode)):
-                v = util.get_c_string(val)
+                get_string_data(val, &v, NULL)
             else:
-                v = util.get_c_string(self.na_string_sentinel)
+                get_string_data(self.na_string_sentinel, &v, NULL)
             vecs[i] = v
 
         with nogil:
@@ -695,9 +697,9 @@ cdef class StringHashTable(HashTable):
             val = values[i]
 
             if isinstance(val, (str, unicode)):
-                v = util.get_c_string(val)
+                get_string_data(val, &v, NULL)
             else:
-                v = util.get_c_string(self.na_string_sentinel)
+                get_string_data(self.na_string_sentinel, &v, NULL)
             vecs[i] = v
 
         with nogil:
@@ -776,7 +778,7 @@ cdef class StringHashTable(HashTable):
                 labels[i] = na_sentinel
             else:
                 # if ignore_na is False, we also stringify NaN/None/etc.
-                v = util.get_c_string(val)
+                get_string_data(val, &v, NULL)
                 vecs[i] = v
 
         # compute

pandas/_libs/tslibs/util.pxd

@@ -241,6 +241,11 @@ cdef inline bint get_string_data(object s, const char **buf,
     Return `False` if it failed to extract such buffer for whatever reason
     otherwise return `True`
 
+    Note
+    ----
+    python object owns memory, `buf` should not be freed
+    `length` can be NULL
+
     Parameters
     ----------
     s      : object

pandas/_libs/util.pxd

@@ -15,21 +15,6 @@ cdef extern from "numpy/arrayobject.h":
         NPY_ARRAY_F_CONTIGUOUS
 
 
-cdef extern from *:
-    """
-    // returns ASCII or UTF8 (py3) view on python str
-    // python object owns memory, should not be freed
-    static const char* get_c_string(PyObject* obj) {
-    #if PY_VERSION_HEX >= 0x03000000
-        return PyUnicode_AsUTF8(obj);
-    #else
-        return PyString_AsString(obj);
-    #endif
-    }
-    """
-    const char *get_c_string(object) except NULL
-
-
 cdef extern from "src/headers/stdint.h":
     enum: UINT8_MAX
     enum: UINT16_MAX