gitdata.ai/gitks
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

refactor(bare): enhance security and performance optimizations

Browse Source 
- Remove unnecessary sorting in advertise_refs for deterministic output
- Add path traversal detection and validation in bare_dir construction
- Implement symlink resolution checks to prevent security vulnerabilities
- Refactor cache system with CRC validation and improved metrics
- Integrate repo-specific cache invalidation using indexed keys
- Add comprehensive unit tests for commit operations and diff functionality
- Move configuration constants to centralized config module
- Optimize string operations in disk cache random value generation
- Enhance license detection algorithm with cleaner matching logic
- Streamline argument processing in various git operations
- Update dependencies including crc32fast and flate2 for performance
- Add signal handling capability to tokio runtime configuration
This commit is contained in:
zhenyi
2026-06-12 15:04:12 +08:00
parent e386f44ee2
commit 10a4398e81
41 changed files with 1373 additions and 365 deletions
Download Patch File Download Diff File Expand all files Collapse all files
repository/find_license.rs
-11
View File
@@ -57,57 +57,46 @@ impl GitBare {
fn detect_license(content: &str) -> (&'static str, &'static str, f64) {
let lower = content.to_lowercase();
// MIT
if lower.contains("permission is hereby granted, free of charge") && lower.contains("mit") {
return ("MIT", "MIT License", 0.95);
}
// Apache 2.0
if lower.contains("apache license, version 2.0") || lower.contains("apache-2.0") {
return ("Apache-2.0", "Apache License 2.0", 0.95);
}
// GPL 3.0
if lower.contains("gnu general public license") && lower.contains("version 3") {
return ("GPL-3.0", "GNU General Public License v3.0", 0.90);
}
// GPL 2.0
if lower.contains("gnu general public license") && lower.contains("version 2") {
return ("GPL-2.0", "GNU General Public License v2.0", 0.90);
}
// BSD 3
if lower.contains("redistribution and use in source and binary forms")
&& lower.contains("neither the name of")
{
return ("BSD-3-Clause", "BSD 3-Clause License", 0.85);
}
// BSD 2
if lower.contains("redistribution and use in source and binary forms") {
return ("BSD-2-Clause", "BSD 2-Clause License", 0.80);
}
// AGPL
if lower.contains("gnu affero general public license") {
return ("AGPL-3.0", "GNU Affero General Public License v3.0", 0.90);
}
// LGPL
if lower.contains("gnu lesser general public license") {
return ("LGPL-3.0", "GNU Lesser General Public License v3.0", 0.85);
}
// MPL
if lower.contains("mozilla public license") {
return ("MPL-2.0", "Mozilla Public License 2.0", 0.90);
}
// Unlicense
if lower.contains("this is free and unencumbered software released into the public domain") {
return ("Unlicense", "The Unlicense", 0.95);
}
// ISC
if lower.contains("permission to use, copy, modify, and/or distribute") && lower.contains("isc")
{
return ("ISC", "ISC License", 0.80);
repository/lang_stats.rs
-15
View File
@@ -7,7 +7,6 @@ use crate::bare::GitBare;
use crate::error::{GitError, GitResult};
use crate::pb::{GetLanguageStatsRequest, GetLanguageStatsResponse, LanguageStat, object_selector};
// Include the generated linguist rules
include!(concat!(env!("OUT_DIR"), "/linguist_generated.rs"));
/// Default max file size for line counting (512 KB).
@@ -17,7 +16,6 @@ const MAX_TREE_WALK_DEPTH: usize = 256;
/// Look up a language by file extension (case-insensitive, includes leading dot).
