def add_field_to_document(document,
field_name,
value,
store,
analyzed,
boost=None):
"""
Adds a field to the passed in Lucene document. If the boost kwarg is passed
in the field will be boosted by the specified value.
"""
field = lucene.Field(field_name, value, store, analyzed)
if boost:
field.setBoost(boost)
document.add(field)
def get_word_list(text, is_list=False, field_name = 'fieldname'):
if is_list:
new_text = ""
for i in text:
new_text += i + "\n"
text = new_text
lucene.initVM(lucene.CLASSPATH)
analyzer = lucene.KoreanAnalyzer();
#directory = lucene.FSDirectory.open("/tmp/testindex");
directory = lucene.RAMDirectory()
# writer
writer = lucene.IndexWriter(directory, analyzer)
doc = lucene.Document()
doc.add(lucene.Field(field_name, text, lucene.Field.Store.YES, lucene.Field.Index.ANALYZED));
writer.addDocument(doc);
writer.close();
# get all terms from all index
ireader = lucene.IndexReader.open(directory, False)
term = lucene.Term(field_name, '')
termenum = ireader.terms(term)
term = termenum.term()
i = 0
word_list = []
while term and term.field() == field_name:
i += 1
termDocs = ireader.termDocs(term)
termDocs.next()
#print "[%04d]===> <%s> " % (i, term.text())
#print term.text() + " : " + str(termDocs.freq())
word_list.append({'text': term.text(), 'freq': termDocs.freq()})
term = termenum.next() and termenum.term()
ireader.close();
directory.close();
return word_list
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
try:
path = os.path.join(root, filename)
file = open(path)
contents = file.read().decode('utf8', 'ignore')
file.close()
doc = lucene.Document()
doc.add(
lucene.Field("name", filename, lucene.Field.Store.YES,
lucene.Field.Index.NOT_ANALYZED))
doc.add(
lucene.Field("path", path, lucene.Field.Store.YES,
lucene.Field.Index.NOT_ANALYZED))
if len(contents) > 0:
title = self.getTxtAttribute(contents, 'Title')
author = self.getTxtAttribute(contents, 'Author')
language = self.getTxtAttribute(contents, 'Language')
doc.add(
lucene.Field("title", title,
lucene.Field.Store.YES,
lucene.Field.Index.ANALYZED))
doc.add(
lucene.Field("author", author,
lucene.Field.Store.YES,
lucene.Field.Index.ANALYZED))
doc.add(
lucene.Field("language", language,
lucene.Field.Store.YES,
lucene.Field.Index.ANALYZED))
doc.add(
lucene.Field("contents", contents,
lucene.Field.Store.NO,
lucene.Field.Index.ANALYZED))
else:
print "warning: no content in %s" % filename
writer.addDocument(doc)
except Exception, e:
print "Failed in indexDocs:", e
def index_review_request(self, writer, request):
if lucene_is_2x:
lucene_tokenized = lucene.Field.Index.TOKENIZED
lucene_un_tokenized = lucene.Field.Index.UN_TOKENIZED
elif lucene_is_3x:
lucene_tokenized = lucene.Field.Index.ANALYZED
lucene_un_tokenized = lucene.Field.Index.NOT_ANALYZED
else:
