summaryrefslogtreecommitdiffstats
diff options
context:
space:
mode:
authorNick Coghlan <ncoghlan@gmail.com>2014-06-16 09:48:02 (GMT)
committerNick Coghlan <ncoghlan@gmail.com>2014-06-16 09:48:02 (GMT)
commit5b1fdc1e377df88078f7788bf85dfebd353dc178 (patch)
tree922b50792ecc56d09650996971ac112971dafd9a
parentb6d1f48c14b7a3bc7047138dc0bf5aadfe6be480 (diff)
downloadcpython-5b1fdc1e377df88078f7788bf85dfebd353dc178.zip
cpython-5b1fdc1e377df88078f7788bf85dfebd353dc178.tar.gz
cpython-5b1fdc1e377df88078f7788bf85dfebd353dc178.tar.bz2
Issue #21669: Special case print & exec syntax errors
-rw-r--r--Lib/test/test_grammar.py25
-rw-r--r--Misc/NEWS5
-rw-r--r--Objects/exceptions.c135
3 files changed, 165 insertions, 0 deletions
diff --git a/Lib/test/test_grammar.py b/Lib/test/test_grammar.py
index f012de1..70d85b1 100644
--- a/Lib/test/test_grammar.py
+++ b/Lib/test/test_grammar.py
@@ -390,6 +390,31 @@ class GrammarTests(unittest.TestCase):
check_syntax_error(self, "x + 1 = 1")
check_syntax_error(self, "a + 1 = b + 2")
+ # Check the heuristic for print & exec covers significant cases
+ # As well as placing some limits on false positives
+ def test_former_statements_refer_to_builtins(self):
+ keywords = "print", "exec"
+ # Cases where we want the custom error
+ cases = [
+ "{} foo",
+ "{} {{1:foo}}",
+ "if 1: {} foo",
+ "if 1: {} {{1:foo}}",
+ "if 1:\n {} foo",
+ "if 1:\n {} {{1:foo}}",
+ ]
+ for keyword in keywords:
+ custom_msg = "call to '{}'".format(keyword)
+ for case in cases:
+ source = case.format(keyword)
+ with self.subTest(source=source):
+ with self.assertRaisesRegex(SyntaxError, custom_msg):
+ exec(source)
+ source = source.replace("foo", "(foo.)")
+ with self.subTest(source=source):
+ with self.assertRaisesRegex(SyntaxError, "invalid syntax"):
+ exec(source)
+
def test_del_stmt(self):
# 'del' exprlist
abc = [1,2,3]
diff --git a/Misc/NEWS b/Misc/NEWS
index 6d5c0a1..90f3c86 100644
--- a/Misc/NEWS
+++ b/Misc/NEWS
@@ -10,6 +10,11 @@ Release date: XXXX-XX-XX
Core and Builtins
-----------------
+- Issue #21669: With the aid of heuristics in SyntaxError.__init__, the
+ parser now attempts to generate more meaningful (or at least more search
+ engine friendly) error messages when "exec" and "print" are used as
+ statements.
+
- Issue #21642: If the conditional if-else expression, allow an integer written
with no space between itself and the ``else`` keyword (e.g. ``True if 42else
False``) to be valid syntax.
diff --git a/Objects/exceptions.c b/Objects/exceptions.c
index a733f30..873fbc6 100644
--- a/Objects/exceptions.c
+++ b/Objects/exceptions.c
@@ -1254,6 +1254,9 @@ SimpleExtendsException(PyExc_Exception, AttributeError,
* SyntaxError extends Exception
*/
+/* Helper function to customise error message for some syntax errors */
+static int _report_missing_parentheses(PySyntaxErrorObject *self);
+
static int
SyntaxError_init(PySyntaxErrorObject *self, PyObject *args, PyObject *kwds)
{
@@ -1298,6 +1301,13 @@ SyntaxError_init(PySyntaxErrorObject *self, PyObject *args, PyObject *kwds)
Py_INCREF(self->text);
Py_DECREF(info);
+
+ /* Issue #21669: Custom error for 'print' & 'exec' as statements */
+ if (self->text && PyUnicode_Check(self->text)) {
+ if (_report_missing_parentheses(self) < 0) {
+ return -1;
+ }
+ }
}
return 0;
}
@@ -2783,3 +2793,128 @@ _PyErr_TrySetFromCause(const char *format, ...)
