Changeset 33744 for main/trunk/gli/src/org/greenstone/gatherer/metadata/FilenameEncoding.java

Timestamp:

2019-12-03T15:04:32+13:00 (4 years ago)

Author:

ak19

Message:

Refactored code to do more inside functions rather than make callers do extra, specific work that requires knowledge of what happened (and didn't happen) inside the called functions. Shifted the new functions about until they appear after Dr Bainbridge's more important functions.

File:

• main/trunk/gli/src/org/greenstone/gatherer/metadata/FilenameEncoding.java (modified) (4 diffs)

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

@@ -438 +438 @@
         return str;
     }
-    
-    
-    // follows Dr Bainbridge's method below, but with a String parameter instead of a file parameter
-    public static String UNUSED_filenameToURLEncoding(String filename) {
-        if(!MULTIPLE_FILENAME_ENCODINGS_SUPPORTED) {
-            return filename;
-        }
-
-         // Can't create a URI out of a filename containing spaces. Spaces must be encoded as %20
-        String filename_url_encoded = filename.replace(" ", "%20");
-        //filename_url_encoded = filename_url_encoded.replace("&", "%26"); // &'s ASCII code is 36 in decimal, and 26 in hex
-        //filename_url_encoded = filename_url_encoded.replace("+", "%2B"); // +'s ASCII code is 43 decimal, 2b in hex, 2B when uppercased
-
-        try {
-            URI filename_uri = new URI(filename_url_encoded);
-            // The trick:
-            //  1. toASCIIString() will %xx encode values > 127
-            //  2. Decode the result to "ISO-8859-1"
-            //  3. URL encode the bytes to string
-            
-            // Step 2 forces the string to be 8-bit values.  It
-            // doesn't matter if the starting raw filename was *not*
-            // in the ISO-8859-1 encoding, the effect is to ensure
-            // we have an 8-bit byte string that (numerically)
-            // captures the right value.  These numerical values are
-            // then used to determine how to URL encode it
-            
-            String filename_ascii = filename_uri.toASCIIString();
-            //filename_ascii = filename_ascii.replace("&", "%26"); // &'s ASCII code is 36 in decimal, and 26 in hex
-            //filename_ascii = filename_ascii.replace("+", "%2B"); // +'s ASCII code is 43 decimal, 2b in hex, 2B when uppercased
-            String filename_raw_bytes = URLDecoder.decode(filename_ascii,"ISO-8859-1");
-            filename_url_encoded = iso_8859_1_filename_to_url_encoded(filename_raw_bytes);
-            
-            // DEALING WITH & and + in filenames: NOT WORKING YET
-            //if(filename_url_encoded.contains("&")) {
-            //  filename_url_encoded = filename_url_encoded.replace("&", "%36amp;");
-            //} else if(filename_url_encoded.contains("&")) {
-            //  filename_url_encoded = filename_url_encoded.replace("&", "%36");
-            //}
-            
-        }
-        catch (Exception e) {
-            e.printStackTrace();
-            // Give up trying to convert
-            filename_url_encoded = filename; 
-        }
-        return filename_url_encoded;
-    }
-    
-    
-    // follows Dr Bainbridge's method below, but with a String parameter instead of a file parameter    
-    public static String filenameToURLEncoding(String filename) {
-        if(!MULTIPLE_FILENAME_ENCODINGS_SUPPORTED) { // on a UTF-8 file system, DO NOT do the stuff below, just return input param
-            return filename;
-        }
-        File file = new File (filename);
-        return fileToURLEncoding(file);
-    }       
 
     
@@ -517 +459 @@
             return file.getAbsolutePath();
         }
-
-        // we'll want to protect & by replacing with &'s hex value
-        // but we don't want to replace &#x....; with the same!
-        Pattern plain_ampersand_not_hex_prefix_Pattern = Pattern.compile("&[^#]");
-        
-        
-        int containsAmp = 0;
-        if(file.getName().contains("&")) {
-            System.err.println("@@@ 1 to encode " + file.getName());
-            containsAmp = 1;
-        } else if(file.getName().contains("&")) {
-            System.err.println("@@@ 2 to encode " + file.getName());
-            containsAmp = 2;
-        } else {
-            System.err.println("@@@ 0 to encode " + file.getName());
-        }
-        
         
         String filename_url_encoded = "";
@@ -571 +496 @@
             
             String filename_ascii = filename_uri.toASCIIString();
-            // protect & and + in the filename too
-            filename_ascii = escapeAllCharWithHexEntity(filename_ascii, '&');
-            
-            if(containsAmp > 0) System.err.println("@@@ filename_ascii: " + filename_ascii);
-            
-            
-            //if(containsAmp > 0) System.err.println("@@@ filename_ascii with hexed &: " + filename_ascii);
+            
+            // Before proceeding, protect & in the filename too.
+            // &'s ASCII code is 36 in decimal, and 26 in hex, so replace with &
+            // But dangerous to do simple replace if there are &#x...; entities in the filename already!
+            // That is, we'll want to protect & by replacing with &'s hex value, but we don't want to replace the & in "&#x....;" with the same!
+            //filename_url_encoded = filename_url_encoded.replace("&", "&x26;");// SO THIS IS BAD
+            //filename_url_encoded = filename_url_encoded.replace("&", hexEntityForChar("&"));// SAME, STILL BAD
+            filename_ascii = escapeAllCharWithHexEntity(filename_ascii, '&'); // Good: CAREFULLY replaces & that are not part of hex entities
+            
+            
             String filename_raw_bytes = URLDecoder.decode(filename_ascii,"ISO-8859-1");         
             filename_url_encoded = iso_8859_1_filename_to_url_encoded(filename_raw_bytes);
-            
-            
-            //filename_url_encoded = filename_url_encoded.replace("&", "%26"); // &'s ASCII code is 36 in decimal, and 26 in hex
-            //filename_ascii = filename_ascii.replace("+", "%2B"); // +'s ASCII code is 43 decimal, 2b in hex, 2B when uppercased
-            //if(containsAmp > 0) System.err.println("@@@ filename_url_encoded: " + filename_url_encoded);
             
