Changeset 4563

Timestamp:

2003-06-11T13:49:35+12:00 (21 years ago)

Author:

jmt12

Message:

2030114: Added an extra static method which when called on a collections archive directory returns an ArrayList of the name of metadata elements found in the doc.xml files within the archives.

File:

• trunk/gli/src/org/greenstone/gatherer/msm/GreenstoneArchiveParser.java (modified) (4 diffs)

trunk/gli/src/org/greenstone/gatherer/msm/GreenstoneArchiveParser.java

@@ -58 +58 @@
     private GShell shell;
 
-    static final String ignore_list[] = {"assocfilepath","gsdl","Identifier","Source","URL"};
+    static final String ignore_list[] = {"assocfilepath", "gsdl", "Source", "Identifier","URL"};
 
     public GreenstoneArchiveParser(GShellProgressMonitor progress, GShell shell) {
@@ -92 +92 @@
         String file_path = null;
         Element archive_element = document.getDocumentElement();
-                // Retrieve all of the Metadata sections.
+        // Retrieve all of the Metadata sections.
         NodeList metadata_elements = archive_element.getElementsByTagName("Metadata");
-                // Now for each Metadata entry retrieved...
+        // Now for each Metadata entry retrieved...
         for(int i = 0; i < metadata_elements.getLength(); i++) {
         Element metadata_element = (Element) metadata_elements.item(i);
@@ -104 +104 @@
         else {
             // Check if its name starts with, or is equal to, one of the values in our ignore list, and if so ignore this metadata.
-            boolean ignore = (name.indexOf(".") != -1);
+            boolean ignore = false;
             for(int j = 0; !ignore && j < ignore_list.length; j++) {
             ignore = name.startsWith(ignore_list[j]);
@@ -167 +167 @@
     }
     }
+
+    static final String metadata_ignore_list[] = {"assocfilepath", "gsdl", "Identifier","URL"};
+
+    static public ArrayList extractMetadataElements(File archive_directory) {
+    ArrayList extracted_metadata_elements = new ArrayList();
+    File document_directories[] = archive_directory.listFiles();
+    for(int i = 0; i < document_directories.length; i++) {
+        // Find the doc.xml file within
+        if(document_directories[i].isDirectory()) {
+        File document_file = new File(document_directories[i], "doc.xml");
+        // Then extract the metadata from it.
+        if(document_file.exists()) {
+            try {
+            Document document = Utility.parse(document_file, false);
+            // Retrieve all of the Metadata sections.
+            Element archive_element = document.getDocumentElement();
+            NodeList metadata_elements = archive_element.getElementsByTagName("Metadata");
+            // Now for each Metadata entry retrieved...
+            for(int j = 0; j < metadata_elements.getLength(); j++) {
+                Element metadata_element = (Element) metadata_elements.item(j);
+                String name = metadata_element.getAttribute("name");
+                // Check if its name starts with, or is equal to, one of the values in our ignore list, and if so ignore this metadata.
+                boolean ignore = false;
+                for(int k = 0; !ignore && k < metadata_ignore_list.length; k++) {
+                ignore = name.startsWith(metadata_ignore_list[k]);
+                }
+                if(!ignore && !extracted_metadata_elements.contains(name)) {
+                extracted_metadata_elements.add(name);
+                }
+                name = null;
+                metadata_element = null;
+            }
+            metadata_elements = null;
+            archive_element = null;
+            document = null;
+            }
+            catch (Exception error) {
+            Gatherer.printStackTrace(error);
+            }
+        }
+        document_file = null;
+        }
+    }
+    document_directories = null;
+    return extracted_metadata_elements;
+    }
 }