Changeset 33748 for main/trunk/gli/src/org/greenstone/gatherer/metadata/FilenameEncoding.java

Timestamp:

2019-12-03T21:06:44+13:00 (4 years ago)

Author:

ak19

Message:

Linux bugfixes to recent commits to do with getting file-level meta assigned to non-ascii filenames or filenames containing plus/ampersand signs to work. Cumulative past commits were sufficient for fixing these issues on Windows. All those changes plus the current ones get it all working on Linux too.

File:

• main/trunk/gli/src/org/greenstone/gatherer/metadata/FilenameEncoding.java (modified) (7 diffs)

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

@@ -76 +76 @@
     /** Compiled pattern for hex entities of characters. These are of the forn "&#x....;" with 1 to 4 digits */
     public static final Pattern HEX_PATTERN = Pattern.compile("(&#x[0-9a-zA-Z]{1,4}+;)");
-    
+
+    /** The hex entity version of the ampersand character.
+     * We use this in place of the ampersand character in filenames in metadata.xml files to
+     * preserve the reference to the literal ampersand in the real file name on the file system.
+     */
+    public static final String HEX_ENTITY_AMPERSAND = FilenameEncoding.hexEntityForChar("&"); //"&";
+    
 
 //*********************** BUSY REFRESHING / REQUIRING  REFRESH *********************
@@ -371 +377 @@
     
     public static String fileToURLEncoding(File file) {
+    // on a UTF-8 file system, DO NOT do the stuff further below,
+    // just return input filename param, but with any & in the filename replaced with its hex entity
         if(!MULTIPLE_FILENAME_ENCODINGS_SUPPORTED) {
-            return file.getAbsolutePath();
+            // protect ampersands in filenames by converting it to its hex entity
+            String filepath = file.getAbsolutePath();
+            filepath = filepath.replace("&", HEX_ENTITY_AMPERSAND);
+            return filepath;
         }
         
@@ -419 +430 @@
             
             // Before proceeding, protect & in the filename too.
-            // &'s ASCII code is 36 in decimal, and 26 in hex, so replace with &
+            // &'s ASCII code is 36 in decimal, and 26 in hex, so replace with & (HEX_ENTITY_AMPERSAND)
             // 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!
@@ -434 +445 @@
             //filename_url_encoded = filename_url_encoded.replace("%2B", "+"); // Don't do this, won't get regex escaped when converted back to a + by caller
             filename_url_encoded = filename_url_encoded.replace("%2B", "+"); // + signs are special, as they will need to be escaped since the caller wants the filename representing a regex
-            filename_url_encoded = filename_url_encoded.replace("%26", "&"); // convert URL encoding for ampersand into hex entity for ampersand
+            filename_url_encoded = filename_url_encoded.replace("%26", HEX_ENTITY_AMPERSAND); // convert URL encoding for ampersand into hex entity for ampersand
         }
         catch (Exception e) {
@@ -530 +541 @@
     */
     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;
+        // on a UTF-8 file system, DO NOT do the stuff further below,
+        // just return input filename param, but with any & in the filename replaced with its hex entity
+        if(!MULTIPLE_FILENAME_ENCODINGS_SUPPORTED) {
+            return filename.replace("&", HEX_ENTITY_AMPERSAND);
         }
         
@@ -554 +567 @@
     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;
+            return filename.replace("&", HEX_ENTITY_AMPERSAND);
         }
         
@@ -567 +580 @@
     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;
+            return filename.replace("&", HEX_ENTITY_AMPERSAND);
         }