tree-sitter replaces ast-grep
This commit is contained in:
@@ -26,3 +26,11 @@ rand = "0.8"
|
||||
regex = "1.0"
|
||||
shellexpand = "3.1"
|
||||
serde_yaml = "0.9"
|
||||
|
||||
# tree-sitter for embedded code search
|
||||
tree-sitter = "0.22"
|
||||
tree-sitter-rust = "0.21"
|
||||
tree-sitter-python = "0.21"
|
||||
tree-sitter-javascript = "0.21"
|
||||
tree-sitter-typescript = "0.21"
|
||||
walkdir = "2.4"
|
||||
|
||||
58
crates/g3-core/examples/inspect_ast.rs
Normal file
58
crates/g3-core/examples/inspect_ast.rs
Normal file
@@ -0,0 +1,58 @@
|
||||
//! Inspect tree-sitter AST structure for Rust code
|
||||
|
||||
use tree_sitter::{Parser, Language};
|
||||
|
||||
fn print_tree(node: tree_sitter::Node, source: &str, indent: usize) {
|
||||
let indent_str = " ".repeat(indent);
|
||||
let node_text = &source[node.byte_range()];
|
||||
let preview = if node_text.len() > 50 {
|
||||
format!("{}...", &node_text[..50])
|
||||
} else {
|
||||
node_text.to_string()
|
||||
};
|
||||
|
||||
println!(
|
||||
"{}{} [{}:{}] '{}'",
|
||||
indent_str,
|
||||
node.kind(),
|
||||
node.start_position().row + 1,
|
||||
node.start_position().column + 1,
|
||||
preview.replace('\n', "\\n")
|
||||
);
|
||||
|
||||
let mut cursor = node.walk();
|
||||
for child in node.children(&mut cursor) {
|
||||
print_tree(child, source, indent + 1);
|
||||
}
|
||||
}
|
||||
|
||||
fn main() -> anyhow::Result<()> {
|
||||
let source_code = r#"
|
||||
pub async fn example_async() {
|
||||
println!("Hello");
|
||||
}
|
||||
|
||||
fn regular_function() {
|
||||
println!("Regular");
|
||||
}
|
||||
|
||||
pub async fn another_async(x: i32) -> Result<(), ()> {
|
||||
Ok(())
|
||||
}
|
||||
"#;
|
||||
|
||||
println!("Source code:");
|
||||
println!("{}", source_code);
|
||||
println!("\n{}", "=".repeat(80));
|
||||
println!("AST Structure:");
|
||||
println!("{}\n", "=".repeat(80));
|
||||
|
||||
let mut parser = Parser::new();
|
||||
let language: Language = tree_sitter_rust::language().into();
|
||||
parser.set_language(&language)?;
|
||||
|
||||
let tree = parser.parse(source_code, None).unwrap();
|
||||
print_tree(tree.root_node(), source_code, 0);
|
||||
|
||||
Ok(())
|
||||
}
|
||||
56
crates/g3-core/examples/inspect_python_ast.rs
Normal file
56
crates/g3-core/examples/inspect_python_ast.rs
Normal file
@@ -0,0 +1,56 @@
|
||||
//! Inspect tree-sitter AST structure for Python code
|
||||
|
||||
use tree_sitter::{Parser, Language};
|
||||
|
||||
fn print_tree(node: tree_sitter::Node, source: &str, indent: usize) {
|
||||
let indent_str = " ".repeat(indent);
|
||||
let node_text = &source[node.byte_range()];
|
||||
let preview = if node_text.len() > 50 {
|
||||
format!("{}...", &node_text[..50])
|
||||
} else {
|
||||
node_text.to_string()
|
||||
};
|
||||
|
||||
println!(
|
||||
"{}{} [{}:{}] '{}'",
|
||||
indent_str,
|
||||
node.kind(),
|
||||
node.start_position().row + 1,
|
||||
node.start_position().column + 1,
|
||||
preview.replace('\n', "\\n")
|
||||
);
|
||||
|
||||
let mut cursor = node.walk();
|
||||
for child in node.children(&mut cursor) {
|
||||
print_tree(child, source, indent + 1);
|
||||
}
|
||||
}
|
||||
|
||||
fn main() -> anyhow::Result<()> {
|
||||
let source_code = r#"
|
||||
def regular_function():
|
||||
pass
|
||||
|
||||
async def async_function():
|
||||
pass
|
||||
|
||||
class MyClass:
|
||||
def method(self):
|
||||
pass
|
||||
"#;
|
||||
|
||||
println!("Source code:");
|
||||
println!("{}", source_code);
|
||||
println!("\n{}", "=".repeat(80));
|
||||
println!("AST Structure:");
|
||||
println!("{}\n", "=".repeat(80));
|
||||
|
||||
let mut parser = Parser::new();
|
||||
let language: Language = tree_sitter_python::language().into();
|
||||
parser.set_language(&language)?;
|
||||
|
||||
let tree = parser.parse(source_code, None).unwrap();
|
||||
print_tree(tree.root_node(), source_code, 0);
|
||||
|
||||
Ok(())
|
||||
}
|
||||
43
crates/g3-core/examples/test_python_query.rs
Normal file
43
crates/g3-core/examples/test_python_query.rs
Normal file
@@ -0,0 +1,43 @@
|
||||
//! Test Python async query
|
||||
|
||||
use tree_sitter::{Parser, Query, QueryCursor, Language};
|
||||
|
||||
fn main() -> anyhow::Result<()> {
|
||||
let source_code = r#"
|
||||
def regular_function():
|
||||
pass
|
||||
|
||||
async def async_function():
|
||||
pass
|
||||
"#;
|
||||
|
||||
let mut parser = Parser::new();
|
||||
let language: Language = tree_sitter_python::language().into();
|
||||
parser.set_language(&language)?;
|
||||
|
||||
let tree = parser.parse(source_code, None).unwrap();
|
||||
|
||||
// Try different queries
|
||||
let queries = vec![
|
||||
"(function_definition (async) name: (identifier) @name)",
|
||||
"(function_definition (async))",
|
||||
"(async)",
|
||||
];
|
||||
|
||||
for query_str in queries {
|
||||
println!("\nTrying query: {}", query_str);
|
||||
match Query::new(&language, query_str) {
|
||||
Ok(query) => {
|
||||
let mut cursor = QueryCursor::new();
|
||||
let matches = cursor.matches(&query, tree.root_node(), source_code.as_bytes());
|
||||
let count = matches.count();
|
||||
println!(" ✓ Valid query, found {} matches", count);
|
||||
}
|
||||
Err(e) => {
|
||||
println!(" ✗ Invalid query: {}", e);
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
Ok(())
|
||||
}
|
||||
@@ -1,787 +0,0 @@
|
||||
//! Code search functionality using ast-grep for syntax-aware semantic searches
|
||||
|
||||
use anyhow::{anyhow, Result};
|
||||
use serde::{Deserialize, Serialize};
|
||||
use serde_json::Value;
|
||||
use std::collections::HashMap;
|
||||
use std::process::Stdio;
|
||||
use std::time::{Duration, Instant};
|
||||
use tokio::io::{AsyncBufReadExt, BufReader};
|
||||
use tokio::process::Command;
|
||||
use tokio::sync::Semaphore;
|
||||
use tracing::{debug, error, info, warn};
|
||||
|
||||
/// Maximum number of searches allowed per request
|
||||
const MAX_SEARCHES: usize = 20;
|
||||
|
||||
/// Default timeout for individual searches in seconds
|
||||
const DEFAULT_TIMEOUT_SECS: u64 = 60;
|
||||
|
||||
/// Default maximum concurrency
|
||||
const DEFAULT_MAX_CONCURRENCY: usize = 4;
|
||||
|
||||
/// Default maximum matches per search
|
||||
const DEFAULT_MAX_MATCHES: usize = 500;
|
||||
|
||||
/// Search specification for a single ast-grep search
|
||||
#[derive(Debug, Clone, Deserialize)]
|
||||
pub struct SearchSpec {
|
||||
pub name: String,
|
||||
pub mode: SearchMode,
|
||||
|
||||
// Pattern mode fields
|
||||
pub pattern: Option<String>,
|
||||
pub language: Option<String>,
|
||||
|
||||
// YAML mode fields
|
||||
pub rule_yaml: Option<String>,
|
||||
|
||||
// Common fields
|
||||
pub paths: Option<Vec<String>>,
|
||||
pub globs: Option<Vec<String>>,
|
||||
pub json_style: Option<JsonStyle>,
|
||||
pub context: Option<u32>,
|
||||
pub threads: Option<u32>,
|
||||
pub include_metadata: Option<bool>,
|
||||
pub no_ignore: Option<Vec<NoIgnoreType>>,
|
||||
pub severity: Option<HashMap<String, SeverityLevel>>,
|
||||
pub timeout_secs: Option<u64>,
|
||||
}
|
||||
|
||||
/// Search mode: pattern or yaml
|
||||
#[derive(Debug, Clone, Deserialize, PartialEq)]
|
||||
#[serde(rename_all = "lowercase")]
|
||||
pub enum SearchMode {
|
||||
Pattern,
|
||||
Yaml,
|
||||
}
|
||||
|
||||
/// JSON output style
|
||||
#[derive(Debug, Clone, Deserialize, PartialEq)]
|
||||
#[serde(rename_all = "lowercase")]
|
||||
pub enum JsonStyle {
|
||||
Pretty,
|
||||
Stream,
|
||||
Compact,
|
||||
}
|
||||
|
||||
impl Default for JsonStyle {
|
||||
fn default() -> Self {
|
||||
JsonStyle::Stream
|
||||
}
|
||||
}
|
||||
|
||||
/// No-ignore types
|
||||
#[derive(Debug, Clone, Deserialize, PartialEq)]
|
||||
#[serde(rename_all = "lowercase")]
|
||||
pub enum NoIgnoreType {
|
||||
Hidden,
|
||||
Dot,
|
||||
Exclude,
|
||||
Global,
|
||||
Parent,
|
||||
Vcs,
|
||||
}
|
||||
|
||||
/// Severity levels for YAML rules
|
||||
#[derive(Debug, Clone, Deserialize, PartialEq)]
|
||||
#[serde(rename_all = "lowercase")]
|
||||
pub enum SeverityLevel {
|
||||
Error,
|
||||
Warning,
|
||||
Info,
|
||||
Hint,
|
||||
Off,
|
||||
}
|
||||
|
||||
/// Request structure for code search
|
||||
#[derive(Debug, Deserialize)]
|
||||
pub struct CodeSearchRequest {
|
||||
pub searches: Vec<SearchSpec>,
|
||||
pub max_concurrency: Option<usize>,
|
||||
pub max_matches_per_search: Option<usize>,
|
||||
}
|
||||
|
||||
/// Result of a single search
|
||||
#[derive(Debug, Serialize)]
|
||||
pub struct SearchResult {
|
||||
pub name: String,
|
||||
pub mode: String,
|
||||
pub status: String,
|
||||
pub cmd: Vec<String>,
|
||||
pub match_count: Option<usize>,
|
||||
pub truncated: Option<bool>,
|
||||
pub matches: Option<Vec<Value>>,
|
||||
pub stderr: Option<String>,
|
||||
pub exit_code: Option<i32>,
|
||||
pub duration_ms: u64,
|
||||
}
|
||||
|
||||
/// Summary of all searches
|
||||
#[derive(Debug, Serialize)]
|
||||
pub struct SearchSummary {
|
||||
pub completed: usize,
|
||||
pub total: usize,
|
||||
pub total_matches: usize,
|
||||
pub duration_ms: u64,
|
||||
}
|
||||
|
||||
/// Complete response structure
|
||||
#[derive(Debug, Serialize)]
|
||||
pub struct CodeSearchResponse {
|
||||
pub summary: SearchSummary,
|
||||
pub searches: Vec<SearchResult>,
|
||||
}
|
||||
|
||||
/// YAML rule structure for validation
|
||||
#[derive(Debug, Deserialize)]
|
||||
struct YamlRule {
|
||||
pub id: String,
|
||||
pub language: String,
|
||||
pub rule: Value,
|
||||
}
|
||||
|
||||
/// Execute a batch of code searches using ast-grep
|
||||
pub async fn execute_code_search(request: CodeSearchRequest) -> Result<CodeSearchResponse> {
|
||||
let start_time = Instant::now();
|
||||
|
||||
// Validate request
|
||||
if request.searches.is_empty() {
|
||||
return Err(anyhow!("No searches specified"));
|
||||
}
|
||||
|
||||
if request.searches.len() > MAX_SEARCHES {
|
||||
return Err(anyhow!(
|
||||
"Too many searches: {} (max: {})",
|
||||
request.searches.len(),
|
||||
MAX_SEARCHES
|
||||
));
|
||||
}
|
||||
|
||||
// Check if ast-grep is available
|
||||
check_ast_grep_available().await?;
|
||||
|
||||
let max_concurrency = request.max_concurrency.unwrap_or(DEFAULT_MAX_CONCURRENCY);
|
||||
let max_matches = request.max_matches_per_search.unwrap_or(DEFAULT_MAX_MATCHES);
|
||||
|
||||
// Create semaphore for concurrency control
|
||||
let semaphore = std::sync::Arc::new(Semaphore::new(max_concurrency));
|
||||
|
||||
// Execute searches concurrently
|
||||
let mut tasks = Vec::new();
|
||||
|
||||
for search in request.searches {
|
||||
let sem = semaphore.clone();
|
||||
let task = tokio::spawn(async move {
|
||||
let _permit = sem.acquire().await.unwrap();
|
||||
execute_single_search(search, max_matches).await
|
||||
});
|
||||
tasks.push(task);
|
||||
}
|
||||
|
||||
// Wait for all searches to complete
|
||||
let mut results = Vec::new();
|
||||
let mut total_matches = 0;
|
||||
let mut completed = 0;
|
||||
|
||||
for task in tasks {
|
||||
match task.await {
|
||||
Ok(result) => {
|
||||
if result.status == "ok" {
|
||||
completed += 1;
|
||||
if let Some(count) = result.match_count {
|
||||
total_matches += count;
|
||||
}
|
||||
}
|
||||
results.push(result);
|
||||
}
|
||||
Err(e) => {
|
||||
error!("Task join error: {}", e);
|
||||
// Create an error result
|
||||
results.push(SearchResult {
|
||||
name: "unknown".to_string(),
|
||||
mode: "unknown".to_string(),
|
||||
status: "error".to_string(),
|
||||
cmd: vec![],
|
||||
match_count: None,
|
||||
truncated: None,
|
||||
matches: None,
|
||||
stderr: Some(format!("Task execution error: {}", e)),
|
||||
exit_code: None,
|
||||
duration_ms: 0,
|
||||
});
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
let total_duration = start_time.elapsed();
|
||||
|
||||
Ok(CodeSearchResponse {
|
||||
summary: SearchSummary {
|
||||
completed,
|
||||
total: results.len(),
|
||||
total_matches,
|
||||
duration_ms: total_duration.as_millis() as u64,
|
||||
},
|
||||
searches: results,
|
||||
})
|
||||
}
|
||||
|
||||
/// Execute a single search
|
||||
async fn execute_single_search(search: SearchSpec, max_matches: usize) -> SearchResult {
|
||||
let start_time = Instant::now();
|
||||
let timeout_secs = search.timeout_secs.unwrap_or(DEFAULT_TIMEOUT_SECS);
|
||||
|
||||
// Validate the search specification
|
||||
if let Err(e) = validate_search_spec(&search) {
|
||||
return SearchResult {
|
||||
name: search.name,
|
||||
mode: format!("{:?}", search.mode).to_lowercase(),
|
||||
status: "error".to_string(),
|
||||
cmd: vec![],
|
||||
match_count: None,
|
||||
truncated: None,
|
||||
matches: None,
|
||||
stderr: Some(format!("Validation error: {}", e)),
|
||||
exit_code: None,
|
||||
duration_ms: start_time.elapsed().as_millis() as u64,
|
||||
};
|
||||
}
|
||||
|
||||
// Build command
|
||||
let cmd_args = match build_ast_grep_command(&search) {
|
||||
Ok(args) => args,
|
||||
Err(e) => {
|
||||
return SearchResult {
|
||||
name: search.name,
|
||||
mode: format!("{:?}", search.mode).to_lowercase(),
|
||||
status: "error".to_string(),
|
||||
cmd: vec![],
|
||||
match_count: None,
|
||||
truncated: None,
|
||||
matches: None,
|
||||
stderr: Some(format!("Command build error: {}", e)),
|
||||
exit_code: None,
|
||||
duration_ms: start_time.elapsed().as_millis() as u64,
|
||||
};
|
||||
}
|
||||
};
|
||||
|
||||
debug!("Executing ast-grep command: {:?}", cmd_args);
|
||||
|
||||
// Execute with timeout
|
||||
let timeout_duration = Duration::from_secs(timeout_secs);
|
||||
|
||||
match tokio::time::timeout(timeout_duration, run_ast_grep_command(&cmd_args)).await {
|
||||
Ok(Ok((stdout, stderr, exit_code))) => {
|
||||
let duration_ms = start_time.elapsed().as_millis() as u64;
|
||||
|
||||
if exit_code == 0 {
|
||||
// Parse JSON output
|
||||
match parse_ast_grep_output(&stdout, max_matches) {
|
||||
Ok((matches, truncated)) => {
|
||||
SearchResult {
|
||||
name: search.name,
|
||||
mode: format!("{:?}", search.mode).to_lowercase(),
|
||||
status: "ok".to_string(),
|
||||
cmd: cmd_args,
|
||||
match_count: Some(matches.len()),
|
||||
truncated: Some(truncated),
|
||||
matches: Some(matches),
|
||||
stderr: if stderr.is_empty() { None } else { Some(stderr) },
|
||||
exit_code: None,
|
||||
duration_ms,
|
||||
}
|
||||
}
|
||||
Err(e) => {
|
||||
SearchResult {
|
||||
name: search.name,
|
||||
mode: format!("{:?}", search.mode).to_lowercase(),
|
||||
status: "error".to_string(),
|
||||
cmd: cmd_args,
|
||||
match_count: None,
|
||||
truncated: None,
|
||||
matches: None,
|
||||
stderr: Some(format!("JSON parse error: {}\nRaw output: {}", e, stdout)),
|
||||
exit_code: Some(exit_code),
|
||||
duration_ms,
|
||||
}
|
||||
}
|
||||
}
|
||||
} else {
|
||||
SearchResult {
|
||||
name: search.name,
|
||||
mode: format!("{:?}", search.mode).to_lowercase(),
|
||||
status: "error".to_string(),
|
||||
cmd: cmd_args,
|
||||
match_count: None,
|
||||
truncated: None,
|
||||
matches: None,
|
||||
stderr: Some(stderr),
|
||||
exit_code: Some(exit_code),
|
||||
duration_ms,
|
||||
}
|
||||
}
|
||||
}
|
||||
Ok(Err(e)) => {
|
||||
SearchResult {
|
||||
name: search.name,
|
||||
mode: format!("{:?}", search.mode).to_lowercase(),
|
||||
status: "error".to_string(),
|
||||
cmd: cmd_args,
|
||||
match_count: None,
|
||||
truncated: None,
|
||||
matches: None,
|
||||
stderr: Some(format!("Execution error: {}", e)),
|
||||
exit_code: None,
|
||||
duration_ms: start_time.elapsed().as_millis() as u64,
|
||||
}
|
||||
}
|
||||
Err(_) => {
|
||||
SearchResult {
|
||||
name: search.name,
|
||||
mode: format!("{:?}", search.mode).to_lowercase(),
|
||||
status: "timeout".to_string(),
|
||||
cmd: cmd_args,
|
||||
match_count: None,
|
||||
truncated: None,
|
||||
matches: None,
|
||||
stderr: Some(format!("Search timed out after {} seconds", timeout_secs)),
|
||||
exit_code: None,
|
||||
duration_ms: start_time.elapsed().as_millis() as u64,
|
||||
}
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
/// Validate a search specification
|
||||
fn validate_search_spec(search: &SearchSpec) -> Result<()> {
|
||||
match search.mode {
|
||||
SearchMode::Pattern => {
|
||||
if search.pattern.is_none() || search.pattern.as_ref().unwrap().is_empty() {
|
||||
return Err(anyhow!("Pattern mode requires non-empty 'pattern' field"));
|
||||
}
|
||||
}
|
||||
SearchMode::Yaml => {
|
||||
let rule_yaml = search.rule_yaml.as_ref()
|
||||
.ok_or_else(|| anyhow!("YAML mode requires 'rule_yaml' field"))?;
|
||||
|
||||
if rule_yaml.is_empty() {
|
||||
return Err(anyhow!("YAML mode requires non-empty 'rule_yaml' field"));
|
||||
}
|
||||
|
||||
// Parse and validate YAML structure
|
||||
let parsed: YamlRule = serde_yaml::from_str(rule_yaml)
|
||||
.map_err(|e| anyhow!("Invalid YAML rule: {}", e))?;
|
||||
|
||||
if parsed.id.is_empty() {
|
||||
return Err(anyhow!("YAML rule must have non-empty 'id' field"));
|
||||
}
|
||||
|
||||
if parsed.language.is_empty() {
|
||||
return Err(anyhow!("YAML rule must have non-empty 'language' field"));
|
||||
}
|
||||
|
||||
// Validate language is supported (basic check)
|
||||
validate_language(&parsed.language)?;
|
||||
}
|
||||
}
|
||||
|
||||
// Validate context range
|
||||
if let Some(context) = search.context {
|
||||
if context > 20 {
|
||||
return Err(anyhow!("Context lines cannot exceed 20"));
|
||||
}
|
||||
}
|
||||
|
||||
Ok(())
|
||||
}
|
||||
|
||||
/// Validate that a language is supported by ast-grep
|
||||
fn validate_language(language: &str) -> Result<()> {
|
||||
let supported_languages = [
|
||||
"rust", "javascript", "typescript", "python", "java", "c", "cpp", "csharp",
|
||||
"go", "html", "css", "json", "yaml", "xml", "bash", "kotlin", "swift",
|
||||
"php", "ruby", "scala", "dart", "lua", "r", "sql", "dockerfile",
|
||||
"Rust", "JavaScript", "TypeScript", "Python", "Java", "C", "Cpp", "CSharp",
|
||||
"Go", "Html", "Css", "Json", "Yaml", "Xml", "Bash", "Kotlin", "Swift",
|
||||
"Php", "Ruby", "Scala", "Dart", "Lua", "R", "Sql", "Dockerfile"
|
||||
];
|
||||
|
||||
if !supported_languages.contains(&language) {
|
||||
warn!("Language '{}' may not be supported by ast-grep", language);
|
||||
}
|
||||
|
||||
Ok(())
|
||||
}
|
||||
|
||||
/// Build ast-grep command arguments
|
||||
fn build_ast_grep_command(search: &SearchSpec) -> Result<Vec<String>> {
|
||||
let mut args = vec!["ast-grep".to_string()];
|
||||
|
||||
match search.mode {
|
||||
SearchMode::Pattern => {
|
||||
args.push("run".to_string());
|
||||
|
||||
// Add pattern
|
||||
args.push("-p".to_string());
|
||||
args.push(search.pattern.as_ref().unwrap().clone());
|
||||
|
||||
// Add language if specified
|
||||
if let Some(ref lang) = search.language {
|
||||
args.push("-l".to_string());
|
||||
args.push(lang.clone());
|
||||
}
|
||||
}
|
||||
SearchMode::Yaml => {
|
||||
args.push("scan".to_string());
|
||||
|
||||
// Add inline rules
|
||||
args.push("--inline-rules".to_string());
|
||||
args.push(search.rule_yaml.as_ref().unwrap().clone());
|
||||
|
||||
// Add include-metadata if requested
|
||||
if search.include_metadata.unwrap_or(false) {
|
||||
args.push("--include-metadata".to_string());
|
||||
}
|
||||
|
||||
// Add severity overrides
|
||||
if let Some(ref severity_map) = search.severity {
|
||||
for (rule_id, severity) in severity_map {
|
||||
match severity {
|
||||
SeverityLevel::Error => {
|
||||
args.push("--error".to_string());
|
||||
args.push(rule_id.clone());
|
||||
}
|
||||
SeverityLevel::Warning => {
|
||||
args.push("--warning".to_string());
|
||||
args.push(rule_id.clone());
|
||||
}
|
||||
SeverityLevel::Info => {
|
||||
args.push("--info".to_string());
|
||||
args.push(rule_id.clone());
|
||||
}
|
||||
SeverityLevel::Hint => {
|
||||
args.push("--hint".to_string());
|
||||
args.push(rule_id.clone());
|
||||
}
|
||||
SeverityLevel::Off => {
|
||||
args.push("--off".to_string());
|
||||
args.push(rule_id.clone());
|
||||
}
|
||||
}
|
||||
}
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
// Add common arguments
|
||||
|
||||
// Add globs if specified
|
||||
if let Some(ref globs) = search.globs {
|
||||
if !globs.is_empty() {
|
||||
args.push("--globs".to_string());
|
||||
args.push(globs.join(","));
|
||||
}
|
||||
}
|
||||
|
||||
// Add context
|
||||
if let Some(context) = search.context {
|
||||
args.push("-C".to_string());
|
||||
args.push(context.to_string());
|
||||
}
|
||||
|
||||
// Add threads
|
||||
if let Some(threads) = search.threads {
|
||||
args.push("-j".to_string());
|
||||
args.push(threads.to_string());
|
||||
}
|
||||
|
||||
// Add JSON output style
|
||||
let json_style = search.json_style.as_ref().unwrap_or(&JsonStyle::Stream);
|
||||
let json_arg = match json_style {
|
||||
JsonStyle::Pretty => "--json=pretty",
|
||||
JsonStyle::Stream => "--json=stream",
|
||||
JsonStyle::Compact => "--json=compact",
|
||||
};
|
||||
args.push(json_arg.to_string());
|
||||
|
||||
// Add no-ignore options
|
||||
if let Some(ref no_ignore_list) = search.no_ignore {
|
||||
for no_ignore_type in no_ignore_list {
|
||||
let flag = match no_ignore_type {
|
||||
NoIgnoreType::Hidden => "--no-ignore=hidden",
|
||||
NoIgnoreType::Dot => "--no-ignore=dot",
|
||||
NoIgnoreType::Exclude => "--no-ignore=exclude",
|
||||
NoIgnoreType::Global => "--no-ignore=global",
|
||||
NoIgnoreType::Parent => "--no-ignore=parent",
|
||||
NoIgnoreType::Vcs => "--no-ignore=vcs",
|
||||
};
|
||||
args.push(flag.to_string());
|
||||
}
|
||||
}
|
||||
|
||||
// Add paths (default to current directory if none specified)
|
||||
if let Some(ref paths) = search.paths {
|
||||
if !paths.is_empty() {
|
||||
args.extend(paths.clone());
|
||||
} else {
|
||||
args.push(".".to_string());
|
||||
}
|
||||
} else {
|
||||
args.push(".".to_string());
|
||||
}
|
||||
|
||||
Ok(args)
|
||||
}
|
||||
|
||||
/// Run ast-grep command and capture output
|
||||
async fn run_ast_grep_command(args: &[String]) -> Result<(String, String, i32)> {
|
||||
let mut cmd = Command::new(&args[0]);
|
||||
cmd.args(&args[1..]);
|
||||
cmd.stdout(Stdio::piped());
|
||||
cmd.stderr(Stdio::piped());
|
||||
|
||||
debug!("Running command: {:?}", args);
|
||||
|
||||
let mut child = cmd.spawn()
|
||||
.map_err(|e| anyhow!("Failed to spawn ast-grep process: {}", e))?;
|
||||
|
||||
let stdout = child.stdout.take().unwrap();
|
||||
let stderr = child.stderr.take().unwrap();
|
||||
|
||||
let stdout_reader = BufReader::new(stdout);
|
||||
let stderr_reader = BufReader::new(stderr);
|
||||
|
||||
let stdout_task = tokio::spawn(async move {
|
||||
let mut lines = stdout_reader.lines();
|
||||
let mut output = String::new();
|
||||
while let Ok(Some(line)) = lines.next_line().await {
|
||||
if !output.is_empty() {
|
||||
output.push('\n');
|
||||
}
|
||||
output.push_str(&line);
|
||||
}
|
||||
output
|
||||
});
|
||||
|
||||
let stderr_task = tokio::spawn(async move {
|
||||
let mut lines = stderr_reader.lines();
|
||||
let mut output = String::new();
|
||||
while let Ok(Some(line)) = lines.next_line().await {
|
||||
if !output.is_empty() {
|
||||
output.push('\n');
|
||||
}
|
||||
output.push_str(&line);
|
||||
}
|
||||
output
|
||||
});
|
||||
|
||||
let status = child.wait().await
|
||||
.map_err(|e| anyhow!("Failed to wait for ast-grep process: {}", e))?;
|
||||
|
||||
let stdout_output = stdout_task.await
|
||||
.map_err(|e| anyhow!("Failed to read stdout: {}", e))?;
|
||||
let stderr_output = stderr_task.await
|
||||
.map_err(|e| anyhow!("Failed to read stderr: {}", e))?;
|
||||
|
||||
let exit_code = status.code().unwrap_or(-1);
|
||||
|
||||
Ok((stdout_output, stderr_output, exit_code))
|
||||
}
|
||||
|
||||
/// Parse ast-grep JSON output
|
||||
fn parse_ast_grep_output(output: &str, max_matches: usize) -> Result<(Vec<Value>, bool)> {
|
||||
if output.trim().is_empty() {
|
||||
return Ok((vec![], false));
|
||||
}
|
||||
|
||||
let mut matches = Vec::new();
|
||||
let mut truncated = false;
|
||||
|
||||
// Handle stream format (line-delimited JSON)
|
||||
for line in output.lines() {
|
||||
let line = line.trim();
|
||||
if line.is_empty() {
|
||||
continue;
|
||||
}
|
||||
|
||||
match serde_json::from_str::<Value>(line) {
|
||||
Ok(match_obj) => {
|
||||
if matches.len() >= max_matches {
|
||||
truncated = true;
|
||||
break;
|
||||
}
|
||||
matches.push(match_obj);
|
||||
}
|
||||
Err(e) => {
|
||||
debug!("Failed to parse JSON line '{}': {}", line, e);
|
||||
// Try to parse the entire output as a single JSON array
|
||||
match serde_json::from_str::<Vec<Value>>(output) {
|
||||
Ok(array_matches) => {
|
||||
let take_count = array_matches.len().min(max_matches);
|
||||
let total_count = array_matches.len();
|
||||
matches = array_matches.into_iter().take(take_count).collect();
|
||||
