@colbymchenry/codegraph-darwin-arm64 1.1.6 → 1.3.0

package/lib/dist/extraction/languages/arkts.js

@@ -0,0 +1,127 @@
+"use strict";
+Object.defineProperty(exports, "__esModule", { value: true });
+exports.arktsExtractor = void 0;
+const typescript_1 = require("./typescript");
+/**
+ * ArkTS (HarmonyOS / OpenHarmony, `.ets`) — a TypeScript superset whose
+ * headline feature is declarative UI: an `@Component struct` with a `build()`
+ * method describing the view tree, `@State`/`@Prop`/`@Link` reactive
+ * properties, and global `@Builder`/`@Extend`/`@Styles` functions.
+ *
+ * The vendored grammar (harmony-contrib/tree-sitter-arkts) extends
+ * tree-sitter-javascript exactly the way tree-sitter-typescript does, so every
+ * TS node type — and therefore the whole typescriptExtractor — applies
+ * verbatim. ArkTS-specific shapes it adds:
+ *
+ *   - `struct_declaration` / `struct_body` — the `@Component struct`. Same
+ *     `name:`/`body:` fields as class_declaration; members are ordinary
+ *     `method_definition` / `public_field_definition` nodes, so struct members
+ *     extract through the standard class-member paths.
+ *   - `arkui_component_expression` — a build()-DSL component instantiation
+ *     (`Column() { … }`). Carries a `function:` field (the component), an
+ *     optional `children:` block, and — unlike TS — the CHAINED ATTRIBUTES as
+ *     repeated `property:`/`arguments:` field pairs on the SAME node
+ *     (`Text(x).fontSize(16).opacity(0.6)` is ONE node, not nested calls).
+ *     Handled by the arkts branch in extractCall (tree-sitter.ts).
+ *   - Decorators on functions (`@Builder function F() {}`) — invalid in TS,
+ *     first-class here (a `decorator:` field on function_declaration), so the
+ *     core's existing extractDecoratorsFor path captures them.
+ */
+/** Reactive/state decorators that make a member worth flagging (searchable). */
+const DECORATED_MEMBER_TYPES = new Set([
+    'struct_declaration',
+    'public_field_definition',
+    'method_definition',
+    'function_declaration',
+]);
+/**
+ * Collect decorator names for a declaration from BOTH positions the grammar
+ * produces: direct `decorator` children (`@Entry @Component struct X`,
+ * `@State count` on a field) and preceding `decorator` siblings (`@Builder`
+ * before a method_definition inside struct_body; `@Component` on the
+ * export_statement wrapping `export struct X`). The backwards sibling walk
+ * stops at the first non-decorator so an earlier declaration's decorators
+ * never leak in (mirrors extractDecoratorsFor's sibling pass).
+ */
+function collectDecoratorNames(node) {
+    const names = [];
+    const nameOf = (dec) => {
+        for (let i = 0; i < dec.namedChildCount; i++) {
+            const child = dec.namedChild(i);
+            if (!child)
+                continue;
+            if (child.type === 'identifier')
+                return child.text;
+            if (child.type === 'call_expression') {
+                // `@StorageLink('theme')` / `@Extend(Text)` — the decorator name is
+                // the callee.
+                const fn = child.childForFieldName('function');
+                if (fn?.type === 'identifier')
+                    return fn.text;
+            }
+        }
+        return undefined;
+    };
+    for (let i = 0; i < node.namedChildCount; i++) {
+        const child = node.namedChild(i);
+        if (child?.type === 'decorator') {
+            const n = nameOf(child);
+            if (n)
+                names.push(n);
+        }
+    }
+    const parent = node.parent;
+    if (parent) {
+        // Find this node among the parent's named children by start offset
+        // (wrapper identity is not stable across navigation), then walk backwards.
