Support extra extensions with optional language mapping (#32)

* feat: allow adding file extensions via COCOINDEX_CODE_EXTRA_EXTENSIONS env var

Users can now specify additional file extensions to index without editing
source code, e.g. COCOINDEX_CODE_EXTRA_EXTENSIONS="inc,tpl"

* feat: support language mapping in COCOINDEX_CODE_EXTRA_EXTENSIONS

Allow `ext:lang` format (e.g. "inc:php,yaml,tpl:html") to override
language detection for extra extensions, enabling proper AST-based
chunking for unrecognized extensions.

Author: ikeisuke

README.md

@@ -114,6 +114,7 @@ Use the cocoindex-code MCP server for semantic code search when:
 | `COCOINDEX_CODE_ROOT_PATH` | Root path of the codebase | Auto-discovered (see below) |
 | `COCOINDEX_CODE_EMBEDDING_MODEL` | Embedding model (see below) | `sbert/sentence-transformers/all-MiniLM-L6-v2` |
 | `COCOINDEX_CODE_BATCH_SIZE` | Max batch size for local embedding model | `16` |
+| `COCOINDEX_CODE_EXTRA_EXTENSIONS` | Additional file extensions to index (comma-separated, e.g. `"inc:php,yaml,toml"` — use `ext:lang` to override language detection) | _(none)_ |
 
 
 ### Root Path Discovery

src/cocoindex_code/config.py

@@ -66,6 +66,7 @@ class Config:
     device: str
     trust_remote_code: bool
     batch_size: int
+    extra_extensions: dict[str, str | None]
 
     @classmethod
     def from_env(cls) -> Config:
@@ -113,13 +114,27 @@ def from_env(cls) -> Config:
                 f"COCOINDEX_CODE_BATCH_SIZE must be a positive integer, got: {batch_size}"
             )
 
+        # Extra file extensions (format: "inc:php,yaml,toml" — optional lang after colon)
+        raw_extra = os.environ.get("COCOINDEX_CODE_EXTRA_EXTENSIONS", "")
+        extra_extensions: dict[str, str | None] = {}
+        for token in raw_extra.split(","):
+            token = token.strip()
+            if not token:
+                continue
+            if ":" in token:
+                ext, lang = token.split(":", 1)
+                extra_extensions[f".{ext.strip()}"] = lang.strip() or None
+            else:
+                extra_extensions[f".{token}"] = None
+
         return cls(
             codebase_root_path=root,
             embedding_model=embedding_model,
             index_dir=index_dir,
             device=device,
             trust_remote_code=trust_remote_code,
             batch_size=batch_size,
+            extra_extensions=extra_extensions,
         )
 
     @property

src/cocoindex_code/indexer.py

@@ -8,10 +8,11 @@
 from cocoindex.resources.file import PatternFilePathMatcher
 from cocoindex.resources.id import IdGenerator
 
+from .config import config
 from .shared import CODEBASE_DIR, SQLITE_DB, CodeChunk, embedder
 
 # File patterns for supported languages
-INCLUDED_PATTERNS = [
+DEFAULT_INCLUDED_PATTERNS = [
     "**/*.py",  # Python
     "**/*.pyi",  # Python stubs
     "**/*.js",  # JavaScript
@@ -43,6 +44,13 @@
     "**/*.php",  # PHP
 ]
 
+INCLUDED_PATTERNS = DEFAULT_INCLUDED_PATTERNS + [f"**/*{ext}" for ext in config.extra_extensions]
+
+# Language overrides from extra_extensions (e.g. ".inc" -> "php")
+LANGUAGE_OVERRIDES: dict[str, str] = {
+    ext: lang for ext, lang in config.extra_extensions.items() if lang is not None
+}
+
 EXCLUDED_PATTERNS = [
     "**/.*",  # Hidden directories
     "**/__pycache__",  # Python cache
@@ -81,7 +89,12 @@ async def process_file(
         return
 
