|
1
|
|
|
from abc import ABC, abstractmethod |
|
2
|
|
|
|
|
3
|
|
|
from antlr4 import InputStream # type: ignore |
|
4
|
|
|
from antlr4 import CommonTokenStream, ParserRuleContext, ParseTreeWalker |
|
5
|
|
|
from antlr4.Token import CommonToken # type: ignore |
|
6
|
|
|
|
|
7
|
|
|
from menderbot.antlr_generated.PythonLexer import PythonLexer # type: ignore |
|
8
|
|
|
from menderbot.antlr_generated.PythonParser import PythonParser # type: ignore |
|
9
|
|
|
from menderbot.antlr_generated.PythonParserListener import ( # type: ignore |
|
10
|
|
|
PythonParserListener, |
|
11
|
|
|
) |
|
12
|
|
|
|
|
13
|
|
|
|
|
14
|
|
|
def node_str(node) -> str: |
|
15
|
|
|
return get_text_including_whitespace(node) |
|
16
|
|
|
|
|
17
|
|
|
|
|
18
|
|
|
def node_start_line(node: ParserRuleContext) -> int: |
|
19
|
|
|
node_start: CommonToken = node.start |
|
20
|
|
|
return node_start.line |
|
21
|
|
|
|
|
22
|
|
|
|
|
23
|
|
|
def node_stop_line(node: ParserRuleContext) -> int: |
|
24
|
|
|
node_stop: CommonToken = node.stop |
|
25
|
|
|
return node_stop.line |
|
26
|
|
|
|
|
27
|
|
|
|
|
28
|
|
|
def node_start_column(node: ParserRuleContext) -> int: |
|
29
|
|
|
node_start: CommonToken = node.start |
|
30
|
|
|
return node_start.column |
|
31
|
|
|
|
|
32
|
|
|
|
|
33
|
|
|
def node_stop_column(node: ParserRuleContext) -> int: |
|
34
|
|
|
node_start: CommonToken = node.stop |
|
35
|
|
|
return node_start.column |
|
36
|
|
|
|
|
37
|
|
|
|
|
38
|
|
|
def get_text_including_whitespace(ctx: ParserRuleContext): |
|
39
|
|
|
if not ctx: |
|
40
|
|
|
return "" |
|
41
|
|
|
start: CommonToken = ctx.start |
|
42
|
|
|
stop: CommonToken = ctx.stop |
|
43
|
|
|
start_idx: int = start.start |
|
44
|
|
|
stop_idx: int = stop.stop |
|
45
|
|
|
stream: InputStream = start.getInputStream() |
|
46
|
|
|
return stream.getText(start_idx, stop_idx) |
|
47
|
|
|
|
|
48
|
|
|
|
|
49
|
|
|
def line_indent(line: str) -> str: |
|
50
|
|
|
count = len(line) - len(line.lstrip()) |
|
51
|
|
|
return line[:count] |
|
52
|
|
|
|
|
53
|
|
|
|
|
54
|
|
|
def function_indent(code: str) -> str: |
|
55
|
|
|
second_line_start = code.find("\n") + 1 |
|
56
|
|
|
no_first_line = code[second_line_start:] |
|
57
|
|
|
if no_first_line.find("\n") > -1: |
|
58
|
|
|
second_line_end = second_line_start + no_first_line.find("\n") |
|
59
|
|
|
second_line = code[second_line_start:second_line_end] |
|
60
|
|
|
else: |
|
61
|
|
|
second_line = no_first_line |
|
62
|
|
|
return line_indent(second_line) |
|
63
|
|
|
|
|
64
|
|
|
|
|
65
|
|
|
def reindent(text: str, indent: str) -> str: |
|
66
|
|
|
lines = text.split("\n") |
|
67
|
|
|
indented_lines = [indent + line.lstrip() for line in lines] |
