|
15 | 15 | result.save('output/benchmark.json') |
16 | 16 | """ |
17 | 17 |
|
18 | | -import re |
19 | 18 | import sys |
20 | 19 | import time |
21 | 20 | from pathlib import Path |
22 | | -from typing import Dict, List, Optional, Tuple, Callable |
23 | | -from concurrent.futures import ThreadPoolExecutor, as_completed |
24 | | -from dataclasses import dataclass |
| 21 | +from typing import List, Optional |
25 | 22 |
|
26 | 23 | from ..analyzer import analyze_project |
27 | 24 | from ..llm_clients import get_client, BaseLLMClient |
28 | | -from ..reproduction import extract_code_block |
29 | 25 | from ..utils import estimate_tokens |
30 | 26 | from ..metrics import ReproductionMetrics |
31 | | -from ..terminal import render, ShellRenderer |
| 27 | +from ..terminal import render |
32 | 28 |
|
33 | 29 | from .results import ( |
34 | 30 | BenchmarkResult, BenchmarkConfig, FileResult, |
35 | 31 | FunctionResult, FormatResult |
36 | 32 | ) |
37 | 33 | from .common import ( |
38 | | - generate_spec, generate_spec_token, create_single_project, |
39 | | - get_token_reproduction_prompt, get_simple_reproduction_prompt |
| 34 | + generate_spec_token, create_single_project, |
| 35 | + get_token_reproduction_prompt |
40 | 36 | ) |
41 | 37 |
|
42 | 38 |
|
@@ -605,7 +601,6 @@ def _test_function( |
605 | 601 | result.similarity = SequenceMatcher(None, orig_norm, repr_norm).ratio() * 100 |
606 | 602 |
|
607 | 603 | if verbose: |
608 | | - status = "✓" if result.similarity > 50 else "○" |
609 | 604 | syntax = "S✓" if result.syntax_ok else "S✗" |
610 | 605 | print(f" {func.name}: {result.similarity:.1f}% {syntax}") |
611 | 606 |
|
|
0 commit comments