From cf1d1e4f0030c28caaca9a81776c7c69f695d04e Mon Sep 17 00:00:00 2001
From: Chris North <chris@cnorth.com>
Date: Wed, 21 Feb 2024 11:01:55 -0800
Subject: [PATCH] fix: change text detect to check first and last 512 bytes
 (#2310)

## Description

Alters text detection logic to read the first and last 512 bytes.

Tested with 5 files:
- [NVIDIA
installer](https://us.download.nvidia.com/XFree86/Linux-x86_64/535.154.05/NVIDIA-Linux-x86_64-535.154.05.run)
    Detected as application type when reading last 512.
- 3 4k size files of junk text with a ZARF_CONST replacement, in
straight text, yaml, and json
    All 3 detected as text/plain, ZARF_CONST was replaced.
- 1 small 100 byte file with a ZARF_CONST replacement.
   Was still detected as text and ZARF_CONST was replaced.

Existing unit tests succeeded.

## Related Issue

Fixes #2308
<!-- or -->
Relates to #

## Type of change

- [x] Bug fix (non-breaking change which fixes an issue)
- [ ] New feature (non-breaking change which adds functionality)
- [ ] Other (security config, docs update, etc)

## Checklist before merging

- [x] Test, docs, adr added or updated as needed
- [x] [Contributor Guide
Steps](https://github.com/defenseunicorns/zarf/blob/main/CONTRIBUTING.md#developer-workflow)
followed

---------

Co-authored-by: Wayne Starr <Racer159@users.noreply.github.com>
---
 src/pkg/utils/io.go | 41 ++++++++++++++++++++++++++++++-----------
 1 file changed, 30 insertions(+), 11 deletions(-)

diff --git a/src/pkg/utils/io.go b/src/pkg/utils/io.go
index bb6ae79db2..f69599802e 100755
--- a/src/pkg/utils/io.go
+++ b/src/pkg/utils/io.go
@@ -475,22 +475,41 @@ func IsTextFile(path string) (bool, error) {
 	}
 	defer f.Close() // Make sure to close the file when we're done
 
-	// Read the first 512 bytes of the file
-	data := make([]byte, 512)
-	n, err := f.Read(data)
-	if err != nil && err != io.EOF {
+	// Get file stat
+	stat, err := f.Stat()
+	if err != nil {
 		return false, err
 	}
 
-	// Use http.DetectContentType to determine the MIME type of the file
-	mimeType := http.DetectContentType(data[:n])
+	// Clip offset to minimum of 0
+	lastOffset := max(0, stat.Size()-512)
+
+	// Take two passes checking front and back of the file
+	offsetPasses := []int64{0, lastOffset}
+	isTextCheck := []bool{false, false}
+	for idx, offset := range offsetPasses {
+		// Create 512 byte buffer
+		data := make([]byte, 512)
+
+		n, err := f.ReadAt(data, offset)
+		if err != nil && err != io.EOF {
+			return false, err
+		}
 
-	// Check if the MIME type indicates that the file is text
-	hasText := strings.HasPrefix(mimeType, "text/")
-	hasJSON := strings.Contains(mimeType, "json")
-	hasXML := strings.Contains(mimeType, "xml")
+		// Use http.DetectContentType to determine the MIME type of the file
+		mimeType := http.DetectContentType(data[:n])
+
+		// Check if the MIME type indicates that the file is text
+		hasText := strings.HasPrefix(mimeType, "text/")
+		hasJSON := strings.Contains(mimeType, "json")
+		hasXML := strings.Contains(mimeType, "xml")
+
+		// Save result
+		isTextCheck[idx] = hasText || hasJSON || hasXML
+	}
 
-	return hasText || hasJSON || hasXML, nil
+	// Returns true if both front and back show they are text
+	return isTextCheck[0] && isTextCheck[1], nil
 }
 
 // IsTrashBin checks if the given directory path corresponds to an operating system's trash bin.