dnaber 2004/08/03 14:49:24
Modified: src/demo/org/apache/lucene/demo DeleteFiles.java
HTMLDocument.java SearchFiles.java IndexHTML.java
FileDocument.java
Log:
Store the path as a Keyword field. Also rename HTMLDocument's "url" to "path"
and store it as a Keyword field, too. DeleteFiles now takes such a path
as its command line parameter and works on the index directory "index", like the
other demos.
This fixes bug http://issues.apache.org/bugzilla/show_bug.cgi?id=30330
Revision Changes Path
1.3 +18 -9 jakarta-lucene/src/demo/org/apache/lucene/demo/DeleteFiles.java
Index: DeleteFiles.java
===================================================================
RCS file: /home/cvs/jakarta-lucene/src/demo/org/apache/lucene/demo/DeleteFiles.java,v
retrieving revision 1.2
retrieving revision 1.3
diff -u -r1.2 -r1.3
--- DeleteFiles.java 29 Mar 2004 22:48:00 -0000 1.2
+++ DeleteFiles.java 3 Aug 2004 21:49:24 -0000 1.3
@@ -16,27 +16,36 @@
* limitations under the License.
*/
-import java.io.IOException;
-
import org.apache.lucene.store.Directory;
import org.apache.lucene.store.FSDirectory;
import org.apache.lucene.index.IndexReader;
import org.apache.lucene.index.Term;
+//import org.apache.lucene.index.Term;
class DeleteFiles {
+
public static void main(String[] args) {
+ String usage = "java org.apache.lucene.demo.DeleteFiles <unique_term>";
+ if (args.length == 0) {
+ System.err.println("Usage: " + usage);
+ System.exit(1);
+ }
try {
- Directory directory = FSDirectory.getDirectory("demo index", false);
+ Directory directory = FSDirectory.getDirectory("index", false);
IndexReader reader = IndexReader.open(directory);
-// Term term = new Term("path", "pizza");
-// int deleted = reader.delete(term);
+ Term term = new Term("path", args[0]);
+ int deleted = reader.delete(term);
-// System.out.println("deleted " + deleted +
-// " documents containing " + term);
+ System.out.println("deleted " + deleted +
+ " documents containing " + term);
- for (int i = 0; i < reader.maxDoc(); i++)
- reader.delete(i);
+ // one can also delete documents by their internal id:
+ /*
+ for (int i = 0; i < reader.maxDoc(); i++) {
+ System.out.println("Deleting document with id " + i);
+ reader.delete(i);
+ }*/
reader.close();
directory.close();
1.3 +4 -3 jakarta-lucene/src/demo/org/apache/lucene/demo/HTMLDocument.java
Index: HTMLDocument.java
===================================================================
RCS file:
/home/cvs/jakarta-lucene/src/demo/org/apache/lucene/demo/HTMLDocument.java,v
retrieving revision 1.2
retrieving revision 1.3
diff -u -r1.2 -r1.3
--- HTMLDocument.java 29 Mar 2004 22:48:00 -0000 1.2
+++ HTMLDocument.java 3 Aug 2004 21:49:24 -0000 1.3
@@ -45,9 +45,10 @@
// make a new, empty document
Document doc = new Document();
- // Add the url as a field named "url". Use an UnIndexed field, so
- // that the url is just stored with the document, but is not searchable.
- doc.add(Field.UnIndexed("url", f.getPath().replace(dirSep, '/')));
+ // Add the url as a field named "path". Use a Keyword field, so
+ // that it's searchable, but so that no attempt is made
+ // to tokenize the field into words.
+ doc.add(Field.Keyword("path", f.getPath().replace(dirSep, '/')));
// Add the last modified date of the file a field named "modified". Use a
// Keyword field, so that it's searchable, but so that no attempt is made
1.3 +6 -9 jakarta-lucene/src/demo/org/apache/lucene/demo/SearchFiles.java
Index: SearchFiles.java
===================================================================
RCS file: /home/cvs/jakarta-lucene/src/demo/org/apache/lucene/demo/SearchFiles.java,v
retrieving revision 1.2
retrieving revision 1.3
diff -u -r1.2 -r1.3
--- SearchFiles.java 29 Mar 2004 22:48:00 -0000 1.2
+++ SearchFiles.java 3 Aug 2004 21:49:24 -0000 1.3
@@ -16,7 +16,6 @@
* limitations under the License.
*/
-import java.io.IOException;
import java.io.BufferedReader;
import java.io.InputStreamReader;
@@ -56,15 +55,13 @@
Document doc = hits.doc(i);
String path = doc.get("path");
if (path != null) {
- System.out.println(i + ". " + path);
- } else {
- String url = doc.get("url");
- if (url != null) {
- System.out.println(i + ". " + url);
- System.out.println(" - " + doc.get("title"));
- } else {
- System.out.println(i + ". " + "No path nor URL for this document");
+ System.out.println((i+1) + ". " + path);
+ String title = doc.get("title");
+ if (title != null) {
+ System.out.println(" Title: " + doc.get("title"));
}
+ } else {
+ System.out.println((i+1) + ". " + "No path for this document");
}
}
1.4 +2 -2 jakarta-lucene/src/demo/org/apache/lucene/demo/IndexHTML.java
Index: IndexHTML.java
===================================================================
RCS file: /home/cvs/jakarta-lucene/src/demo/org/apache/lucene/demo/IndexHTML.java,v
retrieving revision 1.3
retrieving revision 1.4
diff -u -r1.3 -r1.4
--- IndexHTML.java 29 Mar 2004 22:48:00 -0000 1.3
+++ IndexHTML.java 3 Aug 2004 21:49:24 -0000 1.4
@@ -144,12 +144,12 @@
uidIter.next(); // keep matching docs
} else if (!deleting) { // add new docs
Document doc = HTMLDocument.Document(file);
- System.out.println("adding " + doc.get("url"));
+ System.out.println("adding " + doc.get("path"));
writer.addDocument(doc);
}
} else { // creating a new index
Document doc = HTMLDocument.Document(file);
- System.out.println("adding " + doc.get("url"));
+ System.out.println("adding " + doc.get("path"));
writer.addDocument(doc); // add docs unconditionally
}
}
1.3 +4 -3 jakarta-lucene/src/demo/org/apache/lucene/demo/FileDocument.java
Index: FileDocument.java
===================================================================
RCS file:
/home/cvs/jakarta-lucene/src/demo/org/apache/lucene/demo/FileDocument.java,v
retrieving revision 1.2
retrieving revision 1.3
diff -u -r1.2 -r1.3
--- FileDocument.java 29 Mar 2004 22:48:00 -0000 1.2
+++ FileDocument.java 3 Aug 2004 21:49:24 -0000 1.3
@@ -47,9 +47,10 @@
// make a new, empty document
Document doc = new Document();
- // Add the path of the file as a field named "path". Use a Text field, so
- // that the index stores the path, and so that the path is searchable
- doc.add(Field.Text("path", f.getPath()));
+ // Add the path of the file as a field named "path". Use a
+ // Keyword field, so that it's searchable, but so that no attempt is made
+ // to tokenize the field into words.
+ doc.add(Field.Keyword("path", f.getPath()));
// Add the last modified date of the file a field named "modified". Use a
// Keyword field, so that it's searchable, but so that no attempt is made
---------------------------------------------------------------------
To unsubscribe, e-mail: [EMAIL PROTECTED]
For additional commands, e-mail: [EMAIL PROTECTED]
