PS: Also extract files from the PSModulePath environment variable.

Author: MathiasVP

powershell/extractor/Semmle.Extraction.PowerShell.Standalone/Options.cs

@@ -24,6 +24,9 @@ public override bool HandleFlag(string key, bool value)
                 case "dry-run":
                     SkipExtraction = value;
                     return true;
+                case "skip-psmodulepath-files":
+                    SkipPSModulePathFiles = value;
+                    return true;
                 default:
                     return base.HandleFlag(key, value);
             }
@@ -127,6 +130,12 @@ private static FileInfo[] GetDefaultFiles()
         /// </summary>
         public bool SkipExtraction { get; private set; } = false;
 
+        /// <summary>
+        /// Whether to extract files in the paths found in the `PSModulePath`
+        /// environment variable.
+        /// </summary>
+        public bool SkipPSModulePathFiles { get; private set; } = false;
+
         /// <summary>
         /// Whether errors were encountered parsing the arguments.
         /// </summary>
@@ -158,13 +167,14 @@ public static void ShowHelp(System.IO.TextWriter output)
                 "PowerShell# standalone extractor\n\nExtracts PowerShell scripts in the current directory.\n"
             );
             output.WriteLine("Additional options:\n");
-            output.WriteLine("    <path>           Use the provided path instead.");
+            output.WriteLine("    <path>                       Use the provided path instead.");
             output.WriteLine(
-                "    --exclude:xxx    Exclude a file or directory (can be specified multiple times)"
+                "    --exclude:xxx                Exclude a file or directory (can be specified multiple times)"
             );
-            output.WriteLine("    --dry-run        Stop before extraction");
-            output.WriteLine("    --threads:nnn    Specify number of threads (default=CPU cores)");
-            output.WriteLine("    --verbose        Produce more output");
+            output.WriteLine("    --dry-run                    Stop before extraction");
+            output.WriteLine("    --threads:nnn                Specify number of threads (default=CPU cores)");
+            output.WriteLine("    --verbose                    Produce more output");
+            output.WriteLine("    --skip-psmodulepath-files    Avoid extracting source files in paths specified by the PSModulePath environment variable.");
         }
 
         private Options() { }

powershell/extractor/Semmle.Extraction.PowerShell.Standalone/Program.cs

@@ -45,7 +45,8 @@ public static int Main(string[] args)
 
             output.Log(Severity.Info, "Running PowerShell standalone extractor");
             var sourceFiles = options
-                .Files.Where(d =>
+                .Files.Concat(GetPSModuleFiles(options))
+                .Where(d =>
                     options.Extensions.Contains(
                         d.Extension,
                         StringComparer.InvariantCultureIgnoreCase
@@ -87,6 +88,30 @@ public static int Main(string[] args)
             return 0;
         }
 
+        private static String[] GetPSModulePaths()
+        {
+            return Environment.GetEnvironmentVariable("PSModulePath")?.Split(Path.PathSeparator)
+                ?? Array.Empty<string>();
+        }
+
+        private static IEnumerable<FileInfo> GetPSModuleFiles(Options options)
+        {
+            if(options.SkipPSModulePathFiles)
+            {
+                return Array.Empty<FileInfo>();
+            }
+            
+            return GetPSModulePaths()
+                .Where(d => Directory.Exists(d))
+                .SelectMany(d =>
+                {
+                    var di = new DirectoryInfo(d);
+                    return di.Exists
+                        ? di.GetFiles("*.*", SearchOption.AllDirectories)
+                        : new FileInfo[] { new(d) };
+                });
+        }
+
         private class ExtractionProgress : IProgressMonitor
         {
             public ExtractionProgress(ILogger output)