+        const start = node.startIndex;
+        let idx = -1;
+        for (let i = 0; i < parent.namedChildCount; i++) {
+            const sib = parent.namedChild(i);
+            if (sib && sib.startIndex === start) {
+                idx = i;
+                break;
+            }
+        }
+        for (let i = idx - 1; i >= 0; i--) {
+            const sib = parent.namedChild(i);
+            if (!sib || sib.type !== 'decorator')
+                break;
+            const n = nameOf(sib);
+            if (n)
+                names.unshift(n);
+        }
+    }
+    return names.length > 0 ? names : undefined;
+}
+exports.arktsExtractor = {
+    ...typescript_1.typescriptExtractor,
+    // `@Component struct X { … }` — extractStruct handles it (kind `struct`,
+    // members extracted like class members, `this.m()` resolution and the
+    // class/struct containment gates in the name-matcher all apply as-is). The
+    // component-ness is preserved on the node's decorators (`Component`,
+    // `Entry`, `CustomDialog`, `Reusable`), captured by extractModifiers below.
+    structTypes: ['struct_declaration'],
+    // build()-DSL component instantiations are call sites: `TodoRow({...})`
+    // inside a parent's build() is the parent→child component edge, resolved by
+    // the ordinary call pipeline against the child's struct node. The arkts
+    // branch in extractCall also lifts each chained `.attr(...)` (emitted
+    // dot-prefixed so it can ONLY resolve to `@Extend`/`@Styles`/`@Builder`
+    // attribute helpers — see matchReference) and `.onXxx(this.handler)`
+    // method-reference bindings. `leading_dot_expression` is the detached-chain
+    // shape the grammar produces when a nested component's chain starts on the
+    // line after its closing `}` inside arkui_children.
+    callTypes: ['call_expression', 'arkui_component_expression', 'leading_dot_expression'],
+    // Surface ArkTS decorators on the node's `decorators` list (searchable, and
+    // the hook a future ArkUI state→build synthesizer keys off). Core paths
+    // already emit `decorates` REFERENCES for classes/methods/properties/
+    // functions; this hook is what puts the names on struct nodes too —
+    // extractStruct has no extractDecoratorsFor call, and node.decorators is
+    // only populated via extractModifiers (see createNode).
+    extractModifiers: (node) => {
+        if (!DECORATED_MEMBER_TYPES.has(node.type))
+            return undefined;
+        return collectDecoratorNames(node);
+    },
+};
+//# sourceMappingURL=arkts.js.map

package/lib/dist/extraction/languages/arkts.js.map

@@ -0,0 +1 @@