PyErr_Restore(new_exc, new_val, new_tb);
return new_val;
}
+
+
+/* To help with migration from Python 2, SyntaxError.__init__ applies some
+ * heuristics to try to report a more meaningful exception when print and
+ * exec are used like statements.
+ *
+ * The heuristics are currently expected to detect the following cases:
+ * - top level statement
+ * - statement in a nested suite
+ * - trailing section of a one line complex statement
+ *
+ * They're currently known not to trigger:
+ * - after a semi-colon
+ *
+ * The error message can be a bit odd in cases where the "arguments" are
+ * completely illegal syntactically, but that isn't worth the hassle of
+ * fixing.
+ *
+ * We also can't do anything about cases that are legal Python 3 syntax
+ * but mean something entirely different from what they did in Python 2
+ * (omitting the arguments entirely, printing items preceded by a unary plus
+ * or minus, using the stream redirection syntax).
+ */
+
+static int
+_check_for_legacy_statements(PySyntaxErrorObject *self, Py_ssize_t start)
+{
+ /* Return values:
+ * -1: an error occurred
+ * 0: nothing happened
+ * 1: the check triggered & the error message was changed
+ */
+ static PyObject *print_prefix = NULL;
+ static PyObject *exec_prefix = NULL;
+ Py_ssize_t text_len = PyUnicode_GET_LENGTH(self->text);
+ int kind = PyUnicode_KIND(self->text);
+ void *data = PyUnicode_DATA(self->text);
+
+ /* Ignore leading whitespace */
+ while (start < text_len) {
+ Py_UCS4 ch = PyUnicode_READ(kind, data, start);
+ if (!Py_UNICODE_ISSPACE(ch))
+ break;
+ start++;
+ }
+ /* Checking against an empty or whitespace-only part of the string */
+ if (start == text_len) {
+ return 0;
+ }
+
+ /* Check for legacy print statements */
+ if (print_prefix == NULL) {
+ print_prefix = PyUnicode_InternFromString("print ");
+ if (print_prefix == NULL) {
+ return -1;
+ }
+ }
+ if (PyUnicode_Tailmatch(self->text, print_prefix,
+ start, text_len, -1)) {
+ Py_CLEAR(self->msg);
+ self->msg = PyUnicode_FromString(
+ "Missing parentheses in call to 'print'");
+ return 1;
+ }
+
+ /* Check for legacy exec statements */
+ if (exec_prefix == NULL) {
+ exec_prefix = PyUnicode_InternFromString("exec ");
+ if (exec_prefix == NULL) {
+ return -1;
+ }
+ }
+ if (PyUnicode_Tailmatch(self->text, exec_prefix,
+ start, text_len, -1)) {
+ Py_CLEAR(self->msg);
+ self->msg = PyUnicode_FromString(
+ "Missing parentheses in call to 'exec'");
+ return 1;
+ }
+ /* Fall back to the default error message */
+ return 0;
+}
+
+static int
+_report_missing_parentheses(PySyntaxErrorObject *self)
+{
+ Py_UCS4 left_paren = 40;
+ Py_ssize_t left_paren_index;
+ Py_ssize_t text_len = PyUnicode_GET_LENGTH(self->text);
+ int legacy_check_result = 0;
+
+ /* Skip entirely if there is an opening parenthesis */
+ left_paren_index = PyUnicode_FindChar(self->text, left_paren,
+ 0, text_len, 1);
+ if (left_paren_index < -1) {
+ return -1;
+ }
+ if (left_paren_index != -1) {
+ /* Use default error message for any line with an opening paren */
+ return 0;
+ }
+ /* Handle the simple statement case */
+ legacy_check_result = _check_for_legacy_statements(self, 0);
+ if (legacy_check_result < 0) {
+ return -1;
+
+ }
+ if (legacy_check_result == 0) {
+ /* Handle the one-line complex statement case */
+ Py_UCS4 colon = 58;
+ Py_ssize_t colon_index;
+ colon_index = PyUnicode_FindChar(self->text, colon,
+ 0, text_len, 1);
+ if (colon_index < -1) {
+ return -1;
+ }
+ if (colon_index >= 0 && colon_index < text_len) {
+ /* Check again, starting from just after the colon */
+ if (_check_for_legacy_statements(self, colon_index+1) < 0) {
+ return -1;
+ }
+ }
+ }
+ return 0;
+}