Fix combinatorial explosion on backtracking broken if chains

Signed-off-by: Marcel Müller <neikos@neikos.email>

flake.nix

@@ -95,6 +95,10 @@
             pkgs.cargo-flamegraph
           ];
         };
+
+        devShells.fuzz = devShells.crate.overrideAttrs (prev: {
+          nativeBuildInputs = [ unstableRustTarget pkgs.cargo-fuzz ];
+        });
       }
     );
 }

fuzz/.envrc

@@ -0,0 +1 @@
+use flake .#fuzz

fuzz/.gitignore

@@ -0,0 +1,6 @@
+.direnv/
+
+target
+corpus
+artifacts
+coverage

fuzz/Cargo.lock

@@ -0,0 +1,277 @@
+# This file is automatically @generated by Cargo.
+# It is not intended for manual editing.
+version = 4
+
+[[package]]
+name = "annotate-snippets"
+version = "0.12.13"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "74fc7650eedcb2fee505aad48491529e408f0e854c2d9f63eb86c1361b9b3f93"
+dependencies = [
+ "anstyle",
+ "memchr",
+ "unicode-width",
+]
+
+[[package]]
+name = "anstyle"
+version = "1.0.13"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "5192cca8006f1fd4f7237516f40fa183bb07f8fbdfedaa0036de5ea9b0b45e78"
+
+[[package]]
+name = "arbitrary"
+version = "1.4.2"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "c3d036a3c4ab069c7b410a2ce876bd74808d2d0888a82667669f8e783a898bf1"
+
+[[package]]
+name = "cc"
+version = "1.2.56"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "aebf35691d1bfb0ac386a69bac2fde4dd276fb618cf8bf4f5318fe285e821bb2"
+dependencies = [
+ "find-msvc-tools",
+ "jobserver",
+ "libc",
+ "shlex",
+]
+
+[[package]]
+name = "cfg-if"
+version = "1.0.4"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "9330f8b2ff13f34540b44e946ef35111825727b38d33286ef986142615121801"
+
+[[package]]
+name = "displaydoc"
+version = "0.2.5"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "97369cbbc041bc366949bc74d34658d6cda5621039731c6310521892a3a20ae0"
+dependencies = [
+ "proc-macro2",
+ "quote",
+ "syn",
+]
+
+[[package]]
+name = "find-msvc-tools"
+version = "0.1.9"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "5baebc0774151f905a1a2cc41989300b1e6fbb29aff0ceffa1064fdd3088d582"
+
+[[package]]
+name = "getrandom"
+version = "0.3.4"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "899def5c37c4fd7b2664648c28120ecec138e4d395b459e5ca34f9cce2dd77fd"
+dependencies = [
+ "cfg-if",
+ "libc",
+ "r-efi",
+ "wasip2",
+]
+
+[[package]]
+name = "itoa"
+version = "1.0.17"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "92ecc6618181def0457392ccd0ee51198e065e016d1d527a7ac1b6dc7c1f09d2"
+
+[[package]]
+name = "jobserver"
+version = "0.1.34"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "9afb3de4395d6b3e67a780b6de64b51c978ecf11cb9a462c66be7d4ca9039d33"
+dependencies = [
+ "getrandom",
+ "libc",
+]
+
+[[package]]
+name = "libc"
+version = "0.2.183"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "b5b646652bf6661599e1da8901b3b9522896f01e736bad5f723fe7a3a27f899d"
+
+[[package]]
+name = "libfuzzer-sys"
+version = "0.4.12"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "f12a681b7dd8ce12bff52488013ba614b869148d54dd79836ab85aafdd53f08d"
+dependencies = [
+ "arbitrary",
+ "cc",
+]
+
+[[package]]
+name = "memchr"
+version = "2.8.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "f8ca58f447f06ed17d5fc4043ce1b10dd205e060fb3ce5b979b8ed8e59ff3f79"
+
+[[package]]
+name = "nomo"
+version = "0.1.0"
+dependencies = [
+ "annotate-snippets",
+ "displaydoc",
+ "serde",
+ "serde_json",
+ "thiserror",
+ "winnow",
+]
+
+[[package]]
+name = "nomo-fuzz"
+version = "0.0.0"
+dependencies = [
+ "libfuzzer-sys",
+ "nomo",
+]
+
+[[package]]
+name = "proc-macro2"
+version = "1.0.106"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "8fd00f0bb2e90d81d1044c2b32617f68fcb9fa3bb7640c23e9c748e53fb30934"
+dependencies = [
+ "unicode-ident",
+]
+
+[[package]]
+name = "quote"
+version = "1.0.45"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "41f2619966050689382d2b44f664f4bc593e129785a36d6ee376ddf37259b924"
+dependencies = [
+ "proc-macro2",
+]
+
+[[package]]
+name = "r-efi"
+version = "5.3.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "69cdb34c158ceb288df11e18b4bd39de994f6657d83847bdffdbd7f346754b0f"
+
+[[package]]
+name = "serde"
+version = "1.0.228"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "9a8e94ea7f378bd32cbbd37198a4a91436180c5bb472411e48b5ec2e2124ae9e"
+dependencies = [
+ "serde_core",
+ "serde_derive",
+]
+
+[[package]]
+name = "serde_core"
+version = "1.0.228"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "41d385c7d4ca58e59fc732af25c3983b67ac852c1a25000afe1175de458b67ad"
+dependencies = [
+ "serde_derive",
+]
+
+[[package]]
+name = "serde_derive"
+version = "1.0.228"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "d540f220d3187173da220f885ab66608367b6574e925011a9353e4badda91d79"
+dependencies = [
+ "proc-macro2",
+ "quote",
+ "syn",
+]
+
+[[package]]
+name = "serde_json"
+version = "1.0.149"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "83fc039473c5595ace860d8c4fafa220ff474b3fc6bfdb4293327f1a37e94d86"
+dependencies = [
+ "itoa",
+ "memchr",
+ "serde",
+ "serde_core",
+ "zmij",
+]
+
+[[package]]
+name = "shlex"
+version = "1.3.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "0fda2ff0d084019ba4d7c6f371c95d8fd75ce3524c3cb8fb653a3023f6323e64"
+
+[[package]]
+name = "syn"
+version = "2.0.117"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "e665b8803e7b1d2a727f4023456bbbbe74da67099c585258af0ad9c5013b9b99"
+dependencies = [
+ "proc-macro2",
+ "quote",
+ "unicode-ident",
+]
+
+[[package]]
+name = "thiserror"
+version = "2.0.18"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "4288b5bcbc7920c07a1149a35cf9590a2aa808e0bc1eafaade0b80947865fbc4"
+dependencies = [
+ "thiserror-impl",
+]
+
+[[package]]
+name = "thiserror-impl"
+version = "2.0.18"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "ebc4ee7f67670e9b64d05fa4253e753e016c6c95ff35b89b7941d6b856dec1d5"
+dependencies = [
+ "proc-macro2",
+ "quote",
+ "syn",
+]
+
+[[package]]
+name = "unicode-ident"
+version = "1.0.24"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "e6e4313cd5fcd3dad5cafa179702e2b244f760991f45397d14d4ebf38247da75"
+
+[[package]]
+name = "unicode-width"
+version = "0.2.2"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "b4ac048d71ede7ee76d585517add45da530660ef4390e49b098733c6e897f254"
+
+[[package]]
+name = "wasip2"
+version = "1.0.2+wasi-0.2.9"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "9517f9239f02c069db75e65f174b3da828fe5f5b945c4dd26bd25d89c03ebcf5"
+dependencies = [
+ "wit-bindgen",
+]
+
+[[package]]
+name = "winnow"
+version = "0.7.15"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "df79d97927682d2fd8adb29682d1140b343be4ac0f08fd68b7765d9c059d3945"
+dependencies = [
+ "memchr",
+]
+
+[[package]]
+name = "wit-bindgen"
+version = "0.51.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "d7249219f66ced02969388cf2bb044a09756a083d0fab1e566056b04d9fbcaa5"
+
+[[package]]
+name = "zmij"
+version = "1.0.21"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "b8848ee67ecc8aedbaf3e4122217aff892639231befc6a1b58d29fff4c2cabaa"