fn lookup_by_extension(ext: &str) -> Option<(&'static str, &'static str)> {
let ext_lower = ext.to_lowercase();
// Binary search on the sorted EXTENSION_MAP
EXTENSION_MAP
.binary_search_by(|&(e, _, _)| e.cmp(ext_lower.as_str()))
.ok()
@@ -54,13 +52,11 @@ fn detect_language(path: &str, is_binary: bool) -> Option<(&'static str, &'stati
.and_then(|n| n.to_str())
.unwrap_or("");
// Try filename match first (e.g., Makefile, Dockerfile)
if let Some(result) = lookup_by_filename(file_name) {
tracing::debug!(path = %path, lang = result.0, "matched by filename");
return Some(result);
}
// Try extension match
if let Some(ext) = Path::new(path).extension().and_then(|e| e.to_str()) {
let ext_with_dot = format!(".{ext}");
if let Some(result) = lookup_by_extension(&ext_with_dot) {
@@ -72,13 +68,10 @@ fn detect_language(path: &str, is_binary: bool) -> Option<(&'static str, &'stati
tracing::debug!(path = %path, "no extension found");
}
// For binary files with no recognized extension, classify by media type
if is_binary {
// Try extension-based binary classification
if let Some(ext) = Path::new(path).extension().and_then(|e| e.to_str()) {
let ext_lower = format!(".{ext}").to_lowercase();
let media_type = classify_binary_extension(&ext_lower);
// Return as a synthetic language name
return Some((media_type, "data"));
}
return Some(("Binary", "data"));
@@ -146,7 +139,6 @@ impl GitBare {
.try_into_tree()
.map_err(|e| GitError::Gix(e.to_string()))?;
// If path is specified, descend into subdirectory
if !request.path.is_empty() {
crate::sanitize::validate_file_path(&request.path)?;
let entry = tree
@@ -173,7 +165,6 @@ impl GitBare {
};
self.walk_tree(&repo, &tree, &prefix, 0, &mut ctx)?;
// Resolve groups: merge child language stats into parent group
tracing::info!(
total_files,
total_bytes,
@@ -193,13 +184,11 @@ impl GitBare {
entry.file_count = entry.file_count.saturating_add(s.file_count);
entry.bytes = entry.bytes.saturating_add(s.bytes);
entry.lines = entry.lines.saturating_add(s.lines);
// Keep the lang_type from the parent (or first encountered)
if entry.lang_type.is_empty() {
entry.lang_type = s.lang_type;
}
}
// Build response sorted by bytes descending
let mut languages: Vec<LanguageStat> = resolved
.into_iter()
.map(|(language, s)| {
@@ -272,15 +261,12 @@ impl GitBare {
let data = &blob.data;
let size = data.len() as u64;
// Skip empty files
if size == 0 {
continue;
}
// Check if binary (contains null byte)
let is_binary = data.contains(&0);
// Detect language
let Some((lang_name, lang_type)) = detect_language(&path, is_binary) else {
tracing::debug!(path = %path, is_binary, "no language detected");
continue;
@@ -288,7 +274,6 @@ impl GitBare {
let lang_key = lang_name.to_string();
// Count code lines only for non-binary files within size limit
let lines = if !is_binary && size <= u64::from(ctx.max_file_size) {
count_code_lines(data)
} else {
repository/optimize.rs
-7
View File
@@ -18,7 +18,6 @@ impl GitBare {
OptimizeStrategy::Heuristic | OptimizeStrategy::Aggressive => {
let stats = self.get_repository_statistics()?;
// Run commit-graph write if needed
if (stats.commit_graph_size_bytes == 0 || strategy == OptimizeStrategy::Aggressive)
&& let Ok(resp) = write_commit_graph(self, false, false)
{
@@ -28,7 +27,6 @@ impl GitBare {
stdout_all.push_str(&resp.stdout);
}
// Repack if many loose objects or packfiles
let repack_needed = stats.loose_object_count > 1000 || stats.packfile_count > 10;
if repack_needed || strategy == OptimizeStrategy::Aggressive {
@@ -41,7 +39,6 @@ impl GitBare {
}
}
// Prune if aggressive
if strategy == OptimizeStrategy::Aggressive
&& let Ok(resp) = run_gc(self, true, true)
{
@@ -52,7 +49,6 @@ impl GitBare {
}
}
OptimizeStrategy::Incremental => {
// Just run commit-graph write incrementally
if let Ok(resp) = write_commit_graph(self, false, false) {
if !resp.ok {
stderr_all.push_str(&resp.stderr);
@@ -71,7 +67,6 @@ impl GitBare {
}
fn get_repository_statistics(&self) -> GitResult<RepositoryStatistics> {
// Count loose objects
let loose = std::fs::read_dir(self.bare_dir.join("objects"))
.map(|d| {
d.filter_map(|e| e.ok())
@@ -83,13 +78,11 @@ impl GitBare {
})
.unwrap_or(0);
// Count packfiles
let pack_dir = self.bare_dir.join("objects").join("pack");
let pack_count = std::fs::read_dir(&pack_dir)
.map(|d| d.filter_map(|e| e.ok()).count() as u64)
.unwrap_or(0);
// Check commit-graph
let cg_size = std::fs::metadata(
self.bare_dir
.join("objects")
repository/search_files.rs
-2
View File
@@ -67,7 +67,6 @@ impl GitBare {
let mut results = Vec::new();
for line in stdout.lines() {
// Format: path:line:col:matched_text
if let Some((path_and_rest, matched)) = line.rsplit_once(':') {
let prefix_parts: Vec<&str> = path_and_rest.rsplitn(3, ':').collect();
if prefix_parts.len() >= 3
@@ -144,7 +143,6 @@ impl GitBare {
continue;
}
// Simple substring/case-insensitive matching for file names
let query = &request.query;
let matched = if query.is_empty() {
true