Add new 'split' functionality

shublang/shublang.py

@@ -46,6 +46,25 @@ def decode(iterable, encoding):
     return (x.decode(encoding) for x in iterable)
 
 
+@Pipe
+def split(iterable, sep, maxsplit=-1):
+    """Returns a list of words in the string, using sep as the delimiter.
+    If maxsplit is given, at most maxsplit splits are done.
+
+    :param iterable: collection of data to transform
+    :type iterable: list
+
+    :param sep: this is a delimiter. The string will be split by this separator.
+    :type sep: string
+
+    :param maxsplit: (optional) if given, there will be at most maxsplit splits.
+    :type maxsplit: int
+    """
+
+
+    return (x.split(sep, maxsplit) for x in iterable)
+
+
 @Pipe
 def sanitize(iterable):
     # TODO change name and add other options

tests/test_functions.py

@@ -1,5 +1,6 @@
 # TODO add tests for functions
 
+import pytest
 from shublang import evaluate
 
 def test_sub():
@@ -21,6 +22,26 @@ def test_decode():
            b'\xbe\x80\xe1\xbe\x90'
     assert evaluate('decode("UTF8")', data=[text]) == ["ἀἐἠἰὀὐὠὰᾀᾐ"]
 
+
+@pytest.mark.parametrize(
+    "test_input,expected",
+    [
+        (
+            ['split(",")', ['Python,Haskell,Scala,Rust']],
+            [['Python', 'Haskell', 'Scala', 'Rust']]
+        ),
+
+        # maxsplit should limit the number of separations
+        (
+            ['split(",", 2)', ['Python,Haskell,Scala,Rust']],
+            [['Python', 'Haskell', 'Scala,Rust']]
+        ),
+    ]
+)
+def test_split(test_input, expected):
+    assert evaluate(*test_input) == expected
+
+
 def test_sanitize():
     text = ["Python \t\t\t\t",
             "<br/>Haskell",