fuzz/Cargo.toml

@@ -0,0 +1,21 @@
+[package]
+name = "nomo-fuzz"
+version = "0.0.0"
+publish = false
+edition = "2024"
+
+[package.metadata]
+cargo-fuzz = true
+
+[dependencies]
+libfuzzer-sys = "0.4"
+
+[dependencies.nomo]
+path = ".."
+
+[[bin]]
+name = "fuzz_target_1"
+path = "fuzz_targets/fuzz_target_1.rs"
+test = false
+doc = false
+bench = false

fuzz/fuzz_targets/fuzz_target_1.rs

@@ -0,0 +1,18 @@
+#![no_main]
+
+use libfuzzer_sys::Corpus;
+use libfuzzer_sys::fuzz_target;
+
+fuzz_target!(|data: String| -> Corpus {
+    let Ok(parsed) = nomo::parser::parse(data.into()) else {
+        return Corpus::Reject;
+    };
+
+    let Ok(ast) = nomo::ast::parse(parsed.tokens()) else {
+        return Corpus::Keep;
+    };
+
+    let _instructions = nomo::emit::emit_machine(ast);
+
+    Corpus::Keep
+});

src/ast/mod.rs

@@ -345,39 +345,67 @@ fn parse_conditional_chain<'input>(
 
         chain.push(if_block);
 
-        loop {
+        let content = resume_after_cut(
-            let (content, end_block): (Vec<_>, _) = repeat_till(
+            cut_err(inner_conditional_chain),
-                0..,
+            repeat_till(0.., any, parse_end).map(|((), _)| ()),
-                parse_ast,
+        )
-                trace(
+        .parse_next(input)?;
-                    "conditional_chain_else/end",
-                    alt((parse_end, parse_conditional_else)),
-                ),
-            )
-            .parse_next(input)?;
 
