class PyLuceneTestCase(TestCase):
def __init__(self, *args):
super(PyLuceneTestCase, self).__init__(*args)
self.TEST_VERSION = Version.LUCENE_CURRENT
def setUp(self):
self.directory = RAMDirectory()
def tearDown(self):
self.directory.close()
def getWriter(self, directory=None, analyzer=None, open_mode=None):
config = IndexWriterConfig(self.TEST_VERSION,
analyzer or LimitTokenCountAnalyzer(WhitespaceAnalyzer(Version.LUCENE_CURRENT), 10000)
)
config.setOpenMode(open_mode or IndexWriterConfig.OpenMode.CREATE)
return IndexWriter(directory or self.directory, config)
def getSearcher(self, directory=None, reader=None):
if reader is not None:
return IndexSearcher(reader)
return self.getReader(directory=directory)
def getReader(self, directory=None):
return DirectoryReader.open(directory or self.directory)
def testSlurp(self):
fsDirReader = IndexReader.open(self.dir, True)
self.assertEqual(len(self.keywords), fsDirReader.maxDoc())
self.assertEqual(len(self.keywords), fsDirReader.numDocs())
ramDir = RAMDirectory(self.dir)
ramDirReader = IndexReader.open(ramDir, True)
self.assertEqual(fsDirReader.maxDoc(), ramDirReader.maxDoc())
self.assertEqual(fsDirReader.numDocs(), ramDirReader.numDocs())
fsDirReader.close()
ramDir.close()
def testSlurp(self):
fsDirReader = IndexReader.open(self.dir, True)
self.assertEqual(len(self.keywords), fsDirReader.maxDoc())
self.assertEqual(len(self.keywords), fsDirReader.numDocs())
ramDir = RAMDirectory(self.dir)
ramDirReader = IndexReader.open(ramDir, True)
self.assertEqual(fsDirReader.maxDoc(), ramDirReader.maxDoc())
self.assertEqual(fsDirReader.numDocs(), ramDirReader.numDocs())
fsDirReader.close()
ramDir.close()
def setUp(self):
self.directory = RAMDirectory()
writer = IndexWriter(self.directory, WhitespaceAnalyzer(), True,
IndexWriter.MaxFieldLength.UNLIMITED)
# Elwood
document = Document()
document.add(
Field("owner", "elwood", Field.Store.YES,
Field.Index.NOT_ANALYZED))
document.add(
Field("keywords", "elwoods sensitive info", Field.Store.YES,
Field.Index.ANALYZED))
writer.addDocument(document)
# Jake
document = Document()
document.add(
Field("owner", "jake", Field.Store.YES, Field.Index.NOT_ANALYZED))
document.add(
Field("keywords", "jakes sensitive info", Field.Store.YES,
Field.Index.ANALYZED))
writer.addDocument(document)
writer.close()
def setUp(self):
self.directory = RAMDirectory()
self.analyzer = WhitespaceAnalyzer()
writer = IndexWriter(self.directory, self.analyzer, True,
IndexWriter.MaxFieldLength.UNLIMITED)
doc = Document()
doc.add(
Field("f", "the quick brown fox jumps over the lazy dog",
Field.Store.YES, Field.Index.ANALYZED))
writer.addDocument(doc)
doc = Document()
doc.add(
Field("f", "the quick red fox jumps over the sleepy cat",
Field.Store.YES, Field.Index.ANALYZED))
writer.addDocument(doc)
writer.close()
self.searcher = IndexSearcher(self.directory, True)
self.reader = IndexReader.open(self.directory, True)
self.quick = SpanTermQuery(Term("f", "quick"))
self.brown = SpanTermQuery(Term("f", "brown"))
self.red = SpanTermQuery(Term("f", "red"))
self.fox = SpanTermQuery(Term("f", "fox"))
self.lazy = SpanTermQuery(Term("f", "lazy"))
self.sleepy = SpanTermQuery(Term("f", "sleepy"))
self.dog = SpanTermQuery(Term("f", "dog"))
self.cat = SpanTermQuery(Term("f", "cat"))
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):
self.directory = RAMDirectory()
writer = IndexWriter(self.directory, self.porterAnalyzer, True,
IndexWriter.MaxFieldLength.UNLIMITED)
doc = Document()
doc.add(Field("contents",
"The quick brown fox jumps over the lazy dogs",
Field.Store.YES, Field.Index.ANALYZED))
writer.addDocument(doc)
writer.close()
def setUp(self):
animals = [
"aardvark", "beaver", "coati", "dog", "elephant", "frog",
"gila monster", "horse", "iguana", "javelina", "kangaroo", "lemur",
"moose", "nematode", "orca", "python", "quokka", "rat", "scorpion",
"tarantula", "uromastyx", "vicuna", "walrus", "xiphias", "yak",
"zebra"
]
analyzer = WhitespaceAnalyzer()
aTOmDirectory = RAMDirectory()
nTOzDirectory = RAMDirectory()
aTOmWriter = IndexWriter(aTOmDirectory, analyzer, True,
IndexWriter.MaxFieldLength.UNLIMITED)
nTOzWriter = IndexWriter(nTOzDirectory, analyzer, True,
