异度部落格

学习是一种生活态度。

0%

PyLucene学习笔记 文件索引及检索

Posted on In

一、使用 Indexer 建立文本文件索引

这里简化为对某一目录下面的所有后缀为“.py”的文件建立索引。

1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
'''
Created on 2011-11-16

@author: killua
@E-mail:[email protected]
'''
import os

from time import time
from datetime import timedelta
from lucene import \
    IndexWriter, StandardAnalyzer, Document, Field, \
    InputStreamReader, FileInputStream, Version, SimpleFSDirectory, File, \
    initVM, CLASSPATH

class Indexer(object):
    _indexDir = ""
    _dataDir = ""

    def __init__(self, indexDir, dataDir):
        self._indexDir = indexDir
        self._dataDir = dataDir

    def index(self):
        if not (os.path.exists(self._dataDir) and os.path.isdir(self._dataDir)):
            raise IOError, "%s isn't existed or is not a directory" % (self._dataDir)

        dir = SimpleFSDirectory(File(self._indexDir))
        writer = IndexWriter(dir, StandardAnalyzer(Version.LUCENE_CURRENT),
                             True, IndexWriter.MaxFieldLength.LIMITED)
        writer.setUseCompoundFile(False);
        self.indexDirectory(writer, self._dataDir)
        numIndexed = writer.numDocs();
        writer.optimize()
        writer.close()
        dir.close()

        return numIndexed

    def indexDirectory(self, writer, dir):

        for name in os.listdir(dir):
            path = os.path.join(dir, name)
            if os.path.isfile(path):
                if path.endswith('.py'):
                    self.indexFile(writer, path)
            elif os.path.isdir(path):
                self.indexDirectory(writer, path)

    def indexFile(self, writer, path):
        try:
            reader = InputStreamReader(FileInputStream(path), 'UTF-8')
        except IOError, e:
            print 'IOError while opening %s: %s' %(path, e)
        else:
            print 'Indexing', path
            doc = Document()
            doc.add(Field("contents", reader))
            doc.add(Field("path", os.path.abspath(path),
                          Field.Store.YES, Field.Index.NOT_ANALYZED))
            writer.addDocument(doc)
            reader.close()

def main():
    initVM(CLASSPATH)
    indexDir = "./index/"
    dataDir = "/home/killua/Workspace/"
    indexer = Indexer(indexDir, dataDir)

    start = time()
    numIndexed = indexer.index()
    duration = timedelta(seconds=time() - start)
    print "Indexing %s files took %s" %(numIndexed, duration)

if __name__ == "__main__":
    main()

运行结果：

Indexer.py 将在 index 目录下建立一些索引文件，用于对.py 文件建立索引

二、使用 Searcher 检索文件

下面程序中实现了对文件的检索，其中参数 q 是一个表达式，可以理解为检索使用的关键字，如果文件中包含次关键字将被检索出来

1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
'''
Created on 2011-11-17

@author: killua
@E-mail:[email protected]
'''

import os

from time import time
from datetime import timedelta

from lucene import \
     Document, IndexSearcher, FSDirectory, QueryParser, StandardAnalyzer, \
     SimpleFSDirectory, File, Version, initVM, CLASSPATH

class Searcher(object):

    def search(self, indexDir, q):
        fsDir = SimpleFSDirectory(File(indexDir))
        searcher = IndexSearcher(fsDir, True)
        query = QueryParser(Version.LUCENE_CURRENT, "contents",
                            StandardAnalyzer(Version.LUCENE_CURRENT)).parse(q)
        starttime = time()
        hits = searcher.search(query, 50).scoreDocs
        duration = timedelta(seconds=time() - starttime)

        print "Found %d document(s) (in%s) that matched query '%s':" %(len(hits), duration, q)

        for hit in hits:
            doc = searcher.doc(hit.doc)
            print 'path:', doc.get("path")

def main():
    initVM(CLASSPATH)
    indexDir = "./index/"
    q = "Killua"
    searcher = Searcher()
    searcher.search(indexDir, q)

if __name__ == "__main__":
    main()