/**
* Add a file to the Lucene index (and generate a xref file)
*
* @param file The file to add
* @param path The path to the file (from source root)
* @throws java.io.IOException if an error occurs
*/
private void addFile(File file, String path) throws IOException {
try (InputStream in = new BufferedInputStream(new FileInputStream(file))) {
FileAnalyzer fa = AnalyzerGuru.getAnalyzer(in, path);
for (IndexChangedListener listener : listeners) {
listener.fileAdd(path, fa.getClass().getSimpleName());
}
fa.setCtags(ctags);
fa.setProject(Project.getProject(path));
Document d;
try {
d = analyzerGuru.getDocument(file, in, path, fa);
} catch (Exception e) {
log.log(
Level.INFO,
"Skipped file ''{0}'' because the analyzer didn''t " + "understand it.",
path);
StringBuilder stack = new StringBuilder();
for (StackTraceElement ste : e.getStackTrace()) {
stack.append(ste.toString()).append(System.lineSeparator());
}
StringBuilder sstack = new StringBuilder();
for (Throwable t : e.getSuppressed()) {
for (StackTraceElement ste : t.getStackTrace()) {
sstack.append(ste.toString()).append(System.lineSeparator());
}
}
log.log(
Level.FINE,
"Exception from analyzer {0}: {1} {2}{3}{4}{5}{6}",
new String[] {
fa.getClass().getName(),
e.toString(),
System.lineSeparator(),
stack.toString(),
System.lineSeparator(),
sstack.toString()
});
return;
}
writer.addDocument(d, fa);
Genre g = fa.getFactory().getGenre();
if (xrefDir != null && (g == Genre.PLAIN || g == Genre.XREFABLE)) {
File xrefFile = new File(xrefDir, path);
// If mkdirs() returns false, the failure is most likely
// because the file already exists. But to check for the
// file first and only add it if it doesn't exists would
// only increase the file IO...
if (!xrefFile.getParentFile().mkdirs()) {
assert xrefFile.getParentFile().exists();
}
fa.writeXref(xrefDir, path);
}
setDirty();
for (IndexChangedListener listener : listeners) {
listener.fileAdded(path, fa.getClass().getSimpleName());
}
}
}
/** @param args */
public static void main(String[] args) {
SingleUserAnalyse sua = new SingleUserAnalyse("胡新辰点点点", "usr.txt");
LuceneAnalyser ts = new LuceneAnalyser();
try {
String semiFile = "C:\\Users\\Edward\\Desktop\\semi.txt";
String resultFile = "C:\\Users\\Edward\\Desktop\\result.txt";
// PrintWriter Pout = new PrintWriter(new FileWriter(semiFile));
// JSONObject semiData = sua.getIndexData();
// Pout.println(semiData.toString());
// Pout.close();
File input = new File(semiFile);
JSONObject js = new JSONObject(new JSONTokener(new FileReader(input)));
// js=sua.weightAdjust(js);
JSONObject result = ts.getKeyWords(js);
PrintWriter resultOut = new PrintWriter(new FileWriter(resultFile));
resultOut.println(result.toString());
resultOut.close();
} catch (Exception e) {
// TODO Auto-generated catch block
e.printStackTrace();
}
// TODO Auto-generated method stub
}
@SuppressWarnings("finally")
public JSONObject getKeyWords(JSONObject semiData) {
JSONObject keyWords = new JSONObject();
try {
this.buildIndex(semiData);
this.getIndexInfo(this.indexDir, 4);
this.generateWekaFile(this.termList, this.maxDocNum, this.wekaFile);
JSONArray array = this.Cluster(this.wekaFile, 7);
int totalNum = 0;
for (int i = 0; i < array.length(); i++) {
totalNum += array.getJSONArray(i).length();
}
keyWords.put("maxFreq", this.maxFreq);
keyWords.put("totalNum", totalNum);
keyWords.put("WordList", array);
} catch (WeiboException e) {
System.out.print("getKeyWords++++++weibo\n");
System.out.print("error:" + e.getError() + "toString:" + e.toString());
keyWords.put("error", e.getError());
e.printStackTrace();
} catch (Exception e) {
System.out.print("getKeyWords++++++Exception");
keyWords.put("error", e.toString());
e.printStackTrace();
} finally {
try {
this.myDelete(this.indexDir);
this.myDelete(this.wekaFile);
} catch (Exception e) {
e.printStackTrace();
}
return keyWords;
}
}
/**
* Search a picture
*
* @param imageBytes
* @param maxHits
* @param feature
* @param pictures
* @return
* @throws IOException
*/
public static List<LirePictureSortable> search(
byte[] imageBytes, int maxHits, FeatureEnumerate feature, List<LirePictureSortable> pictures)
throws IOException {
File path = getPath(feature.getText());
log.debug("reading from indexed path " + path.getAbsolutePath());
List<LirePictureSortable> result = new ArrayList<>();
try {
IndexReader ir = DirectoryReader.open(FSDirectory.open(path));
ImageSearcher searcher = new GenericFastImageSearcher(maxHits, feature.getValueClass());
// searching with a image file ...
InputStream in = new ByteArrayInputStream(imageBytes);
ImageSearchHits hits = searcher.search(in, ir);
float score = 0.0F;
for (int i = 0; i < hits.length(); i++) {
score = hits.score(i);
LirePictureSortable lp =
new LirePictureSortable(
UUID.fromString(hits.doc(i).getValues(DocumentBuilder.FIELD_NAME_IDENTIFIER)[0]),
score,
feature);
/* check is its a picture was repeated by picture UUID */
if (pictures.contains(lp)) {
lp = pictures.get(pictures.indexOf(lp));
lp.addDescriptor(feature, score);
lp.addScore(score);
} else {
result.add(lp);
}
}
} catch (Exception e) {
e.printStackTrace();
}
return result;
}
/**
* Index for each builder type
*
* @param image
* @param picture_id
* @param prefix
* @param builder
* @param conf
* @throws IOException
*/
private static void luceneIndexer(
BufferedImage image,
UUID picture_id,
String prefix,
DocumentBuilder builder,
IndexWriterConfig conf)
throws IOException {
File path = getPath(prefix);
log.debug("creating indexed path " + path.getAbsolutePath());
IndexWriter iw = new IndexWriter(FSDirectory.open(path), conf);
try {
Document document = builder.createDocument(image, picture_id.toString());
iw.addDocument(document);
} catch (Exception e) {
System.err.println("Error reading image or indexing it.");
e.printStackTrace();
}
// closing the IndexWriter
iw.close();
}