Issue #18038: SyntaxError raised during compilation sources with illegal
encoding now always contains an encoding name.
diff --git a/Parser/tokenizer.c b/Parser/tokenizer.c
index 93a4a5c..7fe384b 100644
--- a/Parser/tokenizer.c
+++ b/Parser/tokenizer.c
@@ -291,20 +291,20 @@
tok->encoding = cs;
tok->decoding_state = STATE_NORMAL;
}
- else
+ else {
+ PyErr_Format(PyExc_SyntaxError,
+ "encoding problem: %s", cs);
PyMem_FREE(cs);
+ }
}
} else { /* then, compare cs with BOM */
r = (strcmp(tok->encoding, cs) == 0);
+ if (!r)
+ PyErr_Format(PyExc_SyntaxError,
+ "encoding problem: %s with BOM", cs);
PyMem_FREE(cs);
}
}
- if (!r) {
- cs = tok->encoding;
- if (!cs)
- cs = "with BOM";
- PyErr_Format(PyExc_SyntaxError, "encoding problem: %s", cs);
- }
return r;
}