You are viewing a plain text version of this content. The canonical link for it is here.
Posted to pylucene-commits@lucene.apache.org by va...@apache.org on 2010/07/12 23:31:53 UTC
svn commit: r963493 - in /lucene/pylucene/branches/python_3/samples:
IndexFiles.py PorterStemmerAnalyzer.py SearchFiles.py TermPositionVector.py
ThreadIndexFiles.py manindex.py mansearch.py
Author: vajda
Date: Mon Jul 12 21:31:52 2010
New Revision: 963493
URL: http://svn.apache.org/viewvc?rev=963493&view=rev
Log:
2to3 on samples
Modified:
lucene/pylucene/branches/python_3/samples/IndexFiles.py
lucene/pylucene/branches/python_3/samples/PorterStemmerAnalyzer.py
lucene/pylucene/branches/python_3/samples/SearchFiles.py
lucene/pylucene/branches/python_3/samples/TermPositionVector.py
lucene/pylucene/branches/python_3/samples/ThreadIndexFiles.py
lucene/pylucene/branches/python_3/samples/manindex.py
lucene/pylucene/branches/python_3/samples/mansearch.py
Modified: lucene/pylucene/branches/python_3/samples/IndexFiles.py
URL: http://svn.apache.org/viewvc/lucene/pylucene/branches/python_3/samples/IndexFiles.py?rev=963493&r1=963492&r2=963493&view=diff
==============================================================================
--- lucene/pylucene/branches/python_3/samples/IndexFiles.py (original)
+++ lucene/pylucene/branches/python_3/samples/IndexFiles.py Mon Jul 12 21:31:52 2010
@@ -36,23 +36,23 @@ class IndexFiles(object):
writer.setMaxFieldLength(1048576)
self.indexDocs(root, writer)
ticker = Ticker()
- print 'optimizing index',
+ print('optimizing index', end=' ')
threading.Thread(target=ticker.run).start()
writer.optimize()
writer.close()
ticker.tick = False
- print 'done'
+ print('done')
def indexDocs(self, root, writer):
for root, dirnames, filenames in os.walk(root):
for filename in filenames:
if not filename.endswith('.txt'):
continue
- print "adding", filename
+ print("adding", filename)
try:
path = os.path.join(root, filename)
file = open(path)
- contents = unicode(file.read(), 'iso-8859-1')
+ contents = str(file.read(), 'iso-8859-1')
file.close()
doc = lucene.Document()
doc.add(lucene.Field("name", filename,
@@ -66,21 +66,21 @@ class IndexFiles(object):
lucene.Field.Store.NO,
lucene.Field.Index.ANALYZED))
else:
- print "warning: no content in %s" % filename
+ print("warning: no content in %s" % filename)
writer.addDocument(doc)
- except Exception, e:
- print "Failed in indexDocs:", e
+ except Exception as e:
+ print("Failed in indexDocs:", e)
if __name__ == '__main__':
if len(sys.argv) < 2:
- print IndexFiles.__doc__
+ print(IndexFiles.__doc__)
sys.exit(1)
lucene.initVM()
- print 'lucene', lucene.VERSION
+ print('lucene', lucene.VERSION)
start = datetime.now()
try:
IndexFiles(sys.argv[1], "index", lucene.StandardAnalyzer(lucene.Version.LUCENE_CURRENT))
end = datetime.now()
- print end - start
- except Exception, e:
- print "Failed: ", e
+ print(end - start)
+ except Exception as e:
+ print("Failed: ", e)
Modified: lucene/pylucene/branches/python_3/samples/PorterStemmerAnalyzer.py
URL: http://svn.apache.org/viewvc/lucene/pylucene/branches/python_3/samples/PorterStemmerAnalyzer.py?rev=963493&r1=963492&r2=963493&view=diff
==============================================================================
--- lucene/pylucene/branches/python_3/samples/PorterStemmerAnalyzer.py (original)
+++ lucene/pylucene/branches/python_3/samples/PorterStemmerAnalyzer.py Mon Jul 12 21:31:52 2010
@@ -47,14 +47,14 @@ class PorterStemmerAnalyzer(PythonAnalyz
if __name__ == '__main__':
if len(sys.argv) < 2:
- print IndexFiles.__doc__
+ print(IndexFiles.__doc__)
sys.exit(1)
initVM()
- print 'lucene', VERSION
+ print('lucene', VERSION)
start = datetime.now()
try:
IndexFiles(sys.argv[1], "index", PorterStemmerAnalyzer())
end = datetime.now()
- print end - start
- except Exception, e:
- print "Failed: ", e
+ print(end - start)
+ except Exception as e:
+ print("Failed: ", e)
Modified: lucene/pylucene/branches/python_3/samples/SearchFiles.py
URL: http://svn.apache.org/viewvc/lucene/pylucene/branches/python_3/samples/SearchFiles.py?rev=963493&r1=963492&r2=963493&view=diff
==============================================================================
--- lucene/pylucene/branches/python_3/samples/SearchFiles.py (original)
+++ lucene/pylucene/branches/python_3/samples/SearchFiles.py Mon Jul 12 21:31:52 2010
@@ -15,28 +15,28 @@ some cases.
