Generate UIDs for AST nodes with Expression base class

docs/rtd/parsing_rulesets.rst

@@ -302,7 +302,8 @@ Let's say we want to print each function that is in called in the rule condition
 Expression types
 ****************
 
-There are a lot of expression types that you can visit. Here is a list of them all:
+Each expression type has its own unique id (uid). These uids are unique only within scope of a single rule,
+this allows to identify specific node in the AST for extra processing. There are a lot of expression types that you can visit. Here is a list of them all:
 
 **String expressions**
 

include/yaramod/parser/parser_driver.h

@@ -19,6 +19,7 @@
 #include <pog/pog.h>
 
 #include "yaramod/parser/file_context.h"
+#include "yaramod/parser/uid_generator.h"
 #include "yaramod/parser/value.h"
 #include "yaramod/types/expressions.h"
 #include "yaramod/types/meta.h"
@@ -204,6 +205,8 @@ class ParserDriver
 	bool _sectionStrings = false; ///< flag used to determine if we parse section after 'strings:'
 	bool _escapedContent = false; ///< flag used to determine if a currently parsed literal contains hexadecimal byte (such byte must be unescaped in getPureText())
 
+	UidGenerator _uidGen;
+
 	ParserMode _mode; ///< Parser mode.
 
 	Features _features; ///< Used to determine whether to include Avast-specific or VirusTotal-specific symbols or to skip them

include/yaramod/parser/uid_generator.h

@@ -0,0 +1,32 @@
+/**
+ * @file src/parser/uid_generator.h
+ * @brief Declaration of class UidGenerator.
+ * @copyright (c) 2022 Avast Software, licensed under the MIT license
+*/
+
+#pragma once
+
+#include <cstdint>
+
+namespace yaramod {
+
+/**
+ * Class that deterministically generates 
+ * up to 2^64 unique IDs for AST nodes
+ *
+ * The IDs are unique for a given input
+ * so only pair (input; node) has a UID
+ * This means UidGenerator has to be reset
+ * For every new input
+ */
+class UidGenerator 
+{
+public:
+	std::uint64_t next() { return _counter++; }
+	void reset() { _counter = 0; }
+
+private:
+	std::uint64_t _counter = 0;
+};
+
+} // namespace yaramod

include/yaramod/types/expression.h

@@ -6,6 +6,7 @@
 
 #pragma once
 
+#include <cstdint>
 #include <memory>
 #include <sstream>
 #include <string>
@@ -56,6 +57,7 @@ class Expression
 
 	/// @name Getter methods
 	/// @{
+	std::uint64_t getUid() const { return _uid; }
 	Expression::Type getType() const { return _type; }
 	std::string getTypeString() const
 	{
@@ -86,6 +88,7 @@ class Expression
 
 	/// @name Setter methods
 	/// @{
+	void setUid(std::uint64_t uid) { _uid = uid; }
 	void setType(Expression::Type type) { _type = type; }
 	void setTokenStream(const std::shared_ptr<TokenStream>& ts) { _tokenStream = ts; }
 	/// @}
@@ -157,6 +160,7 @@ class Expression
 
 private:
 	Type _type; ///< Type of the expression
+	std::uint64_t _uid;
 };
 
 }