[[ LCB ]] Replace overlong unicode escapes with U+FFFD.

runrevmark · runrevmark · commit f2513dc1dc68 · 2015-02-10T10:00:54.000Z
diff --git a/docs/specs/livecode_builder_language_reference.md b/docs/specs/livecode_builder_language_reference.md
@@ -30,7 +30,7 @@ Strings use backslash ('\') as an escape - the following are understood:
  - **\r**: CR (ASCII 13)
  - **\t**: TAB (ASCII 9)
  - **\q**: quote '"'
- - **\u{X…X}: character with unicode codepoint hex value 0xX...X - any number of nibbles may be specified, but the value will be clamped to 0x10FFFF.
+ - **\u{X...X}: character with unicode codepoint U+X...X - any number of nibbles may be specified, but any values greater than 0x10FFFF will be replaced by U+FFFD.
  - **\\**: backslash '\'
 
 > **Note:** The presence of '.' in identifiers are used as a namespace scope delimiter.
diff --git a/toolchain/lc-compile/src/literal.c b/toolchain/lc-compile/src/literal.c
@@ -208,7 +208,7 @@ int UnescapeStringLiteral(long p_position, const char *p_string, long *r_unescap
                         if (t_overflow)
                         {
                             Warning_UnicodeEscapeTooBig(p_position + (t_escape - p_string));
-                            t_char = 0x10FFFF;
+                            t_char = 0xFFFD;
                         }
                         
                         append_utf8_char(t_value, &t_length, t_char);
diff --git a/toolchain/lc-compile/src/report.c b/toolchain/lc-compile/src/report.c
@@ -186,7 +186,7 @@ DEFINE_ERROR(NonHandlerTypeVariablesCannotBeCalled, "Variables must have handler
 
 DEFINE_WARNING(MetadataClausesShouldComeAfterUseClauses, "Metadata clauses should come after use clauses")
 DEFINE_WARNING(EmptyUnicodeEscape, "Unicode escape sequence specified with no nibbles")
-DEFINE_WARNING(UnicodeEscapeTooBig, "Unicode escape sequence too big, character clamped to \\u{10FFFF}");
+DEFINE_WARNING(UnicodeEscapeTooBig, "Unicode escape sequence too big, replaced with U+FFFD");
 
 ////////////////////////////////////////////////////////////////////////////////
 

Original file line number	Diff line number	Diff line change
`@@ -208,7 +208,7 @@ int UnescapeStringLiteral(long p_position, const char p_string, long r_unescap`
`208`	`208`	`if (t_overflow)`
`209`	`209`	`{`
`210`	`210`	`Warning_UnicodeEscapeTooBig(p_position + (t_escape - p_string));`
`211`		`- t_char = 0x10FFFF;`
	`211`	`+ t_char = 0xFFFD;`
`212`	`212`	`}`
`213`	`213`
`214`	`214`	`append_utf8_char(t_value, &t_length, t_char);`