codegraph/__tests__/generated-detection.test.ts

/**
 * Regression coverage for the generated-file detector that drives
 * symbol-disambiguation down-ranking. Locked here because the suffix
 * list is a contract: if a future edit drops `.pb.go`, the cosmos-sdk
 * trace endpoint regresses to the gRPC stub (see
 * `project_go_multi_module_audit` memory + the audit in #N/A).
 *
 * The content-header half (#1500) is a second contract: the marker table is
 * precision-first, because a false positive silently demotes hand-written code
 * in EVERY ranking path. Measured on a shallow clone of kubernetes/client-go
 * (2,453 Go files): the path check flags 0, the content check flags 2,001 —
 * exactly the set that greps to the canonical banner, no false positives and
 * no misses. Every one of those files has an ordinary name.
 */

import { describe, it, expect } from 'vitest';
import * as fs from 'fs';
import * as path from 'path';
import {
  isGeneratedFile,
  hasGeneratedHeader,
  detectGeneratedFile,
  isMinifiedContent,
} from '../src/extraction/generated-detection';

describe('isGeneratedFile', () => {
  it('classifies Go protobuf / gRPC / pulsar / mock outputs as generated', () => {
    expect(isGeneratedFile('api/cosmos/bank/v1beta1/tx_grpc.pb.go')).toBe(true);
    expect(isGeneratedFile('x/bank/types/tx.pb.go')).toBe(true);
    expect(isGeneratedFile('api/cosmos/bank/v1beta1/tx.pulsar.go')).toBe(true);
    // cosmos-sdk uses `<base>_mocks.go`; mockgen's default is `mock_<src>.go`;
    // many projects use `<base>_mock.go`. All three are mockgen output.
    expect(isGeneratedFile('x/auth/testutil/expected_keepers_mocks.go')).toBe(true);
    expect(isGeneratedFile('internal/foo_mock.go')).toBe(true);
    expect(isGeneratedFile('mock_keeper.go')).toBe(true);
  });

  it('does not flag the hand-written keeper as generated', () => {
    expect(isGeneratedFile('x/bank/keeper/msg_server.go')).toBe(false);
    expect(isGeneratedFile('x/bank/keeper/send.go')).toBe(false);
  });

  it('catches common cross-language codegen suffixes', () => {
    expect(isGeneratedFile('app/foo.generated.ts')).toBe(true);
    expect(isGeneratedFile('app/foo.generated.tsx')).toBe(true);
    expect(isGeneratedFile('proto/bar_pb2.py')).toBe(true);
    expect(isGeneratedFile('proto/bar_pb2_grpc.py')).toBe(true);
    expect(isGeneratedFile('lib/baz.pb.cc')).toBe(true);
    expect(isGeneratedFile('lib/baz.pb.h')).toBe(true);
    expect(isGeneratedFile('lib/quux.g.dart')).toBe(true);
    expect(isGeneratedFile('lib/quux.freezed.dart')).toBe(true);
  });

  it('leaves ordinary source files alone', () => {
    expect(isGeneratedFile('src/index.ts')).toBe(false);
    expect(isGeneratedFile('src/components/Foo.tsx')).toBe(false);
    expect(isGeneratedFile('lib/main.dart')).toBe(false);
    expect(isGeneratedFile('cmd/server/main.go')).toBe(false);
    expect(isGeneratedFile('app/db.py')).toBe(false);
  });
});

