Created
October 5, 2009 10:35
-
-
Save dopuskh3/202042 to your computer and use it in GitHub Desktop.
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
#!/usr/bin/env python2.5 | |
# vim:set fileencoding=utf-8 | |
import os | |
import sys | |
import tagpy | |
from lucene import \ | |
Document, IndexSearcher, FSDirectory, MultiFieldQueryParser, QueryParser, StandardAnalyzer, IndexWriter, \ | |
StringReader, IndexReader, MoreLikeThis, Term, TermQuery, BooleanQuery,BooleanClause , Field, initVM, CLASSPATH | |
def indexFilesFromPath(dir, idxPath): | |
initVM(CLASSPATH) | |
writer = IndexWriter(idxPath, StandardAnalyzer(), True) | |
count = 1 | |
for root, dirs, files in os.walk(dir): | |
for file in files: | |
#print "- "+str(root)+" "+file | |
sfx = file[-3:] | |
if sfx.lower() not in [ "mp3","mp4", "ogg", "flac" ]: | |
continue | |
filepath = os.path.join(root, file) | |
try: | |
doc = Document() | |
f = tagpy.FileRef(filepath) | |
title = unicode(f.tag().title) | |
artist = unicode(f.tag().artist) | |
album = unicode(f.tag().album) | |
genre = unicode(f.tag().genre) | |
path = unicode(filepath) | |
doc.add(Field("title", title, Field.Store.YES, Field.Index.TOKENIZED)) | |
doc.add(Field("artist", artist, Field.Store.YES, Field.Index.TOKENIZED)) | |
doc.add(Field("album",album, Field.Store.YES, Field.Index.TOKENIZED)) | |
doc.add(Field("genre",genre, Field.Store.YES, Field.Index.TOKENIZED)) | |
doc.add(Field("all", album + u" " + artist + u" " + title, Field.Store.YES, Field.Index.TOKENIZED)) | |
doc.add(Field("path", path, Field.Store.YES, Field.Index.UN_TOKENIZED)) | |
print "\r %5d files indexed"%count, # (%s/%s/%s)..."%(count, f.tag().artist, f.tag().album. f.tag().title) | |
count+=1 | |
writer.addDocument(doc) | |
except Exception, e: | |
#print str(e) | |
# print "+" | |
continue | |
print "Done %d"%count | |
writer.optimize() | |
writer.close() | |
def search( searchRequest, idxPath): | |
initVM(CLASSPATH) | |
fsDir = FSDirectory.getDirectory(idxPath, False) | |
searcher = IndexSearcher(fsDir) | |
language = StandardAnalyzer() | |
queryp = QueryParser('all', language) | |
query = queryp.parse(searchRequest) # "title", language) | |
hits = searcher.search(query) | |
print "# Found %d hits for %s"%(len(hits), searchRequest) | |
for i in range(0, hits.length()): | |
doc = hits.doc(i) | |
#print u"# %s - %s - %s"%(doc.getField('artist'), doc.getField('album'), doc.getField('title')) | |
print u"%s"%unicode(doc.getField('path').stringValue()) | |
if __name__ == "__main__": | |
if sys.argv[1] == "index": | |
indexFilesFromPath(sys.argv[2], sys.argv[3]) | |
elif sys.argv[1] == "search": | |
search(sys.argv[2], sys.argv[3]) | |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment