add diff_nfas, function out do_fuzz so clippy can do its thing

Author: addisoncrump

fuzz/Cargo.toml

@@ -71,6 +71,10 @@ path = "fuzz_targets/ast_fuzz_match_bytes.rs"
 name = "ast_diff_default"
 path = "fuzz_targets/ast_diff_default.rs"
 
+[[bin]]
+name = "ast_diff_nfas"
+path = "fuzz_targets/ast_diff_nfas.rs"
+
 [profile.release]
 opt-level = 3
 debug = true

fuzz/fuzz_targets/ast_diff_default.rs

@@ -22,7 +22,7 @@ impl std::fmt::Debug for FuzzData {
     }
 }
 
-fuzz_target!(|data: FuzzData| -> Corpus {
+fn do_fuzz(data: FuzzData) -> Corpus {
     let _ = env_logger::try_init();
 
     let pattern = format!("{}", data.ast);
@@ -61,9 +61,11 @@ fuzz_target!(|data: FuzzData| -> Corpus {
                 assert_eq!(c1.start(), c2.start);
                 assert_eq!(c1.end(), c2.end);
             } else {
-                assert!(!c2.is_some(), "Matched in baseline, but not target!");
+                assert!(c2.is_none(), "Matched in baseline, but not target!");
             }
         }
     }
     Corpus::Keep
-});
+}
+
+fuzz_target!(|data: FuzzData| -> Corpus { do_fuzz(data) });

fuzz/fuzz_targets/ast_diff_nfas.rs

@@ -0,0 +1,94 @@
+#![no_main]
+
+use {
+    libfuzzer_sys::{fuzz_target, Corpus},
+    regex_automata::nfa::thompson::{
+        backtrack::BoundedBacktracker, pikevm::PikeVM, NFA,
+    },
+    regex_syntax::ast::Ast,
+};
+
+#[derive(Eq, PartialEq, arbitrary::Arbitrary)]
+struct FuzzData {
+    ast: Ast,
+    haystack: String,
+}
+
+impl std::fmt::Debug for FuzzData {
+    fn fmt(&self, f: &mut std::fmt::Formatter<'_>) -> std::fmt::Result {
+        let mut builder = f.debug_struct("FuzzData");
+        builder.field("ast", &format!("{}", self.ast));
+        builder.field("haystack", &self.haystack);
+        builder.finish()
+    }
+}
+
+fn do_fuzz(data: FuzzData) -> Corpus {
+    let _ = env_logger::try_init();
+
+    let pattern = format!("{}", data.ast);
+    let config = NFA::config().nfa_size_limit(Some(1 << 20));
+    let Ok(nfa) = NFA::compiler().configure(config).build(&pattern) else {
+        return Corpus::Reject;
+    };
+    let Ok(backtracker) = BoundedBacktracker::new_from_nfa(nfa.clone()) else {
+        return Corpus::Reject; };
+    let mut backtracker_cache = backtracker.create_cache();
+    let Ok(baseline) = PikeVM::new_from_nfa(nfa) else {
+        return Corpus::Reject;
+    };
+    let mut baseline_cache = baseline.create_cache();
+
+    if let Ok(backtracked) =
+        backtracker.try_is_match(&mut backtracker_cache, &data.haystack)
+    {
+        assert_eq!(
+            backtracked,
+            baseline.is_match(&mut baseline_cache, &data.haystack)
+        );
+    }
+    if let Ok(found1) =
+        backtracker.try_find(&mut backtracker_cache, &data.haystack)
+    {
+        let found2 = baseline.find(&mut baseline_cache, &data.haystack);
+        if let Some(found1) = found1 {
+            let found2 =
+                found2.expect("Found in target, but not in baseline!");
+            assert_eq!(found1.start(), found2.start());
+            assert_eq!(found1.end(), found2.end());
+        }
+    }
+    let mut backtracker_captures = backtracker.create_captures();
+    if let Ok(()) = backtracker.try_captures(
+        &mut backtracker_cache,
+        &data.haystack,
+        &mut backtracker_captures,
+    ) {
+        let mut baseline_captures = baseline.create_captures();
+
+        baseline.captures(
+            &mut baseline_cache,
+            &data.haystack,
+            &mut baseline_captures,
+        );
+        drop(baseline_cache);
+        assert_eq!(
+            backtracker_captures.group_len(),
+            baseline_captures.group_len()
+        );
+        for (c1, c2) in
+            backtracker_captures.iter().zip(baseline_captures.iter())
+        {
+            if let Some(c1) = c1 {
+                let c2 = c2.expect("Matched in target, but not baseline!");
+                assert_eq!(c1.start, c2.start);
+                assert_eq!(c1.end, c2.end);
+            } else {
+                assert!(c2.is_none(), "Matched in baseline, but not target!");
+            }
+        }
+    }
+    Corpus::Keep
+}
+
+fuzz_target!(|data: FuzzData| -> Corpus { do_fuzz(data) });

fuzz/oss-fuzz-build.sh

@@ -3,17 +3,7 @@
 cd $SRC/regex
 cargo fuzz build -O --debug-assertions
 
-targets=(
-  fuzz_regex_match
-  fuzz_regex_lite_match
-  fuzz_regex_automata_deserialize_dense_dfa
-  fuzz_regex_automata_deserialize_sparse_dfa
-  ast_roundtrip
-  ast_fuzz_match
-  ast_fuzz_regex
-  ast_fuzz_match_bytes
-  ast_diff_default
-)
+targets=$(cargo fuzz list)
 for target in "${targets[@]}"; do
   cp "fuzz/target/x86_64-unknown-linux-gnu/release/${target}" "${OUT}/"
   if [[ "$target" == ast_* ]]; then