From 87c6dc267d48f9fd30dd458180a2ed5e75af9399 Mon Sep 17 00:00:00 2001
From: Wim Brand <fornax@fornaxian.com>
Date: Fri, 18 May 2018 22:52:02 +0200
Subject: [PATCH] Add build script and remove an array index operation

---
 build.sh |  3 +++
 main.go  | 40 +++++++++++++++++++++++++++-------------
 2 files changed, 30 insertions(+), 13 deletions(-)
 create mode 100755 build.sh

diff --git a/build.sh b/build.sh
new file mode 100755
index 0000000..e5462ba
--- /dev/null
+++ b/build.sh
@@ -0,0 +1,3 @@
+#!/bin/sh
+
+go build -o rapidgrep -ldflags="-s -w" main.go
diff --git a/main.go b/main.go
index 6b6c1fc..1ee0e5f 100644
--- a/main.go
+++ b/main.go
@@ -6,12 +6,17 @@ import (
 	"io"
 	"os"
 	"runtime"
+	"runtime/pprof"
 	"sync"
 )
 
 const lf = byte('\n')
 
 func main() {
+	f, _ := os.Create("cprof")
+	pprof.StartCPUProfile(f)
+	defer pprof.StopCPUProfile()
+
 	if len(os.Args) != 2 {
 		print("One argument required\n")
 		os.Exit(1)
@@ -68,21 +73,28 @@ func main() {
 func scannerThread(workchannel chan []byte, needle []byte, wg *sync.WaitGroup) {
 	var batch []byte
 	var ok bool
-	var start, end int
-	var linelen int
-	var i int
-	defer wg.Done()
+	var i, linelen, start, end int
+
+	defer wg.Done() // Sync up the goroutines when done
+
 	for {
 		batch, ok = <-workchannel
 		if !ok {
 			return // channel closed. we're done
 		}
 
-		// This loop is for every result found, when there are no more results it stops
-		for i = bytes.Index(batch, needle); i != -1; i = bytes.Index(batch, needle) {
-			start, end = i, i
+		linelen = len(batch)
+
+		// This loop is for every result found, when there are no more results
+		// it stops. When it runs for the first time the first index function is
+		// executed, which indexes the entire batch. In the following iterations
+		// the second index function is used, which begins searching where the
+		// last result ended so it doesn't get found twice.
+		for i = bytes.Index(batch, needle); i != -1; i = bytes.Index(batch[end:], needle) {
+			start, end = i+end, i+end
 			// needle was found, but where?
-			for { // find the start
+
+			for { // find the start (line feed of the line before it, or index 0)
 				if batch[start] == lf {
 					start++ // the line feed is from the previous line, so skip it
 					break
@@ -92,7 +104,7 @@ func scannerThread(workchannel chan []byte, needle []byte, wg *sync.WaitGroup) {
 				start--
 			}
 
-			for { // find the end
+			for { // find the end (line feed at the end of the line)
 				if batch[end] == lf {
 					end++ // include the line feed in the line
 					// https://stackoverflow.com/questions/26857582/in-a-go-slice-why-does-slohi-end-at-element-hi-1
@@ -103,12 +115,14 @@ func scannerThread(workchannel chan []byte, needle []byte, wg *sync.WaitGroup) {
 				end++
 			}
 
+			// Print the result. Note that stdout is not necessarily
+			// concurrency-safe, so in a real application this would have to be
+			// passed through a channel.
 			os.Stdout.Write(batch[start:end])
 
-			// Chop all of the bytes before the result off so it doesn't get
-			// searched again
-			batch = batch[end:]
-			linelen = len(batch)
+			// This is to keep track of where the end of the byte array is so we
+			// can avoid index out of bounds panics
+			linelen = linelen - end
 		}
 	}
 }