Added Rust files as stub

3 files changed, 223 insertions, 3 deletions

diff --git a/.gitignore b/.gitignore
index 97f2a16..9a7d9b6 100644
--- a/.gitignore
+++ b/.gitignore
@@ -1,6 +1,6 @@
 yara
-# Created by https://www.toptal.com/developers/gitignore/api/python,windows,linux,macos,visualstudiocode
-# Edit at https://www.toptal.com/developers/gitignore?templates=python,windows,linux,macos,visualstudiocode
+# Created by https://www.toptal.com/developers/gitignore/api/rust,linux,macos,python,windows,visualstudiocode
+# Edit at https://www.toptal.com/developers/gitignore?templates=rust,linux,macos,python,windows,visualstudiocode
 
 ### Linux ###
 *~
@@ -222,6 +222,21 @@ poetry.toml
 # LSP config files
 pyrightconfig.json
 
+### Rust ###
+# Generated by Cargo
+# will have compiled files and executables
+debug/
+
+# Remove Cargo.lock from gitignore if creating an executable, leave it for libraries
+# More information here https://doc.rust-lang.org/cargo/guide/cargo-toml-vs-cargo-lock.html
+Cargo.lock
+
+# These are backup files generated by rustfmt
+**/*.rs.bk
+
+# MSVC Windows builds of rustc generate these, which store debugging information
+*.pdb
+
 ### VisualStudioCode ###
 .vscode/*
 !.vscode/settings.json
@@ -267,4 +282,8 @@ $RECYCLE.BIN/
 # Windows shortcuts
 *.lnk
 
