@colbymchenry/codegraph-darwin-x64 0.9.5 → 0.9.7

package/lib/dist/extraction/tree-sitter.js

@@ -48,6 +48,7 @@ const liquid_extractor_1 = require("./liquid-extractor");
 const svelte_extractor_1 = require("./svelte-extractor");
 const dfm_extractor_1 = require("./dfm-extractor");
 const vue_extractor_1 = require("./vue-extractor");
+const mybatis_extractor_1 = require("./mybatis-extractor");
 const frameworks_1 = require("../resolution/frameworks");
 // Re-export for backward compatibility
 var tree_sitter_helpers_2 = require("./tree-sitter-helpers");
@@ -221,7 +222,16 @@ class TreeSitterExtractor {
             this.nodes.push(fileNode);
             // Push file node onto stack so top-level declarations get contains edges
             this.nodeStack.push(fileNode.id);
+            // File-level package declaration (Kotlin/Java). Creates an implicit
+            // `namespace` node wrapping every top-level declaration so their
+            // qualifiedName carries the FQN — required for cross-file import
+            // resolution on JVM languages where filename ≠ class name.
+            const packageNodeId = this.extractFilePackage(this.tree.rootNode);
+            if (packageNodeId)
+                this.nodeStack.push(packageNodeId);
             this.visitNode(this.tree.rootNode);
+            if (packageNodeId)
+                this.nodeStack.pop();
             this.nodeStack.pop();
         }
         catch (error) {
@@ -386,6 +396,17 @@ class TreeSitterExtractor {
         // their own `calls` refs.
         else if (INSTANTIATION_KINDS.has(nodeType)) {
             this.extractInstantiation(node);
+            // Java/C# `new T(...) { ... }` — anonymous class with body. Without
+            // extracting it as a class node + its methods, the interface→impl
+            // synthesizer (Phase 5.5) can't bridge T's abstract methods to the
+            // anonymous overrides, and an agent investigating a call through T
+            // (`strategy.iterator(...)` where strategy is a Strategy lambda body)
+            // has to Read the file to find the actual implementation.
+            const anonBody = this.findAnonymousClassBody(node);
+            if (anonBody) {
+                this.extractAnonymousClass(node, anonBody);
+                skipChildren = true;
+            }
         }
         // (Decorator handling lives inside the symbol-creating extractors
         // — extractClass / extractFunction / extractProperty — because the
@@ -395,6 +416,20 @@ class TreeSitterExtractor {
         else if (nodeType === 'impl_item') {
             this.extractRustImplItem(node);
         }
+        // TypeScript interface members: property_signature (`foo: T`, `foo?: T`)
+        // and method_signature (`foo(arg: A): R`) both carry type annotations the
+        // interface walker would otherwise drop. Extract them as `references`
+        // edges from the interface so resolvers can wire callers/impact for
+        // types that only appear in interface members.
+        else if ((nodeType === 'property_signature' || nodeType === 'method_signature') &&
+            this.isInsideClassLikeNode() &&
+            this.TYPE_ANNOTATION_LANGUAGES.has(this.language)) {
+            const parentId = this.nodeStack[this.nodeStack.length - 1];
+            if (parentId) {
+                this.extractTypeAnnotations(node, parentId);
+            }
+            // don't skipChildren — nested signatures still need traversal
+        }
         // Visit children (unless the extract method already visited them)
         if (!skipChildren) {
             for (let i = 0; i < node.namedChildCount; i++) {
@@ -468,6 +503,32 @@ class TreeSitterExtractor {
         }
         return null;
     }
+    /**
+     * Find a `packageTypes` child under the root, create a `namespace` node
+     * for it, and return its id so the caller can scope top-level
+     * declarations underneath. Returns null when no package header is
+     * present (script files, .kts without a package).
+     */
+    extractFilePackage(rootNode) {
+        const types = this.extractor?.packageTypes;
+        if (!types || types.length === 0 || !this.extractor?.extractPackage)
+            return null;
+        let pkgNode = null;
+        for (let i = 0; i < rootNode.namedChildCount; i++) {
+            const child = rootNode.namedChild(i);
+            if (child && types.includes(child.type)) {
+                pkgNode = child;
+                break;
+            }
+        }
+        if (!pkgNode)
+            return null;
+        const pkgName = this.extractor.extractPackage(pkgNode, this.source);
+        if (!pkgName)
+            return null;
+        const ns = this.createNode('namespace', pkgName, pkgNode);
+        return ns?.id ?? null;
+    }
     /**
      * Build qualified name from node stack
      */
@@ -651,6 +712,11 @@ class TreeSitterExtractor {
             // in inline objects). These are ephemeral and create noise (e.g., Svelte context
             // objects: `ctx.set({ get view() { ... } })`).
