cgraphx 1.1.0

package/dist/extraction/tree-sitter-types.d.ts

@@ -0,0 +1,239 @@
+/**
+ * Tree-sitter Extraction Types
+ *
+ * Defines the LanguageExtractor interface and related types used by
+ * the core TreeSitterExtractor and per-language extraction configs.
+ * Extracted to a leaf module to avoid circular imports.
+ */
+import { Node as SyntaxNode } from 'web-tree-sitter';
+import { Node, NodeKind, UnresolvedReference } from '../types';
+/**
+ * Information returned by a language's extractImport hook.
+ */
+export interface ImportInfo {
+    /** The module/package name being imported */
+    moduleName: string;
+    /** Full import statement text for display */
+    signature: string;
+    /** If true, the hook already created unresolved references itself */
+    handledRefs?: boolean;
+}
+/**
+ * Information about a single variable within a declaration.
+ * Returned by a language's extractVariables hook.
+ */
+export interface VariableInfo {
+    /** Variable name */
+    name: string;
+    /** Node kind: 'variable' or 'constant' */
+    kind: NodeKind;
+    /** Optional signature string */
+    signature?: string;
+    /** If set, this declarator is actually a function and should be extracted as such */
+    delegateToFunction?: SyntaxNode;
+    /** The AST node to use for positioning (may differ from the declaration node) */
+    positionNode?: SyntaxNode;
+}
+/**
+ * Context object passed to language hooks that need to call back into the core extractor.
+ * Provides a controlled API surface — hooks can create nodes, visit children, and add
+ * references without accessing the full TreeSitterExtractor internals.
+ */
+export interface ExtractorContext {
+    /** Create a node and add it to the extraction result */
+    createNode(kind: NodeKind, name: string, node: SyntaxNode, extra?: Partial<Node>): Node | null;
+    /** Visit a child node (dispatches through the standard visitNode logic) */
+    visitNode(node: SyntaxNode): void;
+    /** Visit a function body to extract calls */
+    visitFunctionBody(body: SyntaxNode, functionId: string): void;
+    /** Add an unresolved reference */
+    addUnresolvedReference(ref: UnresolvedReference): void;
+    /** Push a node ID onto the scope stack (for containment/qualified name building) */
+    pushScope(nodeId: string): void;
+    /** Pop the last node ID from the scope stack */
+    popScope(): void;
+    /** Current file path */
+    readonly filePath: string;
+    /** Current source text */
+    readonly source: string;
+    /** Stack of parent node IDs (current scope) */
+    readonly nodeStack: readonly string[];
+    /** All nodes extracted so far */
+    readonly nodes: readonly Node[];
+}
+/**
+ * Language-specific extraction configuration.
+ *
+ * Each supported language provides an implementation of this interface
+ * that configures which AST node types to look for and how to extract
+ * language-specific details like signatures, visibility, and imports.
+ */
+export interface LanguageExtractor {
+    /**
+     * Optional source transform applied immediately before the grammar parses the
+     * file. Used to work around grammar gaps that would otherwise corrupt the
+     * parse tree (e.g. C# blanks conditional-compilation directive lines the
+     * grammar mis-parses inside enum bodies). MUST preserve byte offsets (replace
+     * removed text with spaces, keep newlines) so node positions and getNodeText
+     * stay correct; the returned string is used for both parsing and extraction.