         }
@@ -672 +595 @@
     }
    
+ // FURTHER HELPER METHODS 
+ 
+    /**
+     * Produce the equivalent of method fileToURLEncoding(), but taking a String as input parameter.
+     * If filename is relative, then the current directory (gli?) will be prefixed to what is returned
+     * and should be removed manually by the caller. Alternatively, for relative paths, call the variant
+     * relativeFilenameToURLEncoding(String), which will remove any added filepath prefix.
+    */
+    public static String fullFilepathToURLEncoding(String filename) {
+        if(!MULTIPLE_FILENAME_ENCODINGS_SUPPORTED) { // on a UTF-8 file system, DO NOT do the stuff below, just return input param
+            return filename;
+        }
+        
+        File file = new File (filename);
+        //return fileToURLEncoding(file);
+        String filename_url_encoded = fileToURLEncoding(file);
+        
+        // if the current directory (".") was passed in as filename,
+        // then the filename_url_encoded looks like /full/path/./
+        // In that case, remove the ./ at the end
+        if (filename_url_encoded.endsWith(FilenameEncoding.URL_FILE_SEPARATOR+"."+FilenameEncoding.URL_FILE_SEPARATOR)) {
+            filename_url_encoded = filename_url_encoded.substring(0, filename_url_encoded.length()-2); // cut off /. at end
+        }
+        
+        return filename_url_encoded;
+    }
+ 
+    /**
+     * Produce the equivalent of method fileToURLEncoding(), but taking a String as input parameter
+     * If filename is a relative path, call this method to get it specially URL encoded.
+     * This method will remove the current directory that is prefixed as an intermediary step.
+    */
+    public static String relativeFilenameToURLEncoding(String filename) {
+        if(!MULTIPLE_FILENAME_ENCODINGS_SUPPORTED) { // on a UTF-8 file system, DO NOT do the stuff below, just return input param
+            return filename;
+        }
+        
+        String curr_directory_path = FilenameEncoding.fullFilepathToURLEncoding(".");
+        return filenameToURLEncodingWithPrefixRemoved(filename, curr_directory_path);
+        
+        /*
+        String curr_directory_path = FilenameEncoding.fullFilepathToURLEncoding(".");       
+        if (curr_directory_path.endsWith("."+FilenameEncoding.URL_FILE_SEPARATOR)) {
+            curr_directory_path = curr_directory_path.substring(0, curr_directory_path.length()-2); // cut off /. at end            
+        }
+        
+        File file = new File (filename);        
+        String filename_url_encoded = fileToURLEncoding(file); // returns a full filepath
+        
+        // now lop off the current dir prefix that FilenameEncoding.filenameToURLEncoding(STRING) variant would have added
+        filename_url_encoded = filename_url_encoded.substring(curr_directory_path.length());
+        // remove any remaining slash prefix
+        if (filename_url_encoded.startsWith(FilenameEncoding.URL_FILE_SEPARATOR)) {
+            filename_url_encoded = filename_url_encoded.substring(FilenameEncoding.URL_FILE_SEPARATOR.length());
+        }
+        
+        return filename_url_encoded;
+        */
+    }
+    
+    /**
+     * Produce the equivalent of method fileToURLEncoding(), but taking a String as input parameter
+     * Convenience method that will return the specially URL encoded version of filename
+     * with the provided removeFilePathPrefix removed */
+    public static String filenameToURLEncodingWithPrefixRemoved(String filename, String removeFilePathPrefix) {
+        if(!MULTIPLE_FILENAME_ENCODINGS_SUPPORTED) { // on a UTF-8 file system, DO NOT do the stuff below, just return input param
+            return filename;
+        }
+        
+        /*if (removeFilePathPrefix.endsWith("."+FilenameEncoding.URL_FILE_SEPARATOR)) {
+            removeFilePathPrefix = removeFilePathPrefix.substring(0, removeFilePathPrefix.length()-2); // cut off /. at end     
+        }
+        */
+        
+        File file = new File (filename);        
+        String filename_url_encoded = fileToURLEncoding(file); // returns a full filepath
+        
+        System.err.println("@@@ full url encoded filename: " + filename_url_encoded);
+        
+        // now lop off the given removeFilePathPrefix that FilenameEncoding.filenameToURLEncoding(STRING) variant would have added
+        filename_url_encoded = filename_url_encoded.substring(removeFilePathPrefix.length());
+        // remove any remaining slash prefix
+        if (filename_url_encoded.startsWith(FilenameEncoding.URL_FILE_SEPARATOR)) {
+            filename_url_encoded = filename_url_encoded.substring(FilenameEncoding.URL_FILE_SEPARATOR.length());
+        }
+        
+        return filename_url_encoded;
+    }
 }