truncated = take_count < total_count;
|
||||
break;
|
||||
}
|
||||
Err(e2) => {
|
||||
return Err(anyhow!(
|
||||
"Failed to parse ast-grep output as line-delimited JSON or JSON array. Line error: {}, Array error: {}",
|
||||
e, e2
|
||||
));
|
||||
}
|
||||
}
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
Ok((matches, truncated))
|
||||
}
|
||||
|
||||
/// Check if ast-grep is available and provide installation hints if not
|
||||
async fn check_ast_grep_available() -> Result<()> {
|
||||
match Command::new("ast-grep")
|
||||
.arg("--version")
|
||||
.output()
|
||||
.await
|
||||
{
|
||||
Ok(output) => {
|
||||
if output.status.success() {
|
||||
let version = String::from_utf8_lossy(&output.stdout);
|
||||
info!("Found ast-grep: {}", version.trim());
|
||||
Ok(())
|
||||
} else {
|
||||
Err(anyhow!("ast-grep command failed: {}", String::from_utf8_lossy(&output.stderr)))
|
||||
}
|
||||
}
|
||||
Err(_) => {
|
||||
Err(anyhow!(
|
||||
"ast-grep not found. Please install it using one of these methods:\n\n\
|
||||
• Homebrew (macOS): brew install ast-grep\n\
|
||||
• MacPorts (macOS): sudo port install ast-grep\n\
|
||||
• Nix: nix-env -iA nixpkgs.ast-grep\n\
|
||||
• Cargo: cargo install ast-grep\n\
|
||||
• npm: npm install -g @ast-grep/cli\n\
|
||||
• pip: pip install ast-grep\n\n\
|
||||
For more installation options, visit: https://ast-grep.github.io/guide/quick-start.html"
|
||||
))
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
#[cfg(test)]
|
||||
mod tests {
|
||||
use super::*;
|
||||
|
||||
#[test]
|
||||
fn test_validate_pattern_search() {
|
||||
let search = SearchSpec {
|
||||
name: "test".to_string(),
|
||||
mode: SearchMode::Pattern,
|
||||
pattern: Some("fn $NAME() {}".to_string()),
|
||||
language: Some("rust".to_string()),
|
||||
rule_yaml: None,
|
||||
paths: None,
|
||||
globs: None,
|
||||
json_style: None,
|
||||
context: None,
|
||||
threads: None,
|
||||
include_metadata: None,
|
||||
no_ignore: None,
|
||||
severity: None,
|
||||
timeout_secs: None,
|
||||
};
|
||||
|
||||
assert!(validate_search_spec(&search).is_ok());
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn test_validate_yaml_search() {
|
||||
let yaml_rule = r#"
|
||||
id: test-rule
|
||||
language: Rust
|
||||
rule:
|
||||
pattern: "fn $NAME() {}"
|
||||
"#;
|
||||
|
||||
let search = SearchSpec {
|
||||
name: "test".to_string(),
|
||||
mode: SearchMode::Yaml,
|
||||
pattern: None,
|
||||
language: None,
|
||||
rule_yaml: Some(yaml_rule.to_string()),
|
||||
paths: None,
|
||||
globs: None,
|
||||
json_style: None,
|
||||
context: None,
|
||||
threads: None,
|
||||
include_metadata: None,
|
||||
no_ignore: None,
|
||||
severity: None,
|
||||
timeout_secs: None,
|
||||
};
|
||||
|
||||
assert!(validate_search_spec(&search).is_ok());
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn test_build_pattern_command() {
|
||||
let search = SearchSpec {
|
||||
name: "test".to_string(),
|
||||
mode: SearchMode::Pattern,
|
||||
pattern: Some("fn $NAME() {}".to_string()),
|
||||
language: Some("rust".to_string()),
|
||||
rule_yaml: None,
|
||||
paths: Some(vec!["src/".to_string()]),
|
||||
globs: None,
|
||||
json_style: Some(JsonStyle::Stream),
|
||||
context: Some(2),
|
||||
threads: Some(4),
|
||||
include_metadata: None,
|
||||
no_ignore: None,
|
||||
severity: None,
|
||||
timeout_secs: None,
|
||||
};
|
||||
|
||||
let cmd = build_ast_grep_command(&search).unwrap();
|
||||
|
||||
assert_eq!(cmd[0], "ast-grep");
|
||||
assert_eq!(cmd[1], "run");
|
||||
assert!(cmd.contains(&"-p".to_string()));
|
||||
assert!(cmd.contains(&"fn $NAME() {}".to_string()));
|
||||
assert!(cmd.contains(&"-l".to_string()));
|
||||
assert!(cmd.contains(&"rust".to_string()));
|
||||
assert!(cmd.contains(&"--json=stream".to_string()));
|
||||
assert!(cmd.contains(&"-C".to_string()));
|
||||
assert!(cmd.contains(&"2".to_string()));
|
||||
assert!(cmd.contains(&"-j".to_string()));
|
||||
assert!(cmd.contains(&"4".to_string()));
|
||||
assert!(cmd.contains(&"src/".to_string()));
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn test_parse_stream_json() {
|
||||
let output = r#"{"file":"test.rs","text":"fn hello() {}"}
|
||||
{"file":"test2.rs","text":"fn world() {}"}"#;
|
||||
|
||||
let (matches, truncated) = parse_ast_grep_output(output, 10).unwrap();
|
||||
|
||||
assert_eq!(matches.len(), 2);
|
||||
assert!(!truncated);
|
||||
assert_eq!(matches[0]["file"], "test.rs");
|
||||
assert_eq!(matches[1]["file"], "test2.rs");
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn test_parse_truncated_output() {
|
||||
let output = r#"{"file":"test1.rs","text":"fn a() {}"}
|
||||
{"file":"test2.rs","text":"fn b() {}"}
|
||||
{"file":"test3.rs","text":"fn c() {}"}"#;
|
||||
|
||||
let (matches, truncated) = parse_ast_grep_output(output, 2).unwrap();
|
||||
|
||||
assert_eq!(matches.len(), 2);
|
||||
assert!(truncated);
|
||||
}
|
||||
}
|
||||
81
crates/g3-core/src/code_search/mod.rs
Normal file
81
crates/g3-core/src/code_search/mod.rs
Normal file
@@ -0,0 +1,81 @@
|
||||
//! Code search functionality using tree-sitter for syntax-aware searches
|
||||
|
||||
use anyhow::Result;
|
||||
use serde::{Deserialize, Serialize};
|
||||
use std::collections::HashMap;
|
||||
|
||||
mod searcher;
|
||||
pub use searcher::TreeSitterSearcher;
|
||||
|
||||
/// Request for batch code searches
|
||||
#[derive(Debug, Clone, Serialize, Deserialize)]
|
||||
pub struct CodeSearchRequest {
|
||||
pub searches: Vec<SearchSpec>,
|
||||
#[serde(default = "default_concurrency")]
|
||||
pub max_concurrency: usize,
|
||||
#[serde(default = "default_max_matches")]
|
||||
pub max_matches_per_search: usize,
|
||||
}
|
||||
|
||||
fn default_concurrency() -> usize {
|
||||
4
|
||||
}
|
||||
|
||||
fn default_max_matches() -> usize {
|
||||
500
|
||||
}
|
||||
|
||||
/// Individual search specification
|
||||
#[derive(Debug, Clone, Serialize, Deserialize)]
|
||||
pub struct SearchSpec {
|
||||
/// Name/label for this search
|
||||
pub name: String,
|
||||
/// tree-sitter query (S-expression format)
|
||||
pub query: String,
|
||||
/// Language: "rust", "python", "javascript", "typescript"
|
||||
pub language: String,
|
||||
/// Paths to search (default: current directory)
|
||||
#[serde(default)]
|
||||
pub paths: Vec<String>,
|
||||
/// Lines of context around each match
|
||||
#[serde(default)]
|
||||
pub context_lines: usize,
|
||||
}
|
||||
|
||||
/// Response containing all search results
|
||||
#[derive(Debug, Serialize, Deserialize)]
|
||||
pub struct CodeSearchResponse {
|
||||
pub searches: Vec<SearchResult>,
|
||||
pub total_matches: usize,
|
||||
pub total_files_searched: usize,
|
||||
}
|
||||
|
||||
/// Result for a single search
|
||||
#[derive(Debug, Serialize, Deserialize)]
|
||||
pub struct SearchResult {
|
||||
pub name: String,
|
||||
pub matches: Vec<Match>,
|
||||
pub match_count: usize,
|
||||
pub files_searched: usize,
|
||||
#[serde(skip_serializing_if = "Option::is_none")]
|
||||
pub error: Option<String>,
|
||||
}
|
||||
|
||||
/// A single match
|
||||
#[derive(Debug, Serialize, Deserialize)]
|
||||
pub struct Match {
|
||||
pub file: String,
|
||||
pub line: usize,
|
||||
pub column: usize,
|
||||
pub text: String,
|
||||
#[serde(skip_serializing_if = "HashMap::is_empty")]
|
||||
pub captures: HashMap<String, String>,
|
||||
#[serde(skip_serializing_if = "Option::is_none")]
|
||||
pub context: Option<String>,
|
||||
}
|
||||
|
||||
/// Main entry point for code search
|
||||
pub async fn execute_code_search(request: CodeSearchRequest) -> Result<CodeSearchResponse> {
|
||||
let mut searcher = TreeSitterSearcher::new()?;
|
||||
searcher.execute_search(request).await
|
||||
}
|
||||
267
crates/g3-core/src/code_search/searcher.rs
Normal file
267
crates/g3-core/src/code_search/searcher.rs
Normal file
@@ -0,0 +1,267 @@
|
||||
use super::{CodeSearchRequest, CodeSearchResponse, Match, SearchResult, SearchSpec};
|
||||
use anyhow::{anyhow, Result};
|
||||
use std::collections::HashMap;
|
||||
use std::fs;
|
||||
use std::path::Path;
|
||||
use tree_sitter::{Language, Parser, Query, QueryCursor};
|
||||
use walkdir::WalkDir;
|
||||
|
||||
pub struct TreeSitterSearcher {
|
||||
