diff --git a/CHANGELOG.md b/CHANGELOG.md index 1c4652d..1864f8e 100644 --- a/CHANGELOG.md +++ b/CHANGELOG.md @@ -15,6 +15,7 @@ and adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0.html). - C++ methods that return a reference, and user-defined conversion operators, are now indexed under their correct names. An inline getter like `const FGameplayTagContainer& GetActiveTags() const` — everywhere in Unreal Engine headers — was indexed as `& GetActiveTags() const` instead of `GetActiveTags`, and a conversion operator like `operator EALSMovementState() const` kept its trailing `() const` instead of reading `operator EALSMovementState`. In both cases the garbled name meant you couldn't find the symbol by name and its callers weren't linked. Both now read cleanly, matching how pointer-returning and value-returning methods already worked. (#1096) - C++ functions written with an inline-specifier macro before the return type are now indexed correctly. In Unreal Engine, inline helpers are commonly written `FORCEINLINE FString GetEnumerationToString(...)`; the `FORCEINLINE` macro made the parser read the return type as part of the function's name (`FString GetEnumerationToString` instead of `GetEnumerationToString`) and lose the real return type, so the function couldn't be found by name and its callers weren't linked. CodeGraph now recognizes the standard Unreal inline macros (`FORCEINLINE`, `FORCENOINLINE`, `FORCEINLINE_DEBUGGABLE`), so both the name and the return type are captured. (#1100) - The same function-name recovery now covers inline macros from common third-party C++ libraries, not just Unreal Engine — including pugixml (`PUGI__FN`, `PUGIXML_FUNCTION`), Godot (`_FORCE_INLINE_`), Boost (`BOOST_FORCEINLINE`), and generic `ALWAYS_INLINE` / `FORCE_INLINE`. Functions decorated with these are now indexed under their real names. On a large Unreal project vendoring these libraries this cleaned up the large majority of remaining function-name garbling. (#1101) +- C++ function names are now recovered even when decorated with a macro CodeGraph doesn't specifically know about. A function written `SOME_LIBRARY_MACRO ReturnType doWork(...)` previously had the macro or return type absorbed into its name whenever the macro wasn't one CodeGraph recognized; now the real name (`doWork`) is recovered regardless of the macro, so it's findable and its callers link — no per-library configuration needed. The recognized-macro list was also broadened (Qt, Folly, Abseil, LLVM, V8, Eigen, rapidjson) so those additionally capture the return type. This only ever cleans up an already-garbled name and is limited to C and C++, so ordinary names — and languages like Kotlin and Scala where identifiers can legitimately contain spaces — are unaffected. (#1102) ## [1.1.6] - 2026-06-30 diff --git a/__tests__/extraction.test.ts b/__tests__/extraction.test.ts index e2e7f03..4c1ca68 100644 --- a/__tests__/extraction.test.ts +++ b/__tests__/extraction.test.ts @@ -11,7 +11,7 @@ import * as os from 'os'; import { CodeGraph } from '../src'; import { extractFromSource, scanDirectory, buildDefaultIgnore, discoverEmbeddedRepoRoots, buildScopeIgnore } from '../src/extraction'; import { detectLanguage, isLanguageSupported, getSupportedLanguages, initGrammars, loadAllGrammars, isSourceFile } from '../src/extraction/grammars'; -import { stripCppTemplateArgs, blankCppExportMacros, blankCppInlineMacros } from '../src/extraction/languages/c-cpp'; +import { stripCppTemplateArgs, blankCppExportMacros, blankCppInlineMacros, recoverMangledCppName } from '../src/extraction/languages/c-cpp'; import { normalizePath } from '../src/utils'; beforeAll(async () => { @@ -2995,6 +2995,61 @@ class APXCharacter { // the one real definition }); }); + describe('C++ universal macro-mangled name recovery', () => { + // Curated pre-parse blanking can't list every library's inline macro, so a + // post-parse salvage recovers the real function name from ANY leftover + // `MACRO Ret name(…)` mangle — no list needed. It only ever touches an + // already-mangled name, so it can't corrupt a clean one. + const namesOf = (code: string, file = 