Changeset 33724

Timestamp:

2019-11-27T23:41:30+13:00 (4 years ago)

Author:

ak19

Message:

1. A bugfix to Base64.decode(String s) to handle null strings returned from Base64.decode(byte[], ...) variant. 2. Adding a copy of the stringToHex function debugUnicodeString() to gli code.

Location:

main/trunk/gli/src/org/greenstone/gatherer

Files:

• feedback/Base64.java (modified) (1 diff)
• util/Utility.java (modified) (1 diff)

main/trunk/gli/src/org/greenstone/gatherer/feedback/Base64.java

@@ -720 +720 @@
     {   
         byte[] bytes = s.getBytes();
+        byte[] origBytes = bytes;
         bytes = decode( bytes, 0, bytes.length );
-        
+        
+        // if something went wrong base64 decoding the string, just return the original bytes
+        if(bytes == null) {
+            return origBytes;
+        }
+        
         // Check to see if it's gzip-compressed
         // GZIP Magic Two-Byte Number: 0x8b1f (35615)

main/trunk/gli/src/org/greenstone/gatherer/util/Utility.java

@@ -95 +95 @@
     }
 
+    // Copied from GS3 main java code at GSDL3SRCHOME\src\java\org\greenstone/util\Misc.java
+    // Debugging function to print a string's non-basic chars in hex, so stringToHex on all non-basic and non-printable ASCII
+    // Dr Bainbridge said that printing anything with charCode over 128 in hex is okay, but I'd already made extra allowances for non-printable ASCII
+    // Based on https://stackoverflow.com/questions/923863/converting-a-string-to-hexadecimal-in-java
+    public static String debugUnicodeString(String str) {
+      String result = "";
+      for(int i = 0; i < str.length(); i++) {
+            int charCode = str.codePointAt(i); // unicode codepoint / ASCII code
+            
+            // ASCII table: https://cdn.sparkfun.com/assets/home_page_posts/2/1/2/1/ascii_table_black.png
+            // If the unicode character code pt is less than the ASCII code for space and greater than for tilda, let's display the char in hex (x0000 format)
+            if((charCode >= 20 && charCode <= 126) || charCode == 9 || charCode == 10 || charCode == 13) { // space, tilda, TAB, LF, CR are printable, leave them in for XML element printing
+                result += str.charAt(i);
+            } else {
+                result += "x{" + String.format("%04x", charCode) + "}"; // looks like: x{4-char-codepoint}
+            }
+      }
+      
+      return result;
+    }
+    
     /** 
      * Handy function to display the list of calling functions by