parsers: HashMap<String, Parser>,
|
||||
languages: HashMap<String, Language>,
|
||||
}
|
||||
|
||||
impl TreeSitterSearcher {
|
||||
pub fn new() -> Result<Self> {
|
||||
let mut parsers = HashMap::new();
|
||||
let mut languages = HashMap::new();
|
||||
|
||||
// Initialize Rust
|
||||
{
|
||||
let mut parser = Parser::new();
|
||||
let language: Language = tree_sitter_rust::language().into();
|
||||
parser
|
||||
.set_language(&language)
|
||||
.map_err(|e| anyhow!("Failed to set Rust language: {}", e))?;
|
||||
parsers.insert("rust".to_string(), parser);
|
||||
languages.insert("rust".to_string(), language);
|
||||
}
|
||||
|
||||
// Initialize Python
|
||||
{
|
||||
let mut parser = Parser::new();
|
||||
let language: Language = tree_sitter_python::language().into();
|
||||
parser
|
||||
.set_language(&language)
|
||||
.map_err(|e| anyhow!("Failed to set Python language: {}", e))?;
|
||||
parsers.insert("python".to_string(), parser);
|
||||
languages.insert("python".to_string(), language);
|
||||
}
|
||||
|
||||
// Initialize JavaScript
|
||||
{
|
||||
let mut parser = Parser::new();
|
||||
let language: Language = tree_sitter_javascript::language().into();
|
||||
parser
|
||||
.set_language(&language)
|
||||
.map_err(|e| anyhow!("Failed to set JavaScript language: {}", e))?;
|
||||
parsers.insert("javascript".to_string(), parser);
|
||||
|
||||
// Create separate parser for "js" alias
|
||||
let mut parser_js = Parser::new();
|
||||
parser_js.set_language(&language)
|
||||
.map_err(|e| anyhow!("Failed to set JavaScript language: {}", e))?;
|
||||
parsers.insert("js".to_string(), parser_js);
|
||||
languages.insert("javascript".to_string(), language.clone());
|
||||
languages.insert("js".to_string(), language.clone());
|
||||
}
|
||||
|
||||
// Initialize TypeScript
|
||||
{
|
||||
let mut parser = Parser::new();
|
||||
let language: Language = tree_sitter_typescript::language_typescript().into();
|
||||
parser
|
||||
.set_language(&language)
|
||||
.map_err(|e| anyhow!("Failed to set TypeScript language: {}", e))?;
|
||||
parsers.insert("typescript".to_string(), parser);
|
||||
|
||||
// Create separate parser for "ts" alias
|
||||
let mut parser_ts = Parser::new();
|
||||
parser_ts.set_language(&language)
|
||||
.map_err(|e| anyhow!("Failed to set TypeScript language: {}", e))?;
|
||||
parsers.insert("ts".to_string(), parser_ts);
|
||||
languages.insert("typescript".to_string(), language.clone());
|
||||
languages.insert("ts".to_string(), language.clone());
|
||||
}
|
||||
|
||||
if parsers.is_empty() {
|
||||
return Err(anyhow!(
|
||||
"No language parsers available. Enable at least one language feature."
|
||||
));
|
||||
}
|
||||
|
||||
Ok(Self { parsers, languages })
|
||||
}
|
||||
|
||||
pub async fn execute_search(
|
||||
&mut self,
|
||||
request: CodeSearchRequest,
|
||||
) -> Result<CodeSearchResponse> {
|
||||
let mut all_results = Vec::new();
|
||||
let mut total_matches = 0;
|
||||
let mut total_files = 0;
|
||||
|
||||
// Execute searches sequentially (could parallelize with tokio::spawn if needed)
|
||||
for spec in request.searches {
|
||||
let result = self
|
||||
.search_single(&spec, request.max_matches_per_search)
|
||||
.await;
|
||||
match result {
|
||||
Ok(search_result) => {
|
||||
total_matches += search_result.match_count;
|
||||
total_files += search_result.files_searched;
|
||||
all_results.push(search_result);
|
||||
}
|
||||
Err(e) => {
|
||||
all_results.push(SearchResult {
|
||||
name: spec.name.clone(),
|
||||
matches: vec![],
|
||||
match_count: 0,
|
||||
files_searched: 0,
|
||||
error: Some(e.to_string()),
|
||||
});
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
Ok(CodeSearchResponse {
|
||||
searches: all_results,
|
||||
total_matches,
|
||||
total_files_searched: total_files,
|
||||
})
|
||||
}
|
||||
|
||||
async fn search_single(
|
||||
&mut self,
|
||||
spec: &SearchSpec,
|
||||
max_matches: usize,
|
||||
) -> Result<SearchResult> {
|
||||
// Get parser and language
|
||||
let parser = self
|
||||
.parsers
|
||||
.get_mut(&spec.language)
|
||||
.ok_or_else(|| anyhow!("Unsupported language: {}", spec.language))?;
|
||||
let language = self
|
||||
.languages
|
||||
.get(&spec.language)
|
||||
.ok_or_else(|| anyhow!("Language not found: {}", spec.language))?;
|
||||
|
||||
// Parse query
|
||||
let query = Query::new(language, &spec.query)
|
||||
.map_err(|e| anyhow!("Invalid query: {}", e))?;
|
||||
|
||||
let mut matches = Vec::new();
|
||||
let mut files_searched = 0;
|
||||
|
||||
// Determine search paths
|
||||
let search_paths = if spec.paths.is_empty() {
|
||||
vec![".".to_string()]
|
||||
} else {
|
||||
spec.paths.clone()
|
||||
};
|
||||
|
||||
// Walk directories and search files
|
||||
for search_path in search_paths {
|
||||
for entry in WalkDir::new(&search_path)
|
||||
.follow_links(true)
|
||||
.into_iter()
|
||||
.filter_map(|e| e.ok())
|
||||
{
|
||||
if matches.len() >= max_matches {
|
||||
break;
|
||||
}
|
||||
|
||||
let path = entry.path();
|
||||
if !path.is_file() {
|
||||
continue;
|
||||
}
|
||||
|
||||
// Check file extension matches language
|
||||
if !Self::is_language_file(path, &spec.language) {
|
||||
continue;
|
||||
}
|
||||
|
||||
files_searched += 1;
|
||||
|
||||
// Read and parse file
|
||||
if let Ok(source_code) = fs::read_to_string(path) {
|
||||
if let Some(tree) = parser.parse(&source_code, None) {
|
||||
let mut cursor = QueryCursor::new();
|
||||
let query_matches = cursor.matches(
|
||||
&query,
|
||||
tree.root_node(),
|
||||
source_code.as_bytes(),
|
||||
);
|
||||
|
||||
for query_match in query_matches {
|
||||
if matches.len() >= max_matches {
|
||||
break;
|
||||
}
|
||||
|
||||
// Extract captures
|
||||
let mut captures_map = HashMap::new();
|
||||
let mut match_text = String::new();
|
||||
let mut match_line = 0;
|
||||
let mut match_column = 0;
|
||||
|
||||
for capture in query_match.captures {
|
||||
let capture_name = query.capture_names()[capture.index as usize];
|
||||
let node = capture.node;
|
||||
let text = &source_code[node.byte_range()];
|
||||
|
||||
captures_map.insert(capture_name.to_string(), text.to_string());
|
||||
|
||||
// Use first capture for position
|
||||
if match_text.is_empty() {
|
||||
match_text = text.to_string();
|
||||
let start = node.start_position();
|
||||
match_line = start.row + 1;
|
||||
match_column = start.column + 1;
|
||||
}
|
||||
}
|
||||
|
||||
// Get context if requested
|
||||
let context = if spec.context_lines > 0 {
|
||||
Some(Self::get_context(
|
||||
&source_code,
|
||||
match_line,
|
||||
spec.context_lines,
|
||||
))
|
||||
} else {
|
||||
None
|
||||
};
|
||||
|
||||
matches.push(Match {
|
||||
file: path.display().to_string(),
|
||||
line: match_line,
|
||||
column: match_column,
|
||||
text: match_text,
|
||||
captures: captures_map,
|
||||
context,
|
||||
});
|
||||
}
|
||||
}
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
Ok(SearchResult {
|
||||
name: spec.name.clone(),
|
||||
match_count: matches.len(),
|
||||
files_searched,
|
||||
matches,
|
||||
error: None,
|
||||
})
|
||||
}
|
||||
|
||||
fn is_language_file(path: &Path, language: &str) -> bool {
|
||||
let ext = path.extension().and_then(|e| e.to_str());
|
||||
match (language, ext) {
|
||||
("rust", Some("rs")) => true,
|
||||
("python", Some("py")) => true,
|
||||
("javascript" | "js", Some("js" | "jsx" | "mjs")) => true,
|
||||
("typescript" | "ts", Some("ts" | "tsx")) => true,
|
||||
_ => false,
|
||||
}
|
||||
}
|
||||
|
||||
fn get_context(source: &str, line: usize, context_lines: usize) -> String {
|
||||
let lines: Vec<&str> = source.lines().collect();
|
||||
// line is 1-indexed, convert to 0-indexed
|
||||
let line_idx = line.saturating_sub(1);
|
||||
// Get context_lines before and after
|
||||
let start = line_idx.saturating_sub(context_lines);
|
||||
let end = (line_idx + context_lines + 1).min(lines.len());
|
||||
lines[start..end].join("\n")
|
||||
}
|
||||
}
|
||||
@@ -1096,11 +1096,11 @@ If you create temporary files for verification, place these in a subdir named 't
|
||||
For reading files, prioritize use of code_search tool use with multiple search requests per call instead of read_file, if it makes sense.
