C#: Implement compilation_referencing_files and update comments for C#.

Author: calumgrant

csharp/extractor/Semmle.Extraction.CSharp/Entities/Compilation.cs

@@ -1,4 +1,5 @@
-using System;
+using Microsoft.CodeAnalysis;
+using System;
 using System.Collections.Generic;
 using System.Diagnostics;
 using System.Linq;
@@ -28,6 +29,13 @@ public Compilation(Context cx, string cwd, string[] args) : base(cx)
                 cx.Emit(Tuples.compilation_compiling_files(this, index++, file));
             }
 
+            // References
+            index = 0;
+            foreach(var file in cx.Compilation.References.OfType<PortableExecutableReference>().Select(r => Extraction.Entities.File.Create(cx, r.FilePath)))
+            {
+                cx.Emit(Tuples.compilation_referencing_files(this, index++, file));
+            }
+
             // Diagnostics
             index = 0;
             foreach(var diag in cx.Compilation.GetDiagnostics().Select(d => new Diagnostic(cx, d)))

csharp/extractor/Semmle.Extraction.CSharp/Tuples.cs

@@ -45,6 +45,8 @@ internal static class Tuples
 
         internal static Tuple compilation_compiling_files(Compilation compilation, int index, File file) => new Tuple("compilation_compiling_files", compilation, index, file);
 
+        internal static Tuple compilation_referencing_files(Compilation compilation, int index, File file) => new Tuple("compilation_referencing_files", compilation, index, file);
+
         internal static Tuple compilation_finished(Compilation compilation, float cpuSeconds, float elapsedSeconds) => new Tuple("compilation_finished", compilation, cpuSeconds, elapsedSeconds);
 
         internal static Tuple compilation_time(Compilation compilation, int num, int index, float metric) => new Tuple("compilation_time", compilation, num, index, metric);

csharp/ql/src/semmle/code/csharp/commons/Compilation.qll

@@ -24,6 +24,12 @@ class Compilation extends @compilation {
   /** Gets a source file compiled in this compilation. */
   File getAFileCompiled() { result = getFileCompiled(_) }
 
+  /** Gets the `i`th reference in this compilation. */
+  File getReference(int i) { compilation_referencing_files(this, i, result) }
+
+  /** Gets a reference in this compilation. */
+  File getAReference() { result = getReference(_) }
+
   /** Gets a diagnostic associated with this compilation. */
   Diagnostic getADiagnostic() { result.getCompilation() = this }
 

csharp/ql/src/semmlecode.csharp.dbscheme

@@ -4,19 +4,12 @@
  * compiled per invocation. For example, this command compiles three
  * source files:
  *
- *   gcc -c f1.c f2.c f3.c
+ *   csc f1.cs f2.cs f3.cs
  *
  * The `id` simply identifies the invocation, while `cwd` is the working
  * directory from which the compiler was invoked.
  */
 compilations(
-    /**
-     * An invocation of the compiler. Note that more than one file may
-     * be compiled per invocation. For example, this command compiles
-     * three source files:
-     *
-     *   gcc -c f1.c f2.c f3.c
-     */
     unique int id : @compilation,
     string cwd : string ref
 );
@@ -25,19 +18,18 @@ compilations(
  * The arguments that were passed to the extractor for a compiler
  * invocation. If `id` is for the compiler invocation
  *
- *   gcc -c f1.c f2.c f3.c
+ *   csc f1.cs f2.cs f3.cs
  *
  * then typically there will be rows for
  *
  * num | arg
  * --- | ---
- * 0   | *path to extractor*
- * 1   | `--mimic`
- * 2   | `/usr/bin/gcc`
- * 3   | `-c`
- * 4   | f1.c
- * 5   | f2.c
- * 6   | f3.c
+ * 0   | --compiler
+ * 1   | *path to compiler*
+ * 2   | --cil
+ * 3   | f1.cs
+ * 4   | f2.cs
+ * 5   | f3.cs
  */
 #keyset[id, num]
 compilation_args(
@@ -50,18 +42,15 @@ compilation_args(
  * The source files that are compiled by a compiler invocation.
  * If `id` is for the compiler invocation
  *
- *   gcc -c f1.c f2.c f3.c
+ *   csc f1.cs f2.cs f3.cs
  *
  * then there will be rows for
  *
  * num | arg
  * --- | ---
- * 0   | f1.c
- * 1   | f2.c
- * 2   | f3.c
- *
- * Note that even if those files `#include` headers, those headers
- * do not appear as rows.
+ * 0   | f1.cs
+ * 1   | f2.cs
+ * 2   | f3.cs
  */
 #keyset[id, num]
 compilation_compiling_files(
@@ -70,6 +59,27 @@ compilation_compiling_files(
     int file : @file ref
 );
 
+/**
+ * The references used by a compiler invocation.
+ * If `id` is for the compiler invocation
+ *
+ *   csc f1.cs f2.cs f3.cs /r:ref1.dll /r:ref2.dll /r:ref3.dll
+ *
+ * then there will be rows for
+ *
+ * num | arg
+ * --- | ---
+ * 0   | ref1.dll
+ * 1   | ref2.dll
+ * 2   | ref3.dll
+ */
+#keyset[id, num]
+compilation_referencing_files(
+    int id : @compilation ref,
+    int num : int ref,
+    int file : @file ref
+);
+
 /**
  * The time taken by the extractor for a compiler invocation.
  *

csharp/ql/test/library-tests/compilations/Compilations.expected

@@ -28,3 +28,10 @@ diagnosticElements
 | Program.cs:7:13:7:13 | CS0219: The variable 'x' is assigned but its value is never used | Program.cs:7:13:7:13 | x |
 | Program.cs:9:13:9:13 | CS0219: The variable 'y' is assigned but its value is never used | Program.cs:9:13:9:13 | access to local variable y |
 | Program.cs:9:13:9:13 | CS0219: The variable 'y' is assigned but its value is never used | Program.cs:9:13:9:13 | y |
+references
+| compilation | 0 | System.Core.dll |
+| compilation | 1 | System.Console.dll |
+| compilation | 2 | mscorlib.dll |
+| compilation | 3 | System.Runtime.dll |
+| compilation | 4 | System.dll |
+| compilation | 5 | System.Private.CoreLib.dll |

csharp/ql/test/library-tests/compilations/Compilations.ql

@@ -30,3 +30,7 @@ query predicate compilationFolder(Compilation c, string folder) {
 }
 
 query predicate diagnosticElements(Diagnostic d, Element e) { e = d.getElement() }
+
+query predicate references(Compilation c, int i, string reference) {
+  reference = c.getReference(i).getBaseName()
+}