File size: 9,857 Bytes
148b631
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
"""
test_cases.py - Test cases for code completion validation.

Defines specific tests to evaluate if RippleGPT understands
hierarchical code structures.
"""

from dataclasses import dataclass
from typing import List, Callable, Optional
import re


@dataclass
class TestCase:
    """Represents a code completion test case."""
    name: str
    category: str
    prompt: str
    expected_patterns: List[str]  # Regex patterns that MUST appear in output
    forbidden_patterns: List[str] = None  # Patterns that MUST NOT appear
    max_tokens: int = 50
    description: str = ""
    
    def __post_init__(self):
        if self.forbidden_patterns is None:
            self.forbidden_patterns = []


# =============================================================================
# CATEGORY 1: BRACKET CLOSING
# Tests if the model can close parentheses, braces, and brackets
# =============================================================================

BRACKET_TESTS = [
    TestCase(
        name="simple_parenthesis",
        category="brackets",
        prompt="def hello(name",
        expected_patterns=[r"\)"],  # Should close parenthesis
        max_tokens=20,
        description="Should close simple function parenthesis"
    ),
    TestCase(
        name="multiple_args",
        category="brackets",
        prompt="def calculate(a, b, c",
        expected_patterns=[r"\)", r":"],  # Should close and add ':'
        max_tokens=20,
        description="Should close parenthesis with multiple arguments"
    ),
    TestCase(
        name="nested_parenthesis",
        category="brackets",
        prompt="result = sum(range(10",
        expected_patterns=[r"\)\)"],  # Should close both
        max_tokens=20,
        description="Should close nested parentheses"
    ),
    TestCase(
        name="list_bracket",
        category="brackets",
        prompt="items = [1, 2, 3",
        expected_patterns=[r"\]"],
        max_tokens=20,
        description="Should close list bracket"
    ),
    TestCase(
        name="dict_brace",
        category="brackets",
        prompt='data = {"name": "test"',
        expected_patterns=[r"\}"],
        max_tokens=20,
        description="Should close dictionary brace"
    ),
    TestCase(
        name="function_call_chain",
        category="brackets",
        prompt="text.strip().lower(",
        expected_patterns=[r"\)"],
        max_tokens=20,
        description="Should close parenthesis in method chain"
    ),
]

# =============================================================================
# CATEGORY 2: PYTHON INDENTATION
# Tests if the model maintains correct indentation after blocks
# =============================================================================

INDENTATION_TESTS = [
    TestCase(
        name="if_indent",
        category="indentation",
        prompt="if x > 0:\n",
        expected_patterns=[r"^    \S", r"^\t\S"],  # Should indent 4 spaces or tab
        max_tokens=30,
        description="Should indent after if statement"
    ),
    TestCase(
        name="for_indent",
        category="indentation",
        prompt="for i in range(10):\n",
        expected_patterns=[r"    \S"],
        max_tokens=30,
        description="Should indent after for loop"
    ),
    TestCase(
        name="def_indent",
        category="indentation",
        prompt="def process(data):\n",
        expected_patterns=[r"    "],
        max_tokens=30,
        description="Should indent function body"
    ),
    TestCase(
        name="class_indent",
        category="indentation",
        prompt="class MyClass:\n",
        expected_patterns=[r"    "],
        max_tokens=30,
        description="Should indent class body"
    ),
    TestCase(
        name="nested_indent",
        category="indentation",
        prompt="def foo():\n    if True:\n",
        expected_patterns=[r"        \S"],  # 8 spaces (double indentation)
        max_tokens=30,
        description="Should maintain nested indentation"
    ),
    TestCase(
        name="try_except_indent",
        category="indentation",
        prompt="try:\n    x = 1\nexcept:\n",
        expected_patterns=[r"    "],
        max_tokens=30,
        description="Should indent except block"
    ),
]

# =============================================================================
# CATEGORY 3: CODE STRUCTURE
# Tests if the model understands common code patterns
# =============================================================================

