Merge pull request #1074 from onekey-sec/renovate/ruff-0.x

chore(deps): update dependency ruff to v0.9.1

pyproject.toml

@@ -43,7 +43,7 @@ pyright = "^1.1.349"
 pytest = "^8.0.0"
 pytest-cov = ">=3,<7"
 pyyaml = "^6.0.1"
-ruff = "0.8.6"
+ruff = "0.9.1"
 taplo = "^0.9.3"
 
 [tool.poetry.group.docs]
@@ -90,12 +90,14 @@ select = [
   "T10",    # flake8-debugger
   "T20",    # flake8-print
   "TC",     # flake8-type-checking
+  "TID251", # flake8-tidy-imports; banned-api
   "TRY",    # tryceratops
   "UP",     # pyupgrade
   "W",      # pycodestyle (warnings)
 ]
 
 ignore = [
+  "A005",    # stdlib-module-shadowing:                 E.g. `unblog.logging` collides with stdlib `logging`. It's okay for us
   "B027",    # empty-method-without-abstract-decorator: It is okay to have empty methods in abstract classes
   "D1",      # undocumented-*:                          We are not documenting every public symbol
   "D203",    # one-blank-line-before-class:             D211 (no-blank-line-before-class) is used instead
@@ -143,6 +145,9 @@ fixture-parentheses = false
 mark-parentheses = false
 parametrize-names-type = "csv"
 
+[tool.ruff.lint.flake8-tidy-imports.banned-api]
+"attr".msg = "Use `attrs` (with an 's') instead"
+
 [tool.pytest.ini_options]
 addopts = "--cov=unblob --cov=tests --cov-branch --cov-fail-under=90"
 norecursedirs = """

tests/test_cli.py

@@ -377,9 +377,9 @@ def test_skip_extraction(
 
     assert result.exit_code == 0
     process_file_mock.assert_called_once()
-    assert (
-        process_file_mock.call_args.args[0].skip_extraction == skip_extraction
-    ), fail_message
+    assert process_file_mock.call_args.args[0].skip_extraction == skip_extraction, (
+        fail_message
+    )
 
 
 @pytest.mark.parametrize(

tests/test_finder.py

@@ -1,4 +1,4 @@
-import attr
+import attrs
 import pytest
 from pyperscan import Scan
 
@@ -233,4 +233,4 @@ def test_search_chunks(content, expected_chunks, task_result):
 
     assert len(chunks) == len(expected_chunks)
     for expected_chunk, chunk in zip(expected_chunks, chunks):
-        assert attr.evolve(chunk, id="") == attr.evolve(expected_chunk, id="")
+        assert attrs.evolve(chunk, id="") == attrs.evolve(expected_chunk, id="")

tests/test_processing.py

@@ -6,7 +6,7 @@
 from statistics import mean
 from typing import Optional, TypeVar
 
-import attr
+import attrs
 import pytest
 
 from unblob import handlers
@@ -54,7 +54,7 @@ def assert_same_chunks(expected, actual, explanation=None):
     """Assert ignoring the chunk.id-s."""
     assert len(expected) == len(actual), explanation
     for e, a in zip(expected, actual):
-        assert attr.evolve(e, id="") == attr.evolve(a, id=""), explanation
+        assert attrs.evolve(e, id="") == attrs.evolve(a, id=""), explanation
 
 
 @pytest.mark.parametrize(

unblob/cli.py

@@ -177,7 +177,7 @@ def __init__(
     help=f"""Skip processing files with given magic prefix.
         The provided values are appended to unblob's own skip magic list unless
         --clear-skip-magic is provided.
-        [default: {', '.join(DEFAULT_SKIP_MAGIC)}]
+        [default: {", ".join(DEFAULT_SKIP_MAGIC)}]
     """,
     multiple=True,
 )
@@ -481,12 +481,12 @@ def print_report(reports: ProcessResult):
             chunks_distribution.items(), key=lambda item: item[1], reverse=True
         ):
             chunks_table.add_row(
-                handler.upper(), human_size(size), f"{(size/total_size) * 100:0.2f}%"
+                handler.upper(), human_size(size), f"{(size / total_size) * 100:0.2f}%"
             )
 