describe('hasGeneratedHeader — per-marker coverage (#1500)', () => {
  // One case per banner the marker table claims to recognize. Each string is
  // the real thing a generator emits, not a paraphrase — if a regex is
  // narrowed, the case that motivated it fails by name.
  const GENERATED: ReadonlyArray<[string, string]> = [
    [
      'Go — the #1500 case: ordinary filename, banner below the package clause',
      'package payroll\n\n// Code generated by fkit. DO NOT EDIT.\n\nimport "context"\n\nfunc CreatePayroll(ctx context.Context) error { return nil }\n',
    ],
    [
      'Go — protoc-gen-go',
      '// Code generated by protoc-gen-go. DO NOT EDIT.\n// versions:\n//   protoc-gen-go v1.28.0\n\npackage pb\n',
    ],
    [
      'Go — banner under build tags',
      '//go:build !windows\n// +build !windows\n\n// Code generated by MockGen. DO NOT EDIT.\npackage mocks\n',
    ],
    [
      'Go — banner under an Apache-2.0 license preamble',
      '// Copyright 2021 The Foo Authors.\n// Licensed under the Apache License, Version 2.0 (the "License");\n// you may not use this file except in compliance with the License.\n//\n//     http://www.apache.org/licenses/LICENSE-2.0\n//\n// Unless required by applicable law or agreed to in writing, software\n// distributed under the License is distributed on an "AS IS" BASIS.\n\n// Code generated by sqlc. DO NOT EDIT.\n// source: query.sql\n\npackage db\n',
    ],
    [
      'protoc — Java banner ("DO NOT EDIT!")',
      '// Generated by the protocol buffer compiler.  DO NOT EDIT!\n// source: foo.proto\n\npackage com.example;\n',
    ],
    [
      'protoc — Python banner behind a coding cookie',
      '# -*- coding: utf-8 -*-\n# Generated by the protocol buffer compiler.  DO NOT EDIT!\n# source: foo.proto\n',
    ],
    [
      'C# — Roslyn / designer <auto-generated> block',
      '//------------------------------------------------------------------------------\n// <auto-generated>\n//     This code was generated by a tool.\n// </auto-generated>\n//------------------------------------------------------------------------------\n',
    ],
    ['C# — EF self-closing <auto-generated />', '// <auto-generated />\nusing System;\n'],
    [
      'JS — Meta/Relay @generated with a SignedSource',
      '/**\n * @generated SignedSource<<0123456789abcdef0123456789abcdef>>\n * @flow\n */\n',
    ],
    [
      'TS — protobuf-es / Buf @generated',
      '// @generated by protoc-gen-es v1.2.0 with parameter "target=ts"\n// @generated from file foo.proto (package example, syntax proto3)\n',
    ],
    [
      'Thrift — "Autogenerated by Thrift Compiler"',
      '/**\n * Autogenerated by Thrift Compiler (0.14.1)\n *\n * DO NOT EDIT UNLESS YOU ARE SURE THAT YOU KNOW WHAT YOU ARE DOING\n */\n',
    ],
    [
      'OpenAPI Generator — "This class is auto generated by"',
      '/*\n * Pet Store API\n *\n * NOTE: This class is auto generated by OpenAPI Generator (https://openapi-generator.tech).\n * Do not edit the class manually.\n */\n',
    ],
    [
      'FlatBuffers — "automatically generated by … do not modify"',
      '// automatically generated by the FlatBuffers compiler, do not modify\n\npackage MyGame;\n',
    ],
    [
      'Rust — bindgen block comment',
      '/* automatically generated by rust-bindgen 0.59.2 */\n\npub const FOO: u32 = 1;\n',
    ],
    ['ANTLR — "Generated from … -- DO NOT EDIT"', '// Generated from Expr.g4 by ANTLR 4.9.2 -- DO NOT EDIT\npackage parser;\n'],
    [
      'Wrangler — "Generated by Wrangler by running `wrangler types`" (CG-25)',
      '/* eslint-disable */\n// Generated by Wrangler by running `wrangler types` (hash: adcfde101dd7d9077590b6b39d3eaf8d)\n// Runtime types generated with workerd@1.20260708.1 2026-07-12\ndeclare namespace Cloudflare {\n\tinterface Env {}\n}\n',
    ],
    [
      'the same "regenerate by running" shape from an in-house CLI',
      '# Generated by ./scripts/schema-gen.py by running `make schema`\n\nfrom typing import Any\n',
    ],
    [
      'banner on an unprefixed line INSIDE a block comment',
      '/*\n   Code generated by ent. DO NOT EDIT.\n*/\npackage ent\n',
    ],
    [
      'Python — banner inside a module docstring',
      '"""Generated by the protocol buffer compiler.  DO NOT EDIT!"""\nimport sys\n',
    ],
    ['YAML/shell — "#" comment leader', '# This file is generated by kustomize. Do not edit.\napiVersion: v1\n'],
    ['SQL — "--" comment leader', '-- Code generated by sqlc. DO NOT EDIT.\nCREATE TABLE foo (id INT);\n'],
    ['HTML/XML — "<!--" comment leader', '<!-- Autogenerated by docgen. Do not edit. -->\n<html></html>\n'],
  ];

  it.each(GENERATED)('flags: %s', (_label, source) => {
    expect(hasGeneratedHeader(source)).toBe(true);
  });

  // Precision cases. Each is a shape that a looser marker table WOULD flag.
  const HAND_WRITTEN: ReadonlyArray<[string, string]> = [
    [
      'ordinary Go source',
      'package keeper\n\nimport "context"\n\n// SendCoins moves coins between accounts.\nfunc (k Keeper) SendCoins(ctx context.Context) error { return nil }\n',
    ],
    [
      'a generator\'s own source, which merely talks about generating',
      '// This package generates SQL migrations from the schema.\n// The generated output lives under db/migrations.\npackage gen\n',
    ],
    [
      'prose using "automatically generated" without naming a tool',
      '"""Report builder.\n\nThe summary table is automatically generated at runtime from the\nrows below; callers should not edit it in place.\n"""\n',
    ],
    [
      'a generator holding the banner as a string constant in its BODY',
      'package main\n\n// Package main implements the fkit CRUD generator.\n\nimport "fmt"\n\nfunc header() string {\n\treturn "// Code generated by fkit. DO NOT EDIT."\n}\n',
    ],
    ['an email address that happens to contain "@generated"', '// Contact: build@generated.example.com for issues.\npackage main\n'],
    ['"DO NOT EDIT" with no generation claim', '// DO NOT EDIT THIS FILE BY HAND — run `make fmt` instead.\npackage main\n'],
    [
      'prose: bare "generated by" naming no tool and no reproduction command (CG-25)',
      '// The table below is generated by the build at runtime, so the\n// literal values here are only a fallback.\npackage main\n',
    ],
    [
      'prose: "generated by running …" — one "by" clause, not the Wrangler shape (CG-25)',
      '// The nightly summary is generated by running the ETL job against\n// yesterday\'s partition.\npackage main\n',
    ],
    ['empty file', ''],
  ];

