Skip to content

[3.7] bpo-36440: include node names in ParserError messages, instead of numeric IDs (GH-12565) #12671

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
pablogsal merged 1 commit into from
Apr 3, 2019
Merged

[3.7] bpo-36440: include node names in ParserError messages, instead of numeric IDs (GH-12565) #12671

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
16 changes: 16 additions & 0 deletions Lib/test/test_parser.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -713,6 +713,22 @@ def test_illegal_encoding(self):
with self.assertRaises(UnicodeEncodeError):
parser.sequence2st(tree)

def test_invalid_node_id(self):
tree = (257, (269, (-7, '')))
self.check_bad_tree(tree, "negative node id")
tree = (257, (269, (99, '')))
self.check_bad_tree(tree, "invalid token id")
tree = (257, (269, (9999, (0, ''))))
self.check_bad_tree(tree, "invalid symbol id")

def test_ParserError_message(self):
try:
parser.sequence2st((257,(269,(257,(0,'')))))
except parser.ParserError as why:
self.assertIn("simple_stmt", str(why)) # Expected
self.assertIn("file_input", str(why)) # Got



class CompileTestCase(unittest.TestCase):

Expand Down
2 changes: 2 additions & 0 deletions Misc/NEWS.d/next/Core and Builtins/2019-03-25-13-45-19.bpo-36440.gkvzhi.rst
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -0,0 +1,2 @@
Include node names in ``ParserError`` messages, instead of numeric IDs.
Patch by A. Skrobov.
17 changes: 11 additions & 6 deletions Modules/parsermodule.c
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -24,10 +24,6 @@
* Py_[X]DECREF() and Py_[X]INCREF() macros. The lint annotations
* look like "NOTE(...)".
*
* To debug parser errors like
* "parser.ParserError: Expected node type 12, got 333."
* decode symbol numbers using the automatically-generated files
* Lib/symbol.h and Include/token.h.
*/

#include "Python.h" /* general Python API */
Expand Down Expand Up @@ -663,6 +659,13 @@ validate_node(node *tree)
for (pos = 0; pos < nch; ++pos) {
node *ch = CHILD(tree, pos);
int ch_type = TYPE(ch);
if ((ch_type >= NT_OFFSET + _PyParser_Grammar.g_ndfas)
|| (ISTERMINAL(ch_type) && (ch_type >= N_TOKENS))
|| (ch_type < 0)
) {
PyErr_Format(parser_error, "Unrecognized node type %d.", ch_type);
return 0;
}
for (arc = 0; arc < dfa_state->s_narcs; ++arc) {
short a_label = dfa_state->s_arc[arc].a_lbl;
assert(a_label < _PyParser_Grammar.g_ll.ll_nlabels);
Expand Down Expand Up @@ -691,8 +694,10 @@ validate_node(node *tree)
const char *expected_str = _PyParser_Grammar.g_ll.ll_label[a_label].lb_str;

if (ISNONTERMINAL(next_type)) {
PyErr_Format(parser_error, "Expected node type %d, got %d.",
next_type, ch_type);
PyErr_Format(parser_error, "Expected %s, got %s.",
_PyParser_Grammar.g_dfa[next_type - NT_OFFSET].d_name,
ISTERMINAL(ch_type) ? _PyParser_TokenNames[ch_type] :
_PyParser_Grammar.g_dfa[ch_type - NT_OFFSET].d_name);
}
else if (expected_str != NULL) {
PyErr_Format(parser_error, "Illegal terminal: expected '%s'.",
Expand Down