def send_segment(request):
'''
get segment
:param request:
:return:
'''
if request.method == "POST":
utils.update_db(request)
dbname = request.POST.get("db", "")
try:
info = dict()
info['seg'] = dict()
info['origin'] = dict()
info['source'] = dict()
# info['checked'] = [] # 已经查看过的index
filename = request.session.get(utils.SESSION_FILE, "")
if filename == "":
msg = request.POST.get("msg", "")
msg_list = seg_from_disk(msg)
else:
msg_list = seg_from_file(filename)
# 分词每次分MAX_TERM个，避免时间过长
data = msg_list[:utils.SEGS_PER_PAGE] if len(
msg_list) > utils.SEGS_PER_PAGE else msg_list
seg_list = update_segments(data, dbname)
terms = [] # 文本的分词
for i, origin in enumerate(msg_list):
info['origin'][i + 1] = origin #所有数据，用于计算总共多少页
i = 1
for seg_item in seg_list:
# info['origin'][i] = seg_item[0]
# 获取第一页的分词，显示来源
if i <= utils.SEGS_PER_PAGE:
info['seg'][i] = dict()
tmp = []
for j, seg in enumerate(seg_item[1]):
seg = seg.decode('utf8')
info['seg'][i][j + 1] = [s for s in seg]
tmp.append(seg)
terms.append(tmp)
i += 1
info['source'] = get_seg_source(
request.session.get(utils.SESSION_DB, ""), terms)
info["page_count"] = utils.SEGS_PER_PAGE
except Exception, e:
exc_type, exc_obj, exc_tb = sys.exc_info()
fname = os.path.split(exc_tb.tb_frame.f_code.co_filename)[1]
output = ",".join([str(e), fname, str(exc_tb.tb_lineno)])
error_logger.info(
request.session.get("username", "") + " - 分词服务错误 - " + output)
return HttpResponse(json.dumps(info), content_type='application/json')
def update_category(request):
utils.update_db(request)
dic = utils.update_nav_style({},
requests.session.get(utils.SESSION_DB, ""))
dic["username"] = request.session.get(utils.SESSION_USER, "")
return HttpResponse(json.dumps(dic), content_type='application/json')
def send_suggest(request):
'''
进入标注界面，获得分词，调用标注服务
:param request:
:return:
'''
if request.method == "POST":
try:
utils.update_db(request)
new_sugs = request.POST.get("new_segs", "")[:-1] # 去掉末尾的;
origin_msg = request.POST.get("origin", "") # 原文
if origin_msg:
origin_msg = origin_msg.split(",")
filename = request.session.get(utils.SESSION_FILE, "")
info = dict()
# 手动输入
if filename == "":
# 诊断的分词对应标注和来源
info['sug'], info['source'], info['msg'] = get_sug_from_disk(new_sugs,
request.session.get(utils.SESSION_DB, ""))
# 从文件读取
else:
edit_index = request.POST.get("edit_index", "") # 已编辑的index
# seg_index_list = edit_index.split(",")[:-1] # 保存过的诊断index,从0开始
# edit_count = get_sug_from_file(filename, seg_index_list) # 返回编辑的分词个数
edit_count = 0
utils.get_database(request.session.get(utils.SESSION_DB, "")).update_file_checked_seg(filename,
edit_count)
# 诊断的分词对应标注
info['sug'], info['source'], info['msg'] = sort_sugs_by_category(origin_msg,
"从文件 " + request.session.get(
utils.SESSION_ORIGIN_FILE, ""),
new_sugs,
request.session.get(utils.SESSION_USER,
""),
request.session.get(utils.SESSION_DB,
""))
# 所有的标注对应颜色
info['all'] = {}
all_sugs = utils.get_suggests_dic(request.session.get(utils.SESSION_DB, ""))
for k, v in all_sugs.iteritems():
info['all'][k] = v
info["page_count"] = utils.SUGS_PER_PAGE
except Exception, e:
exc_type, exc_obj, exc_tb = sys.exc_info()
fname = os.path.split(exc_tb.tb_frame.f_code.co_filename)[1]
output = ",".join([str(e), fname, str(exc_tb.tb_lineno)])
