2025-06-23 20:27:16 +02:00
|
|
|
use std::cell::RefCell;
|
|
|
|
|
use std::path::Path;
|
|
|
|
|
use tree_sitter::{Language, QueryCursor, StreamingIterator};
|
|
|
|
|
use crate::commands::scan::Diag;
|
|
|
|
|
use crate::errors::{NyxResult, NyxError};
|
|
|
|
|
use crate::utils::{query_cache, Config};
|
|
|
|
|
use crate::utils::ext::lowercase_ext;
|
|
|
|
|
|
|
|
|
|
thread_local! {
|
|
|
|
|
static PARSER: RefCell<tree_sitter::Parser> = RefCell::new(tree_sitter::Parser::new());
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
pub(crate) fn run_rules_on_file(
|
|
|
|
|
path: &Path,
|
|
|
|
|
cfg: &Config,
|
|
|
|
|
) -> NyxResult<Vec<Diag>> {
|
2025-06-23 20:59:49 +02:00
|
|
|
tracing::debug!("Running rules on: {}", path.display());
|
2025-06-23 20:27:16 +02:00
|
|
|
let bytes = std::fs::read(path)?;
|
|
|
|
|
|
|
|
|
|
// Fast binary-file guard (skip if >1% NULs)
|
|
|
|
|
if bytes.iter().filter(|b| **b == 0).count() * 100 / bytes.len().max(1) > 1 {
|
|
|
|
|
return Ok(vec![]);
|
|
|
|
|
}
|
|
|
|
|
|
2025-06-23 20:59:49 +02:00
|
|
|
let (ts_lang, lang_slug) = match lowercase_ext(path) {
|
|
|
|
|
Some("rs") => (Language::from(tree_sitter_rust::LANGUAGE), "rust"),
|
|
|
|
|
Some("c") => (Language::from(tree_sitter_c::LANGUAGE), "c"),
|
|
|
|
|
Some("cpp") => (Language::from(tree_sitter_cpp::LANGUAGE), "cpp"),
|
|
|
|
|
Some("java")=> (Language::from(tree_sitter_java::LANGUAGE), "java"),
|
|
|
|
|
Some("go") => (Language::from(tree_sitter_go::LANGUAGE), "go"),
|
|
|
|
|
Some("php") => (Language::from(tree_sitter_php::LANGUAGE_PHP), "php"),
|
|
|
|
|
Some("py") => (Language::from(tree_sitter_python::LANGUAGE), "python"),
|
|
|
|
|
Some("ts") => (Language::from(tree_sitter_typescript::LANGUAGE_TYPESCRIPT), "typescript"),
|
|
|
|
|
Some("js") => (Language::from(tree_sitter_javascript::LANGUAGE), "javascript"),
|
2025-06-24 18:53:31 +02:00
|
|
|
Some("rb") => (Language::from(tree_sitter_ruby::LANGUAGE), "ruby"),
|
2025-06-23 20:59:49 +02:00
|
|
|
_ => return Ok(vec![]),
|
2025-06-23 20:27:16 +02:00
|
|
|
};
|
|
|
|
|
|
|
|
|
|
let _tree = PARSER.with(|cell| {
|
|
|
|
|
let mut parser = cell.borrow_mut();
|
|
|
|
|
parser.set_language(&ts_lang)?;
|
|
|
|
|
parser.parse(&*bytes, None)
|
|
|
|
|
.ok_or_else(|| NyxError::Other("tree-sitter failed".into()))
|
|
|
|
|
})?;
|
|
|
|
|
|
|
|
|
|
let root = _tree.root_node();
|
|
|
|
|
|
2025-06-23 20:59:49 +02:00
|
|
|
let compiled = query_cache::for_lang(lang_slug, ts_lang);
|
2025-06-23 20:27:16 +02:00
|
|
|
let mut cursor = QueryCursor::new();
|
|
|
|
|
let mut out = Vec::new();
|
|
|
|
|
|
|
|
|
|
for cq in compiled.iter() {
|
2025-06-23 20:59:49 +02:00
|
|
|
if cfg.scanner.min_severity <= cq.meta.severity {
|
2025-06-23 20:27:16 +02:00
|
|
|
continue;
|
|
|
|
|
}
|
|
|
|
|
let mut matches = cursor.matches(&cq.query, root, &*bytes);
|
|
|
|
|
while let Some(m) = matches.next() {
|
|
|
|
|
if let Some(cap) = m.captures.iter().find(|c| c.index == 0) {
|
|
|
|
|
let point = cap.node.start_position();
|
|
|
|
|
out.push(Diag {
|
|
|
|
|
path: path.to_string_lossy().into_owned(),
|
|
|
|
|
line: point.row + 1,
|
|
|
|
|
col: point.column + 1,
|
|
|
|
|
severity: cq.meta.severity,
|
|
|
|
|
id: cq.meta.id.to_owned(),
|
|
|
|
|
});
|
|
|
|
|
}
|
|
|
|
|
}
|
2025-06-23 20:59:49 +02:00
|
|
|
}
|
2025-06-23 20:27:16 +02:00
|
|
|
Ok(out)
|
|
|
|
|
}
|