fix(c): parse .c files with the C grammar

`.c` files were parsed with tree-sitter-cpp, so valid C that uses C++
keywords as identifiers (`int delete = 0; int new = 1;`, a parameter
named `class`) produced grammar-error diagnostics and lost symbols.

`.c` files now parse with tree-sitter-c (pinned =0.24.2, backend
`c:0.24.2`) while staying on the shared C/C++ extraction path, so C
sources and the headers they include still share one include/declaration
index. Headers (`.h`) keep the C++ grammar, which parses the C subset.

Test: cpp_xtu::c_sources_parse_with_the_c_grammar fails before this
change (grammar errors in util.c).

Cargo.lock

@@ -84,6 +84,7 @@ dependencies = [
  "serde_json",
  "tempfile",
  "tree-sitter",
+ "tree-sitter-c",
  "tree-sitter-cpp",
  "tree-sitter-dart",
  "tree-sitter-javascript",
@@ -423,6 +424,16 @@ dependencies = [
  "tree-sitter-language",
 ]
 
+[[package]]
+name = "tree-sitter-c"
+version = "0.24.2"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "a9b2eb57a55fed6b00812912e730b7a275cf4fe98bfd6a5d76263d4438371728"
+dependencies = [
+ "cc",
+ "tree-sitter-language",
+]
+
 [[package]]
 name = "tree-sitter-cpp"
 version = "0.23.4"

Cargo.toml

@@ -16,6 +16,7 @@ regex = "1.12"
 serde = { version = "1.0", features = ["derive"] }
 serde_json = "1.0"
 tree-sitter = "=0.26.13"
+tree-sitter-c = "=0.24.2"
 tree-sitter-cpp = "=0.23.4"
 tree-sitter-javascript = "=0.25.0"
 tree-sitter-typescript = "=0.23.2"

src/source.rs

@@ -184,6 +184,9 @@ fn preprocessor_alternative_lines(source: &str) -> Vec<bool> {
 
 pub(crate) fn extract(language: &str, path: &str, source: &str) -> Result<Document> {
     let (grammar, version) = match language {
+        // `.c` shares the C/C++ extraction path (and header index) but must parse
+        // as C: identifiers such as `new`, `delete` or `class` are valid C.
+        "cpp" if path.ends_with(".c") => (tree_sitter_c::LANGUAGE, "c:0.24.2"),
         "cpp" => (tree_sitter_cpp::LANGUAGE, "cpp:0.23.4"),
         "rust" => (tree_sitter_rust::LANGUAGE, "rust:0.24.2"),
         "javascript" => (tree_sitter_javascript::LANGUAGE, "javascript:0.25.0"),

tests/cpp_xtu.rs

@@ -406,3 +406,30 @@ fn preprocessor_alternative_branches_are_not_call_targets() {
         Some("alternative")
     );
 }
+
+#[test]
+fn c_sources_parse_with_the_c_grammar() {
+    // `.c` files went through the C++ grammar, so valid C using C++ keywords as
+    // identifiers produced grammar-error diagnostics and damaged extraction.
+    let model = scan_files(&[
+        ("src/util.h", "int twice(int new);\n"),
+        (
+            "src/util.c",
+            "#include \"util.h\"\nint twice(int new) { int delete = new; return delete * 2; }\n",
+        ),
+        (
+            "src/main.c",
+            "#include \"util.h\"\nint main(void) { int class = 1; return twice(class); }\n",
+        ),
+    ]);
+    let grammar_errors: Vec<_> = model
+        .diagnostics
+        .iter()
+        .filter(|d| d.path.as_deref().is_some_and(|p| p.ends_with(".c")))
+        .map(|d| d.message.clone())
+        .collect();
+    assert!(grammar_errors.is_empty(), "{grammar_errors:?}");
+    let (target, reason) = single_call(&model, function(&model, "src/main.c", "main"));
+    assert_eq!(target.path.as_deref(), Some("src/util.c"));
+    assert_eq!(reason, None);
+}