def addDocuments(self, dir, isCompound):
writer = IndexWriter(dir, SimpleAnalyzer(), True,
IndexWriter.MaxFieldLength.LIMITED)
writer.setUseCompoundFile(isCompound)
# change to adjust performance of indexing with FSDirectory
# writer.mergeFactor = writer.mergeFactor
# writer.maxMergeDocs = writer.maxMergeDocs
# writer.minMergeDocs = writer.minMergeDocs
for word in self.docs:
doc = Document()
doc.add(Field("keyword", word,
Field.Store.YES, Field.Index.NOT_ANALYZED))
doc.add(Field("unindexed", word,
Field.Store.YES, Field.Index.NO))
doc.add(Field("unstored", word,
Field.Store.NO, Field.Index.ANALYZED))
doc.add(Field("text", word,
Field.Store.YES, Field.Index.ANALYZED))
writer.addDocument(doc)
writer.optimize()
writer.close()
def commitIndexWriter(self, writer):
directory = writer.getDirectory()
writer.close()
dbDirectory = self.getDirectory()
dbWriter = IndexWriter(dbDirectory, StandardAnalyzer(), False)
dbWriter.setUseCompoundFile(False)
dbWriter.addIndexes([directory])
directory.close()
dbWriter.close()
dbDirectory.close()
def commitIndexWriter(self, writer):
directory = writer.getDirectory()
writer.close()
dbDirectory = self.getDirectory()
dbWriter = IndexWriter(dbDirectory, StandardAnalyzer(), False)
dbWriter.setUseCompoundFile(False)
dbWriter.addIndexes([directory])
directory.close()
dbWriter.close()
dbDirectory.close()
def index(cls, indexDir, dataDir):
if not (os.path.exists(dataDir) and os.path.isdir(dataDir)):
raise IOError, "%s does not exist or is not a directory" % (dataDir)
writer = IndexWriter(indexDir, StandardAnalyzer(), True, IndexWriter.MaxFieldLength.UNLIMITED)
writer.setUseCompoundFile(False)
numIndexed = cls.indexDirectory(writer, dataDir)
writer.optimize()
writer.close()
return numIndexed
def createIndex(cls, dataDir, indexDir, useCompound):
indexDir = SimpleFSDirectory(File(indexDir))
writer = IndexWriter(indexDir,
StandardAnalyzer(Version.LUCENE_CURRENT), True,
IndexWriter.MaxFieldLength.UNLIMITED)
writer.setUseCompoundFile(useCompound)
for dir, dirnames, filenames in os.walk(dataDir):
for filename in filenames:
if filename.endswith('.properties'):
cls.indexFile(writer, os.path.join(dir, filename), dataDir)
writer.optimize()
writer.close()
def createIndex(cls, dataDir, indexDir, useCompound):
indexDir = SimpleFSDirectory(File(indexDir))
writer = IndexWriter(
indexDir, StandardAnalyzer(Version.LUCENE_CURRENT), True, IndexWriter.MaxFieldLength.UNLIMITED
)
writer.setUseCompoundFile(useCompound)
for dir, dirnames, filenames in os.walk(dataDir):
for filename in filenames:
if filename.endswith(".properties"):
cls.indexFile(writer, os.path.join(dir, filename), dataDir)
writer.optimize()
writer.close()
def index(cls, indexDir, dataDir):
if not (os.path.exists(dataDir) and os.path.isdir(dataDir)):
raise IOError, "%s does not exist or is not a directory" %(dataDir)
dir = SimpleFSDirectory(File(indexDir))
writer = IndexWriter(dir, StandardAnalyzer(Version.LUCENE_CURRENT),
True, IndexWriter.MaxFieldLength.LIMITED)
writer.setUseCompoundFile(False)
cls.indexDirectory(writer, dataDir)
numIndexed = writer.numDocs()
writer.commit()
writer.close()
dir.close()
return numIndexed
def index(cls, indexDir, dataDir):
if not (os.path.exists(dataDir) and os.path.isdir(dataDir)):
raise IOError, "%s does not exist or is not a directory" % (
dataDir)
dir = SimpleFSDirectory(File(indexDir))
writer = IndexWriter(dir, StandardAnalyzer(Version.LUCENE_CURRENT),
True, IndexWriter.MaxFieldLength.LIMITED)
writer.setUseCompoundFile(False)
cls.indexDirectory(writer, dataDir)
numIndexed = writer.numDocs()
writer.optimize()
writer.close()
dir.close()
return numIndexed
def addDocuments(self, dir):
writer = IndexWriter(dir, self.getAnalyzer(), True,
IndexWriter.MaxFieldLength.UNLIMITED)
writer.setUseCompoundFile(self.isCompound())
for i in xrange(len(self.keywords)):
doc = Document()
doc.add(Field("id", self.keywords[i],
Field.Store.YES, Field.Index.NOT_ANALYZED))
doc.add(Field("country", self.unindexed[i],
Field.Store.YES, Field.Index.NO))
doc.add(Field("contents", self.unstored[i],
Field.Store.NO, Field.Index.ANALYZED))
doc.add(Field("city", self.text[i],
Field.Store.YES, Field.Index.ANALYZED))
writer.addDocument(doc)
writer.optimize()
writer.close()
def addDocuments(self, dir):
writer = IndexWriter(dir, self.getAnalyzer(), True,
IndexWriter.MaxFieldLength.UNLIMITED)
writer.setUseCompoundFile(self.isCompound())
for i in xrange(len(self.keywords)):
doc = Document()
