bpo-40847: Consider a line with only a LINECONT a blank line (GH-20769)
A line with only a line continuation character should be considered
a blank line at tokenizer level so that only a single NEWLINE token
gets emitted. The old parser was working around the issue, but the
new parser threw a `SyntaxError` for valid input. For example,
an empty line following a line continuation character was interpreted
as a `SyntaxError`.
Co-authored-by: Pablo Galindo <Pablogsal@gmail.com>
diff --git a/Lib/test/test_peg_parser.py b/Lib/test/test_peg_parser.py
index 6ccb257..fae85e3 100644
--- a/Lib/test/test_peg_parser.py
+++ b/Lib/test/test_peg_parser.py
@@ -153,6 +153,13 @@
('dict_comp', '{x:1 for x in a}'),
('dict_comp_if', '{x:1+2 for x in a if b}'),
('dict_empty', '{}'),
+ ('empty_line_after_linecont',
+ r'''
+ pass
+ \
+
+ pass
+ '''),
('for',
'''
for i in a:
diff --git a/Lib/test/test_syntax.py b/Lib/test/test_syntax.py
index f41426a..0c207ec 100644
--- a/Lib/test/test_syntax.py
+++ b/Lib/test/test_syntax.py
@@ -858,6 +858,20 @@
"iterable argument unpacking follows "
"keyword argument unpacking")
+ def test_empty_line_after_linecont(self):
+ # See issue-40847
+ s = r"""\
+pass
+ \
+
+pass
+"""
+ try:
+ compile(s, '<string>', 'exec')
+ except SyntaxError:
+ self.fail("Empty line after a line continuation character is valid.")
+
+
def test_main():
support.run_unittest(SyntaxTestCase)
from test import test_syntax
diff --git a/Misc/NEWS.d/next/Core and Builtins/2020-06-09-23-52-32.bpo-40847.4XAACw.rst b/Misc/NEWS.d/next/Core and Builtins/2020-06-09-23-52-32.bpo-40847.4XAACw.rst
new file mode 100644
index 0000000..0b489f2
--- /dev/null
+++ b/Misc/NEWS.d/next/Core and Builtins/2020-06-09-23-52-32.bpo-40847.4XAACw.rst
@@ -0,0 +1,4 @@
+Fix a bug where a line with only a line continuation character is not considered a blank line at tokenizer level.
+In such cases, more than a single `NEWLINE` token was emitted. The old parser was working around the issue,
+but the new parser threw a :exc:`SyntaxError` for valid input due to this. For example, an empty line following
+a line continuation character was interpreted as a :exc:`SyntaxError`.
diff --git a/Parser/tokenizer.c b/Parser/tokenizer.c
index cebfadc..d461e4e 100644
--- a/Parser/tokenizer.c
+++ b/Parser/tokenizer.c
@@ -1203,8 +1203,9 @@
}
}
tok_backup(tok, c);
- if (c == '#' || c == '\n') {
+ if (c == '#' || c == '\n' || c == '\\') {
/* Lines with only whitespace and/or comments
+ and/or a line continuation character
shouldn't affect the indentation and are
not passed to the parser as NEWLINE tokens,
except *totally* empty lines in interactive