/*
* listTermVectors displays the term vectors for all of the fields
* in a document in an index (specified by reader).
*/
static void listTermVectors(IndexReader reader, String docidString) throws IOException {
System.out.println("\nTermVector: docid " + docidString);
int docid = Integer.parseInt(docidString);
if ((docid < 0) || (docid >= reader.numDocs())) {
System.out.println("ERROR: " + docidString + " is a bad document id.");
return;
}
;
/*
* Iterate over the fields in this document.
*/
Fields fields = reader.getTermVectors(docid);
Iterator<String> fieldIterator = fields.iterator();
while (fieldIterator.hasNext()) {
String fieldName = fieldIterator.next();
System.out.println(" Field: " + fieldName);
Terms terms = fields.terms(fieldName);
termVectorDisplay(terms);
}
;
}
/**
* Create a PriorityQueue from a word->tf map.
*
* @param words a map of words keyed on the word(String) with Int objects as the values.
* @param fieldNames an array of field names to override defaults.
*/
private PriorityQueue<ScoreTerm> createQueue(Map<String, Int> words, String... fieldNames)
throws IOException {
// have collected all words in doc and their freqs
int numDocs = ir.numDocs();
final int limit = Math.min(maxQueryTerms, words.size());
FreqQ queue = new FreqQ(limit); // will order words by score
for (String word : words.keySet()) { // for every word
int tf = words.get(word).x; // term freq in the source doc
if (minTermFreq > 0 && tf < minTermFreq) {
continue; // filter out words that don't occur enough times in the source
}
// go through all the fields and find the largest document frequency
String topField = fieldNames[0];
int docFreq = 0;
for (String fieldName : fieldNames) {
int freq = ir.docFreq(new Term(fieldName, word));
topField = (freq > docFreq) ? fieldName : topField;
docFreq = (freq > docFreq) ? freq : docFreq;
}
if (minDocFreq > 0 && docFreq < minDocFreq) {
continue; // filter out words that don't occur in enough docs
}
if (docFreq > maxDocFreq) {
continue; // filter out words that occur in too many docs
}
if (docFreq == 0) {
continue; // index update problem?
}
float idf = similarity.idf(docFreq, numDocs);
float score = tf * idf;
if (queue.size() < limit) {
// there is still space in the queue
queue.add(new ScoreTerm(word, topField, score, idf, docFreq, tf));
} else {
ScoreTerm term = queue.top();
if (term.score < score) { // update the smallest in the queue in place and update the queue.
term.update(word, topField, score, idf, docFreq, tf);
queue.updateTop();
}
}
}
return queue;
}
/*
* listTermVectorField displays the term vector for a field in
* a document in an index (specified by reader).
*/
static void listTermVectorField(IndexReader reader, String docidString, String field)
throws IOException {
System.out.println("\nTermVector: docid " + docidString + ", field " + field);
int docid = Integer.parseInt(docidString);
if ((docid < 0) || (docid >= reader.numDocs())) {
System.out.println("ERROR: " + docidString + " is a bad document id.");
return;
}
;
Terms terms = reader.getTermVector(docid, field);
termVectorDisplay(terms);
}
public static void main(String[] args) throws IOException {
IndexReader reader = null;
/*
* Opening the index first simplifies the processing of the
* rest of the command line arguments.
*/
for (int i = 0; i < args.length; i++) {
if (("-index".equals(args[i])) && ((i + 1) < args.length)) {
reader = DirectoryReader.open(FSDirectory.open(new File(args[i + 1])));
if (reader == null) {
System.err.println("Error: Can't open index " + args[i + 1]);
System.exit(1);
}
;
break;
}
;
}
;
if (reader == null) {
System.err.println(usage);
System.exit(1);
}
;
/*
* Process the command line arguments sequentially.
*/
for (int i = 0; i < args.length; i++) {
if ("-index".equals(args[i])) {
/*
* Handled in the previous loop, so just skip the argument.
