File size: 14,680 Bytes
f8a39f0 | 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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 | import ast
class FeatureExtractor(ast.NodeVisitor):
"""
Traverses the AST and extracts structural features
from Python source code.
"""
def __init__(self):
self.features = {
"for_loops": 0,
"while_loops": 0,
"function_calls": set(),
"recursion": False,
"max_loop_depth": 0,
"recursive_call_count": 0,
"divide_and_conquer": False,
"binary_search_pattern": False,
"pointer_variables": set(),
"pointer_updates": 0,
"bfs_pattern": False,
"queue_variables": set(),
"queue_operations": 0,
"queue_pop_front": False,
"queue_append_detected": False,
"graph_iteration": False,
"dfs_pattern": False,
"uses_stack": False,
"uses_pop": False,
"dp_pattern": False,
"uses_dp_array": False,
"sorting_pattern": False,
"bubble_sort_pattern": False,
"insertion_sort_pattern": False,
"adjacent_swap_detected": False,
"insertion_shift_detected": False,
"memoization_pattern": False,
"memo_dict_defined": False,
"memo_lookup_detected": False,
"memo_store_detected": False,
"tabulation_pattern": False,
"dp_self_dependency": False,
"dp_dimension": 1,
"merge_sort_pattern": False,
"quick_sort_pattern": False,
"sliding_window_pattern": False,
"window_updates": 0,
"window_shrinks": 0,
"heap_imported": False,
"heap_operations": 0,
"heap_pattern": False,
}
self.current_function = None
self.current_loop_depth = 0
self.max_loop_depth = 0
self.current_function_name = None
def visit_Import(self, node):
for alias in node.names:
if alias.name == "heapq":
self.features["heap_imported"] = True
self.generic_visit(node)
def visit_ImportFrom(self, node):
if node.module == "heapq":
self.features["heap_imported"] = True
self.generic_visit(node)
def visit_FunctionDef(self, node):
previous_function = self.current_function_name
self.current_function_name = node.name
self.generic_visit(node)
self.current_function_name = previous_function
def visit_For(self, node):
self.features["for_loops"] += 1
self.current_loop_depth += 1
self.max_loop_depth = max(self.max_loop_depth, self.current_loop_depth)
# Detect graph[node] iteration
if isinstance(node.iter, ast.Subscript):
self.features["graph_iteration"] = True
self.generic_visit(node)
self.current_loop_depth -= 1
if isinstance(node.target, ast.Name):
var = node.target.id.lower()
if var in ("right", "r", "end"):
self.features["window_updates"] += 1
def visit_While(self, node):
self.features["while_loops"] += 1
self.current_loop_depth += 1
self.max_loop_depth = max(self.max_loop_depth, self.current_loop_depth)
self.generic_visit(node)
self.current_loop_depth -= 1
def visit_Call(self, node):
if isinstance(node.func, ast.Name):
function_name = node.func.id
self.features["function_calls"].add(function_name)
# Detect recursion
if function_name == self.current_function_name:
self.features["recursion"] = True
self.features["recursive_call_count"] += 1
# If recursion + loop present → DFS-style
if self.features["for_loops"] >= 1:
self.features["dfs_pattern"] = True
# Detect divide-and-conquer
for arg in node.args:
