Merge pull request #51 from ajinabraham/3.1.2

3.1.2

Author: ajinabraham

libsast/__init__.py

@@ -12,7 +12,7 @@
 __title__ = 'libsast'
 __authors__ = 'Ajin Abraham'
 __copyright__ = f'Copyright {year} Ajin Abraham, opensecurity.in'
-__version__ = '3.1.1'
+__version__ = '3.1.2'
 __version_info__ = tuple(int(i) for i in __version__.split('.'))
 __all__ = [
     'Scanner',

libsast/core_matcher/choice_matcher.py

@@ -24,6 +24,7 @@ def __init__(self, options: dict) -> None:
         self.scan_rules = get_rules(options.get('choice_rules'))
         self.show_progress = options.get('show_progress')
         self.cpu = options.get('cpu_core')
+        self.queue = options.get('queue')
         self.alternative_path = options.get('alternative_path')
         exts = options.get('choice_extensions')
         self.exts = [ext.lower() for ext in exts] if exts else []
@@ -65,15 +66,20 @@ def read_file_contents(self, paths: list) -> list:
 
     def regex_scan(self, file_contents) -> list:
         """Process regex matches on the file contents."""
-        # Use ProcessPoolExecutor for regex processing
-        with ProcessPoolExecutor(max_workers=self.cpu) as cpu_executor:
-
-            results = []
-            for content in file_contents:
-                # Process Choice Matcher on the file contents
-                process_future = cpu_executor.submit(
-                    self.choice_matcher, content)
-                results.append(process_future.result())
+        if self.queue:
+            # Use billiard's pool for regex (support queues)
+            from billiard import Pool
+            with Pool(processes=self.cpu) as pool:
+                # Run regex on file data
+                results = pool.map(
+                    self.choice_matcher,
+                    file_contents)
+        else:
+            # Use ProcessPoolExecutor for regex processing
+            with ProcessPoolExecutor(max_workers=self.cpu) as cpu_executor:
+                results = list(cpu_executor.map(
+                    self.choice_matcher,
+                    file_contents))
 
         self.add_finding(results)
         return self.findings

libsast/core_matcher/pattern_matcher.py

@@ -25,6 +25,7 @@ def __init__(self, options: dict) -> None:
         self.scan_rules = get_rules(options.get('match_rules'))
         self.show_progress = options.get('show_progress')
         self.cpu = options.get('cpu_core')
+        self.queue = options.get('queue')
         exts = options.get('match_extensions')
         self.exts = [ext.lower() for ext in exts] if exts else []
         self.findings = {}
@@ -62,14 +63,23 @@ def read_file_contents(self, paths: list) -> list:
 
     def regex_scan(self, file_contents: list) -> dict:
         """Scan file(s) content."""
-        # Use a ProcessPool for CPU-bound regex
-        with ProcessPoolExecutor(max_workers=self.cpu) as cpu_executor:
-
-            # Run regex on file data
-            results = cpu_executor.map(
-                self.pattern_matcher,
-                file_contents,
-            )
+        if self.queue:
+            # Use billiard's pool for CPU-bound regex (support queues)
+            from billiard import Pool
+            with Pool(processes=self.cpu) as cpu_executor:
+                # Run regex on file data
+                results = cpu_executor.map(
+                    self.pattern_matcher,
+                    file_contents,
+                )
+        else:
+            # Use a ProcessPool for CPU-bound regex
+            with ProcessPoolExecutor(max_workers=self.cpu) as cpu_executor:
+                # Run regex on file data
+                results = cpu_executor.map(
+                    self.pattern_matcher,
+                    file_contents,
+                )
 
         # Compile findings
         self.add_finding(results)

libsast/scanner.py

@@ -26,6 +26,7 @@ def __init__(self, options: dict, paths: list) -> None:
             'ignore_paths': [],
             'show_progress': False,
             'cpu_core': 1,
+            'queue': False,
             # Overwrite with options from invocation
             **(options or {}),
         }

poetry.lock

@@ -1,6 +1,6 @@
 [tool.poetry]
 name = "libsast"
-version = "3.1.1"
+version = "3.1.2"
 description = "A generic SAST library built on top of semgrep and regex"
 keywords = ["libsast", "SAST", "Python SAST", "SAST API", "Regex SAST", "Pattern Matcher"]
 authors = ["Ajin Abraham <[email protected]>"]
@@ -27,6 +27,7 @@ python = "^3.8"
 requests = "*"
 pyyaml = ">=6.0"
 semgrep = {version = "1.86.0", markers = "sys_platform != 'win32'"}
+billiard = "^4.2.1"
 
 [tool.poetry.group.dev.dependencies]
 bandit = "*"