So common use case of a Search Engine.. Don’t you observe Google highlights the keywords the user searches for? That is what we achieve in this example below
| import whoosh,os | |
| from whoosh import index | |
| import whoosh.index | |
| import whoosh.fields | |
| import whoosh.qparser | |
| import tornado.ioloop | |
| import tornado.web | |
| from whoosh import analysis, fields, formats, query, highlight | |
| class Search(object): | |
| def __init__(self, indexdir, searchstr=None): | |
| self.indexdir = indexdir | |
| self.searchstr = searchstr | |
| def searcher(self): | |
| schema = whoosh.fields.Schema( | |
| path = whoosh.fields.ID(unique=True, stored=True), | |
| title = whoosh.fields.TEXT(stored=True, phrase=False), | |
| content = whoosh.fields.TEXT(stored=True, spelling=True), | |
| tag = whoosh.fields.TEXT(stored=True), | |
| category = whoosh.fields.TEXT(stored=True)) | |
| if not os.path.exists(self.indexdir): | |
| os.mkdir(self.indexdir) | |
| ix = index.create_in(self.indexdir, schema) | |
| writer = ix.writer() | |
| writer.add_document(title=u"Welcome", content=u"This is welcome blog!", | |
| path=u"/welcome", tag=u"Welcome", category=u"Welcome") | |
| writer.add_document(title=u"Python Whoosh", content=u"Whoosh search library in pure Python", | |
| path=u"/whoosh", tag=u"whoosh", category=u"Search") | |
| writer.add_document(title=u"Python Tornado", content=u"Tornado Web Server for real-time web apps", | |
| path=u"/tornado", tag=u"tornado", category=u"Web Server") | |
| writer.add_document(title=u"Python Tornado Async", content=u"Tornado Web Server provides async web requests", | |
| path=u"/tornadoasync", tag=u"async", category=u"Web Server") | |
| writer.add_document(title=u"Python Tornado Templates", content=u"Tornado Web Server has template feature", | |
| path=u"/tornadotemplates", tag=u"templates", category=u"Web Server") | |
| writer.add_document(title=u"Python Tornado", content=u"Tornado Web Server is awesome", | |
| path=u"/tornado", tag=u"great", category=u"Web Server") | |
| writer.commit() | |
| _queryparser = whoosh.qparser.QueryParser('content', schema=schema) | |
| s = ix.searcher() | |
| return s | |
| class Home(tornado.web.RequestHandler): | |
| def get(self): | |
| self.write('It Works!') | |
| class HighLighted(tornado.web.RequestHandler): | |
| def get(self): | |
| self.render('highlighted.html') | |
| def post(self): | |
| from whoosh import qparser | |
| qstring = self.get_argument('qstring') | |
| srch = Search('./indexer') | |
| s = srch.searcher() | |
| results = s.search(query.Term('content', qstring), limit=10) | |
| titles = ''; contents = '' | |
| for hit in results: | |
| titles += hit["title"] + ' ' | |
| contents += hit.highlights("content") + ' ' | |
| self.write('Titles Hit: ' + titles + '<br /> ' + 'Contents Hit: ' + contents) | |
| application = tornado.web.Application([ | |
| (r"/",Home ), | |
| (r"/highlighted", HighLighted ), | |
| ]) | |
| if __name__ == "__main__": | |
| application.listen(7777) | |
| tornado.ioloop.IOLoop.instance().start() |
Search results for highlighted search
