mirror of
https://github.com/ivuorinen/gibidify.git
synced 2026-01-26 03:24:05 +00:00
* build: update Go 1.25, CI workflows, and build tooling - Upgrade to Go 1.25 - Add benchmark targets to Makefile - Implement parallel gosec execution - Lock tool versions for reproducibility - Add shellcheck directives to scripts - Update CI workflows with improved caching * refactor: migrate from golangci-lint to revive - Replace golangci-lint with revive for linting - Configure comprehensive revive rules - Fix all EditorConfig violations - Add yamllint and yamlfmt support - Remove deprecated .golangci.yml * refactor: rename utils to shared and deduplicate code - Rename utils package to shared - Add shared constants package - Deduplicate constants across packages - Address CodeRabbit review feedback * fix: resolve SonarQube issues and add safety guards - Fix all 73 SonarQube OPEN issues - Add nil guards for resourceMonitor, backpressure, metricsCollector - Implement io.Closer for headerFileReader - Propagate errors from processing helpers - Add metrics and templates packages - Improve error handling across codebase * test: improve test infrastructure and coverage - Add benchmarks for cli, fileproc, metrics - Improve test coverage for cli, fileproc, config - Refactor tests with helper functions - Add shared test constants - Fix test function naming conventions - Reduce cognitive complexity in benchmark tests * docs: update documentation and configuration examples - Update CLAUDE.md with current project state - Refresh README with new features - Add usage and configuration examples - Add SonarQube project configuration - Consolidate config.example.yaml * fix: resolve shellcheck warnings in scripts - Use ./*.go instead of *.go to prevent dash-prefixed filenames from being interpreted as options (SC2035) - Remove unreachable return statement after exit (SC2317) - Remove obsolete gibidiutils/ directory reference * chore(deps): upgrade go dependencies * chore(lint): megalinter fixes * fix: improve test coverage and fix file descriptor leaks - Add defer r.Close() to fix pipe file descriptor leaks in benchmark tests - Refactor TestProcessorConfigureFileTypes with helper functions and assertions - Refactor TestProcessorLogFinalStats with output capture and keyword verification - Use shared constants instead of literal strings (TestFilePNG, FormatMarkdown, etc.) - Reduce cognitive complexity by extracting helper functions * fix: align test comments with function names Remove underscores from test comments to match actual function names: - benchmark/benchmark_test.go (2 fixes) - fileproc/filetypes_config_test.go (4 fixes) - fileproc/filetypes_registry_test.go (6 fixes) - fileproc/processor_test.go (6 fixes) - fileproc/resource_monitor_types_test.go (4 fixes) - fileproc/writer_test.go (3 fixes) * fix: various test improvements and bug fixes - Remove duplicate maxCacheSize check in filetypes_registry_test.go - Shorten long comment in processor_test.go to stay under 120 chars - Remove flaky time.Sleep in collector_test.go, use >= 0 assertion - Close pipe reader in benchmark_test.go to fix file descriptor leak - Use ContinueOnError in flags_test.go to match ResetFlags behavior - Add nil check for p.ui in processor_workers.go before UpdateProgress - Fix resource_monitor_validation_test.go by setting hardMemoryLimitBytes directly * chore(yaml): add missing document start markers Add --- document start to YAML files to satisfy yamllint: - .github/workflows/codeql.yml - .github/workflows/build-test-publish.yml - .github/workflows/security.yml - .github/actions/setup/action.yml * fix: guard nil resourceMonitor and fix test deadlock - Guard resourceMonitor before CreateFileProcessingContext call - Add ui.UpdateProgress on emergency stop and path error returns - Fix potential deadlock in TestProcessFile using wg.Go with defer close
131 lines
3.1 KiB
Go
131 lines
3.1 KiB
Go
// Package fileproc handles file processing, collection, and output formatting.
|
|
package fileproc
|
|
|
|
// getNormalizedExtension efficiently extracts and normalizes the file extension with caching.