|
||||
|
||||
Additional examples for the 'code_search' tool:
|
||||
- Example for pattern mode: {\"tool\": \"code_search\", \"args\": {\"searches\": [{\"name\": \"find_functions\", \"mode\": \"pattern\", \"pattern\": \"fn $NAME($$$ARGS) { $$$ }\", \"language\": \"rust\", \"paths\": [\"src/\"]}]}}
|
||||
- Example for YAML mode: {\"tool\": \"code_search\", \"args\": {\"searches\": [{\"name\": \"find_async\", \"mode\": \"yaml\", \"rule_yaml\": \"id: async-fn\nlanguage: Rust\nrule:\n pattern: async fn $NAME($$$) { $$$ }\"}]}}
|
||||
- Example for multiple searches: {\"tool\": \"code_search\", \"args\": {\"searches\": [{\"name\": \"funcs\", \"mode\": \"pattern\", \"pattern\": \"fn $NAME\", \"language\": \"rust\"}, {\"name\": \"structs\", \"mode\": \"pattern\", \"pattern\": \"struct $NAME\", \"language\": \"rust\"}]}}
|
||||
- Example for passing optional args like \"context\": {\"tool\": \"code_search\", \"args\": {\"searches\": [{\"name\": \"funcs\", \"mode\": \"pattern\", \"context\": 3, \"pattern\": \"fn $NAME\", \"language\": \"rust\"}]}
|
||||
- Common optional args for searches:
|
||||
- Find functions: {\"tool\": \"code_search\", \"args\": {\"searches\": [{\"name\": \"find_functions\", \"query\": \"(function_item name: (identifier) @name)\", \"language\": \"rust\", \"paths\": [\"src/\"]}]}}
|
||||
- Find async functions: {\"tool\": \"code_search\", \"args\": {\"searches\": [{\"name\": \"find_async\", \"query\": \"(function_item (function_modifiers) name: (identifier) @name)\", \"language\": \"rust\"}]}}
|
||||
- Find structs: {\"tool\": \"code_search\", \"args\": {\"searches\": [{\"name\": \"structs\", \"query\": \"(struct_item name: (type_identifier) @name)\", \"language\": \"rust\"}]}}
|
||||
- Multiple searches: {\"tool\": \"code_search\", \"args\": {\"searches\": [{\"name\": \"funcs\", \"query\": \"(function_item name: (identifier) @name)\", \"language\": \"rust\"}, {\"name\": \"structs\", \"query\": \"(struct_item name: (type_identifier) @name)\", \"language\": \"rust\"}]}}
|
||||
- With context lines: {\"tool\": \"code_search\", \"args\": {\"searches\": [{\"name\": \"funcs\", \"query\": \"(function_item name: (identifier) @name)\", \"language\": \"rust\", \"context_lines\": 3}]}}
|
||||
- \"context\": 3 (show surrounding lines),
|
||||
- \"json_style\": \"stream\" (for large results)
|
||||
|
||||
@@ -1184,13 +1184,13 @@ Short description for providers without native calling specs:
|
||||
- Format: {\"tool\": \"todo_write\", \"args\": {\"content\": \"- [ ] Task 1\\n- [ ] Task 2\"}}
|
||||
- Example: {\"tool\": \"todo_write\", \"args\": {\"content\": \"- [ ] Implement feature\\n - [ ] Write tests\\n - [ ] Run tests\"}}
|
||||
|
||||
- **code_search**: Batch syntax-aware searches via ast-grep. Supports up to 20 pattern or YAML-rule searches in parallel.
|
||||
- Format: {\"tool\": \"code_search\", \"args\": {\"searches\": [{\"name\": \"search_label\", \"mode\": \"pattern|yaml\", ...}], \"max_concurrency\": 4, \"max_matches_per_search\": 500}}
|
||||
- Example for pattern mode: {\"tool\": \"code_search\", \"args\": {\"searches\": [{\"name\": \"find_functions\", \"mode\": \"pattern\", \"pattern\": \"fn $NAME($$$ARGS) { $$$ }\", \"language\": \"rust\", \"paths\": [\"src/\"]}]}}
|
||||
- Example for YAML mode: {\"tool\": \"code_search\", \"args\": {\"searches\": [{\"name\": \"find_async\", \"mode\": \"yaml\", \"rule_yaml\": \"id: async-fn\nlanguage: Rust\nrule:\n pattern: async fn $NAME($$$) { $$$ }\"}]}}
|
||||
- Example for multiple searches: {\"tool\": \"code_search\", \"args\": {\"searches\": [{\"name\": \"funcs\", \"mode\": \"pattern\", \"pattern\": \"fn $NAME\", \"language\": \"rust\"}, {\"name\": \"structs\", \"mode\": \"pattern\", \"pattern\": \"struct $NAME\", \"language\": \"rust\"}]}}
|
||||
- Example for passing optional args like \"context\": {\"tool\": \"code_search\", \"args\": {\"searches\": [{\"name\": \"funcs\", \"mode\": \"pattern\", \"context\": 3, \"pattern\": \"fn $NAME\", \"language\": \"rust\"}]}
|
||||
- Common optional args for searches:
|
||||
- **code_search**: Syntax-aware code search using tree-sitter. Supports Rust, Python, JavaScript, TypeScript.
|
||||
- Format: {\"tool\": \"code_search\", \"args\": {\"searches\": [{\"name\": \"label\", \"query\": \"tree-sitter query\", \"language\": \"rust|python|javascript|typescript\", \"paths\": [\"src/\"], \"context_lines\": 0}]}}
|
||||
- Find functions: {\"tool\": \"code_search\", \"args\": {\"searches\": [{\"name\": \"find_functions\", \"query\": \"(function_item name: (identifier) @name)\", \"language\": \"rust\", \"paths\": [\"src/\"]}]}}
|
||||
- Find async functions: {\"tool\": \"code_search\", \"args\": {\"searches\": [{\"name\": \"find_async\", \"query\": \"(function_item (function_modifiers) name: (identifier) @name)\", \"language\": \"rust\"}]}}
|
||||
- Find structs: {\"tool\": \"code_search\", \"args\": {\"searches\": [{\"name\": \"structs\", \"query\": \"(struct_item name: (type_identifier) @name)\", \"language\": \"rust\"}]}}
|
||||
- Multiple searches: {\"tool\": \"code_search\", \"args\": {\"searches\": [{\"name\": \"funcs\", \"query\": \"(function_item name: (identifier) @name)\", \"language\": \"rust\"}, {\"name\": \"structs\", \"query\": \"(struct_item name: (type_identifier) @name)\", \"language\": \"rust\"}]}}
|
||||
- With context lines: {\"tool\": \"code_search\", \"args\": {\"searches\": [{\"name\": \"funcs\", \"query\": \"(function_item name: (identifier) @name)\", \"language\": \"rust\", \"context_lines\": 3}]}}
|
||||
- \"context\": 3 (show surrounding lines),
|
||||
- \"json_style\": \"stream\" (for large results)
|
||||
|
||||
@@ -1908,7 +1908,7 @@ Template:
|
||||
// Add code_search tool
|
||||
tools.push(Tool {
|
||||
name: "code_search".to_string(),
|
||||
description: "Batch syntax-aware searches via ast-grep. Supports up to 20 pattern or YAML-rule searches in parallel; returns JSON matches (stream-collated).".to_string(),
|
||||
description: "Batch syntax-aware code searches using embedded tree-sitter. Supports up to 20 searches in parallel for Rust, Python, JavaScript, and TypeScript. Uses tree-sitter query syntax (S-expressions).".to_string(),
|
||||
input_schema: json!({
|
||||
"type": "object",
|
||||
"properties": {
|
||||
@@ -1919,43 +1919,14 @@ Template:
|
||||
"type": "object",
|
||||
"properties": {
|
||||
"name": { "type": "string", "description": "Label for this search." },
|
||||
"mode": {
|
||||
"type": "string",
|
||||
"enum": ["pattern", "yaml"],
|
||||
"description": "`pattern` uses `ast-grep run`; `yaml` uses `ast-grep scan --inline-rules`."
