Python: add regex parser

python/ql/src/semmle/python/PrintAst.qll

@@ -7,6 +7,7 @@
  */
 
 import python
+import semmle.python.RegexTreeView
 
 private newtype TPrintAstConfiguration = MkPrintAstConfiguration()
 
@@ -53,6 +54,9 @@ private newtype TPrintAstNode =
     not list = any(Module mod).getBody() and
     not forall(AstNode child | child = list.getAnItem() | isNotNeeded(child)) and
     exists(list.getAnItem())
+  } or
+  TRegExpTermNode(RegExpTerm term) {
+    exists(StrConst str | term.getRootTerm() = getParsedRegExp(str) and shouldPrint(str, _))
   }
 
 /**
@@ -419,6 +423,41 @@ class ParameterNode extends AstElementNode {
   }
 }
 
+/**
+ * A print node for a `StrConst`.
+ *
+ * The string has a child, if the child is used as a regular expression,
+ * which is the root of the regular expression.
+ */
+class StrConstNode extends AstElementNode {
+  override StrConst element;
+
+  override PrintAstNode getChild(int childIndex) {
+    childIndex = 0 and result.(RegExpTermNode).getTerm() = getParsedRegExp(element)
+  }
+}
+
+/**
+ * A print node for a regular expression term.
+ */
+class RegExpTermNode extends TRegExpTermNode, PrintAstNode {
+  RegExpTerm term;
+
+  RegExpTermNode() { this = TRegExpTermNode(term) }
+
+  RegExpTerm getTerm() { result = term }
+
+  override PrintAstNode getChild(int childIndex) {
+    result.(RegExpTermNode).getTerm() = term.getChild(childIndex)
+  }
+
+  override string toString() {
+    result = "[" + strictconcat(term.getPrimaryQLClass(), " | ") + "] " + term.toString()
+  }
+
+  override Location getLocation() { result = term.getLocation() }
+}
+
 /**
  * Gets the `i`th child from `node` ordered by location.
  */

python/ql/src/semmle/python/RegexLiteral.qll

@@ -0,0 +1,30 @@
+import python
+import semmle.python.regex as R
+private import RegexParserExtended
+
+class RegexLiteralValue extends ParsedString {
+  R::Regex lit;
+
+  RegexLiteralValue() {
+    this = lit.getText() and
+    exists(lit.getLocation().getFile().getRelativePath())
+  }
+
+  override ParserConfiguration getConfiguration() { result instanceof RegexParserConfiguration }
+
+  override predicate getLocationInfo(
+    string file, int startline, int startcol, int endline, int endcol
+  ) {
+    lit.getLocation().hasLocationInfo(file, startline + 1, startcol - 2, endline + 1, endcol - 2)
+  }
+
+  R::Regex getLiteral() { result = lit }
+}
+
+class RegexLiteral extends R::Regex {
+  RegexLiteralValue val;
+
+  RegexLiteral() { val.getLiteral() = this }
+
+  Regex getRegex() { result.getText() = val and result.isRoot() }
+}