*/
i++;
} else if ("-list-edocid".equals(args[i])) {
System.out.println("-list-edocid:");
if ((i + 1) >= args.length) {
System.out.println(usage);
break;
}
;
Document d = reader.document(Integer.parseInt(args[i + 1]));
System.out.println(
"Internal docid --> External docid: " + args[i + 1] + " --> " + d.get("externalId"));
i += 1;
} else if ("-list-docids".equals(args[i])) {
System.out.println("-list-docids:");
for (int j = 0; j < reader.numDocs(); j++) {
Document d = reader.document(j);
System.out.println("Internal --> external docid: " + j + " --> " + d.get("externalId"));
}
;
} else if ("-list-fields".equals(args[i])) {
Fields fields = MultiFields.getFields(reader);
System.out.print("\nNumber of fields: ");
if (fields == null) System.out.println("0");
else {
System.out.println(fields.size());
Iterator<String> is = fields.iterator();
while (is.hasNext()) {
System.out.println("\t" + is.next());
}
;
}
;
} else if ("-list-postings".equals(args[i])) {
if ((i + 2) >= args.length) {
System.out.println(usage);
break;
}
;
listPostings(reader, args[i + 1], args[i + 2], Integer.MAX_VALUE);
i += 2;
} else if ("-list-postings-sample".equals(args[i])) {
if ((i + 2) >= args.length) {
System.out.println(usage);
break;
}
;
listPostings(reader, args[i + 1], args[i + 2], 5);
i += 2;
} else if ("-list-stats".equals(args[i])) {
System.out.println("Corpus statistics:");
System.out.println("\tnumdocs\t\t" + reader.numDocs());
System.out.println(
"\turl:\t"
+ "\tnumdocs="
+ reader.getDocCount("url")
+ "\tsumTotalTF="
+ reader.getSumTotalTermFreq("url")
+ "\tavglen="
+ reader.getSumTotalTermFreq("url") / (float) reader.getDocCount("url"));
System.out.println(
"\tkeywords:"
+ "\tnumdocs="
+ reader.getDocCount("keywords")
+ "\tsumTotalTF="
+ reader.getSumTotalTermFreq("keywords")
+ "\tavglen="
+ reader.getSumTotalTermFreq("keywords") / (float) reader.getDocCount("keywords"));
System.out.println(
"\ttitle:\t"
+ "\tnumdocs="
+ reader.getDocCount("title")
+ "\tsumTotalTF="
+ reader.getSumTotalTermFreq("title")
+ "\tavglen="
+ reader.getSumTotalTermFreq("title") / (float) reader.getDocCount("title"));
System.out.println(
"\tbody:\t"
+ "\tnumdocs="
+ reader.getDocCount("body")
+ "\tsumTotalTF="
+ reader.getSumTotalTermFreq("body")
+ "\tavglen="
+ reader.getSumTotalTermFreq("body") / (float) reader.getDocCount("body"));
System.out.println(
"\tinlink:\t"
+ "\tnumdocs="
+ reader.getDocCount("inlink")
+ "\tsumTotalTF="
+ reader.getSumTotalTermFreq("inlink")
+ "\tavglen="
+ reader.getSumTotalTermFreq("inlink") / (float) reader.getDocCount("inlink"));
} else if ("-list-terms".equals(args[i])) {
if ((i + 1) >= args.length) {
System.out.println(usage);
break;
}
;
listTermDictionary(reader, args[i + 1]);
i += 1;
} else if ("-list-termvector".equals(args[i])) {
if ((i + 1) >= args.length) {
System.out.println(usage);
break;
}
;
listTermVectors(reader, args[i + 1]);
i += 1;
} else if ("-list-termvector-field".equals(args[i])) {
if ((i + 2) >= args.length) {
System.out.println(usage);
break;
}
;
listTermVectorField(reader, args[i + 1], args[i + 2]);
i += 2;
} else System.err.println("\nWarning: Unknown argument " + args[i] + " ignored.");
}
;
/*
* Close the index and exit gracefully.
*/
reader.close();
}
/**
* Set the maximum percentage in which words may still appear. Words that appear in more than this
* many percent of all docs will be ignored.
*
* @param maxPercentage the maximum percentage of documents (0-100) that a term may appear in to
* be still considered relevant
*/
public void setMaxDocFreqPct(int maxPercentage) {
this.maxDocFreq = maxPercentage * ir.numDocs() / 100;
}