From 5f825db8cf4265eada32fe625781cdb75193e6f7 Mon Sep 17 00:00:00 2001
From: Gabriel Vasile <gabriel.vasile@email.com>
Date: Tue, 13 Aug 2024 01:56:10 +0900
Subject: [PATCH] use a pool of buffers to alleviate memory allocs in csv;
 related to #553

When iterating over multiple files, csv detector allocated a new buffer
for each file. This change adds a pool of buffers that can be reused
between detections. The same pool is shared between csv and tsv
detectors.
---
 internal/magic/text_csv.go | 22 +++++++++++++++++++++-
 1 file changed, 21 insertions(+), 1 deletion(-)

diff --git a/internal/magic/text_csv.go b/internal/magic/text_csv.go
index af256438..6083ba8c 100644
--- a/internal/magic/text_csv.go
+++ b/internal/magic/text_csv.go
@@ -1,12 +1,28 @@
 package magic
 
 import (
+	"bufio"
 	"bytes"
 	"encoding/csv"
 	"errors"
 	"io"
+	"sync"
 )
 
+// A bufio.Reader pool to alleviate problems with memory allocations.
+var readerPool = sync.Pool{
+	New: func() any {
+		// Initiate with empty source reader.
+		return bufio.NewReader(nil)
+	},
+}
+
+func newReader(r io.Reader) *bufio.Reader {
+	br := readerPool.Get().(*bufio.Reader)
+	br.Reset(r)
+	return br
+}
+
 // Csv matches a comma-separated values file.
 func Csv(raw []byte, limit uint32) bool {
 	return sv(raw, ',', limit)
@@ -18,7 +34,11 @@ func Tsv(raw []byte, limit uint32) bool {
 }
 
 func sv(in []byte, comma rune, limit uint32) bool {
-	r := csv.NewReader(bytes.NewReader(dropLastLine(in, limit)))
+	in = dropLastLine(in, limit)
+
+	br := newReader(bytes.NewReader(in))
+	defer readerPool.Put(br)
+	r := csv.NewReader(br)
 	r.Comma = comma
 	r.ReuseRecord = true
 	r.LazyQuotes = true