Files
trufflehog/pkg/writers/buffer_writer/bufferwriter.go
ahrav 5257069748 [chore] - move buffers pkg out of writers pkg (#2826)
* Remove specialized handler and archive struct and restructure handlers pkg.

* Refactor RPM archive handlers to use a library instead of shelling out

* make rpm handling context aware

* update test

* Refactor AR/deb archive handler to use an existing library instead of shelling out

* Update tests

* Handle non-archive data within the DefaultHandler

* make structs and methods private

* Remove non-archive data handling within sources

* add max size check

* add filename and size to context kvp

* move skip file check and is binary check before opening file

* fix test

* preserve existing funcitonality of not handling non-archive files in HandleFile

* Handle non-archive data within the DefaultHandler

* rebase

* Remove non-archive data handling within sources

* Adjust check for rpm/deb archive type

* add additional deb mime type

* add gzip

* move diskbuffered rereader setup into handler pkg

* remove DiskBuffereReader creation logic within sources

* update comment

* move rewind closer

* reduce log verbosity

* add metrics for file handling

* add metrics for errors

* make defaultBufferSize a const

* add metrics for file handling

* add metrics for errors

* fix tests

* add metrics for max archive depth and skipped files

* update error

* skip symlinks and dirs

* update err

* Address incompatible reader to openArchive

* remove nil check

* fix err assignment

* Allow git cat-file blob to complete before trying to handle the file

* wrap compReader with DiskbufferReader

* Allow git cat-file blob to complete before trying to handle the file

* updates

* use buffer writer

* update

* refactor

* update context pkg

* revert stuff

* update test

* fix test

* remove

* use correct reader

* add metrics for file handling

* add metrics for errors

* fix tests

* rebase

* add metrics for errors

* add metrics for max archive depth and skipped files

* update error

* skip symlinks and dirs

* update err

* fix err assignment

* rebase

* remove

* Update write method in contentWriter interface

* Add bufferReadSeekCloser

* update name

* update comment

* fix lint

* Remove specialized handler and archive struct and restructure handlers pkg.

* Refactor RPM archive handlers to use a library instead of shelling out

* make rpm handling context aware

* update test

* Refactor AR/deb archive handler to use an existing library instead of shelling out

* Update tests

* add max size check

* add filename and size to context kvp

* move skip file check and is binary check before opening file

* fix test

* preserve existing funcitonality of not handling non-archive files in HandleFile

* Handle non-archive data within the DefaultHandler

* rebase

* Remove non-archive data handling within sources

* Handle non-archive data within the DefaultHandler

* add gzip

* move diskbuffered rereader setup into handler pkg

* remove DiskBuffereReader creation logic within sources

* update comment

* move rewind closer

* reduce log verbosity

* make defaultBufferSize a const

* add metrics for file handling

* add metrics for errors

* fix tests

* add metrics for max archive depth and skipped files

* update error

* skip symlinks and dirs

* update err

* Address incompatible reader to openArchive

* remove nil check

* fix err assignment

* wrap compReader with DiskbufferReader

* Allow git cat-file blob to complete before trying to handle the file

* updates

* use buffer writer

* update

* refactor

* update context pkg

* revert stuff

* update test

* remove

* rebase

* go mod tidy

* lint check

* update metric to ms

* update metric

* update comments

* dont use ptr

* update

* fix

* Remove specialized handler and archive struct and restructure handlers pkg.

* Refactor RPM archive handlers to use a library instead of shelling out

* make rpm handling context aware

* update test

* Refactor AR/deb archive handler to use an existing library instead of shelling out

* Update tests

* add max size check

* add filename and size to context kvp

* move skip file check and is binary check before opening file

* fix test

* preserve existing funcitonality of not handling non-archive files in HandleFile

