Changeset 33728

Timestamp:

2019-11-29T21:46:20+13:00 (4 years ago)

Author:

ak19

Message:

Introducing method that I've tested separately to decode a string that contains html hex entities back to unicode characters. Don't know if it's the most optimal solution, because it's my own code. Didn't know how to google for existing Java solutions, which surely must be out there.

File:

• main/trunk/gli/src/org/greenstone/gatherer/metadata/FilenameEncoding.java (modified) (3 diffs)

main/trunk/gli/src/org/greenstone/gatherer/metadata/FilenameEncoding.java

@@ -34 +34 @@
 import org.greenstone.gatherer.DebugStream;
 
+import java.util.regex.Matcher;
+import java.util.regex.Pattern;
+
+
+
 /** Static access class that contains many of the methods used to work with filename encodings. 
 * Works closely with classes FileNode, CollectionTreeNode, MetadataXMLFile, MetadataXMLFileManager
@@ -291 +296 @@
 
 //************************* GETTING THE URL ENCODING OF FILENAMES *********************************
+
+    /** 
+     * Given a String containing hexentities, will convert back into the unicode version of the String.
+     * e.g. A string like "02 Tēnā Koutou\.mp3" will be returned as "02 Tena Koutou\.mp3" with macrons on e and a
+     * I've tested this in a separate file that imports java.util.regex.Matcher and java.util.regex.Pattern
+     * and contains a copy of Utility.debugUnicodeString(String) with the following main function:
+        public static void main(String args[]) {
+            String str = "02 Tēnā Koutou\\.mp3"; // or more basic case: String str = "mmmmānnnnēpppp\\.txt";        
+            System.err.println("About to decode hex string: " + str);
+            String result = decodeStringContainingHexEntities(str);
+            System.err.println("Decoded hex string: " + result + " - debug unicode form: " + debugUnicodeString(result));
+        }
+    */
+    public static String decodeStringContainingHexEntities(String str) {
+        String result = "";
+        boolean done = false;       
+        Pattern hexPattern = Pattern.compile("(&#x[0-9a-zA-Z]{1,4}+;)");
+        Matcher matcher = hexPattern.matcher(str);
+        
+        int searchFromIndex = 0;
+        int endMatchIndex = -1;
+        
+        while(matcher.find(searchFromIndex)) {
+            String hexPart = matcher.group();
+            //System.err.println("Found hexpart match: " + hexPart);
+            
+            int startMatchIndex = matcher.start();
+            endMatchIndex = matcher.end();
+            result += str.substring(searchFromIndex, startMatchIndex);          
+            
+            String hexNumberStr = hexPart.substring(3, hexPart.length()-1); // lose the "&#x" prefix and the ";" suffix to get just the hex number portion of the match
+            // https://stackoverflow.com/questions/16625865/java-unicode-to-hex-string
+            // https://stackoverflow.com/questions/11194513/convert-hex-string-to-int
+            
+            //System.err.println("hexNumberStr so far: " + hexNumberStr);           
+            int tmpDigit = Integer.parseInt(hexNumberStr);
+            //System.err.println("As digit: " + tmpDigit);
+            hexNumberStr = String.format("%04d", tmpDigit); 
+            //System.err.println("2 hexNumberStr so far: " + hexNumberStr);
+            hexNumberStr = "0x" + hexNumberStr; // e.g "0xDDDD"
+            //int hexNumber = Integer.parseInt(hexNumberStr);
+            int hexNumber = Integer.decode(hexNumberStr);
+            String hexNumberAsChar = Character.toString((char) hexNumber);
+            result += hexNumberAsChar;
+             
+            searchFromIndex = endMatchIndex;
+            
+        }
+        
+        if(endMatchIndex != -1) {
+            result += str.substring(endMatchIndex);
+            //System.err.println("suffix: " + str.substring(endMatchIndex));
+        }
+        
+        return result;
+    }   
+
+    /** Attempting to produce the equivalent method fileToURLEncoding() above, but taking a String as input parameter */
+     public static String fileNameToHex(String filename) {
+        /*String filename_url_encoded = "";
+        try {
+            URI filename_uri = new URI(filename);
+            String filename_ascii = filename_uri.toASCIIString();
+            String filename_raw_bytes = URLDecoder.decode(filename_ascii,"ISO-8859-1");
+            filename_url_encoded = iso_8859_1_filename_to_url_encoded(filename_raw_bytes); 
+            return filename_url_encoded;
+        } catch (Exception e) {
+            e.printStackTrace();
+            // Give up trying to convert
+            filename_url_encoded = filename; 
+        }
+        return filename_url_encoded;
+        */
+        
+        String hexFilename = "";
+        for(int i = 0; i < filename.length(); i++) {
+            int charCode = filename.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
+                hexFilename += filename.charAt(i);
+            } else {
+                hexFilename += "&#x" + String.format("%x", charCode).toUpperCase() + ";"; // looks like: "&#x[up-to-4-hexdigits-in-UPPERCASE];"
+            }
+        }
+          
+        return hexFilename;
+     }
+
     // Dr Bainbridge's methods
     /* On Linux machines that are set to using an ISO-8859 (Latin) type encoding, 
@@ -358 +453 @@
         return filename_url_encoded;
     }
-
-    /** Attempting to produce the equivalent method fileToURLEncoding() above, but taking a String as input parameter */
-     public static String fileNameToHex(String filename) {
-        /*String filename_url_encoded = "";
-        try {
-            URI filename_uri = new URI(filename);
-            String filename_ascii = filename_uri.toASCIIString();
-            String filename_raw_bytes = URLDecoder.decode(filename_ascii,"ISO-8859-1");
-            filename_url_encoded = iso_8859_1_filename_to_url_encoded(filename_raw_bytes); 
-            return filename_url_encoded;
-        } catch (Exception e) {
-            e.printStackTrace();
-            // Give up trying to convert
-            filename_url_encoded = filename; 
-        }
-        return filename_url_encoded;
-        */
-        
-        String hexFilename = "";
-        for(int i = 0; i < filename.length(); i++) {
-            int charCode = filename.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
-                hexFilename += filename.charAt(i);
-            } else {
-                hexFilename += "&#x" + String.format("%x", charCode).toUpperCase() + ";"; // looks like: "&#x[up-to-4-hexdigits-in-UPPERCASE];"
-            }
-        }
-          
-        return hexFilename;
-     }
-    
     
     // For unicode codepoints see: