Merge pull request #47 from ajinabraham/perf_improvement

* Using Threadpool and Processpool to improve performance
* Add support for custom CPU cores
* Code QA
* Added OWASP Mobile Top 10 2024 standards
* Added tests
* Fixes #39, #38 , #46, #45

.github/workflows/publish.yml

@@ -18,7 +18,7 @@ jobs:
     - name: Install dependencies
       run: |
         python -m pip install --upgrade pip
-        pip install poetry==1.6.1
+        pip install poetry
     - name: Build and publish
       env:
         PYPI_TOKEN: ${{ secrets.PYPI_PASSWORD }}

.github/workflows/python_test.yml

@@ -16,7 +16,7 @@ jobs:
     strategy:
       matrix:
         os: [ubuntu-latest, macos-latest]
-        python-version: [3.8, 3.9, '3.10', '3.11']
+        python-version: ['3.10', '3.11', '3.12']
 
     steps:
     - uses: actions/checkout@v3
@@ -27,7 +27,7 @@ jobs:
     - name: Install dependencies
       run: |
         python -m pip install --upgrade pip
-        pip install tox poetry==1.6.1
+        pip install tox poetry
     - name: Lint
       run: |
         tox -e lint

README.md

@@ -31,13 +31,13 @@ usage: libsast [-h] [-o OUTPUT] [-p PATTERN_FILE] [-s SGREP_PATTERN_FILE]
                [--ignore-filenames IGNORE_FILENAMES [IGNORE_FILENAMES ...]]
                [--ignore-extensions IGNORE_EXTENSIONS [IGNORE_EXTENSIONS ...]]
                [--ignore-paths IGNORE_PATHS [IGNORE_PATHS ...]]
-               [--show-progress] [-v]
-               [path [path ...]]
+               [--show-progress] [--cpu-core CPU_CORE] [-v]
+               [path ...]
 
 positional arguments:
   path                  Path can be file(s) or directories
 
-optional arguments:
+options:
   -h, --help            show this help message and exit
   -o OUTPUT, --output OUTPUT
                         Output filename to save JSON report.
@@ -46,7 +46,8 @@ optional arguments:
   -s SGREP_PATTERN_FILE, --sgrep-pattern-file SGREP_PATTERN_FILE
                         sgrep rules directory
   --sgrep-file-extensions SGREP_FILE_EXTENSIONS [SGREP_FILE_EXTENSIONS ...]
-                        File extensions that should be scanned with sgrep
+                        File extensions that should be scanned with semantic
+                        grep
   --file-extensions FILE_EXTENSIONS [FILE_EXTENSIONS ...]
                         File extensions that should be scanned with pattern
                         matcher
@@ -57,6 +58,7 @@ optional arguments:
   --ignore-paths IGNORE_PATHS [IGNORE_PATHS ...]
                         Path(s) to ignore
   --show-progress       Show scan progress
+  --cpu-core CPU_CORE   No of CPU cores to use. Use all cores by default
   -v, --version         Show libsast version
 ```
 

libsast/__init__.py

@@ -1,14 +1,18 @@
 #!/usr/bin/env python
 # -*- coding: utf_8 -*-
+from datetime import datetime
+
 from .core_matcher.pattern_matcher import PatternMatcher
 from .core_matcher.choice_matcher import ChoiceMatcher
 from .core_sgrep.semantic_sgrep import SemanticGrep
 from .scanner import Scanner
 
+
+year = str(datetime.now().year)
 __title__ = 'libsast'
 __authors__ = 'Ajin Abraham'
-__copyright__ = 'Copyright 2020 Ajin Abraham, OpenSecurity'
-__version__ = '2.0.3'
+__copyright__ = f'Copyright {year} Ajin Abraham, opensecurity.in'
+__version__ = '3.0.0'
 __version_info__ = tuple(int(i) for i in __version__.split('.'))
 __all__ = [
     'Scanner',

libsast/__main__.py

@@ -51,7 +51,7 @@ def main():
     parser.add_argument('--sgrep-file-extensions',
                         nargs='+',
                         help=('File extensions that should be scanned'
-                              ' with sgrep'),
+                              ' with semantic grep'),
                         required=False)
     parser.add_argument('--file-extensions',
                         nargs='+',
@@ -74,6 +74,10 @@ def main():
                         help='Show scan progress',
                         required=False,
                         action='store_true')
+    parser.add_argument('--cpu-core',
+                        help='No of CPU cores to use. Use all cores by default',
+                        type=int,
+                        required=False)
     parser.add_argument('-v', '--version',
                         help='Show libsast version',
                         required=False,
@@ -89,6 +93,7 @@ def main():
             'ignore_extensions': args.ignore_extensions,
             'ignore_paths': args.ignore_paths,
             'show_progress': args.show_progress,
+            'cpu_core': args.cpu_core,
         }
         result = Scanner(options, args.path).scan()
         output(args.output, result)

libsast/common.py

@@ -26,7 +26,7 @@ def progress_print(self, index):
         self.output.write(f'- {self.prefix} {prog} {index}\r')
         self.output.flush()
 
-    def progrees_loop(self, iterator):
+    def progress_loop(self, iterator):
         """Show progress for loop."""
         self.progress_print(0)
         for index, item in enumerate(iterator):
@@ -74,15 +74,18 @@ def read_yaml(file_obj, text=False):
 
 def get_worker_count():
     """Get worker count for pool."""
+    libsast_workers = os.getenv('LIBSAST_WORKERS')
+    if libsast_workers:
+        try:
+            return int(libsast_workers)
+        except ValueError:
+            return 1
     try:
         worker_count = os.cpu_count()
-        if not worker_count:
-            worker_count = 1
-        if worker_count != 1 and sys.platform == 'win32':
-            # Work around https://bugs.python.org/issue26903
-            worker_count = min(worker_count, 61)
-        if os.getenv('LIBSAST_WORKERS'):
-            worker_count = int(os.getenv('LIBSAST_WORKERS'))
     except Exception:
-        worker_count = 16
+        worker_count = 1
+
+    # Adjust worker count for Windows
+    if sys.platform == 'win32':
+        worker_count = min(worker_count, 61)
     return worker_count