/** Get an alphabetically sorted list of field names. */
public List<String> getFieldNames() {
HashSet<String> names = new HashSet<String>();
names.addAll(storedFields.keySet());
names.addAll(reconstructedFields.keySet());
ArrayList<String> res = new ArrayList<String>(names.size());
res.addAll(names);
Collections.sort(res);
return res;
}
public void getIndexInfo(String indexdir, int freqThreshold) {
IndexReader reader = null;
try {
Directory dir = FSDirectory.open(new File(indexdir));
System.out.println(dir);
reader = IndexReader.open(dir);
System.out.println("document num:" + reader.numDocs());
System.out.println("======================");
TermEnum terms = reader.terms();
sortedTermQueue.clear();
maxDocNum = reader.maxDoc();
linkMap.clear();
termList.clear();
while (terms.next()) {
// System.out.print(terms.term() + "\tDocFreq:" +
TermDocs termDocs = reader.termDocs(terms.term());
MyTerm temp = new MyTerm(terms.term(), termDocs, maxDocNum);
if (temp.totalFreq < freqThreshold) {
continue;
} /*
* if(temp.originTrem.text().length()==1){ continue; }
*/
linkMap.put(temp.originTrem.text(), temp);
sortedTermQueue.add(temp);
termList.add(temp);
}
System.out.println("total Size:" + sortedTermQueue.size());
System.out.println("mapsize:" + linkMap.keySet().size());
// System.exit(0);
int num = 0;
this.maxFreq = sortedTermQueue.peek().totalFreq;
while (!sortedTermQueue.isEmpty()) {
num++;
System.out.println(num + ":" + sortedTermQueue.poll());
}
System.out.println("read index info done");
} catch (IOException e) {
e.printStackTrace();
} finally {
try {
reader.close();
} catch (IOException e) {
e.printStackTrace();
}
}
}
/**
* Convenience routine to make it easy to return the most interesting words in a document. More
* advanced users will call {@link #retrieveTerms(Reader, String) retrieveTerms()} directly.
*
* @param r the source document
* @param fieldName field passed to analyzer to use when analyzing the content
* @return the most interesting words in the document
* @see #retrieveTerms(java.io.Reader, String)
* @see #setMaxQueryTerms
*/
public String[] retrieveInterestingTerms(Reader r, String fieldName) throws IOException {
ArrayList<Object> al = new ArrayList<>(maxQueryTerms);
PriorityQueue<ScoreTerm> pq = retrieveTerms(r, fieldName);
ScoreTerm scoreTerm;
int lim =
maxQueryTerms; // have to be careful, retrieveTerms returns all words but that's probably
// not useful to our caller...
// we just want to return the top words
while (((scoreTerm = pq.pop()) != null) && lim-- > 0) {
al.add(scoreTerm.word); // the 1st entry is the interesting word
}
String[] res = new String[al.size()];
return al.toArray(res);
}
protected TestConfig[] generateTestConfigs(
int numberOfTests, TestDoc[] testDocs, TestFieldSetting[] fieldSettings) {
ArrayList<TestConfig> configs = new ArrayList<TestConfig>();
for (int i = 0; i < numberOfTests; i++) {
ArrayList<String> selectedFields = null;
if (randomBoolean()) {
// used field selection
selectedFields = new ArrayList<String>();
if (randomBoolean()) {
selectedFields.add("Doesnt_exist"); // this will be ignored.
}
for (TestFieldSetting field : fieldSettings)
if (randomBoolean()) {
selectedFields.add(field.name);
}
if (selectedFields.size() == 0) {
selectedFields = null; // 0 length set is not supported.
