Files
compliance-scanner-agent/compliance-agent/src/pipeline/plc/parser.rs
T
sharang 6d02b138c6
CI / Check (push) Has been skipped
CI / Detect Changes (push) Successful in 3s
CI / Deploy Agent (push) Successful in 3m48s
CI / Deploy Dashboard (push) Successful in 2m51s
CI / Deploy Docs (push) Has been skipped
CI / Deploy MCP (push) Successful in 2m2s
feat(pipeline): PLC/SPS control-logic security scanner (IEC 61131-3) (#162)
2026-07-16 08:31:43 +00:00

767 lines
24 KiB
Rust

//! Recursive-descent parser for the security-relevant subset of Structured Text.
//!
//! Tolerant by design: it parses the POUs, variable sections, and statement
//! bodies it understands, and skips (with statement/POU-level recovery) anything
//! it does not, so a single odd construct never sinks the whole file.
use super::ast::*;
use super::lexer::{Keyword as K, Tok, Token};
pub struct Parser {
toks: Vec<Token>,
pos: usize,
}
impl Parser {
pub fn new(toks: Vec<Token>) -> Self {
Self { toks, pos: 0 }
}
// ── token helpers ──────────────────────────────────────────────
fn peek(&self) -> &Tok {
&self.toks[self.pos.min(self.toks.len() - 1)].kind
}
fn line(&self) -> u32 {
self.toks[self.pos.min(self.toks.len() - 1)].line
}
fn at_end(&self) -> bool {
matches!(self.peek(), Tok::Eof)
}
fn advance(&mut self) -> Tok {
let t = self.toks[self.pos.min(self.toks.len() - 1)].kind.clone();
if self.pos < self.toks.len() - 1 {
self.pos += 1;
}
t
}
fn eat(&mut self, t: &Tok) -> bool {
if self.peek() == t {
self.advance();
true
} else {
false
}
}
fn eat_kw(&mut self, k: K) -> bool {
if matches!(self.peek(), Tok::Kw(x) if *x == k) {
self.advance();
true
} else {
false
}
}
fn at_kw(&self, k: K) -> bool {
matches!(self.peek(), Tok::Kw(x) if *x == k)
}
fn ident(&mut self) -> Option<String> {
if let Tok::Ident(s) = self.peek() {
let s = s.clone();
self.advance();
Some(s)
} else {
None
}
}
// ── top level ──────────────────────────────────────────────────
/// Parse every POU in the token stream.
pub fn parse_units(&mut self) -> Vec<Pou> {
let mut pous = Vec::new();
while !self.at_end() {
match self.peek() {
Tok::Kw(K::Program) => {
self.advance();
if let Some(p) = self.parse_pou(PouKind::Program, K::EndProgram) {
pous.push(p);
}
}
Tok::Kw(K::Function) => {
self.advance();
if let Some(p) = self.parse_pou(PouKind::Function, K::EndFunction) {
pous.push(p);
}
}
Tok::Kw(K::FunctionBlock) => {
self.advance();
if let Some(p) = self.parse_pou(PouKind::FunctionBlock, K::EndFunctionBlock) {
pous.push(p);
}
}
// Skip TYPE...END_TYPE and anything else at top level.
_ => {
self.advance();
}
}
}
pous
}
fn parse_pou(&mut self, kind: PouKind, end: K) -> Option<Pou> {
let line = self.line();
let name = self.ident().unwrap_or_else(|| "<anonymous>".to_string());
// Optional `: return_type` for functions.
if self.eat(&Tok::Colon) {
let _ = self.advance(); // return type token
}
let mut vars = Vec::new();
// Variable sections precede the body.
while let Some(section) = self.var_section_kw() {
self.advance();
let _ = self.eat_kw(K::Constant); // CONSTANT is informational for our rules
self.parse_var_decls(section, &mut vars);
}
// Body statements until END_<kind>.
let mut body = Vec::new();
while !self.at_end() && !self.at_kw(end) {
if let Some(s) = self.parse_stmt() {
body.push(s);
}
}
self.eat_kw(end);
Some(Pou {
name,
kind,
vars,
body,
line,
})
}
fn var_section_kw(&self) -> Option<VarSection> {
match self.peek() {
Tok::Kw(K::Var) => Some(VarSection::Var),
Tok::Kw(K::VarInput) => Some(VarSection::Input),
Tok::Kw(K::VarOutput) => Some(VarSection::Output),
Tok::Kw(K::VarInOut) => Some(VarSection::InOut),
Tok::Kw(K::VarGlobal) => Some(VarSection::Global),
Tok::Kw(K::VarTemp) => Some(VarSection::Temp),
Tok::Kw(K::VarExternal) => Some(VarSection::External),
_ => None,
}
}
fn parse_var_decls(&mut self, section: VarSection, out: &mut Vec<VarDecl>) {
while !self.at_end() && !self.at_kw(K::EndVar) {
let line = self.line();
// names: a, b, c
let mut names = Vec::new();
match self.ident() {
Some(n) => names.push(n),
None => {
// Not a declaration we understand — skip to next ; or END_VAR.
self.sync_decl();
continue;
}
}
while self.eat(&Tok::Comma) {
if let Some(n) = self.ident() {
names.push(n);
}
}
if !self.eat(&Tok::Colon) {
self.sync_decl();
continue;
}
let (type_name, array_bounds) = self.parse_type();
let init = if self.eat(&Tok::Assign) {
Some(self.parse_expr())
} else {
None
};
self.eat(&Tok::Semi);
for n in names {
out.push(VarDecl {
name: n,
section,
type_name: type_name.clone(),
array_bounds,
init: init.clone(),
line,
});
}
}
self.eat_kw(K::EndVar);
}
/// Parse a (possibly ARRAY) type, returning its rendered name and literal
/// bounds when present.
fn parse_type(&mut self) -> (String, Option<(i64, i64)>) {
if self.eat_kw(K::Array) {
let mut bounds = None;
if self.eat(&Tok::LBrack) {
let lo = self.int_lit();
self.eat(&Tok::DotDot);
let hi = self.int_lit();
if let (Some(lo), Some(hi)) = (lo, hi) {
bounds = Some((lo, hi));
}
// Skip any further dimensions / tokens to the closing bracket.
while !self.at_end() && !self.eat(&Tok::RBrack) {
self.advance();
}
}
self.eat_kw(K::Of);
let elem = self.type_ident();
(format!("ARRAY OF {elem}"), bounds)
} else {
(self.type_ident(), None)
}
}
fn type_ident(&mut self) -> String {
// Types can be qualified idents; keep it simple: one token, plus any
// string-length suffix like STRING[80].
let base = match self.advance() {
Tok::Ident(s) => s,
Tok::Kw(_) => "TYPE".to_string(),
other => format!("{other:?}"),
};
if self.eat(&Tok::LBrack) {
while !self.at_end() && !self.eat(&Tok::RBrack) {
self.advance();
}
}
base
}
fn int_lit(&mut self) -> Option<i64> {
match self.peek() {
Tok::Int(n) => {
let n = *n;
self.advance();
Some(n)
}
Tok::Minus => {
self.advance();
if let Tok::Int(n) = self.peek() {
let n = -*n;
self.advance();
Some(n)
} else {
None
}
}
_ => None,
}
}
fn sync_decl(&mut self) {
while !self.at_end() && !self.eat(&Tok::Semi) && !self.at_kw(K::EndVar) {
self.advance();
}
}
fn sync_stmt(&mut self) {
while !self.at_end() && !self.eat(&Tok::Semi) {
// Stop at block terminators so recovery doesn't swallow structure.
if matches!(
self.peek(),
Tok::Kw(
K::EndIf
| K::EndFor
| K::EndWhile
| K::EndCase
| K::EndRepeat
| K::EndProgram
| K::EndFunction
| K::EndFunctionBlock
| K::Else
| K::Elsif
)
) {
return;
}
self.advance();
}
}
// ── statements ─────────────────────────────────────────────────
fn parse_stmt(&mut self) -> Option<Stmt> {
let line = self.line();
match self.peek().clone() {
Tok::Semi => {
self.advance();
None
}
Tok::Kw(K::If) => self.parse_if(),
Tok::Kw(K::Case) => self.parse_case(),
Tok::Kw(K::For) => self.parse_for(),
Tok::Kw(K::While) => self.parse_while(),
Tok::Kw(K::Repeat) => self.parse_repeat(),
Tok::Kw(K::Return) => {
self.advance();
self.eat(&Tok::Semi);
Some(Stmt::Return { line })
}
Tok::Kw(K::Exit) => {
self.advance();
self.eat(&Tok::Semi);
Some(Stmt::Exit { line })
}
Tok::Kw(K::Jmp) => {
self.advance();
let label = self.ident().unwrap_or_default();
self.eat(&Tok::Semi);
Some(Stmt::Jump { label, line })
}
Tok::Ident(name) => {
// Could be `label:`, `call(...)`, or an assignment.