|
||||
},
|
||||
// pattern mode (fast one-off)
|
||||
"pattern": { "type": "string", "description": "ast-grep pattern code (e.g., \"async fn $NAME($$$ARGS) { $$$ }\")"},
|
||||
"language": { "type": "string", "description": "Optional language for pattern mode; ast-grep may infer from file extensions if omitted." },
|
||||
// yaml mode (full rule object)
|
||||
"rule_yaml": { "type": "string", "description": "A full YAML rule object text. Must include `id`, `language`, and `rule`." },
|
||||
// targeting
|
||||
"query": { "type": "string", "description": "tree-sitter query in S-expression format (e.g., \"(function_item name: (identifier) @name)\")"},
|
||||
"language": { "type": "string", "enum": ["rust", "python", "javascript", "typescript"], "description": "Programming language to search." },
|
||||
"paths": { "type": "array", "items": { "type": "string" }, "description": "Paths/dirs to search. Defaults to current dir if empty." },
|
||||
"globs": { "type": "array", "items": { "type": "string" }, "description": "Optional include/exclude globs for CLI --globs." },
|
||||
// result formatting & performance knobs
|
||||
"json_style": { "type": "string", "enum": ["pretty","stream","compact"], "default": "stream", "description": "Use stream for large codebases." },
|
||||
"context": { "type": "integer", "minimum": 0, "maximum": 20, "default": 0, "description": "CLI -C context lines in text output; also affects JSON `lines` field." },
|
||||
"threads": { "type": "integer", "minimum": 1, "description": "Optional override for ast-grep -j (per process)." },
|
||||
"include_metadata": { "type": "boolean", "default": false, "description": "If yaml mode and rule has metadata, add --include-metadata." },
|
||||
// robustness
|
||||
"no_ignore": {
|
||||
"type": "array",
|
||||
"items": { "type": "string", "enum": ["hidden","dot","exclude","global","parent","vcs"] },
|
||||
"description": "Forwarded to --no-ignore to bypass ignore files/hidden."
|
||||
},
|
||||
// severity overrides for yaml mode
|
||||
"severity": {
|
||||
"type": "object",
|
||||
"additionalProperties": { "type": "string", "enum": ["error","warning","info","hint","off"] },
|
||||
"description": "Optional map<ruleId, severity> -> passed via --error/--warning/--info/--hint/--off."
|
||||
},
|
||||
// per-search timeout seconds (default 60)
|
||||
"timeout_secs": { "type": "integer", "minimum": 1, "default": 60 }
|
||||
"context_lines": { "type": "integer", "minimum": 0, "maximum": 20, "default": 0, "description": "Lines of context to include around each match." }
|
||||
},
|
||||
"required": ["name","mode"]
|
||||
"required": ["name", "query", "language"]
|
||||
}
|
||||
},
|
||||
// global concurrency & truncation
|
||||
"max_concurrency": { "type": "integer", "minimum": 1, "default": 4 },
|
||||
"max_matches_per_search": { "type": "integer", "minimum": 1, "default": 500 }
|
||||
},
|
||||
@@ -2395,13 +2366,6 @@ Template:
|
||||
|
||||
// Check if we need to summarize before starting
|
||||
if self.context_window.should_summarize() {
|
||||
info!(
|
||||
"Context window at {}% ({}/{} tokens), triggering auto-summarization",
|
||||
self.context_window.percentage_used() as u32,
|
||||
self.context_window.used_tokens,
|
||||
self.context_window.total_tokens
|
||||
);
|
||||
|
||||
// Notify user about summarization
|
||||
self.ui_writer.print_context_status(&format!(
|
||||
"\n🗜️ Context window reaching capacity ({}%). Creating summary...",
|
||||
@@ -4590,13 +4554,7 @@ Template:
|
||||
}
|
||||
}
|
||||
Err(e) => {
|
||||
// Check if it's an ast-grep not found error and provide helpful message
|
||||
let error_msg = e.to_string();
|
||||
if error_msg.contains("ast-grep not found") {
|
||||
Ok(format!("❌ {}", error_msg))
|
||||
} else {
|
||||
Ok(format!("❌ Code search failed: {}", error_msg))
|
||||
}
|
||||
Ok(format!("❌ Code search failed: {}", e))
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
412
crates/g3-core/tests/code_search_test.rs
Normal file
412
crates/g3-core/tests/code_search_test.rs
Normal file
@@ -0,0 +1,412 @@
|
||||
//! Integration tests for tree-sitter code search
|
||||
|
||||
use g3_core::code_search::{execute_code_search, CodeSearchRequest, SearchSpec};
|
||||
use std::fs;
|
||||
|
||||
#[tokio::test]
|
||||
async fn test_find_async_functions() {
|
||||
// Create a temporary test file
|
||||
let test_dir = std::env::temp_dir().join("g3_test_code_search");
|
||||
fs::create_dir_all(&test_dir).unwrap();
|
||||
|
||||
let test_file = test_dir.join("test.rs");
|
||||
fs::write(
|
||||
&test_file,
|
||||
r#"
|
||||
pub async fn example_async() {
|
||||
println!("Hello");
|
||||
}
|
||||
|
||||
fn regular_function() {
|
||||
println!("Regular");
|
||||
}
|
||||
|
||||
pub async fn another_async(x: i32) -> Result<(), ()> {
|
||||
Ok(())
|
||||
}
|
||||
"#,
|
||||
)
|
||||
.unwrap();
|
||||
|
||||
// Test 1: Find async functions
|
||||
let request = CodeSearchRequest {
|
||||
searches: vec![SearchSpec {
|
||||
name: "find_async_functions".to_string(),
|
||||
// In tree-sitter-rust, async is a token inside function_modifiers
|
||||
query: "(function_item (function_modifiers) name: (identifier) @name)".to_string(),
|
||||
language: "rust".to_string(),
|
||||
paths: vec![test_dir.to_string_lossy().to_string()],
|
||||
context_lines: 0,
|
||||
}],
|
||||
max_concurrency: 4,
|
||||
max_matches_per_search: 100,
|
||||
};
|
||||
|
||||
let response = execute_code_search(request).await.unwrap();
|
||||
|
||||
assert_eq!(response.searches.len(), 1);
|
||||
let search_result = &response.searches[0];
|
||||
assert_eq!(search_result.name, "find_async_functions");
|
||||
assert_eq!(search_result.match_count, 2, "Should find 2 async functions");
|
||||
assert!(search_result.error.is_none());
|
||||
|
||||
// Check that we found the right functions
|
||||
let function_names: Vec<String> = search_result
|
||||
.matches
|
||||
.iter()
|
||||
.filter_map(|m| m.captures.get("name").cloned())
|
||||
.collect();
|
||||
|
||||
assert!(function_names.contains(&"example_async".to_string()));
|
||||
assert!(function_names.contains(&"another_async".to_string()));
|
||||
|
||||
// Cleanup
|
||||
fs::remove_dir_all(&test_dir).ok();
|
||||
}
|
||||
|
||||
#[tokio::test]
|
||||
async fn test_find_all_functions() {
|
||||
// Create a temporary test file
|
||||
let test_dir = std::env::temp_dir().join("g3_test_code_search_2");
|
||||
fs::create_dir_all(&test_dir).unwrap();
|
||||
|
||||
let test_file = test_dir.join("test.rs");
|
||||
fs::write(
|
||||
&test_file,
|
||||
r#"
|
||||
pub async fn example_async() {
|
||||
println!("Hello");
|
||||
}
|
||||
|
||||
fn regular_function() {
|
||||
println!("Regular");
|
||||
}
|
||||
|
||||
pub async fn another_async(x: i32) -> Result<(), ()> {
|
||||
Ok(())
|
||||
}
|
||||
"#,
|
||||
)
|
||||
.unwrap();
|
||||
|
||||
// Test 2: Find all functions (async and regular)
|
||||
let request = CodeSearchRequest {
|
||||
searches: vec![SearchSpec {
|
||||
name: "find_all_functions".to_string(),
|
||||
query: "(function_item name: (identifier) @name)".to_string(),
|
||||
language: "rust".to_string(),
|
||||
paths: vec![test_dir.to_string_lossy().to_string()],
|
||||
context_lines: 0,
|
||||
}],
|
||||
max_concurrency: 4,
|
||||
max_matches_per_search: 100,
|
||||
};
|
||||
|
||||
let response = execute_code_search(request).await.unwrap();
|
||||
|
||||
assert_eq!(response.searches.len(), 1);
|
||||
let search_result = &response.searches[0];
|
||||
assert_eq!(search_result.name, "find_all_functions");
|
||||
assert_eq!(search_result.match_count, 3, "Should find 3 functions total");
|
||||
assert!(search_result.error.is_none());
|
||||
|
||||
// Check that we found all functions
|
||||
let function_names: Vec<String> = search_result
|
||||
.matches
|
||||
.iter()
|
||||
.filter_map(|m| m.captures.get("name").cloned())
|
||||
.collect();
|
||||
|
||||
assert!(function_names.contains(&"example_async".to_string()));
|
||||
assert!(function_names.contains(&"regular_function".to_string()));
|
||||
assert!(function_names.contains(&"another_async".to_string()));
|
||||
|
||||
// Cleanup
|
||||
fs::remove_dir_all(&test_dir).ok();
|
||||
}
|
||||
|
||||
#[tokio::test]
|
||||
async fn test_find_structs() {
|
||||
// Create a temporary test file
|
||||
let test_dir = std::env::temp_dir().join("g3_test_code_search_3");
|
||||
fs::create_dir_all(&test_dir).unwrap();
|
||||
|
||||
let test_file = test_dir.join("test.rs");
|
||||
fs::write(
|
||||
&test_file,
|
||||
r#"
|
||||
pub struct MyStruct {
|
||||
field: String,
|
||||
}
|
||||
|
||||
struct AnotherStruct;
|
||||
|
||||
enum MyEnum {
|
||||
Variant,
|
||||
}
|
||||
"#,
|
||||
)
|
||||
.unwrap();
