lex: accept zero codepoints in strings

Zero characters (codepoints) are acceptable in strings. The current
Lexer::parse_string skipped such zero codepoints by accidents. The
zero codepoint was also used as error/skip indicator, but that is only
true if the third argument of utf8_escape_pair is true (yes, it is
called pair, but is a triple).

Add a testcase that checks the (sub)strings are separated by zero
chars. Since we cannot slice strings yet this uses extern "C"
functions, printf and memchr.

2 files changed, 28 insertions, 1 deletions

diff --git a/gcc/rust/lex/rust-lex.cc b/gcc/rust/lex/rust-lex.cc
index 0b8a8ea..49b6b6d 100644
--- a/gcc/rust/lex/rust-lex.cc
+++ b/gcc/rust/lex/rust-lex.cc
@@ -1827,7 +1827,8 @@ Lexer::parse_string (Location loc)
 	  else
 	    length += std::get<1> (utf8_escape_pair);
 
-	  if (current_char32 != Codepoint (0))
+	  if (current_char32 != Codepoint (0)
+	      || !std::get<2> (utf8_escape_pair))
 	    str += current_char32;
 
 	  // required as parsing utf8 escape only changes current_char
diff --git a/gcc/testsuite/rust/execute/torture/str-zero.rs b/gcc/testsuite/rust/execute/torture/str-zero.rs
new file mode 100644
index 0000000..e7fba0d
--- /dev/null
+++ b/gcc/testsuite/rust/execute/torture/str-zero.rs
@@ -0,0 +1,26 @@
+/* { dg-output "bar foo baz foobar\n" } */
+extern "C"
+{
+  fn printf(s: *const i8, ...);
+  fn memchr(s: *const i8, c: u8, n: usize) -> *const i8;
+}
+
+pub fn main () -> i32
+{
+  let f = "%s %s %s %s\n\0";
+  let s = "bar\0\
+           foo\
+           \x00\
+           baz\u{0000}\
+           foobar\0";
+  let cf = f as *const str as *const i8;
+  let cs = s as *const str as *const i8;
+  unsafe
+    {
+      let cs2 = memchr (cs, b'f', 5);
+      let cs3 = memchr (cs2, b'b', 5);
+      let cs4 = memchr (cs3, b'f', 5);
+      printf (cf, cs, cs2, cs3, cs4);
+    }
+  0
+}