logging when indexing

这个提交包含在:
voje 2019-04-28 23:24:40 +02:00
父节点 c5fc78dca1
当前提交 14a6e2423b

查看文件

@ -453,6 +453,9 @@ def prepare_app_index(appindex_json):
for corpus in CORPORA: for corpus in CORPORA:
res_hws = {} res_hws = {}
res_fns = {} res_fns = {}
nentries = valdb[corpus].count()
idx = 0
for e in valdb[corpus].find({}): for e in valdb[corpus].find({}):
if "headwords" not in e: if "headwords" not in e:
continue continue
@ -468,6 +471,10 @@ def prepare_app_index(appindex_json):
res_fns[fn] += 1 res_fns[fn] += 1
else: else:
res_fns[fn] = 1 res_fns[fn] = 1
idx += 1
if idx % 10000 == 0:
log.debug("indexing {}: {}/{}".format(
corpus, idx, nentries))
alphabetical = {} alphabetical = {}
for k, e in res_hws.items(): for k, e in res_hws.items():