input: fix infinite loop regression

This fixes a bug introduced by a bug fix for #557. In particular, the
termination condition wasn't exactly right, and this appears to have
slipped through the test suite. This probably reveals a hole in our test
suite, which is specifically the testing of Unicode regexes with
bytes::Regex on invalid UTF-8.

This bug was originally reported against ripgrep:
BurntSushi/ripgrep#1247

CHANGELOG.md

@@ -1,6 +1,14 @@
+1.1.6 (2019-04-16)
+==================
+This release fixes a regression introduced by a bug fix (for
+[BUG #557](https://github.com/rust-lang/regex/issues/557)) which could cause
+the regex engine to enter an infinite loop. This bug was originally
+[reported against ripgrep](https://github.com/BurntSushi/ripgrep/issues/1247).
+
+
 1.1.5 (2019-04-01)
 ==================
-This releases fixes a bug in regex's dependency specification where it requires
+This release fixes a bug in regex's dependency specification where it requires
 a newer version of regex-syntax, but this wasn't communicated correctly in the
 Cargo.toml. This would have been caught by a minimal version check, but this
 check was disabled because the `rand` crate itself advertises incorrect

src/backtrack.rs

@@ -98,7 +98,7 @@ impl<'a, 'm, 'r, 's, I: Input> Bounded<'a, 'm, 'r, 's, I> {
         slots: &'s mut [Slot],
         input: I,
         start: usize,
-        end: usize, 
+        end: usize,
     ) -> bool {
         let mut cache = cache.borrow_mut();
         let cache = &mut cache.backtrack;
@@ -171,7 +171,7 @@ impl<'a, 'm, 'r, 's, I: Input> Bounded<'a, 'm, 'r, 's, I> {
             if matched && self.prog.matches.len() == 1 {
                 return true;
             }
-            if at.pos() == end {
+            if at.pos() == end || at.is_end() {
                 break;
             }
             at = self.input.at(at.next_pos());

src/pikevm.rs

@@ -107,7 +107,7 @@ impl<'r, I: Input> Fsm<'r, I> {
         quit_after_match: bool,
         input: I,
         start: usize,
-        end: usize, 
+        end: usize,
     ) -> bool {
         let mut cache = cache.borrow_mut();
         let cache = &mut cache.pikevm;
@@ -125,7 +125,7 @@ impl<'r, I: Input> Fsm<'r, I> {
             slots,
             quit_after_match,
             at,
-            end, 
+            end,
         )
     }
 
@@ -137,7 +137,7 @@ impl<'r, I: Input> Fsm<'r, I> {
         slots: &mut [Slot],
         quit_after_match: bool,
         mut at: InputAt,
-        end: usize, 
+        end: usize,
     ) -> bool {
         let mut matched = false;
         let mut all_matched = false;
@@ -215,7 +215,7 @@ impl<'r, I: Input> Fsm<'r, I> {
                     }
                 }
             }
-            if at.pos() == end {
+            if at.pos() == end || at.is_end() {
                 break;
             }
             at = at_next;

tests/regression.rs

@@ -141,3 +141,10 @@ mat!(
     "samwise",
     Some((0, 7))
 );
+
+// See: https://github.com/BurntSushi/ripgrep/issues/1247
+#[test]
+fn regression_nfa_stops1() {
+    let re = ::regex::bytes::Regex::new(r"\bs(?:[ab])").unwrap();
+    assert_eq!(0, re.find_iter(b"s\xE4").count());
+}