python2.6 +jcc + pylucen (lucene2.4)安装

redskywy

附件中的两个文件是 mingw32下面编译好的 jcc和pylucen的安装包
python通过 jni调用 lucene api感觉还比较好的,
jre1.6.0.3

xiaoyu9805119

期待楼主分享点实例出来看看

redskywy

下面的代码是 pylucene sample的代码 创建索引 import sys, os, lucene, threading, time from datetime import datetime """ This class is loosely based on the Lucene (java implementation) demo class org.apache.lucene.demo.IndexFiles.  It will take a directory as an argument and will index all of the files in that directory and downward recursively. It will index on the file path, the file name and the file contents.  The resulting Lucene index will be placed in the current directory and called 'index'. """ class Ticker(object):     def __init__(self):         self.tick = True     def run(self):         while self.tick:             sys.stdout.write('.')             sys.stdout.flush()             time.sleep(1.0) class IndexFiles(object):     """Usage: python IndexFiles <doc_directory>"""     def __init__(self, root, storeDir, analyzer):         if not os.path.exists(storeDir):             os.mkdir(storeDir)         store = lucene.FSDirectory.getDirectory(storeDir, True)         writer = lucene.IndexWriter(store, analyzer, True)         writer.setMaxFieldLength(1048576)         self.indexDocs(root, writer)         ticker = Ticker()         print 'optimizing index',         threading.Thread(target=ticker.run).start()         writer.optimize()         writer.close()         ticker.tick = False         print 'done'     def indexDocs(self, root, writer):         for root, dirnames, filenames in os.walk(root):             for filename in filenames:                 if not filename.endswith('.txt') and not filename.endswith(".py"):                     continue                 print "adding", filename                 try:                     path = os.path.join(root, filename)                     file = open(path)                     contents = unicode(file.read(), 'iso-8859-1')                     file.close()                     doc = lucene.Document()                     doc.add(lucene.Field("name", filename,                                          lucene.Field.Store.YES,                                          lucene.Field.Index.UN_TOKENIZED))                     doc.add(lucene.Field("path", path,                                          lucene.Field.Store.YES,                                          lucene.Field.Index.UN_TOKENIZED))                     if len(contents) > 0:                         doc.add(lucene.Field("contents", contents,                                              lucene.Field.Store.NO,                                              lucene.Field.Index.TOKENIZED))                     else:                         print "warning: no content in %s" % filename                     writer.addDocument(doc)                 except Exception, e:                     print "Failed in indexDocs:", e if __name__ == '__main__':     sys.argv.append(".")     if len(sys.argv) < 2:         print IndexFiles.__doc__         sys.exit(1)     lucene.initVM(lucene.CLASSPATH)     print 'lucene', lucene.VERSION     start = datetime.now()     try:         IndexFiles(sys.argv[1], "index", lucene.StandardAnalyzer())         end = datetime.now()         print end - start     except Exception, e:         print "Failed: ", e

redskywy

from lucene import \     QueryParser, IndexSearcher, StandardAnalyzer, FSDirectory, Hit, \     VERSION, initVM, CLASSPATH """ This script is loosely based on the Lucene (java implementation) demo class org.apache.lucene.demo.SearchFiles.  It will prompt for a search query, then it will search the Lucene index in the current directory called 'index' for the search query entered against the 'contents' field.  It will then display the 'path' and 'name' fields for each of the hits it finds in the index.  Note that search.close() is currently commented out because it causes a stack overflow in some cases. """ def run(searcher, analyzer):     while True:         print         print "Hit enter with no input to quit."         command = raw_input("Query:")         if command == '':             return         print         print "Searching for:", command         query = QueryParser("contents", analyzer).parse(command)         hits = searcher.search(query)         print "%s total matching documents." % hits.length()         for hit in hits:             doc = Hit.cast_(hit).getDocument()             print 'path:', doc.get("path"), 'name:', doc.get("name") if __name__ == '__main__':     STORE_DIR = "index"     initVM(CLASSPATH)     print 'lucene', VERSION     directory = FSDirectory.getDirectory(STORE_DIR, False)     searcher = IndexSearcher(directory)     analyzer = StandardAnalyzer()     run(searcher, analyzer)     searcher.close()

linu_z

能分享下mingw win下怎么编译的吗