IndexWriter.MaxFieldLength.UNLIMITED)
for animal in animals:
doc = Document()
doc.add(
Field("animal", animal, Field.Store.YES,
Field.Index.NOT_ANALYZED))
if animal[0].lower() < "n":
aTOmWriter.addDocument(doc)
else:
nTOzWriter.addDocument(doc)
aTOmWriter.close()
nTOzWriter.close()
self.searchers = [
IndexSearcher(aTOmDirectory),
IndexSearcher(nTOzDirectory)
]
def setUp(self):
# set up sample document
directory = RAMDirectory()
writer = IndexWriter(directory, WhitespaceAnalyzer(), True,
IndexWriter.MaxFieldLength.UNLIMITED)
doc = Document()
doc.add(
Field("field", "the quick brown fox jumped over the lazy dog",
Field.Store.YES, Field.Index.ANALYZED))
writer.addDocument(doc)
writer.close()
self.searcher = IndexSearcher(directory)
def setUp(self):
self.analyzer = WhitespaceAnalyzer()
self.directory = RAMDirectory()
writer = IndexWriter(self.directory, self.analyzer, True,
IndexWriter.MaxFieldLength.LIMITED)
for i in xrange(1, 501):
doc = Document()
doc.add(Field("id", NumberUtils.pad(i),
Field.Store.YES, Field.Index.NOT_ANALYZED))
writer.addDocument(doc)
writer.close()
def setUp(self):
self.directory = RAMDirectory()
writer = IndexWriter(self.directory, WhitespaceAnalyzer(), True,
IndexWriter.MaxFieldLength.UNLIMITED)
self.addPoint(writer, "El Charro", "restaurant", 1, 2)
self.addPoint(writer, "Cafe Poca Cosa", "restaurant", 5, 9)
self.addPoint(writer, "Los Betos", "restaurant", 9, 6)
self.addPoint(writer, "Nico's Taco Shop", "restaurant", 3, 8)
writer.close()
self.searcher = IndexSearcher(self.directory, True)
self.query = TermQuery(Term("type", "restaurant"))
def setUp(self):
self.directory = RAMDirectory()
writer = IndexWriter(self.directory, SimpleAnalyzer(), True,
IndexWriter.MaxFieldLength.UNLIMITED)
doc = Document()
doc.add(
Field("partnum", "Q36", Field.Store.YES, Field.Index.NOT_ANALYZED))
doc.add(
Field("description", "Illidium Space Modulator", Field.Store.YES,
Field.Index.ANALYZED))
writer.addDocument(doc)
writer.close()
self.searcher = IndexSearcher(self.directory, True)
def someMethod(self):
directory = RAMDirectory()
analyzer = StandardAnalyzer()
writer = IndexWriter(directory, analyzer, True)
doc = Document()
doc.add(Field.Text("title", "This is the title"))
doc.add(Field.UnStored("contents", "...document contents..."))
writer.addDocument(doc)
writer.addDocument(doc, analyzer)
expression = "some query"
query = QueryParser.parse(expression, "contents", analyzer)
parser = QueryParser("contents", analyzer)
query = parser.parseQuery(expression)
def setUp(self):
directory = RAMDirectory()
writer = IndexWriter(directory, WhitespaceAnalyzer(), True,
IndexWriter.MaxFieldLength.UNLIMITED)
doc1 = Document()
doc1.add(
Field("field", "the quick brown fox jumped over the lazy dog",
Field.Store.YES, Field.Index.ANALYZED))
writer.addDocument(doc1)
doc2 = Document()
doc2.add(
Field("field", "the fast fox hopped over the hound",
Field.Store.YES, Field.Index.ANALYZED))
writer.addDocument(doc2)
writer.close()
self.searcher = IndexSearcher(directory, True)
def _createIndex(self, inputDF, colname):
"""
function to create lucene index, iterates over inputDF row
by row, and indexes the relevant column
By default - WhitespaceAnalyzer is used, other Analyzers are also available.
"""
# Create index directory
directory = RAMDirectory()
writer = IndexWriter(directory, WhitespaceAnalyzer(), True,
IndexWriter.MaxFieldLength.LIMITED)
# Inline indexing of column data
inputDF.apply(lambda x: self._addDoc(x[colname], writer), axis=1)
# Optimize, close and return
writer.optimize()
writer.close()
return directory
def getIndexWriter(self):
writer = IndexWriter(RAMDirectory(), StandardAnalyzer(), True)
writer.setUseCompoundFile(False)
return writer
def __init__(self, indexDir):
self.directory = RAMDirectory(SimpleFSDirectory(File(indexDir)))
self.searcher = IndexSearcher(self.directory)
def indexFile(self):
self._th=lucene.initVM()
self._analyzer = StandardAnalyzer(Version.LUCENE_36)
self._dir = RAMDirectory()
self._writer = IndexWriter(self._dir, self._analyzer, True, IndexWriter.MaxFieldLength(25000))
def setUp(self):
self.directory = RAMDirectory()
def setUp(self):
super(ScoreTest, self).setUp()
self.directory = RAMDirectory()