assert False
# There are several fields we want to make available to users.
# We index them individually, but also create a big hunk of text
# to use for the default field, so people can just type in a
# string and get results.
doc = lucene.Document()
doc.add(lucene.Field('id', str(request.id),
lucene.Field.Store.YES,
lucene.Field.Index.NO))
doc.add(lucene.Field('summary', request.summary,
lucene.Field.Store.NO,
lucene_tokenized))
if request.changenum:
doc.add(lucene.Field('changenum',
unicode(request.changenum),
lucene.Field.Store.NO,
lucene_tokenized))
# Remove commas, since lucene won't tokenize it right with them
bugs = ' '.join(request.bugs_closed.split(','))
doc.add(lucene.Field('bug', bugs,
lucene.Field.Store.NO,
lucene_tokenized))
name = ' '.join([request.submitter.username,
request.submitter.get_full_name()])
doc.add(lucene.Field('author', name,
lucene.Field.Store.NO,
lucene_tokenized))
doc.add(lucene.Field('username', request.submitter.username,
lucene.Field.Store.NO,
lucene_un_tokenized))
# FIXME: index reviews
# FIXME: index dates
files = []
if request.diffset_history:
for diffset in request.diffset_history.diffsets.all():
for filediff in diffset.files.all():
if filediff.source_file:
files.append(filediff.source_file)
if filediff.dest_file:
files.append(filediff.dest_file)
aggregate_files = '\n'.join(set(files))
# FIXME: this tokenization doesn't let people search for files
# in a really natural way. It'll split on '/' which handles the
# majority case, but it'd be nice to be able to drill down
# (main.cc, vmuiLinux/main.cc, and player/linux/main.cc)
doc.add(lucene.Field('file', aggregate_files,
lucene.Field.Store.NO,
lucene_tokenized))
text = '\n'.join([request.summary,
request.description,
unicode(request.changenum),
request.testing_done,
bugs,
name,
aggregate_files])
doc.add(lucene.Field('text', text,
lucene.Field.Store.NO,
lucene_tokenized))
writer.addDocument(doc)
def UpdateIndex(self):
# 인덱스를 최신 내용으로 갱신
writer = lucene.IndexWriter(self.indexDir, self.analyzer, True,
lucene.IndexWriter.MaxFieldLength(512))
try:
# DB에서 내용 가져오기
for row in self.rows:
doc = lucene.Document()
doc.add(
lucene.Field("bookUrl", row[0], lucene.Field.Store.YES,
lucene.Field.Index.NO))
doc.add(
lucene.Field("thumbUrl", row[1], lucene.Field.Store.YES,
lucene.Field.Index.NO))
doc.add(
lucene.Field("price", row[2], lucene.Field.Store.YES,
lucene.Field.Index.NO))
doc.add(
lucene.Field("title", row[3], lucene.Field.Store.YES,
lucene.Field.Index.ANALYZED))
doc.add(
lucene.Field("subTitle", row[4], lucene.Field.Store.YES,
lucene.Field.Index.NO))
doc.add(
lucene.Field("author", row[5], lucene.Field.Store.YES,
lucene.Field.Index.ANALYZED))
doc.add(
lucene.Field("publisher", row[6], lucene.Field.Store.YES,
lucene.Field.Index.ANALYZED))
doc.add(
lucene.Field("publishDate", row[7], lucene.Field.Store.YES,
lucene.Field.Index.NO))
doc.add(
lucene.Field("offcode", row[8], lucene.Field.Store.YES,
lucene.Field.Index.ANALYZED))
date = str(row[9]).split('-')
date = ''.join(date)
print 'regDate : ' + date + ' ' + str(type(date))
doc.add(
lucene.Field("regDate", date, lucene.Field.Store.YES,
lucene.Field.Index.ANALYZED))
date = str(row[10]).split('-')
date = ''.join(date)
print 'updateDate : ' + date
doc.add(
lucene.Field("updateDate", date, lucene.Field.Store.YES,
lucene.Field.Index.ANALYZED))
writer.addDocument(doc)
except Exception, e:
print "Failed in adding index : %s" % e
exit(1)
def __makeUnStoredField(self, fieldname, fielddata):
return lucene.Field(fieldname, fielddata, lucene.Field.Store.NO,
lucene.Field.Index.TOKENIZED)
def __makeUnIndexedField(self, fieldname, fielddata):
return lucene.Field(fieldname, fielddata, lucene.Field.Store.YES,
lucene.Field.Index.NO)
def __makeKeywordField(self, fieldname, fielddata):
return lucene.Field(fieldname, fielddata, lucene.Field.Store.YES,
lucene.Field.Index.UN_TOKENIZED)
lucene.initVM()
print("lucene version is:", lucene.VERSION)
# Get the analyzer
analyzer = lucene.StandardAnalyzer(lucene.Version.LUCENE_CURRENT)
# Get index storage
store = lucene.SimpleFSDirectory(lucene.File(INDEX_DIR))
# Get index writer
writer = lucene.IndexWriter(store, analyzer, True,
lucene.IndexWriter.MaxFieldLength.LIMITED)
try:
# create a document that would we added to the index
doc = lucene.Document()
# Add a field to this document
field = lucene.Field("titlendia", lucene.Field.Store.YES,
lucene.Field.Index.ANALYZED)
# Add this field to the document
doc.add(field)
# Add the document to the index
writer.addDocument(doc)
except Exception as e:
