public static Document Document(File f) throws IOException, InterruptedException {
// 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 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 tokenize the field into words.
doc.add(Field.Keyword("modified", DateField.timeToString(f.lastModified())));
// Add the uid as a field, so that index can be incrementally maintained.
// This field is not stored with document, it is indexed, but it is not
// tokenized prior to indexing.
doc.add(new Field("uid", uid(f), false, true, false));
HTMLParser parser = new HTMLParser(f);
// Add the tag-stripped contents as a Reader-valued Text field so it will
// get tokenized and indexed.
doc.add(Field.Text("contents", parser.getReader()));
// Add the summary as an UnIndexed field, so that it is stored and returned
// with hit documents for display.
doc.add(Field.UnIndexed("summary", parser.getSummary()));
// Add the title as a separate Text field, so that it can be searched
// separately.
doc.add(Field.Text("title", parser.getTitle()));
// return the document
return doc;
}
/** for testing DateTools support */
private String getDate(Date d, DateTools.Resolution resolution) throws Exception {
if (resolution == null) {
return DateField.dateToString(d);
} else {
return DateTools.dateToString(d, resolution);
}
}
public static String uid(File f) {
// Append path and date into a string in such a way that lexicographic
// sorting gives the same results as a walk of the file hierarchy. Thus
// null (\u0000) is used both to separate directory components and to
// separate the path from the date.
return f.getPath().replace(dirSep, '\u0000')
+ "\u0000"
+ DateField.timeToString(f.lastModified());
}
/** for testing legacy DateField support */
public void testLegacyDateRange() throws Exception {
String startDate = getLocalizedDate(2002, 1, 1, false);
String endDate = getLocalizedDate(2002, 1, 4, false);
Calendar endDateExpected = new GregorianCalendar();
endDateExpected.set(2002, 1, 4, 23, 59, 59);
endDateExpected.set(Calendar.MILLISECOND, 999);
assertQueryEquals(
"[ " + escapeDateString(startDate) + " TO " + escapeDateString(endDate) + "]",
null,
"["
+ getLegacyDate(startDate)
+ " TO "
+ DateField.dateToString(endDateExpected.getTime())
+ "]");
assertQueryEquals(
"{ " + escapeDateString(startDate) + " " + escapeDateString(endDate) + " }",
null,
"{" + getLegacyDate(startDate) + " TO " + getLegacyDate(endDate) + "}");
}
private static void addDateDoc(
String content,
int year,
int month,
int day,
int hour,
int minute,
int second,
IndexWriter iw)
throws IOException {
Document d = new Document();
d.add(new Field("f", content, Field.Store.YES, Field.Index.ANALYZED));
Calendar cal = Calendar.getInstance(Locale.ENGLISH);
cal.set(year, month - 1, day, hour, minute, second);
d.add(
new Field(
"date",
DateField.dateToString(cal.getTime()),
Field.Store.YES,
Field.Index.NOT_ANALYZED));
iw.addDocument(d);
}
/** for testing legacy DateField support */
private String getLegacyDate(String s) throws Exception {
DateFormat df = DateFormat.getDateInstance(DateFormat.SHORT);
return DateField.dateToString(df.parse(s));
}