's.cpp') => + extractFromSource(file, code).nodes + .filter((n) => n.kind === 'method' || n.kind === 'function') + .map((n) => n.name); + + it('recovers the name from a completely unknown macro (no list entry)', () => { + expect(namesOf('WEBKIT_EXPORT WTFString computeThing(int x) { return H(x); }')).toContain('computeThing'); + expect(namesOf('SOMELIB_INLINE MyResult doWork(int x) { return H(x); }')).toContain('doWork'); + expect(namesOf('MZ_FORCEINLINE char_t* to_str(double v) { return H(v); }')).toContain('to_str'); + }); + + it('recoverMangledCppName only touches already-mangled names, with guards', () => { + // Recovered: + expect(recoverMangledCppName('WTFString computeThing')).toBe('computeThing'); + expect(recoverMangledCppName('char_t* to_str(double v)')).toBe('to_str'); + expect(recoverMangledCppName('unspecified_bool_type() const')).toBe('unspecified_bool_type'); + // Left unchanged — clean names, operators, destructors, the `Ret (name)` + // idiom, and non-identifier tails: + expect(recoverMangledCppName('computeThing')).toBe('computeThing'); + expect(recoverMangledCppName('operator EALSMovementState')).toBe('operator EALSMovementState'); + expect(recoverMangledCppName('~Widget')).toBe('~Widget'); + expect(recoverMangledCppName('bool (likely)')).toBe('bool (likely)'); + expect(recoverMangledCppName('void (free)')).toBe('void (free)'); + expect(recoverMangledCppName('QDockWidget *')).toBe('QDockWidget *'); + }); + + it('does not disturb clean C++ names or non-C++ (Kotlin backtick) names', () => { + expect(namesOf('int foo(int x) { return x; }')).toEqual(['foo']); + // Kotlin backtick identifiers legitimately contain spaces; the salvage is + // C/C++-only, so they are untouched. + const kt = extractFromSource('T.kt', 'class T {\n fun `decode simple cert`() { }\n}').nodes + .filter((n) => n.kind === 'method' || n.kind === 'function') + .map((n) => n.name); + expect(kt).toContain('`decode simple cert`'); + }); + + it('curated list now also covers Qt / Folly / Abseil / LLVM / V8 / Eigen / rapidjson (full recovery)', () => { + const info = (c: string) => + extractFromSource('x.cpp', c).nodes + .filter((n) => n.kind === 'method' || n.kind === 'function') + .map((n) => ({ name: n.name, ret: n.returnType })); + expect(info('FOLLY_ALWAYS_INLINE Str f(int x) { return H(x); }')).toEqual([{ name: 'f', ret: 'Str' }]); + expect(namesOf('Q_INVOKABLE void onClicked() { H(); }')).toContain('onClicked'); + expect(namesOf('ABSL_ATTRIBUTE_ALWAYS_INLINE int hash(int x) { return H(x); }')).toContain('hash'); + expect(namesOf('EIGEN_STRONG_INLINE Scalar dot(const V& v) { return H(v); }')).toContain('dot'); + expect(namesOf('V8_INLINE MaybeLocal Get(int i) { return H(i); }')).toContain('Get'); + expect(namesOf('RAPIDJSON_FORCEINLINE bool Parse(const char* s) { return H(s); }')).toContain('Parse'); + }); + }); + describe('C++ templated base-class inheritance (#1043)', () => { // Inheriting from a template (`class D : public Base`) recorded the base // ref as the full instantiation `Base`, which never name-matched the diff --git a/src/extraction/languages/c-cpp.ts b/src/extraction/languages/c-cpp.ts index 8aae0de..35f2754 100644 --- a/src/extraction/languages/c-cpp.ts +++ b/src/extraction/languages/c-cpp.ts @@ -123,6 +123,8 @@ function extractCppReturnType(node: SyntaxNode, source: string): string | undefi } export const cExtractor: LanguageExtractor = { + // Universal net: recover a real name from any macro-mangled function name. + recoverMangledName: recoverMangledCppName, functionTypes: ['function_definition'], classTypes: [], methodTypes: [], @@ -275,6 +277,15 @@ const CPP_INLINE_MACROS = [ '_ALWAYS_INLINE_', '_FORCE_INLINE_', // Boost 'BOOST_FORCEINLINE', 'BOOST_NOINLINE', + // Qt (per-method markers + inline) + 'Q_INVOKABLE', 'Q_SCRIPTABLE', 'Q_ALWAYS_INLINE', 'Q_SLOT', 'Q_SIGNAL', + // Folly / Abseil / LLVM / V8 / Eigen / rapidjson + 'FOLLY_ALWAYS_INLINE', 'FOLLY_NOINLINE', + 'ABSL_ATTRIBUTE_ALWAYS_INLINE', 'ABSL_ATTRIBUTE_NOINLINE', + 'LLVM_ATTRIBUTE_ALWAYS_INLINE', 'LLVM_ATTRIBUTE_NOINLINE', + 'V8_INLINE', 'V8_NOINLINE', + 'EIGEN_STRONG_INLINE', 'EIGEN_ALWAYS_INLINE', 'EIGEN_DEVICE_FUNC', + 'RAPIDJSON_FORCEINLINE', // Common