# Case 1: n // 2 or n / 2
if isinstance(arg, ast.BinOp) and isinstance(arg.op, (ast.FloorDiv, ast.Div)):
self.features["divide_and_conquer"] = True
# Case 2: slicing like arr[:mid]
if isinstance(arg, ast.Subscript):
if isinstance(arg.slice, ast.Slice):
self.features["divide_and_conquer"] = True
if isinstance(arg, ast.Subscript) and isinstance(arg.slice, ast.Slice):
self.features["merge_sort_pattern"] = True
# Detect queue operations
if isinstance(node.func, ast.Attribute):
if isinstance(node.func.value, ast.Name):
var = node.func.value.id
if var in self.features["queue_variables"]:
if node.func.attr in ("append", "popleft"):
self.features["queue_operations"] += 1
# Detect stack.pop() or queue.pop()
if isinstance(node.func, ast.Attribute):
method = node.func.attr
if method == "pop":
self.features["uses_pop"] = True
if method == "append":
# mark append usage
pass
# Detect pop(0) for list-based BFS
if isinstance(node.func, ast.Attribute):
method = node.func.attr
# pop(0)
if method == "pop":
if node.args and isinstance(node.args[0], ast.Constant):
if node.args[0].value == 0:
self.features["queue_pop_front"] = True
# append()
if method == "append":
self.features["queue_append_detected"] = True
# popleft()
if method == "popleft":
self.features["queue_pop_front"] = True
# Iterative DFS heuristic
if (
self.features["uses_stack"]
and self.features["uses_pop"]
and self.features["for_loops"] >= 1
):
self.features["dfs_pattern"] = True
# Heap operations
if isinstance(node.func, ast.Attribute):
if isinstance(node.func.value, ast.Name):
if node.func.value.id == "heapq":
if node.func.attr in ("heappush", "heappop", "heapify"):
self.features["heap_operations"] += 1
self.generic_visit(node)
def visit_Assign(self, node):
# -------- Binary Search Pattern Detection --------
if isinstance(node.value, ast.BinOp):
if isinstance(node.value.op, ast.FloorDiv):
if isinstance(node.value.left, ast.BinOp):
if isinstance(node.value.left.op, ast.Add):
self.features["binary_search_pattern"] = True
# -------- Two Pointer Detection --------
if node.targets and isinstance(node.targets[0], ast.Name):
var = node.targets[0].id
# Case 1: left = 0
if isinstance(node.value, (ast.Constant, ast.Num)):
self.features["pointer_variables"].add(var)
# Case 2: right = len(arr) - 1
if isinstance(node.value, ast.BinOp):
self.features["pointer_variables"].add(var)
# -------- BFS Detection --------
if isinstance(node.value, ast.Call):
if isinstance(node.value.func, ast.Name):
if node.value.func.id == "deque":
if node.targets and isinstance(node.targets[0], ast.Name):
var = node.targets[0].id
self.features["queue_variables"].add(var)
# ------- Detect stack initialization
if node.targets and isinstance(node.targets[0], ast.Name):
var = node.targets[0].id
if isinstance(node.value, (ast.List, ast.Call)):
if var.lower() == "stack":
self.features["uses_stack"] = True
# ------- Detect memo dictionary initialization
if isinstance(node.value, ast.Dict):
if node.targets and isinstance(node.targets[0], ast.Name):
var = node.targets[0].id.lower()
if var in ("memo", "cache", "dp"):
