def run(searcher, analyzer, command, urlclick):
if command == '':
return []
res = firstsearch(searcher, analyzer, command)
command = ''.join(my_jieba.cut(command))
command = " ".join(jieba.cut(command, cut_all=True))
if len(res) > 0:
scoreDocs = res
else:
querys = BooleanQuery()
for k in tag:
query = QueryParser(Version.LUCENE_CURRENT, k,
analyzer).parse(command)
if k == 'taste' or k == 'tech':
query.setBoost(0.5)
querys.add(query, BooleanClause.Occur.SHOULD)
scoreDocs = searcher.search(querys, 10000).scoreDocs
swxc_res = findres(command, scoreDocs, searcher)
formatter = SimpleHTMLFormatter("<span style='color:red'>", "</span>")
formatter_name = SimpleHTMLFormatter("<span,style='color:red'>", "</span>")
scorer = QueryScorer(
QueryParser(Version.LUCENE_CURRENT, 'name', analyzer).parse(command))
highlighter1 = Highlighter(formatter_name, scorer)
highlighter2 = Highlighter(
formatter_name,
QueryScorer(
QueryParser(Version.LUCENE_CURRENT, 'content',
analyzer).parse(command)))
highlighter3 = Highlighter(
formatter,
QueryScorer(
QueryParser(Version.LUCENE_CURRENT, 'ingredient',
analyzer).parse(command)))
highlighter4 = Highlighter(
formatter,
QueryScorer(
QueryParser(Version.LUCENE_CURRENT, 'taste',
analyzer).parse(command)))
highlighter5 = Highlighter(
formatter,
QueryScorer(
QueryParser(Version.LUCENE_CURRENT, 'tech',
analyzer).parse(command)))
highlighter6 = Highlighter(
formatter,
QueryScorer(
QueryParser(Version.LUCENE_CURRENT, 'others',
analyzer).parse(command)))
fragmenter = SimpleFragmenter(1000)
highlighter1.setTextFragmenter(fragmenter)
highlighter2.setTextFragmenter(fragmenter)
highlighter3.setTextFragmenter(fragmenter)
highlighter4.setTextFragmenter(fragmenter)
highlighter5.setTextFragmenter(fragmenter)
highlighter6.setTextFragmenter(fragmenter)
results = []
for scoreDoc in scoreDocs:
if (len(scoreDocs) > 200 and
len(scoreDocs) * scoreDoc.score < 2) or scoreDoc.score < 0.002:
continue
doc = searcher.doc(scoreDoc.doc)
highlighterContent = highlighter1.getBestFragment(
analyzer, 'name', doc.get('name'))
highlighterContent2 = highlighter2.getBestFragment(
analyzer, 'content', doc.get('content'))
highlighterContent3 = highlighter3.getBestFragment(
analyzer, 'ingredient', doc.get('ingredient'))
highlighterContent4 = highlighter4.getBestFragment(
analyzer, 'taste', doc.get('taste'))
highlighterContent5 = highlighter5.getBestFragment(
analyzer, 'tech', doc.get('tech'))
highlighterContent6 = highlighter6.getBestFragment(
analyzer, 'others', doc.get('others'))
if highlighterContent:
highlighterContent = highlighterContent.replace(' ', '')
highlighterContent = highlighterContent.replace(',', ' ')
else:
highlighterContent = doc.get('name').replace(' ', '')
if highlighterContent2:
highlighterContent2 = highlighterContent2.replace(' ', '')
highlighterContent2 = highlighterContent2.replace(',', ' ')
else:
highlighterContent2 = doc.get('content').replace(' ', '')
if highlighterContent3:
highlighterContent3 = highlighterContent3.replace(',', '')
else:
highlighterContent3 = (doc.get('ingredient')).replace(',', '')
if highlighterContent4:
pass
else:
highlighterContent4 = doc.get('taste')
if highlighterContent5:
pass
else:
highlighterContent5 = doc.get('tech')
if highlighterContent6:
highlighterContent6 = highlighterContent6.replace(',', '')
else:
highlighterContent6 = (doc.get('others')).replace(',', '')
results.append(
(highlighterContent, doc.get('img'), highlighterContent2,
highlighterContent3, highlighterContent4, highlighterContent5,
highlighterContent6, doc.get('url'), scoreDoc.score))
for i in range(0, min(20, len(results)) - 1):
flag = True
for j in range(0, min(20, len(results)) - i - 1):
if abs(results[j][8] - results[j + 1][8]) < 0.1 and urlclick[
results[j][7]] < urlclick[results[j + 1][7]]:
flag = False
results[j], results[j + 1] = results[j + 1], results[j]
if flag:
break
return results, swxc_res
def run(searcher, analyzer, command, judge):
print "\nSearching for: " + command
# command = unicode(command, 'UTF-8')
if command == '':
return
commands = " ".join(jieba.cut(command)).split()
commands_notseg = command.split()
querys = BooleanQuery()
querys1 = BooleanQuery()
querys2 = BooleanQuery()
for i in commands:
query = QueryParser(Version.LUCENE_CURRENT, "name", analyzer).parse(i)
querys.setBoost(math.sqrt(len(i)))
querys.add(query, BooleanClause.Occur.MUST) #分词匹配
querys1.add(query, BooleanClause.Occur.SHOULD)
scoreDocs = searcher.search(querys, 50).scoreDocs
if len(scoreDocs) == 0:
querys = BooleanQuery()
for i in commands:
for j in i:
query = QueryParser(Version.LUCENE_CURRENT, "not_seg",
analyzer).parse(j)
querys.add(query, BooleanClause.Occur.MUST) #逐字匹配
querys1.add(query, BooleanClause.Occur.SHOULD)
scoreDocs = searcher.search(querys, 50).scoreDocs
for i in commands:
query = QueryParser(Version.LUCENE_CURRENT, "comment",
analyzer).parse(i)
query.setBoost(0.5)
querys2.add(query, BooleanClause.Occur.SHOULD) #评论匹配
if len(commands) > 1:
querys2.add(querys1, BooleanClause.Occur.MUST)
querys2.add(querys, BooleanClause.Occur.SHOULD)
querys = BooleanQuery()
for i in commands_notseg:
query = QueryParser(Version.LUCENE_CURRENT, "type", analyzer).parse(i)
query.setBoost(2)
querys.add(query, BooleanClause.Occur.SHOULD) #标签匹配
if len(commands_notseg) > 1:
querys.add(querys1, BooleanClause.Occur.MUST)
querys2.add(querys, BooleanClause.Occur.SHOULD)
scoreDocs = searcher.search(querys2, 20).scoreDocs
print "%s total matching documents." % len(scoreDocs)
res = []
temp = []
for scoreDoc in scoreDocs:
doc = searcher.doc(scoreDoc.doc)
temp = [
doc.get("org"),
doc.get("type"),
doc.get("price"),
doc.get("imgsrc"),
doc.get('comment_notseg'),
doc.get('ISBN'),
doc.get('ID')
]
print temp
for i in SearchFiles.main(doc.get("org")):
temp.append(i)
res.append(temp)
res1 = []
if judge == True:
for i in range(len(res)):
temp = res[i]
tempres = main(temp[0], False) #迭代寻找相似书籍
if len(tempres) >= 4:
for j in tempres[1:4]:
temp.append(j)
elif len(tempres) == 1:
for j in range(3):
temp.append(tempres[0])
else:
for j in range(1, len(tempres)):
temp.append(tempres[j])
for j in range(len(tempres), 4):
temp.append(tempres[-1])
res1.append(temp)
return res1
def superSearch(command, command_dict, urlclick):
vm_env = lucene.getVMEnv()
vm_env.attachCurrentThread()
directory = SimpleFSDirectory(File('index2.3'))
print "run super search..."