// Lookahead: ident ':' (not ':=') → label.
if matches!(
self.toks.get(self.pos + 1).map(|t| &t.kind),
Some(Tok::Colon)
) && !matches!(self.toks.get(self.pos + 2).map(|t| &t.kind), Some(Tok::Eq))
{
self.advance(); // ident
self.advance(); // ':'
return Some(Stmt::Label { name, line });
}
let lhs = self.parse_expr();
if self.eat(&Tok::Assign) {
let value = self.parse_expr();
self.eat(&Tok::Semi);
Some(Stmt::Assign {
target: lhs,
value,
line,
})
} else if let Expr::Call { callee, args, .. } = lhs {
self.eat(&Tok::Semi);
Some(Stmt::Call { callee, args, line })
} else {
// Bare expression / FB invocation without args recognized —
// skip to the terminator.
self.sync_stmt();
None
}
}
_ => {
self.sync_stmt();
None
}
}
}
fn parse_block_until(&mut self, terms: &[K]) -> Vec<Stmt> {
let mut body = Vec::new();
while !self.at_end() && !terms.iter().any(|k| self.at_kw(*k)) {
if let Some(s) = self.parse_stmt() {
body.push(s);
}
}
body
}
fn parse_if(&mut self) -> Option<Stmt> {
let line = self.line();
self.eat_kw(K::If);
let mut branches = Vec::new();
let cond = self.parse_expr();
self.eat_kw(K::Then);
let body = self.parse_block_until(&[K::Elsif, K::Else, K::EndIf]);
branches.push((cond, body));
while self.eat_kw(K::Elsif) {
let c = self.parse_expr();
self.eat_kw(K::Then);
let b = self.parse_block_until(&[K::Elsif, K::Else, K::EndIf]);
branches.push((c, b));
}
let else_body = if self.eat_kw(K::Else) {
Some(self.parse_block_until(&[K::EndIf]))
} else {
None
};
self.eat_kw(K::EndIf);
self.eat(&Tok::Semi);
Some(Stmt::If {
branches,
else_body,
line,
})
}
fn parse_case(&mut self) -> Option<Stmt> {
let line = self.line();
self.eat_kw(K::Case);
let selector = self.parse_expr();
self.eat_kw(K::Of);
let mut arms = Vec::new();
let mut else_body = None;
while !self.at_end() && !self.at_kw(K::EndCase) {
if self.eat_kw(K::Else) {
else_body = Some(self.parse_block_until(&[K::EndCase]));
break;
}
// labels: expr {, expr} :
let mut labels = vec![self.parse_expr()];
while self.eat(&Tok::Comma) {
labels.push(self.parse_expr());
}
self.eat(&Tok::Colon);
let body = self.parse_block_until(&[K::EndCase, K::Else]);
arms.push((labels, body));
}
self.eat_kw(K::EndCase);
self.eat(&Tok::Semi);
Some(Stmt::Case {
selector,
arms,
else_body,
line,
})
}
fn parse_for(&mut self) -> Option<Stmt> {
let line = self.line();
self.eat_kw(K::For);
let var = self.ident().unwrap_or_default();
self.eat(&Tok::Assign);
let from = self.parse_expr();
self.eat_kw(K::To);
let to = self.parse_expr();
let by = if self.eat_kw(K::By) {
Some(self.parse_expr())
} else {
None
};
self.eat_kw(K::Do);
let body = self.parse_block_until(&[K::EndFor]);
self.eat_kw(K::EndFor);
self.eat(&Tok::Semi);
Some(Stmt::For {
var,
from,
to,
by,
body,
line,
})
}
fn parse_while(&mut self) -> Option<Stmt> {
let line = self.line();
self.eat_kw(K::While);
let cond = self.parse_expr();
self.eat_kw(K::Do);
let body = self.parse_block_until(&[K::EndWhile]);
self.eat_kw(K::EndWhile);
self.eat(&Tok::Semi);
Some(Stmt::While { cond, body, line })
}
fn parse_repeat(&mut self) -> Option<Stmt> {
let line = self.line();
self.eat_kw(K::Repeat);
let body = self.parse_block_until(&[K::Until, K::EndRepeat]);
self.eat_kw(K::Until);
let until = self.parse_expr();
self.eat_kw(K::EndRepeat);