* Adjust check for rpm/deb archive type

* add additional deb mime type

* update comment

* go mod tidy

* update go mod

* Add a buffered file reader

* update comments

* use Buffered File Readder

* return buffer

* update

* fix

* return

* go mod tidy

* merge

* use a shared pool

* use sync.Once

* reorganzie

* remove unused code

* fix double init

* fix stuff

* nil check

* reduce allocations

* updates

* update metrics

* updates

* reset buffer instead of putting it back

* skip binaries

* skip

* concurrently process diffs

* close chan

* concurrently enumerate orgs

* increase workers

* ignore pbix and vsdx files

* add metrics for gitparse's Diffchan

* fix metric

* update metrics

* update

* fix checks

* fix

* inc

* update

* reduce

* Create workers to handle binary files

* modify workers

* updates

* add check

* delete code

* use custom reader

* rename struct

* add nonarchive handler

* fix break

* add comments

* add tests

* refactor

* remove log

* do not scan rpm links

* simplify

* rename var

* rename

* fix benchmark

* add buffer

* buffer

* buffer

* handle panic

* merge main

* merge main

* add recover

* revert stuff

* revert

* revert to using reader

* fixes

* remove

* update

* fixes

* linter

* fix test

* move buffers pkg out of writers pkg

* rename

* [refactor] - move buffer pool logic into own pkg (#2828)

* move buffer pool logic into own pkg

* fix test

* fix test

* whoops

* [feat] - additional buffer pool (#2829)

* move buffer pool logic into own pkg

* move

* fix test

* fix test

* fix test

* remove

* fix test

* whoops

* revert

* fix
2024-05-16 14:38:36 -07:00

104 lines
3.0 KiB
Go

// Package bufferwriter provides a contentWriter implementation using a shared buffer pool for memory management.
package bufferwriter
import (
"fmt"
"io"
"time"
"github.com/trufflesecurity/trufflehog/v3/pkg/buffers/buffer"
"github.com/trufflesecurity/trufflehog/v3/pkg/buffers/pool"
)
type metrics struct{}
func (metrics) recordDataProcessed(size int64, dur time.Duration) {
writeSize.Observe(float64(size))
totalWriteDuration.Add(float64(dur.Microseconds()))
}
const defaultBufferSize = 1 << 12 // 4KB
func init() { bufferPool = pool.NewBufferPool(defaultBufferSize) }
// bufferPool is the shared Buffer pool used by all BufferedFileWriters.
// This allows for efficient reuse of buffers across multiple writers.
var bufferPool *pool.Pool
// state represents the current mode of buffer.
type state uint8
const (
// writeOnly indicates the buffer is in write-only mode.
writeOnly state = iota
// readOnly indicates the buffer has been closed and is in read-only mode.
readOnly
)
// BufferWriter implements contentWriter, using a shared buffer pool for memory management.
type BufferWriter struct {
buf *buffer.Buffer // The current buffer in use.
bufPool *pool.Pool // The buffer pool used to manage the buffer.
size int // The total size of the content written to the buffer.
state state // The current state of the buffer.
metrics metrics
}
// New creates a new instance of BufferWriter.
func New() *BufferWriter {
return &BufferWriter{state: writeOnly, bufPool: bufferPool}
}
// Write delegates the writing operation to the underlying bytes.Buffer.
func (b *BufferWriter) Write(data []byte) (int, error) {
if b.state != writeOnly {
return 0, fmt.Errorf("buffer must be in write-only mode to write data; current state: %d", b.state)
}
if b.buf == nil {
b.buf = b.bufPool.Get()
if b.buf == nil {
b.buf = buffer.NewBuffer()
}
}
size := len(data)
b.size += size
start := time.Now()
defer func(start time.Time) {
b.metrics.recordDataProcessed(int64(size), time.Since(start))
}(start)
return b.buf.Write(data)
}
// ReadCloser provides a read-closer for the buffer's content.
// It wraps the buffer's content in a NopCloser to provide a ReadCloser without additional closing behavior,
// as closing a bytes.Buffer is a no-op.
func (b *BufferWriter) ReadCloser() (io.ReadCloser, error) {
if b.state != readOnly {
return nil, fmt.Errorf("buffer is in read-only mode")
}
if b.buf == nil {
return nil, fmt.Errorf("writer buffer is nil")
}
return buffer.ReadCloser(b.buf.Bytes(), func() { b.bufPool.Put(b.buf) }), nil
}
// CloseForWriting is a no-op for buffer, as there is no resource cleanup needed for bytes.Buffer.
func (b *BufferWriter) CloseForWriting() error {
b.state = readOnly
return nil
}
// String returns the buffer's content as a string.
func (b *BufferWriter) String() (string, error) {
if b.buf == nil {
return "", fmt.Errorf("buffer is nil")
}
return b.buf.String(), nil
}
// Len returns the length of the buffer's content.
func (b *BufferWriter) Len() int { return b.size }