fix: skip consecutive invalid bytes and file size validation

Author: sundanc

src/mmap.rs

@@ -11,9 +11,31 @@ pub struct MmapParser {
     mmap: Mmap,
 }
 
+const MAX_MMAP_SIZE: u64 = 16 * 1024 * 1024 * 1024;
+
 impl MmapParser {
     pub fn open<P: AsRef<Path>>(path: P) -> io::Result<Self> {
-        let file = File::open(path)?;
+        let file = File::open(&path)?;
+        let metadata = file.metadata()?;
+
+        if metadata.len() > MAX_MMAP_SIZE {
+            return Err(io::Error::new(
+                io::ErrorKind::InvalidData,
+                format!(
+                    "File too large for mmap: {} bytes (max {})",
+                    metadata.len(),
+                    MAX_MMAP_SIZE
+                ),
+            ));
+        }
+
+        if metadata.len() == 0 {
+            return Err(io::Error::new(
+                io::ErrorKind::InvalidData,
+                "Cannot mmap empty file",
+            ));
+        }
+
         let mmap = unsafe { Mmap::map(&file)? };
         Ok(Self { mmap })
     }

src/simd.rs

@@ -1854,7 +1854,16 @@ pub fn validate_message_stream_simd(data: &[u8], max_errors: usize) -> Validatio
             if result.error_offsets.len() >= max_errors {
                 break;
             }
-            offset += 1;
+            if msg_len == 0 {
+                let skip = data[offset..]
+                    .iter()
+                    .take_while(|&&b| b == 0)
+                    .count()
+                    .max(1);
+                offset += skip;
+            } else {
+                offset += 1;
+            }
             continue;
         }