IndexHTMLpublic class IndexHTML extends Object
| Fields Summary |
|---|
| private static boolean | deleting | | private static IndexReader | reader | | private static IndexWriter | writer | | private static TermEnum | uidIter |
| Constructors Summary |
|---|
private IndexHTML()
|
| Methods Summary |
|---|
| private static void | indexDocs(java.io.File file, java.lang.String index, boolean create)
if (!create) { // incrementally update
reader = IndexReader.open(index); // open existing index
uidIter = reader.terms(new Term("uid", "")); // init uid iterator
indexDocs(file);
if (deleting) { // delete rest of stale docs
while (uidIter.term() != null && uidIter.term().field() == "uid") {
System.out.println("deleting " +
HTMLDocument.uid2url(uidIter.term().text()));
reader.deleteDocuments(uidIter.term());
uidIter.next();
}
deleting = false;
}
uidIter.close(); // close uid iterator
reader.close(); // close existing index
} else // don't have exisiting
indexDocs(file);
| | private static void | indexDocs(java.io.File file)
if (file.isDirectory()) { // if a directory
String[] files = file.list(); // list its files
Arrays.sort(files); // sort the files
for (int i = 0; i < files.length; i++) // recursively index them
indexDocs(new File(file, files[i]));
} else if (file.getPath().endsWith(".html") || // index .html files
file.getPath().endsWith(".htm") || // index .htm files
file.getPath().endsWith(".txt")) { // index .txt files
if (uidIter != null) {
String uid = HTMLDocument.uid(file); // construct uid for doc
while (uidIter.term() != null && uidIter.term().field() == "uid" &&
uidIter.term().text().compareTo(uid) < 0) {
if (deleting) { // delete stale docs
System.out.println("deleting " +
HTMLDocument.uid2url(uidIter.term().text()));
reader.deleteDocuments(uidIter.term());
}
uidIter.next();
}
if (uidIter.term() != null && uidIter.term().field() == "uid" &&
uidIter.term().text().compareTo(uid) == 0) {
uidIter.next(); // keep matching docs
} else if (!deleting) { // add new docs
Document doc = HTMLDocument.Document(file);
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("path"));
writer.addDocument(doc); // add docs unconditionally
}
}
| | public static void | main(java.lang.String[] argv)Indexer for HTML files. // document id iterator
try {
String index = "index";
boolean create = false;
File root = null;
String usage = "IndexHTML [-create] [-index <index>] <root_directory>";
if (argv.length == 0) {
System.err.println("Usage: " + usage);
return;
}
for (int i = 0; i < argv.length; i++) {
if (argv[i].equals("-index")) { // parse -index option
index = argv[++i];
} else if (argv[i].equals("-create")) { // parse -create option
create = true;
} else if (i != argv.length-1) {
System.err.println("Usage: " + usage);
return;
} else
root = new File(argv[i]);
}
Date start = new Date();
if (!create) { // delete stale docs
deleting = true;
indexDocs(root, index, create);
}
writer = new IndexWriter(index, new StandardAnalyzer(), create);
writer.setMaxFieldLength(1000000);
indexDocs(root, index, create); // add new docs
System.out.println("Optimizing index...");
writer.optimize();
writer.close();
Date end = new Date();
System.out.print(end.getTime() - start.getTime());
System.out.println(" total milliseconds");
} catch (Exception e) {
System.out.println(" caught a " + e.getClass() +
"\n with message: " + e.getMessage());
}
|
|
