def main(cls, argv):
allBooks = MatchAllDocsQuery()
parser = QueryParser(Version.LUCENE_CURRENT, "contents",
StandardAnalyzer(Version.LUCENE_CURRENT))
query = BooleanQuery()
query.add(allBooks, BooleanClause.Occur.SHOULD)
query.add(parser.parse("java OR action"), BooleanClause.Occur.SHOULD)
indexDir = System.getProperty("index.dir")
directory = SimpleFSDirectory(File(indexDir))
example = SortingExample(directory)
example.displayResults(query, Sort.RELEVANCE)
example.displayResults(query, Sort.INDEXORDER)
example.displayResults(query,
Sort(SortField("category", SortField.STRING)))
example.displayResults(query,
Sort(SortField("pubmonth", SortField.INT, True)))
example.displayResults(query,
Sort([SortField("category", SortField.STRING),
SortField.FIELD_SCORE,
SortField("pubmonth", SortField.INT, True)]))
example.displayResults(query,
Sort([SortField.FIELD_SCORE,
SortField("category", SortField.STRING)]))
directory.close()
def setUp(self):
fsIndexDir = os.path.join(System.getProperty("java.io.tmpdir", "tmp"),
"fs-index")
self.rmdir(fsIndexDir)
self.ramDir = RAMDirectory()
self.fsDir = SimpleFSDirectory(File(fsIndexDir))
def setUp(self):
indexDir = os.path.join(System.getProperty('java.io.tmpdir', 'tmp'),
'index-dir')
self.rmdir(indexDir)
self.dir = SimpleFSDirectory(File(indexDir))
self.addDocuments(self.dir)
def main(cls, argv):
if len(argv) < 5:
print "Usage: python IndexTuningDemo.py <numDocs> <mergeFactor> <maxMergeDocs> <maxBufferedDocs>"
return
docsInIndex = int(argv[1])
# create an index called 'index-dir' in a temp directory
indexDir = os.path.join(System.getProperty('java.io.tmpdir', 'tmp'),
'index-dir')
dir = FSDirectory.getDirectory(indexDir, True)
analyzer = SimpleAnalyzer()
writer = IndexWriter(dir, analyzer, True)
# set variables that affect speed of indexing
writer.setMergeFactor(int(argv[2]))
writer.setMaxMergeDocs(int(argv[3]))
writer.setMaxBufferedDocs(int(argv[4]))
# writer.infoStream = System.out
print "Merge factor: ", writer.getMergeFactor()
print "Max merge docs:", writer.getMaxMergeDocs()
print "Max buffered docs:", writer.getMaxBufferedDocs()
start = time()
for i in xrange(docsInIndex):
doc = Document()
doc.add(
Field("fieldname", "Bibamus", Field.Store.YES,
Field.Index.TOKENIZED))
writer.addDocument(doc)
writer.close()
print "Time: ", timedelta(seconds=time() - start)
def setUp(self):
indexDir = os.path.join(System.getProperty('java.io.tmpdir', 'tmp'),
'index-dir')
self.rmdir(indexDir)
self.dir = SimpleFSDirectory(File(indexDir))
self.addDocuments(self.dir)
def setUp(self):
fsIndexDir = os.path.join(System.getProperty("java.io.tmpdir", "tmp"),
"fs-index")
self.rmdir(fsIndexDir)
self.ramDir = RAMDirectory()
self.fsDir = SimpleFSDirectory(File(fsIndexDir))
def setUp(self):
indexDir = os.path.join(System.getProperty("java.io.tmpdir", "tmp"), "index-dir")
cIndexDir = "%s-compound" % (indexDir)
mIndexDir = "%s-multi" % (indexDir)
self.rmdir(cIndexDir)
self.rmdir(mIndexDir)
self.cDir = SimpleFSDirectory(File(cIndexDir))
self.mDir = SimpleFSDirectory(File(mIndexDir))
def setUp(self):
indexDir = os.path.join(System.getProperty("java.io.tmpdir", "tmp"),
"index-dir")
cIndexDir = "%s-compound" % (indexDir)
mIndexDir = "%s-multi" % (indexDir)
self.rmdir(cIndexDir)
self.rmdir(mIndexDir)
self.cDir = SimpleFSDirectory(File(cIndexDir))
self.mDir = SimpleFSDirectory(File(mIndexDir))
def index(self):
dirPath = os.path.join(System.getProperty("java.io.tmpdir", "tmp"),
"verbose-index")
dir = FSDirectory.getDirectory(dirPath, True)
writer = IndexWriter(dir, SimpleAnalyzer(), True)
writer.setInfoStream(System.out)
for i in xrange(100):
doc = Document()
doc.add(Field("keyword", "goober",
Field.Store.YES, Field.Index.UN_TOKENIZED))
writer.addDocument(doc)
writer.optimize()
writer.close()
def main(cls, argv):
indexDir = System.getProperty("index.dir")
directory = SimpleFSDirectory(File(indexDir))
reader = IndexReader.open(directory, True)
blt = BooksLikeThis(reader)
for id in xrange(reader.maxDoc()):
if reader.isDeleted(id):
continue
doc = reader.document(id)
print ''
print doc.get("title").encode('utf-8')
docs = blt.docsLike(id, doc, 10)
if not docs:
print " None like this"
else:
for doc in docs:
print " ->", doc.get("title").encode('utf-8')
def main(cls, argv):
indexDir = System.getProperty("index.dir")
directory = SimpleFSDirectory(File(indexDir))
reader = IndexReader.open(directory, True)
blt = BooksLikeThis(reader)
for id in xrange(reader.maxDoc()):
if reader.isDeleted(id):
continue
doc = reader.document(id)
print ''
print doc.get("title").encode('utf-8')
docs = blt.docsLike(id, doc, 10)
if not docs:
print " None like this"
else:
for doc in docs:
print " ->", doc.get("title").encode('utf-8')
import os, sys, lucene
lucene.initVM()
baseDir = os.path.dirname(os.path.abspath(sys.argv[0]))
sys.path.append(baseDir)
from lia.advsearching.BooksLikeThis import BooksLikeThis
from lucene import System
System.setProperty("index.dir", os.path.join(baseDir, "index"))
BooksLikeThis.main(sys.argv)
def setUp(self):
indexDir = os.path.join(System.getProperty("java.io.tmpdir", "tmp"),
"index-dir")
self.dir = SimpleFSDirectory(File(indexDir))
import os, sys, unittest, lucene
lucene.initVM()
baseDir = os.path.dirname(os.path.abspath(sys.argv[0]))
sys.path.append(baseDir)
import lia.searching.TermRangeQueryTest
from lucene import System
System.setProperty("index.dir", os.path.join(baseDir, 'index'))
unittest.main(lia.searching.TermRangeQueryTest)
def __init__(self, *args):
super(LiaTestCase, self).__init__(*args)
self.indexDir = System.getProperty("index.dir")
def __init__(self, *args):
super(LiaTestCase, self).__init__(*args)
self.indexDir = System.getProperty("index.dir")