Resolve PyCQA#1948

To use a curly brace in an f-string, you must escape it. For example:

  >>> k = 1
  >>> f'{{{k}'
  '{1'

Saving this as a script and running the 'tokenize' module higlights
something odd around our counting:

  ❯ python -m tokenize wow.py
  0,0-0,0:            ENCODING       'utf-8'
  1,0-1,1:            NAME           'k'
  1,2-1,3:            OP             '='
  1,4-1,5:            NUMBER         '1'
  1,5-1,6:            NEWLINE        '\n'
  2,0-2,2:            FSTRING_START  "f'"
  2,2-2,3:            FSTRING_MIDDLE '{'     # <-- here...
  2,4-2,5:            OP             '{'     # <-- and here
  2,5-2,6:            NAME           'k'
  2,6-2,7:            OP             '}'
  2,7-2,8:            FSTRING_END    "'"
  2,8-2,9:            NEWLINE        '\n'
  3,0-3,0:            ENDMARKER      ''

The FSTRING_MIDDLE character we have is the escaped/post-parse single
curly brace rather than the raw double curly brace, however, while our
end index of this token accounts for the parsed form, the start index of
the next token does not (put another way, it jumps from 3 -> 4). This
triggers some existing, unrelated code that we need to bypass. Do just
that.

Signed-off-by: Stephen Finucane <[email protected]>

src/flake8/processor.py

@@ -203,9 +203,17 @@ def build_logical_line_tokens(self) -> _Logical:  # noqa: C901
             if token_type == tokenize.STRING:
                 text = mutate_string(text)
             elif token_type == FSTRING_MIDDLE:  # pragma: >=3.12 cover
-                text = "x" * len(text)
+                # A curly brace in an FSTRING_MIDDLE token must be an escaped
+                # curly brace. Both 'text' and 'end' will account for the
+                # escaped version of the token (i.e. a single brace) rather
+                # than the raw double brace version, so we must counteract this
+                fstring_offset = 0
+                if "{" in text or "}" in text:
+                    fstring_offset = text.count("{") + text.count("}")
+                text = "x" * (len(text) + fstring_offset)
+                end = (end[0], end[1] + fstring_offset)
             if previous_row:
-                (start_row, start_column) = start
+                start_row, start_column = start
                 if previous_row != start_row:
                     row_index = previous_row - 1
                     column_index = previous_column - 1
@@ -219,7 +227,7 @@ def build_logical_line_tokens(self) -> _Logical:  # noqa: C901
             logical.append(text)
             length += len(text)
             mapping.append((length, end))
-            (previous_row, previous_column) = end
+            previous_row, previous_column = end
         return comments, logical, mapping
 
     def build_ast(self) -> ast.AST:

tests/integration/test_plugins.py

@@ -248,7 +248,7 @@ def test_logical_line_plugin(tmpdir, capsys):
     cfg.write(cfg_s)
 
     src = """\
-f'hello world'
+f'{{"{hello}": "{world}"}}'
 """
     t_py = tmpdir.join("t.py")
     t_py.write_binary(src.encode())
@@ -257,7 +257,7 @@ def test_logical_line_plugin(tmpdir, capsys):
         assert main(("t.py", "--config", str(cfg))) == 1
 
     expected = """\
-t.py:1:1: T001 "f'xxxxxxxxxxx'"
+t.py:1:1: T001 "f'xxx{hello}xxxx{world}xxx'"
 """
     out, err = capsys.readouterr()
     assert out == expected