+     */
+    preParse?: (source: string) => string;
+    /** Node types that represent functions */
+    functionTypes: string[];
+    /** Node types that represent classes */
+    classTypes: string[];
+    /** Node types that represent methods */
+    methodTypes: string[];
+    /** Node types that represent interfaces/protocols/traits */
+    interfaceTypes: string[];
+    /** Node types that represent structs */
+    structTypes: string[];
+    /** Node types that represent enums */
+    enumTypes: string[];
+    /** Node types that represent enum members/cases (e.g. Swift: 'enum_entry', Rust: 'enum_variant') */
+    enumMemberTypes?: string[];
+    /** Node types that represent type aliases (e.g. `type X = ...`) */
+    typeAliasTypes: string[];
+    /** Node types that represent imports */
+    importTypes: string[];
+    /** Node types that represent function calls */
+    callTypes: string[];
+    /** Node types that represent variable declarations (const, let, var, etc.) */
+    variableTypes: string[];
+    /** Node types that represent class fields (extracted as 'field' kind inside class bodies) */
+    fieldTypes?: string[];
+    /** Node types that represent class properties (extracted as 'property' kind inside class bodies) */
+    propertyTypes?: string[];
+    /** Field name for identifier/name */
+    nameField: string;
+    /** Field name for body */
+    bodyField: string;
+    /** Field name for parameters */
+    paramsField: string;
+    /** Field name for return type */
+    returnField?: string;
+    /** Override symbol name extraction (e.g. ObjC multi-part selectors). */
+    resolveName?: (node: SyntaxNode, source: string) => string | undefined;
+    /** Extract property name when the generic name walk fails (e.g. ObjC @property). */
+    extractPropertyName?: (node: SyntaxNode, source: string) => string | null;
+    /** Extract signature from node */
+    getSignature?: (node: SyntaxNode, source: string) => string | undefined;
+    /** Extract visibility from node */
+    getVisibility?: (node: SyntaxNode) => 'public' | 'private' | 'protected' | 'internal' | undefined;
+    /** Check if node is exported */
+    isExported?: (node: SyntaxNode, source: string) => boolean;
+    /** Check if node is async */
+    isAsync?: (node: SyntaxNode) => boolean;
+    /** Check if node is static */
+    isStatic?: (node: SyntaxNode) => boolean;
+    /** Check if variable declaration is a constant (const vs let/var) */
+    isConst?: (node: SyntaxNode) => boolean;
+    /**
+     * Extract extra symbol-level modifier keywords to persist on the node's
+     * `decorators` list (e.g. Kotlin `expect`/`actual` multiplatform markers).
+     * Called generically for every created node; return undefined/[] when none.
+     * Used by the resolver to link `expect` declarations to their `actual`
+     * implementations across source sets.
+     */
+    extractModifiers?: (node: SyntaxNode) => string[] | undefined;
+    /** Additional node types to treat as class declarations (e.g. Dart: 'mixin_declaration') */
+    extraClassNodeTypes?: string[];
+    /** Whether methods can be top-level without enclosing class (Go: true) */
+    methodsAreTopLevel?: boolean;
+    /** NodeKind to use for interface-like declarations (Rust: 'trait'). Default: 'interface' */
+    interfaceKind?: NodeKind;
+    /**
+     * Custom node visitor. Return true if the node was fully handled (skip default dispatch).
+     * Used by languages with fundamentally different AST structures (e.g. Pascal).
+     */
+    visitNode?: (node: SyntaxNode, ctx: ExtractorContext) => boolean;
+    /**
+     * Synthesize members that exist at compile time but not in the source AST,
+     * called at the end of class extraction with the class still on the scope
+     * stack (so `ctx.createNode` attaches containment + qualified names) and the
+     * class's real members already extracted (so the hook can skip a member the
+     * source explicitly declares). Used by Java for Lombok-generated accessors
+     * (`@Getter`/`@Setter`/`@Data`/`@Value`/`@Builder` → `getX`/`setX`/`builder`/
+     * `equals`/`hashCode`/`toString` + the `log` field), which are otherwise
+     * invisible and break call-chain analysis (#912). The created nodes carry a
+     * `lombok` decorator + a docstring naming the generating annotation, so an
+     * agent can tell them apart from hand-written code.
+     */
+    synthesizeMembers?: (classNode: SyntaxNode, ctx: ExtractorContext) => void;
+    /**
+     * Classify a class_declaration node when the grammar reuses one node type
+     * for multiple concepts (e.g. Swift uses class_declaration for classes, structs, and enums).
