Add test that validates fingerprint.StartsWith when read from files (#…

…145)

operator/builtin/input/file/fingerprint.go

@@ -25,6 +25,8 @@ const defaultFingerprintSize = 1000 // bytes
 const minFingerprintSize = 16       // bytes
 
 // Fingerprint is used to identify a file
+// A file's fingerprint is the first N bytes of the file,
+// where N is the fingerprintSize on the file_input operator
 type Fingerprint struct {
 	FirstBytes []byte
 }
@@ -56,6 +58,10 @@ func (f Fingerprint) Copy() *Fingerprint {
 
 // StartsWith returns true if the fingerprints are the same
 // or if the new fingerprint starts with the old one
+// This is important functionality for tracking new files,
+// since their initial size is typically less than that of
+// a fingerprint. As the file grows, its fingerprint is updated
+// until it reaches a maximum size, as configured on the operator
 func (f Fingerprint) StartsWith(old *Fingerprint) bool {
 	l0 := len(old.FirstBytes)
 	if l0 == 0 {

operator/builtin/input/file/fingerprint_test.go

@@ -16,6 +16,8 @@ package file
 
 import (
 	"fmt"
+	"io/ioutil"
+	"math/rand"
 	"strings"
 	"testing"
 
@@ -212,4 +214,57 @@ func TestFingerprintStartsWith(t *testing.T) {
 	}
 }
 
+// Generates a file filled with many random bytes, then
+// writes the same bytes to a second file, one byte at a time.
+// Validates, after each byte is written, that fingerprint
+// matching would successfully associate the two files.
+// The static file can be thought of as the present state of
+// the file, while each iteration of the growing file represents
+// a possible state of the same file at a previous time.
+func TestFingerprintStartsWith_FromFile(t *testing.T) {
+	r := rand.New(rand.NewSource(112358))
+
+	operator, _, tempDir := newTestFileOperator(t, nil, nil)
+	operator.fingerprintSize *= 10
+
+	fileLength := 12 * operator.fingerprintSize
+
+	// Make a []byte we can write one at a time
+	content := make([]byte, fileLength)
+	r.Read(content) // Fill slice with random bytes
+
+	// Overwrite some bytes with \n to ensure
+	// we are testing a file with multiple lines
+	newlineMask := make([]byte, fileLength)
+	r.Read(newlineMask) // Fill slice with random bytes
+	for i, b := range newlineMask {
+		if b == 0 && i != 0 { // 1/256 chance, but never first byte
+			content[i] = byte('\n')
+		}
+	}
+
+	fullFile, err := ioutil.TempFile(tempDir, "")
+	require.NoError(t, err)
+	_, err = fullFile.Write(content)
+	require.NoError(t, err)
+
+	fff, err := operator.NewFingerprint(fullFile)
+	require.NoError(t, err)
+
+	partialFile, err := ioutil.TempFile(tempDir, "")
+	require.NoError(t, err)
+
+	// Write one byte at a time and validate that updated
+	// full fingerprint still starts with partial
+	for i := range content {
+		_, err = partialFile.Write(content[i:i])
+		require.NoError(t, err)
+
+		pff, err := operator.NewFingerprint(fullFile)
+		require.NoError(t, err)
+
+		require.True(t, fff.StartsWith(pff))
+	}
+}
+
 // TODO TestConfig (config_test.go) - sets defaults, errors appropriately, etc