mirror of
https://github.com/elicpeter/nyx.git
synced 2026-06-06 19:35:13 +02:00
* Introduce control flow graph (CFG) support: - Added `cfg.rs` with CFG generation and analysis utilities. - Integrated `petgraph` library for graph-based computations. - Updated `ast.rs` to utilize CFG for function analysis. - Modified `Cargo.toml` and `Cargo.lock` to include new dependencies. - Improved static analysis with taint tracking through CFG paths. * feat: enhance control flow analysis with taint tracking and node labeling * feat: improve control flow graph with enhanced node handling and new tests * Remove unnecessary reference marker in `byte_offset_to_point` comment. * Remove unnecessary reference marker in `byte_offset_to_point` comment. * Refactor `ast.rs` for performance and clarity; enhance `cfg.rs` with recursive CFG generation and improved classification logic for AST analysis. * Refactor CFG and taint tracking logic: - Enhanced `cfg.rs` with inline helper function `text_of` for cleaner UTF-8 handling in AST nodes. - Expanded `labels.rs` rules with detailed `Sources`, `Sanitizers`, and `Sinks` for improved classification. - Refined `push_node` to handle method call expressions with object-function pairing. - Simplified code handling in trivia skipping and debug-only logic. * Enhance `cfg.rs` with `first_call_ident` helper and improve identifier extraction logic in `push_node`. * Add targeted CFG taint-tracking tests to enhance analysis coverage. * Enhance CFG generation with loop expression handling and improve taint tracking logic. Add new sanitization example in `examples/sanitize/example.rs`. * Update README with installation instructions for Cargo and GitHub releases. * Expand taint-tracking with precise `def-use` computation and enhance `labels.rs` for detailed classification. Extend `examples/sanitize` with realistic scenarios demonstrating new rules. * Refactor `labels.rs`: - Removed redundant `LabelRule` entries for cleaner rule definitions. - Adjusted matching logic to prioritize suffix and prefix matches effectively. * Refactor `labels.rs`: - Removed redundant `LabelRule` entries for cleaner rule definitions. - Adjusted matching logic to prioritize suffix and prefix matches effectively. * Add test for taint tracking with multiple sources in `cfg.rs`. * Add `function_summaries` table and implement summary upsert/load methods. Refactor to handle summary storage and retrieval efficiently, with placeholder clean/drop logic. * refactor: split `labels.rs` into modular structure with language-specific files * refactor: split `labels.rs` into modular structure with language-specific files * refactor: clean up SQL table definitions in `database.rs` for better readability * refactor: simplify CFG structure by removing lifetime parameters and enhancing taint metadata handling * refactor: update TODO comments in `cfg.rs` to clarify future enhancements for cap labels and function details * refactor: remove redundant header from README.md for improved clarity * feat: add PHF-based syntax classifiers and Kind enum for efficient syntax mapping across languages * feat: introduce analysis modes for enhanced scanner configuration and diagnostics * feat: define Kind enum for syntax classification in control flow analysis * feat: bump version to 0.2.0-alpha and update CHANGELOG for new features and fixes * refactor: clean up imports and formatting in AST and CFG modules for improved readability * refactor: simplify function signatures and improve code readability in CFG and module files * fix: correct rayon_thread_stack_size comment to reflect actual value of 8 MiB * refactor: update string formatting in clean and project modules for consistency * refactor: fix indentation in clean.rs for improved readability --------- Co-authored-by: elipeter <eli.peter@es.fcm.travel>
121 lines
2.9 KiB
Rust
121 lines
2.9 KiB
Rust
mod javascript;
|
|
mod rust;
|
|
|
|
use bitflags::bitflags;
|
|
use once_cell::sync::Lazy;
|
|
use phf::Map;
|
|
use std::collections::HashMap;
|
|
|
|
/// A single rule: if the AST text equals (or ends with) one of the `matchers`,
|
|
/// the node gets `label`.
