feat: store relative path instead of absolute path (#28)

Author: georgeh0

src/cocoindex_code/indexer.py

@@ -7,8 +7,7 @@
 from cocoindex.resources.file import PatternFilePathMatcher
 from cocoindex.resources.id import IdGenerator
 
-from .config import config
-from .shared import SQLITE_DB, CodeChunk, embedder
+from .shared import CODEBASE_DIR, SQLITE_DB, CodeChunk, embedder
 
 # File patterns for supported languages
 INCLUDED_PATTERNS = [
@@ -128,7 +127,7 @@ async def app_main() -> None:
 
     # Walk source directory
     files = localfs.walk_dir(
-        config.codebase_root_path,
+        coco.use_context(CODEBASE_DIR),
         recursive=True,
         path_matcher=PatternFilePathMatcher(
             included_patterns=INCLUDED_PATTERNS,

src/cocoindex_code/shared.py

@@ -9,6 +9,7 @@
 
 import cocoindex as coco
 from cocoindex.connectors import sqlite
+from cocoindex.connectors.localfs import FilePath, register_base_dir
 from numpy.typing import NDArray
 
 if TYPE_CHECKING:
@@ -54,6 +55,8 @@
 
 # Context key for SQLite database (connection managed in lifespan)
 SQLITE_DB = coco.ContextKey[sqlite.SqliteDatabase]("sqlite_db")
+# Context key for codebase root directory (provided in lifespan)
+CODEBASE_DIR = coco.ContextKey[FilePath]("codebase_dir")
 
 
 @coco.lifespan
@@ -65,6 +68,9 @@ def coco_lifespan(builder: coco.EnvironmentBuilder) -> Iterator[None]:
     # Set CocoIndex state database path
     builder.settings.db_path = config.cocoindex_db_path
 
+    # Provide codebase root directory to environment
+    builder.provide(CODEBASE_DIR, register_base_dir("codebase", config.codebase_root_path))
+
     # Connect to SQLite with vector extension
     conn = sqlite.connect(str(config.target_sqlite_db_path), load_vec="auto")
     builder.provide(SQLITE_DB, sqlite.register_db("index_db", conn))

tests/test_e2e.py

@@ -365,9 +365,9 @@ async def test_filter_by_file_path_glob(
         setup_multi_lang_codebase(test_codebase_root)
         await app.update(report_to_stdout=False)
 
-        results = await query_codebase("function", limit=50, paths=["*/lib/*"])
+        results = await query_codebase("function", limit=50, paths=["lib/*"])
         assert len(results) > 0
-        assert all("/lib/" in r.file_path for r in results)
+        assert all(r.file_path.startswith("lib/") for r in results)
 
     @pytest.mark.asyncio(loop_scope="session")
     async def test_filter_by_file_path_wildcard_extension(
@@ -390,12 +390,10 @@ async def test_filter_by_both_language_and_file_path(
         await app.update(report_to_stdout=False)
 
         # Filter for Python files under lib/
-        results = await query_codebase(
-            "function", limit=50, languages=["python"], paths=["*/lib/*"]
-        )
+        results = await query_codebase("function", limit=50, languages=["python"], paths=["lib/*"])
         assert len(results) > 0
         assert all(r.language == "python" for r in results)
-        assert all("/lib/" in r.file_path for r in results)
+        assert all(r.file_path.startswith("lib/") for r in results)
 
     @pytest.mark.asyncio(loop_scope="session")
     async def test_no_filter_returns_all_languages(