py/lexer: Raise SyntaxError when unicode char point out of range.

dpgeorge · dpgeorge · commit 0be3c70cd88d · 2015-09-07T17:19:17.000+01:00
diff --git a/py/lexer.c b/py/lexer.c
@@ -500,7 +500,9 @@ STATIC void mp_lexer_next_token_into(mp_lexer_t *lex, bool first_token) {
                         }
                         #endif
                         else {
-                            assert(!"TODO: Throw an error, invalid escape code probably");
+                            // unicode character out of range
+                            // this raises a generic SyntaxError; could provide more info
+                            lex->tok_kind = MP_TOKEN_INVALID;
                         }
                     }
                 } else {
diff --git a/tests/unicode/unicode.py b/tests/unicode/unicode.py
@@ -20,3 +20,9 @@
 # printing of unicode chars using repr
 # TODO we don't do this correctly
 #print(repr(s))
+
+# test invalid escape code
+try:
+    eval('"\\U00110000"')
+except SyntaxError:
+    print('SyntaxError')

Original file line number	Diff line number	Diff line change
`@@ -500,7 +500,9 @@ STATIC void mp_lexer_next_token_into(mp_lexer_t *lex, bool first_token) {`
`500`	`500`	`}`
`501`	`501`	`#endif`
`502`	`502`	`else {`
`503`		`- assert(!"TODO: Throw an error, invalid escape code probably");`
	`503`	`+ // unicode character out of range`
	`504`	`+ // this raises a generic SyntaxError; could provide more info`
	`505`	`+ lex->tok_kind = MP_TOKEN_INVALID;`
`504`	`506`	`}`
`505`	`507`	`}`
`506`	`508`	`} else {`