+{"version":3,"file":"arkts.js","sourceRoot":"","sources":["../../../src/extraction/languages/arkts.ts"],"names":[],"mappings":";;;AACA,6CAAmD;AAGnD;;;;;;;;;;;;;;;;;;;;;;;;GAwBG;AAEH,gFAAgF;AAChF,MAAM,sBAAsB,GAAG,IAAI,GAAG,CAAC;IACrC,oBAAoB;IACpB,yBAAyB;IACzB,mBAAmB;IACnB,sBAAsB;CACvB,CAAC,CAAC;AAEH;;;;;;;;GAQG;AACH,SAAS,qBAAqB,CAAC,IAAgB;IAC7C,MAAM,KAAK,GAAa,EAAE,CAAC;IAC3B,MAAM,MAAM,GAAG,CAAC,GAAe,EAAsB,EAAE;QACrD,KAAK,IAAI,CAAC,GAAG,CAAC,EAAE,CAAC,GAAG,GAAG,CAAC,eAAe,EAAE,CAAC,EAAE,EAAE,CAAC;YAC7C,MAAM,KAAK,GAAG,GAAG,CAAC,UAAU,CAAC,CAAC,CAAC,CAAC;YAChC,IAAI,CAAC,KAAK;gBAAE,SAAS;YACrB,IAAI,KAAK,CAAC,IAAI,KAAK,YAAY;gBAAE,OAAO,KAAK,CAAC,IAAI,CAAC;YACnD,IAAI,KAAK,CAAC,IAAI,KAAK,iBAAiB,EAAE,CAAC;gBACrC,oEAAoE;gBACpE,cAAc;gBACd,MAAM,EAAE,GAAG,KAAK,CAAC,iBAAiB,CAAC,UAAU,CAAC,CAAC;gBAC/C,IAAI,EAAE,EAAE,IAAI,KAAK,YAAY;oBAAE,OAAO,EAAE,CAAC,IAAI,CAAC;YAChD,CAAC;QACH,CAAC;QACD,OAAO,SAAS,CAAC;IACnB,CAAC,CAAC;IAEF,KAAK,IAAI,CAAC,GAAG,CAAC,EAAE,CAAC,GAAG,IAAI,CAAC,eAAe,EAAE,CAAC,EAAE,EAAE,CAAC;QAC9C,MAAM,KAAK,GAAG,IAAI,CAAC,UAAU,CAAC,CAAC,CAAC,CAAC;QACjC,IAAI,KAAK,EAAE,IAAI,KAAK,WAAW,EAAE,CAAC;YAChC,MAAM,CAAC,GAAG,MAAM,CAAC,KAAK,CAAC,CAAC;YACxB,IAAI,CAAC;gBAAE,KAAK,CAAC,IAAI,CAAC,CAAC,CAAC,CAAC;QACvB,CAAC;IACH,CAAC;IAED,MAAM,MAAM,GAAG,IAAI,CAAC,MAAM,CAAC;IAC3B,IAAI,MAAM,EAAE,CAAC;QACX,mEAAmE;QACnE,2EAA2E;QAC3E,MAAM,KAAK,GAAG,IAAI,CAAC,UAAU,CAAC;QAC9B,IAAI,GAAG,GAAG,CAAC,CAAC,CAAC;QACb,KAAK,IAAI,CAAC,GAAG,CAAC,EAAE,CAAC,GAAG,MAAM,CAAC,eAAe,EAAE,CAAC,EAAE,EAAE,CAAC;YAChD,MAAM,GAAG,GAAG,MAAM,CAAC,UAAU,CAAC,CAAC,CAAC,CAAC;YACjC,IAAI,GAAG,IAAI,GAAG,CAAC,UAAU,KAAK,KAAK,EAAE,CAAC;gBACpC,GAAG,GAAG,CAAC,CAAC;gBACR,MAAM;YACR,CAAC;QACH,CAAC;QACD,KAAK,IAAI,CAAC,GAAG,GAAG,GAAG,CAAC,EAAE,CAAC,IAAI,CAAC,EAAE,CAAC,EAAE,EAAE,CAAC;YAClC,MAAM,GAAG,GAAG,MAAM,CAAC,UAAU,CAAC,CAAC,CAAC,CAAC;YACjC,IAAI,CAAC,GAAG,IAAI,GAAG,CAAC,IAAI,KAAK,WAAW;gBAAE,MAAM;YAC5C,MAAM,CAAC,GAAG,MAAM,CAAC,GAAG,CAAC,CAAC;YACtB,IAAI,CAAC;gBAAE,KAAK,CAAC,OAAO,CAAC,CAAC,CAAC,CAAC;QAC1B,CAAC;IACH,CAAC;IAED,OAAO,KAAK,CAAC,MAAM,GAAG,CAAC,CAAC,CAAC,CAAC,KAAK,CAAC,CAAC,CAAC,SAAS,CAAC;AAC9C,CAAC;AAEY,QAAA,cAAc,GAAsB;IAC/C,GAAG,gCAAmB;IAEtB,yEAAyE;IACzE,sEAAsE;IACtE,2EAA2E;IAC3E,qEAAqE;IACrE,4EAA4E;IAC5E,WAAW,EAAE,CAAC,oBAAoB,CAAC;IAEnC,wEAAwE;IACxE,4EAA4E;IAC5E,wEAAwE;IACxE,sEAAsE;IACtE,wEAAwE;IACxE,qEAAqE;IACrE,4EAA4E;IAC5E,2EAA2E;IAC3E,oDAAoD;IACpD,SAAS,EAAE,CAAC,iBAAiB,EAAE,4BAA4B,EAAE,wBAAwB,CAAC;IAEtF,4EAA4E;IAC5E,wEAAwE;IACxE,sEAAsE;IACtE,oEAAoE;IACpE,yEAAyE;IACzE,wDAAwD;IACxD,gBAAgB,EAAE,CAAC,IAAI,EAAE,EAAE;QACzB,IAAI,CAAC,sBAAsB,CAAC,GAAG,CAAC,IAAI,CAAC,IAAI,CAAC;YAAE,OAAO,SAAS,CAAC;QAC7D,OAAO,qBAAqB,CAAC,IAAI,CAAC,CAAC;IACrC,CAAC;CACF,CAAC"}

package/lib/dist/extraction/languages/c-cpp.d.ts

@@ -47,5 +47,64 @@ export declare const cExtractor: LanguageExtractor;
  * so C's heavier use of `struct TAG var;` never reaches it.
