fix(bonfire): replace invalid UTF-8 before the control scan in Sanitize (IN-08, quick-261028-rqd)

modules/bonfire/README.md

@@ -140,7 +140,7 @@ if catalog.Has("blog:import") {
 | `bonfire.WithHint` | Wraps an error in a `bonfire.HintError`; `{bin}` in the Try text becomes `bin/<name>` or `summer`. |
 | `bonfire.ErrReported` | Marks an error whose details the command already printed. |
 | `bonfire.Reported` | Wraps an error so it matches `bonfire.ErrReported`: exit code 1, or the code of `bonfire.WithExitCode`, and no error block. |
-| `bonfire.Sanitize` | Removes control characters other than tab (line breaks become spaces), so untrusted text cannot move the cursor or retitle the terminal; error blocks, process views, failure lines, tables and diary's console use it. |
+| `bonfire.Sanitize` | Replaces invalid UTF-8 with U+FFFD and removes control characters other than tab (line breaks become spaces), so untrusted text, including a raw 8-bit C1 byte, cannot move the cursor or retitle the terminal; error blocks, process views, failure lines, tables and diary's console use it. |
 | `bonfire.WithExitCode` | Makes an error carry the exit code `bonfire.Execute` returns for it (1 to 255; other codes give 1). |
 | `bonfire.Listing` | The JSON catalog of `list --format=json`: `Application` (`bonfire.ApplicationInfo`), `GlobalOptions` and `Commands`. |
 | `bonfire.ApplicationInfo` | Name, version and framework version of a binary in a `bonfire.Listing`. |

modules/bonfire/errors.go

@@ -7,6 +7,7 @@ import (
 	"path/filepath"
 	"strings"
 	"unicode"
+	"unicode/utf8"
 
 	"git.golem15.com/golem15/summercms/internal/argmask"
 	"git.golem15.com/golem15/summercms/modules/sunscreen"
@@ -102,18 +103,23 @@ func Reported(err error) error {
 // text, names an administrator typed) then cannot move the cursor, clear
 // the screen or set the window title. Error blocks, process views, failure
 // lines and tables pass their text through it, and so does diary's console
-// channel. A clean string is returned unchanged.
+// channel. Invalid UTF-8 becomes U+FFFD first, so a raw 8-bit C1 byte (such
+// as 0x9b, CSI) cannot reach a terminal that honours it, and the result is
+// always valid UTF-8. A clean, valid string is returned unchanged.
 func Sanitize(s string) string {
-	clean := true
-	for _, r := range s {
-		if r != '\t' && unicode.IsControl(r) {
-			clean = false
-			break
+	clean := utf8.ValidString(s)
+	if clean {
+		for _, r := range s {
+			if r != '\t' && unicode.IsControl(r) {
+				clean = false
+				break
+			}
 		}
 	}
 	if clean {
 		return s
 	}
+	s = strings.ToValidUTF8(s, "\uFFFD")
 	var b strings.Builder
 	for _, r := range s {
 		switch {

modules/bonfire/errors_test.go

@@ -9,6 +9,7 @@ import (
 	"path/filepath"
 	"strings"
 	"testing"
+	"unicode/utf8"
 )
 
 // TestExitCodes: Execute returns 0 on success, 1 on a failure and 2 on an
@@ -323,9 +324,21 @@ func TestSanitize(t *testing.T) {
 		"a\x1b]0;title\x07b":             "a]0;titleb",
 		"nul\x00 and del\x7f and \x01":   "nul and del and ",
 		"boom\x1b[2Jclear":               "boom[2Jclear",
+		// IN-08: invalid UTF-8 becomes U+FFFD, so a raw 8-bit C1 byte
+		// such as 0x9b (CSI) never reaches the terminal.
+		"a\x9b31mb": "a\uFFFD31mb",
+		"\x9b":      "\uFFFD",
+		"\xffok":    "\uFFFDok",
 	} {
 		if got := Sanitize(in); got != want {
 			t.Errorf("Sanitize(%q) = %q, want %q", in, got, want)
 		}
+		if got := Sanitize(in); !utf8.ValidString(got) {
+			t.Errorf("Sanitize(%q) = %q is not valid UTF-8", in, got)
+		}
+	}
+	clean := "plain ok"
+	if got := Sanitize(clean); got != clean {
+		t.Errorf("Sanitize(%q) = %q, want it unchanged", clean, got)
 	}
 }