From 6e14400750c112c3459618b7ab822e5f6d032b92 Mon Sep 17 00:00:00 2001
From: Micah Snyder <micasnyd@cisco.com>
Date: Mon, 13 Nov 2023 17:37:42 -0500
Subject: [PATCH] Fix warning when scanning some HTML files

HTML files with <style> blocks containing non-utf8 sequences are causing
warnings when processing them to extract base64 encoded images.

To resolve this, we can use the to_string_lossy() method that may
allocate and sanitize a copy of the content if the non-utf8 characters
are encountered.

Resolves: https://github.com/Cisco-Talos/clamav/issues/1082
---
 libclamav_rust/src/css_image_extract.rs | 10 ++--------
 1 file changed, 2 insertions(+), 8 deletions(-)

diff --git a/libclamav_rust/src/css_image_extract.rs b/libclamav_rust/src/css_image_extract.rs
index 8abd5dbf52..9046357162 100644
--- a/libclamav_rust/src/css_image_extract.rs
+++ b/libclamav_rust/src/css_image_extract.rs
@@ -288,16 +288,10 @@ pub unsafe extern "C" fn new_css_image_extractor(
         return 0 as sys::css_image_extractor_t;
     } else {
         #[allow(unused_unsafe)]
-        match unsafe { CStr::from_ptr(file_bytes) }.to_str() {
-            Err(e) => {
-                warn!("{} is not valid unicode: {}", stringify!(file_bytes), e);
-                return 0 as sys::css_image_extractor_t;
-            }
-            Ok(s) => s,
-        }
+        unsafe { CStr::from_ptr(file_bytes) }.to_string_lossy()
     };
 
-    if let Ok(extractor) = CssImageExtractor::new(css_input) {
+    if let Ok(extractor) = CssImageExtractor::new(&css_input) {
         Box::into_raw(Box::new(extractor)) as sys::css_image_extractor_t
     } else {
         0 as sys::css_image_extractor_t