searcher = IndexSearcher(DirectoryReader.open(directory))
analyzer = SimpleAnalyzer(Version.LUCENE_CURRENT)
command = ' '.join(jieba.cut_for_search(command))
querys = BooleanQuery()
if command:
query = QueryParser(Version.LUCENE_CURRENT, 'nameforsearch',
analyzer).parse(command)
querys.add(query, BooleanClause.Occur.SHOULD)
for k, v in (command_dict[0]).items():
query = QueryParser(Version.LUCENE_CURRENT, k, analyzer).parse(v)
query.setBoost(0.1)
querys.add(query, BooleanClause.Occur.MUST)
for k, v in (command_dict[1]).items():
query = QueryParser(Version.LUCENE_CURRENT, k, analyzer).parse(v)
querys.add(query, BooleanClause.Occur.MUST_NOT)
scoreDocs = searcher.search(querys, 10000).scoreDocs
swxc_res = findres(command + ' ' + command_dict[0].get("ingredient", ''),
scoreDocs, searcher)
formatter = SimpleHTMLFormatter("<span style='color:red'>", "</span>")
formatter_name = SimpleHTMLFormatter("<span,style='color:red'>", "</span>")
if command:
scorer = QueryScorer(
QueryParser(Version.LUCENE_CURRENT, 'name',
analyzer).parse(command))
highlighters = [Highlighter(formatter_name, scorer)]
else:
highlighters = ['']
if command_dict[0].get('ingredient'):
highlighters.append(
Highlighter(
formatter,
QueryScorer(
QueryParser(Version.LUCENE_CURRENT, 'ingredient',
analyzer).parse(
command_dict[0]['ingredient']))))
else:
highlighters.append('')
if command_dict[0].get('taste'):
highlighters.append(
Highlighter(
formatter,
QueryScorer(
QueryParser(Version.LUCENE_CURRENT, 'taste',
analyzer).parse(command_dict[0]['taste']))))
else:
highlighters.append('')
if command_dict[0].get('tech'):
highlighters.append(
Highlighter(
formatter,
QueryScorer(
QueryParser(Version.LUCENE_CURRENT, 'tech',
analyzer).parse(command_dict[0]['tech']))))
else:
highlighters.append('')
fragmenter = SimpleFragmenter(1000)
for h in highlighters:
if h:
h.setTextFragmenter(fragmenter)
results = []
for scoreDoc in scoreDocs:
if (scoreDoc.score * len(scoreDocs) < 200
and len(scoreDocs) > 200) or scoreDoc.score < 0.1:
continue
doc = searcher.doc(scoreDoc.doc)
if command:
highlighterContent = highlighters[0].getBestFragment(
analyzer, 'name', doc.get('name'))
else:
highlighterContent = ''
if highlighters[1]:
highlighterContent2 = highlighters[1].getBestFragment(
analyzer, 'ingredient', doc.get('ingredient'))
else:
highlighterContent2 = ''
if highlighters[2]:
highlighterContent3 = highlighters[2].getBestFragment(
analyzer, 'taste', doc.get('taste'))
else:
highlighterContent3 = ''
if highlighters[3]:
highlighterContent4 = highlighters[3].getBestFragment(
analyzer, 'tech', doc.get('tech'))
else:
highlighterContent4 = ''
if highlighterContent:
highlighterContent = highlighterContent.replace(' ', '')
highlighterContent = highlighterContent.replace(',', ' ')
else:
highlighterContent = doc.get('name').replace(' ', '')
if highlighterContent2:
highlighterContent2 = highlighterContent2.replace(',', '')
else:
highlighterContent2 = (doc.get('ingredient')).replace(',', '')
if highlighterContent3:
pass
else:
highlighterContent3 = doc.get('taste')
if highlighterContent4:
pass
else:
highlighterContent4 = doc.get('tech')
results.append(
(highlighterContent, doc.get('img'),
doc.get('content').replace(' ', ''),
highlighterContent2, highlighterContent3, highlighterContent4,
doc.get('others').replace(',',
''), doc.get('url'), scoreDoc.score))
for i in range(0, min(20, len(results)) - 1):
flag = True
for j in range(0, min(20, len(results)) - i - 1):
if abs(results[j][8] - results[j + 1][8]) < 0.1 and urlclick[
results[j][7]] < urlclick[results[j + 1][7]]:
flag = False
results[j], results[j + 1] = results[j + 1], results[j]
if flag:
break
return results, swxc_res