"""
def run(searcher, analyzer):
while True:
- print
- print "Hit enter with no input to quit."
- command = raw_input("Query:")
+ print()
+ print("Hit enter with no input to quit.")
+ command = input("Query:")
if command == '':
return
- print
- print "Searching for:", command
+ print()
+ print("Searching for:", command)
query = QueryParser(Version.LUCENE_CURRENT, "contents",
analyzer).parse(command)
scoreDocs = searcher.search(query, 50).scoreDocs
- print "%s total matching documents." % len(scoreDocs)
+ print("%s total matching documents." % len(scoreDocs))
for scoreDoc in scoreDocs:
doc = searcher.doc(scoreDoc.doc)
- print 'path:', doc.get("path"), 'name:', doc.get("name")
+ print('path:', doc.get("path"), 'name:', doc.get("name"))
if __name__ == '__main__':
STORE_DIR = "index"
initVM()
- print 'lucene', VERSION
+ print('lucene', VERSION)
directory = SimpleFSDirectory(File(STORE_DIR))
searcher = IndexSearcher(directory, True)
analyzer = StandardAnalyzer(Version.LUCENE_CURRENT)
Modified: lucene/pylucene/branches/python_3/samples/TermPositionVector.py
URL: http://svn.apache.org/viewvc/lucene/pylucene/branches/python_3/samples/TermPositionVector.py?rev=963493&r1=963492&r2=963493&view=diff
==============================================================================
--- lucene/pylucene/branches/python_3/samples/TermPositionVector.py (original)
+++ lucene/pylucene/branches/python_3/samples/TermPositionVector.py Mon Jul 12 21:31:52 2010
@@ -22,16 +22,16 @@ iwriter.close()
ireader = IndexReader.open(directory, True)
tpv = TermPositionVector.cast_(ireader.getTermFreqVector(0, 'fieldname'))
-for (t,f,i) in zip(tpv.getTerms(),tpv.getTermFrequencies(),xrange(100000)):
- print 'term %s' % t
- print ' freq: %i' % f
+for (t,f,i) in zip(tpv.getTerms(),tpv.getTermFrequencies(),range(100000)):
+ print('term %s' % t)
+ print(' freq: %i' % f)
try:
- print ' pos: ' + str([p for p in tpv.getTermPositions(i)])
+ print(' pos: ' + str([p for p in tpv.getTermPositions(i)]))
except:
- print ' no pos'
+ print(' no pos')
try:
- print ' off: ' + \
+ print(' off: ' + \
str(["%i-%i" % (o.getStartOffset(), o.getEndOffset())
- for o in tpv.getOffsets(i)])
+ for o in tpv.getOffsets(i)]))
except:
- print ' no offsets'
+ print(' no offsets')
Modified: lucene/pylucene/branches/python_3/samples/ThreadIndexFiles.py
URL: http://svn.apache.org/viewvc/lucene/pylucene/branches/python_3/samples/ThreadIndexFiles.py?rev=963493&r1=963492&r2=963493&view=diff
==============================================================================
--- lucene/pylucene/branches/python_3/samples/ThreadIndexFiles.py (original)
+++ lucene/pylucene/branches/python_3/samples/ThreadIndexFiles.py Mon Jul 12 21:31:52 2010
@@ -23,10 +23,10 @@ from IndexFiles import IndexFiles
if __name__ == '__main__':
if len(sys.argv) < 2:
- print IndexFiles.__doc__
+ print(IndexFiles.__doc__)
sys.exit(1)
env=initVM()
- print 'lucene', VERSION
+ print('lucene', VERSION)
def fn():
env.attachCurrentThread()
@@ -34,6 +34,6 @@ if __name__ == '__main__':
IndexFiles(sys.argv[1], "index",
StandardAnalyzer(Version.LUCENE_CURRENT))
end = datetime.now()