-            chain.push(TemplateAstExpr::ConditionalContent { content });
+        chain.extend(content.into_iter().flatten());
-
-            let is_end = if let TemplateAstExpr::Block { ref expression, .. } = end_block
-                && let TemplateAstExpr::EndBlock = &**expression
-            {
-                true
-            } else {
-                false
-            };
-
-            chain.push(end_block);
-
-            if is_end {
-                break;
-            }
-        }
 
         Ok(TemplateAstExpr::ConditionalChain { chain })
     })
     .parse_next(input)
 }
 
+fn inner_conditional_chain<'input>(
+    input: &mut Input<'input>,
+) -> Result<Vec<TemplateAstExpr<'input>>, AstError> {
+    let mut needs_end = false;
+
+    let mut chain = vec![];
+
+    loop {
+        let (content, end_block): (Vec<_>, _) = repeat_till(
+            0..,
+            parse_ast,
+            trace(
+                "conditional_chain_else/end",
+                alt((parse_end, parse_conditional_else)),
+            ),
+        )
+        .parse_next(input)?;
+
+        chain.push(TemplateAstExpr::ConditionalContent { content });
+
+        let is_end = if let TemplateAstExpr::Block { ref expression, .. } = end_block
+            && let TemplateAstExpr::EndBlock = &**expression
+        {
+            true
+        } else {
+            false
+        };
+
+        if !is_end && needs_end {
+            return Err(AstError::from_input(input));
+        }
+
+        if let TemplateAstExpr::Block { expression, .. } = &end_block
+            && let TemplateAstExpr::ElseConditional { expression: None } = &**expression
+        {
+            needs_end = true;
+        }
+
+        chain.push(end_block);
+
+        if is_end {
+            break;
+        }
+    }
+
+    Ok(chain)
+}
+
 fn parse_conditional_if<'input>(
     input: &mut Input<'input>,
 ) -> Result<TemplateAstExpr<'input>, AstError> {

src/emit/mod.rs

@@ -123,14 +123,16 @@ fn emit_ast_expr(
                 {
                     previous_post_whitespace_content = post_whitespace_content;
                     if let Some(ws) = prev_whitespace_content {
+                        let idx = end_indices.last().copied();
                         eval.insert(
-                            eval.len() - 2,
+                            idx.unwrap_or(eval.len()),
                             Instruction::AppendContent {
                                 content: ws.source().clone(),
                             },
                         );
-                        let index_index = end_indices.len() - 1;
+                        if let Some(idx) = end_indices.last_mut() {
-                        end_indices[index_index] += 1;
+                            *idx += 1;
+                        }
                     }
 
                     if let TemplateAstExpr::IfConditional { expression } = &**expression {

src/parser/mod.rs

@@ -383,10 +383,10 @@ fn parse_block_token<'input>(input: &mut Input<'input>) -> PResult<'input, Templ
         "parse_block_token",
         alt((
             parse_ident,
-            parse_literal,
+            terminated(parse_literal, ident_terminator_check),
-            parse_condition_if,
+            terminated(parse_condition_if, ident_terminator_check),
-            parse_condition_else,
+            terminated(parse_condition_else, ident_terminator_check),
-            parse_end,
+            terminated(parse_end, ident_terminator_check),
             parse_whitespace,
         )),
     )

tests/checks.rs

@@ -0,0 +1,18 @@
+#[test]
+fn check_files() {
+    let files = std::fs::read_dir("tests/checks/").unwrap();
+
+    for file in files {
+        let input = std::fs::read_to_string(file.unwrap().path()).unwrap();
+
+        let Ok(parsed) = nomo::parser::parse(input.into()) else {
+            continue;
+        };
+
+        let Ok(ast) = nomo::ast::parse(parsed.tokens()) else {
+            continue;
+        };
+
+        let _emit = nomo::emit::emit_machine(ast);
+    }
+}

tests/checks/minimized-from-20a1f84df1a8d2c7ef7e9d538d6270e0379ab83e

@@ -0,0 +1,2 @@
+
+{{if en}}{{ end}}

tests/checks/minimized-from-288cd3d11ffabe7f439c235924d88509deb93bc4

@@ -0,0 +1,3 @@
+{{ if t }}
+{{else}}{{ else }}
+{{end }}

tests/file_tests.rs

@@ -31,7 +31,13 @@ fn check_cases() {
 
         insta::assert_debug_snapshot!("1-parsed", parsed);
 
-        let ast = nomo::ast::parse(parsed.tokens()).unwrap();
+        let ast = match nomo::ast::parse(parsed.tokens()) {
+            Ok(ast) => ast,
+            Err(err) => {
+                eprintln!("{}", err.to_report(input));
+                panic!("Could not evaluate ast");
+            }
+        };
 
         insta::assert_debug_snapshot!("2-ast", ast);