error_logger.info(request.session.get("username", "") + " - 标注服务错误 - " + output)
return HttpResponse(json.dumps(info), content_type='application/json')
def get_data(request):
'''
获得新增的标注数据
:param request:
:return:
'''
if request.method == "POST":
utils.update_db(request)
d = {}
d = refresh_datafile_sug(d, request.session.get(utils.SESSION_DB, ""))
return HttpResponse(json.dumps(d), content_type='application/json')
def update_suggests(request):
'''
在标注界面,切换术语集,更新标注和颜色
:param request:
:return:
'''
if request.method == "POST":
utils.update_db(request)
dic = get_all_suggest_color({}, request.session.get(utils.SESSION_DB, ""))
dic = utils.update_nav_style(dic, request.session.get(utils.SESSION_DB, ""))
return HttpResponse(json.dumps(dic), content_type='application/json')
def get_origin_data(request):
'''
获得所有数据库中已存的数据
:param request:
:return:
'''
if request.method == "POST":
utils.update_db(request)
data = init_origin_data({}, request.session.get(utils.SESSION_DB, ""))
# 这里按sug排序
request.session[utils.SESSION_ALLDATA] = build_sug_dict(data["items"])
config = json.load(open("config.json"))
data["page_count"] = config['basic']['ITEM_PER_PAGE_ORIGIN_DATA']
return HttpResponse(json.dumps(data), content_type='application/json')
def get_files(request):
'''
获得所有上传文件
:param request:
:return:
'''
if request.method == "POST":
utils.update_db(request)
files = utils.get_database(request.session.get(utils.SESSION_DB,
"")).get_files()
dic = get_file(files)
config = json.load(open("config.json"))
dic["page_count"] = config['basic']['ITEM_PER_PAGE_FILE']
return HttpResponse(json.dumps(dic), content_type='application/json')
def get_session(request):
'''
登录后，更新用户名session，获得用户权限
:param request:
:return:
'''
if request.method == "POST":
utils.update_db(request)
dic = {}
dic['username'] = request.session.get(utils.SESSION_USER, "")
dic['auth_log'] = log_authority(
request.session.get(utils.SESSION_USER, ""))
dic['auth_new_data'] = new_data_authority(
request.session.get(utils.SESSION_USER, ""))
dic['auth_origin_data'] = origin_data_authority(
request.session.get(utils.SESSION_USER, ""))
dic = utils.update_nav_style(dic,
request.session.get(utils.SESSION_DB, ""))
return HttpResponse(json.dumps(dic), content_type='application/json')
def get_log_info(request):
'''
获得所有日志数据
:param request:
:return:
'''
if request.method == "POST":
utils.update_db(request)
log_dic = {}
log_dic["denglu"] = get_login_loginfo()
log_dic["shuju"] = get_data_loginfo()
log_dic["biaozhu"] = get_sug_loginfo()
log_dic["wenjian"] = get_files_loginfo()
# log_dic["error"] = get_error_loginfo()
config = json.load(open("config.json"))
log_dic["page_count"] = config['basic']['ITEM_PER_PAGE_LOG']
return HttpResponse(json.dumps(log_dic),
content_type='application/json')
def get_all_suggests(request):
'''
所有标注传到标注编辑界面
:param request:
:return:
'''
utils.update_db(request)
sug_category = {}
sug_category["category"] = utils.get_database(request.session.get(utils.SESSION_DB, "")).get_categories()
count = {}
for s in sug_category["category"]:
count[s] = 0
sug_data = utils.get_database(request.session.get(utils.SESSION_DB, "")).get_suggests()
for line in sug_data:
try:
count[line["sug"]] += 1
except Exception, e:
print line["sug"]