self.eat(&Tok::Semi);
Some(Stmt::Repeat { body, until, line })
}
// ── expressions (precedence climbing) ──────────────────────────
pub fn parse_expr(&mut self) -> Expr {
self.parse_or()
}
fn parse_or(&mut self) -> Expr {
let mut lhs = self.parse_and();
loop {
let op = match self.peek() {
Tok::Kw(K::Or) => BinOp::Or,
Tok::Kw(K::Xor) => BinOp::Xor,
_ => break,
};
let line = self.line();
self.advance();
let rhs = self.parse_and();
lhs = Expr::Binary {
op,
lhs: Box::new(lhs),
rhs: Box::new(rhs),
line,
};
}
lhs
}
fn parse_and(&mut self) -> Expr {
let mut lhs = self.parse_cmp();
while matches!(self.peek(), Tok::Kw(K::And) | Tok::Amp) {
let op = BinOp::And;
let line = self.line();
self.advance();
let rhs = self.parse_cmp();
lhs = Expr::Binary {
op,
lhs: Box::new(lhs),
rhs: Box::new(rhs),
line,
};
}
lhs
}
fn parse_cmp(&mut self) -> Expr {
let mut lhs = self.parse_add();
loop {
let op = match self.peek() {
Tok::Eq => BinOp::Eq,
Tok::Ne => BinOp::Ne,
Tok::Lt => BinOp::Lt,
Tok::Le => BinOp::Le,
Tok::Gt => BinOp::Gt,
Tok::Ge => BinOp::Ge,
_ => break,
};
let line = self.line();
self.advance();
let rhs = self.parse_add();
lhs = Expr::Binary {
op,
lhs: Box::new(lhs),
rhs: Box::new(rhs),
line,
};
}
lhs
}
fn parse_add(&mut self) -> Expr {
let mut lhs = self.parse_mul();
loop {
let op = match self.peek() {
Tok::Plus => BinOp::Add,
Tok::Minus => BinOp::Sub,
_ => break,
};
let line = self.line();
self.advance();
let rhs = self.parse_mul();
lhs = Expr::Binary {
op,
lhs: Box::new(lhs),
rhs: Box::new(rhs),
line,
};
}
lhs
}
fn parse_mul(&mut self) -> Expr {
let mut lhs = self.parse_unary();
loop {
let op = match self.peek() {
Tok::Star => BinOp::Mul,
Tok::Slash => BinOp::Div,
Tok::Kw(K::Mod) => BinOp::Mod,
Tok::Power => BinOp::Pow,
_ => break,
};
let line = self.line();
self.advance();
let rhs = self.parse_unary();
lhs = Expr::Binary {
op,
lhs: Box::new(lhs),
rhs: Box::new(rhs),
line,
};
}
lhs
}
fn parse_unary(&mut self) -> Expr {
let line = self.line();
match self.peek() {
Tok::Kw(K::Not) => {
self.advance();
Expr::Unary {
op: UnOp::Not,
expr: Box::new(self.parse_unary()),
line,
}
}
Tok::Minus => {
self.advance();
Expr::Unary {
op: UnOp::Neg,
expr: Box::new(self.parse_unary()),
line,
}
}
_ => self.parse_postfix(),
}
}
fn parse_postfix(&mut self) -> Expr {
let mut e = self.parse_primary();
loop {
let line = self.line();
match self.peek() {
Tok::LBrack => {
self.advance();
let index = self.parse_expr();
self.eat(&Tok::RBrack);
e = Expr::Index {
base: Box::new(e),
index: Box::new(index),
line,
};
}
Tok::Dot => {
self.advance();
let field = self.ident().unwrap_or_default();
e = Expr::Member {
base: Box::new(e),
field,
line,
};
}
_ => break,
}
}
e
}
fn parse_primary(&mut self) -> Expr {
let line = self.line();
match self.advance() {
Tok::Int(n) => Expr::Int(n, line),
Tok::Real(r) => Expr::Real(r, line),
Tok::Bool(b) => Expr::Bool(b, line),
Tok::Str(s) => Expr::Str(s, line),
Tok::Time(t) => Expr::Time(t, line),
Tok::LParen => {
let e = self.parse_expr();
self.eat(&Tok::RParen);
e
}
Tok::Ident(name) => {
if self.eat(&Tok::LParen) {
let args = self.parse_call_args();
Expr::Call {
callee: name,
args,
line,
}
} else {
Expr::Ident(name, line)
}
}
// Unrecognized start of expression — yield a placeholder identifier.