cross-ecosystem inline/attribute hints 'ALWAYS_INLINE', 'FORCE_INLINE', 'NOINLINE', ] as const; @@ -288,6 +299,40 @@ export function blankCppInlineMacros(source: string): string { return source.replace(CPP_INLINE_MACRO_RE, (m) => ' '.repeat(m.length)); } +// Bare C/C++ type/qualifier tokens that must never be taken as a recovered +// function name (guards `recoverMangledCppName` against the `Ret (name)` idiom, +// where the token before the params is the return type, not the name). +const CPP_PRIMITIVE_NAMES = new Set([ + 'bool', 'void', 'int', 'char', 'short', 'long', 'float', 'double', 'unsigned', + 'signed', 'wchar_t', 'char8_t', 'char16_t', 'char32_t', 'char_t', 'size_t', + 'auto', 'const', 'struct', 'class', 'enum', 'union', 'typename', +]); + +/** + * 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 function recoverMangledCppName(name: string): string { + if (!/\s/.test(name) || name.startsWith('operator') || name.startsWith('~')) return name; + if (/^\S+\s+\([A-Za-z_]\w*\)/.test(name)) return name; // `Ret (name)` idiom — leave alone + const beforeParams = name.includes('(') ? name.slice(0, name.indexOf('(')) : name; + const tokens = beforeParams.trim().split(/\s+/); + const candidate = tokens[tokens.length - 1]; + if (!candidate || !/^[A-Za-z_]\w*$/.test(candidate) || CPP_PRIMITIVE_NAMES.has(candidate)) return name; + return candidate; +} + /** C/C++ source pre-processing before tree-sitter: recover both macro-annotated * class definitions and macro-prefixed function definitions. Offset-preserving. */ function preParseCppSource(source: string): string { @@ -299,6 +344,8 @@ export const cppExtractor: LanguageExtractor = { // #1061/#946) and macro-prefixed functions (`FORCEINLINE FString Foo()`, #1093 // follow-up) that tree-sitter otherwise misparses. preParse: preParseCppSource, + // Universal net for any macro the curated blank list misses. + recoverMangledName: recoverMangledCppName, functionTypes: ['function_definition'], classTypes: ['class_specifier'], // A bodiless `class_specifier` is a forward declaration (`class Foo;`) or an diff --git a/src/extraction/tree-sitter-types.ts b/src/extraction/tree-sitter-types.ts index 2b0761a..cf65ba9 100644 --- a/src/extraction/tree-sitter-types.ts +++ b/src/extraction/tree-sitter-types.ts @@ -133,6 +133,16 @@ export interface LanguageExtractor { /** Override symbol name extraction (e.g. ObjC multi-part selectors). */ resolveName?: (node: SyntaxNode, source: string) => string | undefined; + /** + * Post-process an already-extracted name to recover a real identifier from a + * name still mangled by a macro the pre-parse didn't blank (C/C++: + * `MACRO Ret name(` misparses to the name "Ret name"). Applied to every name + * this extractor produces, so it MUST be a no-op on a well-formed name — only + * C/C++ set it, because a mangled name there is unambiguous (an internal space), + * whereas e.g. Kotlin/Scala backtick identifiers legitimately contain spaces. + */ + recoverMangledName?: (name: string) => string; + /** Extract property name when the generic name walk fails (e.g. ObjC @property). */ extractPropertyName?: (node: SyntaxNode, source: string) => string | null; diff --git a/src/extraction/tree-sitter.ts b/src/extraction/tree-sitter.ts index 695c467..fc49784 100644 --- a/src/extraction/tree-sitter.ts +++ b/src/extraction/tree-sitter.ts @@ -63,6 +63,14 @@ const VUE_STORE_FILE_SIGNAL = /\bdefineStore\b|\bcreateStore\b|\bVuex\b|\bmutati * Extract the name from a node based on language */ function extractName(node: SyntaxNode, source: string, extractor: LanguageExtractor): string { + const name = extractNameRaw(node, source, extractor); + // Universal fallback: recover a real identifier from a name still mangled by a + // macro the pre-parse didn't blank (C/C++ only — see recoverMangledName). A + // no-op on well-formed names, so a clean name is never altered. + return extractor.recoverMangledName ? extractor.recoverMangledName(name) : name; +} + +function extractNameRaw(node: SyntaxNode, source: string, extractor: LanguageExtractor): string { const hookName = extractor.resolveName?.(node, source); if (hookName) return hookName;