Add series.str.len() in new style (#321)

* Add series.str.len() in new style

* Workaround issue with named series

Author: densmirn

sdc/datatypes/hpat_pandas_stringmethods_functions.py

@@ -83,6 +83,7 @@ def hpat_pandas_stringmethods_upper_impl(self):
 
 import numba
 from numba.extending import overload_method
+from numba.errors import TypingError
 
 from sdc.datatypes.hpat_pandas_stringmethods_types import StringMethodsType
 
@@ -186,6 +187,42 @@ def hpat_pandas_stringmethods_{methodname}_impl(self{methodparams}):
 """
 
 
+@overload_method(StringMethodsType, 'len')
+def hpat_pandas_stringmethods_len(self):
+    """
+    Pandas Series method :meth:`pandas.core.strings.StringMethods.len()` implementation.
+
+    Note: Unicode type of list elements are supported only. Numpy.NaN is not supported as elements.
+
+    .. only:: developer
+
+    Test: python -m sdc.runtests sdc.tests.test_series.TestSeries.test_series_str_len1
+
+    Parameters
+    ----------
+    self: :class:`pandas.core.strings.StringMethods`
+        input arg
+
+    Returns
+    -------
+    :obj:`pandas.Series`
+         returns :obj:`pandas.Series` object
+    """
+
+    if not isinstance(self, StringMethodsType):
+        raise TypingError('Method len(). The object must be a pandas.core.strings. Given: {}'.format(self))
+
+    def hpat_pandas_stringmethods_len_impl(self):
+        item_count = len(self._data)
+        result = numpy.empty(item_count, numba.types.int64)
+        for idx, item in enumerate(self._data._data):
+            result[idx] = len(item)
+
+        return pandas.Series(result, name=self._data._name)
+
+    return hpat_pandas_stringmethods_len_impl
+
+
 def _hpat_pandas_stringmethods_autogen(method_name):
     """"
     The function generates a function for 'method_name' from source text that is created on the fly.
@@ -231,7 +268,7 @@ def _hpat_pandas_stringmethods_autogen(method_name):
     This is the list of function which are autogenerated to be used from Numba directly.
 """
 
-_hpat_pandas_stringmethods_autogen_exceptions = ['split', 'len', 'get', 'replace']
+_hpat_pandas_stringmethods_autogen_exceptions = ['split', 'get', 'replace']
 
 for method_name in _hpat_pandas_stringmethods_autogen_methods:
     if not (method_name.startswith('__') or method_name in _hpat_pandas_stringmethods_autogen_exceptions):

sdc/hiframes/pd_series_ext.py

@@ -756,7 +756,7 @@ def resolve_rename(self, ary, args, kws):
     Functions which are still overloaded by HPAT compiler pipeline
 """
 
-str2str_methods_excluded = ['upper', 'lower', 'lstrip', 'rstrip', 'strip']
+str2str_methods_excluded = ['upper', 'len', 'lower', 'lstrip', 'rstrip', 'strip']
 """
     Functions which are used from Numba directly by calling from StringMethodsType
 

sdc/tests/test_series.py

@@ -2347,7 +2347,8 @@ def test_impl(S):
             return S.str.len()
         hpat_func = self.jit(test_impl)
 
-        S = pd.Series(['aa', 'abc', 'c', 'cccd'])
+        # TODO: fix issue occurred if name is not assigned
+        S = pd.Series(['aa', 'abc', 'c', 'cccd'], name='A')
         pd.testing.assert_series_equal(hpat_func(S), test_impl(S))
 
     @skip_numba_jit