+     */
+    classifyClassNode?: (node: SyntaxNode) => 'class' | 'struct' | 'enum' | 'interface' | 'trait';
+    /**
+     * Classify a methodTypes node when the grammar reuses one node type for
+     * both callable and data members (#808): TS/JS class FIELDS
+     * (`public_field_definition` / `field_definition`) are methods only when
+     * their value is callable (`onClick = () => {}`); a plain field
+     * (`public fonts: Fonts;`, `count = 0`) is a property. Default: 'method'.
+     */
+    classifyMethodNode?: (node: SyntaxNode) => 'method' | 'property';
+    /**
+     * Resolve the body node for a function/method/class when it's not a child field.
+     * (e.g. Dart puts function_body as a sibling, not a child.)
+     */
+    resolveBody?: (node: SyntaxNode, bodyField: string) => SyntaxNode | null;
+    /**
+     * Extract import information from an import node.
+     * Return null if the node isn't a recognized import form.
+     */
+    extractImport?: (node: SyntaxNode, source: string) => ImportInfo | null;
+    /**
+     * Extract variable declarations from a variable declaration node.
+     * Returns info about each declared variable, allowing the core to create nodes.
+     */
+    extractVariables?: (node: SyntaxNode, source: string) => VariableInfo[];
+    /**
+     * Extract receiver/owner type name from a method declaration.
+     * Used by Go to get the struct receiver (e.g., "scrapeLoop" from "func (sl *scrapeLoop) run()").
+     * When present, the receiver type is included in the qualified name for better searchability.
+     */
+    getReceiverType?: (node: SyntaxNode, source: string) => string | undefined;
+    /**
+     * Extract a function/method's normalized return type name (bare class name,
+     * smart-pointer pointee unwrapped), stored on the node as `returnType`. Used
+     * by C/C++ so resolution can infer a chained receiver's type from what the
+     * inner call returns (`Foo::instance().bar()` → resolve `bar` on `Foo`,
+     * issue #645). Return undefined for primitives / void / constructors.
+     */
+    getReturnType?: (node: SyntaxNode, source: string) => string | undefined;
+    /**
+     * Resolve the actual node kind for a type alias declaration.
+     * Used by Go where `type_spec` is the named declaration wrapper for structs/interfaces:
+     *   `type Foo struct { ... }` → type_spec (name: "Foo") → struct_type
+     * Returns 'struct', 'interface', etc. to override the default 'type_alias' kind,
+     * or undefined to keep it as a type alias.
+     */
+    resolveTypeAliasKind?: (node: SyntaxNode, source: string) => NodeKind | undefined;
+    /**
+     * Check if a function/method name is a misparse artifact that should be skipped.
+     * Used by C/C++ where macros (e.g. NLOHMANN_JSON_NAMESPACE_BEGIN) cause tree-sitter
+     * to misparse namespace blocks as function_definitions. When this returns true,
+     * the function node is NOT created, but the body is still visited for calls and
+     * structural nodes (classes, structs, enums).
+     */
+    isMisparsedFunction?: (name: string, node: SyntaxNode) => boolean;
+    /**
+     * Detect bare method calls that don't use call expression syntax.
+     * Used by Ruby where `reset` (no parens, no receiver) is a method call but
+     * tree-sitter parses it as a plain `identifier` node instead of `call`/`method_call`.
+     * Returns the callee name if this node is a bare call, or undefined if not.
+     */
+    extractBareCall?: (node: SyntaxNode, source: string) => string | undefined;
+    /**
+     * Node types representing a file-level package/namespace declaration
+     * (e.g. Kotlin `package_header`, Java `package_declaration`). When set,
+     * the core wraps every top-level declaration in an implicit `namespace`
+     * node carrying the FQN, so cross-file import resolution can match by
+     * qualifiedName instead of filename (Kotlin filename ≠ class name).