             if (node.parent?.type === 'object' || node.parent?.type === 'object_expression') {
+                const body = this.extractor.resolveBody?.(node, this.extractor.bodyField)
+                    ?? (0, tree_sitter_helpers_1.getChildByField)(node, this.extractor.bodyField);
+                if (body) {
+                    this.visitFunctionBody(body, '');
+                }
                 return;
             }
             // Not inside a class-like node and no receiver type, treat as function
@@ -875,6 +941,10 @@ class TreeSitterExtractor {
         // decorator->target relationship for class properties too.
         if (propNode) {
             this.extractDecoratorsFor(node, propNode.id);
+            // Emit `references` edges from the property to types named in its
+            // type annotation (#381). The generic walker handles TS-style
+            // `type_annotation` children; the C# branch walks the `type` field.
+            this.extractTypeAnnotations(node, propNode.id);
         }
     }
     /**
@@ -947,8 +1017,15 @@ class TreeSitterExtractor {
                 });
                 // Java/Kotlin annotations / TS field decorators sit on the
                 // outer field_declaration, not on the individual declarator.
-                if (fieldNode)
+                if (fieldNode) {
                     this.extractDecoratorsFor(node, fieldNode.id);
+                    // Same as properties: emit `references` to the field's annotated
+                    // type. The outer `field_declaration` is the right scope to
+                    // search from — C# carries the `type` inside `variable_declaration`
+                    // and the language-aware path in `extractTypeAnnotations` descends
+                    // into that wrapper (#381).
+                    this.extractTypeAnnotations(node, fieldNode.id);
+                }
             }
         }
         else {
@@ -1016,6 +1093,11 @@ class TreeSitterExtractor {
                         if (varNode) {
                             this.extractVariableTypeAnnotation(child, varNode.id);
                         }
+                        if (valueNode &&
+                            valueNode.type !== 'object' &&
+                            valueNode.type !== 'object_expression') {
+                            this.visitFunctionBody(valueNode, '');
+                        }
                         // Exported const object-of-functions: `export const actions =
                         // { default: async () => {} }` (SvelteKit form actions / handler maps
                         // / route tables). Extract each function-valued property as a function
@@ -1221,8 +1303,87 @@ class TreeSitterExtractor {
             const value = (0, tree_sitter_helpers_1.getChildByField)(node, 'value');
             if (value) {
                 this.extractTypeRefsFromSubtree(value, typeAliasNode.id);
+                // `type X = { foo: T; bar(): T }` — make the members first-class
+                // property/method nodes under the type alias so `recorder.stop()`
+                // can attach the call edge to `RecorderHandle.stop` instead of
+                // an unrelated class method picked by path-proximity (#359).
+                if (this.language === 'typescript' || this.language === 'tsx') {
+                    this.extractTsTypeAliasMembers(value, typeAliasNode);
+                }
+            }
+        }
+        return false;
+    }
+    /**
+     * Surface the members of a TypeScript `type X = { ... }` (or intersection
+     * thereof) as `property` / `method` nodes under the type-alias node. Only
+     * walks the immediate object_type / intersection operands so anonymous
+     * nested object types inside generic arguments (`Promise<{ ok: true }>`)
+     * don't produce phantom members.
+     */
+    extractTsTypeAliasMembers(value, typeAliasNode) {
+        const objectTypes = [];
+        if (value.type === 'object_type') {
+            objectTypes.push(value);
+        }
+        else if (value.type === 'intersection_type') {
+            for (let i = 0; i < value.namedChildCount; i++) {
+                const op = value.namedChild(i);
+                if (op && op.type === 'object_type')
+                    objectTypes.push(op);
+            }
+        }
+        else {
+            return;
+        }
+        this.nodeStack.push(typeAliasNode.id);
+        for (const objType of objectTypes) {
+            for (let i = 0; i < objType.namedChildCount; i++) {
+                const child = objType.namedChild(i);
+                if (!child)
+                    continue;
+                if (child.type !== 'property_signature' && child.type !== 'method_signature')
+                    continue;
+                const nameNode = (0, tree_sitter_helpers_1.getChildByField)(child, 'name');
+                const memberName = nameNode ? (0, tree_sitter_helpers_1.getNodeText)(nameNode, this.source) : '';
+                if (!memberName)
+                    continue;
+                // `foo: () => T` and `foo(): T` are functionally a method on the
+                // type contract. Treat the property_signature with a function-typed
+                // annotation as a method too so call sites can resolve to it.