         console.print(chunks_table)
         console.print(
-            f"Chunk identification ratio: [#00FFC8]{(valid_size/total_size) * 100:0.2f}%[/#00FFC8]"
+            f"Chunk identification ratio: [#00FFC8]{(valid_size / total_size) * 100:0.2f}%[/#00FFC8]"
         )
 
     if len(reports.errors):

unblob/dependencies.py

@@ -1,11 +1,11 @@
 import shutil
 
-import attr
+import attrs
 
 from .models import DirectoryHandlers, Handlers
 
 
-@attr.define
+@attrs.define
 class Dependency:
     command: str
     is_installed: bool

unblob/finder.py

@@ -6,7 +6,7 @@
 from functools import lru_cache
 from typing import Optional
 
-import attr
+import attrs
 from pyperscan import Flag, Pattern, Scan, StreamDatabase
 from structlog import get_logger
 
@@ -19,7 +19,7 @@
 logger = get_logger()
 
 
-@attr.define
+@attrs.define
 class HyperscanMatchContext:
     file: File
     file_size: int

unblob/handlers/archive/cpio.py

@@ -4,7 +4,7 @@
 from pathlib import Path
 from typing import Optional
 
-import attr
+import attrs
 from structlog import get_logger
 
 from ...file_utils import (
@@ -110,7 +110,7 @@
 """
 
 
-@attr.define
+@attrs.define
 class CPIOEntry:
     start_offset: int
     size: int

unblob/handlers/archive/qnap/qnap_nas.py

@@ -2,7 +2,7 @@
 from pathlib import Path
 from typing import Optional
 
-import attr
+import attrs
 from pyperscan import Flag, Pattern, Scan, StreamDatabase
 from structlog import get_logger
 
@@ -36,7 +36,7 @@
 ]
 
 
-@attr.define
+@attrs.define
 class QTSSearchContext:
     start_offset: int
     file: File

unblob/handlers/archive/tar.py

@@ -206,7 +206,7 @@ def _padded_field(re_content_char, size, leftpad_re=" ", rightpad_re=r"[ \0x00]"
     field_regexes = []
 
     for padsize in range(size):
-        content_re = f"{re_content_char}{{{size-padsize}}}"
+        content_re = f"{re_content_char}{{{size - padsize}}}"
 
         for leftpadsize in range(padsize + 1):
             rightpadsize = padsize - leftpadsize

unblob/handlers/compression/_gzip_reader.py

@@ -30,8 +30,7 @@ def read(self):
                 break
             if buf == b"":
                 raise EOFError(
-                    "Compressed file ended before the "
-                    "end-of-stream marker was reached"
+                    "Compressed file ended before the end-of-stream marker was reached"
                 )
 
         self._add_read_data(uncompress)

unblob/handlers/compression/bzip2.py

@@ -1,6 +1,6 @@
 from typing import Optional
 
-import attr
+import attrs
 from pyperscan import Flag, Pattern, Scan, StreamDatabase
 from structlog import get_logger
 
@@ -63,7 +63,7 @@ def build_stream_end_scan_db(pattern_list):
 parser = StructParser(C_DEFINITIONS)
 
 
-@attr.define
+@attrs.define
 class Bzip2SearchContext:
     start_offset: int
     file: File

unblob/handlers/compression/xz.py

@@ -1,7 +1,7 @@
 import io
 from typing import Optional
 
-import attr
+import attrs
 from pyperscan import Flag, Pattern, Scan, StreamDatabase
 from structlog import get_logger
 
@@ -61,7 +61,7 @@ def build_stream_end_scan_db(pattern_list):
 hyperscan_stream_end_magic_db = build_stream_end_scan_db(STREAM_END_MAGIC_PATTERNS)
 
 
-@attr.define
+@attrs.define
 class XZSearchContext:
     start_offset: int
     file: File

unblob/handlers/executable/elf.py

@@ -3,7 +3,7 @@
 from pathlib import Path
 from typing import Optional
 
-import attr
+import attrs
 import lief
 from structlog import get_logger
 
@@ -29,7 +29,7 @@
 KERNEL_INIT_DATA_SECTION = ".init.data"
 
 
-@attr.define(repr=False)
+@attrs.define(repr=False)
 class ElfChunk(ValidChunk):
     def extract(self, inpath: Path, outdir: Path):
         # ELF file extraction is special in that in the general case no new files are extracted, thus