java-codebase-rag 0.6.3__py3-none-any.whl → 0.6.5__py3-none-any.whl

ast_java.py

@@ -14,8 +14,8 @@ from __future__ import annotations
 
 import posixpath
 import sys
+import threading
 from dataclasses import dataclass, field
-from functools import lru_cache
 from typing import Iterable
 
 import tree_sitter_java as _ts_java
@@ -215,10 +215,23 @@ _ANON_SUPER_AS_INTERFACE: frozenset[str] = frozenset({
 })
 
 
-@lru_cache(maxsize=1)
+# tree-sitter's ``Parser`` mutates internal state during ``parse()`` and is NOT
+# thread-safe, so each OS thread gets its own instance. ``parse_java`` is called
+# concurrently from worker threads when indexing runs with cocoindex's inflight
+# parallelism — both directly (java_index_flow_lancedb.py: process_java_file
+# offloads parse+enrich to asyncio.to_thread) and transitively
+# (graph_enrich.collect_annotation_meta_chain -> _collect_annotation_decl_index
+# -> parse_java, reached from enrich_chunk). The ``Language`` is immutable and
+# shared; per-thread ``Parser`` construction is lazy and cheap (once per thread),
+# which also preserves parse parallelism instead of serializing it.
+_parser_tls = threading.local()
+
+
 def _parser() -> Parser:
-    lang = Language(_ts_java.language())
-    return Parser(lang)
+    p = getattr(_parser_tls, "parser", None)
+    if p is None:
+        _parser_tls.parser = p = Parser(Language(_ts_java.language()))
+    return p
 
 
 # ---------- dataclasses ----------
@@ -1565,62 +1578,20 @@ def _parse_codebase_http_route_inner_annotation(
     return out
 
 
-def _codebase_route_inner_annotation_nodes(container_ann: Node, src: bytes) -> list[Node]:
-    found: list[Node] = []
-
-    def visit(n: Node) -> None:
-        if n.type == "annotation":
-            name_node = n.child_by_field_name("name")
-            n_simple = _txt(name_node, src).rsplit(".", 1)[-1] if name_node is not None else ""
-            if n_simple == "CodebaseHttpRoute":
-                found.append(n)
-        for c in n.children:
-            visit(c)
+def _inner_annotation_nodes(container_ann: Node, src: bytes, target_simple: str) -> list[Node]:
+    """Collect nested ``@<target_simple>`` annotations anywhere under ``container_ann``.
 
-    visit(container_ann)
-    return found
-
-
-def _codebase_async_route_inner_annotation_nodes(container_ann: Node, src: bytes) -> list[Node]:
-    found: list[Node] = []
-
-    def visit(n: Node) -> None:
-        if n.type == "annotation":
-            name_node = n.child_by_field_name("name")
-            n_simple = _txt(name_node, src).rsplit(".", 1)[-1] if name_node is not None else ""
-            if n_simple == "CodebaseAsyncRoute":
-                found.append(n)
-        for c in n.children:
-            visit(c)
-
-    visit(container_ann)
-    return found
-
-
-def _codebase_http_client_inner_annotation_nodes(container_ann: Node, src: bytes) -> list[Node]:
-    found: list[Node] = []
-
-    def visit(n: Node) -> None:
-        if n.type == "annotation":
-            name_node = n.child_by_field_name("name")
-            n_simple = _txt(name_node, src).rsplit(".", 1)[-1] if name_node is not None else ""
-            if n_simple == "CodebaseHttpClient":
-                found.append(n)
-        for c in n.children:
-            visit(c)
-
-    visit(container_ann)
-    return found
-
-
-def _codebase_producer_inner_annotation_nodes(container_ann: Node, src: bytes) -> list[Node]:
+    Shared by the four brownfield container walkers — ``CodebaseHttpRoute``,
+    ``CodebaseAsyncRoute``, ``CodebaseHttpClient``, ``CodebaseProducer`` — which
+    differ only by the target annotation simple name.
+    """
     found: list[Node] = []
 
     def visit(n: Node) -> None:
         if n.type == "annotation":
             name_node = n.child_by_field_name("name")
             n_simple = _txt(name_node, src).rsplit(".", 1)[-1] if name_node is not None else ""
-            if n_simple == "CodebaseProducer":
+            if n_simple == target_simple:
                 found.append(n)
         for c in n.children:
             visit(c)
@@ -1842,7 +1813,7 @@ def _outgoing_calls_from_codebase_http_client_producer_annotations(
                 ),
             )
         elif simple == "CodebaseHttpClients":
-            for inner in _codebase_http_client_inner_annotation_nodes(ann, src):
+            for inner in _inner_annotation_nodes(ann, src, "CodebaseHttpClient"):
                 out.append(
                     _parse_codebase_http_client_annotation(
                         inner,
@@ -1869,7 +1840,7 @@ def _outgoing_calls_from_codebase_http_client_producer_annotations(
                 ),
             )
         elif simple == "CodebaseProducers":
-            for inner in _codebase_producer_inner_annotation_nodes(ann, src):
+            for inner in _inner_annotation_nodes(ann, src, "CodebaseProducer"):
                 out.append(
                     _parse_codebase_producer_annotation(
                         inner,
@@ -2343,7 +2314,7 @@ def _collect_routes(
                 ),
             )
         elif simple == "CodebaseHttpRoutes":
-            for inner in _codebase_route_inner_annotation_nodes(node, src):
+            for inner in _inner_annotation_nodes(node, src, "CodebaseHttpRoute"):
                 routes.extend(
                     _parse_codebase_http_route_inner_annotation(
                         inner,
@@ -2359,7 +2330,7 @@ def _collect_routes(
         elif simple in ("CodebaseAsyncRoute", "CodebaseAsyncRoutes"):
             nodes = [node]
             if simple == "CodebaseAsyncRoutes":
-                nodes = list(_codebase_async_route_inner_annotation_nodes(node, src))
+                nodes = list(_inner_annotation_nodes(node, src, "CodebaseAsyncRoute"))
             for ann in nodes:
                 pairs, _ = _annotation_kv_nodes(ann, src)
                 topic_node = pairs.get("topic")