From 34c99245b33a3fe23a132ff0df18d64d251a848c Mon Sep 17 00:00:00 2001
From: Bryce Kwon <bryce@brycekwon.com>
Date: Fri, 14 Aug 2026 10:58:51 -1000
Subject: Treat text blobs with stray nuls as binary

---
 source/ui-blame.c | 14 +++++++++++++-
 source/ui-blob.c  | 19 ++++++++++++++++---
 source/ui-tree.c  |  5 ++++-
 3 files changed, 33 insertions(+), 5 deletions(-)

(limited to 'source')

diff --git a/source/ui-blame.c b/source/ui-blame.c
index 80512a0..a7010d0 100644
--- a/source/ui-blame.c
+++ b/source/ui-blame.c
@@ -307,7 +307,19 @@ static void print_blame_page(const struct object_id *oid, const char *path,
 	cgit_tree_link("tree", NULL, NULL, ctx.qry.head, rev, path);
 	html(")\n");
 
-	if (buffer_is_binary(buf, size)) {
+	// A NUL past the window buffer_is_binary sniffs would end html_txt
+	// early while the hash and line number columns still cover the whole
+	// file, so a blob holding one anywhere is treated as binary too.
+	if (buffer_is_binary(buf, size) || memchr(buf, 0, size)) {
+		struct blame_entry *ent = sb.ent, *next;
+
+		// The scoreboard is normally consumed by the column passes,
+		// so this early exit has to release it itself.
+		for (; ent; ent = next) {
+			next = ent->next;
+			free(ent);
+		}
+		free((void *)sb.final_buf);
 		html("<div class='error'>blob is binary.</div>");
 		goto cleanup;
 	}
diff --git a/source/ui-blob.c b/source/ui-blob.c
index beb968b..db1d0c1 100644
--- a/source/ui-blob.c
+++ b/source/ui-blob.c
@@ -126,10 +126,23 @@ int cgit_print_file(char *path, const char *head, int file_only, int html_escape
 	// html_txt wants a terminated string, and git leaves a spare byte
 	// past every object it reads, so this write stays in the allocation.
 	buf[size] = '\0';
-	if (html_escape)
-		html_txt(buf);
-	else
+	if (html_escape) {
+		// html_txt stops at a NUL, so a blob holding one is written
+		// segment by segment with a replacement character standing in
+		// for each NUL byte, rather than silently cut short.
+		const char *p = buf, *end = buf + size;
+
+		while (p < end) {
+			html_txt(p);
+			p += strlen(p);
+			while (p < end && !*p) {
+				html("\xef\xbf\xbd");
+				p++;
+			}
+		}
+	} else {
 		html_raw(buf, size);
+	}
 	free(buf);
 	return 0;
 }
diff --git a/source/ui-tree.c b/source/ui-tree.c
index 7d24d53..7df7375 100644
--- a/source/ui-tree.c
+++ b/source/ui-tree.c
@@ -191,7 +191,10 @@ static bool print_object(const struct object_id *oid, const char *path,
 			"Error reading object %s", oid_to_hex(oid));
 		return false;
 	}
-	is_binary = buffer_is_binary(buf, size);
+	// buffer_is_binary only sniffs the front of the blob, and a NUL past
+	// that window would end the escaped text render early while the line
+	// number column still counts the whole file, so check the rest too.
+	is_binary = buffer_is_binary(buf, size) || memchr(buf, 0, size);
 
 	cgit_set_title_from_path(path);
 
-- 
cgit v2.8.0