Skip to content

Commit 8d8b854

Browse files
umarbutlerumarbutler
authored
pythongh-128016: Improved invalid escape sequence warning message (python#128020)
1 parent 40a4d88 commit 8d8b854

File tree

9 files changed

+63
-25
lines changed

9 files changed

+63
-25
lines changed

‎Lib/test/test_cmd_line_script.py‎

Lines changed: 2 additions & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -659,7 +659,8 @@ def test_syntaxerror_invalid_escape_sequence_multi_line(self):
659659
stderr.splitlines()[-3:],
660660
[ b' foo = """\\q"""',
661661
b' ^^^^^^^^',
662-
b'SyntaxError: invalid escape sequence \'\\q\''
662+
b'SyntaxError: "\\q" is an invalid escape sequence. '
663+
b'Did you mean "\\\\q"? A raw string is also an option.'
663664
],
664665
)
665666

‎Lib/test/test_codeop.py‎

Lines changed: 1 addition & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -282,7 +282,7 @@ def test_warning(self):
282282
# Test that the warning is only returned once.
283283
with warnings_helper.check_warnings(
284284
('"is" with \'str\' literal', SyntaxWarning),
285-
("invalid escape sequence", SyntaxWarning),
285+
('"\\\\e" is an invalid escape sequence', SyntaxWarning),
286286
) as w:
287287
compile_command(r"'\e' is 0")
288288
self.assertEqual(len(w.warnings), 2)

‎Lib/test/test_string_literals.py‎

Lines changed: 20 additions & 9 deletions
Original file line numberDiff line numberDiff line change
@@ -116,7 +116,9 @@ def test_eval_str_invalid_escape(self):
116116
warnings.simplefilter('always', category=SyntaxWarning)
117117
eval("'''\n\\z'''")
118118
self.assertEqual(len(w), 1)
119-
self.assertEqual(str(w[0].message), r"invalid escape sequence '\z'")
119+
self.assertEqual(str(w[0].message), r'"\z" is an invalid escape sequence. '
120+
r'Such sequences will not work in the future. '
121+
r'Did you mean "\\z"? A raw string is also an option.')
120122
self.assertEqual(w[0].filename, '<string>')
121123
self.assertEqual(w[0].lineno, 1)
122124

@@ -126,7 +128,8 @@ def test_eval_str_invalid_escape(self):
126128
eval("'''\n\\z'''")
127129
exc = cm.exception
128130
self.assertEqual(w, [])
129-
self.assertEqual(exc.msg, r"invalid escape sequence '\z'")
131+
self.assertEqual(exc.msg, r'"\z" is an invalid escape sequence. '
132+
r'Did you mean "\\z"? A raw string is also an option.')
130133
self.assertEqual(exc.filename, '<string>')
131134
self.assertEqual(exc.lineno, 1)
132135
self.assertEqual(exc.offset, 1)
@@ -153,7 +156,9 @@ def test_eval_str_invalid_octal_escape(self):
153156
eval("'''\n\\407'''")
154157
self.assertEqual(len(w), 1)
155158
self.assertEqual(str(w[0].message),
156-
r"invalid octal escape sequence '\407'")
159+
r'"\407" is an invalid octal escape sequence. '
160+
r'Such sequences will not work in the future. '
161+
r'Did you mean "\\407"? A raw string is also an option.')
157162
self.assertEqual(w[0].filename, '<string>')
158163
self.assertEqual(w[0].lineno, 1)
159164

@@ -163,7 +168,8 @@ def test_eval_str_invalid_octal_escape(self):
163168
eval("'''\n\\407'''")
164169
exc = cm.exception
165170
self.assertEqual(w, [])
166-
self.assertEqual(exc.msg, r"invalid octal escape sequence '\407'")
171+
self.assertEqual(exc.msg, r'"\407" is an invalid octal escape sequence. '
172+
r'Did you mean "\\407"? A raw string is also an option.')
167173
self.assertEqual(exc.filename, '<string>')
168174
self.assertEqual(exc.lineno, 1)
169175
self.assertEqual(exc.offset, 1)
@@ -205,7 +211,9 @@ def test_eval_bytes_invalid_escape(self):
205211
warnings.simplefilter('always', category=SyntaxWarning)
206212
eval("b'''\n\\z'''")
207213
self.assertEqual(len(w), 1)
208-
self.assertEqual(str(w[0].message), r"invalid escape sequence '\z'")
214+
self.assertEqual(str(w[0].message), r'"\z" is an invalid escape sequence. '
215+
r'Such sequences will not work in the future. '
216+
r'Did you mean "\\z"? A raw string is also an option.')
209217
self.assertEqual(w[0].filename, '<string>')
210218
self.assertEqual(w[0].lineno, 1)
211219