|
68
|
|
|
return "\n".join(indented_lines) |
|
69
|
|
|
|
|
70
|
|
|
|
|
71
|
|
|
class LanguageStrategy(ABC): |
|
72
|
|
|
@abstractmethod |
|
73
|
|
|
def function_has_comment(self, node) -> bool: |
|
74
|
|
|
pass |
|
75
|
|
|
|
|
76
|
|
|
@abstractmethod |
|
77
|
|
|
def parse_source_to_tree(self, source: bytes) -> None: |
|
78
|
|
|
pass |
|
79
|
|
|
|
|
80
|
|
|
@abstractmethod |
|
81
|
|
|
def get_function_nodes(self, tree) -> list: |
|
82
|
|
|
pass |
|
83
|
|
|
|
|
84
|
|
|
def get_imports(self, tree) -> list: |
|
85
|
|
|
del tree |
|
86
|
|
|
return [] |
|
87
|
|
|
|
|
88
|
|
|
@property |
|
89
|
|
|
@abstractmethod |
|
90
|
|
|
def function_doc_line_offset(self) -> int: |
|
91
|
|
|
pass |
|
92
|
|
|
|
|
93
|
|
|
|
|
94
|
|
|
class PythonLanguageStrategy(LanguageStrategy): |
|
95
|
|
|
def function_has_comment(self, node: PythonParser.FuncdefContext) -> bool: |
|
96
|
|
|
"""Checks if function has a docstring.""" |
|
97
|
|
|
body_node: PythonParser.SuiteContext = node.suite() |
|
98
|
|
|
if body_node: |
|
99
|
|
|
# https://peps.python.org/pep-0257/ |
|
100
|
|
|
first_stmt_node: PythonParser.StmtContext = body_node.stmt(0) |
|
101
|
|
|
first_stmt_text = first_stmt_node.getText().strip() |
|
102
|
|
|
has_doc_prefix = ( |
|
103
|
|
|
first_stmt_text.startswith('"""') |
|
104
|
|
|
or first_stmt_text.startswith('r"""') |
|
105
|
|
|
or first_stmt_text.startswith('u"""') |
|
106
|
|
|
) |
|
107
|
|
|
|
|
108
|
|
|
has_doc_suffix = first_stmt_text.endswith('"""') |
|
109
|
|
|
return has_doc_prefix and has_doc_suffix |
|
110
|
|
|
return False |
|
111
|
|
|
|
|
112
|
|
|
def parse_source_to_tree(self, source: bytes): |
|
113
|
|
|
input_stream = InputStream(str(source, encoding="utf-8") + "\n") |
|
114
|
|
|
lexer = PythonLexer(input_stream) |
|
115
|
|
|
token_stream = CommonTokenStream(lexer) |
|
116
|
|
|
parser = PythonParser(token_stream) |
|
117
|
|
|
return parser.file_input() |
|
118
|
|
|
|
|
119
|
|
|
def get_function_nodes(self, tree) -> list[PythonParser.FuncdefContext]: |
|
120
|
|
|
function_nodes: list[PythonParser.FuncdefContext] = [] |
|
121
|
|
|
|
|
122
|
|
|
class MyListener(PythonParserListener): |
|
123
|
|
|
def enterFuncdef(self, ctx: PythonParser.FuncdefContext): |
|
124
|
|
|
function_nodes.append(ctx) |
|
125
|
|
|
# print(ctx.toStringTree(recog=parser)) |
|
126
|
|
|
|
|
127
|
|
|
walker = ParseTreeWalker() |
|
128
|
|
|
walker.walk(MyListener(), tree) |
|
129
|
|
|
return function_nodes |
|
130
|
|
|
|
|
131
|
|
|
def get_function_node_name(self, node): |
|
132
|
|
|
name_node: PythonParser.NameContext = node.name() |
|
133
|
|
|
name = name_node.getText() |