  it.each(HAND_WRITTEN)('does not flag: %s', (_label, source) => {
    expect(hasGeneratedHeader(source)).toBe(false);
  });

  it('only looks at the header — a banner buried 80 lines down is not a banner', () => {
    const filler = Array.from({ length: 80 }, (_, i) => `// filler line ${i}`).join('\n');
    expect(hasGeneratedHeader(`${filler}\n// Code generated by foo. DO NOT EDIT.\npackage main\n`)).toBe(false);
    // …but the same banner within the window is caught.
    const shortFiller = Array.from({ length: 20 }, (_, i) => `// filler line ${i}`).join('\n');
    expect(hasGeneratedHeader(`${shortFiller}\n// Code generated by foo. DO NOT EDIT.\npackage main\n`)).toBe(true);
  });

  it('requires a comment line — the same words in executable code are not a banner', () => {
    // No comment leader, no open block: this is a bare statement.
    expect(hasGeneratedHeader('const banner = "Code generated by tool. DO NOT EDIT.";\n')).toBe(false);
  });

  it('does not classify the detector module itself (the pattern table must stay below the header window)', () => {
    const self = fs.readFileSync(
      path.join(__dirname, '..', 'src', 'extraction', 'generated-detection.ts'),
      'utf-8'
    );
    expect(hasGeneratedHeader(self)).toBe(false);
  });
});

describe('detectGeneratedFile — the union the indexer persists', () => {
  it('is true when only the PATH says so', () => {
    expect(detectGeneratedFile('x/bank/types/tx.pb.go', 'package types\n')).toBe(true);
  });

  it('is true when only the CONTENT says so — the #1500 acceptance case', () => {
    // A Go file named `payroll.go` sitting beside hand-written workflow
    // use-cases. Nothing in the path gives it away.
    expect(
      detectGeneratedFile('internal/payroll/payroll.go', 'package payroll\n\n// Code generated by fkit. DO NOT EDIT.\n\nfunc Create() {}\n')
    ).toBe(true);
    expect(isGeneratedFile('internal/payroll/payroll.go')).toBe(false);
  });

  it('is false for a hand-written file with an ordinary name', () => {
    expect(
      detectGeneratedFile('internal/payroll/workflow.go', 'package payroll\n\n// RunPayrollWorkflow drives the monthly run.\nfunc RunPayrollWorkflow() {}\n')
    ).toBe(false);
  });
});

describe('isMinifiedContent — a bundle not named .min.js', () => {
  const bundle = Array.from({ length: 300 }, (_, i) => `function f${i}(e){return n(e,${i})+t(e)}`).join(';');

  it('recognizes a minified script by its enormous code lines', () => {
    expect(isMinifiedContent('docs/assets/bundle.js', bundle)).toBe(true);
    expect(isMinifiedContent('site/app.mjs', bundle)).toBe(true);
    expect(detectGeneratedFile('docs/assets/bundle.js', bundle)).toBe(true);
  });

  it('recognizes a readable webpack build by its module loader, and `-min.js` by name', () => {
    const webpack = `/*! lib */\n(function(modules) {\n  function __webpack_require__(moduleId) {\n    return modules[moduleId];\n  }\n${'  var x = 1;\n'.repeat(400)}})([]);\n`;
    expect(isMinifiedContent('assets/js/syntaxhighlighter.js', webpack)).toBe(true);
    expect(isGeneratedFile('vendor/underscore/underscore-min.js')).toBe(true);
  });

  it('leaves an ordinary file with one long string literal alone', () => {
    const fixture = [
      'export function decode(input) {',
      '  return atob(input);',
      '}',
      `export const LOGO = "${'QUJD'.repeat(4000)}";`,
      'export function size() { return LOGO.length; }',
    ].join('\n');
    expect(isMinifiedContent('src/logo.js', fixture)).toBe(false);
  });

  it('leaves hand-written code, TypeScript and short files alone', () => {
    const code = Array.from({ length: 400 }, (_, i) => `export function f${i}(e) {\n  return e + ${i};\n}`).join('\n');
    expect(isMinifiedContent('src/code.js', code)).toBe(false);
    expect(isMinifiedContent('src/bundle.ts', bundle)).toBe(false);
    expect(isMinifiedContent('src/tiny.js', 'function n(e){return e};function t(e){return n(e)}')).toBe(false);
  });
});