introduce flake8-print linter

.github/flake8.ini

@@ -14,3 +14,16 @@ extend-ignore =
     B010,
     # G200 Logging statement uses exception in arguments
     G200
+
+
+per-file-ignores =
+    # T201 print found.
+    #
+    # scripts are meant to print output
+    scripts/*: T201
+    # capa.exe is meant to print output
+    capa/main.py: T201
+    # IDA tests emit results to output window so need to print
+    tests/test_ida_features.py: T201
+    # utility used to find the Binary Ninja API via invoking python.exe
+    capa/features/extractors/binja/find_binja_api.py: T201

capa/features/extractors/binja/basicblock.py

@@ -6,7 +6,6 @@
 #  is distributed on an "AS IS" BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
 # See the License for the specific language governing permissions and limitations under the License.
 
-import sys
 import string
 import struct
 from typing import Tuple, Iterator
@@ -182,30 +181,3 @@ BASIC_BLOCK_HANDLERS = (
     extract_bb_tight_loop,
     extract_bb_stackstring,
 )
-
-
-def main():
-    if len(sys.argv) < 2:
-        return
-
-    from binaryninja import BinaryViewType
-
-    from capa.features.extractors.binja.extractor import BinjaFeatureExtractor
-
-    bv: BinaryView = BinaryViewType.get_view_of_file(sys.argv[1])
-    if bv is None:
-        return
-
-    features = []
-    extractor = BinjaFeatureExtractor(bv)
-    for fh in extractor.get_functions():
-        for bbh in extractor.get_basic_blocks(fh):
-            features.extend(list(extract_features(fh, bbh)))
-
-    import pprint
-
-    pprint.pprint(features)
-
-
-if __name__ == "__main__":
-    main()

capa/features/extractors/binja/file.py

@@ -6,7 +6,6 @@
 #  is distributed on an "AS IS" BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
 # See the License for the specific language governing permissions and limitations under the License.
 
-import sys
 import struct
 from typing import Tuple, Iterator
 
@@ -166,23 +165,3 @@ FILE_HANDLERS = (
     extract_file_function_names,
     extract_file_format,
 )
-
-
-def main():
-    """ """
-    if len(sys.argv) < 2:
-        return
-
-    from binaryninja import BinaryViewType
-
-    bv: BinaryView = BinaryViewType.get_view_of_file(sys.argv[1])
-    if bv is None:
-        return
-
-    import pprint
-
-    pprint.pprint(list(extract_features(bv)))
-
-
-if __name__ == "__main__":
-    main()

capa/features/extractors/binja/function.py

@@ -5,7 +5,6 @@
 # Unless required by applicable law or agreed to in writing, software distributed under the License
 #  is distributed on an "AS IS" BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
 # See the License for the specific language governing permissions and limitations under the License.
-import sys
 from typing import Tuple, Iterator
 
 from binaryninja import Function, BinaryView, LowLevelILOperation
@@ -67,30 +66,3 @@ def extract_features(fh: FunctionHandle) -> Iterator[Tuple[Feature, Address]]:
 
 
 FUNCTION_HANDLERS = (extract_function_calls_to, extract_function_loop, extract_recursive_call)
-
-
-def main():
-    """ """
-    if len(sys.argv) < 2:
-        return
-
-    from binaryninja import BinaryViewType
-
-    from capa.features.extractors.binja.extractor import BinjaFeatureExtractor
-
-    bv: BinaryView = BinaryViewType.get_view_of_file(sys.argv[1])
-    if bv is None:
-        return
-
-    features = []
-    extractor = BinjaFeatureExtractor(bv)
-    for fh in extractor.get_functions():
-        features.extend(list(extract_features(fh)))
-
-    import pprint
-
-    pprint.pprint(features)
-
-
-if __name__ == "__main__":
-    main()

capa/features/extractors/binja/insn.py

@@ -5,7 +5,6 @@
 # Unless required by applicable law or agreed to in writing, software distributed under the License
 #  is distributed on an "AS IS" BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
 # See the License for the specific language governing permissions and limitations under the License.
-import sys
 from typing import Any, List, Tuple, Iterator, Optional
 
 from binaryninja import Function
@@ -585,32 +584,3 @@ INSTRUCTION_HANDLERS = (
     extract_function_calls_from,
     extract_function_indirect_call_characteristic_features,
 )
-
-
-def main():
-    """ """
-    if len(sys.argv) < 2:
-        return
-
-    from binaryninja import BinaryViewType
-
-    from capa.features.extractors.binja.extractor import BinjaFeatureExtractor
-
-    bv: BinaryView = BinaryViewType.get_view_of_file(sys.argv[1])
-    if bv is None:
-        return
-
-    features = []
-    extractor = BinjaFeatureExtractor(bv)
-    for fh in extractor.get_functions():
-        for bbh in extractor.get_basic_blocks(fh):
-            for insn in extractor.get_instructions(fh, bbh):
-                features.extend(list(extract_features(fh, bbh, insn)))
-
-    import pprint
-
-    pprint.pprint(features)
-
-
-if __name__ == "__main__":
-    main()