  */
 export declare function blankCppExportMacros(source: string): string;
+export declare function blankCppInlineMacros(source: string): string;
+/**
+ * Universal fallback (any macro, no list) for a C/C++ function name still mangled
+ * because a macro we don't blank sat in front of the return type: `MACRO Ret
+ * name(…)` / `Ret MACRO name(…)` misparse so the return type is glued onto the
+ * name ("Ret name", "char_t* to_str(double v)"). Recover the real identifier —
+ * the token immediately before the parameter list (or the last token). This runs
+ * AFTER the curated pre-parse blank, so it only ever sees the residual tail that
+ * blanking didn't already fix cleanly (which also recovers the return type).
+ *
+ * Safe by construction: only touches an ALREADY-mangled name — one with an
+ * internal space that isn't a legit `operator …`/destructor — so a well-formed
+ * name is returned unchanged. Guarded against the two ways it could mis-pick:
+ * the `Ret (name)` parenthesized-name idiom (left as-is, ambiguous), and a token
+ * that is a bare primitive/keyword rather than a real identifier.
+ */
+export declare function recoverMangledCppName(name: string): string;
+export declare function blankMetalAttributes(source: string): string;
+/**
+ * Blank annotation-style macro invocations that decorate a declaration but carry
+ * NO terminating semicolon — the pervasive Unreal-Engine reflection markup
+ * (`UPROPERTY(...)`, `UFUNCTION(...)`, `UCLASS(...)`, `GENERATED_BODY()`,
+ * `UE_DEPRECATED_FORGAME(...)`, `DECLARE_DELEGATE_*(...)`, …) that sits on its
+ * own line right before a member/type. tree-sitter's C++ grammar doesn't know
+ * these are macros, so each one drops into error recovery; in a big reflected
+ * class (`CharacterMovementComponent.h` has ~240 of them) the errors accumulate
+ * until the enclosing `class_specifier` can't close and collapses into an ERROR
+ * node — the whole class definition, its members, and its `extends` edges vanish
+ * from the graph. Neither `blankCppExportMacros` (class-header export macros) nor
+ * `blankCppInlineMacros` (return-type inline specifiers) touches these in-body
+ * markup macros. Replacing each with equal-length spaces preserves every byte
+ * offset (so line/column stay exact) and the class then parses normally.
+ *
+ * Deliberately name-list-FREE — UE alone has hundreds of such macros and projects
+ * add their own — so it keys on structure, not a curated list, matched tightly to
+ * avoid touching legitimate C++:
+ *  - the macro must be the FIRST non-whitespace token on its line (`^[ \t]*`),
+ *    which is where declaration markup lives — so a macro used inside an
+ *    expression or condition (`if (CHECK(x))`, `x = MACRO(a) + b`) is never
+ *    matched (it isn't line-leading);
+ *  - the name must be ALL-CAPS (`[A-Z][A-Z0-9_]{2,}`), since ordinary
+ *    function/type names called at line start are lower/mixed case;
+ *  - the char after the balanced `(...)` must START A DECLARATION — a letter,
+ *    `_`, `~` (destructor), or `#` (a following directive). Declaration markup is
+ *    always followed by the thing it decorates (`UPROPERTY(...)\n float X;`,
+ *    `UE_DEPRECATED(...) UPROPERTY(...)`), whereas a statement call is followed by
+ *    `;` (`FOO(x);`), an init-list item by `,`/`{`, and an expression fragment by
+ *    an operator (`MAKE(a) + 1`) — all rejected. String/char literals inside the
+ *    args are skipped so an embedded `)` can't mis-close the balance.