     # Get relative path and detect language
-    language = detect_code_language(filename=file.file_path.path.name) or "text"
+    suffix = file.file_path.path.suffix
+    language = (
+        LANGUAGE_OVERRIDES.get(suffix)
+        or detect_code_language(filename=file.file_path.path.name)
+        or "text"
+    )
 
     # Split into chunks
     chunks = splitter.split(

tests/test_config.py

@@ -138,3 +138,82 @@ def test_batch_size_raises_on_negative(self, tmp_path: Path) -> None:
         ):
             with pytest.raises(ValueError, match="COCOINDEX_CODE_BATCH_SIZE"):
                 Config.from_env()
+
+
+class TestExtraExtensions:
+    """Tests for COCOINDEX_CODE_EXTRA_EXTENSIONS env var."""
+
+    def test_empty_by_default(self, tmp_path: Path) -> None:
+        with patch.dict(
+            os.environ,
+            {"COCOINDEX_CODE_ROOT_PATH": str(tmp_path)},
+        ):
+            os.environ.pop("COCOINDEX_CODE_EXTRA_EXTENSIONS", None)
+            config = Config.from_env()
+            assert config.extra_extensions == {}
+
+    def test_parses_comma_separated(self, tmp_path: Path) -> None:
+        with patch.dict(
+            os.environ,
+            {
+                "COCOINDEX_CODE_ROOT_PATH": str(tmp_path),
+                "COCOINDEX_CODE_EXTRA_EXTENSIONS": "rb,yaml,toml",
+            },
+        ):
+            config = Config.from_env()
+            assert config.extra_extensions == {".rb": None, ".yaml": None, ".toml": None}
+
+    def test_trims_whitespace(self, tmp_path: Path) -> None:
+        with patch.dict(
+            os.environ,
+            {
+                "COCOINDEX_CODE_ROOT_PATH": str(tmp_path),
+                "COCOINDEX_CODE_EXTRA_EXTENSIONS": " rb , yaml , ",
+            },
+        ):
+            config = Config.from_env()
+            assert config.extra_extensions == {".rb": None, ".yaml": None}
+
+    def test_empty_string_gives_empty_dict(self, tmp_path: Path) -> None:
+        with patch.dict(
+            os.environ,
+            {
+                "COCOINDEX_CODE_ROOT_PATH": str(tmp_path),
+                "COCOINDEX_CODE_EXTRA_EXTENSIONS": "",
+            },
+        ):
+            config = Config.from_env()
+            assert config.extra_extensions == {}
+
+    def test_dot_prefix_passed_through(self, tmp_path: Path) -> None:
+        with patch.dict(
+            os.environ,
+            {
+                "COCOINDEX_CODE_ROOT_PATH": str(tmp_path),
+                "COCOINDEX_CODE_EXTRA_EXTENSIONS": ".rb,yaml",
+            },
+        ):
+            config = Config.from_env()
+            assert config.extra_extensions == {"..rb": None, ".yaml": None}
+
+    def test_parses_lang_mapping(self, tmp_path: Path) -> None:
+        with patch.dict(
+            os.environ,
+            {
+                "COCOINDEX_CODE_ROOT_PATH": str(tmp_path),
+                "COCOINDEX_CODE_EXTRA_EXTENSIONS": "inc:php",
+            },
+        ):
+            config = Config.from_env()
+            assert config.extra_extensions == {".inc": "php"}
+
+    def test_mixed_with_and_without_lang(self, tmp_path: Path) -> None:
+        with patch.dict(
+            os.environ,
+            {
+                "COCOINDEX_CODE_ROOT_PATH": str(tmp_path),
+                "COCOINDEX_CODE_EXTRA_EXTENSIONS": "inc:php,yaml,tpl:html",
+            },
+        ):
+            config = Config.from_env()
+            assert config.extra_extensions == {".inc": "php", ".yaml": None, ".tpl": "html"}