summaryrefslogtreecommitdiffstats
diff options
context:
space:
mode:
authorPablo Galindo <Pablogsal@gmail.com>2020-01-06 15:59:09 (GMT)
committerGitHub <noreply@github.com>2020-01-06 15:59:09 (GMT)
commit5ec91f78d59d9c39b984f284e00cd04b96ddb5db (patch)
tree3584ef9005da8bc532c12665147c8313142ff0e6
parent075ebad369d94342624792a41d3055c907bfa436 (diff)
downloadcpython-5ec91f78d59d9c39b984f284e00cd04b96ddb5db.zip
cpython-5ec91f78d59d9c39b984f284e00cd04b96ddb5db.tar.gz
cpython-5ec91f78d59d9c39b984f284e00cd04b96ddb5db.tar.bz2
bpo-39209: Manage correctly multi-line tokens in interactive mode (GH-17860)
-rw-r--r--Lib/test/test_repl.py36
-rw-r--r--Misc/NEWS.d/next/Core and Builtins/2020-01-06-10-29-16.bpo-39209.QHAONe.rst2
-rw-r--r--Parser/tokenizer.c2
3 files changed, 40 insertions, 0 deletions
diff --git a/Lib/test/test_repl.py b/Lib/test/test_repl.py
index 9efd459..71f192f 100644
--- a/Lib/test/test_repl.py
+++ b/Lib/test/test_repl.py
@@ -58,5 +58,41 @@ class TestInteractiveInterpreter(unittest.TestCase):
# Exit code 120: Py_FinalizeEx() failed to flush stdout and stderr.
self.assertIn(p.returncode, (1, 120))
+ @cpython_only
+ def test_multiline_string_parsing(self):
+ # bpo-39209: Multiline string tokens need to be handled in the tokenizer
+ # in two places: the interactive path and the non-interactive path.
+ user_input = '''\
+ x = """<?xml version="1.0" encoding="iso-8859-1"?>
+ <test>
+ <Users>
+ <fun25>
+ <limits>
+ <total>0KiB</total>
+ <kbps>0</kbps>
+ <rps>1.3</rps>
+ <connections>0</connections>
+ </limits>
+ <usages>
+ <total>16738211KiB</total>
+ <kbps>237.15</kbps>
+ <rps>1.3</rps>
+ <connections>0</connections>
+ </usages>
+ <time_to_refresh>never</time_to_refresh>
+ <limit_exceeded_URL>none</limit_exceeded_URL>
+ </fun25>
+ </Users>
+ </test>"""
+ '''
+ user_input = dedent(user_input)
+ user_input = user_input.encode()
+ p = spawn_repl()
+ with SuppressCrashReport():
+ p.stdin.write(user_input)
+ output = kill_python(p)
+ self.assertEqual(p.returncode, 0)
+
+
if __name__ == "__main__":
unittest.main()
diff --git a/Misc/NEWS.d/next/Core and Builtins/2020-01-06-10-29-16.bpo-39209.QHAONe.rst b/Misc/NEWS.d/next/Core and Builtins/2020-01-06-10-29-16.bpo-39209.QHAONe.rst
new file mode 100644
index 0000000..c05b3f8
--- /dev/null
+++ b/Misc/NEWS.d/next/Core and Builtins/2020-01-06-10-29-16.bpo-39209.QHAONe.rst
@@ -0,0 +1,2 @@
+Correctly handle multi-line tokens in interactive mode. Patch by Pablo
+Galindo.
diff --git a/Parser/tokenizer.c b/Parser/tokenizer.c
index f84093d..f73c326 100644
--- a/Parser/tokenizer.c
+++ b/Parser/tokenizer.c
@@ -886,6 +886,7 @@ tok_nextc(struct tok_state *tok)
size_t start = tok->start - tok->buf;
size_t oldlen = tok->cur - tok->buf;
size_t newlen = oldlen + strlen(newtok);
+ Py_ssize_t cur_multi_line_start = tok->multi_line_start - tok->buf;
char *buf = tok->buf;
buf = (char *)PyMem_REALLOC(buf, newlen+1);
tok->lineno++;
@@ -898,6 +899,7 @@ tok_nextc(struct tok_state *tok)
}
tok->buf = buf;
tok->cur = tok->buf + oldlen;
+ tok->multi_line_start = tok->buf + cur_multi_line_start;
tok->line_start = tok->cur;
strcpy(tok->buf + oldlen, newtok);
PyMem_FREE(newtok);