+ *
+ * C++-only (wired into cppExtractor). A blanked macro inside a block comment is
+ * harmless (comments don't parse), and the rare line-leading no-semicolon
+ * ALL-CAPS call that isn't markup only loses that one annotation, never a whole
+ * class.
+ */
+export declare function blankCppAnnotationMacroCalls(source: string): string;
+export declare function blankCppApiPrefixMacros(source: string): string;
+export declare function blankCppInlineAnnotationMacros(source: string): string;
+export declare function blankCudaConstructs(source: string): string;
 export declare const cppExtractor: LanguageExtractor;
 //# sourceMappingURL=c-cpp.d.ts.map

package/lib/dist/extraction/languages/c-cpp.d.ts.map

@@ -1 +1 @@
-{"version":3,"file":"c-cpp.d.ts","sourceRoot":"","sources":["../../../src/extraction/languages/c-cpp.ts"],"names":[],"mappings":"AAEA,OAAO,KAAK,EAAE,iBAAiB,EAAE,MAAM,sBAAsB,CAAC;AAyD9D;;;;;;GAMG;AACH,wBAAgB,sBAAsB,CAAC,GAAG,EAAE,MAAM,GAAG,MAAM,GAAG,SAAS,CAkBtE;AAED;;;;;;;;;;;;;;GAcG;AACH,wBAAgB,oBAAoB,CAAC,IAAI,EAAE,MAAM,GAAG,MAAM,CAUzD;AAaD,eAAO,MAAM,UAAU,EAAE,iBAmDxB,CAAC;AAoCF;;;;;;;;;;;;;;;;;;;;;GAqBG;AACH,wBAAgB,oBAAoB,CAAC,MAAM,EAAE,MAAM,GAAG,MAAM,CAM3D;AAED,eAAO,MAAM,YAAY,EAAE,iBA6E1B,CAAC"}
+{"version":3,"file":"c-cpp.d.ts","sourceRoot":"","sources":["../../../src/extraction/languages/c-cpp.ts"],"names":[],"mappings":"AAEA,OAAO,KAAK,EAAE,iBAAiB,EAAE,MAAM,sBAAsB,CAAC;AAwG9D;;;;;;GAMG;AACH,wBAAgB,sBAAsB,CAAC,GAAG,EAAE,MAAM,GAAG,MAAM,GAAG,SAAS,CAkBtE;AAED;;;;;;;;;;;;;;GAcG;AACH,wBAAgB,oBAAoB,CAAC,IAAI,EAAE,MAAM,GAAG,MAAM,CAUzD;AAaD,eAAO,MAAM,UAAU,EAAE,iBAuDxB,CAAC;AAoCF;;;;;;;;;;;;;;;;;;;;;GAqBG;AACH,wBAAgB,oBAAoB,CAAC,MAAM,EAAE,MAAM,GAAG,MAAM,CAM3D;AA8ED,wBAAgB,oBAAoB,CAAC,MAAM,EAAE,MAAM,GAAG,MAAM,CAG3D;AAWD;;;;;;;;;;;;;;GAcG;AACH,wBAAgB,qBAAqB,CAAC,IAAI,EAAE,MAAM,GAAG,MAAM,CAQ1D;AAyBD,wBAAgB,oBAAoB,CAAC,MAAM,EAAE,MAAM,GAAG,MAAM,CAG3D;AAED;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;GAoCG;AACH,wBAAgB,4BAA4B,CAAC,MAAM,EAAE,MAAM,GAAG,MAAM,CAwCnE;AA4BD,wBAAgB,uBAAuB,CAAC,MAAM,EAAE,MAAM,GAAG,MAAM,CAG9D;AAuBD,wBAAgB,8BAA8B,CAAC,MAAM,EAAE,MAAM,GAAG,MAAM,CAiCrE;AAiDD,wBAAgB,mBAAmB,CAAC,MAAM,EAAE,MAAM,GAAG,MAAM,CAmB1D;AA2CD,eAAO,MAAM,YAAY,EAAE,iBAsF1B,CAAC"}