Add Kotlin support

#19

Author: krlvi

README.md

@@ -188,7 +188,7 @@ You can experiment with your own sentence transformer models with the `--model`
 ## Bugs and limitations
 
 - Currently, the `.embeddings` index is not updated when repository files change. As a temporary workaround, `sem embed` can be re-ran occasionally.
-- Supported languages: `{ 'python', 'javascript', 'typescript', 'ruby', 'go', 'rust', 'java', 'c', 'c++' }`
+- Supported languages: `{ 'python', 'javascript', 'typescript', 'ruby', 'go', 'rust', 'java', 'c', 'c++', 'kotlin' }`
 - Supported text editors for opening results in: `{ 'vscode', 'vim' }`
 
 ## License

setup.py

@@ -5,7 +5,7 @@
 
 setuptools.setup(
     name='semantic-code-search',
-    version='0.3.0',
+    version='0.4.0',
     author='Kiril Videlov',
     author_email='kiril@codeball.ai',
     description='Search your codebase with natural language.',

src/semantic_code_search/embed.py

@@ -23,6 +23,9 @@ def _supported_file_extensions():
         '.h': 'c',
         '.cpp': 'cpp',
         '.hpp': 'cpp',
+        '.kt': 'kotlin',
+        '.kts': 'kotlin',
+        '.ktm': 'kotlin',
     }
 
 

src/semantic_code_search/prompt.py

@@ -46,7 +46,7 @@ def _syntax_highlighting(text, file):
         lexer = TypeScriptLexer
     elif file.endswith('java'):
         lexer = JavaLexer
-    elif file.endswith('kt'):
+    elif file.endswith('kt') or file.endswith('kts') or file.endswith('ktm'):
         lexer = KotlinLexer
     elif file.endswith('rb'):
         lexer = RubyLexer