feat(pipeline): PLC/SPS control-logic security scanner (IEC 61131-3) (#162)

compliance-agent/src/pipeline/plc/ast.rs

@@ -0,0 +1,226 @@
+//! Abstract syntax tree for IEC 61131-3 Structured Text (ST).
+//!
+//! This is the security-relevant subset: POUs with their variable declarations
+//! and statement bodies, enough to run semantic control-logic rules over. It is
+//! deliberately not a full language model — declarations we don't reason about
+//! (e.g. exotic type definitions) are parsed loosely and kept as raw text.
+
+/// A Program Organization Unit: a PROGRAM, FUNCTION, or FUNCTION_BLOCK.
+#[derive(Debug, Clone)]
+pub struct Pou {
+    pub name: String,
+    pub kind: PouKind,
+    /// The declared variables, across all VAR_* sections.
+    pub vars: Vec<VarDecl>,
+    /// The statement body.
+    pub body: Vec<Stmt>,
+    /// 1-based line where the POU header appears (in the source that was parsed).
+    pub line: u32,
+}
+
+#[derive(Debug, Clone, Copy, PartialEq, Eq)]
+pub enum PouKind {
+    Program,
+    Function,
+    FunctionBlock,
+}
+
+impl PouKind {
+    pub fn label(self) -> &'static str {
+        match self {
+            PouKind::Program => "PROGRAM",
+            PouKind::Function => "FUNCTION",
+            PouKind::FunctionBlock => "FUNCTION_BLOCK",
+        }
+    }
+}
+
+/// A single declared variable.
+#[derive(Debug, Clone)]
+pub struct VarDecl {
+    pub name: String,
+    pub section: VarSection,
+    /// The declared type as written (e.g. `BOOL`, `INT`, `ARRAY[0..9] OF INT`).
+    pub type_name: String,
+    /// Whether the type is an ARRAY, and its declared bounds `(lo, hi)` when
+    /// they are literal integers — used by the array-bounds rule.
+    pub array_bounds: Option<(i64, i64)>,
+    /// The initializer expression, if any (`:= <expr>`).
+    pub init: Option<Expr>,
+    pub line: u32,
+}
+
+#[derive(Debug, Clone, Copy, PartialEq, Eq)]
+pub enum VarSection {
+    Var,
+    Input,
+    Output,
+    InOut,
+    Global,
+    Temp,
+    External,
+}
+
+/// A statement.
+#[derive(Debug, Clone)]
+pub enum Stmt {
+    Assign {
+        target: Expr,
+        value: Expr,
+        line: u32,
+    },
+    If {
+        /// (condition, body) for IF and each ELSIF, in order.
+        branches: Vec<(Expr, Vec<Stmt>)>,
+        else_body: Option<Vec<Stmt>>,
+        line: u32,
+    },
+    Case {
+        selector: Expr,
+        /// (label expressions, body) per CASE arm.
+        arms: Vec<(Vec<Expr>, Vec<Stmt>)>,
+        else_body: Option<Vec<Stmt>>,
+        line: u32,
+    },
+    For {
+        var: String,
+        from: Expr,
+        to: Expr,
+        by: Option<Expr>,
+        body: Vec<Stmt>,
+        line: u32,
+    },
+    While {
+        cond: Expr,
+        body: Vec<Stmt>,
+        line: u32,
+    },
+    Repeat {
+        body: Vec<Stmt>,
+        until: Expr,
+        line: u32,
+    },
+    /// A bare call statement, e.g. `TON1(IN := x, PT := T#5s);`.
+    Call {
+        callee: String,
+        args: Vec<CallArg>,
+        line: u32,
+    },
+    Return {
+        line: u32,
+    },
+    Exit {
+        line: u32,
+    },
+    /// `JMP label;` — an unstructured jump.
+    Jump {
+        label: String,
+        line: u32,
+    },
+    /// `label:` — a jump target.
+    Label {
+        name: String,
+        line: u32,
+    },
+}
+
+/// One argument in a call: positional (`name: None`) or named (`X := expr`).
+#[derive(Debug, Clone)]
+pub struct CallArg {
+    pub name: Option<String>,
+    pub value: Expr,
+}
+
+/// An expression.
+#[derive(Debug, Clone)]
+pub enum Expr {
+    Int(i64, u32),
+    Real(f64, u32),
+    Bool(bool, u32),
+    /// A string literal, with the unquoted contents.
+    Str(String, u32),
+    /// A duration / date / time literal, kept as raw text (`T#5s`, `DT#...`).
+    Time(String, u32),
+    Ident(String, u32),
+    /// `base[index]`.
+    Index {
+        base: Box<Expr>,
+        index: Box<Expr>,
+        line: u32,
+    },
+    /// `base.field`.
+    Member {
+        base: Box<Expr>,
+        field: String,
+        line: u32,
+    },
+    Unary {
+        op: UnOp,
+        expr: Box<Expr>,
+        line: u32,
+    },
+    Binary {
+        op: BinOp,
+        lhs: Box<Expr>,
+        rhs: Box<Expr>,
+        line: u32,
+    },
+    /// A function call used as an expression, e.g. `LIMIT(a, b, c)`.
+    Call {
+        callee: String,
+        args: Vec<CallArg>,
+        line: u32,
+    },
+}
+
+impl Expr {
+    /// The 1-based source line this expression starts on.
+    pub fn line(&self) -> u32 {
+        match self {
+            Expr::Int(_, l)
+            | Expr::Real(_, l)
+            | Expr::Bool(_, l)
+            | Expr::Str(_, l)
+            | Expr::Time(_, l)
+            | Expr::Ident(_, l)
+            | Expr::Index { line: l, .. }
+            | Expr::Member { line: l, .. }
+            | Expr::Unary { line: l, .. }
+            | Expr::Binary { line: l, .. }
+            | Expr::Call { line: l, .. } => *l,
+        }
+    }
+
+    /// If this expression is a plain identifier, its name.
+    pub fn as_ident(&self) -> Option<&str> {
+        match self {
+            Expr::Ident(name, _) => Some(name.as_str()),
+            _ => None,
+        }
+    }
+}
+
+#[derive(Debug, Clone, Copy, PartialEq, Eq)]
+pub enum UnOp {
+    Not,
+    Neg,
+}
+
+#[derive(Debug, Clone, Copy, PartialEq, Eq)]
+pub enum BinOp {
+    Add,
+    Sub,
+    Mul,
+    Div,
+    Mod,
+    Pow,
+    Eq,
+    Ne,
+    Lt,
+    Le,
+    Gt,
+    Ge,
+    And,
+    Or,
+    Xor,
+}