Merge pull request #653 from onekey-sec/update-ruff

Update ruff

.github/workflows/update-vendored-nix-dependencies.py

@@ -55,7 +55,8 @@ def create_pr(
 def update_dependencies():
     with NamedTemporaryFile() as log:
         subprocess.run(
-            ["nvfetcher", "--build-dir", "nix/_sources", "--changelog", log.name]
+            ["nvfetcher", "--build-dir", "nix/_sources", "--changelog", log.name],
+            check=True,
         )
         return Path(log.name).read_text()
 

.pre-commit-config.yaml

@@ -14,7 +14,7 @@ repos:
       - id: check-added-large-files
 
   - repo: https://github.com/charliermarsh/ruff-pre-commit
-    rev: "v0.0.259"
+    rev: "v0.0.290"
     hooks:
       - id: ruff
         name: Check python (ruff)

pyproject.toml

@@ -99,7 +99,11 @@ ignore = [
   "N818",    # error-suffix-on-exception-name:          Exception names can be meaningful without smurfs
   "PLC0414", # useless-import-alias:                    Enable explicitly re-exporting public symbols
   "PLR09",   # too-many-{arguments,branches,...}:       We do not want to impose hard limits
+  "PTH201",  # path-constructor-current-directory:      Having "." explicitly passed expresses intent more clearly
+  "RUF012",  # mutable-class-default:                   Wants to annotate things like `Handler.PATTERNS` with `ClassVar`, producing noise
   "S101",    # assert:                                  Enable usage of asserts
+  "S603",    # subprocess-without-shell-equals-true:    This check just highlights, that we should check for untrusted inputs
+  "S607",    # start-process-with-partial-path:         In our case, the convenience of allowing partial paths outweighs the risks
   "TRY003",  # raise-vanilla-args:                      We are adding contextual information in exception messages
   "TRY400",  # error-instead-of-exception:              It is okay to log without backtrace in except blocks
 ]

tests/handlers/filesystem/test_romfs.py

@@ -25,7 +25,6 @@ def test_get_string(content, expected):
         (b"\x00\x00\x00\x00", True),
         (b"\x00\x00\x00\x00\x00\x00\x00\x00", True),
         (b"\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00", True),
-        (b"\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00", True),
         (b"\x00\x00\x00", False),
         (b"\x00\x00\x00\x00\x00\x00\x00", False),
         (b"\x00\x00\x00\x00\x00\x00\x00\x00\x00", False),

tests/test_cli.py

@@ -158,7 +158,7 @@ def test_non_existing_file(tmp_path: Path):
     result = runner.invoke(unblob.cli.cli, ["--extract-dir", str(tmp_path), str(path)])
     assert result.exit_code == 2
     assert "Invalid value for 'FILE'" in result.output
-    assert f"File '{str(path)}' does not exist" in result.output
+    assert f"File '{path}' does not exist" in result.output
 
 
 def test_dir_for_file(tmp_path: Path):

tests/test_iter_utils.py

@@ -8,8 +8,8 @@
     [
         ([], set()),
         ([0, 0], {0}),
-        ([0, 0, 0], {0, 0}),
-        ([1, 2, 3], {1, 1}),
+        ([0, 0, 0], {0}),
+        ([1, 2, 3], {1}),
         ([1, 5, 8, 8, 10, 15], {4, 3, 0, 2, 5}),
     ],
 )

tests/test_logging.py

@@ -12,7 +12,6 @@
     "value, expected",
     [
         (10, "0xa"),
-        (0xA, "0xa"),
         ("10", "10"),
         (noformat(10), 10),
         (noformat(Path("/absolute/path")), Path("/absolute/path")),

unblob/extractors/command.py

@@ -54,6 +54,7 @@ def no_op():
                 stdout=stdout_file,
                 stderr=subprocess.PIPE,
                 timeout=COMMAND_TIMEOUT,
+                check=False,
             )
             if res.returncode != 0:
                 error_report = ExtractCommandFailedReport(
@@ -64,7 +65,7 @@ def no_op():
                 )
 
                 logger.error("Extract command failed", **error_report.asdict())
-                raise ExtractError(error_report)  # noqa: TRY301
+                raise ExtractError(error_report)
         except FileNotFoundError:
             error_report = ExtractorDependencyNotFoundReport(
                 dependencies=self.get_dependencies()

unblob/handlers/archive/zip.py

@@ -93,7 +93,7 @@ def has_encrypted_files(
         end_of_central_directory: Instance,
     ) -> bool:
         file.seek(start_offset + end_of_central_directory.offset_of_cd, io.SEEK_SET)
-        for _ in range(0, end_of_central_directory.total_entries):
+        for _ in range(end_of_central_directory.total_entries):
             cd_header = self.cparser_le.cd_file_header_t(file)
             if cd_header.flags & self.ENCRYPTED_FLAG:
                 return True

unblob/handlers/compression/lz4.py

@@ -15,10 +15,10 @@
 
 logger = get_logger()
 
-SKIPPABLE_FRAMES_MAGIC = [0x184D2A50 + i for i in range(0, 16)]
+SKIPPABLE_FRAMES_MAGIC = [0x184D2A50 + i for i in range(16)]
 FRAME_MAGIC = 0x184D2204
 LEGACY_FRAME_MAGIC = 0x184C2102
-FRAME_MAGICS = [*SKIPPABLE_FRAMES_MAGIC, FRAME_MAGIC] + [LEGACY_FRAME_MAGIC]
+FRAME_MAGICS = [*SKIPPABLE_FRAMES_MAGIC, FRAME_MAGIC, LEGACY_FRAME_MAGIC]
 
 _1BIT = 0x01
 _2BITS = 0x03

unblob/handlers/compression/lzma.py

@@ -77,9 +77,7 @@ def calculate_chunk(self, file: File, start_offset: int) -> Optional[ValidChunk]
                 data = file.read(DEFAULT_BUFSIZE)
                 if not data:
                     if read_size < (uncompressed_size * MIN_READ_RATIO):
-                        raise InvalidInputFormat(  # noqa: TRY301
-                            "Very early truncated LZMA stream"
-                        )
+                        raise InvalidInputFormat("Very early truncated LZMA stream")
 
                     logger.debug(
                         "LZMA stream is truncated.",

unblob/handlers/compression/xz.py

@@ -107,7 +107,7 @@ def get_stream_size(footer_offset: int, file: File) -> int:
 
     # read Record 'Unpadded Size' and 'Uncompressed Size' for every Record
     blocks_size = 0
-    for _ in range(0, num_records):
+    for _ in range(num_records):
         size, unpadded_size = read_multibyte_int(file)
         index_size += size
 

unblob/processing.py

@@ -738,7 +738,7 @@ def calculate_block_size(
     block_size = file_size // chunk_count
     block_size = max(min_limit, block_size)
     block_size = min(block_size, max_limit)
-    return block_size
+    return block_size  # noqa: RET504
 
 
 def format_entropy_plot(percentages: List[float], block_size: int):

unblob/testing.py

@@ -24,8 +24,12 @@ def configure_logging(tmp_path_factory):  # noqa: PT004
 
 
 def gather_integration_tests(test_data_path: Path):
+    # Path.glob() trips on some invalid files
     test_input_dirs = [
-        Path(p) for p in glob.iglob(f"{test_data_path}/**/__input__", recursive=True)
+        Path(p)
+        for p in glob.iglob(  # noqa: PTH207
+            f"{test_data_path}/**/__input__", recursive=True
+        )
     ]
     test_case_dirs = [p.parent for p in test_input_dirs]
     test_output_dirs = [p / "__output__" for p in test_case_dirs]