|
||||
|
||||
// Test 3: Find structs
|
||||
let request = CodeSearchRequest {
|
||||
searches: vec![SearchSpec {
|
||||
name: "find_structs".to_string(),
|
||||
query: "(struct_item name: (type_identifier) @name)".to_string(),
|
||||
language: "rust".to_string(),
|
||||
paths: vec![test_dir.to_string_lossy().to_string()],
|
||||
context_lines: 0,
|
||||
}],
|
||||
max_concurrency: 4,
|
||||
max_matches_per_search: 100,
|
||||
};
|
||||
|
||||
let response = execute_code_search(request).await.unwrap();
|
||||
|
||||
assert_eq!(response.searches.len(), 1);
|
||||
let search_result = &response.searches[0];
|
||||
assert_eq!(search_result.name, "find_structs");
|
||||
assert_eq!(search_result.match_count, 2, "Should find 2 structs");
|
||||
assert!(search_result.error.is_none());
|
||||
|
||||
// Check that we found the right structs
|
||||
let struct_names: Vec<String> = search_result
|
||||
.matches
|
||||
.iter()
|
||||
.filter_map(|m| m.captures.get("name").cloned())
|
||||
.collect();
|
||||
|
||||
assert!(struct_names.contains(&"MyStruct".to_string()));
|
||||
assert!(struct_names.contains(&"AnotherStruct".to_string()));
|
||||
|
||||
// Cleanup
|
||||
fs::remove_dir_all(&test_dir).ok();
|
||||
}
|
||||
|
||||
#[tokio::test]
|
||||
async fn test_context_lines() {
|
||||
// Create a temporary test file
|
||||
let test_dir = std::env::temp_dir().join("g3_test_code_search_4");
|
||||
fs::create_dir_all(&test_dir).unwrap();
|
||||
|
||||
let test_file = test_dir.join("test.rs");
|
||||
fs::write(
|
||||
&test_file,
|
||||
r#"
|
||||
// Line 1
|
||||
// Line 2
|
||||
pub fn target_function() {
|
||||
// Line 4
|
||||
println!("target");
|
||||
}
|
||||
// Line 7
|
||||
// Line 8
|
||||
"#,
|
||||
)
|
||||
.unwrap();
|
||||
|
||||
// Test 4: Context lines
|
||||
let request = CodeSearchRequest {
|
||||
searches: vec![SearchSpec {
|
||||
name: "find_with_context".to_string(),
|
||||
query: "(function_item name: (identifier) @name)".to_string(),
|
||||
language: "rust".to_string(),
|
||||
paths: vec![test_dir.to_string_lossy().to_string()],
|
||||
context_lines: 2,
|
||||
}],
|
||||
max_concurrency: 4,
|
||||
max_matches_per_search: 100,
|
||||
};
|
||||
|
||||
let response = execute_code_search(request).await.unwrap();
|
||||
|
||||
assert_eq!(response.searches.len(), 1);
|
||||
let search_result = &response.searches[0];
|
||||
assert_eq!(search_result.match_count, 1);
|
||||
|
||||
let match_result = &search_result.matches[0];
|
||||
assert!(match_result.context.is_some());
|
||||
|
||||
let context = match_result.context.as_ref().unwrap();
|
||||
assert!(context.contains("Line 2"), "Should include 2 lines before");
|
||||
assert!(context.contains("target_function"), "Should include the function");
|
||||
// Note: context_lines=2 means 2 lines before and after the match line (line 4)
|
||||
// So we get lines 2-6, which includes up to println but not the closing brace
|
||||
assert!(context.contains("println"), "Should include 2 lines after the match");
|
||||
|
||||
// Cleanup
|
||||
fs::remove_dir_all(&test_dir).ok();
|
||||
}
|
||||
|
||||
#[tokio::test]
|
||||
async fn test_multiple_searches() {
|
||||
// Create a temporary test file
|
||||
let test_dir = std::env::temp_dir().join("g3_test_code_search_5");
|
||||
fs::create_dir_all(&test_dir).unwrap();
|
||||
|
||||
let test_file = test_dir.join("test.rs");
|
||||
fs::write(
|
||||
&test_file,
|
||||
r#"
|
||||
pub async fn async_func() {}
|
||||
fn regular_func() {}
|
||||
pub struct MyStruct;
|
||||
"#,
|
||||
)
|
||||
.unwrap();
|
||||
|
||||
// Test 5: Multiple searches in one request
|
||||
let request = CodeSearchRequest {
|
||||
searches: vec![
|
||||
SearchSpec {
|
||||
name: "async_functions".to_string(),
|
||||
query: "(function_item (function_modifiers) name: (identifier) @name)".to_string(),
|
||||
language: "rust".to_string(),
|
||||
paths: vec![test_dir.to_string_lossy().to_string()],
|
||||
context_lines: 0,
|
||||
},
|
||||
SearchSpec {
|
||||
name: "structs".to_string(),
|
||||
query: "(struct_item name: (type_identifier) @name)".to_string(),
|
||||
language: "rust".to_string(),
|
||||
paths: vec![test_dir.to_string_lossy().to_string()],
|
||||
context_lines: 0,
|
||||
},
|
||||
],
|
||||
max_concurrency: 4,
|
||||
max_matches_per_search: 100,
|
||||
};
|
||||
|
||||
let response = execute_code_search(request).await.unwrap();
|
||||
|
||||
assert_eq!(response.searches.len(), 2);
|
||||
assert_eq!(response.total_matches, 2); // 1 async function + 1 struct
|
||||
|
||||
// Check first search (async functions)
|
||||
let async_search = &response.searches[0];
|
||||
assert_eq!(async_search.name, "async_functions");
|
||||
assert_eq!(async_search.match_count, 1);
|
||||
|
||||
// Check second search (structs)
|
||||
let struct_search = &response.searches[1];
|
||||
assert_eq!(struct_search.name, "structs");
|
||||
assert_eq!(struct_search.match_count, 1);
|
||||
|
||||
// Cleanup
|
||||
fs::remove_dir_all(&test_dir).ok();
|
||||
}
|
||||
|
||||
#[tokio::test]
|
||||
async fn test_python_search() {
|
||||
// Create a temporary Python test file
|
||||
let test_dir = std::env::temp_dir().join("g3_test_code_search_python");
|
||||
fs::create_dir_all(&test_dir).unwrap();
|
||||
|
||||
let test_file = test_dir.join("test.py");
|
||||
fs::write(
|
||||
&test_file,
|
||||
r#"
|
||||
def regular_function():
|
||||
pass
|
||||
|
||||
async def async_function():
|
||||
pass
|
||||
|
||||
class MyClass:
|
||||
def method(self):
|
||||
pass
|
||||
"#,
|
||||
)
|
||||
.unwrap();
|
||||
|
||||
// Test 6: Python async functions
|
||||
let request = CodeSearchRequest {
|
||||
searches: vec![SearchSpec {
|
||||
name: "python_async".to_string(),
|
||||
// Note: tree-sitter-python doesn't expose 'async' as a queryable node
|
||||
// For now, we'll just find all functions (async detection would need text matching)
|
||||
query: "(function_definition name: (identifier) @name)".to_string(),
|
||||
language: "python".to_string(),
|
||||
paths: vec![test_dir.to_string_lossy().to_string()],
|
||||
context_lines: 0,
|
||||
}],
|
||||
max_concurrency: 4,
|
||||
max_matches_per_search: 100,
|
||||
};
|
||||
|
||||
let response = execute_code_search(request).await.unwrap();
|
||||
|
||||
assert_eq!(response.searches.len(), 1);
|
||||
let search_result = &response.searches[0];
|
||||
assert_eq!(search_result.match_count, 3, "Should find 3 functions in Python (2 regular + 1 async + 1 method)");
|
||||
|
||||
let function_names: Vec<String> = search_result
|
||||
.matches
|
||||
.iter()
|
||||
.filter_map(|m| m.captures.get("name").cloned())
|
||||
.collect();
|
||||
|
||||
assert!(function_names.contains(&"regular_function".to_string()));
|
||||
assert!(function_names.contains(&"async_function".to_string()));
|
||||
assert!(function_names.contains(&"method".to_string()));
|
||||
|
||||
// Cleanup
|
||||
fs::remove_dir_all(&test_dir).ok();
|
||||
}
|
||||
|
||||
#[tokio::test]
|
||||
async fn test_javascript_search() {
|
||||
// Create a temporary JavaScript test file
|
||||
let test_dir = std::env::temp_dir().join("g3_test_code_search_js");
|
||||
fs::create_dir_all(&test_dir).unwrap();
|
||||
|
||||
let test_file = test_dir.join("test.js");
|
||||
fs::write(
|
||||
&test_file,
|
||||
r#"
|
||||
function regularFunction() {
|
||||
console.log("regular");
|
||||
}
|
||||
|
||||
async function asyncFunction() {
|
||||
console.log("async");
|
||||
}
|
||||
|
||||
class MyClass {
|
||||
constructor() {}
|
||||
}
|
||||
"#,
|
||||
)
|
||||
.unwrap();
|
||||
|
||||
// Test 7: JavaScript functions
|
||||
let request = CodeSearchRequest {
|
||||
searches: vec![SearchSpec {
|
||||
name: "js_functions".to_string(),
|
||||
query: "(function_declaration name: (identifier) @name)".to_string(),
|
||||
language: "javascript".to_string(),
|
||||
paths: vec![test_dir.to_string_lossy().to_string()],
|
||||
context_lines: 0,
|
||||
}],
|
||||
max_concurrency: 4,
|
||||
max_matches_per_search: 100,
|
||||
};
|
||||
|
||||
let response = execute_code_search(request).await.unwrap();
|
||||
|
||||
assert_eq!(response.searches.len(), 1);
|
||||
let search_result = &response.searches[0];
|
||||
assert_eq!(search_result.match_count, 2, "Should find 2 functions in JavaScript");
|
||||
|
||||
let function_names: Vec<String> = search_result
|
||||
.matches
|
||||
.iter()
|
||||
.filter_map(|m| m.captures.get("name").cloned())
|
||||
.collect();
|
||||
|
||||
assert!(function_names.contains(&"regularFunction".to_string()));
|
||||
assert!(function_names.contains(&"asyncFunction".to_string()));
|
||||
|
||||
// Cleanup
|
||||
fs::remove_dir_all(&test_dir).ok();
|
||||
}
|
||||
Reference in New Issue
Block a user