Added fmt and lint to benchmarks/ tests

Makefile

@@ -15,13 +15,13 @@ show:             ## Show the current environment.
 
 .PHONY: fmt
 fmt:              ## Format code using black & isort.
-	isort sqlelf/
-	black sqlelf/
+	isort sqlelf/ benchmarks/ tests/
+	black sqlelf/ benchmarks/ tests/
 
 .PHONY: lint
 lint:             ## Run pep8, black, mypy linters.
-	flake8 sqlelf/
-	black --check sqlelf/
+	flake8 sqlelf/ benchmarks/ tests/
+	black --check sqlelf/ benchmarks/ tests/
 	pyright
 	mypy --strict --install-types --non-interactive sqlelf tests
 

benchmarks/bin_symbol_size.py

@@ -0,0 +1,26 @@
+#! /usr/bin/env python
+"""Go through /bin and print out the number of symbols in each binary."""
+
+import json
+import os
+import subprocess
+from collections import defaultdict
+
+data = defaultdict(lambda: 0)
+
+for root, dirs, files in os.walk("/bin"):
+    for file in files:
+        full_path_file = os.path.join(root, file)
+        if not os.path.isfile(full_path_file) or not os.access(full_path_file, os.X_OK):
+            pass
+        result = subprocess.run(
+            f"readelf -s {full_path_file} | wc -l",
+            capture_output=True,
+            text=True,
+            shell=True,
+        )
+        num_symbols = int(result.stdout)
+        data[full_path_file] = num_symbols
+
+with open("symbols.json", "w") as f:
+    json.dump(data, f, indent=2)

benchmarks/graph_symbol_size_benchmark.py

@@ -1,35 +1,44 @@
 #! /usr/bin/env python3
 
-from plotnine import *
 import pandas as pd
-import numpy as np
+from plotnine import (
+    aes,
+    geom_line,
+    ggplot,
+    labs,
+    save_as_pdf_pages,
+    scale_x_continuous,
+    scale_y_log10,
+    theme_classic,
+)
 
 # Raw data
 data = {
     "Number of Functions": [10, 100, 1000, 10000, 100000],
     "readelf": [
-        0.0052862250013276935,
-        0.005087099008960649,
-        0.005879847012693062,
-        0.01378464701701887,
-        0.09143825399223715,
+        0.004524321004282683,
+        0.004533555009402335,
+        0.005225651984801516,
+        0.012913715007016435,
+        0.08858381301979534,
     ],
     "sqlelf": [
-        0.026774031983222812,
-        0.07022259500809014,
-        0.5325515430013184,
-        5.426244292000774,
-        51.41806371998973,
+        0.02732730400748551,
+        0.0717524380015675,
+        0.5335653759830166,
+        5.1397658770147245,
+        51.25160684299772,
     ],
     "sqlelf-memoized": [
-        0.0006310690077953041,
-        0.0012372269993647933,
-        0.0005934310029260814,
-        0.0008586860203649849,
-        0.0030715609900653362,
+        0.000236856983974576,
+        0.00015781400725245476,
+        0.0001789960078895092,
+        0.0003311840118840337,
+        0.002041122002992779,
     ],
 }
 
+
 # Create the pandas DataFrame
 df = pd.DataFrame(data=data)
 

benchmarks/symbol_size_benchmark.py

@@ -1,12 +1,16 @@
 #! /usr/bin/env python3
-"""A benchmark to measure the time it takes to load a binary with a given number of functions."""
-import timeit
-import tempfile
-import subprocess
-from sqlelf import sql, elf
+"""A benchmark to measure the time it takes to load a
+    binary with a given number of functions.
+
+Afterwards, run the file graph_symbol_size_benchmark.py to
+generate a graph of the results."""
 import pprint
 import sqlite3
-import time
+import subprocess
+import tempfile
+import timeit
+
+from sqlelf import elf, sql
 
 
 def create_executable_file(
@@ -61,7 +65,7 @@ def sqlelf_memoized_benchmark(sqlite_database: str, num_functions: int) -> None:
     num_functions = 10**exponent
     data["Number of Functions"].append(num_functions)
 
-    print(f"Number of functions: {num_functions}")
+    print(f"Number of functions: {num_functions}")  # noqa: T201
     # create the executable
     with tempfile.NamedTemporaryFile(mode="w") as file:
         file_name = file.name
@@ -93,4 +97,4 @@ def sqlelf_memoized_benchmark(sqlite_database: str, num_functions: int) -> None:
             )
         )
 
-pprint.pprint(data)
+pprint.pprint(data)  # noqa: T203

tests/test_cli.py

@@ -1,7 +1,9 @@
-from sqlelf import cli
-import pytest
 from io import StringIO
 
+import pytest
+
+from sqlelf import cli
+
 
 def test_cli_bad_arguments() -> None:
     with pytest.raises(SystemExit):
@@ -19,7 +21,7 @@ def test_cli_single_file_arguments() -> None:
 
 
 def test_cli_single_non_existent_file_arguments() -> None:
-    with pytest.raises(SystemExit) as err:
+    with pytest.raises(SystemExit):
         cli.start(["does_not_exist"])
 
 

tests/test_examples.py

@@ -1,8 +1,9 @@
 """This file tests the examples in the README.md file"""
 
-from sqlelf import sql, elf
 import pytest
 
+from sqlelf import elf, sql
+
 
 @pytest.mark.slow
 def test_symbol_resolutions() -> None:

tests/test_sql.py

@@ -1,8 +1,10 @@
-from sqlelf import sql
-import lief
 from unittest.mock import patch
+
+import lief
 import sh  # type: ignore
 
+from sqlelf import sql
+
 
 def test_simple_binary_real() -> None:
     binary = lief.parse("/bin/ls")
@@ -21,14 +23,14 @@ def test_simple_binary_mocked(Command: sh.Command) -> None:
         fake.so.6 => /some-path/fake.so.6
         libc.so.6 => /nix/store/46m4xx889wlhsdj72j38fnlyyvvvvbyb-glibc-2.37-8/lib/libc.so.6 (0x00007f6995bac000)
         /lib64/ld-linux-x86-64.so.2 => /nix/store/46m4xx889wlhsdj72j38fnlyyvvvvbyb-glibc-2.37-8/lib64/ld-linux-x86-64.so.2 (0x00007f6995dc1000)
-    """
+    """  # noqa: E501
     Command(interpreter).return_value = expected_return_value  # pyright: ignore
     result = sql.find_libraries(binary)
     assert len(result) == 4
     assert result["fake.so.6"] == "/some-path/fake.so.6"
     assert (
         result["/lib64/ld-linux-x86-64.so.2"]
-        == "/nix/store/46m4xx889wlhsdj72j38fnlyyvvvvbyb-glibc-2.37-8/lib64/ld-linux-x86-64.so.2"
+        == "/nix/store/46m4xx889wlhsdj72j38fnlyyvvvvbyb-glibc-2.37-8/lib64/ld-linux-x86-64.so.2"  # noqa: E501
     )
     assert (
         result["libc.so.6"]