+                const memberKind = child.type === 'method_signature'
+                    ? 'method'
+                    : this.isTsFunctionTypedProperty(child) ? 'method' : 'property';
+                const docstring = (0, tree_sitter_helpers_1.getPrecedingDocstring)(child, this.source);
+                const signature = (0, tree_sitter_helpers_1.getNodeText)(child, this.source);
+                this.createNode(memberKind, memberName, child, {
+                    docstring,
+                    signature,
+                    qualifiedName: `${typeAliasNode.name}::${memberName}`,
+                });
+                // Emit `references` edges from the type alias to types named in the
+                // member's signature, matching the interface-member behavior added in
+                // #432. We attach refs to the type-alias parent (consistent with
+                // interface property_signature treatment).
+                this.extractTypeAnnotations(child, typeAliasNode.id);
             }
         }
+        this.nodeStack.pop();
+    }
+    /**
+     * `foo: () => T` → property_signature whose type_annotation contains a
+     * `function_type`. Treat that as a method-shaped contract member, since
+     * the call site `obj.foo()` has identical semantics to `bar(): T`.
+     */
+    isTsFunctionTypedProperty(propertySignature) {
+        const typeAnno = (0, tree_sitter_helpers_1.getChildByField)(propertySignature, 'type');
+        if (!typeAnno)
+            return false;
+        for (let i = 0; i < typeAnno.namedChildCount; i++) {
+            const inner = typeAnno.namedChild(i);
+            if (inner && inner.type === 'function_type')
+                return true;
+        }
         return false;
     }
     // extractExportedVariables removed — the walker now descends into
@@ -1373,7 +1534,25 @@ class TreeSitterExtractor {
         if (nameField && objectField && (node.type === 'method_invocation' || node.type === 'member_call_expression' || node.type === 'scoped_call_expression')) {
             // Method call with explicit receiver: receiver.method() / $receiver->method() / ClassName::method()
             const methodName = (0, tree_sitter_helpers_1.getNodeText)(nameField, this.source);
-            let receiverName = (0, tree_sitter_helpers_1.getNodeText)(objectField, this.source);
+            // Java `this.userbo.toLogin2()` parses as method_invocation(object=field_access(this, userbo)).
+            // Without unwrapping, receiverName is `this.userbo` and the name-matcher's
+            // single-dot receiver regex fails. Pull out the immediate field after `this.`
+            // so the receiver is the field name (`userbo`), which the resolver can then
+            // look up in the enclosing class's field declarations.
+            let receiverName;
+            if (objectField.type === 'field_access') {
+                const inner = (0, tree_sitter_helpers_1.getChildByField)(objectField, 'object');
+                const fld = (0, tree_sitter_helpers_1.getChildByField)(objectField, 'field');
+                if (inner && fld && (inner.type === 'this' || inner.type === 'this_expression')) {
+                    receiverName = (0, tree_sitter_helpers_1.getNodeText)(fld, this.source);
+                }
+                else {
+                    receiverName = (0, tree_sitter_helpers_1.getNodeText)(objectField, this.source);
+                }
+            }
+            else {
+                receiverName = (0, tree_sitter_helpers_1.getNodeText)(objectField, this.source);
+            }
             // Strip PHP $ prefix from variable names
             receiverName = receiverName.replace(/^\$/, '');
             if (methodName) {
@@ -1427,10 +1606,11 @@ class TreeSitterExtractor {
         else {
             const func = (0, tree_sitter_helpers_1.getChildByField)(node, 'function') || node.namedChild(0);
             if (func) {
-                if (func.type === 'member_expression' || func.type === 'attribute' || func.type === 'selector_expression' || func.type === 'navigation_expression') {
+                if (func.type === 'member_expression' || func.type === 'attribute' || func.type === 'selector_expression' || func.type === 'navigation_expression' || func.type === 'field_expression') {
                     // Method call: obj.method() or obj.field.method()
                     // Go uses selector_expression with 'field', JS/TS uses member_expression with 'property'
                     // Kotlin uses navigation_expression with navigation_suffix > simple_identifier
+                    // C/C++ use field_expression for both `obj.method()` and `ptr->method()`
