gh-105564: Don't include artificial newlines in the line attribute of tokens

Signed-off-by: Pablo Galindo <[email protected]>

Author: pablogsal

Lib/test/test_peg_generator/test_pegen.py

@@ -655,10 +655,10 @@ def test_lookahead(self) -> None:
             node,
             [
                 TokenInfo(
-                    NAME, string="foo", start=(1, 0), end=(1, 3), line="foo = 12 + 12 .\n"
+                    NAME, string="foo", start=(1, 0), end=(1, 3), line="foo = 12 + 12 ."
                 ),
                 TokenInfo(
-                    OP, string="=", start=(1, 4), end=(1, 5), line="foo = 12 + 12 .\n"
+                    OP, string="=", start=(1, 4), end=(1, 5), line="foo = 12 + 12 ."
                 ),
                 [
                     TokenInfo(
@@ -675,14 +675,14 @@ def test_lookahead(self) -> None:
                                 string="+",
                                 start=(1, 9),
                                 end=(1, 10),
-                                line="foo = 12 + 12 .\n",
+                                line="foo = 12 + 12 .",
                             ),
                             TokenInfo(
                                 NUMBER,
                                 string="12",
                                 start=(1, 11),
                                 end=(1, 13),
-                                line="foo = 12 + 12 .\n",
+                                line="foo = 12 + 12 .",
                             ),
                         ]
                     ],
@@ -734,9 +734,9 @@ def test_cut(self) -> None:
         self.assertEqual(
             node,
             [
-                TokenInfo(OP, string="(", start=(1, 0), end=(1, 1), line="(1)\n"),
-                TokenInfo(NUMBER, string="1", start=(1, 1), end=(1, 2), line="(1)\n"),
-                TokenInfo(OP, string=")", start=(1, 2), end=(1, 3), line="(1)\n"),
+                TokenInfo(OP, string="(", start=(1, 0), end=(1, 1), line="(1)"),
+                TokenInfo(NUMBER, string="1", start=(1, 1), end=(1, 2), line="(1)"),
+                TokenInfo(OP, string=")", start=(1, 2), end=(1, 3), line="(1)"),
             ],
         )
 

Lib/test/test_tokenize.py

@@ -1229,7 +1229,7 @@ def readline():
         # skip the initial encoding token and the end tokens
         tokens = list(_generate_tokens_from_c_tokenizer(readline().__next__, encoding='utf-8',
                       extra_tokens=True))[:-2]
-        expected_tokens = [TokenInfo(3, '"ЉЊЈЁЂ"', (1, 0), (1, 7), '"ЉЊЈЁЂ"\n')]
+        expected_tokens = [TokenInfo(3, '"ЉЊЈЁЂ"', (1, 0), (1, 7), '"ЉЊЈЁЂ"')]
         self.assertEqual(tokens, expected_tokens,
                          "bytes not decoded with encoding")
 
@@ -1638,8 +1638,8 @@ def test_comment_at_the_end_of_the_source_without_newline(self):
             TokenInfo(type=token.NUMBER, string='1', start=(1, 4), end=(1, 5), line='b = 1\n'),
             TokenInfo(type=token.NEWLINE, string='\n', start=(1, 5), end=(1, 6), line='b = 1\n'),
             TokenInfo(type=token.NL, string='\n', start=(2, 0), end=(2, 1), line='\n'),
-            TokenInfo(type=token.COMMENT, string='#test', start=(3, 0), end=(3, 5), line='#test\n'),
-            TokenInfo(type=token.NL, string='', start=(3, 5), end=(3, 6), line='#test\n'),
+            TokenInfo(type=token.COMMENT, string='#test', start=(3, 0), end=(3, 5), line='#test'),
+            TokenInfo(type=token.NL, string='', start=(3, 5), end=(3, 6), line='#test'),
             TokenInfo(type=token.ENDMARKER, string='', start=(4, 0), end=(4, 0), line='')
         ]
 
@@ -1653,7 +1653,7 @@ def test_newline_and_space_at_the_end_of_the_source_without_newline(self):
             TokenInfo(token.ENCODING, string='utf-8', start=(0, 0), end=(0, 0), line=''),
             TokenInfo(token.NAME, string='a', start=(1, 0), end=(1, 1), line='a\n'),
             TokenInfo(token.NEWLINE, string='\n', start=(1, 1), end=(1, 2), line='a\n'),
-            TokenInfo(token.NL, string='', start=(2, 1), end=(2, 2), line=' \n'),
+            TokenInfo(token.NL, string='', start=(2, 1), end=(2, 2), line=' '),
             TokenInfo(token.ENDMARKER, string='', start=(3, 0), end=(3, 0), line='')
         ]
 
@@ -1889,10 +1889,10 @@ def readline(encoding):
             yield "1+1".encode(encoding)
 
         expected = [
-            TokenInfo(type=NUMBER, string='1', start=(1, 0), end=(1, 1), line='1+1\n'),
-            TokenInfo(type=OP, string='+', start=(1, 1), end=(1, 2), line='1+1\n'),
-            TokenInfo(type=NUMBER, string='1', start=(1, 2), end=(1, 3), line='1+1\n'),
-            TokenInfo(type=NEWLINE, string='', start=(1, 3), end=(1, 4), line='1+1\n'),
+            TokenInfo(type=NUMBER, string='1', start=(1, 0), end=(1, 1), line='1+1'),
+            TokenInfo(type=OP, string='+', start=(1, 1), end=(1, 2), line='1+1'),
+            TokenInfo(type=NUMBER, string='1', start=(1, 2), end=(1, 3), line='1+1'),
+            TokenInfo(type=NEWLINE, string='', start=(1, 3), end=(1, 4), line='1+1'),
             TokenInfo(type=ENDMARKER, string='', start=(2, 0), end=(2, 0), line='')
         ]
         for encoding in ["utf-8", "latin-1", "utf-16"]:

Misc/NEWS.d/next/Core and Builtins/2023-06-09-15-25-12.gh-issue-105564.sFdUu4.rst

@@ -0,0 +1,2 @@
+Don't include artificil newlines in the ``line`` attribute of tokens in the
+APIs of the :mod:`tokenize` module. Patch by Pablo Galindo

Python/Python-tokenize.c

@@ -206,6 +206,9 @@ tokenizeriter_next(tokenizeriterobject *it)
         line = PyUnicode_FromString("");
     } else {
         Py_ssize_t size = it->tok->inp - line_start;
+        if (size >= 1 && it->tok->implicit_newline) {
+            size -= 1;
+        }
         line = PyUnicode_DecodeUTF8(line_start, size, "replace");
     }
     if (line == NULL) {