Spaces:
Running
Running
Create parser.py
Browse files
parser.py
ADDED
@@ -0,0 +1,71 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
# parser.py
|
2 |
+
import ast
|
3 |
+
|
4 |
+
def get_category(node):
|
5 |
+
"""
|
6 |
+
Determine the category of an AST node based on its type.
|
7 |
+
"""
|
8 |
+
if isinstance(node, (ast.Import, ast.ImportFrom)):
|
9 |
+
return 'import'
|
10 |
+
elif isinstance(node, (ast.Assign, ast.AnnAssign, ast.AugAssign)):
|
11 |
+
return 'assignment'
|
12 |
+
elif isinstance(node, ast.FunctionDef):
|
13 |
+
return 'function'
|
14 |
+
elif isinstance(node, ast.AsyncFunctionDef):
|
15 |
+
return 'async_function'
|
16 |
+
elif isinstance(node, ast.ClassDef):
|
17 |
+
return 'class'
|
18 |
+
elif isinstance(node, ast.Expr):
|
19 |
+
return 'expression'
|
20 |
+
else:
|
21 |
+
return 'other'
|
22 |
+
|
23 |
+
def parse_python_file(file_path):
|
24 |
+
"""
|
25 |
+
Parse a Python file and return a list of its parts with categories, source code, and locations.
|
26 |
+
|
27 |
+
Args:
|
28 |
+
file_path (str): Path to the Python file to parse.
|
29 |
+
|
30 |
+
Returns:
|
31 |
+
list: A list of dictionaries, each containing 'category', 'source', and 'location'.
|
32 |
+
"""
|
33 |
+
with open(file_path, 'r') as file:
|
34 |
+
code = file.read()
|
35 |
+
|
36 |
+
lines = code.splitlines(keepends=True)
|
37 |
+
tree = ast.parse(code)
|
38 |
+
|
39 |
+
parts = []
|
40 |
+
prev_end = 0
|
41 |
+
|
42 |
+
for stmt in tree.body:
|
43 |
+
start_line = stmt.lineno
|
44 |
+
end_line = getattr(stmt, 'end_lineno', start_line)
|
45 |
+
|
46 |
+
if start_line > prev_end + 1:
|
47 |
+
spacer_lines = lines[prev_end:start_line - 1]
|
48 |
+
parts.append({
|
49 |
+
'category': 'spacer',
|
50 |
+
'source': ''.join(spacer_lines),
|
51 |
+
'location': (prev_end + 1, start_line - 1)
|
52 |
+
})
|
53 |
+
|
54 |
+
stmt_lines = lines[start_line - 1:end_line]
|
55 |
+
parts.append({
|
56 |
+
'category': get_category(stmt),
|
57 |
+
'source': ''.join(stmt_lines),
|
58 |
+
'location': (start_line, end_line)
|
59 |
+
})
|
60 |
+
|
61 |
+
prev_end = end_line
|
62 |
+
|
63 |
+
if prev_end < len(lines):
|
64 |
+
remaining_lines = lines[prev_end:]
|
65 |
+
parts.append({
|
66 |
+
'category': 'spacer',
|
67 |
+
'source': ''.join(remaining_lines),
|
68 |
+
'location': (prev_end + 1, len(lines) + 1)
|
69 |
+
})
|
70 |
+
|
71 |
+
return parts
|