Python: create semmle/python/dataflow/new/Regex.qll

Author: aibaars

python/ql/lib/semmle/python/RegexTreeView.qll

@@ -2,7 +2,6 @@
 
 import python
 private import semmle.python.regex
-private import semmle.python.dataflow.new.DataFlow
 
 /**
  * An element containing a regular expression term, that is, either
@@ -49,19 +48,6 @@ newtype TRegExpParent =
   /** A back reference */
   TRegExpBackRef(Regex re, int start, int end) { re.backreference(start, end) }
 
-/**
- * Provides utility predicates related to regular expressions.
- */
-module RegExpPatterns {
-  /**
-   * Gets a pattern that matches common top-level domain names in lower case.
-   */
-  string getACommonTld() {
-    // according to ranking by http://google.com/search?q=site:.<<TLD>>
-    result = "(?:com|org|edu|gov|uk|net|io)(?![a-z0-9])"
-  }
-}
-
 /**
  * An element containing a regular expression term, that is, either
  * a string literal (parsed as a regular expression)
@@ -1028,24 +1014,3 @@ class RegExpBackRef extends RegExpTerm, TRegExpBackRef {
 
 /** Gets the parse tree resulting from parsing `re`, if such has been constructed. */
 RegExpTerm getParsedRegExp(StrConst re) { result.getRegex() = re and result.isRootTerm() }
-
-/**
- * A node whose value may flow to a position where it is interpreted
- * as a part of a regular expression.
- */
-class RegExpPatternSource extends DataFlow::CfgNode {
-  private Regex astNode;
-
-  RegExpPatternSource() { astNode = this.asExpr() }
-
-  /**
-   * Gets a node where the pattern of this node is parsed as a part of
-   * a regular expression.
-   */
-  DataFlow::Node getAParse() { result = this }
-
-  /**
-   * Gets the root term of the regular expression parsed from this pattern.
-   */
-  RegExpTerm getRegExpTerm() { result.getRegex() = astNode }
-}

python/ql/lib/semmle/python/dataflow/new/Regexp.qll

@@ -0,0 +1,41 @@
+/**
+ * Provides classes for working with regular expressions.
+ */
+
+private import semmle.python.RegexTreeView
+private import semmle.python.regex
+private import semmle.python.dataflow.new.DataFlow
+
+/**
+ * Provides utility predicates related to regular expressions.
+ */
+module RegExpPatterns {
+  /**
+   * Gets a pattern that matches common top-level domain names in lower case.
+   */
+  string getACommonTld() {
+    // according to ranking by http://google.com/search?q=site:.<<TLD>>
+    result = "(?:com|org|edu|gov|uk|net|io)(?![a-z0-9])"
+  }
+}
+
+/**
+ * A node whose value may flow to a position where it is interpreted
+ * as a part of a regular expression.
+ */
+class RegExpPatternSource extends DataFlow::CfgNode {
+  private Regex astNode;
+
+  RegExpPatternSource() { astNode = this.asExpr() }
+
+  /**
+   * Gets a node where the pattern of this node is parsed as a part of
+   * a regular expression.
+   */
+  DataFlow::Node getAParse() { result = this }
+
+  /**
+   * Gets the root term of the regular expression parsed from this pattern.
+   */
+  RegExpTerm getRegExpTerm() { result.getRegex() = astNode }
+}

python/ql/src/Security/CWE-020/HostnameRegexpSpecific.qll

@@ -1,2 +1,3 @@
 import semmle.python.security.performance.RegExpTreeView
 import semmle.python.dataflow.new.DataFlow
+import semmle.python.dataflow.new.Regexp