                     let property = (0, tree_sitter_helpers_1.getChildByField)(func, 'property') || (0, tree_sitter_helpers_1.getChildByField)(func, 'field');
                     if (!property) {
                         const child1 = func.namedChild(1);
@@ -1448,9 +1628,12 @@ class TreeSitterExtractor {
                         // This helps the resolver distinguish method calls from bare function calls
                         // (e.g., Python's console.print() vs builtin print())
                         // Skip self/this/cls as they don't aid resolution
-                        const receiver = (0, tree_sitter_helpers_1.getChildByField)(func, 'object') || (0, tree_sitter_helpers_1.getChildByField)(func, 'operand') || func.namedChild(0);
+                        const receiver = (0, tree_sitter_helpers_1.getChildByField)(func, 'object') ||
+                            (0, tree_sitter_helpers_1.getChildByField)(func, 'operand') ||
+                            (0, tree_sitter_helpers_1.getChildByField)(func, 'argument') ||
+                            func.namedChild(0);
                         const SKIP_RECEIVERS = new Set(['self', 'this', 'cls', 'super']);
-                        if (receiver && (receiver.type === 'identifier' || receiver.type === 'simple_identifier')) {
+                        if (receiver && (receiver.type === 'identifier' || receiver.type === 'simple_identifier' || receiver.type === 'field_identifier')) {
                             const receiverName = (0, tree_sitter_helpers_1.getNodeText)(receiver, this.source);
                             if (!SKIP_RECEIVERS.has(receiverName)) {
                                 calleeName = `${receiverName}.${methodName}`;
@@ -1531,6 +1714,76 @@ class TreeSitterExtractor {
             });
         }
     }
+    /**
+     * Find a `class_body` child of an `object_creation_expression` — the
+     * marker for an anonymous class (`new T() { ... }`). Returns the body
+     * node so the caller can walk it as the anon class's members.
+     */
+    findAnonymousClassBody(node) {
+        for (let i = 0; i < node.namedChildCount; i++) {
+            const child = node.namedChild(i);
+            // Java: `class_body`. C# uses the same node kind.
+            if (child && (child.type === 'class_body' || child.type === 'declaration_list')) {
+                return child;
+            }
+        }
+        return null;
+    }
+    /**
+     * Extract a Java/C# anonymous class — `new T() { ...members }`. Emits a
+     * `class` node named `<T$anon@line>`, an `extends` reference to T (so
+     * Phase 5.5 interface-impl can bridge), and walks the body so its
+     * `method_declaration` members become method nodes under the anon class.
+     *
+     * Why this matters: without anon-class extraction, the overrides inside
+     * a lambda-returned `new T() { @Override int foo(){...} }` are not nodes,
+     * so a call through T.foo (the abstract parent method) has no static
+     * target — the agent has to Read the file to find the implementation.
+     */
+    extractAnonymousClass(node, body) {
+        if (!this.extractor)
+            return;
+        // The instantiated type sits in the same field/position that
+        // extractInstantiation reads from. Use the same lookup so the anon
+        // class's `extends` target matches the `instantiates` edge.
+        const typeNode = (0, tree_sitter_helpers_1.getChildByField)(node, 'constructor') ||
+            (0, tree_sitter_helpers_1.getChildByField)(node, 'type') ||
+            (0, tree_sitter_helpers_1.getChildByField)(node, 'name') ||
+            node.namedChild(0);
+        let typeName = typeNode ? (0, tree_sitter_helpers_1.getNodeText)(typeNode, this.source) : 'Object';
+        const ltIdx = typeName.indexOf('<');
+        if (ltIdx > 0)
+            typeName = typeName.slice(0, ltIdx);
+        const lastDot = Math.max(typeName.lastIndexOf('.'), typeName.lastIndexOf('::'));
+        if (lastDot >= 0)
+            typeName = typeName.slice(lastDot + 1).replace(/^[:.]/, '');
+        typeName = typeName.trim() || 'Object';
+        const anonName = `<${typeName}$anon@${node.startPosition.row + 1}>`;
+        const classNode = this.createNode('class', anonName, node, {});
+        if (!classNode)
+            return;
+        // The anonymous class implicitly extends/implements the named type.
+        // We can't tell at extraction time whether T is a class or an interface,
+        // so emit `extends`. Resolution will still bind T to whatever it is, and
+        // Phase 5.5 (which already handles both `extends` and `implements`) will
+        // bridge T's methods to the override names found in the anon body.