-# End of https://www.toptal.com/developers/gitignore/api/python,windows,linux,macos,visualstudiocode
\ No newline at end of file
+# End of https://www.toptal.com/developers/gitignore/api/rust,linux,macos,python,windows,visualstudiocode
+
+# Added by cargo
+
+/target
diff --git a/Cargo.toml b/Cargo.toml
new file mode 100644
index 0000000..66b5e5a
--- /dev/null
+++ b/Cargo.toml
@@ -0,0 +1,11 @@
+[package]
+name = "yara-compiler"
+version = "0.1.0"
+edition = "2024"
+
+[dependencies]
+regex = "1"
+serde = { version = "1", features = ["derive"] }
+serde_json = "1"
+log = "0.4"
+byteorder = "1.4"
\ No newline at end of file
diff --git a/src/main.rs b/src/main.rs
new file mode 100644
index 0000000..e23d224
--- /dev/null
+++ b/src/main.rs
@@ -0,0 +1,190 @@
+use std::fs::File;
+use std::io::Read;
+use std::path::Path;
+use std::collections::HashMap;
+
+use byteorder::{WriteBytesExt, BigEndian};
+use regex::Regex;
+use serde::Deserialize;
+use log::{debug, warn};
+
+#[derive(Debug)]
+struct OperatorTree {
+    left: Box<OperatorNode>,
+    right: Box<OperatorNode>,
+    operator: u8,
+}
+
+#[derive(Debug)]
+struct OperatorOf {
+    n: String,
+    pattern: String,
+}
+
+#[derive(Debug)]
+enum OperatorNode {
+    Tree(OperatorTree),
+    Of(OperatorOf),
+    Identifier(String),
+}
+
+#[derive(Deserialize, Debug)]
+struct RuleString {
+    id: String,
+    #[serde(rename = "type")]
+    string_type: u8,
+    text: String,
+    modifiers: HashMap<String, bool>,
+}
+
+#[derive(Deserialize, Debug)]
+struct RuleEntry {
+    identifier: String,
+    condition: String,
+    strings: Vec<RuleString>,
+}
+
+pub struct YaraDatabase {
+    entries: Vec<RuleEntry>,
+    pub data: Vec<u8>,
+}
+
+impl YaraDatabase {
+    const STRING_TYPE_STRING: u8 = 0;
+    const STRING_TYPE_HEX: u8 = 1;
+    const STRING_TYPE_REGEX: u8 = 2;
+
+    const WILDCARD_NIBBLE_LOW: u8 = 0;
+    const WILDCARD_NIBBLE_HIGH: u8 = 1;
+    const WILDCARD_NIBBLE_BOTH: u8 = 2;
+
+    const CONDITION_OPERATOR_OR: u8 = 0;
+    const CONDITION_OPERATOR_AND: u8 = 1;
+    const CONDITION_OPERATOR_OF: u8 = 2;
+    const CONDITION_OPERATOR_SINGLE: u8 = 3;
+    const CONDITION_OPERATOR_TRUE: u8 = 4;
+
+    pub fn new() -> Self {
+        YaraDatabase {
+            entries: Vec::new(),
+            data: Vec::new(),
+        }
+    }
+
+    pub fn add_file<P: AsRef<Path>>(&mut self, path: P) -> Result<(), Box<dyn std::error::Error>> {
+        let mut f = File::open(path)?;
+        let mut content = String::new();
+        f.read_to_string(&mut content)?;
+        let json: serde_json::Value = serde_json::from_str(&content)?;
+        if let Some(rules) = json.get("rules") {
+            self.entries.extend(serde_json::from_value::<Vec<RuleEntry>>(rules.clone())?);
+        }
+        Ok(())
+    }
+
+    fn build_tree(condition: &str) -> OperatorNode {
+        let pattern_or = Regex::new(r"(.*)\s+or\s+(.*)").unwrap();
+        let pattern_and = Regex::new(r"(.*)\s+and\s+(.*)").unwrap();
+        let pattern_of = Regex::new(r"((\d+)|(all)|(any))\s+of\s+([\w\_\(\)\$\*\,]+)").unwrap();
+
+        debug!("Parsing condition = {}", condition);
+
+        if let Some(caps) = pattern_or.captures(condition) {
+            return OperatorNode::Tree(OperatorTree {
+                left: Box::new(Self::build_tree(&caps[1])),
+                right: Box::new(Self::build_tree(&caps[2])),
+                operator: Self::CONDITION_OPERATOR_OR,
+            });
+        }
+
+        if let Some(caps) = pattern_and.captures(condition) {
+            return OperatorNode::Tree(OperatorTree {
+                left: Box::new(Self::build_tree(&caps[1])),
+                right: Box::new(Self::build_tree(&caps[2])),
+                operator: Self::CONDITION_OPERATOR_AND,
+            });
+        }
+
+        if let Some(caps) = pattern_of.captures(condition) {
+            let n = caps[1].to_string();
+            let pattern = caps[5].to_string();
+            debug!("Leaf: OperatorOf, n = {}, pattern = {}", n, pattern);
+            return OperatorNode::Of(OperatorOf { n, pattern });
+        }
+
+        debug!("Leaf: remainder = {}", condition);
+        OperatorNode::Identifier(condition.trim().to_string())
+    }
+
+    fn compile_tree(node: &OperatorNode, strings: &[String]) -> Vec<u8> {
+        let mut data = Vec::new();
+
+        match node {
+            OperatorNode::Tree(tree) => {
+                data.write_u8(tree.operator).unwrap();
+                data.extend(Self::compile_tree(&tree.left, strings));
+                data.extend(Self::compile_tree(&tree.right, strings));
+            }
+            OperatorNode::Of(op_of) => {
+                debug!("Compiling OperatorOf, n = {}, pattern = {}", op_of.n, op_of.pattern);
+                data.write_u8(Self::CONDITION_OPERATOR_OF).unwrap();
+
+                let mut pattern = String::new();
+                let mut para = 0;
+                for c in op_of.pattern.chars() {
+                    match c {
+                        '$' => pattern.push_str(r"\$"),
+                        '*' => pattern.push_str(".*"),
+                        ',' => pattern.push_str(")|("),
+                        '(' => { pattern.push('('); para += 1; }
+                        ')' => {
+                            if para == 0 {
+                                warn!("Unmatched parenthesis in pattern {}", op_of.pattern);
+                            } else {
+                                pattern.push(')');
+                                para -= 1;
+                            }
+                        }
+                        ' ' => {}
+                        other => pattern.push(other),
+                    }
+                }
+                let re = Regex::new(&format!("^({})$", pattern)).unwrap();
+                let of_elements: Vec<u8> = strings.iter().enumerate()
+                    .filter(|(_, s)| re.is_match(s))
+                    .map(|(i, _)| i as u8)
+                    .collect();
+
+                let n = match op_of.n.as_str() {
+                    "all" => 0,
+                    "any" => 1,
+                    _ => op_of.n.parse::<u8>().unwrap_or(0),
+                };
+
+                data.write_u8(n).unwrap();
+                data.write_u8(of_elements.len() as u8).unwrap();
+                for e in of_elements {
+                    data.write_u8(e).unwrap();
+                }
+            }
+            OperatorNode::Identifier(id) => {
+                debug!("Compiling single identifier {}", id);
+                let mut found = false;
+                for (i, s) in strings.iter().enumerate() {
+                    if s == id {
+                        data.write_u8(Self::CONDITION_OPERATOR_SINGLE).unwrap();
+                        data.write_u8(i as u8).unwrap();
+                        found = true;
+                        break;
+                    }
+                }
+                if !found {
+                    warn!("Single identifier {} not found, defaulting to true", id);
+                    data.write_u8(Self::CONDITION_OPERATOR_TRUE).unwrap();
+                }
+            }
+        }
+
+        data
+    }
+}