doc.add(
Field("id", self.keywords[i], Field.Store.YES,
Field.Index.NOT_ANALYZED))
doc.add(
Field("country", self.unindexed[i], Field.Store.YES,
Field.Index.NO))
doc.add(
Field("contents", self.unstored[i], Field.Store.NO,
Field.Index.ANALYZED))
doc.add(
Field("city", self.text[i], Field.Store.YES,
Field.Index.ANALYZED))
writer.addDocument(doc)
writer.optimize()
writer.close()
def addDocuments(self, dir, isCompound):
writer = IndexWriter(dir, SimpleAnalyzer(), True,
IndexWriter.MaxFieldLength.LIMITED)
writer.setUseCompoundFile(isCompound)
# change to adjust performance of indexing with FSDirectory
# writer.mergeFactor = writer.mergeFactor
# writer.maxMergeDocs = writer.maxMergeDocs
# writer.minMergeDocs = writer.minMergeDocs
for word in self.docs:
doc = Document()
doc.add(
Field("keyword", word, Field.Store.YES,
Field.Index.NOT_ANALYZED))
doc.add(Field("unindexed", word, Field.Store.YES, Field.Index.NO))
doc.add(
Field("unstored", word, Field.Store.NO, Field.Index.ANALYZED))
doc.add(Field("text", word, Field.Store.YES, Field.Index.ANALYZED))
writer.addDocument(doc)
writer.optimize()
writer.close()
def main(cls, argv):
if len(argv) < 2:
print "Usage: BerkeleyDbIndexer <index dir> -create"
return
dbHome = argv[1]
create = len(argv) > 2 and argv[2] == "-create"
if not os.path.exists(dbHome):
os.makedirs(dbHome)
elif create:
for name in os.listdir(dbHome):
if name.startswith('__'):
os.remove(os.path.join(dbHome, name))
env = DBEnv()
env.set_flags(DB_LOG_INMEMORY, 1);
if os.name == 'nt':
env.set_cachesize(0, 0x4000000, 1)
elif os.name == 'posix':
from commands import getstatusoutput
if getstatusoutput('uname') == (0, 'Linux'):
env.set_cachesize(0, 0x4000000, 1)
env.open(dbHome, (DB_CREATE | DB_THREAD |
DB_INIT_MPOOL | DB_INIT_LOCK | DB_INIT_TXN), 0)
index = DB(env)
blocks = DB(env)
txn = None
try:
txn = env.txn_begin(None)
index.open(filename = '__index__', dbtype = DB_BTREE,
flags = DB_CREATE | DB_THREAD, txn = txn)
blocks.open(filename = '__blocks__', dbtype = DB_BTREE,
flags = DB_CREATE | DB_THREAD, txn = txn)
except:
if txn is not None:
txn.abort()
txn = None
raise
else:
txn.commit()
txn = None
try:
txn = env.txn_begin(None)
directory = DbDirectory(txn, index, blocks, 0)
writer = IndexWriter(directory, StandardAnalyzer(), create,
IndexWriter.MaxFieldLength.UNLIMITED)
writer.setUseCompoundFile(False)
doc = Document()
doc.add(Field("contents", "The quick brown fox...",
Field.Store.YES, Field.Index.ANALYZED))
writer.addDocument(doc)
writer.commit()
writer.close()
except:
if txn is not None:
txn.abort()
txn = None
raise
else:
txn.commit()
index.close()
blocks.close()
env.close()
print "Indexing Complete"
def main(cls, argv):
if len(argv) < 2:
print "Usage: BerkeleyDbIndexer <index dir> -create"
return
dbHome = argv[1]
create = len(argv) > 2 and argv[2] == "-create"
if not os.path.exists(dbHome):
os.makedirs(dbHome)
elif create:
for name in os.listdir(dbHome):
if name.startswith('__'):
os.remove(os.path.join(dbHome, name))
env = DBEnv()
env.set_flags(DB_LOG_INMEMORY, 1)
if os.name == 'nt':
env.set_cachesize(0, 0x4000000, 1)
elif os.name == 'posix':
from commands import getstatusoutput
if getstatusoutput('uname') == (0, 'Linux'):
env.set_cachesize(0, 0x4000000, 1)
env.open(dbHome, (DB_CREATE | DB_THREAD | DB_INIT_MPOOL | DB_INIT_LOCK
| DB_INIT_TXN), 0)
index = DB(env)
blocks = DB(env)
txn = None
try:
txn = env.txn_begin(None)
index.open(filename='__index__',
dbtype=DB_BTREE,
flags=DB_CREATE | DB_THREAD,
txn=txn)
blocks.open(filename='__blocks__',
dbtype=DB_BTREE,
flags=DB_CREATE | DB_THREAD,
txn=txn)
except:
if txn is not None:
txn.abort()
txn = None
raise
else:
txn.commit()
txn = None
try:
txn = env.txn_begin(None)
directory = DbDirectory(txn, index, blocks, 0)
writer = IndexWriter(directory, StandardAnalyzer(), create,
IndexWriter.MaxFieldLength.UNLIMITED)
writer.setUseCompoundFile(False)
doc = Document()
doc.add(
Field("contents", "The quick brown fox...", Field.Store.YES,
Field.Index.ANALYZED))
writer.addDocument(doc)
writer.optimize()
writer.close()
except:
if txn is not None:
txn.abort()
txn = None
raise
else:
txn.commit()
index.close()
blocks.close()
env.close()
print "Indexing Complete"
def getIndexWriter(self):
writer = IndexWriter(RAMDirectory(), StandardAnalyzer(), True)
writer.setUseCompoundFile(False)
return writer
def getIndexWriter(self):
writer = IndexWriter(RAMDirectory(), StandardAnalyzer(), True)
writer.setUseCompoundFile(False)
return writer
