Apply suggestions from @vmarkovtsev

Signed-off-by: Irina <irenekhismatullina@gmail.com>

sourced/ml/algorithms/token_parser.py

@@ -34,9 +34,9 @@ class TokenParser:
     # if you do not want to filter small tokens set min_split_length=1.
     SAVE_TOKEN_STYLE = False  # whether yield metadata that can be used to reconstruct initial
     # identifier.
-    ATTACH_UPPER = False  # True to attach the last of several uppercase letters in a row to
-    # the next token. Example: 'HTMLResponce' -> ["html", "responce"] if True,
-    # 'HTMLResponce' -> ["htmlr", "esponce"] if False.
+    ATTACH_UPPER = True  # True to attach the last of several uppercase letters in a row to
+    # the next token. Example: 'HTMLResponse' -> ["html", "response"] if True,
+    # 'HTMLResponse' -> ["htmlr", "esponse"] if False.
 
     def __init__(self, stem_threshold=STEM_THRESHOLD, max_token_length=MAX_TOKEN_LENGTH,
                  min_split_length=MIN_SPLIT_LENGTH, single_shot=DEFAULT_SINGLE_SHOT,

sourced/ml/tests/test_token_parser.py

@@ -6,7 +6,7 @@
 
 class TokenParserTests(unittest.TestCase):
     def setUp(self):
-        self.tp = TokenParser(stem_threshold=4, max_token_length=20)
+        self.tp = TokenParser(stem_threshold=4, max_token_length=20, attach_upper=False)
         self.tp._single_shot = False
 
     def test_process_token(self):
@@ -55,7 +55,7 @@ def test_process_token(self):
 
     def test_process_token_with_attach_upper(self):
         tp = TokenParser(stem_threshold=100, single_shot=True, max_token_length=100,
-                         min_split_length=1, attach_upper=True)
+                         min_split_length=1)
         tokens = [
             ("UpperCamelCase", ["upper", "camel", "case"]),
             ("camelCase", ["camel", "case"]),