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
|
# Licensed under the GPL: https://www.gnu.org/licenses/old-licenses/gpl-2.0.html
# For details: https://github.com/pylint-dev/pylint/blob/main/LICENSE
# Copyright (c) https://github.com/pylint-dev/pylint/blob/main/CONTRIBUTORS.txt
from __future__ import annotations
import tokenize
from typing import TYPE_CHECKING, Any, Literal, cast
from pylint.checkers import BaseTokenChecker
from pylint.reporters.ureports.nodes import Paragraph, Section, Table, Text
from pylint.utils import LinterStats, diff_string
if TYPE_CHECKING:
from pylint.lint import PyLinter
def report_raw_stats(
sect: Section,
stats: LinterStats,
old_stats: LinterStats | None,
) -> None:
"""Calculate percentage of code / doc / comment / empty."""
total_lines = stats.code_type_count["total"]
sect.insert(0, Paragraph([Text(f"{total_lines} lines have been analyzed\n")]))
lines = ["type", "number", "%", "previous", "difference"]
for node_type in ("code", "docstring", "comment", "empty"):
node_type = cast(Literal["code", "docstring", "comment", "empty"], node_type)
total = stats.code_type_count[node_type]
percent = float(total * 100) / total_lines if total_lines else None
old = old_stats.code_type_count[node_type] if old_stats else None
diff_str = diff_string(old, total) if old else None
lines += [
node_type,
str(total),
f"{percent:.2f}" if percent is not None else "NC",
str(old) if old else "NC",
diff_str if diff_str else "NC",
]
sect.append(Table(children=lines, cols=5, rheaders=1))
class RawMetricsChecker(BaseTokenChecker):
"""Checker that provides raw metrics instead of checking anything.
Provides:
* total number of lines
* total number of code lines
* total number of docstring lines
* total number of comments lines
* total number of empty lines
"""
# configuration section name
name = "metrics"
# configuration options
options = ()
# messages
msgs: Any = {}
# reports
reports = (("RP0701", "Raw metrics", report_raw_stats),)
def open(self) -> None:
"""Init statistics."""
self.linter.stats.reset_code_count()
def process_tokens(self, tokens: list[tokenize.TokenInfo]) -> None:
"""Update stats."""
i = 0
tokens = list(tokens)
while i < len(tokens):
i, lines_number, line_type = get_type(tokens, i)
self.linter.stats.code_type_count["total"] += lines_number
self.linter.stats.code_type_count[line_type] += lines_number
JUNK = (tokenize.NL, tokenize.INDENT, tokenize.NEWLINE, tokenize.ENDMARKER)
def get_type(
tokens: list[tokenize.TokenInfo], start_index: int
) -> tuple[int, int, Literal["code", "docstring", "comment", "empty"]]:
"""Return the line type : docstring, comment, code, empty."""
i = start_index
start = tokens[i][2]
pos = start
line_type = None
while i < len(tokens) and tokens[i][2][0] == start[0]:
tok_type = tokens[i][0]
pos = tokens[i][3]
if line_type is None:
if tok_type == tokenize.STRING:
line_type = "docstring"
elif tok_type == tokenize.COMMENT:
line_type = "comment"
elif tok_type in JUNK:
pass
else:
line_type = "code"
i += 1
if line_type is None:
line_type = "empty"
elif i < len(tokens) and tokens[i][0] == tokenize.NEWLINE:
i += 1
# Mypy fails to infer the literal of line_type
return i, pos[0] - start[0] + 1, line_type # type: ignore[return-value]
def register(linter: PyLinter) -> None:
linter.register_checker(RawMetricsChecker(linter))
|