|
134
|
|
|
return name |
|
135
|
|
|
|
|
136
|
|
|
def get_imports(self, tree) -> list[tuple[str, str]]: |
|
137
|
|
|
results: list[tuple[str, str]] = [] |
|
138
|
|
|
|
|
139
|
|
|
class MyListener(PythonParserListener): |
|
140
|
|
|
def enterFrom_stmt(self, ctx: PythonParser.From_stmtContext): |
|
141
|
|
|
dotted_name_ctx: PythonParser.Dotted_nameContext = ctx.dotted_name() |
|
142
|
|
|
import_as_names_ctx: PythonParser.Import_as_namesContext = ( |
|
143
|
|
|
ctx.import_as_names() |
|
144
|
|
|
) |
|
145
|
|
|
import_as_name_ctxs: list[PythonParser.Import_as_nameContext] = ( |
|
146
|
|
|
import_as_names_ctx.import_as_name() |
|
147
|
|
|
) |
|
148
|
|
|
# print(type(import_as_name_ctxs)) |
|
149
|
|
|
for import_as_name_ctx in import_as_name_ctxs: |
|
150
|
|
|
results.append( |
|
151
|
|
|
(dotted_name_ctx.getText(), node_str(import_as_name_ctx)) |
|
152
|
|
|
) |
|
153
|
|
|
# print(ctx.toStringTree(recog=parser)) |
|
154
|
|
|
|
|
155
|
|
|
def enterImport_stmt(self, ctx: PythonParser.Import_stmtContext): |
|
156
|
|
|
dotted_as_names_ctx: PythonParser.Dotted_as_namesContext = ( |
|
157
|
|
|
ctx.dotted_as_names() |
|
158
|
|
|
) |
|
159
|
|
|
dotted_as_name_ctxs: list[PythonParser.Dotted_nameContext] = ( |
|
160
|
|
|
dotted_as_names_ctx.dotted_as_name() |
|
161
|
|
|
) |
|
162
|
|
|
for dottedAsNameCtx in dotted_as_name_ctxs: |
|
163
|
|
|
results.append(("", node_str(dottedAsNameCtx))) |
|
164
|
|
|
|
|
165
|
|
|
walker = ParseTreeWalker() |
|
166
|
|
|
walker.walk(MyListener(), tree) |
|
167
|
|
|
return results |
|
168
|
|
|
|
|
169
|
|
|
function_doc_line_offset = 1 |
|
170
|
|
|
|
|
171
|
|
|
|
|
172
|
|
|
# class CppLanguageStrategy(LanguageStrategy): |
|
173
|
|
|
# def function_has_comment(self, node) -> bool: |
|
174
|
|
|
# return node.prev_sibling.type in ["comment"] |
|
175
|
|
|
# |
|
176
|
|
|
# def parse_source_to_tree(self, source: bytes): |
|
177
|
|
|
# return parse_source_to_tree(source, CPP_LANGUAGE) |
|
178
|
|
|
# |
|
179
|
|
|
# def get_function_nodes(self, tree) -> list: |
|
180
|
|
|
# query = CPP_LANGUAGE.query( |
|
181
|
|
|
# """ |
|
182
|
|
|
# [ |
|
183
|
|
|
# (function_definition) @function |
|
184
|
|
|
# ] |
|
185
|
|
|
# """ |
|
186
|
|
|
# ) |
|
187
|
|
|
# captures = query.captures(tree.root_node) |
|
188
|
|
|
# return [capture[0] for capture in captures] |
|
189
|
|
|
# |
|
190
|
|
|
# function_doc_line_offset = 0 |
|
191
|
|
|
|
|
192
|
|
|
|
|
193
|
|
|
LANGUAGE_STRATEGIES = { |
|
194
|
|
|
".py": PythonLanguageStrategy(), |
|
195
|
|
|
# ".c": CppLanguageStrategy(), |
|
196
|
|
|
# ".cpp": CppLanguageStrategy(), |
|
197
|
|
|
} |
|
198
|
|
|
|
craftvscruft /
menderbot