+        this.unresolvedReferences.push({
+            fromNodeId: classNode.id,
+            referenceName: typeName,
+            referenceKind: 'extends',
+            line: typeNode?.startPosition.row ?? node.startPosition.row,
+            column: typeNode?.startPosition.column ?? node.startPosition.column,
+        });
+        // Walk the body's children so method_declaration nodes inside become
+        // method nodes scoped to the anon class.
+        this.nodeStack.push(classNode.id);
+        for (let i = 0; i < body.namedChildCount; i++) {
+            const child = body.namedChild(i);
+            if (child)
+                this.visitNode(child);
+        }
+        this.nodeStack.pop();
+    }
     /**
      * Scan `declNode` and its preceding siblings (within the parent's
      * named children) for decorator nodes, emitting a `decorates`
@@ -1661,6 +1914,14 @@ class TreeSitterExtractor {
                 // about `call_expression`, so constructor invocations
                 // produced no graph edges at all.
                 this.extractInstantiation(node);
+                // Anonymous class with body: `new T() { ... }` (Java/C#). Extract as
+                // a class so interface-impl synthesis (Phase 5.5) can bridge T's
+                // methods to the overrides — same rationale as in visitNode.
+                const anonBody = this.findAnonymousClassBody(node);
+                if (anonBody) {
+                    this.extractAnonymousClass(node, anonBody);
+                    return;
+                }
             }
             else if (this.extractor.extractBareCall) {
                 const calleeName = this.extractor.extractBareCall(node, this.source);
@@ -2083,6 +2344,16 @@ class TreeSitterExtractor {
             return;
         if (!this.TYPE_ANNOTATION_LANGUAGES.has(this.language))
             return;
+        // C# tree-sitter doesn't produce `type_identifier` leaves — it uses
+        // `identifier`, `predefined_type`, `qualified_name`, `generic_name`,
+        // etc. — so the generic walker below emits zero references for it.
+        // Dispatch to a C#-aware path that only walks type-position subtrees
+        // (the `type` field of a parameter/method/property/field), so
+        // parameter NAMES never accidentally surface as type refs (#381).
+        if (this.language === 'csharp') {
+            this.extractCsharpTypeRefs(node, nodeId);
+            return;
+        }
         // Extract parameter type annotations
         const params = (0, tree_sitter_helpers_1.getChildByField)(node, this.extractor.paramsField || 'parameters');
         if (params) {
@@ -2099,6 +2370,112 @@ class TreeSitterExtractor {
             this.extractTypeRefsFromSubtree(typeAnnotation, nodeId);
         }
     }
+    /**
+     * Extract C# type references from a node that owns a type position —
+     * a method/constructor declaration, a property declaration, or a
+     * field declaration (which wraps `variable_declaration → type`).
+     *
+     * Walks ONLY into known type fields, so parameter names like
+     * `request` in `Build(UserDto request)` are never mis-emitted as
+     * type references. Once inside a type subtree, `walkCsharpTypePosition`
+     * recognizes C#'s actual type-leaf node kinds (`identifier`,
+     * `qualified_name`, `generic_name`, `array_type`, `nullable_type`,
+     * `tuple_type`, …) — none of which are `type_identifier`. Closes #381.
+     */
+    extractCsharpTypeRefs(node, nodeId) {
+        // Return type / property type — the field is named `type`.
+        const directType = (0, tree_sitter_helpers_1.getChildByField)(node, 'type');
+        if (directType)
+            this.walkCsharpTypePosition(directType, nodeId);
+        // Field declarations wrap declarators in a `variable_declaration`
+        // whose `type` field carries the type. The outer `field_declaration`
+        // has no `type` field of its own, so the call above is a no-op here
+        // and we descend one level.
+        const varDecl = node.namedChildren.find((c) => c.type === 'variable_declaration');
+        if (varDecl) {
+            const vdType = (0, tree_sitter_helpers_1.getChildByField)(varDecl, 'type');
+            if (vdType)
+                this.walkCsharpTypePosition(vdType, nodeId);
+        }
+        // Method / constructor parameters. The field name on
+        // `method_declaration` is `parameters`; it points at a
+        // `parameter_list` whose `parameter` children each have their own
+        // `type` field. Walking ONLY the type field skips parameter NAMES,
+        // which would otherwise mis-emit as type references.
