def list_files(self, realpath, path_parts, page) :
path_tuple = tuple(path_parts)
MindIndex.update_entry_index(self.server.dir2doclist, DATA_DIR, realpath)
# get dir doclist
try :
doc_num, page_num, page_idx, doclist = self.server.dir2doclist[path_tuple].get_page(page)
except KeyError :
doc_num = 0
page_num = 0
page_idx = 1
doclist = []
data = '<?xml version="1.0" encoding="GBK"?>'
data += '<entrylist>'
data += '<page><total>%d</total><pages>%d</pages><ipage>%d</ipage></page>' % (doc_num, page_num, page_idx)
for doc in doclist :
data += '<file>'
data += '<rlt_path>%s</rlt_path>' % cgi.escape(doc.rlt_path())
data += '<url_path>%s</url_path>' % cgi.escape(doc.url_path())
data += '<create>%s</create>' % doc.ctime_str()
data += '</file>'
data += '</entrylist>'
self.send_response(200)
self.send_header('Content-type', 'text/xml')
self.send_header('Content-Length', str(len(data)))
self.end_headers()
return StringIO(data)
def list_search(self, path_parts, page, query) :
print >> sys.stderr, '\n-\n-\n-\nDEBUG: list_search: query = %s\n-\n-\n-\n' % repr(query)
try :
uquery = query.decode('utf8')
except UnicodeDecodeError :
uquery = query.decode('gbk')
srch_words = self.server.ws.get_dict_words(uquery)
result = MindIndex.get_search_result(self.server.doc_profile, self.server.word_docset, self.server.word_idf, srch_words)
# TODO: search result cache
doc_num, page_num, page_idx, doc_list = result.get_page(page)
data = '<?xml version="1.0" encoding="GBK"?>'
data += '<entrylist>'
data += '<page><total>%d</total><pages>%d</pages><ipage>%d</ipage></page>' % (doc_num, page_num, page_idx)
for doc in doc_list :
data += '<file>'
data += '<rlt_path>%s</rlt_path>' % cgi.escape(doc.rlt_path())
data += '<path>%s</path>' % cgi.escape(doc.url_path())
data += '<create>%s</create>' % doc.ctime_str()
data += '<score>%f</score>' % doc.score
data += '</file>'
data += '</entrylist>'
self.send_response(200)
self.send_header('Content-type', 'text/xml')
self.send_header('Content-Length', str(len(data)))
self.end_headers()
return StringIO(data)
def __init__(self, server_address, RequestHandlerClass) :
ThreadingTCPServer.__init__(self, server_address, RequestHandlerClass)
self.server_name = 'MindWiki'
self.server_port = SERVER_PORT
self.page_head = open(os.path.join(MAIN_DIR, 'index_1.html'), 'r').read()
self.page_tail = open(os.path.join(MAIN_DIR, 'index_2.html'), 'r').read()
self.file_cache = {} # path -> (modify, head-content)
# Entry Index
self.dir2doclist = {}
MindIndex.build_entry_index(self.dir2doclist, DATA_DIR)
print "[%s] built entries' index." % time.strftime(TIME_FMT)
# WORD INDEX
self.ws = MindIndex.Word.WordSeg()
self.doc_profile = [] # profile item: (entry_tuple, ctime, mtime, words)
self.word_docset = {} # word->doc_id_set
self.word_idf = {}
#self.build_word_index()
t = threading.Thread(target=self.build_word_index, args=())
#t.setDaemon(True)
t.start()