@@ -215,7 +223,8 @@ def test_eval_bytes_invalid_escape(self):
215223
eval("b'''\n\\z'''")
216224
exc = cm.exception
217225
self.assertEqual(w, [])
218-
self.assertEqual(exc.msg, r"invalid escape sequence '\z'")
226+
self.assertEqual(exc.msg, r'"\z" is an invalid escape sequence. '
227+
r'Did you mean "\\z"? A raw string is also an option.')
219228
self.assertEqual(exc.filename, '<string>')
220229
self.assertEqual(exc.lineno, 1)
221230

@@ -228,8 +237,9 @@ def test_eval_bytes_invalid_octal_escape(self):
228237
warnings.simplefilter('always', category=SyntaxWarning)
229238
eval("b'''\n\\407'''")
230239
self.assertEqual(len(w), 1)
231-
self.assertEqual(str(w[0].message),
232-
r"invalid octal escape sequence '\407'")
240+
self.assertEqual(str(w[0].message), r'"\407" is an invalid octal escape sequence. '
241+
r'Such sequences will not work in the future. '
242+
r'Did you mean "\\407"? A raw string is also an option.')
233243
self.assertEqual(w[0].filename, '<string>')
234244
self.assertEqual(w[0].lineno, 1)
235245

@@ -239,7 +249,8 @@ def test_eval_bytes_invalid_octal_escape(self):
239249
eval("b'''\n\\407'''")
240250
exc = cm.exception
241251
self.assertEqual(w, [])
242-
self.assertEqual(exc.msg, r"invalid octal escape sequence '\407'")
252+
self.assertEqual(exc.msg, r'"\407" is an invalid octal escape sequence. '
253+
r'Did you mean "\\407"? A raw string is also an option.')
243254
self.assertEqual(exc.filename, '<string>')
244255
self.assertEqual(exc.lineno, 1)
245256

‎Lib/test/test_unparse.py‎

Lines changed: 3 additions & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -651,7 +651,9 @@ def test_multiquote_joined_string(self):
651651

652652
def test_backslash_in_format_spec(self):
653653
import re
654-
msg = re.escape("invalid escape sequence '\\ '")
654+
msg = re.escape('"\\ " is an invalid escape sequence. '
655+
'Such sequences will not work in the future. '
656+
'Did you mean "\\\\ "? A raw string is also an option.')
655657
with self.assertWarnsRegex(SyntaxWarning, msg):
656658
self.check_ast_roundtrip("""f"{x:\\ }" """)
657659
self.check_ast_roundtrip("""f"{x:\\n}" """)

‎Misc/NEWS.d/next/Core_and_Builtins/2024-12-17-09-28-17.gh-issue-128016.DPqhah.rst‎

Lines changed: 1 addition & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -0,0 +1 @@
1+
Improved the ``SyntaxWarning`` message for invalid escape sequences to clarify that such sequences will raise a ``SyntaxError`` in future Python releases. The new message also suggests a potential fix, i.e., ``Did you mean "\\e"?``.

‎Objects/bytesobject.c‎

Lines changed: 4 additions & 3 deletions
Original file line numberDiff line numberDiff line change
@@ -1205,7 +1205,8 @@ PyObject *PyBytes_DecodeEscape(const char *s,
12051205
unsigned char c = *first_invalid_escape;
12061206
if ('4' <= c && c <= '7') {
12071207
if (PyErr_WarnFormat(PyExc_DeprecationWarning, 1,
1208-
"invalid octal escape sequence '\\%.3s'",
1208+
"b\"\\%.3s\" is an invalid octal escape sequence. "
1209+
"Such sequences will not work in the future. ",
12091210
first_invalid_escape) < 0)
12101211
{
12111212
Py_DECREF(result);
@@ -1214,7 +1215,8 @@ PyObject *PyBytes_DecodeEscape(const char *s,
12141215
}
12151216
else {
12161217
if (PyErr_WarnFormat(PyExc_DeprecationWarning, 1,
1217-
"invalid escape sequence '\\%c'",
1218+
"b\"\\%c\" is an invalid escape sequence. "
1219+
"Such sequences will not work in the future. ",
12181220
c) < 0)
12191221
{
12201222
Py_DECREF(result);
@@ -1223,7 +1225,6 @@ PyObject *PyBytes_DecodeEscape(const char *s,
12231225
}
12241226
}
12251227
return result;
1226-
12271228
}
12281229
/* -------------------------------------------------------------------- */
12291230
/* object api */