self.features["memo_dict_defined"] = True
# Detect memo[n] = ...
if node.targets and isinstance(node.targets[0], ast.Subscript):
target = node.targets[0]
if isinstance(target.value, ast.Name):
var = target.value.id.lower()
if var in ("memo", "cache", "dp"):
self.features["memo_store_detected"] = True
# Detect 2D DP Tables
if isinstance(node.value, ast.ListComp):
self.features["dp_dimension"] = 2
if isinstance(node.value, ast.List):
if any(isinstance(el, ast.List) for el in node.value.elts):
self.features["dp_dimension"] = 2
# Detect true tabulation recurrence && 2D KNAPSACK FIX
if node.targets and isinstance(node.targets[0], ast.Subscript):
target = node.targets[0]
# Find base name
base = target.value
while isinstance(base, ast.Subscript):
base = base.value
if isinstance(base, ast.Name):
var = base.id.lower()
if var in ("dp", "memo", "cache"):
for child in ast.walk(node.value):
if isinstance(child, ast.Name) and child.id.lower() == var:
self.features["dp_self_dependency"] = True
# -------- Bubble Sort Adjacent Swap Detection --------
if (
isinstance(node.targets[0], ast.Tuple)
and isinstance(node.value, ast.Tuple)
and len(node.targets[0].elts) == 2
and len(node.value.elts) == 2
):
left = node.targets[0].elts
right = node.value.elts
if all(isinstance(el, ast.Subscript) for el in left + right):
self.features["adjacent_swap_detected"] = True
# -------- Insertion Sort Shift Detection --------
if node.targets and isinstance(node.targets[0], ast.Subscript):
target = node.targets[0]
if isinstance(node.value, ast.Subscript):
self.features["insertion_shift_detected"] = True
# Merge Sort
if node.targets and isinstance(node.targets[0], ast.Name):
var = node.targets[0].id.lower()
if var == "pivot":
self.features["quick_sort_pattern"] = True
self.generic_visit(node)
def visit_AugAssign(self, node):
if isinstance(node.target, ast.Name):
var = node.target.id
if isinstance(node.op, (ast.Add, ast.Sub)):
if var in self.features["pointer_variables"]:
self.features["pointer_updates"] += 1
if isinstance(node.target, ast.Name):
var = node.target.id.lower()
if var in ("left", "l", "start"):
self.features["window_shrinks"] += 1
self.generic_visit(node)
# ------ subscript access -----
def visit_Subscript(self, node):
# Walk up until we find base name
base = node.value
while isinstance(base, ast.Subscript):
base = base.value
if isinstance(base, ast.Name):
var = base.id.lower()
if var in ("dp", "memo", "cache"):
self.features["uses_dp_array"] = True
self.generic_visit(node)
def visit_Compare(self, node):
# Detect: X in memo/cache/dp
if any(isinstance(op, ast.In) for op in node.ops):
for comparator in node.comparators:
if isinstance(comparator, ast.Name):
if comparator.id.lower() in ("memo", "cache", "dp"):
self.features["memo_lookup_detected"] = True
self.generic_visit(node)
def extract_features(tree: ast.AST) -> dict:
extractor = FeatureExtractor()
extractor.visit(tree)
extractor.features["max_loop_depth"] = extractor.max_loop_depth
if (
extractor.features["while_loops"] >= 1
and extractor.features["queue_pop_front"]
and extractor.features["queue_append_detected"]
and extractor.features["graph_iteration"]
):
extractor.features["bfs_pattern"] = True
# High confidence memoization
if (
extractor.features["recursion"]
and extractor.features["memo_dict_defined"]
and extractor.features["memo_lookup_detected"]
and extractor.features["memo_store_detected"]
):
extractor.features["memoization_pattern"] = True
# Tabulation
if (
extractor.features["uses_dp_array"]
and extractor.features["dp_self_dependency"]
and extractor.features["for_loops"] >= 1
):
extractor.features["tabulation_pattern"] = True
# Final DP pattern
if (
extractor.features["memoization_pattern"]
or extractor.features["tabulation_pattern"]
):
extractor.features["dp_pattern"] = True
# Sorting detection
if extractor.features["max_loop_depth"] >= 2:
if extractor.features["adjacent_swap_detected"]:
extractor.features["bubble_sort_pattern"] = True
extractor.features["sorting_pattern"] = True
elif extractor.features["insertion_shift_detected"]:
extractor.features["insertion_sort_pattern"] = True
extractor.features["sorting_pattern"] = True
# Sliding Window heuristic
if (
extractor.features["for_loops"] >= 1
and extractor.features["while_loops"] >= 1
and extractor.features["window_updates"] >= 1
and extractor.features["window_shrinks"] >= 1
):
extractor.features["sliding_window_pattern"] = True
# Heap pattern detection
if (
extractor.features["heap_imported"]
and extractor.features["heap_operations"] >= 1
):
extractor.features["heap_pattern"] = True
return extractor.features
|