STRUCTURE_TESTS = [
    TestCase(
        name="return_statement",
        category="structure",
        prompt="def add(a, b):\n    return a",
        expected_patterns=[r"\+\s*b", r"a \+ b"],
        max_tokens=20,
        description="Should complete addition operation"
    ),
    TestCase(
        name="for_loop_pattern",
        category="structure",
        prompt="for i in range(",
        expected_patterns=[r"\d+\)"],  # Number followed by )
        max_tokens=20,
        description="Should complete range() with number"
    ),
    TestCase(
        name="import_statement",
        category="structure",
        prompt="import os\nimport sys\nimport ",
        expected_patterns=[r"[a-z]+"],  # Module name
        forbidden_patterns=[r"^\d"],  # Must not start with digit
        max_tokens=20,
        description="Should suggest valid module name"
    ),
    TestCase(
        name="list_comprehension",
        category="structure",
        prompt="squares = [x**2 for x in ",
        expected_patterns=[r"range\(|list\(|\["],
        max_tokens=30,
        description="Should complete list comprehension"
    ),
    TestCase(
        name="method_definition",
        category="structure",
        prompt="class Dog:\n    def __init__(self",
        expected_patterns=[r"\)", r":"],
        max_tokens=30,
        description="Should complete __init__ definition"
    ),
    TestCase(
        name="conditional_else",
        category="structure",
        prompt="if condition:\n    do_something()\nelse",
        expected_patterns=[r":"],
        max_tokens=20,
        description="Should add ':' after else"
    ),
]

# =============================================================================
# CATEGORY 4: LONG CONTEXT
# Tests if the model maintains coherence in longer code
# =============================================================================

LONG_CONTEXT_TESTS = [
    TestCase(
        name="function_body",
        category="long_context",
        prompt="""def calculate_average(numbers):
    if not numbers:
        return 0
    total = 0
    for num in numbers:
        total +="""
    ,
        expected_patterns=[r"num"],  # Should use loop variable
        max_tokens=20,
        description="Should recall loop variable"
    ),
    TestCase(
        name="class_method_reference",
        category="long_context",
        prompt="""class Calculator:
    def __init__(self):
        self.result = 0
    
    def add(self, value):
        self.result +="""
    ,
        expected_patterns=[r"value"],  # Should use parameter
        max_tokens=20,
        description="Should reference method parameter"
    ),
    TestCase(
        name="variable_reuse",
        category="long_context",
        prompt="""data = load_file("input.txt")
processed = clean_data(data)
result = analyze("""
    ,
        expected_patterns=[r"processed|data"],  # Should use defined variable
        max_tokens=20,
        description="Should reuse previously defined variable"
    ),
]

# =============================================================================
# CATEGORY 5: PYTHON IDIOMS
# Tests knowledge of Python idioms
# =============================================================================

PYTHON_IDIOM_TESTS = [
    TestCase(
        name="with_statement",
        category="python_idioms",
        prompt='with open("file.txt", "r") as',
        expected_patterns=[r"f:|file:|handle:"],
        max_tokens=20,
        description="Should complete with statement"
    ),
    TestCase(
        name="f_string",
        category="python_idioms",
        prompt='name = "World"\ngreeting = f"Hello, {',
        expected_patterns=[r"name"],
        max_tokens=20,
        description="Should use variable in f-string"
    ),
    TestCase(
        name="lambda",
        category="python_idioms",
        prompt="double = lambda x:",
        expected_patterns=[r"x\s*\*\s*2|2\s*\*\s*x"],
        max_tokens=20,
        description="Should complete lambda correctly"
    ),
    TestCase(
        name="enumerate",
        category="python_idioms",
        prompt="for i, item in enumerate(",
        expected_patterns=[r"[a-z_]+\)"],  # iterable followed by )
        max_tokens=20,
        description="Should complete enumerate"
    ),
]


def get_all_test_cases() -> List[TestCase]:
    """Returns all test cases."""
    return (
        BRACKET_TESTS +
        INDENTATION_TESTS +
        STRUCTURE_TESTS +
        LONG_CONTEXT_TESTS +
        PYTHON_IDIOM_TESTS
    )


def get_tests_by_category(category: str) -> List[TestCase]:
    """Returns tests for a specific category."""
    all_tests = get_all_test_cases()
    return [t for t in all_tests if t.category == category]


def get_categories() -> List[str]:
    """Returns list of available categories."""
    return [
        "brackets",
        "indentation",
        "structure",
        "long_context",
        "python_idioms"
    ]


if __name__ == '__main__':
    # List all available tests
    print("📋 Available Test Cases:")
    print("=" * 60)
    
    for category in get_categories():
        tests = get_tests_by_category(category)
        print(f"\n[{category.upper()}] ({len(tests)} tests)")
        for test in tests:
            print(f"  • {test.name}: {test.description}")
    
    print(f"\n📊 Total: {len(get_all_test_cases())} tests")