From fc973a3bb934de7fe6001be7b6c39714e7b5470d Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Daniel=20Ekl=C3=B6f?= <daniel@ekloef.se>
Date: Sat, 22 Jul 2023 11:21:12 +0200
Subject: [PATCH 1/3] selection: send_clipboard_or_primary(): handle selection
 text being NULL

---
 selection.c | 4 +---
 1 file changed, 1 insertion(+), 3 deletions(-)

diff --git a/selection.c b/selection.c
index f6349d7f..d1a7ea28 100644
--- a/selection.c
+++ b/selection.c
@@ -1662,7 +1662,7 @@ send_clipboard_or_primary(struct seat *seat, int fd, const char *selection,
         return;
     }
 
-    size_t len = strlen(selection);
+    size_t len = selection != NULL ? strlen(selection) : 0;
     size_t async_idx = 0;
 
     switch (async_write(fd, selection, len, &async_idx)) {
@@ -1701,7 +1701,6 @@ send(void *data, struct wl_data_source *wl_data_source, const char *mime_type,
     struct seat *seat = data;
     const struct wl_clipboard *clipboard = &seat->clipboard;
 
-    xassert(clipboard->text != NULL);
     send_clipboard_or_primary(seat, fd, clipboard->text, "clipboard");
 }
 
@@ -1756,7 +1755,6 @@ primary_send(void *data,
     struct seat *seat = data;
     const struct wl_primary *primary = &seat->primary;
 
-    xassert(primary->text != NULL);
     send_clipboard_or_primary(seat, fd, primary->text, "primary");
 }
 

From b59fd7c388c8d59a08e7e30f07e4639d2fd5451f Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Daniel=20Ekl=C3=B6f?= <daniel@ekloef.se>
Date: Sat, 22 Jul 2023 11:21:41 +0200
Subject: [PATCH 2/3] vt: detect and ignore invalid UTF-8 sequences

This patch detects invalid codepoints in the UTF-8 EDxxxx range, and
the F4xxxxxx range.

Note that we still allow the E0xxxx and F0xxxxxx ranges. These
contains overlong encodings. We allow them, because they still decode
into correct UTF-32.

Closes #1423
---
 vt.c | 21 +++++++++++++++++++++
 1 file changed, 21 insertions(+)

diff --git a/vt.c b/vt.c
index 51b69c7e..772bd41f 100644
--- a/vt.c
+++ b/vt.c
@@ -913,6 +913,16 @@ action_utf8_33(struct terminal *term, uint8_t c)
 {
     // wc = ((utf8[0] & 0xf) << 12) | ((utf8[1] & 0x3f) << 6) | (utf8[2] & 0x3f)
     term->vt.utf8 |= c & 0x3f;
+
+    const char32_t utf32 = term->vt.utf8;
+    if (unlikely(utf32 >= 0xd800 && utf32 <= 0xdfff)) {
+        /* Invalid sequence - invalid UTF-16 surrogate halves */
+        return;
+    }
+
+    /* Note: the E0 range contains overlong encodings. We don’t try to
+       detect, as they’ll still decode to valid UTF-32. */
+
     action_utf8_print(term, term->vt.utf8);
 }
 
@@ -942,6 +952,17 @@ action_utf8_44(struct terminal *term, uint8_t c)
 {
     // wc = ((utf8[0] & 7) << 18) | ((utf8[1] & 0x3f) << 12) | ((utf8[2] & 0x3f) << 6) | (utf8[3] & 0x3f);
     term->vt.utf8 |= c & 0x3f;
+
+    const char32_t utf32 = term->vt.utf8;
+
+    if (unlikely(utf32 > 0x10FFFF)) {
+        /* Invalid UTF-8 */
+        return;
+    }
+
+    /* Note: the F0 range contains overlong encodings. We don’t try to
+       detect, as they’ll still decode to valid UTF-32. */
+
     action_utf8_print(term, term->vt.utf8);
 }
 

From 8223b4b76cb6ab0d4320859b2497dc222c9762bb Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Daniel=20Ekl=C3=B6f?= <daniel@ekloef.se>
Date: Sat, 22 Jul 2023 11:23:22 +0200
Subject: [PATCH 3/3] changelog: ignore invalid UTF-8 in input

---
 CHANGELOG.md | 6 ++++++
 1 file changed, 6 insertions(+)

diff --git a/CHANGELOG.md b/CHANGELOG.md
index 84a8aef4..ed0990eb 100644
--- a/CHANGELOG.md
+++ b/CHANGELOG.md
@@ -50,6 +50,12 @@
 ### Deprecated
 ### Removed
 ### Fixed
+
+* Crash when copying text that contains invalid UTF-8 ([#1423][1423]).
+
+[1423]: https://codeberg.org/dnkl/foot/issues/1423
+
+
 ### Security
 ### Contributors