altair823
5497c6e7b5
Dogfood (PR #142 1B + multi-root: kebab-docs + httpx + zod + lodash) showed 28 files skipped by extension that are routable to existing extractors: - .mts (ESM TypeScript) / .cts (CommonJS TypeScript) — same grammar as .ts in tree-sitter-typescript 0.23 (LANGUAGE_TYPESCRIPT covers JSX- agnostic variants; LANGUAGE_TSX stays for .tsx only) - .mdx (Markdown + JSX) — routed as MediaType::Markdown; the md parser folds JSX islands through as raw passthrough Changes: - crates/kebab-source-fs/src/media.rs: 'mts'|'cts' → Code(typescript), 'mdx' → Markdown. +2 unit tests. - crates/kebab-parse-code/src/lang.rs: code_lang_for_path matches mts/cts; module_path_for_tsjs strips .mts/.cts as well. Test cases extended. - crates/kebab-parse-code/src/typescript.rs: doc comment on select_grammar refreshed to mention .mts/.cts. - crates/kebab-parse-code/tests/lang.rs: 2 new assertions. verify: kebab-source-fs 44 / kebab-parse-code lib 20 + lang 4 all pass; clippy clean. Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
68 lines
2.2 KiB
Rust
68 lines
2.2 KiB
Rust
use kebab_parse_code::code_lang_for_path;
|
|
use std::path::Path;
|
|
|
|
#[test]
|
|
fn known_extensions_map_to_canonical_identifiers() {
|
|
let cases = [
|
|
("foo.rs", Some("rust")),
|
|
("foo.py", Some("python")),
|
|
("foo.pyi", Some("python")),
|
|
("foo.ts", Some("typescript")),
|
|
("foo.tsx", Some("typescript")),
|
|
("foo.mts", Some("typescript")), // ESM TS — same grammar
|
|
("foo.cts", Some("typescript")), // CommonJS TS — same grammar
|
|
("foo.js", Some("javascript")),
|
|
("foo.mjs", Some("javascript")),
|
|
("foo.cjs", Some("javascript")),
|
|
("foo.jsx", Some("javascript")),
|
|
("foo.go", Some("go")),
|
|
("foo.java", Some("java")),
|
|
("foo.kt", Some("kotlin")),
|
|
("foo.kts", Some("kotlin")),
|
|
("foo.c", Some("c")),
|
|
("foo.h", Some("c")),
|
|
("foo.cpp", Some("cpp")),
|
|
("foo.cc", Some("cpp")),
|
|
("foo.cxx", Some("cpp")),
|
|
("foo.hpp", Some("cpp")),
|
|
("foo.hh", Some("cpp")),
|
|
("foo.hxx", Some("cpp")),
|
|
("foo.yaml", Some("yaml")),
|
|
("foo.yml", Some("yaml")),
|
|
("foo.toml", Some("toml")),
|
|
("foo.json", Some("json")),
|
|
("foo.sh", Some("shell")),
|
|
("foo.bash", Some("shell")),
|
|
("foo.zsh", Some("shell")),
|
|
("foo.mk", Some("make")),
|
|
];
|
|
for (path, expected) in cases {
|
|
assert_eq!(
|
|
code_lang_for_path(Path::new(path)),
|
|
expected,
|
|
"path = {path}"
|
|
);
|
|
}
|
|
}
|
|
|
|
#[test]
|
|
fn special_filenames_map_to_identifiers() {
|
|
assert_eq!(code_lang_for_path(Path::new("Dockerfile")), Some("dockerfile"));
|
|
assert_eq!(code_lang_for_path(Path::new("foo.dockerfile")), Some("dockerfile"));
|
|
assert_eq!(code_lang_for_path(Path::new("Makefile")), Some("make"));
|
|
assert_eq!(code_lang_for_path(Path::new("GNUmakefile")), Some("make"));
|
|
}
|
|
|
|
#[test]
|
|
fn unknown_extension_returns_none() {
|
|
assert_eq!(code_lang_for_path(Path::new("foo.docx")), None);
|
|
assert_eq!(code_lang_for_path(Path::new("foo")), None);
|
|
assert_eq!(code_lang_for_path(Path::new("foo.unknown")), None);
|
|
}
|
|
|
|
#[test]
|
|
fn case_insensitive() {
|
|
assert_eq!(code_lang_for_path(Path::new("Foo.RS")), Some("rust"));
|
|
assert_eq!(code_lang_for_path(Path::new("FOO.YAML")), Some("yaml"));
|
|
}
|