capa/features/extractors/ida/basicblock.py

@@ -104,19 +104,3 @@ BASIC_BLOCK_HANDLERS = (
     extract_bb_tight_loop,
     extract_bb_stackstring,
 )
-
-
-def main():
-    features = []
-    for fhandle in helpers.get_functions(skip_thunks=True, skip_libs=True):
-        f: idaapi.func_t = fhandle.inner
-        for bb in idaapi.FlowChart(f, flags=idaapi.FC_PREDS):
-            features.extend(list(extract_features(fhandle, bb)))
-
-    import pprint
-
-    pprint.pprint(features)
-
-
-if __name__ == "__main__":
-    main()

capa/features/extractors/ida/file.py

@@ -199,14 +199,3 @@ FILE_HANDLERS = (
     extract_file_function_names,
     extract_file_format,
 )
-
-
-def main():
-    """ """
-    import pprint
-
-    pprint.pprint(list(extract_features()))
-
-
-if __name__ == "__main__":
-    main()

capa/features/extractors/ida/function.py

@@ -50,18 +50,3 @@ def extract_features(fh: FunctionHandle) -> Iterator[Tuple[Feature, Address]]:
 
 
 FUNCTION_HANDLERS = (extract_function_calls_to, extract_function_loop, extract_recursive_call)
-
-
-def main():
-    """ """
-    features = []
-    for fhandle in capa.features.extractors.ida.helpers.get_functions(skip_thunks=True, skip_libs=True):
-        features.extend(list(extract_features(fhandle)))
-
-    import pprint
-
-    pprint.pprint(features)
-
-
-if __name__ == "__main__":
-    main()

capa/features/extractors/ida/insn.py

@@ -501,20 +501,3 @@ INSTRUCTION_HANDLERS = (
     extract_function_calls_from,
     extract_function_indirect_call_characteristic_features,
 )
-
-
-def main():
-    """ """
-    features = []
-    for f in capa.features.extractors.ida.helpers.get_functions(skip_thunks=True, skip_libs=True):
-        for bb in idaapi.FlowChart(f, flags=idaapi.FC_PREDS):
-            for insn in capa.features.extractors.ida.helpers.get_instructions_in_range(bb.start_ea, bb.end_ea):
-                features.extend(list(extract_features(f, bb, insn)))
-
-    import pprint
-
-    pprint.pprint(features)
-
-
-if __name__ == "__main__":
-    main()

capa/features/extractors/strings.py

@@ -85,20 +85,3 @@ def extract_unicode_strings(buf, n=4):
             yield String(match.group().decode("utf-16"), match.start())
         except UnicodeDecodeError:
             pass
-
-
-def main():
-    import sys
-
-    with open(sys.argv[1], "rb") as f:
-        b = f.read()
-
-    for s in extract_ascii_strings(b):
-        print("0x{:x}: {:s}".format(s.offset, s.s))
-
-    for s in extract_unicode_strings(b):
-        print("0x{:x}: {:s}".format(s.offset, s.s))
-
-
-if __name__ == "__main__":
-    main()

capa/helpers.py

@@ -96,7 +96,7 @@ def redirecting_print_to_tqdm(disable_progress):
     with one that is compatible with tqdm.
     via: https://stackoverflow.com/a/42424890/87207
     """
-    old_print = print
+    old_print = print  # noqa: T202 [reserved word print used]
 
     def new_print(*args, **kwargs):
         # If tqdm.tqdm.write raises error, use builtin print

setup.py

@@ -80,6 +80,7 @@ setuptools.setup(
             "flake8-comprehensions==3.13.0",
             "flake8-logging-format==0.9.0",
             "flake8-no-implicit-concat==0.3.4",
+            "flake8-print==5.0.0",
             "ruff==0.0.275",
             "black==23.3.0",
             "isort==5.11.4",

tests/test_scripts.py

@@ -8,11 +8,14 @@
 
 import os
 import sys
+import logging
 import textwrap
 import subprocess
 
 import pytest
 
+logger = logging.getLogger(__name__)
+
 CD = os.path.dirname(__file__)
 
 
@@ -63,7 +66,7 @@ def test_bulk_process(tmpdir):
 
 def run_program(script_path, args):
     args = [sys.executable] + [script_path] + args
-    print(f"running: '{args}'")
+    logger.debug("running: %r", args)
     return subprocess.run(args, stdout=subprocess.PIPE)