_ => Expr::Ident(String::new(), line),
}
}
fn parse_call_args(&mut self) -> Vec<CallArg> {
let mut args = Vec::new();
if self.eat(&Tok::RParen) {
return args;
}
loop {
// Named arg: ident := expr (peek two tokens).
if let Tok::Ident(name) = self.peek().clone() {
if matches!(
self.toks.get(self.pos + 1).map(|t| &t.kind),
Some(Tok::Assign)
) {
self.advance(); // ident
self.advance(); // :=
let value = self.parse_expr();
args.push(CallArg {
name: Some(name),
value,
});
if self.eat(&Tok::Comma) {
continue;
}
break;
}
}
let value = self.parse_expr();
args.push(CallArg { name: None, value });
if self.eat(&Tok::Comma) {
continue;
}
break;
}
self.eat(&Tok::RParen);
args
}
}
/// Parse ST source into its POUs.
pub fn parse(src: &str) -> Vec<Pou> {
let toks = super::lexer::lex(src);
Parser::new(toks).parse_units()
}
#[cfg(test)]
mod tests {
use super::*;
const SAMPLE: &str = r#"
PROGRAM Main
VAR
idx : INT;
pw : STRING := 'admin123';
buf : ARRAY[0..9] OF INT;
ok : BOOL := FALSE;
END_VAR
// a comment
IF idx > 0 THEN
buf[idx] := idx * 2;
ELSE
JMP done;
END_IF;
Comm(IP := '10.0.0.1', PORT := 502);
done:
ok := TRUE;
END_PROGRAM
"#;
#[test]
fn parses_program_vars_and_body() {
let pous = parse(SAMPLE);
assert_eq!(pous.len(), 1, "one POU");
let p = &pous[0];
assert_eq!(p.name, "Main");
assert_eq!(p.kind, PouKind::Program);
// vars: idx, pw, buf, ok
assert_eq!(p.vars.len(), 4);
let pw = p.vars.iter().find(|v| v.name == "pw").expect("pw");
assert!(matches!(&pw.init, Some(Expr::Str(s, _)) if s == "admin123"));
let buf = p.vars.iter().find(|v| v.name == "buf").expect("buf");
assert_eq!(buf.array_bounds, Some((0, 9)));
// body has an IF, a Call, a Label, and an Assign
assert!(p.body.iter().any(|s| matches!(s, Stmt::If { .. })));
assert!(p
.body
.iter()
.any(|s| matches!(s, Stmt::Call { callee, .. } if callee == "Comm")));
assert!(p
.body
.iter()
.any(|s| matches!(s, Stmt::Label { name, .. } if name == "done")));
}
#[test]
fn jmp_inside_if_is_captured() {
let pous = parse(SAMPLE);
let p = &pous[0];
// find the IF, check its else branch has a JMP
let has_jmp = p.body.iter().any(|s| match s {
Stmt::If { else_body, .. } => else_body
.as_ref()
.map(|b| b.iter().any(|s| matches!(s, Stmt::Jump { .. })))
.unwrap_or(false),
_ => false,
});
assert!(has_jmp, "JMP should be parsed inside the ELSE branch");
}
}