‎Objects/unicodeobject.c‎

Lines changed: 4 additions & 2 deletions
Original file line numberDiff line numberDiff line change
@@ -6853,7 +6853,8 @@ _PyUnicode_DecodeUnicodeEscapeStateful(const char *s,
68536853
unsigned char c = *first_invalid_escape;
68546854
if ('4' <= c && c <= '7') {
68556855
if (PyErr_WarnFormat(PyExc_DeprecationWarning, 1,
6856-
"invalid octal escape sequence '\\%.3s'",
6856+
"\"\\%.3s\" is an invalid octal escape sequence. "
6857+
"Such sequences will not work in the future. ",
68576858
first_invalid_escape) < 0)
68586859
{
68596860
Py_DECREF(result);
@@ -6862,7 +6863,8 @@ _PyUnicode_DecodeUnicodeEscapeStateful(const char *s,
68626863
}
68636864
else {
68646865
if (PyErr_WarnFormat(PyExc_DeprecationWarning, 1,
6865-
"invalid escape sequence '\\%c'",
6866+
"\"\\%c\" is an invalid escape sequence. "
6867+
"Such sequences will not work in the future. ",
68666868
c) < 0)
68676869
{
68686870
Py_DECREF(result);

‎Parser/string_parser.c‎

Lines changed: 18 additions & 6 deletions
Original file line numberDiff line numberDiff line change
@@ -28,9 +28,16 @@ warn_invalid_escape_sequence(Parser *p, const char *first_invalid_escape, Token
2828
int octal = ('4' <= c && c <= '7');
2929
PyObject *msg =
3030
octal
31-
? PyUnicode_FromFormat("invalid octal escape sequence '\\%.3s'",
32-
first_invalid_escape)
33-
: PyUnicode_FromFormat("invalid escape sequence '\\%c'", c);
31+
? PyUnicode_FromFormat(
32+
"\"\\%.3s\" is an invalid octal escape sequence. "
33+
"Such sequences will not work in the future. "
34+
"Did you mean \"\\\\%.3s\"? A raw string is also an option.",
35+
first_invalid_escape, first_invalid_escape)
36+
: PyUnicode_FromFormat(
37+
"\"\\%c\" is an invalid escape sequence. "
38+
"Such sequences will not work in the future. "
39+
"Did you mean \"\\\\%c\"? A raw string is also an option.",
40+
c, c);
3441
if (msg == NULL) {
3542
return -1;
3643
}
@@ -53,11 +60,16 @@ warn_invalid_escape_sequence(Parser *p, const char *first_invalid_escape, Token
5360
error location, if p->known_err_token is not set. */
5461
p->known_err_token = t;
5562
if (octal) {
56-
RAISE_SYNTAX_ERROR("invalid octal escape sequence '\\%.3s'",
57-
first_invalid_escape);
63+
RAISE_SYNTAX_ERROR(
64+
"\"\\%.3s\" is an invalid octal escape sequence. "
65+
"Did you mean \"\\\\%.3s\"? A raw string is also an option.",
66+
first_invalid_escape, first_invalid_escape);
5867
}
5968
else {
60-
RAISE_SYNTAX_ERROR("invalid escape sequence '\\%c'", c);
69+
RAISE_SYNTAX_ERROR(
70+
"\"\\%c\" is an invalid escape sequence. "
71+
"Did you mean \"\\\\%c\"? A raw string is also an option.",
72+
c, c);
6173
}
6274
}
6375
Py_DECREF(msg);

‎Parser/tokenizer/helpers.c‎

Lines changed: 10 additions & 2 deletions
Original file line numberDiff line numberDiff line change
@@ -113,7 +113,10 @@ _PyTokenizer_warn_invalid_escape_sequence(struct tok_state *tok, int first_inval
113113
}
114114

115115
PyObject *msg = PyUnicode_FromFormat(
116-
"invalid escape sequence '\\%c'",
116+
"\"\\%c\" is an invalid escape sequence. "
117+
"Such sequences will not work in the future. "
118+
"Did you mean \"\\\\%c\"? A raw string is also an option.",
119+
(char) first_invalid_escape_char,
117120
(char) first_invalid_escape_char
118121
);
119122

@@ -129,7 +132,12 @@ _PyTokenizer_warn_invalid_escape_sequence(struct tok_state *tok, int first_inval
129132
/* Replace the SyntaxWarning exception with a SyntaxError
130133
to get a more accurate error report */
131134
PyErr_Clear();
132-
return _PyTokenizer_syntaxerror(tok, "invalid escape sequence '\\%c'", (char) first_invalid_escape_char);
135+
136+
return _PyTokenizer_syntaxerror(tok,
137+
"\"\\%c\" is an invalid escape sequence. "
138+
"Did you mean \"\\\\%c\"? A raw string is also an option.",
139+
(char) first_invalid_escape_char,
140+
(char) first_invalid_escape_char);
133141
}
134142

135143
return -1;

0 commit comments

Comments
 (0)