+     */
+    packageTypes?: string[];
+    /** Extract the dotted package name from a package declaration node. */
+    extractPackage?: (node: SyntaxNode, source: string) => string | null;
+}
+//# sourceMappingURL=tree-sitter-types.d.ts.map

package/dist/extraction/tree-sitter-types.d.ts.map

@@ -0,0 +1 @@
+{"version":3,"file":"tree-sitter-types.d.ts","sourceRoot":"","sources":["../../src/extraction/tree-sitter-types.ts"],"names":[],"mappings":"AAAA;;;;;;GAMG;AAEH,OAAO,EAAE,IAAI,IAAI,UAAU,EAAE,MAAM,iBAAiB,CAAC;AACrD,OAAO,EACL,IAAI,EACJ,QAAQ,EACR,mBAAmB,EACpB,MAAM,UAAU,CAAC;AAElB;;GAEG;AACH,MAAM,WAAW,UAAU;IACzB,6CAA6C;IAC7C,UAAU,EAAE,MAAM,CAAC;IACnB,6CAA6C;IAC7C,SAAS,EAAE,MAAM,CAAC;IAClB,qEAAqE;IACrE,WAAW,CAAC,EAAE,OAAO,CAAC;CACvB;AAED;;;GAGG;AACH,MAAM,WAAW,YAAY;IAC3B,oBAAoB;IACpB,IAAI,EAAE,MAAM,CAAC;IACb,0CAA0C;IAC1C,IAAI,EAAE,QAAQ,CAAC;IACf,gCAAgC;IAChC,SAAS,CAAC,EAAE,MAAM,CAAC;IACnB,qFAAqF;IACrF,kBAAkB,CAAC,EAAE,UAAU,CAAC;IAChC,iFAAiF;IACjF,YAAY,CAAC,EAAE,UAAU,CAAC;CAC3B;AAED;;;;GAIG;AACH,MAAM,WAAW,gBAAgB;IAC/B,wDAAwD;IACxD,UAAU,CAAC,IAAI,EAAE,QAAQ,EAAE,IAAI,EAAE,MAAM,EAAE,IAAI,EAAE,UAAU,EAAE,KAAK,CAAC,EAAE,OAAO,CAAC,IAAI,CAAC,GAAG,IAAI,GAAG,IAAI,CAAC;IAC/F,2EAA2E;IAC3E,SAAS,CAAC,IAAI,EAAE,UAAU,GAAG,IAAI,CAAC;IAClC,6CAA6C;IAC7C,iBAAiB,CAAC,IAAI,EAAE,UAAU,EAAE,UAAU,EAAE,MAAM,GAAG,IAAI,CAAC;IAC9D,kCAAkC;IAClC,sBAAsB,CAAC,GAAG,EAAE,mBAAmB,GAAG,IAAI,CAAC;IACvD,oFAAoF;IACpF,SAAS,CAAC,MAAM,EAAE,MAAM,GAAG,IAAI,CAAC;IAChC,gDAAgD;IAChD,QAAQ,IAAI,IAAI,CAAC;IACjB,wBAAwB;IACxB,QAAQ,CAAC,QAAQ,EAAE,MAAM,CAAC;IAC1B,0BAA0B;IAC1B,QAAQ,CAAC,MAAM,EAAE,MAAM,CAAC;IACxB,+CAA+C;IAC/C,QAAQ,CAAC,SAAS,EAAE,SAAS,MAAM,EAAE,CAAC;IACtC,iCAAiC;IACjC,QAAQ,CAAC,KAAK,EAAE,SAAS,IAAI,EAAE,CAAC;CACjC;AAED;;;;;;GAMG;AACH,MAAM,WAAW,iBAAiB;IAChC;;;;;;;OAOG;IACH,QAAQ,CAAC,EAAE,CAAC,MAAM,EAAE,MAAM,KAAK,MAAM,CAAC;IAItC,0CAA0C;IAC1C,aAAa,EAAE,MAAM,EAAE,CAAC;IACxB,wCAAwC;IACxC,UAAU,EAAE,MAAM,EAAE,CAAC;IACrB,wCAAwC;IACxC,WAAW,EAAE,MAAM,EAAE,CAAC;IACtB,4DAA4D;IAC5D,cAAc,EAAE,MAAM,EAAE,CAAC;IACzB,wCAAwC;IACxC,WAAW,EAAE,MAAM,EAAE,CAAC;IACtB,sCAAsC;IACtC,SAAS,EAAE,MAAM,EAAE,CAAC;IACpB,oGAAoG;IACpG,eAAe,CAAC,EAAE,MAAM,EAAE,CAAC;IAC3B,mEAAmE;IACnE,cAAc,EAAE,MAAM,EAAE,CAAC;IACzB,wCAAwC;IACxC,WAAW,EAAE,MAAM,EAAE,CAAC;IACtB,+CAA+C;IAC/C,SAAS,EAAE,MAAM,EAAE,CAAC;IACpB,8EAA8E;IAC9E,aAAa,EAAE,MAAM,EAAE,CAAC;IACxB,6FAA6F;IAC7F,UAAU,CAAC,EAAE,MAAM,EAAE,CAAC;IACtB,oGAAoG;IACpG,aAAa,CAAC,EAAE,MAAM,EAAE,CAAC;IAIzB,qCAAqC;IACrC,SAAS,EAAE,MAAM,CAAC;IAClB,0BAA0B;IAC1B,SAAS,EAAE,MAAM,CAAC;IAClB,gCAAgC;IAChC,WAAW,EAAE,MAAM,CAAC;IACpB,iCAAiC;IACjC,WAAW,CAAC,EAAE,MAAM,CAAC;IAIrB,wEAAwE;IACxE,WAAW,CAAC,EAAE,CAAC,IAAI,EAAE,UAAU,EAAE,MAAM,EAAE,MAAM,KAAK,MAAM,GAAG,SAAS,CAAC;IAEvE,oFAAoF;IACpF,mBAAmB,CAAC,EAAE,CAAC,IAAI,EAAE,UAAU,EAAE,MAAM,EAAE,MAAM,KAAK,MAAM,GAAG,IAAI,CAAC;IAE1E,kCAAkC;IAClC,YAAY,CAAC,EAAE,CAAC,IAAI,EAAE,UAAU,EAAE,MAAM,EAAE,MAAM,KAAK,MAAM,GAAG,SAAS,CAAC;IACxE,mCAAmC;IACnC,aAAa,CAAC,EAAE,CAAC,IAAI,EAAE,UAAU,KAAK,QAAQ,GAAG,SAAS,GAAG,WAAW,GAAG,UAAU,GAAG,SAAS,CAAC;IAClG,gCAAgC;IAChC,UAAU,CAAC,EAAE,CAAC,IAAI,EAAE,UAAU,EAAE,MAAM,EAAE,MAAM,KAAK,OAAO,CAAC;IAC3D,6BAA6B;IAC7B,OAAO,CAAC,EAAE,CAAC,IAAI,EAAE,UAAU,KAAK,OAAO,CAAC;IACxC,8BAA8B;IAC9B,QAAQ,CAAC,EAAE,CAAC,IAAI,EAAE,UAAU,KAAK,OAAO,CAAC;IACzC,qEAAqE;IACrE,OAAO,CAAC,EAAE,CAAC,IAAI,EAAE,UAAU,KAAK,OAAO,CAAC;IACxC;;;;;;OAMG;IACH,gBAAgB,CAAC,EAAE,CAAC,IAAI,EAAE,UAAU,KAAK,MAAM,EAAE,GAAG,SAAS,CAAC;IAI9D,4FAA4F;IAC5F,mBAAmB,CAAC,EAAE,MAAM,EAAE,CAAC;IAC/B,0EAA0E;IAC1E,kBAAkB,CAAC,EAAE,OAAO,CAAC;IAC7B,4FAA4F;IAC5F,aAAa,CAAC,EAAE,QAAQ,CAAC;IAIzB;;;OAGG;IACH,SAAS,CAAC,EAAE,CAAC,IAAI,EAAE,UAAU,EAAE,GAAG,EAAE,gBAAgB,KAAK,OAAO,CAAC;IAEjE;;;;;;;;;;;OAWG;IACH,iBAAiB,CAAC,EAAE,CAAC,SAAS,EAAE,UAAU,EAAE,GAAG,EAAE,gBAAgB,KAAK,IAAI,CAAC;IAE3E;;;OAGG;IACH,iBAAiB,CAAC,EAAE,CAAC,IAAI,EAAE,UAAU,KAAK,OAAO,GAAG,QAAQ,GAAG,MAAM,GAAG,WAAW,GAAG,OAAO,CAAC;IAE9F;;;;;;OAMG;IACH,kBAAkB,CAAC,EAAE,CAAC,IAAI,EAAE,UAAU,KAAK,QAAQ,GAAG,UAAU,CAAC;IAEjE;;;OAGG;IACH,WAAW,CAAC,EAAE,CAAC,IAAI,EAAE,UAAU,EAAE,SAAS,EAAE,MAAM,KAAK,UAAU,GAAG,IAAI,CAAC;IAEzE;;;OAGG;IACH,aAAa,CAAC,EAAE,CAAC,IAAI,EAAE,UAAU,EAAE,MAAM,EAAE,MAAM,KAAK,UAAU,GAAG,IAAI,CAAC;IAExE;;;OAGG;IACH,gBAAgB,CAAC,EAAE,CAAC,IAAI,EAAE,UAAU,EAAE,MAAM,EAAE,MAAM,KAAK,YAAY,EAAE,CAAC;IAExE;;;;OAIG;IACH,eAAe,CAAC,EAAE,CAAC,IAAI,EAAE,UAAU,EAAE,MAAM,EAAE,MAAM,KAAK,MAAM,GAAG,SAAS,CAAC;IAE3E;;;;;;OAMG;IACH,aAAa,CAAC,EAAE,CAAC,IAAI,EAAE,UAAU,EAAE,MAAM,EAAE,MAAM,KAAK,MAAM,GAAG,SAAS,CAAC;IAEzE;;;;;;OAMG;IACH,oBAAoB,CAAC,EAAE,CAAC,IAAI,EAAE,UAAU,EAAE,MAAM,EAAE,MAAM,KAAK,QAAQ,GAAG,SAAS,CAAC;IAElF;;;;;;OAMG;IACH,mBAAmB,CAAC,EAAE,CAAC,IAAI,EAAE,MAAM,EAAE,IAAI,EAAE,UAAU,KAAK,OAAO,CAAC;IAElE;;;;;OAKG;IACH,eAAe,CAAC,EAAE,CAAC,IAAI,EAAE,UAAU,EAAE,MAAM,EAAE,MAAM,KAAK,MAAM,GAAG,SAAS,CAAC;IAE3E;;;;;;OAMG;IACH,YAAY,CAAC,EAAE,MAAM,EAAE,CAAC;IAExB,uEAAuE;IACvE,cAAc,CAAC,EAAE,CAAC,IAAI,EAAE,UAAU,EAAE,MAAM,EAAE,MAAM,KAAK,MAAM,GAAG,IAAI,CAAC;CACtE"}

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

@@ -0,0 +1,10 @@
+"use strict";
+/**
+ * Tree-sitter Extraction Types
+ *
+ * Defines the LanguageExtractor interface and related types used by
+ * the core TreeSitterExtractor and per-language extraction configs.
+ * Extracted to a leaf module to avoid circular imports.
+ */
+Object.defineProperty(exports, "__esModule", { value: true });
+//# sourceMappingURL=tree-sitter-types.js.map

package/dist/extraction/tree-sitter-types.js.map

@@ -0,0 +1 @@
+{"version":3,"file":"tree-sitter-types.js","sourceRoot":"","sources":["../../src/extraction/tree-sitter-types.ts"],"names":[],"mappings":";AAAA;;;;;;GAMG"}