Merge pull request github#9024 from hvitved/dataflow/content-flow-lib

Data flow: Introduce `ContentDataFlow.qll`

Author: hvitved

config/identical-files.json

@@ -22,6 +22,7 @@
     "csharp/ql/lib/semmle/code/csharp/dataflow/internal/DataFlowImpl3.qll",
     "csharp/ql/lib/semmle/code/csharp/dataflow/internal/DataFlowImpl4.qll",
     "csharp/ql/lib/semmle/code/csharp/dataflow/internal/DataFlowImpl5.qll",
+    "csharp/ql/lib/semmle/code/csharp/dataflow/internal/DataFlowImplForContentDataFlow.qll",
     "python/ql/lib/semmle/python/dataflow/new/internal/DataFlowImpl.qll",
     "python/ql/lib/semmle/python/dataflow/new/internal/DataFlowImpl2.qll",
     "python/ql/lib/semmle/python/dataflow/new/internal/DataFlowImpl3.qll",
@@ -559,4 +560,4 @@
     "javascript/ql/src/Expressions/TypoDatabase.qll",
     "ql/ql/src/codeql_ql/style/TypoDatabase.qll"
   ]
-}
+}

cpp/ql/lib/semmle/code/cpp/dataflow/internal/DataFlowImplCommon.qll

@@ -788,24 +788,31 @@ private module Cached {
   cached
   predicate readSet(Node node1, ContentSet c, Node node2) { readStep(node1, c, node2) }
 
+  cached
+  predicate storeSet(
+    Node node1, ContentSet c, Node node2, DataFlowType contentType, DataFlowType containerType
+  ) {
+    storeStep(node1, c, node2) and
+    contentType = getNodeDataFlowType(node1) and
+    containerType = getNodeDataFlowType(node2)
+    or
+    exists(Node n1, Node n2 |
+      n1 = node1.(PostUpdateNode).getPreUpdateNode() and
+      n2 = node2.(PostUpdateNode).getPreUpdateNode()
+    |
+      argumentValueFlowsThrough(n2, TReadStepTypesSome(containerType, c, contentType), n1)
+      or
+      readSet(n2, c, n1) and
+      contentType = getNodeDataFlowType(n1) and
+      containerType = getNodeDataFlowType(n2)
+    )
+  }
+
   private predicate store(
     Node node1, Content c, Node node2, DataFlowType contentType, DataFlowType containerType
   ) {
-    exists(ContentSet cs | c = cs.getAStoreContent() |
-      storeStep(node1, cs, node2) and
-      contentType = getNodeDataFlowType(node1) and
-      containerType = getNodeDataFlowType(node2)
-      or
-      exists(Node n1, Node n2 |
-        n1 = node1.(PostUpdateNode).getPreUpdateNode() and
-        n2 = node2.(PostUpdateNode).getPreUpdateNode()
-      |
-        argumentValueFlowsThrough(n2, TReadStepTypesSome(containerType, cs, contentType), n1)
-        or
-        readSet(n2, cs, n1) and
-        contentType = getNodeDataFlowType(n1) and
-        containerType = getNodeDataFlowType(n2)
-      )
+    exists(ContentSet cs |
+      c = cs.getAStoreContent() and storeSet(node1, cs, node2, contentType, containerType)
     )
   }
 

cpp/ql/lib/semmle/code/cpp/ir/dataflow/internal/DataFlowImplCommon.qll

@@ -788,24 +788,31 @@ private module Cached {
   cached
   predicate readSet(Node node1, ContentSet c, Node node2) { readStep(node1, c, node2) }
 
+  cached
+  predicate storeSet(
+    Node node1, ContentSet c, Node node2, DataFlowType contentType, DataFlowType containerType
+  ) {
+    storeStep(node1, c, node2) and
+    contentType = getNodeDataFlowType(node1) and
+    containerType = getNodeDataFlowType(node2)
+    or
+    exists(Node n1, Node n2 |
+      n1 = node1.(PostUpdateNode).getPreUpdateNode() and
+      n2 = node2.(PostUpdateNode).getPreUpdateNode()
+    |
+      argumentValueFlowsThrough(n2, TReadStepTypesSome(containerType, c, contentType), n1)
+      or
+      readSet(n2, c, n1) and
+      contentType = getNodeDataFlowType(n1) and
+      containerType = getNodeDataFlowType(n2)
+    )
+  }
+
   private predicate store(
     Node node1, Content c, Node node2, DataFlowType contentType, DataFlowType containerType
   ) {
-    exists(ContentSet cs | c = cs.getAStoreContent() |
-      storeStep(node1, cs, node2) and
-      contentType = getNodeDataFlowType(node1) and
-      containerType = getNodeDataFlowType(node2)
-      or
-      exists(Node n1, Node n2 |
-        n1 = node1.(PostUpdateNode).getPreUpdateNode() and
-        n2 = node2.(PostUpdateNode).getPreUpdateNode()
-      |
-        argumentValueFlowsThrough(n2, TReadStepTypesSome(containerType, cs, contentType), n1)
-        or
-        readSet(n2, cs, n1) and
-        contentType = getNodeDataFlowType(n1) and
-        containerType = getNodeDataFlowType(n2)
-      )
+    exists(ContentSet cs |
+      c = cs.getAStoreContent() and storeSet(node1, cs, node2, contentType, containerType)
     )
   }