Fix possible out of bound array access (haoel#254)

zhao-gang · qinyafee · commit 58d35ff0005c · 2022-01-28T15:05:19.000+08:00
Should check array size before accessing the second to fourth bytes of
utf8 as there might be not enough data left in the array.
diff --git a/algorithms/cpp/UTF8Validation/UTF8Validation.cpp b/algorithms/cpp/UTF8Validation/UTF8Validation.cpp
@@ -67,6 +67,10 @@ class Solution {
                 return false;
             }
             
+            // invalid utf-8 as it doesn't have enough 10xxxxxx
+            if (i + len > data.size()) {
+                return false;
+            }
             
             for (int j=i+1; j < i+len; j++) { //checking 10xxxxxx
                 if ( (data[j] & 0xC0) != 0x80 ) {
@@ -75,11 +79,6 @@ class Solution {
             }
             
             i += len ;
-            
-            if (i > data.size()) {
-                return false;
-            }
-            
         }
         return true;
     }

Original file line number	Diff line number	Diff line change
`@@ -67,6 +67,10 @@ class Solution {`
`67`	`67`	`return false;`
`68`	`68`	`}`
`69`	`69`
	`70`	`+ // invalid utf-8 as it doesn't have enough 10xxxxxx`
	`71`	`+ if (i + len > data.size()) {`
	`72`	`+ return false;`
	`73`	`+ }`
`70`	`74`
`71`	`75`	`for (int j=i+1; j < i+len; j++) { //checking 10xxxxxx`
`72`	`76`	`if ( (data[j] & 0xC0) != 0x80 ) {`
`@@ -75,11 +79,6 @@ class Solution {`
`75`	`79`	`}`
`76`	`80`
`77`	`81`	`i += len ;`
`78`		`-`
`79`		`- if (i > data.size()) {`
`80`		`- return false;`
`81`		`- }`
`82`		`-`
`83`	`82`	`}`
`84`	`83`	`return true;`
`85`	`84`	`}`