|
|
func (r *FileTypeRegistry) getNormalizedExtension(filename string) string {
|
|
// Try cache first (read lock)
|
|
r.cacheMutex.RLock()
|
|
if ext, exists := r.extCache[filename]; exists {
|
|
r.cacheMutex.RUnlock()
|
|
|
|
return ext
|
|
}
|
|
r.cacheMutex.RUnlock()
|
|
|
|
// Compute normalized extension
|
|
ext := normalizeExtension(filename)
|
|
|
|
// Cache the result (write lock)
|
|
r.cacheMutex.Lock()
|
|
// Check cache size and clean if needed
|
|
if len(r.extCache) >= r.maxCacheSize*2 {
|
|
r.clearExtCache()
|
|
r.stats.CacheEvictions++
|
|
}
|
|
r.extCache[filename] = ext
|
|
r.cacheMutex.Unlock()
|
|
|
|
return ext
|
|
}
|
|
|
|
// getFileTypeResult gets cached file type detection result or computes it.
|
|
func (r *FileTypeRegistry) getFileTypeResult(filename string) FileTypeResult {
|
|
ext := r.getNormalizedExtension(filename)
|
|
|
|
// Update statistics
|
|
r.updateStats(func() {
|
|
r.stats.TotalLookups++
|
|
})
|
|
|
|
// Try cache first (read lock)
|
|
r.cacheMutex.RLock()
|
|
if result, exists := r.resultCache[ext]; exists {
|
|
r.cacheMutex.RUnlock()
|
|
r.updateStats(func() {
|
|
r.stats.CacheHits++
|
|
})
|
|
|
|
return result
|
|
}
|
|
r.cacheMutex.RUnlock()
|
|
|
|
// Cache miss
|
|
r.updateStats(func() {
|
|
r.stats.CacheMisses++
|
|
})
|
|
|
|
// Compute result
|
|
result := FileTypeResult{
|
|
Extension: ext,
|
|
IsImage: r.imageExts[ext],
|
|
IsBinary: r.binaryExts[ext],
|
|
Language: r.languageMap[ext],
|
|
}
|
|
|
|
// Handle special cases for binary detection (like .DS_Store)
|
|
if !result.IsBinary && isSpecialFile(filename, r.binaryExts) {
|
|
result.IsBinary = true
|
|
}
|
|
|
|
// Cache the result (write lock)
|
|
r.cacheMutex.Lock()
|
|
if len(r.resultCache) >= r.maxCacheSize {
|
|
r.clearResultCache()
|
|
r.stats.CacheEvictions++
|
|
}
|
|
r.resultCache[ext] = result
|
|
r.cacheMutex.Unlock()
|
|
|
|
return result
|
|
}
|
|
|
|
// clearExtCache clears half of the extension cache (LRU-like behavior).
|
|
func (r *FileTypeRegistry) clearExtCache() {
|
|
r.clearCache(&r.extCache, r.maxCacheSize)
|
|
}
|
|
|
|
// clearResultCache clears half of the result cache.
|
|
func (r *FileTypeRegistry) clearResultCache() {
|
|
newCache := make(map[string]FileTypeResult, r.maxCacheSize)
|
|
count := 0
|
|
for k, v := range r.resultCache {
|
|
if count >= r.maxCacheSize/2 {
|
|
break
|
|
}
|
|
newCache[k] = v
|
|
count++
|
|
}
|
|
r.resultCache = newCache
|
|
}
|
|
|
|
// clearCache is a generic cache clearing function.
|
|
func (r *FileTypeRegistry) clearCache(cache *map[string]string, maxSize int) {
|
|
newCache := make(map[string]string, maxSize)
|
|
count := 0
|
|
for k, v := range *cache {
|
|
if count >= maxSize/2 {
|
|
break
|
|
}
|
|
newCache[k] = v
|
|
count++
|
|
}
|
|
*cache = newCache
|
|
}
|
|
|
|
// invalidateCache clears both caches when the registry is modified.
|
|
func (r *FileTypeRegistry) invalidateCache() {
|
|
r.cacheMutex.Lock()
|
|
defer r.cacheMutex.Unlock()
|
|
|
|
r.extCache = make(map[string]string, r.maxCacheSize)
|
|
r.resultCache = make(map[string]FileTypeResult, r.maxCacheSize)
|
|
r.stats.CacheEvictions++
|
|
}
|
|
|
|
// updateStats safely updates statistics.
|
|
func (r *FileTypeRegistry) updateStats(fn func()) {
|
|
r.cacheMutex.Lock()
|
|
fn()
|
|
r.cacheMutex.Unlock()
|
|
}
|