print("Failed in indexDocs:", e)
def indexDocs(self, root, writer):
t = open('index.txt', "r")
while True:
line = t.readline()
if line:
try:
line = line.strip().split()
url = line[0]
doc_name = line[1]
print "adding", url
path = os.path.join(root, doc_name)
f = open(path)
tmp = f.read() #str
f.close()
try:
domain = get_tld(url)
except:
domain = "Unknown"
print domain
charset = (chardet.detect(tmp))['encoding']
if charset==None:
charset = 'utf-8'
#print charset
#contents = unicode(tmp, charset)
contents = tmp.decode(charset, 'ignore')
soup = BeautifulSoup(contents)
try:
title = soup.title.text
tmp = str(title).replace('\n','')
title = tmp.decode('utf-8')
except:
title = "None"
print title
contents = soup.get_text()
contents = " ".join(jieba.cut(contents))
#print contents
doc = lucene.Document()
doc.add(lucene.Field("name", doc_name,
lucene.Field.Store.YES,
lucene.Field.Index.NOT_ANALYZED))
doc.add(lucene.Field("path", path,
lucene.Field.Store.YES,
lucene.Field.Index.NOT_ANALYZED))
doc.add(lucene.Field("url", url,
lucene.Field.Store.YES,
lucene.Field.Index.NOT_ANALYZED))
doc.add(lucene.Field("title", title,
lucene.Field.Store.YES,
lucene.Field.Index.NOT_ANALYZED))
doc.add(lucene.Field("site", domain,
lucene.Field.Store.YES,
lucene.Field.Index.ANALYZED))
if len(contents) > 0:
doc.add(lucene.Field("contents", contents,
lucene.Field.Store.NO,
lucene.Field.Index.ANALYZED))
else:
print "warning: no content in %s" % doc_name
writer.addDocument(doc) #IndexWriter调用函数addDocument将索引写到索引文件夹中
except Exception, e:
print "Failed in indexDocs:", e
else:
break
def indexDocs(self, root, writer):
t = open('index.txt', "r")
while True:
line = t.readline()
if line:
try:
line = line.strip().split()
url = line[0]
doc_name = line[1]
print "adding", url
path = os.path.join(root, doc_name)
f = open(path)
tmp = f.read() #str
f.close()
contents = tmp.decode('gbk', 'ignore')
soup = BeautifulSoup(contents)
try:
title = soup.title.text
tmp = str(title).replace('\n','')
title = tmp.decode('utf-8')
except:
title = "None"
print title
collection = [] #存放imgurl和对应的discription
dic = {}
p_box = soup.find(id='p-box') #处理一开始左上角一大图和下面几张小图
#print p_box.get('id','')
sub_p_box = p_box.div.nextSibling.nextSibling.nextSibling.nextSibling
#print sub_p_box.get('class','')
#print sub_p_box
big_pic = sub_p_box.div.div.div.img
dic['imgurl'] = urlparse.urljoin(url, big_pic.get('src',''))
dic['discription'] = big_pic.get('alt','')
#print dic
collection.append(dic)
small_pic_group = big_pic.parent.nextSibling.nextSibling.div.ul
for i in small_pic_group.findAll('li'):
small_pic = i.img
dic['imgurl'] = urlparse.urljoin(url, small_pic.get('src',''))
dic['discription'] = " ".join(jieba.cut(small_pic.get('alt','')))
#print dic
collection.append(dic)
doc = lucene.Document()
for i in collection:
imgurl = i['imgurl']
discription = i['discription']
doc.add(lucene.Field("imgurl", imgurl,
lucene.Field.Store.YES,
lucene.Field.Index.NOT_ANALYZED))
doc.add(lucene.Field("discription", discription,
lucene.Field.Store.NO,
lucene.Field.Index.ANALYZED))
doc.add(lucene.Field("url", url,
lucene.Field.Store.YES,
lucene.Field.Index.NOT_ANALYZED))
doc.add(lucene.Field("urltitle", title,
lucene.Field.Store.YES,
lucene.Field.Index.NOT_ANALYZED))
writer.addDocument(doc) #IndexWriter调用函数addDocument将索引写到索引文件夹中
print "----------------------------------------------------"
except Exception, e:
print "Failed in indexDocs:", e
else:
break
lucene.initVM()
indexDir = "D:/Downloads/index"
dir_ = lucene.SimpleFSDirectory(lucene.File(indexDir))
analyzer = lucene.StandardAnalyzer(lucene.Version.LUCENE_CURRENT)
writer = lucene.IndexWriter(dir_, analyzer, True,
lucene.IndexWriter.MaxFieldLength(512))
print("Currently there are %d documents in the index..." %
writer.numDocs())
content = (
"Strategische Konzeption, Umsetzung und Betreuung von langfristig " +
"hochwirksamen und messbar erfolgreichen Maßnahmen in Social Media.")
doc = lucene.Document()
doc.add(
lucene.Field("content", content, lucene.Field.Store.YES,
lucene.Field.Index.ANALYZED))
doc.add(
lucene.Field("filePath", "Projekte/bericht.txt",
lucene.Field.Store.YES, lucene.Field.Index.ANALYZED))
writer.addDocument(doc)
content = (
"Design von Marken, Screens und Interfaces sowie Entwicklung von " +
"individuellen Facebook Apps, iPhone Apps und Webauftritten.")
doc = lucene.Document()
doc.add(
lucene.Field("content", content, lucene.Field.Store.YES,
lucene.Field.Index.ANALYZED))
doc.add(
lucene.Field("filePath", "Projekte/implementierung.txt",
lucene.Field.Store.YES, Field.Index.ANALYZED))