}
}
TestConfig config =
new TestConfig(
testDocs[randomInt(testDocs.length - 1)],
selectedFields == null ? null : selectedFields.toArray(new String[] {}),
randomBoolean(),
randomBoolean(),
randomBoolean());
configs.add(config);
}
// always adds a test that fails
configs.add(
new TestConfig(
new TestDoc("doesnt_exist", new TestFieldSetting[] {}, new String[] {})
.index("doesn't_exist"),
new String[] {"doesnt_exist"},
true,
true,
true)
.expectedException(IndexMissingException.class));
refresh();
return configs.toArray(new TestConfig[] {});
}
public void generateWekaFile(ArrayList<MyTerm> myTerms, int maxDocNum, String wekaFilePath)
throws IOException {
String text = "@relation interest\n";
text += "@attribute text string\n";
for (int i = 0; i < maxDocNum; i++) {
text += "@attribute doc" + i + "\treal\n";
}
text += "@data\n";
for (int j = 0; j < myTerms.size(); j++) {
MyTerm term = myTerms.get(j);
String line = "";
line += term.originTrem.text();
for (int i = 0; i < term.vector.length; i++) {
line += "," + term.vector[i];
}
line += "\n";
text += line;
}
// System.out.println(text);
PrintWriter Pout = new PrintWriter(new FileWriter(wekaFilePath));
Pout.println(text);
Pout.close();
}
public JSONArray Cluster(String wekaFilePath, int clusterNum) throws Exception {
File inputFile = new File(wekaFilePath);
ArffLoader arf = new ArffLoader();
arf.setFile(inputFile);
Instances originIns = arf.getDataSet();
Instances insTest = new Instances(originIns);
insTest.deleteStringAttributes();
int totalNum = insTest.numInstances();
// SimpleKMeans sm = new SimpleKMeans();
EM em = new EM();
em.setNumClusters(clusterNum);
MakeDensityBasedClusterer sm = new MakeDensityBasedClusterer();
sm.setClusterer(em);
sm.buildClusterer(insTest);
System.out.println("totalNum:" + insTest.numInstances());
System.out.println("============================");
System.out.println(sm.toString());
Map<Integer, ArrayList<String>> result = new HashMap<Integer, ArrayList<String>>();
for (int i = 0; i < clusterNum; i++) {
result.put(i, new ArrayList<String>());
}
for (int i = 0; i < totalNum; i++) {
Instance ins = originIns.instance(i);
String word = ins.stringValue(0);
Instance tempIns = new Instance(ins);
tempIns.deleteAttributeAt(0);
int cluster = sm.clusterInstance(tempIns);
result.get(cluster).add(word);
}
// print the result
ArrayList<String> words = new ArrayList<String>();
JSONArray keyWords = new JSONArray();
for (int k : result.keySet()) {
words = result.get(k);
PriorityQueue<MyTerm> clusterQueue = new PriorityQueue<MyTerm>(1, MyTermCompare);
for (int i = 0; i < words.size(); i++) {
String s = words.get(i);
assert linkMap.containsKey(s);
int freq = linkMap.get(s).totalFreq;
clusterQueue.add(linkMap.get(s));
words.set(i, "(" + s + ":" + freq + ")");
}
JSONArray clusterArray = new JSONArray();
int num = clusterQueue.size() / 10 + 1; // 5%
int totalFreq = 0;
int totalLength = 0;
for (int i = 0; i < num && !clusterQueue.isEmpty(); ) {
JSONObject mem = new JSONObject();
MyTerm myTerm = clusterQueue.poll();
String word = myTerm.originTrem.text();
if (word.length() == 1) {
continue;
}
mem.put("text", word);
mem.put("freq", myTerm.totalFreq);
clusterArray.put(mem);
i++;
totalFreq += myTerm.totalFreq;
totalLength += word.length();
}
double averFreq = totalFreq * 1.0 / num;
double averLength = totalLength * 1.0 / num;
int count = 0;
while (!clusterQueue.isEmpty() && count < num) {
MyTerm myTerm = clusterQueue.poll();
String word = myTerm.originTrem.text();
int freq = myTerm.totalFreq;
int times = (int) (word.length() / averFreq) + 1;
if (freq > averFreq / times) {
JSONObject mem = new JSONObject();
mem.put("text", word);
mem.put("freq", freq);
mem.put("extra", true);
clusterArray.put(mem);
}
}
keyWords.put(clusterArray);
System.out.println(
"cluster" + k + ":" + words.size() + ":\t" + (int) (words.size() * 1.0 / totalNum * 100));
if (result.get(k).size() < 100) {
System.out.println(result.get(k));
}
}
// System.out.println("errorNum:"+errorNum);
return keyWords;
}
/**
* Searches pages using a particular combination of flags.
*
* @param query The query to perform in Lucene query language
* @param flags A set of flags
* @return A Collection of SearchResult instances
* @throws ProviderException if there is a problem with the backend
*/
public Collection findPages(String query, int flags) throws ProviderException {
IndexSearcher searcher = null;
ArrayList<SearchResult> list = null;
Highlighter highlighter = null;
try {
String[] queryfields = {
LUCENE_PAGE_CONTENTS, LUCENE_PAGE_NAME, LUCENE_AUTHOR, LUCENE_ATTACHMENTS
};
QueryParser qp =
new MultiFieldQueryParser(Version.LUCENE_36, queryfields, getLuceneAnalyzer());
// QueryParser qp = new QueryParser( LUCENE_PAGE_CONTENTS, getLuceneAnalyzer() );
Query luceneQuery = qp.parse(query);
if ((flags & FLAG_CONTEXTS) != 0) {
highlighter =
new Highlighter(
new SimpleHTMLFormatter("<span class=\"searchmatch\">", "</span>"),
new SimpleHTMLEncoder(),
new QueryScorer(luceneQuery));
}
try {
File dir = new File(m_luceneDirectory);
Directory luceneDir = new SimpleFSDirectory(dir, null);
IndexReader reader = IndexReader.open(luceneDir);
searcher = new IndexSearcher(reader);
} catch (Exception ex) {
log.info("Lucene not yet ready; indexing not started", ex);
return null;
}
ScoreDoc[] hits = searcher.search(luceneQuery, MAX_SEARCH_HITS).scoreDocs;
list = new ArrayList<SearchResult>(hits.length);
for (int curr = 0; curr < hits.length; curr++) {
int docID = hits[curr].doc;
Document doc = searcher.doc(docID);
String pageName = doc.get(LUCENE_ID);
WikiPage page = m_engine.getPage(pageName, WikiPageProvider.LATEST_VERSION);
if (page != null) {
if (page instanceof Attachment) {
// Currently attachments don't look nice on the search-results page
// When the search-results are cleaned up this can be enabled again.
}
int score = (int) (hits[curr].score * 100);
// Get highlighted search contexts
String text = doc.get(LUCENE_PAGE_CONTENTS);
String[] fragments = new String[0];
if (text != null && highlighter != null) {
TokenStream tokenStream =
getLuceneAnalyzer().tokenStream(LUCENE_PAGE_CONTENTS, new StringReader(text));
fragments = highlighter.getBestFragments(tokenStream, text, MAX_FRAGMENTS);
}
SearchResult result = new SearchResultImpl(page, score, fragments);
list.add(result);
} else {
log.error(
"Lucene found a result page '"
+ pageName
+ "' that could not be loaded, removing from Lucene cache");
pageRemoved(new WikiPage(m_engine, pageName));
}
}
} catch (IOException e) {
log.error("Failed during lucene search", e);
} catch (ParseException e) {
log.info("Broken query; cannot parse query ", e);
throw new ProviderException(
"You have entered a query Lucene cannot process: " + e.getMessage());
} catch (InvalidTokenOffsetsException e) {
log.error("Tokens are incompatible with provided text ", e);
} finally {
if (searcher != null) {
try {
searcher.close();
} catch (IOException e) {
log.error(e);
}
}
}
return list;
}