- print end - start
+ print(end - start)
threading.Thread(target=fn).start()
Modified: lucene/pylucene/branches/python_3/samples/manindex.py
URL: http://svn.apache.org/viewvc/lucene/pylucene/branches/python_3/samples/manindex.py?rev=963493&r1=963492&r2=963493&view=diff
==============================================================================
--- lucene/pylucene/branches/python_3/samples/manindex.py (original)
+++ lucene/pylucene/branches/python_3/samples/manindex.py Mon Jul 12 21:31:52 2010
@@ -34,7 +34,7 @@ def indexDirectory(dir):
def indexFile(dir,filename):
path = os.path.join(dir, filename)
- print " File: ", filename
+ print(" File: ", filename)
if filename.endswith('.gz'):
child = Popen('gunzip -c ' + path + ' | groff -t -e -E -mandoc -Tascii | col -bx', shell=True, stdout=PIPE, cwd=os.path.dirname(dir)).stdout
@@ -47,7 +47,7 @@ def indexFile(dir,filename):
data = child.read()
err = child.close()
if err:
- raise RuntimeError, '%s failed with exit code %d' %(command, err)
+ raise RuntimeError('%s failed with exit code %d' %(command, err))
matches = re.search('^NAME$(.*?)^\S', data,
re.MULTILINE | re.DOTALL)
@@ -81,7 +81,7 @@ def indexFile(dir,filename):
if __name__ == '__main__':
if len(sys.argv) != 2:
- print "Usage: python manindex.py <index dir>"
+ print("Usage: python manindex.py <index dir>")
else:
initVM()
@@ -91,7 +91,7 @@ if __name__ == '__main__':
IndexWriter.MaxFieldLength.LIMITED)
manpath = os.environ.get('MANPATH', '/usr/share/man').split(os.pathsep)
for dir in manpath:
- print "Crawling", dir
+ print("Crawling", dir)
for name in os.listdir(dir):
path = os.path.join(dir, name)
if os.path.isdir(path):
Modified: lucene/pylucene/branches/python_3/samples/mansearch.py
URL: http://svn.apache.org/viewvc/lucene/pylucene/branches/python_3/samples/mansearch.py?rev=963493&r1=963492&r2=963493&view=diff
==============================================================================
--- lucene/pylucene/branches/python_3/samples/mansearch.py (original)
+++ lucene/pylucene/branches/python_3/samples/mansearch.py Mon Jul 12 21:31:52 2010
@@ -35,8 +35,8 @@ if __name__ == '__main__':
initVM()
def usage():
- print sys.argv[0], "[--format=<format string>] [--index=<index dir>] [--stats] <query...>"
- print "default index is found from MANDEX environment variable"
+ print(sys.argv[0], "[--format=<format string>] [--index=<index dir>] [--stats] <query...>")
+ print("default index is found from MANDEX environment variable")
try:
options, args = getopt(sys.argv[1:], '', ['format=', 'index=', 'stats'])
@@ -72,10 +72,10 @@ start = datetime.now()
scoreDocs = searcher.search(query, 50).scoreDocs
duration = datetime.now() - start
if stats:
- print >>sys.stderr, "Found %d document(s) (in %s) that matched query '%s':" %(len(scoreDocs), duration, query)
+ print("Found %d document(s) (in %s) that matched query '%s':" %(len(scoreDocs), duration, query), file=sys.stderr)
for scoreDoc in scoreDocs:
doc = searcher.doc(scoreDoc.doc)
table = dict((field.name(), field.stringValue())
for field in doc.getFields())
- print template.substitute(table)
+ print(template.substitute(table))