|
|
#[derive(Debug, Clone, Copy)]
|
|
pub struct LabelRule {
|
|
pub matchers: &'static [&'static str],
|
|
pub label: DataLabel,
|
|
}
|
|
|
|
bitflags! {
|
|
#[derive(Debug, Clone, Copy, PartialEq, Eq)]
|
|
pub struct Cap: u8 {
|
|
const ENV_VAR = 0b0000_0001;
|
|
const HTML_ESCAPE = 0b0000_0010;
|
|
const SHELL_ESCAPE = 0b0000_0100;
|
|
const URL_ENCODE = 0b0000_1000;
|
|
const JSON_PARSE = 0b0001_0000;
|
|
// ADD MORE
|
|
}
|
|
}
|
|
|
|
#[derive(Debug, Clone, Copy, PartialEq, Eq)]
|
|
pub enum Kind {
|
|
If,
|
|
InfiniteLoop,
|
|
While,
|
|
For,
|
|
LoopBody,
|
|
CallFn,
|
|
CallMethod,
|
|
CallMacro,
|
|
Break,
|
|
Continue,
|
|
Return,
|
|
Block,
|
|
SourceFile,
|
|
Function,
|
|
Assignment,
|
|
CallWrapper,
|
|
Trivia,
|
|
Other,
|
|
}
|
|
|
|
#[derive(Debug, Clone, Copy, PartialEq, Eq)]
|
|
pub enum DataLabel {
|
|
Source(Cap),
|
|
Sanitizer(Cap),
|
|
Sink(Cap),
|
|
}
|
|
|
|
static REGISTRY: Lazy<HashMap<&'static str, &'static [LabelRule]>> = Lazy::new(|| {
|
|
let mut m = HashMap::new();
|
|
m.insert("rust", rust::RULES);
|
|
m.insert("rs", rust::RULES);
|
|
|
|
m.insert("javascript", javascript::RULES);
|
|
m.insert("js", javascript::RULES);
|
|
|
|
// add more languages in one line:
|
|
// m.insert("go", go::RULES);
|
|
|
|
m
|
|
});
|
|
|
|
type FastMap = &'static Map<&'static str, Kind>;
|
|
|
|
pub(crate) static CLASSIFIERS: Lazy<HashMap<&'static str, FastMap>> = Lazy::new(|| {
|
|
let mut m = HashMap::new();
|
|
m.insert("rust", &rust::KINDS);
|
|
m.insert("rs", &rust::KINDS);
|
|
|
|
// m.insert("javascript", &javascript::KINDS);
|
|
// m.insert("js", &javascript::KINDS);
|
|
|
|
// todo: add more languages
|
|
m
|
|
});
|
|
|
|
#[inline(always)]
|
|
pub fn lookup(lang: &str, raw: &str) -> Kind {
|
|
CLASSIFIERS
|
|
.get(lang)
|
|
.and_then(|m| m.get(raw).copied())
|
|
.unwrap_or(Kind::Other)
|
|
}
|
|
|
|
/// Try to classify a piece of syntax text.
|
|
/// `lang` is the canonicalised language key (“rust”, “javascript”, …).
|
|
pub fn classify(lang: &str, text: &str) -> Option<DataLabel> {
|
|
let key = lang.to_ascii_lowercase();
|
|
let rules = REGISTRY.get(key.as_str())?;
|
|
let head = text.split(['(', '<']).next().unwrap_or("");
|
|
|
|
let text_lc = head.trim().to_ascii_lowercase();
|
|
|
|
for rule in *rules {
|
|
for raw in rule.matchers {
|
|
let m = raw.to_ascii_lowercase();
|
|
|
|
if m.ends_with('_') {
|
|
if text_lc.starts_with(&m) {
|
|
return Some(rule.label);
|
|
}
|
|
} else if text_lc.ends_with(&m) {
|
|
let start = text_lc.len() - m.len();
|
|
let ok = start == 0 || matches!(text_lc.as_bytes()[start - 1], b'.' | b':');
|
|
if ok {
|
|
return Some(rule.label);
|
|
}
|
|
}
|
|
}
|
|
}
|
|
None
|
|
}
|