Recognize .htm files as HTML

crates/languages/src/lib.rs

@@ -155,7 +155,7 @@ pub fn language_by_filename(path: &Path) -> Option<Arc<Language>> {
         "cpp" | "cxx" | "cc" | "h" | "hh" => language_by_name("cpp"),
         "sh" | "zsh" | "bash" => language_by_name("shell"),
         "cs" => language_by_name("csharp"),
-        "html" => language_by_name("html"),
+        "html" | "htm" => language_by_name("html"),
         "css" => language_by_name("css"),
         "c" => language_by_name("c"),
         "json" => language_by_name("json"),

crates/languages/src/lib_tests.rs

@@ -1,4 +1,6 @@
-use crate::{load_language, SUPPORTED_LANGUAGES};
+use std::path::Path;
+
+use crate::{language_by_filename, load_language, SUPPORTED_LANGUAGES};
 
 /// Validate that every supported language can be loaded successfully.
 /// This catches invalid node types, syntax errors, and other issues in .scm query files
@@ -20,3 +22,21 @@ fn all_supported_languages_load_successfully() {
             .join("\n")
     );
 }
+
+/// Both `.html` and the legacy three-character `.htm` extension should resolve to
+/// the same HTML language entry. `.htm` is widely produced by static-site generators
+/// and historical web tooling (DOS 8.3 filename limits) and is already treated as
+/// an HTML/text file elsewhere in the codebase
+/// (see `is_development_text_extension` in `crates/warp_util/src/file_type.rs`).
+#[test]
+fn html_extensions_resolve_to_html() {
+    for filename in ["index.html", "index.htm"] {
+        let language = language_by_filename(Path::new(filename))
+            .unwrap_or_else(|| panic!("expected {filename} to resolve to a language"));
+        assert_eq!(
+            language.display_name(),
+            "HTML",
+            "{filename} should resolve to HTML",
+        );
+    }
+}