+        const params = (0, tree_sitter_helpers_1.getChildByField)(node, 'parameters');
+        if (params) {
+            for (let i = 0; i < params.namedChildCount; i++) {
+                const child = params.namedChild(i);
+                if (!child || child.type !== 'parameter')
+                    continue;
+                const paramType = (0, tree_sitter_helpers_1.getChildByField)(child, 'type');
+                if (paramType)
+                    this.walkCsharpTypePosition(paramType, nodeId);
+            }
+        }
+    }
+    /**
+     * Walk a C# subtree that is KNOWN to be in a type position
+     * (return type, parameter type, property type, field type, generic
+     * argument). Identifiers here are type names, not parameter names.
+     */
+    walkCsharpTypePosition(node, fromNodeId) {
+        // `predefined_type` is int/string/bool/etc. — never a project ref.
+        if (node.type === 'predefined_type')
+            return;
+        // Bare type name: `Foo` in `Foo bar`, or the `Foo` inside `List<Foo>`.
+        if (node.type === 'identifier') {
+            const name = (0, tree_sitter_helpers_1.getNodeText)(node, this.source);
+            if (name && !this.BUILTIN_TYPES.has(name)) {
+                this.unresolvedReferences.push({
+                    fromNodeId,
+                    referenceName: name,
+                    referenceKind: 'references',
+                    line: node.startPosition.row + 1,
+                    column: node.startPosition.column,
+                });
+            }
+            return;
+        }
+        // `Namespace.Foo` → the rightmost identifier is the type. Emit the
+        // full qualified name as the reference; the resolver can still match
+        // on the trailing simple name when needed.
+        if (node.type === 'qualified_name') {
+            const text = (0, tree_sitter_helpers_1.getNodeText)(node, this.source);
+            const last = text.split('.').pop() ?? text;
+            if (last && !this.BUILTIN_TYPES.has(last)) {
+                this.unresolvedReferences.push({
+                    fromNodeId,
+                    referenceName: last,
+                    referenceKind: 'references',
+                    line: node.startPosition.row + 1,
+                    column: node.startPosition.column,
+                });
+            }
+            return;
+        }
+        // `(int Code, Foo Payload)` — tuple element has BOTH a `type` and a
+        // `name` field; descending into all named children would mis-emit
+        // the element name (`Code`, `Payload`) as a type ref. Walk only the
+        // type field.
+        if (node.type === 'tuple_element') {
+            const t = (0, tree_sitter_helpers_1.getChildByField)(node, 'type');
+            if (t)
+                this.walkCsharpTypePosition(t, fromNodeId);
+            return;
+        }
+        // Composite type nodes — recurse into named children. Covers
+        // `generic_name` (head identifier + `type_argument_list`),
+        // `nullable_type`, `array_type`, `pointer_type`, `tuple_type`,
+        // `ref_type`, and any newer wrapping shapes the grammar adds.
+        // Identifiers reached here are all type-positional (parameter/field
+        // names are gated out before we descend).
+        for (let i = 0; i < node.namedChildCount; i++) {
+            const child = node.namedChild(i);
+            if (child)
+                this.walkCsharpTypePosition(child, fromNodeId);
+        }
+    }
     /**
      * Extract type references from a variable's type annotation.
      */
@@ -2535,10 +2912,17 @@ function extractFromSource(filePath, source, language, frameworkNames) {
         const extractor = new liquid_extractor_1.LiquidExtractor(filePath, source);
         result = extractor.extract();
     }
-    else if (detectedLanguage === 'yaml' || detectedLanguage === 'twig') {
-        // No symbol extraction — file is tracked at the file-record level only.
-        // Framework extractors (e.g. Drupal routing resolver) run below and may
-        // add route nodes / references for yaml files such as *.routing.yml.
+    else if (detectedLanguage === 'xml') {
+        // Custom extractor for MyBatis mapper XML. Non-mapper XML returns just a
+        // file node so the watcher tracks it without emitting symbols.
+        const extractor = new mybatis_extractor_1.MyBatisExtractor(filePath, source);
+        result = extractor.extract();
+    }
+    else if (detectedLanguage === 'yaml' || detectedLanguage === 'twig' || detectedLanguage === 'properties') {
+        // No symbol extraction at this stage — files are tracked at the file-record
+        // level only. Framework extractors (Drupal routing yml, Spring `@Value`
+        // resolution against application.yml/application.properties) run later and
+        // add per-file nodes/references when they apply.
         result = { nodes: [], edges: [], unresolvedReferences: [], errors: [], durationMs: 0 };
     }
     else if (detectedLanguage === 'pascal' &&