patchwork

package doc

import (
	"crypto/sha256"
	"encoding/hex"
	"strings"

	"golang.org/x/text/unicode/norm"
)

// Normalize returns the text Patchwork stores: no BOM, LF line endings, NFC.
// Editors and upload tools change these freely, and none of them is a
// revision.
func Normalize(raw []byte) string {
	s := string(raw)
	s = strings.TrimPrefix(s, "\xef\xbb\xbf")
	s = strings.ReplaceAll(s, "\r\n", "\n")
	s = strings.ReplaceAll(s, "\r", "\n")
	return norm.NFC.String(s)
}

// hashText hashes text with trailing whitespace removed from every line and
// trailing blank lines dropped, so re-saving a file never looks like an edit.
func hashText(s string) string {
	lines := strings.Split(s, "\n")
	for i, l := range lines {
		lines[i] = strings.TrimRight(l, " \t")
	}
	sum := sha256.Sum256([]byte(strings.TrimRight(strings.Join(lines, "\n"), "\n")))
	return hex.EncodeToString(sum[:])
}