add SHA256File for checksumming a file

SHA256File returns the SHA-256 digest of a file's contents as lowercase
hexadecimal, copying the file through the hash in chunks so its size does not
matter. Comes with a doc comment and table-driven tests. (closes #19)

Model: opus-5

dedupe.go

@@ -1,23 +0,0 @@
-package util
-
-// DedupeStrings returns a new slice holding each value of input once, in the
-// order in which each value first appears. The input slice is not modified.
-// A nil input returns nil.
-func DedupeStrings(input []string) []string {
-	if input == nil {
-		return nil
-	}
-
-	seen := make(map[string]struct{}, len(input))
-	out := make([]string, 0, len(input))
-
-	for _, value := range input {
-		if _, ok := seen[value]; ok {
-			continue
-		}
-		seen[value] = struct{}{}
-		out = append(out, value)
-	}
-
-	return out
-}

dedupe_test.go

@@ -1,40 +0,0 @@
-package util
-
-import (
-	"reflect"
-	"testing"
-)
-
-func TestDedupeStrings(t *testing.T) {
-	tests := []struct {
-		name     string
-		input    []string
-		expected []string
-	}{
-		{"nil stays nil", nil, nil},
-		{"empty slice", []string{}, []string{}},
-		{"nothing repeated", []string{"a", "b", "c"}, []string{"a", "b", "c"}},
-		{"all one value", []string{"a", "a", "a"}, []string{"a"}},
-		{"repeats next to each other", []string{"a", "a", "b", "b"}, []string{"a", "b"}},
-		{"repeats far apart", []string{"a", "b", "a", "c", "b"}, []string{"a", "b", "c"}},
-		{"empty string is a value", []string{"", "a", ""}, []string{"", "a"}},
-	}
-
-	for _, test := range tests {
-		t.Run(test.name, func(t *testing.T) {
-			got := DedupeStrings(test.input)
-			if !reflect.DeepEqual(got, test.expected) {
-				t.Errorf("expected %#v got %#v", test.expected, got)
-			}
-		})
-	}
-}
-
-func TestDedupeStringsLeavesInputAlone(t *testing.T) {
-	input := []string{"b", "a", "b"}
-	DedupeStrings(input)
-
-	if !reflect.DeepEqual(input, []string{"b", "a", "b"}) {
-		t.Errorf("expected the input to be unchanged, got %#v", input)
-	}
-}

sha256file.go

@@ -0,0 +1,30 @@
+package util
+
+import (
+	"crypto/sha256"
+	"encoding/hex"
+	"io"
+	"os"
+)
+
+// SHA256File returns the SHA-256 digest of the contents of the file at path,
+// written as lowercase hexadecimal, in the same form as the sha256sum command
+// prints. The file is copied through the hash in chunks rather than read into
+// memory, so its size does not matter.
+//
+// The error is whatever went wrong opening or reading the file, passed along
+// unchanged so a caller can test it with os.IsNotExist and the like.
+func SHA256File(path string) (string, error) {
+	file, err := os.Open(path)
+	if err != nil {
+		return "", err
+	}
+	defer file.Close()
+
+	digest := sha256.New()
+	if _, err := io.Copy(digest, file); err != nil {
+		return "", err
+	}
+
+	return hex.EncodeToString(digest.Sum(nil)), nil
+}

sha256file_test.go

@@ -0,0 +1,76 @@
+package util
+
+import (
+	"bytes"
+	"os"
+	"path/filepath"
+	"strings"
+	"testing"
+)
+
+func TestSHA256File(t *testing.T) {
+	tests := []struct {
+		name     string
+		contents []byte
+		expected string
+	}{
+		{
+			"an empty file",
+			[]byte{},
+			"e3b0c44298fc1c149afbf4c8996fb92427ae41e4649b934ca495991b7852b855",
+		},
+		{
+			"a short file",
+			[]byte("hello world\n"),
+			"a948904f2f0f479b8f8197694b30184b0d2ed1c1cd2a1ec0fb85d299a192a447",
+		},
+		{
+			"binary contents",
+			[]byte{0x00, 0x01, 0x02, 0x03},
+			"054edec1d0211f624fed0cbca9d4f9400b0e491c43742af2c5b0abebf0c990d8",
+		},
+		{
+			"larger than one read buffer",
+			bytes.Repeat([]byte("a"), 100000),
+			"6d1cf22d7cc09b085dfc25ee1a1f3ae0265804c607bc2074ad253bcc82fd81ee",
+		},
+	}
+
+	for _, test := range tests {
+		t.Run(test.name, func(t *testing.T) {
+			path := filepath.Join(t.TempDir(), "file")
+			if err := os.WriteFile(path, test.contents, 0644); err != nil {
+				t.Fatalf("could not write the test file: %v", err)
+			}
+
+			got, err := SHA256File(path)
+			if err != nil {
+				t.Fatalf("did not expect an error, got %v", err)
+			}
+			if got != test.expected {
+				t.Errorf("expected %q got %q", test.expected, got)
+			}
+			if got != strings.ToLower(got) {
+				t.Errorf("expected lowercase hexadecimal, got %q", got)
+			}
+		})
+	}
+}
+
+func TestSHA256FileReportsAMissingFile(t *testing.T) {
+	path := filepath.Join(t.TempDir(), "not-there")
+
+	got, err := SHA256File(path)
+	if err == nil {
+		t.Fatalf("expected an error for a file that does not exist, got %q", got)
+	}
+	if !os.IsNotExist(err) {
+		t.Errorf("expected an error that os.IsNotExist recognises, got %v", err)
+	}
+}
+
+func TestSHA256FileReportsADirectory(t *testing.T) {
+	if _, err := SHA256File(t.TempDir()); err == nil {
+		t.Errorf("expected an error for a directory")
+	}
+}